sneak/pixa
1
0
Fork 0
Code Issues 20 Pull Requests 3 Actions Packages Projects Releases Wiki Activity

Compare commits

base: sneak/pixa:issue-310-schema-only-what-pixa-uses
Branches Tags
sneak/pixa:main sneak/pixa:issue-310-schema-only-what-pixa-uses sneak/pixa:next sneak/pixa:prod
sneak/pixa:v1.0.0-rc3 sneak/pixa:v1.0.0-rc2 sneak/pixa:v1.0.0-rc1
..
compare: sneak/pixa:0e345482bc3b2855f5050063e10b44daf03781a0
Branches Tags
sneak/pixa:issue-310-schema-only-what-pixa-uses sneak/pixa:next sneak/pixa:main sneak/pixa:prod
sneak/pixa:v1.0.0-rc3 sneak/pixa:v1.0.0-rc2 sneak/pixa:v1.0.0-rc1
1 Commits
issue-310-schema-only-what-pixa-uses .. 0e345482bc
Author SHA1 Message Date
clawbot 0e345482bc Install libvips JPEG XL support and require it at startup (part of #222)
check / check (push) Canceled after 0s
Details 
script/bootstrap --cgo installs vips-jxl when the package manager it
uses is apk, as Alpine's vips package lacks JPEG XL support; the nix
and brew libvips include it, as does apt's from Debian 12 and Ubuntu
24.04 on. The runtime stage of the Dockerfile installs vips-jxl too.

imgcache.NewService calls the new imageprocessor.CheckJPEGXLSupport
before it builds the image processor and fails with its error, which
names the fix, so pixad does not start without the support. JPEG XL
becomes the default output later in the issue. New tests check the
support and save an image as JPEG XL with govips and load it back.

Model: opus-5-5
 2026-10-08 03:32:19 +00:00
141 changed files with 5205 additions and 13332 deletions
Expand all files Collapse all files
.dockerignore
+9 -18
View File
@@ -13,21 +13,12 @@
# `/myapp`, never `**/myapp`, which also matches `cmd/myapp/` and
# deletes the package directory from the context.
# .git is sent without its config. Without a VERSION build argument the
# stage that compiles runs `git describe --tags --always` on .git, which
# does not need .git/config; that file can hold a credential, such as a
# Unlike the standard file, which leaves out all of .git, pixa sends
# .git without its config. Without a VERSION build argument the stage
# that compiles runs `git describe --tags --always` on .git, which does
# not need .git/config; that file can hold a credential, such as a
# password in a remote URL or the token the CI checkout step stores there.
# Each submodule keeps a config with the same exposure in its git directory
# under .git/modules/, nested again for a submodule's own submodules, or in
# its own .git directory when it keeps one.
# KNOWN GAP: a submodule whose name has a `config` segment (`config`,
# `deploy/config`, `config/lib`) loses its whole git directory, because
# `**/.git/modules/**/config` also matches that segment's directory
# under .git/modules/. Go's version stamping then fails the build;
# nothing leaks. Name such a submodule without that segment:
# `git submodule add --name`.
**/.git/config
**/.git/modules/**/config
.git/config
# Agent scratch: one full checkout of the repo per in-flight agent.
# Anchored because it occurs once where agents run at the repo root.
@@ -51,9 +42,7 @@
**/[iI][dD]_[rR][sS][aA]
**/[iI][dD]_[dD][sS][aA]
**/[iI][dD]_[eE][cC][dD][sS][aA]
**/[iI][dD]_[eE][cC][dD][sS][aA]_[sS][kK]
**/[iI][dD]_[eE][dD]25519
**/[iI][dD]_[eE][dD]25519_[sS][kK]
# Dependencies: restored inside the image, never copied in.
**/node_modules
@@ -71,8 +60,10 @@
**/.vscode
**/*.sublime-*
# pixa's own entries. On the host, `make build` writes bin/pixad, and the
# example config keeps its state directory in data/.
# pixa's own entries. Nothing in the build reads .gitignore. On the
# host, `make build` writes bin/pixad, and the example config keeps its
# state directory in data/.
.gitignore
/bin
/data
.editorconfig
-3
View File
@@ -13,6 +13,3 @@ indent_style = tab
[*.go]
indent_style = tab
# This repository's own sections, such as one for another language it
# uses, go below this comment, and a re-vendor keeps them.
.gitea/workflows/check.yml
+4 -9
View File
@@ -1,20 +1,15 @@
name: check
on: [push]
# Free the shared runner: a new push cancels only the same branch's older run.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
check:
runs-on: ubuntu-latest
# Free the shared runner from a hung build.
timeout-minutes: 20
steps:
# actions/checkout v4.2.2, 2026-02-22
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
# script/cibuild needs no token, so none is left in .git/config.
# The default clone is shallow and has no tags, so the
# version the build takes from `git describe` would be a
# bare commit; this fetches the whole history with its tags.
with:
persist-credentials: false
# All history and tags, so git describe finds the version tag.
fetch-depth: 0
- run: script/cibuild
- run: script/docker-smoke
.gitignore
+6 -37
View File
@@ -17,46 +17,15 @@ Thumbs.db
# entry and must not be given a `**/` prefix on the way into one.
.claude/
# Node
node_modules/
# Secrets. Unanchored like every entry above, so each matches at every
# depth. Matching is case-sensitive on Linux, so names use character
# ranges rather than a lowercase form that misses `Server.Key`.
# Environment files. `*.env` covers bare `.env` and the `prod.env`
# convention. Only the templates `example.env` and `sample.env` are
# re-included below. A repository that commits any other template adds
# its own negation at the end of this file, for example `!.env.example`.
*.[eE][nN][vV]
.[eE][nN][vV].*
.[eE][nN][vV][rR][cC]
!example.env
!sample.env
# Private keys and the bundles carrying them.
*.[pP][eE][mM]
*.[kK][eE][yY]
*.[pP]12
*.[pP][fF][xX]
[iI][dD]_[rR][sS][aA]
[iI][dD]_[dD][sS][aA]
[iI][dD]_[eE][cC][dD][sS][aA]
[iI][dD]_[eE][cC][dD][sS][aA]_[sS][kK]
[iI][dD]_[eE][dD]25519
[iI][dD]_[eE][dD]25519_[sS][kK]
# This repository's own entries, such as its build outputs, go below
# this comment, and a re-vendor keeps them. Anchor a binary built at the
# root: `/myapp`, never `myapp`, which also ignores `cmd/myapp/`.
# Go
*.log
*.out
*.test
# Environment / secrets
.env
.env.*
*.pem
*.key
# Dependencies
vendor/
node_modules/
# Build output
/bin/
.golangci.yml
-3
View File
@@ -17,7 +17,6 @@ linters:
disable:
# Genuinely incompatible with project patterns
- exhaustruct # Requires all struct fields
- exhaustruct_v5 # Requires all struct fields (successor to exhaustruct)
- godot # Requires comments to end with periods
- wrapcheck # Too verbose for internal packages
- varnamelen # Short names like db, id are idiomatic Go
@@ -25,8 +24,6 @@ linters:
# silenced by disabling that name, not by enabling the successor.
- wsl # Deprecated, replaced by wsl_v5
- gomodguard # Deprecated, replaced by gomodguard_v2
# Misses findings at random in v2.14.0; back once a pinned release fixes it
- canonicalheader
settings:
lll:
line-length: 88
.prettierignore
+5
View File
@@ -1,2 +1,7 @@
node_modules/
yarn.lock
# A byte-for-byte copy of the one in sneak/prompts.
REPO_POLICIES.md
vendor/
AGENTS.md → CLAUDE.md
+1 -5
View File
@@ -14,11 +14,7 @@ These rules MUST be followed at all times, it is very important.
without asking first. In almost all cases, the code should be changed, NOT the
tests. If you think the test needs to be changed, make your case for that and
ask for permission to proceed, then stop. You need explicit user approval to
modify existing tests. A bug fix may change an existing test without asking
when that test pins exactly the behavior the filed bug calls wrong, and the
change moves it to the fixed behavior and nothing else; any other change to an
existing test still needs explicit user approval. (You do not need user
approval for writing NEW tests.)
modify existing tests. (You do not need user approval for writing NEW tests.)
- When linting, assume the linter config is CORRECT, and that each item output
by the linter is something that legitimately needs fixing in the code.
Dockerfile
+44 -76
View File
@@ -1,16 +1,7 @@
# In every stage ARG CACHEBUST comes right after the steps that install
# system packages and download Go's modules, or right after FROM in a
# stage with neither, and every step that lints, tests or compiles
# comes after it. script/ passes a new value on every build, which
# reruns every RUN step after it. Docker keeps the layers above it
# until the base image, their own lines or go.mod and go.sum change.
# The steps that compile mount Go's build cache, and golangci-lint run
# also mounts golangci-lint's; both survive from build to build.
# Lint phase. script/lint builds it alone. The linter is run directly:
# `make lint` and script/lint are themselves a docker build.
# golangci/golangci-lint:v2.14.0, 2026-10-15
FROM golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
# golangci/golangci-lint:v2.12.2, 2026-10-04
FROM golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240 AS lint
# The linter compiles every package, and govips needs the libvips
# headers for that. REPO_POLICIES.md has the lint phase install them
@@ -22,95 +13,73 @@ RUN apt-get update \
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
ARG CACHEBUST
COPY . .
RUN --mount=type=cache,target=/root/.cache/go-build \
--mount=type=cache,target=/root/.cache/golangci-lint \
golangci-lint run --config .golangci.yml ./...
RUN golangci-lint run --config .golangci.yml ./...
# Test phase. script/test builds it alone. -race needs cgo and so a C
# compiler, which the Debian Go image ships and the alpine one does not.
# golang:1.25.4-trixie, 2026-10-15
FROM golang@sha256:a02d35efc036053fdf0da8c15919276bf777a80cbfda6a35c5e9f087e652adfc AS test
# govips compiles against the libvips and libheif headers, and the tests
# need libvips' JPEG XL support; libvips-dev brings all three. The tests
# also encode AVIF, which needs libheif's AVIF encoder,
# libheif-plugin-aomenc: Debian only recommends it, so it is named here.
RUN apt-get update \
&& apt-get install -y --no-install-recommends libvips-dev libheif-plugin-aomenc \
&& rm -rf /var/lib/apt/lists/*
# Test phase. script/test builds it alone.
# golang:1.25.4-alpine, 2026-02-25
FROM golang:1.25.4-alpine@sha256:d3f0cf7723f3429e3f9ed846243970b20a2de7bae6a5b66fc5914e228d831bbb AS test
WORKDIR /src
# script/bootstrap --cgo installs the build dependencies (a C compiler,
# the libvips and libheif headers, and libvips' JPEG XL support, which
# the tests need) and downloads the Go modules.
COPY script/ ./script/
COPY go.mod go.sum ./
RUN go mod download
ARG CACHEBUST
RUN script/bootstrap --cgo
COPY . .
# Without -v first; on a failure, again with -v for the details, and
# the step fails even if the second run passes. -count=1 because the
# mounted cache also holds test results, which go test would otherwise
# replay. -parallel 4: by default a package runs as many of its tests at
# once as the host has CPUs, and on a busy host they then wait so long
# to be scheduled that a test that times a request can see it return a
# second late.
RUN --mount=type=cache,target=/root/.cache/go-build \
go test -count=1 -timeout 90s -race -parallel 4 -cover ./... || \
# the step fails even if the second run passes.
RUN go test -count=1 -timeout 90s -race -cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \
go test -count=1 -timeout 90s -race -parallel 4 -v ./...; exit 1; }
go test -count=1 -timeout 90s -race -v ./...; exit 1; }
# Build stage. Nothing is wanted from the two phases above: these copies
# make BuildKit build them first, so nothing after them runs unless lint
# and test passed.
# golang:1.25.4-alpine3.22, 2026-02-25; the runtime stage uses Alpine 3.22 too
FROM golang:1.25.4-alpine3.22@sha256:d3f0cf7723f3429e3f9ed846243970b20a2de7bae6a5b66fc5914e228d831bbb AS builder
# git for the version, and for govips a C compiler, pkg-config and the
# libvips and libheif headers
RUN apk add --no-cache git build-base pkgconfig vips-dev libheif-dev
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
ARG CACHEBUST
# make BuildKit build them first, so this stage runs only when lint and
# test passed.
# golang:1.25.4-alpine, 2026-02-25
FROM golang:1.25.4-alpine@sha256:d3f0cf7723f3429e3f9ed846243970b20a2de7bae6a5b66fc5914e228d831bbb AS builder
COPY --from=lint /src/go.sum /dev/null
COPY --from=test /src/go.sum /dev/null
# A tar-stream context keeps the sender's file owners, which git refuses.
RUN git config --system --add safe.directory /src
WORKDIR /src
# Build dependencies and Go modules, as in the test phase
COPY script/ ./script/
COPY go.mod go.sum ./
RUN script/bootstrap --cgo
# Copy source code
COPY . .
# The VERSION build arg when one is given, otherwise
# `git describe --tags --always` on the .git in the build context: the
# tag on a tagged commit, tag-N-gHASH after one, the short commit when
# no tag is reachable. With .git present, a version that is still empty,
# dev or unknown fails the build: git is missing or could not read the
# checkout. A context without .git, as from a source tarball, stamps an
# empty version. CGO stays enabled for govips; -trimpath keeps build
# paths out of the binary, and -s -w leave out the symbol table and
# debug information.
# VERSION is declared here, not earlier: a new value reruns only the
# build, not script/bootstrap. Given none, the version is
# `git describe --tags --always` of the .git in the build context (git
# comes from script/bootstrap): the tag on a tagged commit, tag-N-gHASH
# after one, the short commit when no tag is reachable. A context that
# carries .git and still yields no version fails the build; one without
# .git, as from a source tarball, stamps an empty version. CGO stays
# enabled for govips; -trimpath keeps build paths out of the binary, and
# -s -w leave out the symbol table and debug information.
ARG VERSION
RUN --mount=type=cache,target=/root/.cache/go-build \
VERSION="${VERSION:-$(git describe --tags --always)}"; \
if [ -e .git ]; then \
case "$VERSION" in ""|dev|unknown) \
echo "version is '$VERSION' although .git is present" >&2; \
exit 1 ;; \
esac; \
RUN version="${VERSION:-$(git describe --tags --always)}"; \
if [ -e .git ] && { [ -z "$version" ] || [ "$version" = dev ] || \
[ "$version" = unknown ]; }; then \
echo "the build context carries .git but yields no version" >&2; \
exit 1; \
fi; \
CGO_ENABLED=1 GOTOOLCHAIN=auto go build -trimpath \
-ldflags="-s -w -X main.Version=${VERSION}" \
-ldflags "-s -w -X main.Version=${version}" \
-o /pixad ./cmd/pixad
# Runtime stage, and the last one: a plain `docker build .` builds this
# stage and what it depends on, and nothing else. It must use the Alpine
# release the golang image above is based on, so that pixad runs against
# the libvips and musl it was built with.
# alpine:3.22, 2026-10-08
FROM alpine:3.22@sha256:5291449c3df73caf6ed85e649dec1b9e818b39a5d8c871e97afc13e9cd5e8fa8
# stage and what it depends on, and nothing else.
# alpine:3.21, 2026-02-25
FROM alpine:3.21@sha256:c3f8e73fdb79deaebaa2037150150191b9dcbfba68b4a46d70103204c53f4709
# Install runtime dependencies only. vips-jxl is libvips' JPEG XL
# support, without which pixad does not start.
@@ -121,7 +90,6 @@ RUN apk add --no-cache \
ca-certificates \
tzdata \
su-exec
ARG CACHEBUST
# Copy binary from builder
COPY --from=builder /pixad /usr/local/bin/pixad
Makefile
+1 -7
View File
@@ -1,4 +1,4 @@
.PHONY: bootstrap setup check lint test fmt fmt-check build clean docker docker-smoke docker-versioned docker-test devserver devserver-stop hooks loadtest bench
.PHONY: bootstrap setup check lint test fmt fmt-check build clean docker docker-smoke docker-versioned docker-test devserver devserver-stop hooks loadtest
VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
LDFLAGS := -X main.Version=$(VERSION)
@@ -64,12 +64,6 @@ docker-smoke:
loadtest:
@script/loadtest
# Serve cache hits in parallel through the image handler and report hits per
# second (needs Go on the host after `script/bootstrap --cgo`, not Docker; a
# benchmark, not part of check)
bench:
@script/bench
# Build Docker image as `make docker` does, and also tag it pixa:$(VERSION)
docker-versioned:
@script/docker
README.md
+114 -386
View File
@@ -26,11 +26,6 @@ make docker
docker run -p 8080:8080 -e PIXA_SIGNING_KEY="$(openssl rand -base64 32)" pixa:latest
```
The example config allowlists no host (`allowlist_hosts`), so pixa serves an
image only for a signed or encrypted URL. Every image on an allowlisted host is
served to anyone without a signature, at any size and in any format, so
allowlist only hosts you control, where nobody else can put images.
A container takes its settings from environment variables (see Configuration
below for the list). Only `PIXA_SIGNING_KEY` is required; if it is unset the
container exits at startup naming the variable. Everything else has a built-in
@@ -51,9 +46,9 @@ everything in this list without further settings. The reverse proxy must:
builds encrypted URLs from `Host`, and checks `Referer` against
`referer_blocklist`;
- set `X-Forwarded-For` to the client's address, with `trusted_proxies` set to
the address pixa sees the proxy's requests come from, so the login limit and
`image_requests_per_minute` count each client by its own address (see
`trusted_proxies` under Configuration);
the address pixa sees the proxy's requests come from, so the login limit
counts each client by its own address (see `trusted_proxies` under
Configuration);
- wait for pixa's answer for at least `downstream_timeout` (default `60s`), the
longest pixa takes to fetch, convert and send an image.
@@ -63,20 +58,19 @@ password there.
pixa does the rest itself: it checks signatures and encrypted URLs, applies the
allowlist, refuses upstream hosts with private or local addresses, limits login
attempts, each client's image requests, upstream response size and image
dimensions, and sends the security headers, `Strict-Transport-Security`
included, with every response.
attempts, upstream response size and image dimensions, and sends the security
headers, `Strict-Transport-Security` included, with every response.
The state directory (`state_dir`, `/var/lib/pixa` in the container) holds the
database and the disk cache:
- It needs a persistent volume: without one, every restart starts with an empty
cache. Losing the directory also ends every login session (see Encrypted
URLs). In the container, the startup script gives the directory to the user
cache. In the container, the startup script gives the directory to the user
pixa runs as (uid 65532) and sets its mode to `750`; outside it, that user
must be able to write the directory.
- `cache_max_bytes` limits the source and transformed images together. The
database and files still being written come on top, and eviction runs in the
database, the metadata files, the `.meta` file beside each transformed image
and files still being written come on top, and eviction runs in the
background, so the cache can pass the limit for a while: leave room on the
volume beyond it.
- Set `cache_max_bytes` for a lasting deployment. Its default, worked out each
@@ -89,21 +83,18 @@ which answers 200 whenever pixa is running, in maintenance mode too (see
`maintenance_mode`).
On SIGTERM or SIGINT pixa stops accepting connections, gives the requests in
progress and the images being processed 5 seconds to finish, then writes to the
database the counts of cache hits, misses, fetches and conversions and the times
cached images were last used that are not written yet (see Storage), and exits:
with 0, or with 1 when images were still being processed after those 5 seconds,
some of those counts or times could not be written, or another part of pixa
failed to stop. A request not finished by then is cut off. `docker stop` waits
10 seconds before it kills the container.
progress and the images being processed 5 seconds to finish, and exits: with 0,
or with 1 when images were still being processed after those 5 seconds or
another part of pixa failed to stop. A request not finished by then is cut off.
`docker stop` waits 10 seconds before it kills the container.
Outside Docker, pixa needs libvips (the image has 8.16) and libheif to run, as
Outside Docker, pixa needs libvips (the image has 8.15) and libheif to run, as
it uses libvips through CGO. pixad does not start unless libvips has its JPEG XL
support, which on Alpine is the `vips-jxl` package and which the nix and brew
packages of libvips include, as do the apt ones from Debian 12 and Ubuntu 24.04
on. Building pixa also needs the development files of libvips and libheif,
`pkg-config` and a C compiler. `script/bootstrap --cgo` installs all of these;
the `Dockerfile` installs its own packages. Plain `script/bootstrap`, which
`pkg-config` and a C compiler. `script/bootstrap --cgo` installs all of these,
as the `Dockerfile` does where it compiles pixa. Plain `script/bootstrap`, which
`script/setup` and `script/cibuild` run, installs git, make and Go, and Node,
Yarn and the prettier pinned in `yarn.lock` for formatting the markdown, but
none of the C libraries: the checks compile pixa in Docker. Docker itself must
@@ -121,44 +112,10 @@ What the [upaas](https://git.eeqj.de/sneak/upaas) app for pixa needs:
- `PIXA_SIGNING_KEY` (required): secret for signed and encrypted URLs and
login, 32+ characters, for example from `openssl rand -base64 32`
- `PIXA_ALLOWLIST_HOSTS`: upstream hosts served without a signature,
comma-separated; default none. Every image on a listed host is served to
anyone without a signature, so list only hosts you control, where nobody
else can put images.
- `PIXA_CACHE_MAX_BYTES`: disk cache limit in bytes; `0` disables it. Set
it: the volume is a directory on the host's filesystem, shared with the
host and every other app. The default is 75% of the sum of that
filesystem's free space and what the cache holds, and at least 500 MiB, so
the cache can grow to three quarters or more of the space they all have
left, and to all of it when that is 500 MiB or less.
comma-separated
- `PIXA_CACHE_MAX_BYTES`: disk cache limit in bytes; `0` disables it;
default 75% of (free space + what the cache holds)
- the rest are in the table under Configuration below
- **Memory:** pixa can use up to `max_concurrent_processing` times 4.2 GiB for
the images it processes at once, plus `upstream_connections` times
`upstream_max_response_size` for the source images it has fetched that wait
for processing. 4.2 GiB is the most resident memory was measured to grow while
pixa, with pixad's libvips settings, processed one 8192x8192 source, the
largest it accepts, saving it at full size to each output format in turn, one
at a time. The sources were a JPEG, a GIF, a WebP, an 8-bit and a 16-bit PNG,
an 8-bit and a 12-bit AVIF, and an 8-bit, a 16-bit and a 32-bit floating-point
JPEG XL; memory grew most for the 16-bit JPEG XL, of random pixels, saved as
WebP. At the defaults that is half the CPUs pixa sees times 4.2 GiB, plus 64
times 50 MiB: on a host where pixa sees 48 CPUs, 24 times 4.2 GiB plus 3.1
GiB, about 104 GiB. Set `PIXA_MAX_CONCURRENT_PROCESSING` and
`PIXA_UPSTREAM_CONNECTIONS` so that this fits the memory the container may
use.
- **Temporary files:** while pixa processes a large source, libvips writes its
decoded pixels to a file in `/tmp`. The file disappears from `/tmp` once it is
written, so a listing of `/tmp` does not show it, but it keeps its space, on
disk or, where `/tmp` is a tmpfs, in memory, until the image is done. For a
GIF, WebP, AVIF or JPEG XL source the decoded pixels are held in memory as
well as written to that file, and the 4.2 GiB above includes that memory. For
an 8192x8192 source the file was measured on pixad at 192 MiB for an 8-bit RGB
JPEG, 512 MiB for a 16-bit RGBA PNG or JPEG XL, and 1 GiB for a JPEG XL of
32-bit floating-point RGBA, the largest measured: up to 1 GiB per image
processed at once, 24 GiB at the defaults on a host where pixa sees 48 CPUs.
This `/tmp` is in the container's own filesystem, not on the volume at
`/var/lib/pixa`, and `cache_max_bytes` does not count it. The 4.2 GiB above
does not include these files; where `/tmp` is a tmpfs, they are memory on top
of it.
- **Health check:** the image's `HEALTHCHECK` requests
`/.well-known/healthcheck.json`. upaas reads the container's health 60 seconds
after a deploy and marks the deploy failed unless it is `healthy`. The probe
@@ -177,46 +134,26 @@ allowlisted source hosts for open access.
### Storage
- **Source images**:
`<state_dir>/cache/sources/<ab>/<cd>/<sha256 of host, path and query>`, one
file for each source URL
- **Source content**:
`<state_dir>/cache/sources/<ab>/<cd>/<sha256 of source content>`
- **Source metadata**:
`<state_dir>/cache/metadata/<hostname>/<sha256 of path and query>.json` (host,
path and query, content hash, upstream status and headers, fetch time)
- **Database**: `<state_dir>/state.sqlite3` (SQLite)
- **Transformed images**:
`<state_dir>/cache/variants/<ab>/<cd>/<sha256 of host, path, query, size, format, quality and fit>`
`<state_dir>/cache/variants/<ab>/<cd>/<sha256 of host, path, query, size, format, quality and fit>`,
each with a `.meta` file beside it holding its content type
`<ab>` and `<cd>` are the first and second pairs of characters of the file's
name.
Each source image and each transformed image has one row in the database,
holding its size and when it was last used. Two source URLs that serve the same
bytes are stored twice, once under each URL. A source image is stored by writing
its file and then its row; when the row cannot be written, the file is removed
again.
Source and transformed image files are written under a temporary name, synced to
disk, and only then renamed into place, so a crash leaves no file under its own
name with part of its data. When pixa starts, and every five minutes after, it
removes each cached source or transformed image whose file is empty, or not the
size the database records for it, with a warning naming the file; the next
request for it fetches the source or converts the image again. Looking for those
files reads the database once for every cached file, so pixa skips each
five-minute look that would start less than ten times as long after the last
look ended as that look took. After a look that took one minute, the next one
starts 10 to 15 minutes after that look ended.
Multiple source paths may reference the same content blob; the database tracks
references rather than using filesystem refcounting.
pixa's target is 1-5k r/s, which has not been measured at that rate (see Load
Test). Toward it, a cache hit opens the transformed image's file and nothing
else, and makes no database call. The content type comes from the file's first
bytes, which are those of the format pixa wrote it in; a file whose first bytes
are not those of a format pixa writes is not served, and the image is converted
again. The time the image was last served, which eviction orders by, and the hit
count are handed to a background writer without waiting for it, as are the
counts of misses, fetches and conversions, and the time a miss last used a
cached source image. Once a second that writer writes the waiting times in one
transaction and the counts in one statement. While 10,000 times of transformed
images, or 10,000 of source images, wait to be written, a further one is
dropped, and that image only looks less recently used to eviction.
`script/bench` measures how many hits pixa serves per second (see Load Test).
Test). Toward it, pixa keeps in memory the content types of the 10,000
transformed images most recently cached or served, so a cache hit on one of them
reads only the image file from disk and not the metadata file stored beside it.
### Routes
@@ -237,32 +174,21 @@ path under `/v1/` answers 200, in maintenance mode too.
session it answers 303 to `/`. Answers: 200 with the page showing the URL; 400
with the page naming a field that is not valid; 500 when the URL cannot be
made.
- `POST /logout` — log out with the generator page's Logout button: end every
login session, in every browser (see Encrypted URLs), and remove the session
cookie. Needs: a login session and the generator page's form (below); without
a login session it only removes the cookie. Answers: 303 to `/`; 500 when the
logout cannot be saved in the database.
- `GET` or `HEAD` `/v1/image/<host>/<path>/<size>.<format>`, or
`/v1/image/<host>/<path>/<size>` with no format — an image, fetched, resized
and converted (below). Needs: a signature, unless the host is allowlisted (see
Source Hosts). Answers: 200; 304 when `If-None-Match` matches the image's
`ETag`; 400 for a URL or parameter that is not valid, or for the format `auto`
an `Accept` header that is not valid; 406 for the format `auto` when `Accept`
allows none of the formats it chooses from; 401 for a missing or wrong
signature, a missing `exp` or an `exp` in the past; 403 when the request's
`Referer` names a host in `referer_blocklist`, checked before the signature,
the cache and the upstream fetch; 403 when the upstream host, or a host it
redirects to, is `localhost`, ends in `.localhost` or `.local`, or has an
address in a blocked network (see `blocked_networks`); 429 over
`image_requests_per_minute` (below); 415 when the upstream answers with a
`Content-Type` that is not one of the source formats (below), with a body
whose first bytes are not those of the format its `Content-Type` names, or
with an image whose first bytes libvips reads as another format; 502 when the
upstream answered with an error status, and for 5 minutes after that, or after
a body whose first bytes are not those of its `Content-Type`, for an image of
the same source URL that pixa can neither serve from its cache nor make from
the source image still in its cache; 503 when pixa is busy or in maintenance
mode; 500 for any other failure.
- `GET /logout` — end the login session. Needs: nothing. Answers: 303 to `/`.
- `GET` or `HEAD` `/v1/image/<host>/<path>/<size>.<format>` — an image, fetched,
resized and converted (below). Needs: a signature, unless the host is
allowlisted (see Source Hosts). Answers: 200; 304 when `If-None-Match` matches
the image's `ETag`; 400 for a URL or parameter that is not valid, or for the
format `auto` an `Accept` header that is not valid; 406 for the format `auto`
when `Accept` allows none of the formats it chooses from; 401 for a missing or
wrong signature, a missing `exp` or an `exp` in the past; 403 when the
request's `Referer` names a host in `referer_blocklist`, checked before the
signature, the cache and the upstream fetch; 403 when the upstream host, or a
host it redirects to, is `localhost`, ends in `.localhost` or `.local`, or has
an address in a blocked network (see `blocked_networks`); 502 when the
upstream answered with an error status, and for 5 minutes after that for the
same source URL; 503 when pixa is busy or in maintenance mode; 500 for any
other failure.
- `GET` or `HEAD` `/v1/e/<token>/<name>` — an image through an encrypted URL
(see Encrypted URLs). Needs: nothing but the URL. Answers: 200; 304 when
`If-None-Match` matches the image's `ETag`; 400 for a token that does not
@@ -270,7 +196,7 @@ path under `/v1/` answers 200, in maintenance mode too.
expired; 504 when the upstream has not sent its response headers within
`upstream_fetch_timeout`, but 500 when that time runs out while the image
itself is still arriving; 400 for an `Accept` header that is not valid, and
406, 403, 415, 429, 502, 503 and 500, as for `/v1/image/`.
406, 403, 502, 503 and 500, as for `/v1/image/`.
- `GET /robots.txt` — asks every crawler to stay away (`Disallow: /`). Needs:
nothing. Answers: 200.
- `GET /.well-known/healthcheck.json` — JSON with `status` (`ok`), `now`,
@@ -291,7 +217,7 @@ the request carries the same ID as `request_id`, and so do the lines it logs
when it fetches, converts and serves an image; the fetch sends it to the
upstream host as `X-Request-ID`.
The `POST` routes accept only a form that pixa's own page served: the page puts
Both `POST` routes accept only a form that pixa's own page served: the page puts
a token in the form and sets a cookie to match, and a request without both is
refused with 403, so another site cannot submit the form from a visitor's
browser. The login and generator pages are meant to be opened over HTTPS: while
@@ -305,11 +231,10 @@ proxy in front of pixa must pass that header on unchanged. A form body over 1
MiB is refused with 413. The image routes answer the errors listed for them with
JSON holding `error`, `status` and `timestamp`.
An image URL has one of these forms, the second with no format:
An image URL has this form:
```
/v1/image/<host>/<path>/<size>.<format>?sig=<signature>&exp=<expiration>&q=<quality>&fit=<fit>
/v1/image/<host>/<path>/<size>?sig=<signature>&exp=<expiration>&q=<quality>&fit=<fit>
```
Images are only fetched from origins using TLS with valid certificates, unless
@@ -320,9 +245,7 @@ A request whose query string cannot be decoded, or gives any parameter more than
once, is refused with 400.
- `<format>`: one of `orig` (or `original`), `jpeg` (or `jpg`), `png`, `webp`,
`avif`, `jxl` (JPEG XL), `gif`, or `auto` (below). A URL with no format (the
second form, with no dot after the size) is served as JPEG XL, the default, as
with `jxl`
`avif`, `gif`, or `auto` (below)
- `<size>`: `orig` or `<width>x<height>` (e.g. `800x600`)
- `sig` and `exp`: the signature and its expiry, needed unless the host is
allowlisted (see Signature Specification)
@@ -330,77 +253,23 @@ once, is refused with 400.
both optional (values under Signature Specification). Both are part of what is
cached, so each value of either is a separate cached image.
A source URL's query follows its path after `%3F`, the encoded `?`:
`/v1/image/<host>/<path>%3F<query>/<size>.<format>`. pixa decodes the
percent-escapes in the image URL's path once, then reads the host up to the
first `/`, the size and format after the last `/`, and between them the source
path up to the first `?` and the source query after it. So the `?` before the
query, any `?` in the query, and every `%` in the source path or query must be
percent-encoded, as `%3F` and `%25`. Any other character may be written as
itself or percent-encoded: `/`, `;`, `,`, `=` and `&` work either way. Neither
the source path nor the source query may hold a `#`, and an image URL that
writes one as `%23` is refused with 400. For example,
`https://cdn.example.com/img?url=https://origin.example.com/my%20cat.jpg` at
800x600 WebP is
`/v1/image/cdn.example.com/img%3Furl=https://origin.example.com/my%2520cat.jpg/800x600.webp`,
signed as shown under Signature Specification.
The source path is the path with its percent-escapes decoded, and pixa fetches
it percent-encoded again: every character other than letters, digits, `-`, `.`,
`_`, `~`, `/`, `$`, `&`, `+`, `,`, `:`, `;`, `=` and `@` is sent as a
percent-escape. So `my%20cat.jpg` in the image URL is the source path
`/my cat.jpg`, fetched as `/my%20cat.jpg`; `my%2520cat.jpg` is the source path
`/my%20cat.jpg`, fetched as `/my%2520cat.jpg`; and `100%25.png` is fetched as
`/100%25.png`. The source query is the source URL's query as that URL writes it,
its percent-escapes included, and is sent as it is, except that the characters a
browser percent-encodes in a query (a space, `"`, `'`, `<`, `>`, control
characters and characters outside ASCII) and a `%` that does not begin a
percent-escape are percent-encoded. pixa signs and caches the query in that
form, so `img%3Fname=my%20cat` and `img%3Fname=my%2520cat` in the image URL are
the same source query, `name=my%20cat`.
A size with one side `0` has that side scaled to keep the source's proportions,
and is refused with 400 when that side would come out above 8192, the most
either side may be; so is a size with `fit=outside`, which scales the image to
cover the size and so past it on one side, when that side would come out
above 8192.
An AVIF image of more than 16,777,216 pixels, the number 4096x4096 and 8192x2048
have, is refused with 400 before anything is decoded, as its encode could take
more than 40 seconds (see below). That includes `orig` of an AVIF source, and
`auto` when it chooses AVIF, so a client whose `Accept` names `image/avif` but
not `image/jxl` is refused such a size.
The source image may be JPEG, PNG, GIF, WebP, AVIF or JPEG XL. The upstream's
`Content-Type` must name its format, and the image's first bytes must match it.
An upstream answering with any other `Content-Type`, SVG included, is refused
with 415. So is a body whose first bytes are not those of the format its
`Content-Type` names, such as a JPEG sent as `image/png`, text sent as an image,
or an empty body. pixa then does not fetch that source URL again for 5 minutes,
as after an upstream error status, and meanwhile answers 502 for an image that
would need that fetch. An image whose first bytes libvips reads as another
format, such as an SVG whose first bytes pass the check for AVIF, is refused
with 415 too.
With the format `auto`, pixa chooses the format for each request from its
`Accept` header, in this order:
1. JPEG XL, when the header names `image/jxl`;
2. AVIF, when it names `image/avif`;
3. WebP, when it names `image/webp`;
4. JPEG, when the first of `image/jpeg`, `image/*` and `*/*` that it names
1. AVIF, when the header names `image/avif`;
2. WebP, when it names `image/webp`;
3. JPEG, when the first of `image/jpeg`, `image/*` and `*/*` that it names
allows it, or when there is no `Accept` header or it is empty.
An entry with `q=0` refuses its format; other `q` values do not change the
order. JPEG XL, AVIF and WebP must be named, as clients that cannot show them
also send `image/*` and `*/*`. pixa never sends a format the client refused:
when the header allows none of the four, the answer is 406, and a header that
does not parse, or has a `q` that is not a number from 0 to 1, is refused
with 400. The signature, or the token of an encrypted URL, covers `auto` itself,
so one URL serves every client. Each format chosen is cached as a separate
image, and every answer that depends on `Accept` (the image, a 304, and the 400
and 406 above) carries `Vary: Accept`, so a shared cache keeps the formats apart
too.
order. AVIF and WebP must be named, as clients that cannot show them also send
`image/*` and `*/*`. pixa never sends a format the client refused: when the
header allows none of the three, the answer is 406, and a header that does not
parse, or has a `q` that is not a number from 0 to 1, is refused with 400. The
signature, or the token of an encrypted URL, covers `auto` itself, so one URL
serves every client. Each format chosen is cached as a separate image, and every
answer that depends on `Accept` (the image, a 304, and the 400 and 406 above)
carries `Vary: Accept`, so a shared cache keeps the formats apart too.
An image is served with `Cache-Control: public, max-age=<seconds>, immutable`.
When the URL has an expiry (an `exp`, or the TTL of an encrypted URL), `max-age`
@@ -413,30 +282,9 @@ cache at once, they share one upstream fetch (or one read of the cached source)
and one transcode: the first request does the work, and the others wait for its
image or its error, holding no upstream connection or processing slot of their
own. A waiting request stops waiting when its own client goes away. The work
goes on for the others even if the first request's client goes away. The shared
fetch sends the first request's ID upstream, and the lines logged for the fetch
and the transcode carry that ID.
A transcode whose request's `downstream_timeout` has ended (for a shared one,
the first request's) stops waiting for a processing slot, or, once it has one,
gives it back without beginning to encode. A request waiting for a shared
transcode that stops this way is answered 503 with the error
`server busy, try again later`, though its own `downstream_timeout` may not have
ended. govips gives pixa no way to stop libvips once an encode has begun, so an
encode keeps its slot until it finishes, which can be after
`downstream_timeout`. The limit of 8192 on each side of the source and of the
output, and for AVIF the limit of 16,777,216 pixels, bound how long that takes.
With one libvips thread, as pixad runs it, encoding 8192x8192 random pixels
takes up to about 1 second as JPEG, 15 as PNG and 16 as GIF, the slowest of 8 or
16 bits per sample, with or without an alpha channel. The WebP and JPEG XL
encoders run below libvips' default effort, and AVIF at the lowest effort govips
can set, so that no encode takes more than 40 seconds of the default
`downstream_timeout` of 60: at any quality and 8 or 16 bits per sample,
8192x8192 random pixels with an alpha channel take up to about 23 seconds as
WebP and 27 as JPEG XL, and 4096x4096, 8192x2048 or 2048x8192 up to about 34 as
AVIF, which at quality 85 would take about 96 at 8192x8192. Without an alpha
channel they take up to about 16, 13 and 22 seconds. Decoding such a source adds
up to about 11 seconds.
goes on for the others even if the first request's client goes away, until that
request's `downstream_timeout` ends. The shared fetch sends the first request's
ID upstream, and the lines logged for the fetch and the transcode carry that ID.
The login form (`POST /`) is limited to 5 attempts per minute per client
address, counting an IPv6 client by its /64; an attempt over the limit is
@@ -455,15 +303,6 @@ its own `X-Forwarded-For`, whether it connects directly or through the proxy,
because its own address is trusted too. Setting `trusted_proxies` to only the
address pixa sees for requests that come through the proxy closes this.
One client may send `image_requests_per_minute` requests per minute
(default 600) to the image routes, `/v1/image/` and `/v1/e/` together, `GET` and
`HEAD`, cache hits included; a request over the limit is refused with 429 and a
`Retry-After` header. Clients are counted as for the login limit. A browser's
CORS preflight is not counted. Behind a CDN or proxy whose addresses are not in
`trusted_proxies`, all requests arriving from one proxy or CDN address count as
one client, so such a deployment needs a higher limit, or `0`, which turns the
limit off.
### Encrypted URLs
An encrypted URL is an image URL made on pixa's own web page by someone who
@@ -473,40 +312,21 @@ nor change what it asks for.
1. Open `/` in a browser over HTTPS (or over plain HTTP while `debug` is on, see
Routes) and log in with the signing key (`signing_key`). The login session
lasts 30 days, or until someone logs out with the generator page's Logout
button. Every login is made with the one signing key, so logging out ends
every login session, in every browser, a copy of the session cookie included.
pixa keeps a random value in its database, which it makes when the database
has none and replaces at each logout. A login session carries the value
current at its login and is refused once the value has changed, also after a
restart (see Deployment). The check for a logout compares no time, so a login
after a logout works whatever the host's clock says; the 30 days are still
measured by the host's clock.
lasts 30 days, or until `/logout`.
2. On the generator page, give the source image's URL, the width and height, the
format, quality and fit, and how long the URL lasts, then submit the form
(`POST /generate`). The format is JPEG XL unless another is chosen; a form
sent with an empty format, or none, also makes a JPEG XL URL. Width and
height both empty or `0` keep the original size; if only one of them is empty
or `0`, that side is scaled to keep the image's proportions. A URL whose
scaled side would come out above 8192 answers 400, and so does an AVIF URL of
more than 16,777,216 pixels or a source URL whose path holds a `..` segment.
So does a source URL that the image URL would fetch written another way, and
the page then shows the URL pixa would fetch: one with a user name and
password, which pixa does not send, or one whose path holds `%2F`, fetched as
`/`, or `(`, fetched as `%28`, as pixa keeps the source path decoded and
fetches it percent-encoded again (see Routes).
(`POST /generate`). Width and height both empty or `0` keep the original
size; if only one of them is empty or `0`, that side is scaled to keep the
image's proportions.
3. The page shows the URL, `https://<host>/v1/e/<token>/img.<format>`, and when
it expires. `<host>` is the host the page was opened on, and the URL starts
with `http` instead while `debug` is on. The name after the token is ignored
and only gives the URL a file extension, `jpg` for `orig` and `auto`, and
`jxl` for a form with no format.
and only gives the URL a file extension, `jpg` for `orig` and `auto`.
The token holds the source's host, path and query and the size, format, quality,
fit and expiry, encrypted with a key derived from `signing_key`. The host is
kept in lower case and an empty path as `/`, as for `/v1/image/`, so
`https://CDN.Example.com` and `https://cdn.example.com/` are one source image,
fetched and cached once. The source URL's scheme is not kept: the image is
fetched like any other (see Routes), and the blocked networks still apply.
fit and expiry, encrypted with a key derived from `signing_key`. The source
URL's scheme is not kept: the image is fetched like any other (see Routes), and
the blocked networks still apply.
How long the URL lasts is chosen on the page, from 1 minute to 1 year, or never.
The expiry is fixed in the token when the URL is made and cannot be changed or
@@ -530,10 +350,6 @@ turned off.
- An image with an ICC profile is converted to sRGB first, since clients show an
image with no profile as sRGB. Colours outside sRGB, such as the most
saturated ones in a Display P3 photo, are clipped.
- The one exception is JPEG XL with libvips 8.16 and later: libvips then writes
an EXIF block of its own into the image, as govips cannot ask libvips to leave
it out. It holds the image's size and otherwise fixed values, such as an
orientation of 1 and a resolution of 72 dpi, and nothing from the source.
### Source Hosts
@@ -555,27 +371,14 @@ HMAC-SHA256(secret, "host:path:query:width:height:format:expiration:quality:fit"
Where:
- `host` — source host as the URL writes it up to the first `/`, in lower case,
keeping an IPv6 address's brackets and any `:` and port after it (e.g.
`cdn.example.com`, `cdn.example.com:8443`, `[2001:db8::1]:8443`)
- `path` — source path, with its percent-escapes decoded as under Routes (e.g.
`/photos/cat.jpg`, or `/photos/my cat.jpg` for `/photos/my%20cat.jpg`), with
each `%` written as `%25` and each `:` as `%3A`, so `/photos/a:b.jpg` is
signed as `/photos/a%3Ab.jpg`
- `query` — source query string as under Routes, empty string if none, with `%`
and `:` written as in `path`; neither then holds a `:`, so path `/a:b` with no
query and path `/a` with query `b:` are signed differently
- `width` — requested width in pixels, or `0`: the width is then worked out from
the source's proportions and the requested height, rounded down but at least
1, or is the source's own width when the height is `0` too (the `orig` size)
- `height` — requested height in pixels, or `0`: the height is then worked out
from the source's proportions and the requested width, rounded down but at
least 1, or is the source's own height when the width is `0` too (the `orig`
size)
- `host` — source origin hostname (e.g. `cdn.example.com`)
- `path` — source path (e.g. `/photos/cat.jpg`)
- `query` — source query string, empty string if none
- `width` — requested width in pixels, `0` for original
- `height` — requested height in pixels, `0` for original
- `format` — output format, one of those listed under Routes, with `original`
signed as `orig`, `jpg` as `jpeg`, and no format as `jxl`, so a URL with no
format has the signature of the same URL ending in `.jxl`; `auto` is signed as
`auto`, not as the format chosen for the request
signed as `orig` and `jpg` as `jpeg`; `auto` is signed as `auto`, not as the
format chosen for the request
- `expiration` — the URL's `exp` query parameter, the Unix timestamp when the
signature expires; a request whose `exp` is not a whole number, an empty
`exp=` included, is refused with 400
@@ -584,10 +387,7 @@ Where:
with 400
- `fit` — the URL's `fit` query parameter (cover, contain, fill, inside,
outside), or `cover` when the URL has no `fit`; a request whose `fit` is
anything else, an empty `fit=` included, is refused with 400. `outside` scales
the image to cover the requested size, keeping its proportions, so it can come
out larger than that size on one side: an 8192x1 source at `100x0`, which is
100x1 by its proportions, comes out at 8192x1
anything else, an empty `fit=` included, is refused with 400
The URL's `sig` is the HMAC-SHA256 result in base64url (the URL-safe alphabet of
RFC 4648) with the trailing `=` padding kept, 44 characters in all. pixa
@@ -611,17 +411,6 @@ For the same image at quality 40 with fit `contain`, the input ends in
and the URL is
`/v1/image/cdn.example.com/photos/cat.jpg/800x600.webp?sig=5IwXUx6vf7yefhaUvFzgXZvG2o0Df4RJxPTK3pKq5VU=&exp=1704067200&q=40&fit=contain`.
For a source URL with a query,
`https://cdn.example.com/img?url=https://origin.example.com/my%20cat.jpg`, at
800x600 WebP with the same key and expiration and the default quality and fit:
1. Build input, with the query's `:` written as `%3A` and its `%` as `%25`:
`cdn.example.com:/img:url=https%3A//origin.example.com/my%2520cat.jpg:800:600:webp:1704067200:85:cover`
2. The signature is `37aFa9GSVCZM1kRY9SzMOk2fOg_M7Wt5gKNR4xM-FYA=`
3. URL, with the `?` before the query written as `%3F` and the query's `%` as
`%25` (see Routes):
`/v1/image/cdn.example.com/img%3Furl=https://origin.example.com/my%2520cat.jpg/800x600.webp?sig=37aFa9GSVCZM1kRY9SzMOk2fOg_M7Wt5gKNR4xM-FYA=&exp=1704067200`
**Allowlist patterns:**
- **Exact match**: `cdn.example.com` — matches only that host
@@ -633,16 +422,6 @@ entry that is neither a host name (letters, digits, hyphens, underscores and
dots, with at most one leading dot) nor an IP address, such as one with a port
or a `*.` wildcard, aborts startup.
pixa lower-cases the host of a `/v1/image/` URL before anything else uses it, so
`CDN.Example.com` is matched, fetched, cached and counted against
`upstream_connections_per_host` as `cdn.example.com`. Such a URL whose host has
a port, as in `cdn.example.com:8443`, or a `:` with no port, needs a signature
even when the host is allowlisted. The host must be a host name or an IPv4
address (letters, digits, hyphens, underscores and dots) or an IPv6 address in
brackets, either one optionally followed by `:` and a port. Any other host, such
as one holding `@`, or a `?`, `#`, `%`, `\` or space written percent-encoded, is
refused with 400.
### Configuration
Every setting can be given as an environment variable, in a YAML config file
@@ -685,8 +464,7 @@ tell. With no file, pixa uses the environment and the defaults.
| `PIXA_ALLOW_HTTP` | `allow_http` | Allow plain-HTTP upstreams, for testing only; default `false` |
| `PIXA_UPSTREAM_CONNECTIONS_PER_HOST` | `upstream_connections_per_host` | Concurrent connections per upstream host; default `20` |
| `PIXA_UPSTREAM_CONNECTIONS` | `upstream_connections` | Concurrent connections to all upstream hosts together; default `64` |
| `PIXA_MAX_CONCURRENT_PROCESSING` | `max_concurrent_processing` | Images processed at once; default half the CPUs, at least 1 |
| `PIXA_IMAGE_REQUESTS_PER_MINUTE` | `image_requests_per_minute` | Image requests per client per minute; `0` turns it off; default `600` |
| `PIXA_MAX_CONCURRENT_PROCESSING` | `max_concurrent_processing` | Images processed at once; default the number of CPUs |
| `PIXA_UPSTREAM_FETCH_TIMEOUT` | `upstream_fetch_timeout` | Time allowed for one fetch from an upstream host; default `30s` |
| `PIXA_UPSTREAM_MAX_RESPONSE_SIZE` | `upstream_max_response_size` | Largest upstream response accepted, in bytes; default 50 MiB |
| `PIXA_DOWNSTREAM_TIMEOUT` | `downstream_timeout` | Time allowed for answering one client request; default `60s` |
@@ -723,12 +501,7 @@ Key settings in more detail:
and generator pages. Default: empty
- `blocked_networks` — list of CIDR ranges to refuse for SSRF protection, added
to the always-enforced built-in ranges (loopback, private, link-local, CGNAT,
benchmark, NAT64, and the like); an invalid CIDR aborts startup. An IPv6
address in the IPv4-mapped form (`::ffff:a.b.c.d`) is matched only as the IPv4
address it holds, so an IPv6 range such as `::/0` refuses neither it nor a
plain IPv4 address. An entry written in that form is read as the IPv4 range it
covers, so `::ffff:10.0.0.0/104` refuses what `10.0.0.0/8` refuses; such an
entry shorter than `/96` covers more than IPv4 addresses and aborts startup
benchmark, NAT64, and the like); an invalid CIDR aborts startup
- `trusted_proxies` — list of CIDR ranges of the reverse proxies in front of
pixa. `X-Forwarded-For` is believed only when the direct peer falls inside one
of these ranges; the logged and login-recorded client address is then the
@@ -738,22 +511,16 @@ Key settings in more detail:
omitted key defaults to the RFC 1918 private ranges (`10.0.0.0/8`,
`172.16.0.0/12`, `192.168.0.0/16`), since pixa is deployed behind a proxy on a
private network; an explicitly empty list (`[]`) trusts no one, and an
explicit list replaces the default. An invalid CIDR aborts startup. An IPv6
address in the IPv4-mapped form (`::ffff:a.b.c.d`) is matched only as the IPv4
address it holds, so an IPv6 range such as `::/0` trusts neither it nor a
plain IPv4 address. An entry written in that form is read as the IPv4 range it
covers, so `::ffff:10.0.0.0/104` trusts what `10.0.0.0/8` trusts; such an
entry shorter than `/96` covers more than IPv4 addresses and aborts startup.
Set this to the address pixa sees for requests that come through your proxy,
such as `172.17.0.1/32`, when the defaults do not cover it, or to trust
nothing else (see the login limit and `image_requests_per_minute` under
Routes). For a proxy on the Docker host that connects to pixa over
`127.0.0.1`, that address is the gateway of the container's Docker network
(`172.17.0.1` on the default bridge), not the proxy's own address; a proxy
that connects through another of the host's addresses is seen with that
address. To be sure which address it is, set this to `[]` (or
`PIXA_TRUSTED_PROXIES` to empty), send a request through the proxy, and read
`remoteIP` in pixa's request log line for it
explicit list replaces the default. An invalid CIDR aborts startup. Set this
to the address pixa sees for requests that come through your proxy, such as
`172.17.0.1/32`, when the defaults do not cover it, or to trust nothing else
(see the login limit under Routes). For a proxy on the Docker host that
connects to pixa over `127.0.0.1`, that address is the gateway of the
container's Docker network (`172.17.0.1` on the default bridge), not the
proxy's own address; a proxy that connects through another of the host's
addresses is seen with that address. To be sure which address it is, set this
to `[]` (or `PIXA_TRUSTED_PROXIES` to empty), send a request through the
proxy, and read `remoteIP` in pixa's request log line for it
- `upstream_fetch_timeout` — time allowed for one fetch from an upstream host,
as a duration such as `30s` (the default) or `2m`
- `upstream_max_response_size` — largest upstream response accepted, in bytes;
@@ -765,14 +532,13 @@ Key settings in more detail:
- `signing_key` — HMAC secret for URL signatures
- `db_url` — the SQLite database to open; omitted, it is
`file:<state_dir>/state.sqlite3?_pragma=journal_mode(WAL)`, which keeps the
database in WAL mode. `state_dir` is percent-encoded in it, so a `%`, `?` or
`#` in the name is written as `%25`, `%3F` or `%23`. For a `state_dir` of `/`
or one starting with `//` it starts `file:////`, so SQLite does not read the
first name in the path as a host. pixa opens one connection to it, so its own
reads and writes run one at a time. pixa adds `_pragma=busy_timeout(5000)` to
any `db_url`, so a write that finds another program writing to the file waits
up to five seconds for it instead of failing. WAL mode comes only from the
URL: keep `_pragma=journal_mode(WAL)` in one you set
database in WAL mode. pixa opens one connection to it, so its own reads and
writes run one at a time. Requests wait while eviction runs one of its
queries, some of which read a whole table. pixa adds
`_pragma=busy_timeout(5000)` to any `db_url`, so a write that finds another
program writing to the file waits up to five seconds for it instead of
failing. WAL mode comes only from the URL: keep `_pragma=journal_mode(WAL)` in
one you set
- `cache_max_bytes` — disk cache size limit in bytes; `0` disables the disk
cache entirely; omitted defaults to 75% of the sum of the free space on the
filesystem containing `<state_dir>/cache/` and the bytes of source and
@@ -785,18 +551,10 @@ Key settings in more detail:
does, and `downstream_timeout` has not ended first, the request is answered
503 with the error `server busy, try again later`
- `max_concurrent_processing` — the most images decoded and encoded at once;
default half the CPUs pixa can use (`GOMAXPROCS`, which follows a container's
CPU limit), rounded down, and at least 1. A value that is not a whole number
of at least 1 aborts startup. A request that finds all of them in use waits up
to 10 seconds for one to free up; if none does, and `downstream_timeout` has
not ended first, it is answered 503 the same way. Each one can take a lot of
memory: see "Running under upaas"
- `image_requests_per_minute` — how many requests one client may send to the
image routes per minute (see the limit on them under Routes); default `600`.
`0` turns the limit off, and a negative or non-integer value aborts startup.
Behind a CDN or proxy whose addresses are not in `trusted_proxies`, all
requests arriving from one proxy or CDN address count as one client, so raise
the limit there, or set `0`
default the number of CPUs pixa can use (`GOMAXPROCS`), which follows a
container's CPU limit. A request that finds all of them in use waits up to 10
seconds for one to free up; if none does, and `downstream_timeout` has not
ended first, it is answered 503 the same way
- `maintenance_mode` — while `true`, the image routes (`/v1/image/` and
`/v1/e/`) answer every request for an image with 503, a `Retry-After` header
and a JSON error body. The health check (`/.well-known/healthcheck.json`)
@@ -817,12 +575,7 @@ See `configs/config.example.yml` for all options with defaults.
- **Metrics**: Prometheus, at `/metrics`: generic HTTP request metrics
(duration, response size, requests in flight) and the Go runtime and process
metrics; requests are measured and `/metrics` is served only when
`metrics.username` and `metrics.password` are set. A request's `handler` label
is the pattern of the route it matches, such as `/v1/image/*`, never its path.
Requests that match no route share the label `unmatched`: those the router
answers 404 or 405, and CORS preflights. A request's `method` label is its
method when that is `GET`, `HEAD`, `POST`, `PUT`, `PATCH`, `DELETE`,
`OPTIONS`, `CONNECT` or `TRACE`, and `other` for any other method
`metrics.username` and `metrics.password` are set
- **Logging**: stdlib slog
## Entrypoints
@@ -841,9 +594,9 @@ provide:
install-precommit)
- `script/projectname` — output the project name ("pixa")
- `script/test` — run the test suite: build the `test` phase of the
`Dockerfile`, writing no image
`Dockerfile`, tagged `pixa-test`
- `script/lint` — run golangci-lint: build the `lint` phase of the `Dockerfile`,
writing no image; the linter never runs on the host
tagged `pixa-lint`; the linter never runs on the host
- `script/fmt` — format the Go code with gofmt and the markdown with prettier
(writes)
- `script/fmt-check` — check the same formatting (read-only), on the host
@@ -854,9 +607,6 @@ provide:
- `script/docker-smoke` — build the image, start it, wait for it to be healthy
- `script/loadtest` — measure pixad's throughput, latency and peak memory; a
benchmark, not part of `script/check` (see Load Test)
- `script/bench` — run the Go benchmark that serves cache hits in parallel
through the image handler, with Go on the host after `script/bootstrap --cgo`;
a benchmark, not part of `script/check` (see Load Test)
- `script/cibuild` — CI entrypoint: run `script/bootstrap` (without `--cgo`),
then `script/check`, then build the image as `script/docker` does
- `script/precommit` — pre-commit checks (`go mod tidy` guard, then
@@ -864,26 +614,15 @@ provide:
- `script/install-precommit` — install the git pre-commit hook that runs
`script/precommit`
Every `docker build` in these scripts passes a new value of the `CACHEBUST`
build argument, which every stage of the `Dockerfile` declares, so every `RUN`
step after that line, the lint and test steps included, runs on every build
instead of coming from the build cache. Above the line are the steps that
install system packages and download the Go modules; Docker keeps their layers
until the base image, the step itself, `go.mod` or `go.sum` changes. Go's build
cache is kept from build to build: the steps that compile mount it, so a package
whose inputs are unchanged is not compiled again, and both `go test` runs pass
`-count=1` so that no stored test result is replayed. The lint step also mounts
golangci-lint's cache, which reuses a package's findings only when its files,
those of the packages it imports, `go.mod`, the linters and their settings in
`.golangci.yml`, and the golangci-lint version are all unchanged. The `test`
phase runs on the Debian Go image, with Debian's libvips and libheif; the image
pixa ships is built and runs on Alpine. `script/check`, `script/cibuild`,
`script/docker`, `script/lint`, `script/test`, `script/setup` and
`script/install-precommit` are the standard copies from `sneak/prompts`, kept
identical to them. `script/fmt` and `script/fmt-check` are the standard copies
with pixa's `gofmt` step kept before prettier. prettier formats the markdown
only, not the HTML templates, as it cannot parse a Go template action inside a
tag.
Every `docker build` in these scripts passes `--no-cache`, so the lint and test
phases run on every build instead of coming from the build cache.
`script/check`, `script/cibuild`, `script/docker`, `script/lint`, `script/test`,
`script/setup` and `script/install-precommit` are the standard copies from
`sneak/prompts`, kept identical to them. `script/fmt` and `script/fmt-check` are
the standard copies with pixa's `gofmt` step kept before prettier. prettier
formats the markdown only: not the HTML templates, as it cannot parse a Go
template action inside a tag, and not `REPO_POLICIES.md` (see
`.prettierignore`), a copy of the one in `sneak/prompts`.
## Load Test
@@ -937,17 +676,6 @@ The numbers depend on the machine and on whatever else runs on it. The first
measurement, made on a shared machine with few clients, is in `TODO.md`; it says
nothing about the target.
`script/bench` (or `make bench`) measures cache hits alone, without the network
and with no pixad process: a Go benchmark in `internal/handlers` serves one
cached image through the `/v1/image/` handler from as many goroutines at once as
the machine has CPUs, and reports the hits served per second as `hits/s`. Each
run starts with an empty cache and an empty database, a SQLite file of its own,
and puts the image in the cache before it measures. The benchmark fails if
serving the hits ran any statement on the database. Like the load test it is not
part of `script/check`. It runs Go on the host, as the load test does, and
compiles pixa there, so it needs the C compiler and libraries that
`script/bootstrap --cgo` installs, but not Docker.
## TODO
See [TODO.md](TODO.md) for the full prioritized task list.
REPO_POLICIES.md
+109 -295
View File
@@ -1,6 +1,6 @@
---
title: Repository Policies
last_modified: 2026-10-18
last_modified: 2026-09-08
---
This document covers repository structure, tooling, and workflow standards. Code
@@ -54,39 +54,34 @@ style conventions are in separate documents:
`cibuild`. `script/bootstrap` installs all dependencies idempotently and
assumes nothing is present: base tools come from nix, apt, brew, or apk
(detected in that order; apt runs noninteractive). For node it uses the
installed node only when its major version is the pinned one; otherwise (node
missing, or another major, such as the node 24 the CI runner image ships) it
installs the PINNED node version via nvm and installs yarn and the packages
under it. nvm itself is installed first if missing, from a hash-verified
GitHub release archive (never `curl | sh`), with bash installed as an explicit
prerequisite since nvm requires bash. Only the major version is compared
because the `Dockerfile` stages start from a node image whose exact version is
not the pin, and nvm cannot install a prebuilt node on alpine. yarn is pinned
via `corepack prepare yarn@<version> --activate`. Never install "latest" or
"lts"; always exact versions. `script/cibuild` runs the CI build: it changes
to the repo root, runs `script/bootstrap`, runs `script/check`, and builds the
image with the version; the Gitea workflow calls it. **`script/cibuild` runs
installed node if present; otherwise it installs a PINNED node version via
nvm, first installing nvm itself if missing — from a hash-verified GitHub
release archive (never `curl | sh`), with bash installed as an explicit
prerequisite since nvm requires bash. yarn is then pinned via
`corepack prepare yarn@<version> --activate`. Never install "latest" or "lts";
always exact versions. `script/cibuild` runs the CI build: it changes to the
repo root, runs `script/bootstrap`, runs `script/check`, and builds the image
with the version; the Gitea workflow calls it. **`script/cibuild` runs
`script/bootstrap` first**, because the workflow checks out the repo and runs
nothing else, while `script/fmt-check` runs the formatter on the host: on a
pristine checkout with nothing installed the run dies there, after the
containerised gates have passed. **The bootstrap alone is not enough**: when
`script/bootstrap` installs node and yarn under nvm it leaves neither on the
`PATH` of the shell that called it, so a bare `yarn` either exits 127 or runs
under another node. The host entrypoints that need yarn — `script/fmt` and
`script/fmt-check` — therefore use the same test as `script/bootstrap`: when
the node on `PATH` has the pinned major version they run the `yarn` on `PATH`,
and otherwise they load nvm through `$HOME/.nvm/nvm.sh` and run yarn under the
pinned node. A runner carrying nothing but docker and git then gets through
`script/check`. Four further scripts are our own extensions to the standard:
`script/check` runs `script/test`, `script/lint` and `script/fmt-check`;
`script/precommit` is what the git pre-commit hook runs, and it calls
`script/check`; `script/install-precommit` installs the git pre-commit hook
(the `make hooks` target shims to it); and `script/projectname` (literally
that filename) simply outputs the project's name. Scripts that need the name
call `script/projectname` — e.g. `script/docker` assembles its image tag from
it — so those scripts stay byte-identical across all repos. Repo-type-specific
pre-commit extras (e.g. `go mod tidy` verification in Go repos) belong in
`script/precommit`, not in the hook itself. Model scripts are at
containerised gates have passed. **The bootstrap alone is not enough**:
`script/bootstrap` installs node and yarn under nvm and leaves neither on the
`PATH` of the shell that called it, so a bare `yarn` still exits 127. The host
entrypoints that need yarn — `script/fmt` and `script/fmt-check` — therefore
source nvm for the pinned node version before invoking it, exactly as
`script/bootstrap`'s own install step does. A runner carrying nothing but
docker and git then gets through `script/check`. Four further scripts are our
own extensions to the standard: `script/check` runs `script/test`,
`script/lint` and `script/fmt-check`; `script/precommit` is what the git
pre-commit hook runs, and it calls `script/check`; `script/install-precommit`
installs the git pre-commit hook (the `make hooks` target shims to it); and
`script/projectname` (literally that filename) simply outputs the project's
name. Scripts that need the name call `script/projectname` — e.g.
`script/docker` assembles its image tag from it — so those scripts stay
byte-identical across all repos. Repo-type-specific pre-commit extras (e.g.
`go mod tidy` verification in Go repos) belong in `script/precommit`, not in
the hook itself. Model scripts are at
`https://git.eeqj.de/sneak/prompts/raw/branch/main/script/<name>`. The README
must document the provided scripts in an **Entrypoints** section (see the
README requirements below).
@@ -109,24 +104,18 @@ style conventions are in separate documents:
`lint` phase and a `test` phase, with the final stage depending on both so the
image cannot be built unless they pass. For non-server repos the final stage
brings up a development environment; for server repos it is the runtime image.
The gate phases and the build stage start from their pinned base images and
install what those images lack either inline, as the canonical Go `Dockerfile`
below does for `git`, or by running `script/bootstrap`, as the `prompts`
repo's own `Dockerfile` does for its yarn packages. The development
environment stage installs development prerequisites by running
`script/bootstrap` rather than duplicating its installs inline. A stage that
runs `script/bootstrap` COPYs `script/` and the dependency manifests
(`package.json` + `yarn.lock`, `go.mod` + `go.sum`, etc.) before running it.
Dockerfiles install development prerequisites by running `script/bootstrap`
rather than duplicating installs inline; COPY `script/` and the dependency
manifests (`package.json` + `yarn.lock`, `go.mod` + `go.sum`, etc.) before
running it.
- **Linting and testing run in Docker, as phases of the `Dockerfile`.** There is
no separate lint file. `script/lint` and `script/test` each build one phase
and nothing else:
```sh
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
--target lint --output type=cacheonly .
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
--target test --output type=cacheonly .
docker build --no-cache --target lint -t "$(script/projectname)-lint" .
docker build --no-cache --target test -t "$(script/projectname)-test" .
```
**A stage that is not the last one in the file is built only when the final
@@ -136,15 +125,10 @@ style conventions are in separate documents:
plain `docker build .` builds the last stage alone and exits 0 having linted
and tested nothing.
**The gate builds write no image.** With `--output type=cacheonly` the phase
runs and a failing step fails the build, but the result is not exported.
Nothing uses those images, and writing one out is slow: a Go test phase's
image holds the toolchain. A build given neither `--output` nor `-t` writes
an untagged image and leaves it dangling, on every developer host and every
CI runner. `script/cibuild` and `script/docker` build the image that ships
and tag it, so each build replaces the previous image; each assigns the tag
on its own line before the build, so `set -e` stops it where
`script/projectname` fails.
**Every `docker build` in `script/` is tagged**, here and in
`script/cibuild` and `script/docker`. An untagged build leaves a dangling
image behind on every invocation, on every developer host and every CI
runner; a tagged one replaces the previous image.
Inside a phase the tool is invoked directly — `golangci-lint`, `go test`,
`eslint`, `prettier` — never through `make lint` or `script/test`, which are
@@ -159,122 +143,66 @@ style conventions are in separate documents:
one's findings, and a host-global lock in `$TMPDIR` makes concurrent runs
exit non-zero with `parallel golangci-lint is running` — a status a caller
cannot tell from real findings. Both have produced wrong verdicts in this
org, in both directions. A container has its own `TMPDIR`, so the lock is
out of reach. The lint phase does keep golangci-lint's cache between check
builds (below), but it lints every checkout at `/src`, and a finding is
taken from that cache only for the same files, settings and golangci-lint
version.
org, in both directions. A container has its own cache, its own `TMPDIR` and
a digest-pinned binary, so neither is reachable.
- **Any build that runs checks is given a new `CACHEBUST` value.** Docker
invalidates a `COPY` layer only when the copied content changes, so on an
unchanged tree the check `RUN` is served from cache, nothing executes, and the
build still exits 0. Every `docker build` in `script/` therefore passes
`--build-arg CACHEBUST="$(date +%s)-$$"`, the time and the script's process
id, so no two builds share a value, not even the three in one
`script/cibuild`. `script/lint`, `script/test`, `script/cibuild` and
`script/docker` are the four, and there is no fifth — `script/check` runs the
two gate phases and `script/fmt-check`, and builds no image of its own. In
every stage of the `Dockerfile`, `ARG CACHEBUST` comes right after the steps
that install system packages and download Go's modules, or right after `FROM`
in a stage with neither, and every step that lints, tests or compiles comes
after it. A step that installs anything else as well, such as a
`script/bootstrap` that also installs node packages, comes after it too. A new
value reruns every `RUN` step after that line; `COPY` steps are compared by
content and need nothing. Docker keeps the layers above the line until the
base image, their own lines or the files they copy change. A stage without the
`ARG` line is served from cache on an unchanged tree, so a repository
re-vendors the scripts and adds the `ARG` lines in one commit. The scripts do
not pass `--no-cache`: it reruns every step too, but it also builds the layers
above the line again and empties every cache mount, so Go's build cache and
golangci-lint's, which the canonical Go `Dockerfile` below mounts so that they
survive between check builds, would start empty every time. A bare
`docker build .` is not evidence that anything ran: a sub-second build
reporting success is a cache hit, not a result. Never invalidate by pruning —
`docker builder prune` and friends destroy a build cache shared with every
other build on the host. When a check is added or changed, prove it works by
planting a defect it must catch and watching the run fail on it, then revert
the defect. A green run alone shows neither that the check ran nor that it
covers what it should.
- **Any build that runs checks is built with `--no-cache`.** Docker invalidates
a `COPY` layer only when the copied content changes, so on an unchanged tree
the check `RUN` is served from cache, nothing executes, and the build still
exits 0. Every `docker build` in `script/` therefore passes `--no-cache`:
`script/lint`, `script/test`, `script/cibuild` and `script/docker` are the
four, and there is no fifth — `script/check` runs the two gate phases and
`script/fmt-check`, and builds no image of its own. A bare `docker build .` is
not evidence that anything ran: a sub-second build reporting success is a
cache hit, not a result. Never invalidate by pruning — `docker builder prune`
and friends destroy a build cache shared with every other build on the host.
- **The gate phases are separate stages, and the build stage depends on both.**
The lint phase is based on the `golangci/golangci-lint` image (pinned by
hash), so lint failures surface in seconds rather than after a full compile,
and the test phase is based on the Debian Go image. The canonical Go repo
and the test phase is based on the Go image. The canonical Go repo
`Dockerfile`:
```dockerfile
# In every stage ARG CACHEBUST comes right after the steps that install
# system packages and download Go's modules, or right after FROM in a
# stage with neither, and every step that lints, tests or compiles
# comes after it. script/ passes a new value on every build, which
# reruns every RUN step after it. Docker keeps the layers above it
# until the base image, their own lines or go.mod and go.sum change.
# The steps that compile mount Go's build cache, and golangci-lint run
# also mounts golangci-lint's; both survive from build to build.
# Lint phase
# golangci/golangci-lint:v2.x.x, YYYY-MM-DD
FROM golangci/golangci-lint@sha256:... AS lint
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
ARG CACHEBUST
COPY . .
RUN --mount=type=cache,target=/root/.cache/go-build \
--mount=type=cache,target=/root/.cache/golangci-lint \
golangci-lint run --config .golangci.yml ./...
RUN golangci-lint run --config .golangci.yml ./...
# Test phase. -race needs cgo and so a C compiler, which the Debian Go
# image ships and the alpine one does not. -count=1 because the mounted
# cache also holds test results, which go test would otherwise replay.
# golang:1.x, YYYY-MM-DD
# Test phase
# golang:1.x-alpine, YYYY-MM-DD
FROM golang@sha256:... AS test
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
ARG CACHEBUST
COPY . .
RUN --mount=type=cache,target=/root/.cache/go-build \
go test -count=1 -timeout 90s -race -cover ./... || \
RUN go test -timeout 90s -race -cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \
go test -count=1 -timeout 90s -race -v ./...; exit 1; }
go test -timeout 90s -race -v ./...; exit 1; }
# Build stage. Nothing is wanted from either phase above; the copies
# are what make BuildKit build them first, so nothing after them can
# run unless lint and test passed.
# are what make BuildKit build them first, so this stage cannot run
# unless lint and test passed.
# golang:1.x-alpine, YYYY-MM-DD
FROM golang@sha256:... AS builder
RUN apk add --no-cache git
COPY --from=lint /src/go.sum /dev/null
COPY --from=test /src/go.sum /dev/null
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
ARG CACHEBUST
COPY --from=lint /src/go.sum /dev/null
COPY --from=test /src/go.sum /dev/null
# A tar-stream context keeps the sender's file owners, which git refuses.
RUN git config --system --add safe.directory /src
COPY . .
# The VERSION build arg when one is given, otherwise
# `git describe --tags --always` on the .git in the build context. With
# .git present, a version that is still empty, dev or unknown fails the
# build: git is missing or could not read the checkout.
ARG VERSION
RUN --mount=type=cache,target=/root/.cache/go-build \
VERSION="${VERSION:-$(git describe --tags --always)}"; \
if [ -e .git ]; then \
case "$VERSION" in ""|dev|unknown) \
echo "version is '$VERSION' although .git is present" >&2; \
exit 1 ;; \
esac; \
fi; \
CGO_ENABLED=0 go build -trimpath \
-ldflags="-s -w -X main.Version=${VERSION}" \
-o /app ./cmd/app/
ARG VERSION=dev
RUN CGO_ENABLED=0 go build -trimpath \
-ldflags="-s -w -X main.Version=${VERSION}" \
-o /app ./cmd/app/
# Runtime stage, and the last one
FROM alpine@sha256:...
ARG CACHEBUST
COPY --from=builder /app /usr/local/bin/app
ENTRYPOINT ["app"]
```
@@ -289,106 +217,23 @@ style conventions are in separate documents:
- Keep the runtime stage last, and if you add a stage after it, give it the
same two copies. A plain `docker build .` builds the last stage's chain
and nothing else.
- Check builds keep these, and none of them can hand back a stale result:
- The layers above `ARG CACHEBUST`: the system packages and Go's
modules. Docker installs the packages again when the base image or the
install line changes, and downloads the modules again when `go.mod` or
`go.sum` changes. Go checks every module against `go.sum` as it
downloads it, and no later build can change a kept layer. The modules
are kept in a layer rather than a cache mount because a cache mount is
shared by every build on the host, and Go builds from whatever files
it holds without checking them again (only `go mod verify` does), so a
file changed there would go unnoticed.
- Go's build cache (`/root/.cache/go-build`, where Go keeps it for
root), mounted on the steps that compile: `golangci-lint run`, both
`go test` runs and `go build`. Go reuses a compiled package only when
all its inputs are unchanged. The cache also holds test results, which
is why both `go test` runs carry `-count=1`.
- golangci-lint's cache (`/root/.cache/golangci-lint`, where the pinned
image keeps it), mounted on `golangci-lint run`. golangci-lint reuses
a package's findings only when the package's files and those of every
package it imports, `go.mod`, the linters and their settings in
`.golangci.yml`, and the golangci-lint version are all unchanged.
- If the project uses `//go:embed` directives that reference build artifacts
(e.g. a web frontend compiled in a separate stage), the lint phase must
create placeholder files so the embed directives resolve. Example:
`RUN mkdir -p web/dist && touch web/dist/index.html web/dist/style.css`.
- If the project requires CGO or system libraries for linting, install them
in the lint phase. The `golangci/golangci-lint` image is Debian-based and
has no `apk`, so install with `apt-get` under the Debian package name
(`libvips-dev`, where alpine says `vips-dev`), and delete the package
lists in the same `RUN`, so the layer does not keep them. The test phase,
on the Debian Go image, installs the libraries its tests need the same
way. Either install goes right after `FROM`, above `ARG CACHEBUST`, so
Docker keeps it until the base image or the install line changes:
```dockerfile
FROM golangci/golangci-lint@sha256:... AS lint
RUN apt-get update \
&& apt-get install -y --no-install-recommends libvips-dev \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
ARG CACHEBUST
```
- `.dockerignore` lets `.git` into the build context. It keeps out every git
`config` at any depth (`**/.git/config`, `**/.git/modules/**/config`): the
repository's own, each submodule's under `.git/modules/`, and that of a
submodule keeping its own `.git` directory. `git describe` does not need
them, and each can hold a credential: a password in a remote URL, or the
token the CI checkout step stores there. A submodule whose name has a
`config` segment (`config`, `deploy/config`, `config/lib`) loses its whole
git directory to `**/.git/modules/**/config`, and Go's version stamping
then fails the build: give it a name without that segment
(`git submodule add --name`). The stage that compiles has `git` (the
Debian Go image has it; an alpine one needs `apk add --no-cache git`) and
takes the version from the `VERSION` build argument when one is given,
otherwise from `git describe --tags --always`. That gives the tag on a
tagged commit; on a later commit, the tag, the number of commits since it
and the short commit (`v1.2.3-4-gabc1234`); and the short commit when no
tag is reachable. The stage that compiles also marks its working directory
safe for git (`git config --system --add safe.directory /src`): a context
sent as a tar stream keeps the sender's file owners, and git refuses a
checkout owned by another user, so the version would come out empty.
`ARG VERSION` has no default, and the build fails if the context carries
`.git` and the version still comes out empty, `dev` or `unknown`. A plain
`docker build .` with no build arguments must succeed; a Dockerfile that
refuses an empty build argument drops that refusal and keeps the argument.
A checkout whose `.git` is a file (a linked worktree, or a repository
checked out as a submodule) is the exception: that file points to a git
directory outside the build context, so the build cannot read the version
and a plain `docker build .` fails; pass the version with
`--build-arg VERSION=...`, as `script/docker` and `script/cibuild` already
do.
- If the project requires CGO or system libraries for linting (e.g.
`vips-dev`), install them in the lint phase with `apk add`.
- `ARG VERSION=dev` is declared in the stage that compiles and supplied by
`script/docker` and `script/cibuild`; no stage may call `git describe`.
- Every repo should have a Gitea Actions workflow (`.gitea/workflows/`) that
runs `script/cibuild` on push, and checks out the repo as its only other step,
with `persist-credentials: false`: `script/cibuild` needs no token, and
without it the checkout leaves the job's token in `.git/config` for every
later step. The checkout step also sets `fetch-depth: 0`, which fetches the
tags `git describe` needs: by default it clones shallow with no tags, and a
tagged repository's CI build would stamp a bare short commit id. The
workflow's `concurrency` block groups runs by workflow and branch
(`${{ github.workflow }}-${{ github.ref }}`) with `cancel-in-progress: true`,
so a new push cancels the older run on the same branch, queued or running, and
no other: runs for replaced commits do not hold up the shared runner.
`script/cibuild` bootstraps, runs the gate phases, and then builds the image,
so a successful run means every check passed; a bare `docker build .` does not
runs `script/cibuild` on push, and checks out the repo as its only other step.
That script bootstraps, runs the gate phases, and then builds the image, so a
successful run means every check passed; a bare `docker build .` does not
carry the same guarantee, because its gate phases may come from the cache. The
image build gets a `CACHEBUST` value of its own and so runs the gate phases a
second time. That is the price of the rule above, and it is worth paying: the
image that ships is built from a run of its own gates rather than from a cache
entry. The `check` job sets `timeout-minutes: 20`, so a hung build frees the
shared runner after 20 minutes. That allows for the three Docker builds
described above (the test phase, the lint phase, then the image), each held to
the 5-minute Docker build limit below, plus the bootstrap. A separate workflow
limited to `main` by a `branches` list under `on: push` cannot be checked by
review: to try a change to it, add the feature branch to that list and push,
then remove the branch from the list again before merging. Keep any job in it
that publishes behind `if: github.ref_name == 'main'`, so the run from the
feature branch publishes nothing.
image build is uncached and so runs the gate phases a second time. That is the
price of the rule above, and it is worth paying: the image that ships is built
from a run of its own gates rather than from a cache entry.
- Use platform-standard formatters: `black` for Python, `prettier` for
JS/CSS/Markdown/HTML, `go fmt` for Go. Always use default configuration with
@@ -441,18 +286,17 @@ style conventions are in separate documents:
```
`-count=1` is required on both invocations: it defeats Go's test _result_
cache, so neither run can report a stored pass in place of running the
tests. It leaves the build cache alone, so it costs the runtime of the suite
and no recompilation.
cache, so the target cannot report a pass it did not earn, and the rerun
reproduces a failure instead of replaying it. It leaves the build cache
alone, so it costs the runtime of the suite and no recompilation.
That cache is Go's own, separate from Docker's layer cache. Go stores a
passing result in its cache directory (`GOCACHE`), and when the same tests
run again on unchanged code it prints that result, marked `(cached)`,
without running them. The directory lasts from one run to the next on a
developer's machine, where this target runs, and in the `test` phase of the
`Dockerfile`, which mounts it to keep compiled packages between check
builds, so the phase's `go test` runs carry `-count=1` too. A new
`CACHEBUST` value (above) is what makes that step run on an unchanged tree.
Note that this is a second, independent cache, stacked below the Docker
layer cache that [issue #26](https://git.eeqj.de/sneak/prompts/issues/26)
addresses. `CHECK_EPOCH` guarantees the `RUN make test` _step_ re-executes;
it does not guarantee `go test` inside that step does any work, because the
`GOCACHE` baked into earlier image layers survives into the re-executed
step. They are two separate defects requiring two separate fixes, and a fix
for one must not be recorded as covering the other.
Python example:
@@ -480,12 +324,9 @@ style conventions are in separate documents:
- `.gitignore` should be comprehensive from the start: OS files (`.DS_Store`),
editor files (`.swp`, `*~`), in-repo agent scratch directories (`.claude/`),
`node_modules/`, and the repo's own build outputs. Fetch the standard
`.gitignore` from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` when setting up
a new repo. A repo's `.gitignore` is the standard file followed by the repo's
own entries, such as its binaries; a re-vendor replaces the standard part and
keeps those entries. These patterns are written to `.gitignore`'s own
language build artifacts, and `node_modules/`. Fetch the standard `.gitignore`
from `https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` when
setting up a new repo. These patterns are written to `.gitignore`'s own
semantics, in which an unanchored pattern already matches at every depth; they
are not a `.dockerignore` and must not be transplanted into one unmodified.
@@ -499,7 +340,7 @@ style conventions are in separate documents:
— which is more dangerous than a short file with no secret patterns at all,
because it reads as solved and stops anyone looking. Give every
depth-independent pattern the `**/` prefix and leave only genuinely
root-anchored entries unprefixed: `.claude`, and the repo's own host-built
root-anchored entries unprefixed: `.git`, and the repo's own host-built
binary, written `/myapp` and never `**/myapp`, which would also match
`cmd/myapp/` and delete the package directory from the context. Matching is
case-sensitive, and an ALL-CAPS twin per pattern still misses `Server.Key`, so
@@ -524,24 +365,21 @@ style conventions are in separate documents:
directory, so a repo running agents in subdirectories still ships
`services/api/.claude/` and must add its own anchored entry there.
- **A plain `docker build .` of a clone stamps the version that
`git describe --tags --always` gives**, derived from the `.git` in the build
context as the canonical `Dockerfile` above shows. Without its failure check,
a missing `git` or an unreadable checkout would leave `-X main.Version=` empty
and the build would still exit 0. `script/docker` and `script/cibuild` pass
the version they compute on the host; it takes precedence. They do this
byte-identically across repos:
- **Excluding `.git` means `git describe` cannot run inside any build stage, and
it fails quietly there.** In a build stage there is no repository, so
`git describe` writes nothing to stdout, `-X main.Version=` comes out empty,
the binary reports no version at all, and the build still exits 0. Compute the
version on the host and thread it in as a build arg. `script/docker` and
`script/cibuild` do this, byte-identically across repos:
```sh
# The version and the tag each get their own line: a failing command
# substitution inside an argument does not trip `set -e`, so the inline
# form degrades to an empty constant.
# Own line: a failing command substitution inside an argument does not
# trip `set -e`, so the inline form degrades to an empty constant.
version="$(git describe --tags --always --dirty 2>/dev/null || true)"
[ -n "$version" ] || version="unknown"
tag="$(script/projectname)"
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
docker build --no-cache \
--build-arg VERSION="$version" \
-t "$tag" .
-t "$(script/projectname)" .
```
`--always` makes an untagged repo yield an abbreviated commit hash rather
@@ -549,12 +387,12 @@ style conventions are in separate documents:
fallback is applied — a live check that fires on a build from an export with
no `.git` and on a repository with no commits yet. Do not fold it into the
substitution as `|| echo unknown`, which makes the guard unreachable. The
Dockerfile's side is `ARG VERSION` in the stage that compiles, declared
Dockerfile's side is `ARG VERSION=dev` in the stage that compiles, declared
there because `ARG` is stage-scoped; passing `VERSION` to a repo whose
Dockerfile declares no such `ARG` is ignored and costs nothing, which is why
the scripts stay byte-identical. One consequence for CI: the standard
checkout action clones shallow and fetches no tags, so the canonical
`.gitea/workflows/check.yml` sets `fetch-depth: 0` on its checkout step.
checkout action clones shallow and fetches no tags, so a repo that embeds a
tag-derived version must set `fetch-depth: 0` on its checkout step.
- **Verify `.dockerignore` by enumerating the image, not by reading the
patterns.** Plant files at the root _and_ at least two directories deep, build
@@ -588,18 +426,12 @@ style conventions are in separate documents:
`test-support` depguard rule, where a repo names its own test-support packages
by full import path. A repo adds entries there and changes nothing else, and a
re-vendor carries its entries forward. The canonical golangci-lint version is
v2.14.0 (released 2026-09-24), pinned as the digest of the lint phase's base
v2.12.2 (released 2026-05-06), pinned as the digest of the lint phase's base
image
(`golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f`,
which reports `2.14.0 built with go1.27.0 from 114493f9`). A module's `go`
directive must not name a newer Go minor version than the one golangci-lint
was built with, or golangci-lint refuses to lint it: this release lints
`go 1.27.1` but not `go 1.28`. That digest is the only pin, since no repo
installs golangci-lint on the host. A repo sets the lint phase digest to the
one named here and re-vendors `.golangci.yml` in the same commit, whichever of
the two prompted the change: the canonical copy can name linters that an older
golangci-lint rejects, and a newer golangci-lint can add linters that
`default: all` switches on until the canonical copy disables them.
(`golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240`,
which reports `2.12.2 built with go1.26.2 from c0d3ddc9`). That digest is the
only pin, since no repo installs golangci-lint on the host: bumping the
version means changing it and nothing else.
- **`script/bootstrap` installs a pinned tool by comparing versions, never by
testing presence.** An `if ! command -v <tool>; then install; fi` guard tests
@@ -621,18 +453,8 @@ style conventions are in separate documents:
function defined and never invoked has the same exit status and the same
empty output as one that worked.
Node is the exception to the whole-token comparison: the canonical
`script/bootstrap` compares only its major version, because the node 22
alpine image the `Dockerfile` stages start from is not the exact pin, and
nvm cannot install a prebuilt node on alpine.
Keep it POSIX sh: no arrays, no `[[`, no `grep -P`.
A Go tool a repo needs on the host is installed with `go install` pinned to
a commit hash (`go install <package>@<commit hash>`). It is never tracked as
a `go.mod` tool dependency or through a `tools.go` file, either of which
pulls the tool's own dependencies into the repo's `go.mod` and `go.sum`.
- When pinning images or packages by hash, add a comment above the reference
with the version and date (YYYY-MM-DD).
@@ -742,17 +564,13 @@ style conventions are in separate documents:
Never edit existing migrations after release.
- All repos should have an `.editorconfig` enforcing the project's indentation
settings: the standard file from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.editorconfig`, which sets
tabs for `Makefile` and Go files, followed by the repo's own sections, such as
one for another language it uses. A re-vendor replaces the standard part and
keeps those sections.
settings.
- Avoid putting files in the repo root unless necessary. Root should contain
only project-level config files (`README.md`, `AGENTS.md`, `Makefile`,
`Dockerfile`, `LICENSE`, `.gitignore`, `.editorconfig`, `REPO_POLICIES.md`,
and language-specific config). Everything else goes in a subdirectory.
Canonical subdirectory names:
only project-level config files (`README.md`, `Makefile`, `Dockerfile`,
`LICENSE`, `.gitignore`, `.editorconfig`, `REPO_POLICIES.md`, and
language-specific config). Everything else goes in a subdirectory. Canonical
subdirectory names:
- `bin/` — executable scripts and tools
- `cmd/` — Go command entrypoints; thin only: one `main.go` per binary whose
body is a single call into `internal/` or `pkg/`, no project logic in
@@ -783,7 +601,3 @@ style conventions are in separate documents:
- Go: `go.mod`, `go.sum`, `.golangci.yml`
- JS: `package.json`, `yarn.lock`, `.prettierrc`, `.prettierignore`
- Python: `pyproject.toml`
- Guidance for coding agents lives in one `AGENTS.md` at the repository root. It
is never committed under a file or directory named after one agent tool, such
as `CLAUDE.md` or `.claude/`, and never split into separate memory files.
TODO.md
+9 -475
View File
@@ -18,7 +18,7 @@
pre-1.0. No git tags exist. The `1.0.0` milestone is in progress; work lands on
`next`, and `main` receives only the milestone PR that the owner merges. `next`
is at the canonical `golangci-lint` v2.14.0 config and is green. Recent work
is at the canonical `golangci-lint` v2.12.2 config and is green. Recent work
extracted the internal/magic, internal/allowlist, internal/httpfetcher, and
internal/signature packages. The gosec findings from the 2026-07-06 survey are
resolved. The disk cache is now size-bounded with LRU eviction
@@ -26,478 +26,10 @@ resolved. The disk cache is now size-bounded with LRU eviction
# Next Step
P2: security: per-origin rate limiting
P2: security: per-IP rate limiting on the image routes
# Completed Steps
- 2026-10-21 the schema file declares only the tables and columns pixa writes
and reads (closes #310): `output_content` and `request_cache` are gone, and so
are the columns nothing read: the host, path, query, `content_type` and
`fetched_at` of `source_content`, the `content_type` and `created_at` of
`variant_content`, and the `status_code`, `error_message` and `fetched_at` of
`negative_cache`. `StoreSource` no longer takes the fetch result,
`LookupSource` returns only the source key, `StoreVariant` no longer takes a
content type, `StoreNegative` no longer takes a status code or message, and
reconciliation adopts a variant file without reading its first bytes.
- 2026-10-21 a cache hit makes no database call (closes #309): `Service.Get`
opens the variant file with `Cache.GetVariant` and nothing else, with no
existence check first. The content type comes from the file's first bytes; a
file whose first bytes are not those of an output format, SVG included, is a
miss, and the variant is made again. A hit hands its access time to a channel
that holds up to 10,000 and drops the rest, and its hit count to the pending
counts, without waiting; every count is now a pending count. A miss that finds
a cached source hands that source's access time to a second such channel. The
goroutine `StartPendingCountWrites` starts writes, once a second, the access
times in one transaction and the counts in one `UPDATE`;
`StopPendingCountWrites` writes what is left once at shutdown and logs
separately the access times and the counts it could not write.
`checkNegativeCache` no longer deletes an expired row; `CleanExpired` in the
eviction goroutine does. The `.meta` files, `VariantMeta`, `LoadWithMeta`,
`variantContentTypeFromSidecar`, `metaCache`, `Lookup` and `golang-lru` are
gone. `make bench` (`script/bench`) runs `BenchmarkHandleImage_CacheHits` with
Go on the host after `script/bootstrap --cgo`, outside `make check`.
- 2026-10-21 a source is stored the way a variant is (closes #308): one
`source_content` row and one file per source URL, the file named by the
source's `SourceKey`, the SHA-256 of its host, path and query made as the
variant key is, under `cache/sources/`. A store writes the file, then the row,
and removes the file when the row cannot be written; an eviction deletes the
row, then the file, with no lock and no transaction. `source_metadata`, the
JSON files under `cache/metadata/`, `MetadataStorage` and the content lock are
gone. Two source URLs that serve the same bytes now store them twice.
- 2026-10-21 one image request type instead of five (closes #307): the new
package `internal/imagerequest`, which imports no other package of pixa, holds
`imagerequest.Request` with its two parts, `Source` (host, path and query) and
`Transform` (size, format, quality and fit), the `Format` and `Fit` types, the
checks, the parsing of the `/v1/image/` path and the variant key.
`imgcache.ParsedURL`, `imgcache.ImageRequest`, `signature.Request`,
`imageprocessor.Request`, the second `Size`, format and fit types and the
conversions between them are gone. The image processor takes a `Transform`
only, and `encurl` keeps a private struct with the token's short CBOR field
names, so tokens made before still decode. Every URL of both image routes
answers as before.
- 2026-10-21 the Gitea workflow checks out the repo and runs `script/cibuild`,
nothing else (closes #203): its `script/docker-smoke` step is removed, as the
canonical `REPO_POLICIES.md` says, since `make check` covers what CI needs to
check. CI no longer starts the image and waits for its healthcheck.
`script/docker-smoke` and `make docker-smoke` stay, to run by hand.
- 2026-10-20 a WebP, AVIF or JPEG XL encode at the limits takes at most about 34
seconds (closes #272): with one libvips thread, 8192x8192 random pixels with
an alpha channel took about 61 seconds to encode as WebP, 81 as JPEG XL and,
at quality 85, 96 as AVIF, so with the default `downstream_timeout` of 60
seconds such an image was never delivered, yet its encode held a processing
slot to the end. WebP is now saved at effort 2 and JPEG XL at effort 4, which
take up to about 23 and 27 seconds at any quality. AVIF was already at the
lowest effort govips can set, so an AVIF output of more than 16,777,216 pixels
is refused with 400 before anything is decoded; 4096x4096, 8192x2048 or
2048x8192 takes up to about 34 seconds at any quality. Resizing with
`fit=cover` already decodes the input, so the output's dimensions are worked
out before resizing. `README.md` gives the limit and the new times.
- 2026-10-20 a source whose first bytes do not match its `Content-Type` answers
415 (closes #253): a body whose first bytes are not those of the format its
`Content-Type` names, such as a JPEG sent as `image/png`, text, or a body
under 12 bytes, answered 500 on both image routes and was logged as an error
of pixa's, and each request for it fetched the whole body again. Both routes
now answer 415, and the image service logs it at warning level as a refused
source. It also gets a negative cache entry, as an upstream error status does,
so the source URL is not fetched again for 5 minutes, and meanwhile an image
that would need that fetch answers 502.
- 2026-10-20 `AGENTS.md`: a bug fix may change an existing test without asking
when that test pins exactly the behavior the filed bug calls wrong, and the
change moves it to the fixed behavior and nothing else (closes #280).
- 2026-10-18 re-vendored from `sneak/prompts` commit `0653579` (closes #221):
each `Dockerfile` stage installs its system packages and downloads the Go
modules above `ARG CACHEBUST`, so check builds keep them, and the lint step
keeps golangci-lint's cache.
- 2026-10-19 a `trusted_proxies` entry in the IPv4-mapped form trusted nothing;
it is now read as the IPv4 range it covers by the same code that reads
`blocked_networks`, and such an entry shorter than `/96` aborts startup
(closes #303).
- 2026-10-18 the next reconciliation pass waits at least ten times as long as
the last one took, so passes on a large cache no longer run back to back
(closes #250).
- 2026-10-18 a `blocked_networks` entry in the IPv4-mapped form refused nothing;
`::ffff:10.0.0.0/104` is now read as `10.0.0.0/8`, and such an entry shorter
than `/96` aborts startup (closes #301).
- 2026-10-16 P1 security bug: the check that keeps pixa from fetching internal
addresses refuses the local-use NAT64 range (`64:ff9b:1::/48`, RFC 8215) as it
refuses `64:ff9b::/96`, and refuses an IPv6 address in the IPv4-compatible
form (`::/96`) when `blocked_networks` contains either the address as written
or the IPv4 address it holds (closes #299). A source host such as
`[64:ff9b:1::a00:1]` was fetched, which on a network that runs NAT64 on that
range reaches the IPv4 address it holds, here `10.0.0.1`; and with
`203.0.113.0/24` in `blocked_networks`, `[::ffff:203.0.113.5]` was refused but
`[::203.0.113.5]` was fetched. Both now answer 403. The mapped form
(`::ffff:a.b.c.d`) is still matched only as the IPv4 address it holds: Go
keeps a plain IPv4 address in that form, and an IPv6 entry such as `::/0` must
not refuse every IPv4 address.
- 2026-10-16 P1 security bug: the check that keeps pixa from fetching internal
addresses judges an IPv6 address in the IPv4-compatible form (`::/96`), such
as `::127.0.0.1` or `::10.0.0.1`, by the IPv4 address in its last four bytes
(closes #297). It read only the mapped form (`::ffff:a.b.c.d`) as IPv4, so a
source host such as `[::127.0.0.1]` was checked as a public IPv6 address and
fetched, which on a network that routes it reaches the internal IPv4 host; it
is now refused with 403. The NAT64 form (`64:ff9b::/96`) was already refused
as a whole, as one of the built-in blocked ranges, and still is.
- 2026-10-16 a source host that is an IPv6 address in brackets with no port,
such as `[2001:db8::a]`, is fetched like one with a port, through `/v1/image/`
and through an encrypted URL (closes #295). The fetcher's check of the source
URL kept the brackets when no port followed them, could not look the host up,
and the request answered 500. It now checks the address without brackets, so a
private one is refused with 403, as with a port.
- 2026-10-16 a `state_dir` whose name holds `%`, `?` or `#` keeps its database
at `state.sqlite3` in that directory (closes #290): the `db_url` derived from
it put the name into a `file:` URL as it was, so SQLite read `%41` as `A`, a
`?` or `#` ended the path early, and the journal mode parameter was lost. The
derived `db_url` is now built with Go's `net/url`, which writes those
characters as `%25`, `%3F` and `%23`. For a `state_dir` of `/` or one starting
with `//` it starts `file:////`, so SQLite no longer reads the first name in
the path as a host.
- 2026-10-16 a size with one side `0` keeps the side computed from the source's
proportions at 1 or more (closes #283): it was rounded down, so for a thin
source it came out at 0, and libvips then made the size square. An 8192x1
source at `100x0` came out at 100x100, and at `1300x0` with `fit=cover` made
libvips ask for about 39 GB at once; an 8192x2 source at `100x0` answered 500.
`fit=contain` and `fit=inside` work both sides out again from the smaller of
the two scales and `fit=outside` from the larger, and each keeps both sides at
1 or more too, so a 1x8192 source at `0x100` with `fit=contain`, and a 49x8192
source at `0x100` or a 49x49 source at `1x1` with `fit=outside`, no longer
answer 500. An 8192x1 source at `1300x0` now comes out at 1300x1, and the
process running it alone peaked at about 34 MiB resident. With `fit=outside`
the image is scaled to cover the size, so that source at `100x0` comes out at
8192x1. `README.md` now says this under Signature Specification, and says how
a `0` side is worked out where it said `0` meant the original.
- 2026-10-16 the generator page lower-cases the source host and writes an empty
source path as `/` before it makes the encrypted URL, as `/v1/image/` does
(closes #293). A host written in upper and in lower case, or a source URL with
no path and with the path `/`, made two cache keys and two upstream requests
for one image.
- 2026-10-16 the source URL a request fetches is built with `net/url` from the
source host, path and query, not joined as text (closes #288). The source
path, decoded, is fetched percent-encoded again, so `100%25.png` fetches
`/100%25.png` where it answered 401, and `my%20cat.png` and `my%2520cat.png`
fetch different paths where both fetched `/my%20cat.png` under two cache keys.
The source query stays as the source URL writes it; the characters a browser
percent-encodes in a query, such as `'` or a space, which was sent raw and
answered 502, are percent-encoded when the image URL is read, so the query is
signed and cached as it is sent. The generator page answers 400, showing the
URL pixa would fetch, for a source URL its image URL would fetch written
another way, such as with `%2F` in the path, whatever else the path holds, or
with a user name and password. It also answers 400 for a source path holding a
`..` segment, as `/v1/image/` refuses one.
- 2026-10-15 a thin source requested with `fit=cover` no longer makes libvips
build a huge image (closes #282): libvips' thumbnail scaled the whole source
to cover the requested size and copied that into memory before it cut out the
centre, so an 8192x64 source at 8192x8192 made it allocate about 24 GiB, and
an 8192x1 source answered 500. The image processor now first cuts the centre
of the source, widened to whole source pixels, and thumbnail scales and cuts
only that, by the same amount on both sides as before. What it copies into
memory is then larger than the output by less than one scaled source pixel on
each side. With the runtime image's libvips and JPEG output at 8192x8192,
resident memory peaked at about 242 MiB for the 8192x64 source and 431 MiB for
the 8192x1 one. The output can sit a fraction of an output pixel from where it
was.
- 2026-10-15 a `/v1/image/` URL whose source path or source query holds a `#`,
written as `%23`, is refused with 400 (closes #286): the source URL built from
it ended at the `#` when fetched, so each text after it fetched the same
upstream image, without a signature for an allowlisted host, and cached it
under keys of its own. `README.md` says neither may hold a `#`.
- 2026-10-15 the host of a `/v1/image/` URL must be a host name or an IPv4
address (letters, digits, hyphens, underscores and dots) or an IPv6 address in
brackets, either one optionally followed by `:` and a port, and any other host
is refused with 400 (closes #275): only `@` was refused, so a `?` written as
`%3F` gave the host `cdn.example.com?x=1`, which Go's URL parser reads as
`cdn.example.com` with a query. Such a URL passed the allowlist, and each text
after the `?` fetched the host's root path and cached the answer under keys of
its own. A `#`, `%`, `\` or space written percent-encoded is refused the same
way, and so is an IPv6 address without brackets, which needed a signature
before. Underscores are kept because `allowlist_hosts` accepts host names
holding them.
- 2026-10-15 the README says how a source URL with a query is written into an
image URL, and the image route accepts it (closes #255): the query follows the
source path after `%3F`. pixa now reads the image URL's path decoded once, so
the `?` before the query, any `?` in it and every `%` in the source path or
query must be percent-encoded, and any other character may be. The route used
to parse chi's wildcard, which holds the path as the client wrote it whenever
that is not Go's own encoding of it; a `/`, `;` or `,` in the query written as
`%2F`, `%3B` or `%2C`, as `GenerateSignedURL` wrote them, kept the `%3F` from
being read as `?`, and the request failed with 401. `GenerateSignedURL` now
writes Go's own encoding of the path. The README has an example with a query
and its signature. The path traversal check no longer reads the source query,
and keeps a `%` that does not start a percent-escape as it is instead of
refusing the URL, so a source path or query holding `%25` is accepted, while a
double-encoded `..` next to such a `%` is still refused.
- 2026-10-15 `max_concurrent_processing` defaults to half the CPUs pixa sees,
rounded down, and at least 1 (closes #242): it defaulted to one image per CPU,
and a container with no CPU limit sees every CPU of the host, so on a 48-CPU
host pixa processed 48 images at once, each of which can take about 4.2 GiB.
`config.DefaultMaxConcurrentProcessing` gives the default to the config and to
`imageprocessor.New`; `PIXA_MAX_CONCURRENT_PROCESSING` still overrides it.
"Running under upaas" in `README.md` gives the worst-case memory, measured,
and tells the operator to set `PIXA_MAX_CONCURRENT_PROCESSING` and
`PIXA_UPSTREAM_CONNECTIONS` to fit the container's memory. It also gives the
file libvips writes to `/tmp` for each large source, up to 1 GiB, measured,
which is outside `/var/lib/pixa` and `cache_max_bytes` and is memory where
`/tmp` is a tmpfs.
- 2026-10-15 the canonical files are re-vendored from `sneak/prompts` commit
`e3f79c4` (closes #221): `.dockerignore`, `.editorconfig`,
`.gitea/workflows/check.yml`, `.gitignore`, `.golangci.yml`,
`.prettierignore`, `.prettierrc`, `REPO_POLICIES.md` and the standard scripts
are its copies. pixa's own entries follow the standard part: `/bin`, `/data`
and the local config files in `.dockerignore`; Go's `*.log`, `*.out` and
`*.test`, `vendor/`, the binaries, `/data/`, `*.sqlite3` and the local config
files in `.gitignore`. The workflow keeps its `script/docker-smoke` step while
https://git.eeqj.de/sneak/pixa/issues/203 is open. The scripts pass a new
`CACHEBUST` build argument in place of `--no-cache`, and every `Dockerfile`
stage declares it first, so every `RUN` step still runs on every build while
Go's build cache, mounted on the steps that compile, is kept; both `go test`
runs keep `-count=1`. The lint and test builds write no image. The lint phase
runs golangci-lint v2.14.0, the test phase runs on the Debian Go image, and
the build stage marks `/src` safe for git. `script/bootstrap`, `script/fmt`
and `script/fmt-check` use the node on the `PATH` only when it has the pinned
major version. Of golangci-lint v2.14.0's two findings, an unused `nolint`
directive is removed, and gosec's new path check is marked as not applying to
the fixed config file locations. The agent guidance moves unchanged from
`CLAUDE.md` to a root `AGENTS.md`, where `REPO_POLICIES.md` keeps it.
- 2026-10-15 the request metrics record any method that is not a standard one as
`other` (closes #274): their `method` label was each request's method as sent,
and Go's HTTP server accepts any method name, so a client sending made-up
methods added series to the Prometheus registry that were never removed. The
label is now the request's method only for `GET`, `HEAD`, `POST`, `PUT`,
`PATCH`, `DELETE`, `OPTIONS`, `CONNECT` and `TRACE`. The metrics library reads
the method from the request it is handed, so the metrics middleware hands it a
copy of the request carrying the label; the handlers still see the method the
client sent.
- 2026-10-15 logging out ends every login session (closes #256): a login session
was a cookie with nothing kept on the server, so `/logout` removed it from one
browser and a copy of it kept working for its 30 days. Every login is made
with the one signing key, so logging out now ends them all: the session
manager keeps a random value, made with `crypto/rand` when the new `logout`
table has none and replaced by each logout, saves it there so that it outlasts
a restart, puts the value at login in each session, and refuses a session
carrying another value. The check for a logout compares no time, so a login
after a logout works whatever the host's clock does; a session's 30 days are
still checked against the clock. Losing the state directory ends every login
session, and no logout can make an ended one work again. Logging out is now
`POST /logout` from a form on the generator page, behind the CSRF check the
other forms have, so a link or image elsewhere on the same site cannot end the
sessions. A logout without a valid login session ends none and only removes
the cookie, as anyone can take a CSRF token from the login page. A logout that
cannot be saved answers 500. `session.NewManager`, which the tests use, keeps
the value in memory only; pixad uses `session.NewManagerWithDatabase`.
- 2026-10-15 a cached file left empty or partial is no longer served, or fetched
again on every request (closes #252). Source and transformed image files, and
each transformed image's `.meta` file, are synced to disk before they are
renamed into place, and their directory after; the `.meta` file is written
before the image, and a failed directory sync removes the renamed file. The
reconciliation pass, at startup and every five minutes, removes a cached
source or transformed image whose file is empty, or not the size the database
records for it, with its rows and a warning naming the file, so the next
request fetches the source or converts the image again; requests compare no
sizes. Storing a source over a file of another size replaces that file. A
source that fails to decode is not removed for that alone: a damaged upstream
image would then be fetched on every request.
- 2026-10-15 a transcode stops once its request's `downstream_timeout` has
ended, unless it has begun encoding (closes #243): the image processor looked
at its context only while it waited for a processing slot, so an image was
decoded and encoded, holding the slot, however long after its request's
deadline that took. `Process` now returns the context's error, and gives the
slot back, when the context has ended by the time it has the slot or before it
encodes. A request that waited for a shared transcode stopped at the first
request's deadline is answered 503 `server busy, try again later`, not 500,
though its own `downstream_timeout` may not have ended. govips gives pixa no
way to stop libvips once an encode has begun, so that encode keeps its slot
until it finishes; the limit of 8192 on each side of the source and of the
output bounds how long that takes. With one libvips thread, 8192x8192 random
pixels take up to about 1 second to encode as JPEG, 15 as PNG, 16 as GIF, 63
as WebP, 110 as AVIF and 96 as JPEG XL, the last three with an alpha channel,
plus up to about 11 seconds to decode the source; `README.md` gives these
times and no longer says the work stops when `downstream_timeout` ends. The
settings of the WebP, AVIF and JPEG XL encoders, which can hold a slot past
the default `downstream_timeout` of 60 seconds, are unchanged.
- 2026-10-15 "Running under upaas" in `README.md` tells the operator to set
`PIXA_CACHE_MAX_BYTES` (closes #251): it listed the variable as optional, but
under upaas the volume is a directory on the host's filesystem. The default,
75% of the sum of that filesystem's free space and what the cache holds, and
at least 500 MiB, let one pixa take three quarters or more of the space the
host and every other app had left, and all of it when that was 500 MiB or
less. The section now says so. The default is unchanged.
- 2026-10-15 the request metrics are labelled by route, not by path (closes
#254): their `handler` label was each request's path, so every new path, a 404
or an encrypted URL, added series to the Prometheus registry that were never
removed, and `/metrics` listed every encrypted URL's token. The label is now
the pattern of the chi route the request matches, such as `/v1/image/*`, or
`unmatched` for a request that matches none: one the router answers 404 or
405, or a CORS preflight. The metrics library takes the label before the
request is routed, so the metrics middleware asks the router which route
matches.
- 2026-10-15 expired negative cache rows are removed on a schedule (closes
#244): the row of a failed fetch, which makes pixa answer 502 for that source
URL for 5 minutes, was deleted only when the same URL was requested again
after that, so a client asking for a new missing path each time added rows
that stayed for good. The eviction goroutine now calls `CleanExpired` at
startup and on each periodic tick, every 5 minutes in pixad, so a row stays at
most about 10 minutes. `CleanExpired` deletes at most 1000 rows per statement,
so a request waits behind 1000 deletions at most, however many rows have
expired. The goroutine runs with the disk cache disabled
(`cache_max_bytes: 0`) too, where it does nothing else, as the negative cache
is used either way.
- 2026-10-15 a cached variant is served while its source URL is in the negative
cache (closes #245): `Get` checked the negative cache before the variant
cache, so once a fetch of the source failed, as one does when another variant
misses after the source was evicted and the upstream is down, every variant of
that source answered 502 for 5 minutes, also one on disk or one that could be
made from the cached source. The negative cache is now checked only just
before a fetch from the upstream, so a cached variant is served and a variant
not in the cache is made from the cached source when there is one. `README.md`
says so under `/v1/image/`. A refusal from the negative cache now counts as a
miss, as any other request that misses the variant cache does.
- 2026-10-15 the host of a `/v1/image/` URL is lower-cased, and one with a port
needs a signature (closes #246): with `cdn.example.com` allowlisted,
`CDN.Example.com` and `cdn.example.com:8443` passed the allowlist too, and
each spelling was fetched and cached on its own and had connections of its own
under `upstream_connections_per_host`. The image URL parser now lower-cases
the host and refuses one holding `@`, which a URL reads as a user name and
password, with 400. A host with a port, or with a `:` and no port, needs a
signature even when it is allowlisted. That is checked in the image service,
not in `allowlist.IsAllowed`, which also matches `referer_blocklist`, where a
`Referer` is blocked whatever its port. A URL is signed over its host as it
writes it, in lower case, with any IPv6 brackets, `:` and port kept.
- 2026-10-15 a `:` in the source path or query no longer moves where the path
ends and the query begins (closes #247): the signed data and the cache key
joined host, path and query with `:` and no escaping, so a URL signed for
`https://h/a:b` verified for `https://h/a?b:`; the two also shared a cache
key, and whichever was fetched first was served for both. In both, the path
and the query now have each `%` written as `%25` and each `:` as `%3A`; a path
and query holding neither are signed and keyed as before. Signature
Specification in `README.md` says so.
- 2026-10-15 the example config allowlists no host (closes #249): it allowlisted
`github.com` and `user-images.githubusercontent.com`, where anyone can put an
image, so a deployment set up as Getting Started says served those images to
anyone without a signature, at any size and in any format.
`configs/config.example.yml` now leaves `allowlist_hosts` out, with one
commented entry under `example.com`. Getting Started and "Running under upaas"
in `README.md` say that every image on an allowlisted host is served without a
signature, so an allowlisted host must be one the operator controls.
- 2026-10-15 a chunked upstream body of exactly `upstream_max_response_size`
bytes is accepted (closes #248): once the limit was used up, the fetcher's
next read refused the body without looking for its end. Go's HTTP client
returns the end of a body sent with a `Content-Length` together with its last
bytes, but the end of a chunked body can come in a later read, so such a body
was refused after it had been downloaded whole, and the image routes
answered 500. Once the limit is used up, the fetcher now reads one more byte:
if the body has ended it is accepted, and if there is more it is refused with
`ErrResponseTooLarge`, as before.
- 2026-10-13 `fit=outside` no longer makes an output above 8192 on a side
(closes #257): it scales the image to cover the requested size, and the side
scaled past that size was held to no maximum, so `1x8192?fit=outside` of a
3000x600 source was resized to 40960x8192 and encoded. The image processor now
refuses such a size with `ErrOutputTooLarge` before resizing, and both image
routes answer it 400, as for a size with one side `0`. The other fit modes
make the requested size or one within it, so none can go above 8192.
- 2026-10-13 a size with one side `0` no longer makes an output above 8192 on a
side (closes #241): that side is computed from the source's proportions, and
nothing held it to the 8192 a requested side is held to, so `0x8192` of a
3000x600 source was resized to 40960x8192 and encoded. The image processor now
refuses such a size with `ErrOutputTooLarge` once it knows the source's
dimensions, before resizing, and both image routes answer it 400 with the JSON
error body. The refusal is not cached as a failed fetch, so the same source is
still served at other sizes. `imgcache.MaxDimension` is now the image
processor's `MaxOutputDimension`, so the two cannot differ.
- 2026-10-13 the unused cache lifetime is removed (closes #69):
`CacheConfig.CacheTTL`, which pixad set to `DefaultCacheTTL` (24 hours), was
never read, so cached images never expired. The field and the constant are
removed. Cached source and transformed images stay until eviction removes them
to keep the cache within `cache_max_bytes`.
- 2026-10-13 SVG sources are refused, and `orig` is never saved as JPEG in place
of the source's own format (closes #68): the upstream fetch no longer accepts
`image/svg+xml`, which libvips would render. Both image routes answer 415 for
an upstream `Content-Type` that is not one of the source formats, SVG
included, where they answered 500. Before decoding, the image processor
refuses with `ErrUnsupportedInputFormat`, also answered 415, any input that
govips' `DetermineImageType`, which picks the libvips loader from the first
bytes, does not name as a source format. That catches an SVG whose first bytes
pass the first-bytes check for another type, as an XML comment can make them
do for AVIF; an SVG whose first bytes do not pass that check answers 500, as
before, and so does a damaged image in a source format, whose first bytes
`DetermineImageType` names. `orig` is always the source's own format, where a
source the processor could not name was saved as JPEG. `README.md` no longer
lists SVG. The SVG detection in `internal/magic` stays: the request path does
not call it, and it goes with the unused code of
https://git.eeqj.de/sneak/pixa/issues/168.
- 2026-10-12 per-client limit on the image routes (closes #236): the new setting
`image_requests_per_minute` (`PIXA_IMAGE_REQUESTS_PER_MINUTE`), default 600,
is how many `GET` and `HEAD` requests one client may send to `/v1/image/` and
`/v1/e/` together per minute, cache hits included; the next is answered 429
with `Retry-After`. It uses the login limit's `RateLimit` middleware, so
clients are told apart the same way, and runs after the CORS middleware, so a
preflight is not counted. `0` turns the limit off; a negative or non-integer
value aborts startup.
- 2026-10-08 a request past its deadline no longer waits for the database to
count it (closes #224). On a busy host, `TestService_Get_ReturnsByItsDeadline`
failed because its request, past its deadline, still waited for its miss count
to be written, a write with no deadline, which in pixad waits for the one
database connection every request shares. Each count write now keeps the
request's deadline but not its cancellation. A count not written by then is
kept in memory, where `Stats` sees it, and one goroutine of the cache writes
those counts, one write at a time, and once more at shutdown before the
database closes. The test phase of the `Dockerfile` also runs at most 4 tests
of a package at once (`go test -parallel 4`), where it ran as many as the host
has CPUs: on a busy host they then wait so long to be scheduled that a test
that times a request can fail. `-p`, how many packages are tested at once, is
unchanged, as capping it also slows compiling.
- 2026-10-08 every output format is saved with settings pixa sets on purpose
(closes #232): each format has its own govips export, as JPEG XL does, in
place of govips' generic `Export`, which sent libvips a zero for some settings
it was not given. PNG gets libvips' default compression, 6, where it had none,
and WebP libvips' default effort, 4, where it had 0. GIF was already at
libvips' default effort, 7, and JPEG output is unchanged. AVIF is saved at
effort 1, the lowest govips can set, where it had libvips' default, 4. With
one libvips thread, an 8192x8192 image of random pixels, the worst case, takes
about 51 seconds as AVIF at effort 1 and 43 as WebP at effort 4, against the
default `downstream_timeout` of 60 seconds. On an image of milder noise, which
AVIF at effort 1 saves in about 12 seconds, effort 4 takes minutes. AVIF is
also saved with 8 bits per sample from a 16-bit source, which libvips would
save with 12: a 16-bit 8192x8192 image of milder noise takes about 54 seconds
at effort 1 with 12 bits, nearly all of the default `downstream_timeout`, and
about 12 with 8.
- 2026-10-08 JPEG XL is the default output (closes #222): a `/v1/image/` URL
whose last segment is a size with no format, such as `800x600` or `orig`, is
served as JPEG XL and signed as `jxl`, so it has the signature of the same URL
ending in `.jxl`. An encrypted URL whose token holds no format is served as
JPEG XL (`encurl.DefaultFormat`). The generator page selects JPEG XL until
another format is chosen, and a form with an empty format, or none, makes a
JPEG XL URL whose name ends in `.jxl`. The image processor no longer takes an
empty format as `orig`: both routes give every request a format, and it
refuses a request with none. `auto` still ends with JPEG.
- 2026-10-08 JPEG XL as an input and output format (part of #222): a source
whose bytes start with either JPEG XL signature, the bare codestream's `FF 0A`
or the container's, is detected as `image/jxl`, which the upstream fetch
accepts; `orig` of such a source is JPEG XL. The format `jxl` works in plain
and encrypted URLs and on the generator page, served as `image/jxl` and cached
like the other formats. `auto` chooses JPEG XL first when `Accept` names
`image/jxl`. govips sends libvips a JPEG XL distance with every save, so
libvips ignores the quality: pixa turns `q` into a distance with libvips' own
formula, keeping 100 lossy, and removes the metadata from the image before
saving, as govips cannot have libvips strip it from JPEG XL. libvips 8.16 and
later still write an EXIF block of their own into JPEG XL, from the image's
size, orientation and resolution, and fixed values; the image is upright and
is given 72 dpi before the save, so the block holds nothing from the source.
An image with an ICC profile is converted to sRGB before the JPEG XL save too,
and a CMYK image with none is converted to sRGB, as libvips cannot save CMYK
as JPEG XL. libvips' default effort, 7, is kept. JPEG XL is not yet the
default output.
- 2026-10-08 pixad runs on the Alpine release it is built on (closes #229): the
runtime stage of the `Dockerfile` uses `alpine:3.22`, the release of the
`golang:1.25.4-alpine3.22` image that the test phase and the build stage use,
so all three have libvips 8.16, where the runtime image had 8.15.
- 2026-10-08 requests no longer wait behind eviction queries that read a whole
table (closes #227): the new `cache_usage` table holds the total cache usage,
kept up to date by triggers on `source_content` and `variant_content` in the
statement that adds, removes or resizes a row, and `UsageBytes` reads it. The
reconciliation pass reads the content tables 1000 rows per query, sums them
and corrects the total when it differs, unless a row changed while it summed.
Source rows get `last_accessed_at` when added, so choosing source images to
evict reads that column's index instead of sorting the whole table.
- 2026-10-08 libvips' JPEG XL support is installed and required (part of #222):
`script/bootstrap --cgo` installs `vips-jxl` when its package manager is apk,
as Alpine's `vips` package lacks the support, and the runtime stage of the
@@ -833,11 +365,11 @@ P2: security: per-origin rate limiting
cancellation but keeps its deadline, and the others wait for its image or
error holding no upstream connection or processing slot, and stop waiting when
their own context ends; the request doing the processing waits for it even
then, until it ends, which can be after its deadline; a request whose context
has already ended starts nothing; each request counts one miss, and the
processing counts its fetch and transcode once; a panic while processing is
reported to Sentry when `sentry_dsn` is set and becomes an error for every
waiting request instead of stopping pixad; documented in `README.md`.
then, up to its deadline; a request whose context has already ended starts
nothing; each request counts one miss, and the processing counts its fetch and
transcode once; a panic while processing is reported to Sentry when
`sentry_dsn` is set and becomes an error for every waiting request instead of
stopping pixad; documented in `README.md`.
- 2026-09-29 only the image routes send CORS headers (closes #98): the CORS
middleware, with the `access_control_allow_origin` origin, moved from the
router root onto a `/v1` subrouter holding `/v1/image/` and `/v1/e/`, where it
@@ -1151,6 +683,8 @@ P2: security: per-origin rate limiting
# Future Steps
- P2: security
- per-origin rate limiting
- P2: HTTP response handling
- Last-Modified headers
- P2: configuration
configs/config.example.yml
+10 -18
View File
@@ -45,14 +45,15 @@ state_dir: ./data
signing_key: "CHANGE_ME_generate_with_openssl_rand_base64_32"
# Hosts that don't require signatures (default: none)
# Every image on an allowlisted host is served to anyone without a
# signature, at any size and in any format, so list only hosts you
# control, where nobody else can put images.
# Use "." prefix for wildcard subdomain matching (e.g., ".example.com" matches "cdn.example.com")
# An entry that is neither a host name nor an IP address (IPv6 without
# brackets), such as one with a port or a "*." wildcard, aborts startup.
# allowlist_hosts:
# - images.example.com
allowlist_hosts:
- s3.sneak.cloud
- static.sneak.cloud
- sneak.berlin
- github.com
- user-images.githubusercontent.com
# Hosts whose pages may not show pixa's images, written as for
# allowlist_hosts. A request to /v1/image/ or /v1/e/ whose Referer header
@@ -108,21 +109,12 @@ upstream_connections_per_host: 20
# downstream_timeout has ended first.
upstream_connections: 64
# Maximum number of images decoded and encoded at once (default: half the
# number of CPUs pixa can use, at least 1; the number of CPUs follows a
# container's CPU limit). A request that finds none free waits up to 10
# seconds for one, and if none frees up it is answered 503, unless
# downstream_timeout has ended first.
# Maximum number of images decoded and encoded at once (default: the
# number of CPUs pixa can use, which follows a container's CPU limit). A
# request that finds none free waits up to 10 seconds for one, and if none
# frees up it is answered 503, unless downstream_timeout has ended first.
# max_concurrent_processing: 4
# How many requests to the image routes (/v1/image/ and /v1/e/) one client
# may send per minute; a request over the limit is answered 429 with a
# Retry-After header. 0 turns the limit off. Clients are told apart as for
# the login limit, so behind a CDN or proxy whose addresses are not in
# trusted_proxies all requests arriving from one proxy or CDN address count
# as one client: raise the limit there, or set 0. (default: 600)
image_requests_per_minute: 600
# Time allowed for one fetch from an upstream host (default: 30s)
upstream_fetch_timeout: 30s
go.mod
+1
View File
@@ -14,6 +14,7 @@ require (
github.com/go-chi/httprate v0.16.0
github.com/gorilla/csrf v1.7.3
github.com/gorilla/securecookie v1.1.2
github.com/hashicorp/golang-lru/v2 v2.0.7
github.com/prometheus/client_golang v1.23.2
github.com/slok/go-http-metrics v0.13.0
github.com/spf13/cobra v1.10.2
go.sum
+2
View File
@@ -228,6 +228,8 @@ github.com/hashicorp/go-version v1.2.1/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09
github.com/hashicorp/golang-lru v0.5.0/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
github.com/hashicorp/golang-lru v0.5.4 h1:YDjusn29QI/Das2iO9M0BHnIbxPeyuCHsjMW+lJfyTc=
github.com/hashicorp/golang-lru v0.5.4/go.mod h1:iADmTwqILo4mZ8BN3D2Q6+9jd8WM5uGBxy+E8yxSoD4=
github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
github.com/hashicorp/hcl v1.0.1-vault-7 h1:ag5OxFVy3QYTFTJODRzTKVZ6xvdfLLCA1cy/Y6xGI0I=
github.com/hashicorp/hcl v1.0.1-vault-7/go.mod h1:XYhtn6ijBSAj6n4YqAaf7RBPS4I06AItNorpy+MoQNM=
github.com/hashicorp/logutils v1.0.0/go.mod h1:QIAnNjmIWmVIIkWDTG1z5v++HQmx9WQRO+LraFDTW64=
internal/config/blocked_networks_internal_test.go
-53
View File
@@ -88,56 +88,3 @@ func TestBlockedNetworksInvalidAbortsStartup(t *testing.T) {
},
})
}
// TestBlockedNetworksMappedEntryIsIPv4Range checks that an entry written in
// the IPv4-mapped form (::ffff:a.b.c.d) is kept as the IPv4 range it covers,
// since the fetcher matches an IPv4-mapped address as the IPv4 address it
// holds. /96, the shortest such entry, covers every IPv4 address.
func TestBlockedNetworksMappedEntryIsIPv4Range(t *testing.T) {
t.Parallel()
yamlContent := signingKeyLine + `blocked_networks:
- "::ffff:10.0.0.0/104"
- "::ffff:0:0/96"
`
c, err := configFromYAML(t, yamlContent)
if err != nil {
t.Fatalf("IPv4-mapped blocked_networks entries should load, got error: %v", err)
}
want := []string{"10.0.0.0/8", "0.0.0.0/0"}
if len(c.BlockedNetworks) != len(want) {
t.Fatalf("BlockedNetworks = %v, want %d entries", c.BlockedNetworks, len(want))
}
for i, w := range want {
if got := c.BlockedNetworks[i].String(); got != w {
t.Errorf("BlockedNetworks[%d] = %q, want %q", i, got, w)
}
}
}
// TestBlockedNetworksMappedEntryShorterThan96AbortsStartup checks that an
// entry in the IPv4-mapped form shorter than /96, which covers more than the
// IPv4 addresses, aborts startup with an error naming the key and the value.
func TestBlockedNetworksMappedEntryShorterThan96AbortsStartup(t *testing.T) {
t.Parallel()
runAbortCases(t, []abortCase{
{
name: "mapped-shorter-than-96",
yaml: signingKeyLine + `blocked_networks:
- "::ffff:0.0.0.0/80"
`,
wantErrSubstrings: []string{keyBlockedNetworks, "::ffff:0.0.0.0/80"},
},
{
name: "mapped-95",
yaml: signingKeyLine + `blocked_networks:
- "::ffff:0:0/95"
`,
wantErrSubstrings: []string{keyBlockedNetworks},
},
})
}
internal/config/concurrency_limits_internal_test.go
+5 -52
View File
@@ -1,7 +1,6 @@
package config
import (
"fmt"
"runtime"
"testing"
)
@@ -13,8 +12,8 @@ const (
)
// TestOmittedConcurrencyLimitsUseDefaults checks that an omitted
// max_concurrent_processing is half the CPUs Go uses, and at least 1, and
// an omitted upstream_connections is 64.
// max_concurrent_processing is the number of CPUs Go uses and an omitted
// upstream_connections is 64.
func TestOmittedConcurrencyLimitsUseDefaults(t *testing.T) {
t.Parallel()
@@ -23,9 +22,9 @@ func TestOmittedConcurrencyLimitsUseDefaults(t *testing.T) {
t.Fatalf("minimal config should be valid, got error: %v", err)
}
if c.MaxConcurrentProcessing != max(runtime.GOMAXPROCS(0)/2, 1) {
t.Errorf("MaxConcurrentProcessing = %d, want %d, half the CPUs",
c.MaxConcurrentProcessing, max(runtime.GOMAXPROCS(0)/2, 1))
if c.MaxConcurrentProcessing != runtime.GOMAXPROCS(0) {
t.Errorf("MaxConcurrentProcessing = %d, want %d, one per CPU",
c.MaxConcurrentProcessing, runtime.GOMAXPROCS(0))
}
if c.UpstreamConnections != 64 {
@@ -33,36 +32,6 @@ func TestOmittedConcurrencyLimitsUseDefaults(t *testing.T) {
}
}
// TestOmittedMaxConcurrentProcessingIsHalfTheCPUsAndAtLeastOne checks
// that an omitted max_concurrent_processing is half the CPUs Go uses,
// rounded down, and 1 when Go uses one CPU.
//
//nolint:paralleltest // it sets GOMAXPROCS, which other tests read
func TestOmittedMaxConcurrentProcessingIsHalfTheCPUsAndAtLeastOne(t *testing.T) {
cpusBefore := runtime.GOMAXPROCS(0)
t.Cleanup(func() { runtime.GOMAXPROCS(cpusBefore) })
for _, tc := range []struct{ cpus, want int }{
{1, 1}, {2, 1}, {3, 1}, {8, 4},
} {
runtime.GOMAXPROCS(tc.cpus)
c, err := configFromYAML(t, signingKeyLine)
if err != nil {
t.Fatalf("minimal config should be valid, got error: %v", err)
}
t.Logf("GOMAXPROCS %d: MaxConcurrentProcessing %d",
tc.cpus, c.MaxConcurrentProcessing)
if c.MaxConcurrentProcessing != tc.want {
t.Errorf("GOMAXPROCS %d: MaxConcurrentProcessing = %d, want %d",
tc.cpus, c.MaxConcurrentProcessing, tc.want)
}
}
}
// TestExplicitConcurrencyLimitsAreUsed checks that valid values for the
// two limits are used as given.
func TestExplicitConcurrencyLimitsAreUsed(t *testing.T) {
@@ -191,19 +160,3 @@ func TestConcurrencyLimitsFromEnvironment(t *testing.T) {
})
}
}
// TestInvalidMaxConcurrentProcessingFromEnvironmentAbortsStartup checks
// that a PIXA_MAX_CONCURRENT_PROCESSING that is not a whole number of at
// least 1, an empty one included, aborts startup naming the variable and
// the key instead of taking the default.
func TestInvalidMaxConcurrentProcessingFromEnvironmentAbortsStartup(t *testing.T) {
for _, value := range []string{"", " ", "0.5", "half", "-1", "4 images"} {
t.Run(fmt.Sprintf("value %q", value), func(t *testing.T) {
t.Setenv(testMaxConcurrentProcessingVar, value)
_, err := configFromYAML(t, signingKeyLine)
wantStartupError(t, err,
testMaxConcurrentProcessingVar, keyMaxConcurrentProcessing)
})
}
}
internal/config/config.go
+15 -96
View File
@@ -34,17 +34,8 @@ const (
DefaultUpstreamFetchTimeout = 30 * time.Second
DefaultUpstreamMaxResponseSize = 50 << 20 // 50 MiB
DefaultDownstreamTimeout = 60 * time.Second
DefaultImageRequestsPerMinute = 600
)
// DefaultMaxConcurrentProcessing returns the most images processed at once
// when max_concurrent_processing is omitted: half the CPUs Go uses
// (runtime.GOMAXPROCS(0), which follows a container's CPU limit), rounded
// down, and at least 1.
func DefaultMaxConcurrentProcessing() int {
return max(runtime.GOMAXPROCS(0)/2, 1) //nolint:mnd // half the CPUs
}
// Configuration key names.
const (
keyDebug = "debug"
@@ -70,7 +61,6 @@ const (
keyUpstreamFetchTimeout = "upstream_fetch_timeout"
keyUpstreamMaxResponseSize = "upstream_max_response_size"
keyDownstreamTimeout = "downstream_timeout"
keyImageRequestsPerMinute = "image_requests_per_minute"
)
// placeholderSigningKey is the dummy signing_key shipped in
@@ -91,7 +81,6 @@ var (
errNotABoolean = errors.New("not a boolean")
errNotAStringList = errors.New("not a list of strings")
errNotAValidCIDR = errors.New("not a valid CIDR network")
errMappedTooShort = errors.New("in the IPv4-mapped form but shorter than /96")
errNotAMetricsMap = errors.New("not a map of metrics settings")
errEmptyListEntry = errors.New("list contains an empty entry")
errEmptyEntry = errors.New("contains an empty entry")
@@ -169,11 +158,6 @@ type Config struct {
// of the per-request timeout middleware.
DownstreamTimeout time.Duration
// ImageRequestsPerMinute is how many requests one client may make to
// the image routes per minute; the next is refused with 429 Too Many
// Requests. 0 turns the limit off.
ImageRequestsPerMinute int
// BlockedNetworks are operator-supplied CIDR ranges to refuse in
// addition to the built-in SSRF blocklist. Enforced by the upstream
// fetcher's dialer; the built-in ranges always apply.
@@ -306,8 +290,10 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
keyUpstreamConnectionsPerHost, DefaultUpstreamConnectionsPerHost),
UpstreamConnections: loader.intVal(
keyUpstreamConnections, DefaultUpstreamConnections),
// Decoding and encoding are CPU-bound, so the default is one image
// per CPU Go uses, which follows a container's CPU limit.
MaxConcurrentProcessing: loader.intVal(
keyMaxConcurrentProcessing, DefaultMaxConcurrentProcessing()),
keyMaxConcurrentProcessing, runtime.GOMAXPROCS(0)),
UpstreamFetchTimeout: loader.durationVal(
keyUpstreamFetchTimeout, DefaultUpstreamFetchTimeout),
UpstreamMaxResponseSize: loader.int64Val(
@@ -316,8 +302,6 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
keyAccessControlAllowOrigin, DefaultAccessControlAllowOrigin),
DownstreamTimeout: loader.durationVal(
keyDownstreamTimeout, DefaultDownstreamTimeout),
ImageRequestsPerMinute: loader.intVal(
keyImageRequestsPerMinute, DefaultImageRequestsPerMinute),
CacheMaxBytes: loader.int64Val(keyCacheMaxBytes, 0),
BlockedNetworks: blockedNetworks,
TrustedProxies: trustedProxies,
@@ -327,7 +311,9 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
// The default for an omitted cache_max_bytes is worked out when
// the cache opens; here we only record whether the operator set
// the key explicitly.
_, c.CacheMaxBytesExplicit = lookupValue(sc, keyCacheMaxBytes)
if _, present := lookupValue(sc, keyCacheMaxBytes); present {
c.CacheMaxBytesExplicit = true
}
// Build DBURL from StateDir if not explicitly set. The derived URL
// is a default: it applies only when db_url is omitted, never to an
@@ -339,7 +325,8 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
settingName(keyDBURL), errValueEmpty)
}
c.DBURL = defaultDBURL(c.StateDir)
// The driver sets the journal mode only through a _pragma parameter.
c.DBURL = fmt.Sprintf("file:%s/state.sqlite3?_pragma=journal_mode(WAL)", c.StateDir)
}
if loader.err != nil {
@@ -354,30 +341,6 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
return c, nil
}
// defaultDBURL returns the db_url used when db_url is omitted: the file
// state.sqlite3 in stateDir, in WAL mode, which the driver sets only
// through a _pragma parameter. String() percent-encodes any %, ? or # in
// the directory name, which SQLite decodes back, so the URL names exactly
// this file. OmitHost writes file:/var/lib/pixa/... instead of
// file:///var/lib/pixa/..., and keeps a relative stateDir from being read
// as a host name. The path written into the URL is stateDir followed by
// /state.sqlite3; when it starts with //, as it does for a stateDir of /
// or one starting with //, the empty host is kept, so the URL starts
// file://// and SQLite does not read the first name in the path as a
// host.
func defaultDBURL(stateDir string) string {
dbPath := stateDir + "/state.sqlite3"
dbURL := url.URL{
Scheme: "file",
OmitHost: !strings.HasPrefix(dbPath, "//"),
Path: dbPath,
RawQuery: "_pragma=journal_mode(WAL)",
}
return dbURL.String()
}
// validateKnownKeys rejects configuration files containing keys the
// application does not understand, so typos fail at startup instead of
// being silently ignored, and rejects keys that are explicitly set to
@@ -463,7 +426,7 @@ func isKnownConfigKey(key string) bool {
keyMaxConcurrentProcessing, keyCacheMaxBytes, keyBlockedNetworks,
keyTrustedProxies, keyAccessControlAllowOrigin, keyUpstreamFetchTimeout,
keyUpstreamMaxResponseSize, keyDownstreamTimeout, keyRefererBlocklist,
keyImageRequestsPerMinute, "env":
"env":
return true
}
@@ -498,7 +461,6 @@ func envVarNames() map[string]string {
keyUpstreamFetchTimeout: "PIXA_UPSTREAM_FETCH_TIMEOUT",
keyUpstreamMaxResponseSize: "PIXA_UPSTREAM_MAX_RESPONSE_SIZE",
keyDownstreamTimeout: "PIXA_DOWNSTREAM_TIMEOUT",
keyImageRequestsPerMinute: "PIXA_IMAGE_REQUESTS_PER_MINUTE",
}
}
@@ -651,14 +613,6 @@ func (c *Config) validate() error {
settingName(keyCacheMaxBytes), c.CacheMaxBytes, errMustNotBeNegative)
}
// Zero is valid (it turns the limit off); only negative values are
// rejected.
if c.ImageRequestsPerMinute < 0 {
return fmt.Errorf("%s: value %d %w",
settingName(keyImageRequestsPerMinute), c.ImageRequestsPerMinute,
errMustNotBeNegative)
}
err = c.validateUpstreamMaxResponseSize()
if err != nil {
return err
@@ -671,9 +625,12 @@ func (c *Config) validate() error {
}
}
err = c.validateSentryDSN()
if err != nil {
return err
if c.SentryDSN != "" {
parsed, err := url.Parse(c.SentryDSN)
if err != nil || parsed.Scheme == "" || parsed.Host == "" {
return fmt.Errorf("%s: value %q is %w",
settingName(keySentryDSN), c.SentryDSN, errNotAValidURL)
}
}
if (c.MetricsUsername == "") != (c.MetricsPassword == "") {
@@ -685,22 +642,6 @@ func (c *Config) validate() error {
return c.validateAccessControlAllowOrigin()
}
// validateSentryDSN checks that sentry_dsn, when set, is a URL with a scheme
// and a host.
func (c *Config) validateSentryDSN() error {
if c.SentryDSN == "" {
return nil
}
parsed, err := url.Parse(c.SentryDSN)
if err != nil || parsed.Scheme == "" || parsed.Host == "" {
return fmt.Errorf("%s: value %q is %w",
settingName(keySentryDSN), c.SentryDSN, errNotAValidURL)
}
return nil
}
// validateUpstreamMaxResponseSize checks that upstream_max_response_size
// is from 1 byte to 1 GiB. An upstream response is read whole into
// memory, and the image processor reads one byte past this limit, which
@@ -853,7 +794,6 @@ func loadConfigFile(log *slog.Logger, appName string) (*smartconfig.Config, erro
// one whose path runs through a file, such as under a HOME of
// /dev/null. One that cannot be read or does not parse is a
// fatal startup error.
//nolint:gosec // G703: a fixed config location; HOME is the operator's
_, statErr := os.Stat(cleanPath)
if errors.Is(statErr, fs.ErrNotExist) || errors.Is(statErr, syscall.ENOTDIR) {
continue
@@ -1249,13 +1189,6 @@ func defaultTrustedProxies() []netip.Prefix {
// wrong type, an empty entry, a non-string entry, or an unparseable CIDR
// aborts startup naming the key and the offending value; the default
// (an empty list) applies only to an omitted key.
//
// An entry written in the IPv4-mapped form (::ffff:a.b.c.d) is kept as the
// IPv4 range it covers: ::ffff:10.0.0.0/104 is kept as 10.0.0.0/8. Both
// blocked_networks and trusted_proxies are matched against an IPv4-mapped
// address as the IPv4 address it holds, so the entry as written would match
// nothing. Such an entry shorter than /96 covers more than the IPv4
// addresses and aborts startup.
func parseCIDRList(sc *smartconfig.Config, key string) ([]netip.Prefix, error) {
raw, ok := lookupValue(sc, key)
if !ok {
@@ -1271,10 +1204,6 @@ func parseCIDRList(sc *smartconfig.Config, key string) ([]netip.Prefix, error) {
return nil, err
}
// An IPv4-mapped address is the 96 bits of ::ffff:0:0/96 followed by
// the 32 bits of the IPv4 address it holds.
const mappedPrefixBits = 96
prefixes := make([]netip.Prefix, 0, len(entries))
for _, entry := range entries {
@@ -1284,16 +1213,6 @@ func parseCIDRList(sc *smartconfig.Config, key string) ([]netip.Prefix, error) {
settingName(key), entry, errNotAValidCIDR)
}
if prefix.Addr().Is4In6() && prefix.Bits() < mappedPrefixBits {
return nil, fmt.Errorf("%s: value %q is %w",
settingName(key), entry, errMappedTooShort)
}
if prefix.Addr().Is4In6() {
prefix = netip.PrefixFrom(prefix.Addr().Unmap(),
prefix.Bits()-mappedPrefixBits)
}
prefixes = append(prefixes, prefix)
}
internal/config/config_internal_test.go
-26
View File
@@ -92,32 +92,6 @@ func TestGetStringSlice_Empty(t *testing.T) {
}
}
// TestExampleConfigAllowlistsNoHost loads configs/config.example.yml
// with a real signing key, as Getting Started in README.md has it copied
// and edited, and checks that it allowlists no host: every image on an
// allowlisted host is served to anyone without a signature.
func TestExampleConfigAllowlistsNoHost(t *testing.T) {
t.Setenv("PIXA_SIGNING_KEY", validTestSigningKey)
examplePath := filepath.Join("..", "..", "configs", "config.example.yml")
sc, err := loadTestConfig(examplePath)
if err != nil {
t.Fatalf("failed to load %s: %v", examplePath, err)
}
c, err := newFromSmartConfig(sc)
if err != nil {
t.Fatalf("%s is not a valid config: %v", examplePath, err)
}
t.Logf("allowlist_hosts in %s: %v", examplePath, c.AllowlistHosts)
if len(c.AllowlistHosts) != 0 {
t.Errorf("%s allowlists %v, want no host", examplePath, c.AllowlistHosts)
}
}
// loadTestConfig is a helper to load a config file for testing.
func loadTestConfig(path string) (*smartconfig.Config, error) {
return smartconfig.NewFromConfigPath(path)
internal/config/config_validation_internal_test.go
-98
View File
@@ -135,104 +135,6 @@ func TestDefaultDBURLOpensTheDatabaseInWALMode(t *testing.T) {
}
}
// TestDerivedDBURLOpensStateDirHoldingURLCharacters opens the db_url
// derived from a state_dir whose name holds %41, ? and #, and checks that
// the database is state.sqlite3 in that directory, in WAL mode. Put into
// a file: URL as it is, the name would lose its meaning: %41 is read as
// A, and the path ends at the ?, which also loses the journal mode.
func TestDerivedDBURLOpensStateDirHoldingURLCharacters(t *testing.T) {
t.Parallel()
stateDir := filepath.Join(t.TempDir(), "a%41b?c#d")
err := os.Mkdir(stateDir, 0o750)
if err != nil {
t.Fatalf("failed to create %q: %v", stateDir, err)
}
// Quoted so YAML takes the whole name as it is.
c, err := configFromYAML(t, signingKeyLine+"state_dir: '"+stateDir+"'\n")
if err != nil {
t.Fatalf("config with state_dir %q should be valid, got: %v", stateDir, err)
}
t.Logf("state_dir %q gives db_url %q", stateDir, c.DBURL)
checkDBURLOpensFileInWALMode(t, c.DBURL, filepath.Join(stateDir, "state.sqlite3"))
}
// TestDerivedDBURLOpensStateDirStartingWithTwoSlashes opens the db_url
// derived from a state_dir that starts with //, and checks that the
// database is state.sqlite3 in that directory, in WAL mode. Written right
// after file:, such a name gives a URL starting file://, and SQLite reads
// the first directory name as a host and refuses to open it.
func TestDerivedDBURLOpensStateDirStartingWithTwoSlashes(t *testing.T) {
t.Parallel()
dir := t.TempDir()
stateDir := "/" + dir
c, err := configFromYAML(t, signingKeyLine+"state_dir: "+stateDir+"\n")
if err != nil {
t.Fatalf("config with state_dir %q should be valid, got: %v", stateDir, err)
}
t.Logf("state_dir %q gives db_url %q", stateDir, c.DBURL)
checkDBURLOpensFileInWALMode(t, c.DBURL, filepath.Join(dir, "state.sqlite3"))
}
// TestDerivedDBURLForRootStateDir checks the db_url derived from a
// state_dir of /. The path written into the URL is then
// //state.sqlite3, and written right after file: it gives a URL starting
// file://, where SQLite reads state.sqlite3 as a host and refuses to open
// it. The test only checks the URL, since it cannot write to /.
func TestDerivedDBURLForRootStateDir(t *testing.T) {
t.Parallel()
c, err := configFromYAML(t, signingKeyLine+"state_dir: /\n")
if err != nil {
t.Fatalf("config with state_dir / should be valid, got: %v", err)
}
t.Logf("state_dir / gives db_url %q", c.DBURL)
wantDBURL := "file:////state.sqlite3?_pragma=journal_mode(WAL)"
if c.DBURL != wantDBURL {
t.Errorf("DBURL = %q, want %q", c.DBURL, wantDBURL)
}
}
// checkDBURLOpensFileInWALMode opens dbURL with the SQLite driver pixad
// uses, and checks that the database is in WAL mode and is the file
// dbFile.
func checkDBURLOpensFileInWALMode(t *testing.T, dbURL, dbFile string) {
t.Helper()
db, err := sql.Open("sqlite", dbURL)
if err != nil {
t.Fatalf("failed to open %q: %v", dbURL, err)
}
t.Cleanup(func() { _ = db.Close() })
var journalMode string
err = db.QueryRowContext(t.Context(), "PRAGMA journal_mode").Scan(&journalMode)
if err != nil {
t.Fatalf("failed to read the journal mode of %q: %v", dbURL, err)
}
if journalMode != "wal" {
t.Errorf("journal mode of %q = %q, want wal", dbURL, journalMode)
}
_, err = os.Stat(dbFile)
if err != nil {
t.Errorf("opening %q did not create %q: %v", dbURL, dbFile, err)
}
}
func TestExplicitValidValuesAreUsed(t *testing.T) {
t.Parallel()
internal/config/env_internal_test.go
-2
View File
@@ -70,7 +70,6 @@ func TestEnvironmentSetsEveryKey(t *testing.T) {
t.Setenv("PIXA_UPSTREAM_CONNECTIONS_PER_HOST", "5")
t.Setenv("PIXA_UPSTREAM_CONNECTIONS", "10")
t.Setenv("PIXA_MAX_CONCURRENT_PROCESSING", "3")
t.Setenv("PIXA_IMAGE_REQUESTS_PER_MINUTE", "30")
t.Setenv("PIXA_CACHE_MAX_BYTES", "1024")
t.Setenv("PIXA_BLOCKED_NETWORKS", "203.0.113.0/24")
t.Setenv("PIXA_TRUSTED_PROXIES", "192.0.2.0/24")
@@ -100,7 +99,6 @@ func TestEnvironmentSetsEveryKey(t *testing.T) {
UpstreamConnectionsPerHost: 5,
UpstreamConnections: 10,
MaxConcurrentProcessing: 3,
ImageRequestsPerMinute: 30,
CacheMaxBytes: 1024,
CacheMaxBytesExplicit: true,
BlockedNetworks: []netip.Prefix{netip.MustParsePrefix("203.0.113.0/24")},
internal/config/image_requests_per_minute_internal_test.go
-107
View File
@@ -1,107 +0,0 @@
package config
import "testing"
// testImageRequestsPerMinuteVar is the variable that sets
// image_requests_per_minute.
const testImageRequestsPerMinuteVar = "PIXA_IMAGE_REQUESTS_PER_MINUTE"
// TestImageRequestsPerMinuteValues checks that an omitted
// image_requests_per_minute is 600, and that 0, which turns the limit off,
// and any larger whole number are used as given.
func TestImageRequestsPerMinuteValues(t *testing.T) {
t.Parallel()
c, err := configFromYAML(t, signingKeyLine)
if err != nil {
t.Fatalf("minimal config should be valid, got error: %v", err)
}
if c.ImageRequestsPerMinute != 600 {
t.Errorf("ImageRequestsPerMinute = %d, want 600", c.ImageRequestsPerMinute)
}
explicit := []struct {
value string
want int
}{
{"0", 0},
{"30", 30},
}
for _, tc := range explicit {
c, err := configFromYAML(t,
signingKeyLine+"image_requests_per_minute: "+tc.value+"\n")
if err != nil {
t.Fatalf("image_requests_per_minute: %s should load, got error: %v",
tc.value, err)
}
if c.ImageRequestsPerMinute != tc.want {
t.Errorf("ImageRequestsPerMinute = %d, want %d",
c.ImageRequestsPerMinute, tc.want)
}
}
}
// TestInvalidImageRequestsPerMinuteAbortsStartup checks that a value that is
// negative, not a whole number, or null aborts startup naming the key and
// the value, and the variable too where the value could have come from it.
func TestInvalidImageRequestsPerMinuteAbortsStartup(t *testing.T) {
t.Parallel()
key := keyImageRequestsPerMinute
runAbortCases(t, []abortCase{
{
name: "negative",
yaml: signingKeyLine + key + ": -1\n",
wantErrSubstrings: []string{
key, testImageRequestsPerMinuteVar, "value -1",
},
},
{
name: "not a number",
yaml: signingKeyLine + key + ": plenty\n",
wantErrSubstrings: []string{
key, testImageRequestsPerMinuteVar, "plenty",
},
},
{
name: "fractional",
yaml: signingKeyLine + key + ": 2.5\n",
wantErrSubstrings: []string{key, "2.5"},
},
{
name: "explicit null",
yaml: signingKeyLine + key + ": null\n",
wantErrSubstrings: []string{key, nullValueText},
},
})
}
// TestImageRequestsPerMinuteFromEnvironment checks that the variable sets the
// limit over the config file, and that an invalid value in it aborts startup
// naming the variable and the value.
func TestImageRequestsPerMinuteFromEnvironment(t *testing.T) {
t.Setenv(testImageRequestsPerMinuteVar, "0")
c, err := configFromYAML(t, signingKeyLine+"image_requests_per_minute: 30\n")
if err != nil {
t.Fatalf("limit from the environment should load: %v", err)
}
if c.ImageRequestsPerMinute != 0 {
t.Errorf("ImageRequestsPerMinute = %d, want 0 from the environment",
c.ImageRequestsPerMinute)
}
for _, value := range []string{"-5", "ten"} {
t.Run(value, func(t *testing.T) {
t.Setenv(testImageRequestsPerMinuteVar, value)
_, err := configFromYAML(t, signingKeyLine)
wantStartupError(t, err, testImageRequestsPerMinuteVar, value)
})
}
}
internal/config/trusted_proxies_internal_test.go
-38
View File
@@ -83,41 +83,3 @@ func TestTrustedProxiesInvalidAbortsStartup(t *testing.T) {
},
})
}
// TestTrustedProxiesMappedEntryIsIPv4Range checks that an entry written in
// the IPv4-mapped form (::ffff:a.b.c.d) is kept as the IPv4 range it covers,
// since the client address is matched as the IPv4 address it holds. /96, the
// shortest such entry, covers every IPv4 address.
func TestTrustedProxiesMappedEntryIsIPv4Range(t *testing.T) {
t.Parallel()
c, err := configFromYAML(t, signingKeyLine+
`trusted_proxies: ["::ffff:10.0.0.0/104", "::ffff:0:0/96"]`+"\n")
if err != nil {
t.Fatalf("IPv4-mapped trusted_proxies entries should load: %v", err)
}
got := make([]string, len(c.TrustedProxies))
for i, p := range c.TrustedProxies {
got[i] = p.String()
}
if joined := strings.Join(got, ","); joined != "10.0.0.0/8,0.0.0.0/0" {
t.Errorf("TrustedProxies = %v, want 10.0.0.0/8 and 0.0.0.0/0", got)
}
}
// TestTrustedProxiesMappedEntryShorterThan96AbortsStartup checks that an
// entry in the IPv4-mapped form shorter than /96, which covers more than the
// IPv4 addresses, aborts startup with an error naming the key and the value.
func TestTrustedProxiesMappedEntryShorterThan96AbortsStartup(t *testing.T) {
t.Parallel()
runAbortCases(t, []abortCase{
{
name: "mapped-95",
yaml: signingKeyLine + `trusted_proxies: ["::ffff:0:0/95"]` + "\n",
wantErrSubstrings: []string{keyTrustedProxies, "::ffff:0:0/95"},
},
})
}
internal/database/concurrent_writes_internal_test.go
+2 -2
View File
@@ -131,13 +131,13 @@ func writeLikeOneRequest(ctx context.Context, db *sql.DB, key string) error {
}
_, err = db.ExecContext(ctx, `INSERT INTO source_content
(source_key, size_bytes) VALUES (?, 1)`, key)
(content_hash, content_type, size_bytes) VALUES (?, 'image/png', 1)`, key)
if err != nil {
return fmt.Errorf("storing a source: %w", err)
}
_, err = db.ExecContext(ctx, `INSERT INTO variant_content
(cache_key, size_bytes) VALUES (?, 1)`, key)
(cache_key, size_bytes, content_type) VALUES (?, 1, 'image/png')`, key)
if err != nil {
return fmt.Errorf("recording a transformed image: %w", err)
}
internal/database/database_internal_test.go
+4 -1
View File
@@ -159,7 +159,10 @@ func TestApplyMigrations_CreatesSchemaAndTables(t *testing.T) {
}
// Verify that the application tables created by 001.sql exist.
tables := []string{"source_content", "negative_cache", "cache_stats"}
tables := []string{
"source_content", "source_metadata", "output_content",
"request_cache", "negative_cache", "cache_stats",
}
for _, table := range tables {
var count int
internal/db/migrations/001_schema.sql
+71 -87
View File
@@ -1,108 +1,100 @@
-- Migration 001: Initial schema
-- Creates all tables for the pixa caching image proxy
-- Source images, one row per source URL
-- Files stored at: cache/sources/<ab>/<cd>/<source_key>, where source_key
-- is the SHA-256 of the source's host, path and query
-- Source content blobs
-- Files stored at: cache/sources/<ab>/<cd>/<sha256>
-- last_accessed_at is NULL until the first LRU touch; eviction falls
-- back to fetched_at for rows that have never been touched.
CREATE TABLE IF NOT EXISTS source_content (
source_key TEXT PRIMARY KEY,
content_hash TEXT PRIMARY KEY,
content_type TEXT NOT NULL,
size_bytes INTEGER NOT NULL,
last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
last_accessed_at DATETIME
);
CREATE INDEX IF NOT EXISTS idx_source_content_last_accessed
ON source_content(last_accessed_at);
-- Source URL metadata - maps URLs to content hashes
-- JSON stored at: cache/metadata/<hostname>/<path_hash>.json
CREATE TABLE IF NOT EXISTS source_metadata (
id INTEGER PRIMARY KEY AUTOINCREMENT,
source_host TEXT NOT NULL,
source_path TEXT NOT NULL,
source_query TEXT NOT NULL DEFAULT '',
path_hash TEXT NOT NULL,
content_hash TEXT,
status_code INTEGER NOT NULL,
content_type TEXT,
response_headers TEXT,
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
expires_at DATETIME,
etag TEXT,
last_modified TEXT,
UNIQUE(source_host, source_path, source_query),
FOREIGN KEY (content_hash) REFERENCES source_content(content_hash)
);
CREATE INDEX IF NOT EXISTS idx_source_meta_host ON source_metadata(source_host);
CREATE INDEX IF NOT EXISTS idx_source_meta_path_hash ON source_metadata(path_hash);
CREATE INDEX IF NOT EXISTS idx_source_meta_expires ON source_metadata(expires_at);
CREATE INDEX IF NOT EXISTS idx_source_meta_content_hash ON source_metadata(content_hash);
-- Processed variant blobs
-- Files stored at: cache/variants/<ab>/<cd>/<cache_key>. Tracked here
-- (like source content blobs above) so total cache usage is known
-- without a directory scan, and so LRU eviction has a timestamp to order
-- on. A cache hit does not read this table: it takes the content type
-- from the file's first bytes, and its last_accessed_at is written
-- later, in a batch.
-- Files stored at: cache/variants/<ab>/<cd>/<cache_key> (plus a .meta
-- sidecar with the content type). Tracked here (like source content
-- blobs above) so total cache usage can be computed with a SUM query,
-- never a directory scan, and so LRU eviction has a timestamp to order
-- on.
CREATE TABLE IF NOT EXISTS variant_content (
cache_key TEXT PRIMARY KEY,
size_bytes INTEGER NOT NULL,
content_type TEXT NOT NULL,
created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
);
CREATE INDEX IF NOT EXISTS idx_variant_content_last_accessed
ON variant_content(last_accessed_at);
-- Total cache usage: the sum of size_bytes over source_content and
-- variant_content, kept by the triggers below in the same statement
-- that adds, removes or resizes a row, so eviction reads this one row
-- instead of summing both tables. Each trigger also adds one to
-- change_count; the reconciliation pass, which sums both tables a page
-- at a time, corrects total_size_bytes only if change_count did not
-- move while it summed.
CREATE TABLE IF NOT EXISTS cache_usage (
id INTEGER PRIMARY KEY CHECK (id = 1),
total_size_bytes INTEGER NOT NULL DEFAULT 0,
change_count INTEGER NOT NULL DEFAULT 0
-- Output/transformed content blobs
-- Not written: transformed images are stored in cache/variants and
-- tracked in variant_content above.
CREATE TABLE IF NOT EXISTS output_content (
content_hash TEXT PRIMARY KEY,
content_type TEXT NOT NULL,
size_bytes INTEGER NOT NULL,
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO cache_usage (id) VALUES (1);
CREATE TRIGGER IF NOT EXISTS source_content_usage_insert
AFTER INSERT ON source_content
BEGIN
UPDATE cache_usage
SET total_size_bytes = total_size_bytes + NEW.size_bytes,
change_count = change_count + 1
WHERE id = 1;
END;
-- Request cache - maps full request params to output content
CREATE TABLE IF NOT EXISTS request_cache (
id INTEGER PRIMARY KEY AUTOINCREMENT,
cache_key TEXT NOT NULL UNIQUE,
source_metadata_id INTEGER NOT NULL,
output_hash TEXT NOT NULL,
width INTEGER NOT NULL,
height INTEGER NOT NULL,
format TEXT NOT NULL,
quality INTEGER NOT NULL DEFAULT 85,
fit_mode TEXT NOT NULL DEFAULT 'cover',
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
access_count INTEGER NOT NULL DEFAULT 1,
FOREIGN KEY (source_metadata_id) REFERENCES source_metadata(id),
FOREIGN KEY (output_hash) REFERENCES output_content(content_hash)
);
CREATE INDEX IF NOT EXISTS idx_request_cache_key ON request_cache(cache_key);
CREATE INDEX IF NOT EXISTS idx_request_cache_source ON request_cache(source_metadata_id);
CREATE INDEX IF NOT EXISTS idx_request_cache_output ON request_cache(output_hash);
CREATE INDEX IF NOT EXISTS idx_request_cache_fetched ON request_cache(fetched_at);
CREATE TRIGGER IF NOT EXISTS source_content_usage_delete
AFTER DELETE ON source_content
BEGIN
UPDATE cache_usage
SET total_size_bytes = total_size_bytes - OLD.size_bytes,
change_count = change_count + 1
WHERE id = 1;
END;
CREATE TRIGGER IF NOT EXISTS source_content_usage_update
AFTER UPDATE OF size_bytes ON source_content
BEGIN
UPDATE cache_usage
SET total_size_bytes = total_size_bytes - OLD.size_bytes + NEW.size_bytes,
change_count = change_count + 1
WHERE id = 1;
END;
CREATE TRIGGER IF NOT EXISTS variant_content_usage_insert
AFTER INSERT ON variant_content
BEGIN
UPDATE cache_usage
SET total_size_bytes = total_size_bytes + NEW.size_bytes,
change_count = change_count + 1
WHERE id = 1;
END;
CREATE TRIGGER IF NOT EXISTS variant_content_usage_delete
AFTER DELETE ON variant_content
BEGIN
UPDATE cache_usage
SET total_size_bytes = total_size_bytes - OLD.size_bytes,
change_count = change_count + 1
WHERE id = 1;
END;
CREATE TRIGGER IF NOT EXISTS variant_content_usage_update
AFTER UPDATE OF size_bytes ON variant_content
BEGIN
UPDATE cache_usage
SET total_size_bytes = total_size_bytes - OLD.size_bytes + NEW.size_bytes,
change_count = change_count + 1
WHERE id = 1;
END;
-- Negative cache: source URLs whose fetch failed with an upstream error
-- status, or whose first bytes did not match their Content-Type. pixa does
-- not fetch such a URL again until its row expires.
-- Negative cache for failed fetches (404s, timeouts, etc.)
CREATE TABLE IF NOT EXISTS negative_cache (
id INTEGER PRIMARY KEY AUTOINCREMENT,
source_host TEXT NOT NULL,
source_path TEXT NOT NULL,
source_query TEXT NOT NULL DEFAULT '',
status_code INTEGER NOT NULL,
error_message TEXT,
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
expires_at DATETIME NOT NULL,
UNIQUE(source_host, source_path, source_query)
);
@@ -119,11 +111,3 @@ CREATE TABLE IF NOT EXISTS cache_stats (
last_updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO cache_stats (id) VALUES (1);
-- A random value that a login session carries from its login. pixa makes it
-- when the table has no row, and each logout replaces it; a login session
-- carrying another value is refused, so logging out ends every login session.
CREATE TABLE IF NOT EXISTS logout (
id INTEGER PRIMARY KEY CHECK (id = 1),
logout_value TEXT NOT NULL
);
internal/encurl/encurl.go
+65 -52
View File
@@ -7,15 +7,15 @@ import (
"github.com/fxamacker/cbor/v2"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/seal"
)
// Default values for optional fields.
const (
DefaultQuality = 85
DefaultFormat = imagerequest.FormatJXL
DefaultFitMode = imagerequest.FitCover
DefaultFormat = imgcache.FormatOriginal
DefaultFitMode = imgcache.FitCover
// HKDF salt for URL encryption key derivation
urlKeySalt = "pixa-urlenc-v1"
@@ -28,19 +28,19 @@ var (
ErrDecryptFailed = errors.New("failed to decrypt URL")
)
// payload contains all image request parameters in a compact format.
// Payload contains all image request parameters in a compact format.
// Field names are short to minimize encoded size.
// Fields with omitempty use sane defaults when absent.
type payload struct {
SourceHost string `cbor:"h"` // required
SourcePath string `cbor:"p"` // required
SourceQuery string `cbor:"q,omitempty"` // optional
Width int `cbor:"w,omitempty"` // 0 = original
Height int `cbor:"ht,omitempty"` // 0 = original
Format imagerequest.Format `cbor:"f,omitempty"` // default: jxl
Quality int `cbor:"ql,omitempty"` // default: 85
FitMode imagerequest.Fit `cbor:"fm,omitempty"` // default: cover
ExpiresAt int64 `cbor:"e,omitempty"` // 0 = never expires
type Payload struct {
SourceHost string `cbor:"h"` // required
SourcePath string `cbor:"p"` // required
SourceQuery string `cbor:"q,omitempty"` // optional
Width int `cbor:"w,omitempty"` // 0 = original
Height int `cbor:"ht,omitempty"` // 0 = original
Format imgcache.ImageFormat `cbor:"f,omitempty"` // default: orig
Quality int `cbor:"ql,omitempty"` // default: 85
FitMode imgcache.FitMode `cbor:"fm,omitempty"` // default: cover
ExpiresAt int64 `cbor:"e,omitempty"` // 0 = never expires
}
// Generator creates and parses encrypted URL tokens.
@@ -59,27 +59,9 @@ func NewGenerator(signingKey string) (*Generator, error) {
return &Generator{key: key}, nil
}
// Generate creates an encrypted URL token from the request's source,
// transform and expiry, each as the request holds it; an empty format, a
// quality of 0 or an empty fit mode is left out of the token, and a zero
// Expires makes a token that never expires. The token is CBOR-encoded,
// encrypted with NaCl secretbox, and base64url-encoded.
func (g *Generator) Generate(req *imagerequest.Request) (string, error) {
p := &payload{
SourceHost: req.Source.Host,
SourcePath: req.Source.Path,
SourceQuery: req.Source.Query,
Width: req.Transform.Size.Width,
Height: req.Transform.Size.Height,
Format: req.Transform.Format,
Quality: req.Transform.Quality,
FitMode: req.Transform.FitMode,
}
if !req.Expires.IsZero() {
p.ExpiresAt = req.Expires.Unix()
}
// Generate creates an encrypted URL token from the payload.
// The token is CBOR-encoded, encrypted with NaCl secretbox, and base64url-encoded.
func (g *Generator) Generate(p *Payload) (string, error) {
// CBOR encode the payload
data, err := cbor.Marshal(p)
if err != nil {
@@ -90,11 +72,9 @@ func (g *Generator) Generate(req *imagerequest.Request) (string, error) {
return seal.Encrypt(g.key, data)
}
// Parse decrypts and validates an encrypted URL token and returns the
// request it holds, with default values for omitted optional fields. A token
// that never expires gives the zero Expires.
// Parse decrypts and validates an encrypted URL token.
// Returns ErrExpired if the token has expired, or other errors for invalid tokens.
func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
func (g *Generator) Parse(token string) (*Payload, error) {
// Decrypt
data, err := seal.Decrypt(g.key, token)
if err != nil {
@@ -107,7 +87,7 @@ func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
}
// CBOR decode
var p payload
var p Payload
err = cbor.Unmarshal(data, &p)
if err != nil {
@@ -119,6 +99,13 @@ func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
return nil, ErrExpired
}
return &p, nil
}
// ToImageRequest converts the payload to an ImageRequest.
// Applies default values for omitted optional fields. An ExpiresAt of 0, a URL
// that never expires, gives the zero Expires.
func (p *Payload) ToImageRequest() *imgcache.ImageRequest {
format := p.Format
if format == "" {
format = DefaultFormat
@@ -139,18 +126,44 @@ func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
expires = time.Unix(p.ExpiresAt, 0)
}
return &imagerequest.Request{
Source: imagerequest.Source{
Host: p.SourceHost,
Path: p.SourcePath,
Query: p.SourceQuery,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: p.Width, Height: p.Height},
Format: format,
Quality: quality,
FitMode: fitMode,
return &imgcache.ImageRequest{
SourceHost: p.SourceHost,
SourcePath: p.SourcePath,
SourceQuery: p.SourceQuery,
Size: imgcache.Size{
Width: p.Width,
Height: p.Height,
},
Format: format,
Quality: quality,
FitMode: fitMode,
Expires: expires,
}, nil
}
}
// FromImageRequest creates a Payload from an ImageRequest with the given expiration.
func FromImageRequest(req *imgcache.ImageRequest, expiresAt time.Time) *Payload {
p := &Payload{
SourceHost: req.SourceHost,
SourcePath: req.SourcePath,
SourceQuery: req.SourceQuery,
Width: req.Size.Width,
Height: req.Size.Height,
ExpiresAt: expiresAt.Unix(),
}
// Only set non-default values to benefit from omitempty
if req.Format != "" && req.Format != DefaultFormat {
p.Format = req.Format
}
if req.Quality != 0 && req.Quality != DefaultQuality {
p.Quality = req.Quality
}
if req.FitMode != "" && req.FitMode != DefaultFitMode {
p.FitMode = req.FitMode
}
return p
}
internal/encurl/encurl_test.go
+174 -91
View File
@@ -6,7 +6,7 @@ import (
"time"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
// Shared test fixture strings.
@@ -24,22 +24,19 @@ func TestGenerator_GenerateAndParse(t *testing.T) {
t.Fatalf("NewGenerator() error = %v", err)
}
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: testSourceHost,
Path: testSourcePath,
Query: testSourceQuery,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 800, Height: 600},
Format: imagerequest.FormatWebP,
Quality: 90,
FitMode: imagerequest.FitContain,
},
Expires: time.Now().Add(time.Hour),
payload := &encurl.Payload{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
SourceQuery: testSourceQuery,
Width: 800,
Height: 600,
Format: imgcache.FormatWebP,
Quality: 90,
FitMode: imgcache.FitContain,
ExpiresAt: time.Now().Add(time.Hour).Unix(),
}
token, err := gen.Generate(req)
token, err := gen.Generate(payload)
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
@@ -54,45 +51,40 @@ func TestGenerator_GenerateAndParse(t *testing.T) {
}
// Verify all fields
if parsed.Source.Host != req.Source.Host {
t.Errorf("SourceHost = %q, want %q", parsed.Source.Host, req.Source.Host)
if parsed.SourceHost != payload.SourceHost {
t.Errorf("SourceHost = %q, want %q", parsed.SourceHost, payload.SourceHost)
}
if parsed.Source.Path != req.Source.Path {
t.Errorf("SourcePath = %q, want %q", parsed.Source.Path, req.Source.Path)
if parsed.SourcePath != payload.SourcePath {
t.Errorf("SourcePath = %q, want %q", parsed.SourcePath, payload.SourcePath)
}
if parsed.Source.Query != req.Source.Query {
t.Errorf("SourceQuery = %q, want %q", parsed.Source.Query, req.Source.Query)
if parsed.SourceQuery != payload.SourceQuery {
t.Errorf("SourceQuery = %q, want %q", parsed.SourceQuery, payload.SourceQuery)
}
if parsed.Transform.Size.Width != req.Transform.Size.Width {
t.Errorf("Width = %d, want %d",
parsed.Transform.Size.Width, req.Transform.Size.Width)
if parsed.Width != payload.Width {
t.Errorf("Width = %d, want %d", parsed.Width, payload.Width)
}
if parsed.Transform.Size.Height != req.Transform.Size.Height {
t.Errorf("Height = %d, want %d",
parsed.Transform.Size.Height, req.Transform.Size.Height)
if parsed.Height != payload.Height {
t.Errorf("Height = %d, want %d", parsed.Height, payload.Height)
}
if parsed.Transform.Format != req.Transform.Format {
t.Errorf("Format = %q, want %q",
parsed.Transform.Format, req.Transform.Format)
if parsed.Format != payload.Format {
t.Errorf("Format = %q, want %q", parsed.Format, payload.Format)
}
if parsed.Transform.Quality != req.Transform.Quality {
t.Errorf("Quality = %d, want %d",
parsed.Transform.Quality, req.Transform.Quality)
if parsed.Quality != payload.Quality {
t.Errorf("Quality = %d, want %d", parsed.Quality, payload.Quality)
}
if parsed.Transform.FitMode != req.Transform.FitMode {
t.Errorf("FitMode = %q, want %q",
parsed.Transform.FitMode, req.Transform.FitMode)
if parsed.FitMode != payload.FitMode {
t.Errorf("FitMode = %q, want %q", parsed.FitMode, payload.FitMode)
}
if parsed.Expires.Unix() != req.Expires.Unix() {
t.Errorf("ExpiresAt = %d, want %d", parsed.Expires.Unix(), req.Expires.Unix())
if parsed.ExpiresAt != payload.ExpiresAt {
t.Errorf("ExpiresAt = %d, want %d", parsed.ExpiresAt, payload.ExpiresAt)
}
}
@@ -101,15 +93,13 @@ func TestGenerator_Parse_Expired(t *testing.T) {
gen, _ := encurl.NewGenerator("test-signing-key-12345")
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: testSourceHost,
Path: testSourcePath,
},
Expires: time.Now().Add(-time.Hour), // Already expired
payload := &encurl.Payload{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
ExpiresAt: time.Now().Add(-time.Hour).Unix(), // Already expired
}
token, err := gen.Generate(req)
token, err := gen.Generate(payload)
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
@@ -140,15 +130,13 @@ func TestGenerator_Parse_TamperedToken(t *testing.T) {
gen, _ := encurl.NewGenerator("test-signing-key-12345")
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: testSourceHost,
Path: testSourcePath,
},
Expires: time.Now().Add(time.Hour),
payload := &encurl.Payload{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
ExpiresAt: time.Now().Add(time.Hour).Unix(),
}
token, _ := gen.Generate(req)
token, _ := gen.Generate(payload)
// Tamper with the token
tampered := []byte(token)
@@ -168,15 +156,13 @@ func TestGenerator_Parse_WrongKey(t *testing.T) {
gen1, _ := encurl.NewGenerator("signing-key-1")
gen2, _ := encurl.NewGenerator("signing-key-2")
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: testSourceHost,
Path: testSourcePath,
},
Expires: time.Now().Add(time.Hour),
payload := &encurl.Payload{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
ExpiresAt: time.Now().Add(time.Hour).Unix(),
}
token, _ := gen1.Generate(req)
token, _ := gen1.Generate(payload)
_, err := gen2.Parse(token)
if err == nil {
@@ -184,41 +170,140 @@ func TestGenerator_Parse_WrongKey(t *testing.T) {
}
}
func TestGenerator_Parse_Defaults(t *testing.T) {
func TestPayload_ToImageRequest(t *testing.T) {
t.Parallel()
gen, _ := encurl.NewGenerator("test-signing-key-12345")
// Request with only required fields - should get defaults
token, err := gen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: testSourceHost,
Path: testSourcePath,
},
Expires: time.Now().Add(time.Hour),
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
payload := &encurl.Payload{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
SourceQuery: testSourceQuery,
Width: 800,
Height: 600,
Format: imgcache.FormatWebP,
Quality: 90,
FitMode: imgcache.FitContain,
ExpiresAt: time.Now().Add(time.Hour).Unix(),
}
req, err := gen.Parse(token)
if err != nil {
t.Fatalf("Parse() error = %v", err)
req := payload.ToImageRequest()
if req.SourceHost != payload.SourceHost {
t.Errorf("SourceHost = %q, want %q", req.SourceHost, payload.SourceHost)
}
if req.Transform.Format != encurl.DefaultFormat {
t.Errorf("Format = %q, want default %q",
req.Transform.Format, encurl.DefaultFormat)
if req.SourcePath != payload.SourcePath {
t.Errorf("SourcePath = %q, want %q", req.SourcePath, payload.SourcePath)
}
if req.Transform.Quality != encurl.DefaultQuality {
t.Errorf("Quality = %d, want default %d",
req.Transform.Quality, encurl.DefaultQuality)
if req.SourceQuery != payload.SourceQuery {
t.Errorf("SourceQuery = %q, want %q", req.SourceQuery, payload.SourceQuery)
}
if req.Transform.FitMode != encurl.DefaultFitMode {
t.Errorf("FitMode = %q, want default %q",
req.Transform.FitMode, encurl.DefaultFitMode)
if req.Size.Width != payload.Width {
t.Errorf("Width = %d, want %d", req.Size.Width, payload.Width)
}
if req.Size.Height != payload.Height {
t.Errorf("Height = %d, want %d", req.Size.Height, payload.Height)
}
if req.Format != payload.Format {
t.Errorf("Format = %q, want %q", req.Format, payload.Format)
}
if req.Quality != payload.Quality {
t.Errorf("Quality = %d, want %d", req.Quality, payload.Quality)
}
if req.FitMode != payload.FitMode {
t.Errorf("FitMode = %q, want %q", req.FitMode, payload.FitMode)
}
}
func TestPayload_ToImageRequest_Defaults(t *testing.T) {
t.Parallel()
// Payload with only required fields - should get defaults
payload := &encurl.Payload{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
ExpiresAt: time.Now().Add(time.Hour).Unix(),
}
req := payload.ToImageRequest()
if req.Format != encurl.DefaultFormat {
t.Errorf("Format = %q, want default %q", req.Format, encurl.DefaultFormat)
}
if req.Quality != encurl.DefaultQuality {
t.Errorf("Quality = %d, want default %d", req.Quality, encurl.DefaultQuality)
}
if req.FitMode != encurl.DefaultFitMode {
t.Errorf("FitMode = %q, want default %q", req.FitMode, encurl.DefaultFitMode)
}
}
func TestFromImageRequest(t *testing.T) {
t.Parallel()
req := &imgcache.ImageRequest{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
SourceQuery: testSourceQuery,
Size: imgcache.Size{Width: 800, Height: 600},
Format: imgcache.FormatWebP,
Quality: 90,
FitMode: imgcache.FitContain,
}
expiresAt := time.Now().Add(time.Hour)
payload := encurl.FromImageRequest(req, expiresAt)
if payload.SourceHost != req.SourceHost {
t.Errorf("SourceHost = %q, want %q", payload.SourceHost, req.SourceHost)
}
if payload.SourcePath != req.SourcePath {
t.Errorf("SourcePath = %q, want %q", payload.SourcePath, req.SourcePath)
}
if payload.Width != req.Size.Width {
t.Errorf("Width = %d, want %d", payload.Width, req.Size.Width)
}
if payload.ExpiresAt != expiresAt.Unix() {
t.Errorf("ExpiresAt = %d, want %d", payload.ExpiresAt, expiresAt.Unix())
}
}
func TestFromImageRequest_OmitsDefaults(t *testing.T) {
t.Parallel()
// Request with default values - payload should omit them for
// smaller encoding
req := &imgcache.ImageRequest{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
Format: encurl.DefaultFormat,
Quality: encurl.DefaultQuality,
FitMode: encurl.DefaultFitMode,
}
payload := encurl.FromImageRequest(req, time.Now().Add(time.Hour))
// These should be zero/empty because they match defaults
if payload.Format != "" {
t.Errorf("Format should be empty for default, got %q", payload.Format)
}
if payload.Quality != 0 {
t.Errorf("Quality should be 0 for default, got %d", payload.Quality)
}
if payload.FitMode != "" {
t.Errorf("FitMode should be empty for default, got %q", payload.FitMode)
}
}
@@ -227,15 +312,13 @@ func TestGenerator_TokenIsURLSafe(t *testing.T) {
gen, _ := encurl.NewGenerator("test-signing-key-12345")
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: testSourceHost,
Path: testSourcePath,
},
Expires: time.Now().Add(time.Hour),
payload := &encurl.Payload{
SourceHost: testSourceHost,
SourcePath: testSourcePath,
ExpiresAt: time.Now().Add(time.Hour).Unix(),
}
token, _ := gen.Generate(req)
token, _ := gen.Generate(payload)
// Check that token only contains URL-safe characters
for _, c := range token {
internal/handlers/auth.go
+38 -116
View File
@@ -9,14 +9,12 @@ import (
"math"
"net/http"
"net/url"
"slices"
"strconv"
"strings"
"time"
"sneak.berlin/go/pixa/internal/clientip"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/templates"
)
@@ -91,18 +89,10 @@ func (s *Handlers) handleLoginPost(w http.ResponseWriter, r *http.Request) {
http.Redirect(w, r, "/", http.StatusSeeOther)
}
// HandleLogout logs out, which ends every login session (see
// session.Manager.Logout), and redirects to login.
// HandleLogout clears the session and redirects to login.
func (s *Handlers) HandleLogout() http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
err := s.sessMgr.Logout(w, r)
if err != nil {
s.log.Error("failed to log out", "error", err)
http.Error(w, "Failed to log out", http.StatusInternalServerError)
return
}
s.sessMgr.ClearSession(w)
http.Redirect(w, r, "/", http.StatusSeeOther)
}
}
@@ -127,7 +117,7 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
sourceURL := r.FormValue("url")
// Validate source URL
parsed, err := parseSourceURL(sourceURL)
parsed, err := url.Parse(sourceURL)
if err != nil || parsed.Host == "" {
s.renderGeneratorWithForm(w, r, "Invalid source URL", r.Form,
http.StatusBadRequest)
@@ -135,17 +125,7 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
return
}
// /v1/image/ refuses a ".." segment in the source path, and so does
// the generator. The path is decoded, so %2e%2e counts too
if slices.Contains(strings.Split(parsed.Path, "/"), "..") {
s.renderGeneratorWithForm(w, r,
"Source URL path cannot hold a .. segment", r.Form,
http.StatusBadRequest)
return
}
req, expiresAt, ttl, err := buildGenerateRequest(parsed, r.Form)
payload, expiresAt, ttl, err := buildGeneratePayload(parsed, r.Form)
if err != nil {
s.renderGeneratorWithForm(w, r, err.Error(), r.Form,
http.StatusBadRequest)
@@ -153,20 +133,8 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
return
}
// The image URL must fetch the source URL as it was written
req.AllowHTTP = s.config.AllowHTTP
fetchURL := req.SourceURL()
if !fetchedAsWritten(parsed, fetchURL) {
s.renderGeneratorWithForm(w, r, "Source URL cannot be fetched as "+
"written: pixa would fetch "+fetchURL,
r.Form, http.StatusBadRequest)
return
}
// Generate encrypted token
token, err := s.encGen.Generate(req)
token, err := s.encGen.Generate(payload)
if err != nil {
s.log.Error("failed to generate encrypted URL", "error", err)
s.renderGeneratorWithForm(w, r, "Failed to generate URL", r.Form,
@@ -197,57 +165,14 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
}
}
// parseSourceURL parses the source URL entered on the generator page with its
// host lower-cased and an empty path written as "/", as /v1/image/ reads a
// source URL, so that each spelling of one source URL makes one cache key and
// one upstream request.
func parseSourceURL(sourceURL string) (*url.URL, error) {
parsed, err := url.Parse(sourceURL)
if err != nil {
return nil, err
}
parsed.Host = strings.ToLower(parsed.Host)
if parsed.Path == "" {
parsed.Path = "/"
}
return parsed, nil
}
// fetchedAsWritten reports whether fetchURL, the URL pixa fetches for an
// image URL made from the source URL source, is source as it was written,
// apart from the scheme, which the token does not keep. It is not when source
// holds a user name and password, which the token does not keep either, or a
// "?" with no query after it. The token keeps the source path decoded and
// pixa fetches it percent-encoded again, so a path written another way, such
// as with %2F, is fetched as another path. url.URL keeps the path as written
// in RawPath when it is not the decoded path percent-encoded again.
// EscapedPath ignores RawPath when it also holds a character net/url encodes,
// such as a space, so RawPath is compared itself.
func fetchedAsWritten(source *url.URL, fetchURL string) bool {
writtenPath := source.RawPath
if writtenPath == "" {
writtenPath = source.EscapedPath()
}
fetched, err := url.Parse(fetchURL)
return err == nil && source.User == nil && !source.ForceQuery &&
fetched.EscapedPath() == writtenPath &&
fetched.RawQuery == source.RawQuery
}
// buildGenerateRequest parses the numeric form fields and assembles the
// image request the encrypted URL's token is made from. ttl=0 means never
// expires (Expires stays the zero time). A non-numeric or out-of-range
// width, height, quality or ttl, or an unrecognized fit mode, is a client
// error naming the offending field. The format field is passed through
// unchecked.
func buildGenerateRequest(
// buildGeneratePayload parses the numeric form fields and assembles the
// encrypted URL payload. ttl=0 means never expires (ExpiresAt stays 0). A
// non-numeric or out-of-range width, height, quality or ttl, or an
// unrecognized fit mode, is a client error naming the offending field. The
// format field is passed through unchecked.
func buildGeneratePayload(
parsed *url.URL, form url.Values,
) (*imagerequest.Request, time.Time, int, error) {
) (*encurl.Payload, time.Time, int, error) {
width, err := parseFormDimension(form, "width")
if err != nil {
return nil, time.Time{}, 0, err
@@ -269,40 +194,42 @@ func buildGenerateRequest(
return nil, time.Time{}, 0, err
}
fitMode := imagerequest.Fit(form.Get("fit"))
fitMode := imgcache.FitMode(form.Get("fit"))
err = imagerequest.ValidateFitMode(fitMode)
err = imgcache.ValidateFitMode(fitMode)
if err != nil {
return nil, time.Time{}, 0,
fmt.Errorf("%w: %s", imagerequest.ErrInvalidFitMode, form.Get("fit"))
fmt.Errorf("%w: %s", imgcache.ErrInvalidFitMode, form.Get("fit"))
}
var expiresAt time.Time
var (
expiresAt time.Time
expiresAtUnix int64
)
if ttl > 0 {
expiresAt = time.Now().Add(time.Duration(ttl) * time.Second)
expiresAtUnix = expiresAt.Unix()
}
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: parsed.Host,
Path: parsed.Path,
Query: parsed.RawQuery,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: width, Height: height},
Format: imagerequest.Format(form.Get("format")),
Quality: quality,
FitMode: fitMode,
},
Expires: expiresAt,
payload := &encurl.Payload{
SourceHost: parsed.Host,
SourcePath: parsed.Path,
SourceQuery: parsed.RawQuery,
Width: width,
Height: height,
Format: imgcache.ImageFormat(form.Get("format")),
Quality: quality,
FitMode: fitMode,
ExpiresAt: expiresAtUnix,
}
return req, expiresAt, ttl, nil
return payload, expiresAt, ttl, nil
}
// parseFormDimension reads an optional width or height form field. An empty
// value means "original size" (0). A non-numeric value, or one
// imagerequest.ValidateDimension rejects, is an error naming the field.
// imgcache.ValidateDimension rejects, is an error naming the field.
func parseFormDimension(form url.Values, field string) (int, error) {
raw := form.Get(field)
if raw == "" {
@@ -314,7 +241,7 @@ func parseFormDimension(form url.Values, field string) (int, error) {
return 0, fmt.Errorf("%w %s: not a number", errInvalidFormField, field)
}
err = imagerequest.ValidateDimension(field, value)
err = imgcache.ValidateDimension(field, value)
if err != nil {
return 0, err
}
@@ -442,15 +369,10 @@ func (s *Handlers) buildGeneratedURL(r *http.Request, token, format string) stri
scheme = "http"
}
// Determine file extension for the trailing filename. A form with no
// format makes a token with none, which is served as encurl.DefaultFormat.
// Determine file extension for the trailing filename
ext := format
switch format {
case "":
ext = string(encurl.DefaultFormat)
case "orig", "auto":
ext = "jpg"
if ext == "" || ext == "orig" || ext == "auto" {
ext = "jpg" // Default extension
}
return scheme + "://" + r.Host + "/v1/e/" + url.PathEscape(token) + "/img." + ext
internal/handlers/auth_generate_internal_test.go
+9 -9
View File
@@ -11,7 +11,7 @@ import (
"time"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
// Generator form field names, and a value that is not a number.
@@ -125,10 +125,10 @@ func TestGeneratePostRejectsBadField(t *testing.T) {
}
}
// TestBuildGenerateRequestDefaultAndLimits verifies that an empty quality
// TestBuildGeneratePayloadDefaultAndLimits verifies that an empty quality
// takes the default, and that the largest accepted width, height, quality and
// ttl are accepted with an expiry still in the future.
func TestBuildGenerateRequestDefaultAndLimits(t *testing.T) {
func TestBuildGeneratePayloadDefaultAndLimits(t *testing.T) {
t.Parallel()
parsed, err := url.Parse(testSourceURL)
@@ -136,19 +136,19 @@ func TestBuildGenerateRequestDefaultAndLimits(t *testing.T) {
t.Fatalf("url.Parse() error = %v", err)
}
req, _, _, err := buildGenerateRequest(parsed, url.Values{})
payload, _, _, err := buildGeneratePayload(parsed, url.Values{})
if err != nil {
t.Fatalf("empty form: error = %v", err)
}
if req.Transform.Quality != encurl.DefaultQuality {
if payload.Quality != encurl.DefaultQuality {
t.Errorf("empty quality gave %d, want %d",
req.Transform.Quality, encurl.DefaultQuality)
payload.Quality, encurl.DefaultQuality)
}
_, expiresAt, _, err := buildGenerateRequest(parsed, url.Values{
widthField: {strconv.Itoa(imagerequest.MaxDimension)},
heightField: {strconv.Itoa(imagerequest.MaxDimension)},
_, expiresAt, _, err := buildGeneratePayload(parsed, url.Values{
widthField: {strconv.Itoa(imgcache.MaxDimension)},
heightField: {strconv.Itoa(imgcache.MaxDimension)},
qualityField: {strconv.Itoa(maxQuality)},
ttlField: {strconv.Itoa(maxTTL)},
})
internal/handlers/auth_session_internal_test.go
+3 -95
View File
@@ -10,7 +10,7 @@ import (
"testing"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/session"
)
@@ -185,98 +185,6 @@ func TestHandleLogout_ClearsSessionCookie(t *testing.T) {
}
}
// TestHandleLogout_EndsCopiedSession verifies that after POST /logout a copy
// of the session cookie taken before it shows the login page, not the
// generator page.
func TestHandleLogout_EndsCopiedSession(t *testing.T) {
t.Parallel()
h, srv := newCSRFTestRouter(t)
copied := newSessionCookie(t, h)
req := httptest.NewRequestWithContext(
t.Context(), http.MethodPost, "/logout", nil)
req.AddCookie(copied)
rec := httptest.NewRecorder()
h.HandleLogout().ServeHTTP(rec, req)
if rec.Code != http.StatusSeeOther {
t.Fatalf("POST /logout status = %d, want %d",
rec.Code, http.StatusSeeOther)
}
req = httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil)
req.AddCookie(copied)
rec = httptest.NewRecorder()
srv.ServeHTTP(rec, req)
body := rec.Body.String()
t.Logf("GET / with the copied cookie: status %d, login page %v",
rec.Code, strings.Contains(body, loginForm))
if !strings.Contains(body, loginForm) || strings.Contains(body, generatorForm) {
t.Error("a cookie copied before /logout still opens the generator page")
}
}
// TestHandleLogout_SaveFails_Answers500 verifies that when the logout cannot
// be saved in the database, POST /logout answers 500, leaves the session
// cookie in place and ends no session.
func TestHandleLogout_SaveFails_Answers500(t *testing.T) {
t.Parallel()
h, srv := newCSRFTestRouter(t)
db := setupTestDB(t)
sessMgr, err := session.NewManagerWithDatabase(
t.Context(), testSigningKey, db)
if err != nil {
t.Fatalf("session.NewManagerWithDatabase() error = %v", err)
}
h.sessMgr = sessMgr
cookie := newSessionCookie(t, h)
// Saving the logout fails on a closed database.
err = db.Close()
if err != nil {
t.Fatalf("closing the database: %v", err)
}
req := httptest.NewRequestWithContext(
t.Context(), http.MethodPost, "/logout", nil)
req.AddCookie(cookie)
rec := httptest.NewRecorder()
h.HandleLogout().ServeHTTP(rec, req)
t.Logf("POST /logout: status %d, Set-Cookie %q",
rec.Code, rec.Header().Get("Set-Cookie"))
if rec.Code != http.StatusInternalServerError {
t.Errorf("POST /logout status = %d, want %d",
rec.Code, http.StatusInternalServerError)
}
if c := findSessionCookie(rec); c != nil {
t.Errorf("a logout that failed set the session cookie: %s", c)
}
req = httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil)
req.AddCookie(cookie)
rec = httptest.NewRecorder()
srv.ServeHTTP(rec, req)
if !strings.Contains(rec.Body.String(), generatorForm) {
t.Error("a logout that failed ended the session")
}
}
// TestGeneratePost_NoSession_RedirectsToLogin verifies that POST /generate
// with a valid CSRF token but no login session answers 303 to / and makes no
// URL.
@@ -314,7 +222,7 @@ func TestGeneratePost_URLServesImage(t *testing.T) {
sourceURLField: {"https://" + signedHost + photoPath},
widthField: {"50"},
heightField: {"50"},
formatField: {string(imagerequest.FormatJPEG)},
formatField: {string(imgcache.FormatJPEG)},
})
if rec.Code != http.StatusOK {
@@ -347,7 +255,7 @@ func TestGeneratePost_URLWithTTLExpires(t *testing.T) {
sourceURLField: {"https://" + signedHost + photoPath},
widthField: {"50"},
heightField: {"50"},
formatField: {string(imagerequest.FormatJPEG)},
formatField: {string(imgcache.FormatJPEG)},
ttlField: {"1"},
})
internal/handlers/avif_too_large_internal_test.go
-49
View File
@@ -1,49 +0,0 @@
package handlers
import (
"fmt"
"log/slog"
"net/http"
"net/http/httptest"
"strings"
"testing"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestAVIFOutputTooLargeAnswers400 checks that respondImageError and
// handleImageError, which answer the errors of the two image routes, answer
// 400 naming the AVIF pixel limit when the image processor refuses an AVIF
// output above it, wrapped as the service wraps it. The request's source only
// goes into a log line, so it is left empty.
func TestAVIFOutputTooLargeAnswers400(t *testing.T) {
t.Parallel()
h := &Handlers{log: slog.New(slog.DiscardHandler)}
err := fmt.Errorf("image processing failed: %w: 4097x4096",
imageprocessor.ErrAVIFOutputTooLarge)
wantBody := fmt.Sprintf("above %d pixels", imageprocessor.MaxAVIFOutputPixels)
plain := httptest.NewRecorder()
h.respondImageError(plain, &imagerequest.Request{}, err)
encrypted := httptest.NewRecorder()
h.handleImageError(encrypted, err)
for name, rec := range map[string]*httptest.ResponseRecorder{
"respondImageError": plain, "handleImageError": encrypted,
} {
t.Logf("%s: status = %d, body = %q", name, rec.Code, rec.Body.String())
if rec.Code != http.StatusBadRequest {
t.Errorf("%s: status = %d, want %d",
name, rec.Code, http.StatusBadRequest)
}
if !strings.Contains(rec.Body.String(), wantBody) {
t.Errorf("%s: body = %q, want it to say %q",
name, rec.Body.String(), wantBody)
}
}
}
internal/handlers/cache_hit_internal_test.go
-265
View File
@@ -1,265 +0,0 @@
package handlers
import (
"bytes"
"context"
"database/sql"
"database/sql/driver"
"image"
"image/jpeg"
"log/slog"
"net/http"
"net/http/httptest"
"path/filepath"
"sync/atomic"
"testing"
"testing/fstest"
"time"
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/database"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
// countingHost is the allowlisted host whose photoPath the server of
// newCountingDatabaseServer serves.
const countingHost = "counting.example.com"
// countingConnector opens connections to the SQLite database file name with
// sqliteDriver, each one counting in statements the statements run on it.
type countingConnector struct {
sqliteDriver driver.Driver
name string
statements *atomic.Int64
}
func (c countingConnector) Connect(context.Context) (driver.Conn, error) {
conn, err := c.sqliteDriver.Open(c.name)
if err != nil {
return nil, err
}
return countingConn{Conn: conn, statements: c.statements}, nil
}
func (c countingConnector) Driver() driver.Driver {
return c.sqliteDriver
}
// countingConn counts the statements run on its connection. It has only the
// methods of driver.Conn, so database/sql prepares every query and every
// other statement with Prepare, which counts it.
type countingConn struct {
driver.Conn
statements *atomic.Int64
}
func (c countingConn) Prepare(query string) (driver.Stmt, error) {
c.statements.Add(1)
return c.Conn.Prepare(query)
}
// newCountingDatabase returns a database with pixa's schema, in a file of
// its own and with one connection, and the count of the statements run on
// it once the schema is in place.
func newCountingDatabase(tb testing.TB) (*sql.DB, *atomic.Int64) {
tb.Helper()
path := filepath.Join(tb.TempDir(), "state.sqlite3")
schemaDB, err := sql.Open("sqlite", path)
if err != nil {
tb.Fatalf("opening the database: %v", err)
}
defer func() { _ = schemaDB.Close() }()
err = database.ApplyMigrations(tb.Context(), schemaDB, nil)
if err != nil {
tb.Fatalf("applying the migrations: %v", err)
}
statements := new(atomic.Int64)
db := sql.OpenDB(countingConnector{
sqliteDriver: schemaDB.Driver(),
name: path,
statements: statements,
})
db.SetMaxOpenConns(1)
tb.Cleanup(func() { _ = db.Close() })
return db, statements
}
// newCountingDatabaseServer returns a router for both image routes whose
// image cache uses newCountingDatabase, the count of the statements run on
// that database, and a URL on each route for a different image of
// photoPath on countingHost. Nothing writes the cache's pending counts and
// access times in the background, so every statement counted comes from a
// request.
func newCountingDatabaseServer(
tb testing.TB,
) (http.Handler, *atomic.Int64, []string) {
tb.Helper()
db, statements := newCountingDatabase(tb)
var photo bytes.Buffer
err := jpeg.Encode(&photo, image.NewRGBA(image.Rect(0, 0, 100, 100)), nil)
if err != nil {
tb.Fatalf("encoding the photo: %v", err)
}
cache, err := imgcache.NewCache(db, imgcache.CacheConfig{
StateDir: tb.TempDir(),
NegativeTTL: 5 * time.Minute,
})
if err != nil {
tb.Fatalf("imgcache.NewCache() error = %v", err)
}
svc, err := imgcache.NewService(&imgcache.ServiceConfig{
Cache: cache,
Fetcher: newMockFetcher(fstest.MapFS{
countingHost + photoPath: &fstest.MapFile{Data: photo.Bytes()},
}),
SigningKey: testSigningKey,
Allowlist: []string{countingHost},
Logger: slog.New(slog.DiscardHandler),
})
if err != nil {
tb.Fatalf("imgcache.NewService() error = %v", err)
}
encGen, err := encurl.NewGenerator(testSigningKey)
if err != nil {
tb.Fatalf("encurl.NewGenerator() error = %v", err)
}
token, err := encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{Host: countingHost, Path: photoPath},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 40, Height: 40},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
})
if err != nil {
tb.Fatalf("encGen.Generate() error = %v", err)
}
h := &Handlers{
log: slog.New(slog.DiscardHandler),
imgSvc: svc,
encGen: encGen,
}
r := chi.NewRouter()
r.Get("/v1/image/*", h.HandleImage())
r.Get("/v1/e/{token}/*", h.HandleImageEnc())
return r, statements, []string{
"/v1/image/" + countingHost + photoPath + "/50x50.jpeg",
"/v1/e/" + token + "/img.jpg",
}
}
// serveImage sends srv a GET for target and returns the response, failing
// the test unless it is a 200 with an image.
func serveImage(
tb testing.TB, srv http.Handler, target string,
) *httptest.ResponseRecorder {
tb.Helper()
rec := httptest.NewRecorder()
srv.ServeHTTP(rec,
httptest.NewRequestWithContext(tb.Context(), http.MethodGet, target, nil))
if rec.Code != http.StatusOK || rec.Body.Len() == 0 {
tb.Errorf("GET %s: %d with %d bytes, want 200 with an image",
target, rec.Code, rec.Body.Len())
}
return rec
}
// TestImageRoutes_CacheHitsMakeNoDatabaseCall serves an image on each image
// route once, which makes and caches it, then serves it again from the cache.
// Serving those cache hits must run no statement on the database.
func TestImageRoutes_CacheHitsMakeNoDatabaseCall(t *testing.T) {
t.Parallel()
srv, statements, targets := newCountingDatabaseServer(t)
for _, target := range targets {
before := statements.Load()
serveImage(t, srv, target)
afterMiss := statements.Load()
t.Logf("GET %s, a miss: %d statements", target, afterMiss-before)
if afterMiss == before {
t.Fatalf("GET %s, a miss: no statement counted, want some", target)
}
for range 3 {
rec := serveImage(t, srv, target)
cacheStatus := rec.Header().Get("X-Pixa-Cache")
if cacheStatus != string(imgcache.CacheHit) {
t.Errorf("GET %s: X-Pixa-Cache = %q, want %s",
target, cacheStatus, imgcache.CacheHit)
}
}
if hitStatements := statements.Load() - afterMiss; hitStatements != 0 {
t.Errorf("GET %s: 3 cache hits ran %d statements, want 0",
target, hitStatements)
}
}
}
// BenchmarkHandleImage_CacheHits serves one cached image through the
// /v1/image/ route from b.RunParallel's goroutines, and reports the cache
// hits served per second. It fails if serving them ran any statement on the
// database. script/bench runs it.
func BenchmarkHandleImage_CacheHits(b *testing.B) {
srv, statements, targets := newCountingDatabaseServer(b)
target := targets[0]
serveImage(b, srv, target)
before := statements.Load()
b.ResetTimer()
b.RunParallel(func(pb *testing.PB) {
for pb.Next() {
rec := serveImage(b, srv, target)
cacheStatus := rec.Header().Get("X-Pixa-Cache")
if cacheStatus != string(imgcache.CacheHit) {
b.Errorf("GET %s: X-Pixa-Cache = %q, want %s",
target, cacheStatus, imgcache.CacheHit)
return
}
}
})
b.ReportMetric(float64(b.N)/b.Elapsed().Seconds(), "hits/s")
if hitStatements := statements.Load() - before; hitStatements != 0 {
b.Fatalf("%d cache hits ran %d statements, want 0", b.N, hitStatements)
}
}
internal/handlers/first_bytes_internal_test.go
-184
View File
@@ -1,184 +0,0 @@
package handlers
import (
"bytes"
"encoding/json"
"image/color"
"log/slog"
"net/http"
"slices"
"testing"
"testing/fstest"
"time"
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
// mismatchedSourcePath is the path of the source that
// TestFirstBytesNotMatchingContentType serves on allowlistedHost. The mock
// fetcher names a file's Content-Type from its extension, so the source is
// sent as image/png.
const mismatchedSourcePath = "/images/source.png"
// newRoutesFetchingThrough returns both image routes, and the Handlers behind
// them, whose image service fetches through fetcher and has allowlistedHost on
// its allowlist. The handlers and the image service log to log.
func newRoutesFetchingThrough(
t *testing.T, fetcher httpfetcher.Fetcher, log *slog.Logger,
) (*Handlers, http.Handler) {
t.Helper()
cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
StateDir: t.TempDir(),
NegativeTTL: 5 * time.Minute,
})
if err != nil {
t.Fatalf("imgcache.NewCache() error = %v", err)
}
svc, err := imgcache.NewService(&imgcache.ServiceConfig{
Cache: cache,
Fetcher: fetcher,
SigningKey: testSigningKey,
Allowlist: []string{allowlistedHost},
Logger: log,
})
if err != nil {
t.Fatalf("imgcache.NewService() error = %v", err)
}
encGen, err := encurl.NewGenerator(testSigningKey)
if err != nil {
t.Fatalf("encurl.NewGenerator() error = %v", err)
}
h := &Handlers{log: log, imgSvc: svc, encGen: encGen}
r := chi.NewRouter()
r.Get("/v1/image/*", h.HandleImage())
r.Get("/v1/e/{token}/*", h.HandleImageEnc())
return h, r
}
// mismatchedSourcePlainURL returns the /v1/image/ URL of mismatchedSourcePath
// on allowlistedHost at 50x50 as a JPEG.
func mismatchedSourcePlainURL(*testing.T, *Handlers) string {
return "/v1/image/" + allowlistedHost + mismatchedSourcePath + "/50x50.jpeg"
}
// mismatchedSourceEncURL returns an encrypted /v1/e/ URL, made with h's
// generator, of mismatchedSourcePath on allowlistedHost at 50x50 as a JPEG.
func mismatchedSourceEncURL(t *testing.T, h *Handlers) string {
t.Helper()
token, err := h.encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: allowlistedHost,
Path: mismatchedSourcePath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
},
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
return "/v1/e/" + token + "/img.jpg"
}
// loggedLevels reads the JSON log lines in logs and returns the messages
// logged at each level.
func loggedLevels(t *testing.T, logs *bytes.Buffer) map[string][]string {
t.Helper()
t.Logf("logged:\n%s", logs.String())
messages := make(map[string][]string)
dec := json.NewDecoder(logs)
for dec.More() {
var line struct {
Level string `json:"level"`
Msg string `json:"msg"`
}
err := dec.Decode(&line)
if err != nil {
t.Fatalf("decoding log line: %v", err)
}
messages[line.Level] = append(messages[line.Level], line.Msg)
}
return messages
}
// TestFirstBytesNotMatchingContentType checks that both image routes answer
// 415 for an upstream body whose first bytes are not those of the format its
// Content-Type names, and log it as a refused source, not as an error of
// pixa's. The next request for that source must answer 502 without fetching
// it again, as after an upstream error status.
func TestFirstBytesNotMatchingContentType(t *testing.T) {
t.Parallel()
bodies := map[string][]byte{
"JPEG sent as image/png": generateTestJPEG(t, 10, 10, color.Black),
"text sent as image/png": []byte("This is just text, not a PNG"),
"body too short to name a format": []byte("short"),
}
// The source's URL on each image route.
sourceURLs := map[string]func(*testing.T, *Handlers) string{
"plain URL": mismatchedSourcePlainURL,
"encrypted URL": mismatchedSourceEncURL,
}
for bodyName, body := range bodies {
for urlName, sourceURL := range sourceURLs {
t.Run(urlName+", "+bodyName, func(t *testing.T) {
t.Parallel()
fetcher := &countingFetcher{
Fetcher: httpfetcher.NewMock(fstest.MapFS{
allowlistedHost + mismatchedSourcePath: &fstest.MapFile{
Data: body,
},
}),
}
var logs bytes.Buffer
h, routes := newRoutesFetchingThrough(t, fetcher,
slog.New(slog.NewJSONHandler(&logs, nil)))
target := sourceURL(t, h)
checkErrorBody(t, sendGet(t, routes, target),
http.StatusUnsupportedMediaType, "unsupported source format")
levels := loggedLevels(t, &logs)
if len(levels[slog.LevelError.String()]) != 0 {
t.Errorf("logged at error level: %q",
levels[slog.LevelError.String()])
}
if !slices.Contains(levels[slog.LevelWarn.String()], "source refused") {
t.Error(`no "source refused" line logged at warning level`)
}
checkErrorBody(t, sendGet(t, routes, target),
http.StatusBadGateway, "upstream error")
if n := fetcher.fetches.Load(); n != 1 {
t.Errorf("upstream fetched %d times, want 1", n)
}
})
}
}
}
internal/handlers/format_auto.go
+16 -20
View File
@@ -8,14 +8,14 @@ import (
"strconv"
"strings"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
// Errors for an Accept header that an auto URL cannot be served for.
var (
errInvalidAccept = errors.New("invalid Accept header")
errNotAcceptable = errors.New("not acceptable: auto serves " +
"image/jxl, image/avif, image/webp or image/jpeg")
errNotAcceptable = errors.New(
"not acceptable: auto serves image/avif, image/webp or image/jpeg")
)
// chooseAutoFormat replaces the format auto in req with the format
@@ -24,9 +24,9 @@ var (
// header that is not valid and 406 for one that allows none of the formats,
// and reports whether req can be served. Any other format is left as it is.
func (s *Handlers) chooseAutoFormat(
w http.ResponseWriter, r *http.Request, req *imagerequest.Request,
w http.ResponseWriter, r *http.Request, req *imgcache.ImageRequest,
) bool {
if req.Transform.Format != imagerequest.FormatAuto {
if req.Format != imgcache.FormatAuto {
return true
}
@@ -45,37 +45,33 @@ func (s *Handlers) chooseAutoFormat(
return false
}
req.Transform.Format = format
req.Format = format
return true
}
// formatForAccept returns the format an auto URL is served in for the Accept
// header accept: JPEG XL when it names image/jxl, else AVIF when it names
// image/avif, else WebP when it names image/webp, else JPEG when its most
// specific entry of image/jpeg, image/* and */* allows it, or when it names
// nothing. A q of 0 refuses a format. JPEG XL, AVIF and WebP must be named, as
// clients that cannot show them send image/* and */* too.
func formatForAccept(accept string) (imagerequest.Format, error) {
// header accept: AVIF when it names image/avif, else WebP when it names
// image/webp, else JPEG when its most specific entry of image/jpeg, image/*
// and */* allows it, or when it names nothing. A q of 0 refuses a format.
// AVIF and WebP must be named, as clients that cannot show them send image/*
// and */* too.
func formatForAccept(accept string) (imgcache.ImageFormat, error) {
qualities, err := parseAccept(accept)
if err != nil {
return "", err
}
if len(qualities) == 0 {
return imagerequest.FormatJPEG, nil
}
if qualities["image/jxl"] > 0 {
return imagerequest.FormatJXL, nil
return imgcache.FormatJPEG, nil
}
if qualities["image/avif"] > 0 {
return imagerequest.FormatAVIF, nil
return imgcache.FormatAVIF, nil
}
if qualities["image/webp"] > 0 {
return imagerequest.FormatWebP, nil
return imgcache.FormatWebP, nil
}
// For JPEG, the most specific entry the header has decides
@@ -89,7 +85,7 @@ func formatForAccept(accept string) (imagerequest.Format, error) {
}
if quality > 0 {
return imagerequest.FormatJPEG, nil
return imgcache.FormatJPEG, nil
}
return "", errNotAcceptable
internal/handlers/format_auto_internal_test.go
+30 -40
View File
@@ -12,7 +12,8 @@ import (
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imgcache"
)
// The content types the tests below expect.
@@ -32,24 +33,24 @@ func TestFormatForAccept(t *testing.T) {
tests := []struct {
name string
accept string
want imagerequest.Format
want imgcache.ImageFormat
wantErr error
}{
{"AVIF-capable browser",
"image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8",
imagerequest.FormatAVIF, nil},
imgcache.FormatAVIF, nil},
{"WebP-capable browser",
"image/webp,image/png,image/svg+xml,image/*;q=0.8,*/*;q=0.5",
imagerequest.FormatWebP, nil},
{"WebP only", webpType, imagerequest.FormatWebP, nil},
{"neither", "image/png,image/*;q=0.8,*/*;q=0.5", imagerequest.FormatJPEG, nil},
{"wildcard only", "*/*", imagerequest.FormatJPEG, nil},
{"image wildcard only", "image/*", imagerequest.FormatJPEG, nil},
{"absent", "", imagerequest.FormatJPEG, nil},
{"q=0 on AVIF", "image/avif;q=0,image/webp,*/*", imagerequest.FormatWebP, nil},
imgcache.FormatWebP, nil},
{"WebP only", webpType, imgcache.FormatWebP, nil},
{"neither", "image/png,image/*;q=0.8,*/*;q=0.5", imgcache.FormatJPEG, nil},
{"wildcard only", "*/*", imgcache.FormatJPEG, nil},
{"image wildcard only", "image/*", imgcache.FormatJPEG, nil},
{"absent", "", imgcache.FormatJPEG, nil},
{"q=0 on AVIF", "image/avif;q=0,image/webp,*/*", imgcache.FormatWebP, nil},
{"AVIF named twice, once with q=0", "image/avif,image/avif;q=0.0,*/*",
imagerequest.FormatJPEG, nil},
{"upper case and spaces", " Image/AVIF ; Q=0.5 ", imagerequest.FormatAVIF, nil},
imgcache.FormatJPEG, nil},
{"upper case and spaces", " Image/AVIF ; Q=0.5 ", imgcache.FormatAVIF, nil},
{"q=0 on JPEG", "image/jpeg;q=0,image/*", "", errNotAcceptable},
{"q=0 on everything", "*/*;q=0", "", errNotAcceptable},
{"PNG only", "image/png", "", errNotAcceptable},
@@ -79,30 +80,23 @@ func TestFormatForAccept(t *testing.T) {
func autoPhotoURLs(t *testing.T, h *Handlers) (string, string) {
t.Helper()
signedURL, err := h.imgSvc.GenerateSignedURL("", &imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatAuto,
},
signedURL, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
SourceHost: signedHost,
SourcePath: photoPath,
Size: imgcache.Size{Width: 50, Height: 50},
Format: imgcache.FormatAuto,
}, time.Minute)
if err != nil {
t.Fatalf("GenerateSignedURL() error = %v", err)
}
token, err := h.encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatAuto,
},
Expires: time.Now().Add(time.Minute),
token, err := h.encGen.Generate(&encurl.Payload{
SourceHost: signedHost,
SourcePath: photoPath,
Width: 50,
Height: 50,
Format: imgcache.FormatAuto,
ExpiresAt: time.Now().Add(time.Minute).Unix(),
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
@@ -190,15 +184,11 @@ func TestFormatAuto_SignatureCoversAuto(t *testing.T) {
h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
signedForAVIF, err := h.imgSvc.GenerateSignedURL("", &imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatAVIF,
},
signedForAVIF, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
SourceHost: signedHost,
SourcePath: photoPath,
Size: imgcache.Size{Width: 50, Height: 50},
Format: imgcache.FormatAVIF,
}, time.Minute)
if err != nil {
t.Fatalf("GenerateSignedURL() error = %v", err)
internal/handlers/handlers.go
+5 -18
View File
@@ -4,7 +4,6 @@ package handlers
import (
"context"
"encoding/json"
"errors"
"log/slog"
"net/http"
"time"
@@ -72,21 +71,16 @@ func New(lc fx.Lifecycle, params Params) (*Handlers, error) {
}
lc.Append(fx.Hook{
//nolint:contextcheck // the cache's goroutines outlive OnStart; OnStop stops them
//nolint:contextcheck // the eviction loop outlives OnStart; OnStop cancels it
OnStart: func(_ context.Context) error {
return s.initImageService()
},
// The pending counts and access times are written here, before the
// database's stop hook closes it.
OnStop: func(ctx context.Context) error {
if s.imgCache == nil {
return nil
}
return errors.Join(
s.imgCache.StopEviction(ctx),
s.imgCache.StopPendingCountWrites(ctx),
)
return s.imgCache.StopEviction(ctx)
},
})
@@ -106,6 +100,7 @@ func (s *Handlers) WaitForProcessing(ctx context.Context) int {
func newCacheConfig(cfg *config.Config, log *slog.Logger) imgcache.CacheConfig {
return imgcache.CacheConfig{
StateDir: cfg.StateDir,
CacheTTL: imgcache.DefaultCacheTTL,
NegativeTTL: imgcache.DefaultNegativeTTL,
MaxBytes: cfg.CacheMaxBytes,
UseDefaultMaxBytes: !cfg.CacheMaxBytesExplicit,
@@ -124,14 +119,9 @@ func (s *Handlers) initImageService() error {
s.imgCache = cache
// Background eviction: startup reconciliation, then periodic and
// write-pressure passes, and the removal of expired negative cache
// rows, which is all it does when the disk cache is disabled.
// write-pressure passes. No-op when the disk cache is disabled.
cache.StartEviction(imgcache.DefaultEvictionInterval)
// Writes the counts and the access times of cache hits that requests
// hand over, so that no request waits for the database to record them
cache.StartPendingCountWrites()
// Create the fetcher config
fetcherCfg := httpfetcher.DefaultConfig()
fetcherCfg.AllowHTTP = s.config.AllowHTTP
@@ -165,10 +155,7 @@ func (s *Handlers) initImageService() error {
// Initialize session manager (signing key is validated at config load
// time). Session cookies are always Secure/HttpOnly/SameSite=Strict.
// The random value that each logout replaces is saved in the database,
// so it outlasts a restart.
sessMgr, err := session.NewManagerWithDatabase(
context.Background(), s.config.SigningKey, s.db.DB())
sessMgr, err := session.NewManager(s.config.SigningKey)
if err != nil {
return err
}
internal/handlers/handlers_internal_test.go
+1
View File
@@ -47,6 +47,7 @@ func setupTestHandler(t *testing.T) *testFixtures {
cache, err := imgcache.NewCache(db, imgcache.CacheConfig{
StateDir: tmpDir,
CacheTTL: time.Hour,
NegativeTTL: 5 * time.Minute,
})
if err != nil {
internal/handlers/image.go
+30 -77
View File
@@ -9,18 +9,16 @@ import (
"strconv"
"time"
"github.com/go-chi/chi/v5"
"github.com/go-chi/chi/v5/middleware"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/magic"
)
// HandleImage handles the main image proxy route:
// /v1/image/<host>/<path>/<width>x<height>.<format>, or with no format
// /v1/image/<host>/<path>/<width>x<height>
// /v1/image/<host>/<path>/<width>x<height>.<format>
func (s *Handlers) HandleImage() http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
if s.refuseBlockedReferer(w, r) {
@@ -36,8 +34,8 @@ func (s *Handlers) HandleImage() http.HandlerFunc {
err := s.imgSvc.ValidateRequest(req)
if err != nil {
s.log.Warn("signature validation failed",
"host", req.Source.Host,
"path", req.Source.Path,
"host", req.SourceHost,
"path", req.SourcePath,
"error", err,
)
s.respondError(w, "unauthorized", http.StatusUnauthorized)
@@ -51,7 +49,7 @@ func (s *Handlers) HandleImage() http.HandlerFunc {
}
// Get cache key for logging
cacheKey := imagerequest.CacheKey(req)
cacheKey := imgcache.CacheKey(req)
// Get the image (from cache or fetch/process)
startTime := time.Now()
@@ -81,21 +79,20 @@ func (s *Handlers) HandleRobotsTxt() http.HandlerFunc {
}
}
// parseImageRequest parses the image URL's path and query parameters into
// an image request. On invalid input it writes an error response and
// parseImageRequest parses the wildcard path and query parameters into
// an ImageRequest. On invalid input it writes an error response and
// returns false.
func (s *Handlers) parseImageRequest(
w http.ResponseWriter, r *http.Request,
) (*imagerequest.Request, bool) {
// The path is parsed decoded once, as r.URL.Path holds it, and not from
// chi's wildcard: chi routes on the path as the client wrote it whenever
// that is not Go's own encoding of it, so its wildcard would still hold
// the %3F before a source query when, say, a "/" in the query is written
// as %2F
req, err := imagerequest.ParseImageURL(r.URL.Path)
) (*imgcache.ImageRequest, bool) {
// Get the wildcard path from chi
pathParam := chi.URLParam(r, "*")
// Parse the URL path
parsed, err := imgcache.ParseImagePath(pathParam)
if err != nil {
s.log.Warn("failed to parse image URL",
"path", r.URL.Path,
"path", pathParam,
"error", err,
)
s.respondError(w, "invalid image URL: "+err.Error(), http.StatusBadRequest)
@@ -103,6 +100,9 @@ func (s *Handlers) parseImageRequest(
return nil, false
}
// Convert to ImageRequest
req := parsed.ToImageRequest()
// Parse signature params from query string. r.URL.Query() would silently
// drop a pair it cannot decode, such as q=80%, so that q would be served
// at 85; a query string that cannot be decoded is refused instead. A
@@ -146,7 +146,7 @@ func (s *Handlers) parseImageRequest(
return nil, false
}
req.Transform.Quality, err = parseFormInt(query, "q",
req.Quality, err = parseFormInt(query, "q",
encurl.DefaultQuality, minQuality, maxQuality)
if err != nil {
s.respondError(w, fmt.Sprintf("%v, got %q", err, qStr),
@@ -158,23 +158,23 @@ func (s *Handlers) parseImageRequest(
// Only a fit missing from the URL is cover. A fit in the URL that is not a
// fit mode is refused by the fit-mode check below; that check would take an
// empty fit as missing, so an empty one is refused here.
req.Transform.FitMode = imagerequest.Fit(query.Get("fit"))
if query.Has("fit") && req.Transform.FitMode == "" {
req.FitMode = imgcache.FitMode(query.Get("fit"))
if query.Has("fit") && req.FitMode == "" {
s.respondError(w, `invalid fit: not a fit mode, got ""`, http.StatusBadRequest)
return nil, false
}
// Default fit mode if not set
if req.Transform.FitMode == "" {
req.Transform.FitMode = imagerequest.FitCover
if req.FitMode == "" {
req.FitMode = imgcache.FitCover
}
// Enforce dimension and fit-mode bounds, shared with the encrypted-URL
// route. Dimensions are already bounded by the path parser above; this
// also rejects an unrecognized fit mode with 400 instead of letting it
// reach the processor as a 500.
err = imagerequest.ValidateImageRequest(req)
err = imgcache.ValidateImageRequest(req)
if err != nil {
s.respondError(w, "invalid image request: "+err.Error(),
http.StatusBadRequest)
@@ -205,35 +205,13 @@ func parseExpires(query url.Values) (time.Time, error) {
return time.Unix(exp, 0), nil
}
// HandleTooManyRequests answers 429 Too Many Requests with the JSON error
// body the image routes send for their other errors. The image routes' rate
// limit calls it for a request over the limit.
func (s *Handlers) HandleTooManyRequests() http.HandlerFunc {
return func(w http.ResponseWriter, _ *http.Request) {
s.respondError(w, "too many requests, try again later",
http.StatusTooManyRequests)
}
}
// respondImageError maps image retrieval errors to HTTP responses.
func (s *Handlers) respondImageError(
w http.ResponseWriter, req *imagerequest.Request, err error,
w http.ResponseWriter, req *imgcache.ImageRequest, err error,
) {
// An upstream body whose first bytes are not those of the format its
// Content-Type names is the upstream's error, not pixa's: the image
// service has logged it as a refused source.
if errors.Is(err, magic.ErrMagicByteMismatch) ||
errors.Is(err, magic.ErrUnknownFormat) ||
errors.Is(err, magic.ErrNotEnoughData) {
s.respondError(w, "unsupported source format",
http.StatusUnsupportedMediaType)
return
}
s.log.Error("failed to get image",
"host", req.Source.Host,
"path", req.Source.Path,
"host", req.SourceHost,
"path", req.SourcePath,
"error", err,
)
@@ -251,38 +229,13 @@ func (s *Handlers) respondImageError(
}
if errors.Is(err, httpfetcher.ErrTooManyConnections) ||
errors.Is(err, imageprocessor.ErrTooManyImages) ||
errors.Is(err, imgcache.ErrProcessingTimedOut) {
errors.Is(err, imageprocessor.ErrTooManyImages) {
s.respondError(w, "server busy, try again later",
http.StatusServiceUnavailable)
return
}
if errors.Is(err, httpfetcher.ErrInvalidContentType) ||
errors.Is(err, imageprocessor.ErrUnsupportedInputFormat) {
s.respondError(w, "unsupported source format",
http.StatusUnsupportedMediaType)
return
}
if errors.Is(err, imageprocessor.ErrOutputTooLarge) {
s.respondError(w, fmt.Sprintf("size too large for the source: the side "+
"computed from its proportions is above %d",
imageprocessor.MaxOutputDimension), http.StatusBadRequest)
return
}
if errors.Is(err, imageprocessor.ErrAVIFOutputTooLarge) {
s.respondError(w, fmt.Sprintf("size too large for AVIF: the output "+
"would be above %d pixels", imageprocessor.MaxAVIFOutputPixels),
http.StatusBadRequest)
return
}
s.respondError(w, "internal error", http.StatusInternalServerError)
}
@@ -344,8 +297,8 @@ func notModified(w http.ResponseWriter, r *http.Request, etag string) bool {
// handling conditional and HEAD requests.
func (s *Handlers) writeImageResponse(
w http.ResponseWriter, r *http.Request,
req *imagerequest.Request, resp *imgcache.ImageResponse,
cacheKey imagerequest.VariantKey, startTime time.Time,
req *imgcache.ImageRequest, resp *imgcache.ImageResponse,
cacheKey imgcache.VariantKey, startTime time.Time,
) {
// Set response headers
w.Header().Set("Content-Type", resp.ContentType)
@@ -386,7 +339,7 @@ func (s *Handlers) writeImageResponse(
"cache_key", cacheKey,
"cache_status", resp.CacheStatus,
"duration_ms", duration.Milliseconds(),
"format", req.Transform.Format,
"format", req.Format,
"served_bytes", servedBytes,
"fetched_bytes", resp.FetchedBytes,
)
internal/handlers/image_cache_control_internal_test.go
+17 -24
View File
@@ -14,7 +14,6 @@ import (
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
@@ -32,6 +31,7 @@ func newSignedHostServer(
cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
StateDir: t.TempDir(),
CacheTTL: time.Hour,
NegativeTTL: 5 * time.Minute,
})
if err != nil {
@@ -108,15 +108,11 @@ func TestHandleImage_SignedURL_MaxAgeEndsAtExp(t *testing.T) {
h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
signedURL, err := h.imgSvc.GenerateSignedURL("", &imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
},
signedURL, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
SourceHost: signedHost,
SourcePath: photoPath,
Size: imgcache.Size{Width: 50, Height: 50},
Format: imgcache.FormatJPEG,
}, time.Minute)
if err != nil {
t.Fatalf("GenerateSignedURL() error = %v", err)
@@ -173,13 +169,13 @@ func TestHandleImageEnc_MaxAge(t *testing.T) {
tests := []struct {
name string
expires time.Time
expiresAt int64
wantAtLeast int
wantAtMost int
}{
{"60 second TTL", time.Now().Add(time.Minute), 50, 60},
{"two-year TTL", time.Now().Add(2 * 365 * 24 * time.Hour), 31536000, 31536000},
{"no TTL", time.Time{}, 31536000, 31536000},
{"60 second TTL", time.Now().Add(time.Minute).Unix(), 50, 60},
{"two-year TTL", time.Now().Add(2 * 365 * 24 * time.Hour).Unix(), 31536000, 31536000},
{"no TTL", 0, 31536000, 31536000},
}
for _, tt := range tests {
@@ -188,16 +184,13 @@ func TestHandleImageEnc_MaxAge(t *testing.T) {
h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
token, err := h.encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
},
Expires: tt.expires,
token, err := h.encGen.Generate(&encurl.Payload{
SourceHost: signedHost,
SourcePath: photoPath,
Width: 50,
Height: 50,
Format: imgcache.FormatJPEG,
ExpiresAt: tt.expiresAt,
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
internal/handlers/image_errors_internal_test.go
+10 -140
View File
@@ -14,7 +14,6 @@ import (
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/signature"
)
@@ -30,6 +29,7 @@ func newImageRoute(t *testing.T, fetcher httpfetcher.Fetcher) http.Handler {
cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
StateDir: t.TempDir(),
CacheTTL: time.Hour,
NegativeTTL: 5 * time.Minute,
})
if err != nil {
@@ -85,18 +85,15 @@ func photoURLWithSig(host, sig string, expires time.Time) string {
// photoSignature returns the signature of photoURL(host) at the default
// quality and fit, made with key and expiring at expires.
func photoSignature(key, host string, expires time.Time) string {
return signature.New(key).Sign(&imagerequest.Request{
Source: imagerequest.Source{
Host: host,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
Expires: expires,
return signature.New(key).Sign(&signature.Request{
SourceHost: host,
SourcePath: photoPath,
Width: 50,
Height: 50,
Format: string(imgcache.FormatJPEG),
Quality: 85,
FitMode: string(imgcache.FitCover),
Expires: expires,
})
}
@@ -268,130 +265,3 @@ func TestHandleImage_AllowlistOrSignature(t *testing.T) {
})
}
}
// TestHandleImage_InvalidHost_Returns400 sends image URLs whose host no URL
// host can be, and checks that each is refused with 400 naming the host as
// decoded: allowlistedHost with a character after it that a URL host cannot
// hold, percent-encoded, an IPv6 address without brackets, and brackets
// around something that is not an IPv6 address. A "?" or "#" after
// allowlistedHost would otherwise end the host when the source URL is read,
// so the request would pass the allowlist and be fetched and cached under a
// host that is not the one fetched.
func TestHandleImage_InvalidHost_Returns400(t *testing.T) {
t.Parallel()
photos := newPhotoFetcher(t, allowlistedHost)
tests := []struct {
name string
writtenHost string
decodedHost string
}{
{"? written as %3F", allowlistedHost + "%3Fx=1", allowlistedHost + "?x=1"},
{"# written as %23", allowlistedHost + "%23x", allowlistedHost + "#x"},
{"% written as %25", allowlistedHost + "%253F", allowlistedHost + "%3F"},
{`\ written as %5C`, allowlistedHost + "%5Cx", allowlistedHost + `\x`},
{"space written as %20", allowlistedHost + "%20", allowlistedHost + " "},
{"IPv6 address without brackets", "2001:db8::1", "2001:db8::1"},
{"IPv4 address in brackets", "[203.0.113.5]", "[203.0.113.5]"},
{"no address in brackets", "[abc]", "[abc]"},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
rec := sendGet(t, newImageRoute(t, photos), photoURL(tt.writtenHost))
checkErrorBody(t, rec, http.StatusBadRequest,
fmt.Sprintf("invalid image URL: invalid source host: %q",
tt.decodedHost))
})
}
}
// TestHandleImage_HostForms_Served checks that the image route serves, with
// a valid signature, the image at photoPath on a host name, an IPv4 address,
// an IPv6 address in brackets, and a host followed by ":" with or without a
// port.
func TestHandleImage_HostForms_Served(t *testing.T) {
t.Parallel()
hosts := []string{
allowlistedHost,
"img_1.example.com",
"203.0.113.5",
"[2001:db8::1]",
allowlistedHost + ":8443",
"[2001:db8::1]:8443",
allowlistedHost + ":",
}
photos := newPhotoFetcher(t, hosts...)
exp := time.Now().Add(time.Hour)
for _, host := range hosts {
t.Run(host, func(t *testing.T) {
t.Parallel()
sig := photoSignature(testSigningKey, host, exp)
rec := sendGet(t, newImageRoute(t, photos),
photoURLWithSig(host, sig, exp))
if rec.Code != http.StatusOK {
t.Errorf("status = %d, want %d: %s",
rec.Code, http.StatusOK, rec.Body)
}
})
}
}
// TestHandleImage_HashInSourcePathOrQuery_Returns400 sends image URLs whose
// source path or source query holds a "#", written as %23, and checks that
// each is refused with 400, the one signed for that source path included. The
// source URL would otherwise end at the "#" when it is fetched, so each text
// after it would fetch the image at photoPath and cache it under keys of its
// own.
func TestHandleImage_HashInSourcePathOrQuery_Returns400(t *testing.T) {
t.Parallel()
photos := newPhotoFetcher(t, allowlistedHost, signedHost)
exp := time.Now().Add(time.Hour)
sig := signature.New(testSigningKey).Sign(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath + "#x",
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
Expires: exp,
})
tests := []struct {
name string
target string
}{
{"# in the source path",
"/v1/image/" + allowlistedHost + photoPath + "%23x/50x50.jpeg"},
{"# in the source query",
"/v1/image/" + allowlistedHost + photoPath + "%3Fv=1%23x/50x50.jpeg"},
{"# in the source path, signed",
fmt.Sprintf("/v1/image/%s%s%%23x/50x50.jpeg?sig=%s&exp=%d",
signedHost, photoPath, sig, exp.Unix())},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
rec := sendGet(t, newImageRoute(t, photos), tt.target)
checkErrorBody(t, rec, http.StatusBadRequest,
`invalid image URL: invalid image path: `+
`the source path or query holds a "#"`)
})
}
}
internal/handlers/image_signature_internal_test.go
+19 -203
View File
@@ -9,7 +9,7 @@ import (
"time"
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/signature"
)
@@ -44,18 +44,15 @@ func TestHandleImage_SignatureCoversQualityAndFit(t *testing.T) {
expires := time.Now().Add(time.Hour)
signer := signature.New("test-signing-key-must-be-32-chars")
sig := signer.Sign(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: "/images/photo.jpg",
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
Expires: expires,
sig := signer.Sign(&signature.Request{
SourceHost: signedHost,
SourcePath: "/images/photo.jpg",
Width: 50,
Height: 50,
Format: string(imgcache.FormatJPEG),
Quality: 85,
FitMode: string(imgcache.FitCover),
Expires: expires,
})
signedURL := fmt.Sprintf("/v1/image/%s/images/photo.jpg/50x50.jpeg?sig=%s&exp=%d",
signedHost, sig, expires.Unix())
@@ -91,9 +88,9 @@ func TestHandleImage_GeneratedSignedURLVerifies(t *testing.T) {
tests := []struct {
name string
quality int
fitMode imagerequest.Fit
fitMode imgcache.FitMode
}{
{"quality 40 and fit contain", 40, imagerequest.FitContain},
{"quality 40 and fit contain", 40, imgcache.FitContain},
{"quality and fit unset", 0, ""},
}
@@ -103,17 +100,13 @@ func TestHandleImage_GeneratedSignedURLVerifies(t *testing.T) {
fix := setupTestHandler(t)
signedURL, err := fix.service.GenerateSignedURL("", &imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: "/images/photo.jpg",
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: tt.quality,
FitMode: tt.fitMode,
},
signedURL, err := fix.service.GenerateSignedURL("", &imgcache.ImageRequest{
SourceHost: signedHost,
SourcePath: "/images/photo.jpg",
Size: imgcache.Size{Width: 50, Height: 50},
Format: imgcache.FormatJPEG,
Quality: tt.quality,
FitMode: tt.fitMode,
}, time.Hour)
if err != nil {
t.Fatalf("GenerateSignedURL() error = %v", err)
@@ -176,180 +169,3 @@ func TestHandleImage_InvalidExp_Returns400(t *testing.T) {
})
}
}
// TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies sends URLs built
// by the service's signed-URL generator for source URLs with a query to the
// route, through a chi router: chi routes on the path as the client wrote it
// whenever that is not Go's own encoding of it. A 502 means the signature
// passed, so the route read the source path and query that were signed.
func TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies(t *testing.T) {
t.Parallel()
tests := []struct {
name string
query string
}{
{"slash and colon", "url=https://origin.example.com/cat.jpg"},
{"semicolon", "a=1;b=2"},
{"comma", "crop=0,0,50,50"},
{"equals and ampersand", "a=1&b=2"},
{"percent-escape", "name=my%20cat"},
{"question mark", "next=/a?b=1"},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
fix := setupTestHandler(t)
signedURL, err := fix.service.GenerateSignedURL("", &imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
Query: tt.query,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
},
}, time.Hour)
if err != nil {
t.Fatalf("GenerateSignedURL() error = %v", err)
}
status := getImage(t, fix, signedURL)
if status != http.StatusBadGateway {
t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
}
})
}
}
// TestHandleImage_SourceQueryEncodedAnyWay signs one source URL with a query
// and writes it into the image URL in ways the README allows: the "?" before
// the query and each "%" in it percent-encoded, and every other character as
// itself or percent-encoded. A 502 means the signature passed.
func TestHandleImage_SourceQueryEncodedAnyWay(t *testing.T) {
t.Parallel()
expires := time.Now().Add(time.Hour)
signer := signature.New("test-signing-key-must-be-32-chars")
sig := signer.Sign(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
Query: "url=https://origin.example.com/my%20cat.jpg",
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
Expires: expires,
})
tests := []struct {
name string
writtenQuery string
}{
{"only ? and % encoded",
"%3Furl=https://origin.example.com/my%2520cat.jpg"},
{"every reserved character encoded",
"%3Furl%3Dhttps%3A%2F%2Forigin.example.com%2Fmy%2520cat.jpg"},
{"lower-case hex digits",
"%3furl=https://origin.example.com/my%2520cat.jpg"},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
target := fmt.Sprintf("/v1/image/%s%s%s/50x50.jpeg?sig=%s&exp=%d",
signedHost, photoPath, tt.writtenQuery, sig, expires.Unix())
status := getImage(t, setupTestHandler(t), target)
if status != http.StatusBadGateway {
t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
}
})
}
}
// TestHandleImage_SourceURLHoldingPercent25Verifies signs a source path and a
// source query that each hold %25, the percent-escape of a literal "%", and
// sends each to the route written as the README says, with that "%" written as
// %25, and as GenerateSignedURL writes it. A 502 means the signature passed.
func TestHandleImage_SourceURLHoldingPercent25Verifies(t *testing.T) {
t.Parallel()
tests := []struct {
name string
sourcePath string
sourceQuery string
// writtenPathAndQuery is the source path and query as the README says
// to write them into the image URL
writtenPathAndQuery string
}{
{"path", "/sale/50%25off.jpg", "", "/sale/50%2525off.jpg"},
{"query", photoPath, "discount=50%25", photoPath + "%3Fdiscount=50%2525"},
}
for _, tt := range tests {
t.Run(tt.name+" written by the README rule", func(t *testing.T) {
t.Parallel()
expires := time.Now().Add(time.Hour)
signer := signature.New("test-signing-key-must-be-32-chars")
sig := signer.Sign(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: tt.sourcePath,
Query: tt.sourceQuery,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
Expires: expires,
})
target := fmt.Sprintf("/v1/image/%s%s/50x50.jpeg?sig=%s&exp=%d",
signedHost, tt.writtenPathAndQuery, sig, expires.Unix())
status := getImage(t, setupTestHandler(t), target)
if status != http.StatusBadGateway {
t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
}
})
t.Run(tt.name+" written by GenerateSignedURL", func(t *testing.T) {
t.Parallel()
fix := setupTestHandler(t)
signedURL, err := fix.service.GenerateSignedURL("", &imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: tt.sourcePath,
Query: tt.sourceQuery,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
},
}, time.Hour)
if err != nil {
t.Fatalf("GenerateSignedURL() error = %v", err)
}
status := getImage(t, fix, signedURL)
if status != http.StatusBadGateway {
t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
}
})
}
}
internal/handlers/imageenc.go
+16 -32
View File
@@ -14,9 +14,7 @@ import (
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
"sneak.berlin/go/pixa/internal/magic"
)
// HandleImageEnc handles requests to /v1/e/{token}/* for encrypted
@@ -38,11 +36,10 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
// Log the request
s.log.Debug("encrypted image request",
"host", req.Source.Host,
"path", req.Source.Path,
"dimensions", fmt.Sprintf("%dx%d",
req.Transform.Size.Width, req.Transform.Size.Height),
"format", req.Transform.Format,
"host", req.SourceHost,
"path", req.SourcePath,
"dimensions", fmt.Sprintf("%dx%d", req.Size.Width, req.Size.Height),
"format", req.Format,
)
// Fetch and process the image (no signature validation
@@ -90,10 +87,10 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
duration := time.Since(start)
s.log.Info("image served",
"request_id", middleware.GetReqID(ctx),
"cache_key", imagerequest.CacheKey(req),
"host", req.Source.Host,
"path", req.Source.Path,
"format", req.Transform.Format,
"cache_key", imgcache.CacheKey(req),
"host", req.SourceHost,
"path", req.SourcePath,
"format", req.Format,
"cache_status", resp.CacheStatus,
"served_bytes", written,
"duration_ms", duration.Milliseconds(),
@@ -102,12 +99,12 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
}
// parseImageEncRequest decrypts the token of an encrypted image URL into an
// image request and checks it. On a token that is missing, does not decrypt,
// ImageRequest and checks it. On a token that is missing, does not decrypt,
// has expired or asks for something not valid, it writes an error response
// and returns false.
func (s *Handlers) parseImageEncRequest(
w http.ResponseWriter, r *http.Request,
) (*imagerequest.Request, bool) {
) (*imgcache.ImageRequest, bool) {
// Extract token from URL
token := chi.URLParam(r, "token")
if token == "" {
@@ -117,7 +114,7 @@ func (s *Handlers) parseImageEncRequest(
}
// Decrypt and validate the payload
req, err := s.encGen.Parse(token)
payload, err := s.encGen.Parse(token)
if err != nil {
if errors.Is(err, encurl.ErrExpired) {
s.log.Debug("encrypted URL expired", "error", err)
@@ -132,11 +129,14 @@ func (s *Handlers) parseImageEncRequest(
return nil, false
}
// Convert payload to ImageRequest
req := payload.ToImageRequest()
// Apply the same dimension and fit-mode bounds as the plain image
// route: a sealed payload is trusted for its origin, not for staying
// within limits, so an over-limit size or unknown fit mode is a 400
// here rather than an out-of-memory or a 500 from the processor.
err = imagerequest.ValidateImageRequest(req)
err = imgcache.ValidateImageRequest(req)
if err != nil {
s.log.Debug("encrypted URL failed validation", "error", err)
s.respondError(w, "invalid encrypted URL: "+err.Error(),
@@ -158,25 +158,9 @@ func (s *Handlers) handleImageError(w http.ResponseWriter, err error) {
case errors.Is(err, httpfetcher.ErrUpstreamTimeout):
s.respondError(w, "upstream timeout", http.StatusGatewayTimeout)
case errors.Is(err, httpfetcher.ErrTooManyConnections),
errors.Is(err, imageprocessor.ErrTooManyImages),
errors.Is(err, imgcache.ErrProcessingTimedOut):
errors.Is(err, imageprocessor.ErrTooManyImages):
s.respondError(w, "server busy, try again later",
http.StatusServiceUnavailable)
case errors.Is(err, httpfetcher.ErrInvalidContentType),
errors.Is(err, imageprocessor.ErrUnsupportedInputFormat),
errors.Is(err, magic.ErrMagicByteMismatch),
errors.Is(err, magic.ErrUnknownFormat),
errors.Is(err, magic.ErrNotEnoughData):
s.respondError(w, "unsupported source format",
http.StatusUnsupportedMediaType)
case errors.Is(err, imageprocessor.ErrOutputTooLarge):
s.respondError(w, fmt.Sprintf("size too large for the source: the side "+
"computed from its proportions is above %d",
imageprocessor.MaxOutputDimension), http.StatusBadRequest)
case errors.Is(err, imageprocessor.ErrAVIFOutputTooLarge):
s.respondError(w, fmt.Sprintf("size too large for AVIF: the output "+
"would be above %d pixels", imageprocessor.MaxAVIFOutputPixels),
http.StatusBadRequest)
default:
s.log.Error("image request failed", "error", err)
s.respondError(w, "internal error", http.StatusInternalServerError)
internal/handlers/imageenc_internal_test.go
+12 -18
View File
@@ -10,7 +10,7 @@ import (
"github.com/go-chi/chi/v5"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
// newEncTestServer builds a router serving the encrypted-URL route with a
@@ -54,14 +54,11 @@ func TestHandleImageEnc_OverLimitDimension_Returns400(t *testing.T) {
encGen, srv := newEncTestServer(t)
token, err := encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: "cdn.example.com",
Path: "/photo.jpg",
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 100000, Height: 100000},
},
token, err := encGen.Generate(&encurl.Payload{
SourceHost: "cdn.example.com",
SourcePath: "/photo.jpg",
Width: 100000,
Height: 100000,
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
@@ -82,15 +79,12 @@ func TestHandleImageEnc_InvalidFitMode_Returns400(t *testing.T) {
encGen, srv := newEncTestServer(t)
token, err := encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: "cdn.example.com",
Path: "/photo.jpg",
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 800, Height: 600},
FitMode: imagerequest.Fit("bogus"),
},
token, err := encGen.Generate(&encurl.Payload{
SourceHost: "cdn.example.com",
SourcePath: "/photo.jpg",
Width: 800,
Height: 600,
FitMode: imgcache.FitMode("bogus"),
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
internal/handlers/imageenc_token_internal_test.go
+6 -10
View File
@@ -9,7 +9,6 @@ import (
"time"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// requireServedPhoto requires that rec answers 200 with the JPEG at photoPath
@@ -60,14 +59,11 @@ func TestHandleImageEnc_RejectedToken(t *testing.T) {
h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
photo := imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
},
photo := encurl.Payload{
SourceHost: signedHost,
SourcePath: photoPath,
Width: 50,
Height: 50,
}
valid, err := h.encGen.Generate(&photo)
@@ -76,7 +72,7 @@ func TestHandleImageEnc_RejectedToken(t *testing.T) {
}
expiredPhoto := photo
expiredPhoto.Expires = time.Now().Add(-time.Minute)
expiredPhoto.ExpiresAt = time.Now().Add(-time.Minute).Unix()
expired, err := h.encGen.Generate(&expiredPhoto)
if err != nil {
internal/handlers/jpegxl_default_internal_test.go
-168
View File
@@ -1,168 +0,0 @@
package handlers
import (
"fmt"
"log/slog"
"maps"
"net/http"
"net/http/httptest"
"net/url"
"strings"
"testing"
"time"
"github.com/davidbyttow/govips/v2/vips"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/signature"
)
// requireJPEGXL requires that rec answers 200 with a JPEG XL image.
func requireJPEGXL(t *testing.T, rec *httptest.ResponseRecorder) {
t.Helper()
if rec.Code != http.StatusOK {
t.Fatalf("status = %d, want %d; body %q",
rec.Code, http.StatusOK, rec.Body.String())
}
if got := rec.Header().Get("Content-Type"); got != jxlType {
t.Errorf("Content-Type = %q, want %s", got, jxlType)
}
if got := vips.DetermineImageType(rec.Body.Bytes()); got != vips.ImageTypeJXL {
t.Errorf("body is %s, want jxl", vips.ImageTypes[got])
}
}
// TestImageWithoutFormat_ServesJPEGXL verifies that a /v1/image/ URL whose
// last segment is a size with no format, 50x50 or orig, answers JPEG XL.
func TestImageWithoutFormat_ServesJPEGXL(t *testing.T) {
t.Parallel()
route := newImageRoute(t, newPhotoFetcher(t, allowlistedHost))
for _, size := range []string{"50x50", "orig"} {
target := "/v1/image/" + allowlistedHost + photoPath + "/" + size
requireJPEGXL(t, sendGet(t, route, target))
}
}
// TestImageWithoutFormat_SignedAsJXL verifies that a /v1/image/ URL with no
// format is signed as jxl: the signature made for the URL ending in .jxl is
// accepted for the same URL without .jxl.
func TestImageWithoutFormat_SignedAsJXL(t *testing.T) {
t.Parallel()
route := newImageRoute(t, newPhotoFetcher(t, signedHost))
expires := time.Now().Add(time.Hour)
sig := signature.New(testSigningKey).Sign(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJXL,
Quality: encurl.DefaultQuality,
FitMode: imagerequest.FitCover,
},
Expires: expires,
})
query := fmt.Sprintf("?sig=%s&exp=%d", sig, expires.Unix())
for _, size := range []string{"50x50.jxl", "50x50"} {
target := "/v1/image/" + signedHost + photoPath + "/" + size + query
requireJPEGXL(t, sendGet(t, route, target))
}
}
// TestImageEncWithoutFormat_ServesJPEGXL verifies that an encrypted URL whose
// token holds no format answers JPEG XL.
func TestImageEncWithoutFormat_ServesJPEGXL(t *testing.T) {
t.Parallel()
h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
token, err := h.encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
},
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
requireJPEGXL(t, getEncToken(srv, token))
}
// TestGeneratorPage_SelectsJPEGXL verifies that the generator page's format
// choice is JPEG XL until another is chosen.
func TestGeneratorPage_SelectsJPEGXL(t *testing.T) {
t.Parallel()
h, srv := newCSRFTestRouter(t)
req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil)
req.AddCookie(newSessionCookie(t, h))
rec := httptest.NewRecorder()
srv.ServeHTTP(rec, req)
if !strings.Contains(rec.Body.String(), `<option value="jxl" selected>`) {
t.Errorf("generator page does not select JPEG XL: %s", rec.Body.String())
}
}
// TestGeneratePost_NoFormat_MakesJPEGXLURL verifies that the generator form
// sent with an empty format field, or with none, makes a URL whose name ends
// in .jxl and which answers JPEG XL.
func TestGeneratePost_NoFormat_MakesJPEGXLURL(t *testing.T) {
t.Parallel()
photo := url.Values{
sourceURLField: {"https://" + signedHost + photoPath},
widthField: {"50"},
heightField: {"50"},
}
emptyFormat := maps.Clone(photo)
emptyFormat.Set(formatField, "")
for name, form := range map[string]url.Values{
"empty format field": emptyFormat,
"no format field": photo,
} {
t.Run(name, func(t *testing.T) {
t.Parallel()
_, imageSrv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
rec := generatePost(t, form)
match := generatedURLPattern.FindStringSubmatch(rec.Body.String())
if match == nil {
t.Fatalf("generator page shows no URL: %d %s",
rec.Code, rec.Body.String())
}
t.Logf("generated URL path: %s", match[1])
if !strings.HasSuffix(match[1], "/img.jxl") {
t.Errorf("generated URL %s does not end in /img.jxl", match[1])
}
imageRec := httptest.NewRecorder()
imageSrv.ServeHTTP(imageRec, httptest.NewRequestWithContext(
t.Context(), http.MethodGet, match[1], nil))
requireJPEGXL(t, imageRec)
})
}
}
internal/handlers/jpegxl_internal_test.go
-73
View File
@@ -1,73 +0,0 @@
package handlers
import (
"log/slog"
"net/http"
"testing"
"github.com/davidbyttow/govips/v2/vips"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// jxlType is the content type of JPEG XL.
const jxlType = "image/jxl"
// TestFormatForAccept_JPEGXL verifies that the format auto chooses JPEG XL
// when Accept names image/jxl, ahead of AVIF whatever their q, and AVIF when
// Accept refuses JPEG XL with q=0.
func TestFormatForAccept_JPEGXL(t *testing.T) {
t.Parallel()
tests := []struct {
name string
accept string
want imagerequest.Format
}{
{"JPEG XL-capable browser",
"image/jxl,image/avif,image/webp,image/*,*/*;q=0.8", imagerequest.FormatJXL},
{"JPEG XL only", jxlType, imagerequest.FormatJXL},
{"JPEG XL with a lower q than AVIF", "image/avif,image/jxl;q=0.5",
imagerequest.FormatJXL},
{"q=0 on JPEG XL", "image/jxl;q=0,image/avif,*/*", imagerequest.FormatAVIF},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
got, err := formatForAccept(tt.accept)
if got != tt.want || err != nil {
t.Errorf("formatForAccept(%q) = %q, %v, want %q",
tt.accept, got, err, tt.want)
}
})
}
}
// TestFormatAuto_JPEGXL requests an auto URL on each image route with an
// Accept header that names image/jxl, and checks that the answer is a JPEG XL
// image.
func TestFormatAuto_JPEGXL(t *testing.T) {
t.Parallel()
h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
signedURL, encryptedURL := autoPhotoURLs(t, h)
for _, target := range []string{signedURL, encryptedURL} {
rec := requestImage(t, srv, http.MethodGet, target,
"image/jxl,image/avif,image/webp,*/*;q=0.8")
gotType := rec.Header().Get("Content-Type")
if rec.Code != http.StatusOK || gotType != jxlType {
t.Errorf("%s: %d %s, want 200 %s; body %s",
target, rec.Code, gotType, jxlType, rec.Body)
continue
}
if got := vips.DetermineImageType(rec.Body.Bytes()); got != vips.ImageTypeJXL {
t.Errorf("%s: body is %s, want jxl", target, vips.ImageTypes[got])
}
}
}
internal/handlers/referer_blocklist_internal_test.go
+1
View File
@@ -49,6 +49,7 @@ func newRefererRoutes(t *testing.T) (http.Handler, *Handlers, *countingFetcher)
cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
StateDir: t.TempDir(),
CacheTTL: time.Hour,
NegativeTTL: 5 * time.Minute,
})
if err != nil {
internal/handlers/request_id_internal_test.go
+13 -19
View File
@@ -13,7 +13,8 @@ import (
"github.com/go-chi/chi/v5/middleware"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/encurl"
"sneak.berlin/go/pixa/internal/imgcache"
)
// signedPhotoURL returns a signed /v1/image/ URL, valid for a minute, for the
@@ -21,15 +22,11 @@ import (
func signedPhotoURL(t *testing.T, h *Handlers) string {
t.Helper()
signedURL, err := h.imgSvc.GenerateSignedURL("", &imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
},
signedURL, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
SourceHost: signedHost,
SourcePath: photoPath,
Size: imgcache.Size{Width: 50, Height: 50},
Format: imgcache.FormatJPEG,
}, time.Minute)
if err != nil {
t.Fatalf("GenerateSignedURL() error = %v", err)
@@ -43,15 +40,12 @@ func signedPhotoURL(t *testing.T, h *Handlers) string {
func encPhotoURL(t *testing.T, h *Handlers) string {
t.Helper()
token, err := h.encGen.Generate(&imagerequest.Request{
Source: imagerequest.Source{
Host: signedHost,
Path: photoPath,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
},
token, err := h.encGen.Generate(&encurl.Payload{
SourceHost: signedHost,
SourcePath: photoPath,
Width: 50,
Height: 50,
Format: imgcache.FormatJPEG,
})
if err != nil {
t.Fatalf("Generate() error = %v", err)
internal/handlers/server_busy_internal_test.go
+1 -42
View File
@@ -1,7 +1,6 @@
package handlers
import (
"context"
"fmt"
"log/slog"
"net/http"
@@ -11,7 +10,6 @@ import (
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/imgcache"
)
@@ -22,9 +20,7 @@ func TestServerBusyAnswers503(t *testing.T) {
t.Parallel()
h := &Handlers{log: slog.New(slog.DiscardHandler)}
req := &imagerequest.Request{
Source: imagerequest.Source{Host: "img.example.com", Path: "/a.jpg"},
}
req := &imgcache.ImageRequest{SourceHost: "img.example.com", SourcePath: "/a.jpg"}
for _, err := range []error{
fmt.Errorf("upstream fetch failed: %w", httpfetcher.ErrTooManyConnections),
@@ -51,40 +47,3 @@ func TestServerBusyAnswers503(t *testing.T) {
}
}
}
// TestProcessingTimedOutAnswers503 checks that respondImageError and
// handleImageError, which answer the errors of the two image routes, answer
// 503 with the server busy error when the image service reports that
// processing stopped at the deadline of the request doing it, wrapped as the
// service wraps it. A request that waited for that processing gets this error
// while its own deadline may have time left. The request's source only goes
// into a log line, so it is left empty.
func TestProcessingTimedOutAnswers503(t *testing.T) {
t.Parallel()
h := &Handlers{log: slog.New(slog.DiscardHandler)}
err := fmt.Errorf("%w: failed to encode: %w",
imgcache.ErrProcessingTimedOut, context.DeadlineExceeded)
plain := httptest.NewRecorder()
h.respondImageError(plain, &imagerequest.Request{}, err)
encrypted := httptest.NewRecorder()
h.handleImageError(encrypted, err)
for name, rec := range map[string]*httptest.ResponseRecorder{
"respondImageError": plain, "handleImageError": encrypted,
} {
t.Logf("%s: status = %d, body = %q", name, rec.Code, rec.Body.String())
if rec.Code != http.StatusServiceUnavailable {
t.Errorf("%s: status = %d, want %d",
name, rec.Code, http.StatusServiceUnavailable)
}
if !strings.Contains(rec.Body.String(), "server busy, try again later") {
t.Errorf("%s: body = %q, want the server busy error",
name, rec.Body.String())
}
}
}
internal/handlers/unsupported_source_internal_test.go
-56
View File
@@ -1,56 +0,0 @@
package handlers
import (
"fmt"
"log/slog"
"net/http"
"net/http/httptest"
"strings"
"testing"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestUnsupportedSourceFormatAnswers415 checks that both image routes answer
// 415 with a clear error when the upstream answers with a content type pixa
// does not accept, such as SVG, and when orig is asked of a source in a
// format the processor cannot name, wrapped as the service wraps them.
func TestUnsupportedSourceFormatAnswers415(t *testing.T) {
t.Parallel()
h := &Handlers{log: slog.New(slog.DiscardHandler)}
req := &imagerequest.Request{
Source: imagerequest.Source{Host: "img.example.com", Path: "/a.svg"},
}
for _, err := range []error{
fmt.Errorf("upstream fetch failed: %w: image/svg+xml",
httpfetcher.ErrInvalidContentType),
fmt.Errorf("image processing failed: %w: unknown",
imageprocessor.ErrUnsupportedInputFormat),
} {
plain := httptest.NewRecorder()
h.respondImageError(plain, req, err)
encrypted := httptest.NewRecorder()
h.handleImageError(encrypted, err)
for route, rec := range map[string]*httptest.ResponseRecorder{
"HandleImage": plain, "HandleImageEnc": encrypted,
} {
t.Logf("%s for %v: %d %s", route, err, rec.Code, rec.Body.String())
if rec.Code != http.StatusUnsupportedMediaType {
t.Errorf("%s for %v: status = %d, want %d",
route, err, rec.Code, http.StatusUnsupportedMediaType)
}
if !strings.Contains(rec.Body.String(), "unsupported source format") {
t.Errorf("%s for %v: body = %q, want the unsupported source format error",
route, err, rec.Body.String())
}
}
}
}
internal/httpfetcher/fetch_internal_test.go
-134
View File
@@ -9,7 +9,6 @@ import (
"net/http"
"net/http/httptest"
"slices"
"strconv"
"strings"
"sync"
"testing"
@@ -298,139 +297,6 @@ func TestFetchMaxResponseSizeEnforced(t *testing.T) {
}
}
// fetchWithMaxResponseSize serves handler as the fake upstream and fetches
// its /image route with MaxResponseSize set to maxResponseSize.
func fetchWithMaxResponseSize(
t *testing.T,
maxResponseSize int64,
handler http.HandlerFunc,
) *FetchResult {
t.Helper()
srv := httptest.NewServer(handler)
t.Cleanup(srv.Close)
cfg := DefaultConfig()
cfg.MaxResponseSize = maxResponseSize
f, _ := newServerFetcher(t, srv, cfg)
res := fetchImage(t, f, "/image")
t.Cleanup(func() { _ = res.Content.Close() })
return res
}
// TestFetchContentLengthBodyAtMaxResponseSize checks that a body sent with a
// Content-Length is read whole at exactly MaxResponseSize bytes and refused
// at one byte more.
func TestFetchContentLengthBodyAtMaxResponseSize(t *testing.T) {
t.Parallel()
const maxResponseSize = 8
for _, tc := range []struct {
size int
wantErr error
}{
{maxResponseSize, nil},
{maxResponseSize + 1, ErrResponseTooLarge},
} {
t.Run(strconv.Itoa(tc.size)+" bytes", func(t *testing.T) {
t.Parallel()
body := strings.Repeat("x", tc.size)
res := fetchWithMaxResponseSize(t, maxResponseSize,
func(w http.ResponseWriter, _ *http.Request) {
w.Header().Set("Content-Type", contentTypeJPEG)
w.Header().Set("Content-Length", strconv.Itoa(tc.size))
_, _ = io.WriteString(w, body)
})
if res.ContentLength != int64(tc.size) {
t.Fatalf("ContentLength = %d, want %d", res.ContentLength, tc.size)
}
data, err := io.ReadAll(res.Content)
t.Logf("body of %d bytes: read %d, error %v", tc.size, len(data), err)
if !errors.Is(err, tc.wantErr) {
t.Fatalf("read error = %v, want %v", err, tc.wantErr)
}
if err == nil && string(data) != body {
t.Errorf("read %q, want %q", data, body)
}
})
}
}
// TestFetchChunkedBodyAtMaxResponseSize checks that a chunked body is read
// whole at exactly MaxResponseSize bytes and refused at one byte more. The
// upstream sends the end of the body only once the test has read
// MaxResponseSize bytes, so the read after them comes before the end of the
// body has arrived, as it can from a real upstream.
func TestFetchChunkedBodyAtMaxResponseSize(t *testing.T) {
t.Parallel()
const maxResponseSize = 8
for _, tc := range []struct {
size int
wantErr error
}{
{maxResponseSize, nil},
{maxResponseSize + 1, ErrResponseTooLarge},
} {
t.Run(strconv.Itoa(tc.size)+" bytes", func(t *testing.T) {
t.Parallel()
body := strings.Repeat("x", tc.size)
endBody := make(chan struct{})
res := fetchWithMaxResponseSize(t, maxResponseSize,
func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", contentTypeJPEG)
_, _ = io.WriteString(w, body)
// With no Content-Length, flushing sends the body
// chunked; its end is sent when the handler returns.
_ = http.NewResponseController(w).Flush()
select {
case <-endBody:
case <-r.Context().Done():
}
})
if res.ContentLength != -1 {
t.Fatalf("ContentLength = %d, want -1 (chunked)", res.ContentLength)
}
head := make([]byte, maxResponseSize)
_, err := io.ReadFull(res.Content, head)
if err != nil {
t.Fatalf("read the first %d bytes: %v", maxResponseSize, err)
}
close(endBody)
rest, err := io.ReadAll(res.Content)
data := string(head) + string(rest)
t.Logf("body of %d bytes: read %d, error %v", tc.size, len(data), err)
if !errors.Is(err, tc.wantErr) {
t.Fatalf("read error = %v, want %v", err, tc.wantErr)
}
if err == nil && data != body {
t.Errorf("read %q, want %q", data, body)
}
})
}
}
func TestFetchSemaphoreReleasedOnError(t *testing.T) {
t.Parallel()
internal/httpfetcher/httpfetcher.go
+19 -66
View File
@@ -45,7 +45,6 @@ const (
contentTypeGIF = "image/gif"
contentTypeWebP = "image/webp"
contentTypeAVIF = "image/avif"
contentTypeJXL = "image/jxl"
contentTypeSVG = "image/svg+xml"
contentTypeOctetStream = "application/octet-stream"
)
@@ -59,17 +58,15 @@ const (
// builtinBlockedPrefixes are internal or special-use ranges that Go's
// net.IP predicates (IsPrivate, IsLinkLocalUnicast, and the like) do not
// already cover. They are always blocked, in addition to any
// operator-supplied networks. IPv4-mapped and IPv4-compatible IPv6
// addresses are read as the IPv4 address they hold before matching, so
// these IPv4 ranges are caught in all three forms.
// operator-supplied networks. IPv4-mapped IPv6 addresses are unmapped
// before matching, so these IPv4 ranges are caught in both forms.
//
//nolint:gochecknoglobals // immutable built-in blocklist
var builtinBlockedPrefixes = []netip.Prefix{
netip.MustParsePrefix("100.64.0.0/10"), // RFC 6598 CGNAT / carrier-grade NAT
netip.MustParsePrefix("192.0.0.0/24"), // RFC 6890 IETF protocol assignments
netip.MustParsePrefix("198.18.0.0/15"), // RFC 2544 benchmarking range
netip.MustParsePrefix("64:ff9b::/96"), // RFC 6052 NAT64 (maps onto IPv4)
netip.MustParsePrefix("64:ff9b:1::/48"), // RFC 8215 local-use NAT64 (maps onto IPv4)
netip.MustParsePrefix("100.64.0.0/10"), // RFC 6598 CGNAT / carrier-grade NAT
netip.MustParsePrefix("192.0.0.0/24"), // RFC 6890 IETF protocol assignments
netip.MustParsePrefix("198.18.0.0/15"), // RFC 2544 benchmarking range
netip.MustParsePrefix("64:ff9b::/96"), // RFC 6052 NAT64 (maps onto IPv4)
}
// Fetcher errors.
@@ -159,7 +156,7 @@ func DefaultConfig() *Config {
contentTypeGIF,
contentTypeWebP,
contentTypeAVIF,
contentTypeJXL,
contentTypeSVG,
},
AllowHTTP: false,
MaxConnectionsPerHost: DefaultMaxConnectionsPerHost,
@@ -475,18 +472,18 @@ func validateURL(ctx context.Context, rawURL string, allowHTTP bool) error {
return ErrUnsupportedScheme
}
parsedURL, err := neturl.Parse(rawURL)
if err != nil {
return fmt.Errorf("%w: %w", ErrInvalidHost, err)
}
// Hostname drops any port, and the brackets of an IPv6 address whether
// or not a port follows them
host := parsedURL.Hostname()
// Parse to extract host
host := extractHost(rawURL)
if host == "" {
return ErrInvalidHost
}
// Remove port if present
h, _, err := net.SplitHostPort(host)
if err == nil {
host = h
}
// Block obvious localhost patterns
if isLocalhost(host) {
return ErrSSRFBlocked
@@ -545,9 +542,6 @@ func isPrivateIP(ip net.IP) bool {
return true
}
// An IPv4-compatible IPv6 address is judged as the IPv4 address it holds
ip = ipv4CompatibleToIPv4(ip)
// Check for loopback
if ip.IsLoopback() {
return true
@@ -599,12 +593,7 @@ func isPrivateIP(ip net.IP) bool {
}
// isBlockedIP reports whether ip is refused, either by the built-in
// internal-range check or by one of the operator-supplied prefixes. An
// IPv4-compatible address (in ::/96) is refused when a prefix contains the
// address as written or the IPv4 address it holds. An IPv4-mapped address (in
// ::ffff:0:0/96) is matched only as the IPv4 address it holds: Go keeps a
// plain IPv4 address in that form too, and an IPv6 prefix such as ::/0 must
// not refuse every IPv4 address.
// internal-range check or by one of the operator-supplied prefixes.
func isBlockedIP(ip net.IP, blocked []netip.Prefix) bool {
if isPrivateIP(ip) {
return true
@@ -617,28 +606,11 @@ func isBlockedIP(ip net.IP, blocked []netip.Prefix) bool {
addr = addr.Unmap()
// ip read as IPv4 where it is or holds an IPv4 address, otherwise the
// zero netip.Addr, which no prefix contains. Matching asIPv4 as well as
// addr refuses more only for an IPv4-compatible address.
asIPv4, _ := netip.AddrFromSlice(ipv4CompatibleToIPv4(ip).To4())
return slices.ContainsFunc(blocked, func(prefix netip.Prefix) bool {
return prefix.Contains(addr) || prefix.Contains(asIPv4)
return prefix.Contains(addr)
})
}
// ipv4CompatibleToIPv4 returns the IPv4 address that an IPv4-compatible IPv6
// address (in ::/96, such as ::127.0.0.1) holds in its last four bytes, and
// any other address unchanged.
func ipv4CompatibleToIPv4(ip net.IP) net.IP {
addr, ok := netip.AddrFromSlice(ip)
if ok && netip.MustParsePrefix("::/96").Contains(addr) {
return ip[12:]
}
return ip
}
// ssrfSafeDialer validates IP addresses against the built-in blocked ranges
// before connecting. New wraps dialSSRFSafe with the operator-supplied
// blocklist; this entry point enforces the built-in ranges alone.
@@ -687,33 +659,14 @@ func dialSSRFSafe(
return nil, fmt.Errorf("%w to %s", errConnectFailed, host)
}
// limitedReader wraps a reader and refuses a body longer than remaining
// bytes with ErrResponseTooLarge. remaining goes below 0 once the body is
// found to be longer.
// limitedReader wraps a reader and limits the number of bytes read.
type limitedReader struct {
reader io.Reader
remaining int64
}
// Read reads at most the remaining bytes. Once they are read, it reads one
// more byte to tell the end of the body from more data: at the end it
// returns the wrapped reader's error, io.EOF; with more data it returns
// ErrResponseTooLarge, as does every later Read.
func (r *limitedReader) Read(p []byte) (int, error) {
if r.remaining < 0 {
return 0, ErrResponseTooLarge
}
if r.remaining == 0 {
var extra [1]byte
n, err := r.reader.Read(extra[:])
r.remaining -= int64(n)
if n == 0 {
return 0, err
}
if r.remaining <= 0 {
return 0, ErrResponseTooLarge
}
internal/httpfetcher/httpfetcher_internal_test.go
-38
View File
@@ -186,44 +186,6 @@ func TestIsPrivateIP(t *testing.T) {
}
}
// TestIsPrivateIPJudgesEmbeddedIPv4Address checks IPv6 addresses that hold an
// IPv4 address in their last four bytes: the IPv4-compatible form (::/96) and
// the NAT64 form (64:ff9b::/96). One holding a loopback, private or
// link-local IPv4 address is refused as that address is, and one holding a
// public IPv4 address in the IPv4-compatible form passes.
func TestIsPrivateIPJudgesEmbeddedIPv4Address(t *testing.T) {
t.Parallel()
tests := []struct {
ip string
want bool
}{
{"::127.0.0.1", true}, // loopback
{"::10.0.0.1", true}, // private
{"::169.254.169.254", true}, // link-local
{"64:ff9b::7f00:1", true}, // NAT64 form of 127.0.0.1
{"::8.8.8.8", false}, // public
}
for _, tc := range tests {
t.Run(tc.ip, func(t *testing.T) {
t.Parallel()
ip := net.ParseIP(tc.ip)
if ip == nil {
t.Fatalf("failed to parse IP %q", tc.ip)
}
got := isPrivateIP(ip)
t.Logf("isPrivateIP(%s) = %v", ip, got)
if got != tc.want {
t.Errorf("isPrivateIP(%q) = %v, want %v", tc.ip, got, tc.want)
}
})
}
}
func TestValidateURL_RejectsNonHTTPS(t *testing.T) {
t.Parallel()
internal/httpfetcher/jpegxl_internal_test.go
-20
View File
@@ -1,20 +0,0 @@
package httpfetcher
import "testing"
// TestJPEGXLContentType verifies that the fetcher accepts an upstream answer
// of type image/jxl by default, and that the mock fetcher serves a .jxl file
// as image/jxl.
func TestJPEGXLContentType(t *testing.T) {
t.Parallel()
const jxlType = "image/jxl"
if !New(DefaultConfig()).isAllowedContentType(jxlType) {
t.Errorf("isAllowedContentType(%q) = false, want true", jxlType)
}
if got := detectContentTypeFromPath("images/photo.jxl"); got != jxlType {
t.Errorf("detectContentTypeFromPath(photo.jxl) = %q, want %q", got, jxlType)
}
}
internal/httpfetcher/mock.go
-2
View File
@@ -109,8 +109,6 @@ func detectContentTypeFromPath(path string) string {
return contentTypeWebP
case strings.HasSuffix(path, ".avif"):
return contentTypeAVIF
case strings.HasSuffix(path, ".jxl"):
return contentTypeJXL
case strings.HasSuffix(path, ".svg"):
return contentTypeSVG
default:
internal/imageprocessor/avif_too_large_internal_test.go
-94
View File
@@ -1,94 +0,0 @@
package imageprocessor
import (
"bytes"
"encoding/binary"
"errors"
"os"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_RefusesAVIFAboveMaxPixels verifies that an AVIF output
// of more than MaxAVIFOutputPixels is refused with ErrAVIFOutputTooLarge
// before anything is decoded, whatever size and fit give it, the source's own
// size included, and that an AVIF output of at most that many pixels, or one
// in another format, is not. One input is a 64x32 PNG cut off in its pixel
// data. The other is testdata/red.avif, a 4x4 AVIF, with the size in its
// header changed to 4097x4096. libvips reads each input's size from its
// header but fails when it decodes its pixel data, so a request that gets
// that failure was not refused, and a refusal came before any decoding.
func TestImageProcessor_RefusesAVIFAboveMaxPixels(t *testing.T) {
t.Parallel()
whole := createTestPNG(t, 64, 32)
cutOff := whole[:len(whole)/2]
largeAVIF, err := os.ReadFile("testdata/red.avif")
if err != nil {
t.Fatalf("failed to read test AVIF: %v", err)
}
// The ispe box gives the width and then the height, 4 bytes each, after
// the box's type and its 4 bytes of version and flags
ispe := bytes.Index(largeAVIF, []byte("ispe"))
binary.BigEndian.PutUint32(largeAVIF[ispe+8:], 4097)
binary.BigEndian.PutUint32(largeAVIF[ispe+12:], 4096)
tests := []struct {
name string
input []byte
format imagerequest.Format
width, height int
fit imagerequest.Fit
refused bool
}{
{"AVIF at the limit", cutOff, imagerequest.FormatAVIF,
4096, 4096, imagerequest.FitCover, false},
{"AVIF above the limit", cutOff, imagerequest.FormatAVIF,
4096, 4097, imagerequest.FitCover, true},
{"WebP above the AVIF limit", cutOff, imagerequest.FormatWebP,
4096, 4097, imagerequest.FitCover, false},
// FitInside does not enlarge, so the output stays 64x32
{"AVIF inside a larger size", cutOff, imagerequest.FormatAVIF,
8192, 8192, imagerequest.FitInside, false},
// FitOutside scales 64x32 by 128 to cover 8192x1: 8192x4096
{"AVIF outside a smaller size", cutOff, imagerequest.FormatAVIF,
8192, 1, imagerequest.FitOutside, true},
// With no size, the output keeps the source's 4097x4096
{"AVIF of the source's size", largeAVIF, imagerequest.FormatAVIF,
0, 0, imagerequest.FitCover, true},
{"orig of an AVIF source", largeAVIF, imagerequest.FormatOriginal,
0, 0, imagerequest.FitCover, true},
{"JPEG of the source's size", largeAVIF, imagerequest.FormatJPEG,
0, 0, imagerequest.FitCover, false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
_, err := New(Params{}).Process(t.Context(), bytes.NewReader(tt.input),
&imagerequest.Transform{
Size: imagerequest.Size{Width: tt.width, Height: tt.height},
Format: tt.format,
FitMode: tt.fit,
})
t.Logf("Process() error = %v", err)
if tt.refused {
if !errors.Is(err, ErrAVIFOutputTooLarge) {
t.Errorf("Process() error = %v, want %v", err, ErrAVIFOutputTooLarge)
}
return
}
if err == nil || errors.Is(err, ErrAVIFOutputTooLarge) {
t.Errorf("Process() error = %v, want the failure to decode "+
"the input", err)
}
})
}
}
internal/imageprocessor/computed_side_internal_test.go
-135
View File
@@ -1,135 +0,0 @@
package imageprocessor
import (
"bytes"
"errors"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_RefusesComputedSideAboveMaximum verifies that a size
// with one side 0, which Process computes from the input's proportions, is
// served when that side comes out at MaxOutputDimension and refused with
// ErrOutputTooLarge when it would be above. A 4096x1 or 1x4096 input given
// 2 for its short side has 8192 for its long side.
func TestImageProcessor_RefusesComputedSideAboveMaximum(t *testing.T) {
t.Parallel()
tests := []struct {
name string
inputWidth, inputHeight int
size imagerequest.Size
wantErr error
}{
{"width at the maximum", 4096, 1,
imagerequest.Size{Height: 2}, nil},
{"width above the maximum", 4096, 1,
imagerequest.Size{Height: 3}, ErrOutputTooLarge},
{"height at the maximum", 1, 4096,
imagerequest.Size{Width: 2}, nil},
{"height above the maximum", 1, 4096,
imagerequest.Size{Width: 3}, ErrOutputTooLarge},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{
Size: tt.size,
Format: imagerequest.FormatJPEG,
FitMode: imagerequest.FitCover,
})
if result != nil {
t.Logf("Process() made %dx%d", result.Width, result.Height)
if max(result.Width, result.Height) != MaxOutputDimension {
t.Errorf("Process() made %dx%d, want a side of %d",
result.Width, result.Height, MaxOutputDimension)
}
}
if !errors.Is(err, tt.wantErr) {
t.Errorf("Process() error = %v, want %v", err, tt.wantErr)
}
})
}
}
// TestImageProcessor_ComputedSideIsAtLeastOne verifies that, for a size with
// one side 0, the side computed from the input's proportions is 1 where it
// would round down to 0, and that Process makes that size in every fit mode
// but FitOutside, which scales the input to cover the size and so can make
// it longer. Each case checks the size targetDimensions gives before it
// calls Process: with that side at 0, an 8192x1 input at 1300x0 makes
// libvips ask for about 39 GB with FitCover.
func TestImageProcessor_ComputedSideIsAtLeastOne(t *testing.T) {
t.Parallel()
tests := []struct {
name string
inputWidth, inputHeight int
size imagerequest.Size
wantWidth, wantHeight int
}{
{"8192x1 at 100x0", 8192, 1, imagerequest.Size{Width: 100}, 100, 1},
{"8192x1 at 1300x0", 8192, 1, imagerequest.Size{Width: 1300}, 1300, 1},
{"8192x2 at 100x0", 8192, 2, imagerequest.Size{Width: 100}, 100, 1},
{"1x8192 at 0x100", 1, 8192, imagerequest.Size{Height: 100}, 1, 100},
{"1x8192 at 0x1300", 1, 8192, imagerequest.Size{Height: 1300}, 1, 1300},
{"2x8192 at 0x100", 2, 8192, imagerequest.Size{Height: 100}, 1, 100},
}
fits := []imagerequest.Fit{
imagerequest.FitCover, imagerequest.FitContain, imagerequest.FitFill,
imagerequest.FitInside, imagerequest.FitOutside,
}
for _, tt := range tests {
for _, fit := range fits {
t.Run(tt.name+" "+string(fit), func(t *testing.T) {
t.Parallel()
width, height, err := targetDimensions(tt.size,
tt.inputWidth, tt.inputHeight)
if err != nil || width != tt.wantWidth || height != tt.wantHeight {
t.Fatalf("targetDimensions() = %dx%d, %v, want %dx%d",
width, height, err, tt.wantWidth, tt.wantHeight)
}
input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{
Size: tt.size,
Format: imagerequest.FormatJPEG,
FitMode: fit,
})
if err != nil {
t.Fatalf("Process() error = %v", err)
}
defer func() { _ = result.Content.Close() }()
t.Logf("Process() made %dx%d", result.Width, result.Height)
ok := result.Width == tt.wantWidth && result.Height == tt.wantHeight
if fit == imagerequest.FitOutside {
ok = result.Width >= tt.wantWidth && result.Height >= tt.wantHeight
}
if !ok {
t.Errorf("Process() made %dx%d, want %dx%d (at least, for %s)",
result.Width, result.Height, tt.wantWidth, tt.wantHeight,
imagerequest.FitOutside)
}
})
}
}
}
internal/imageprocessor/deadline_internal_test.go
-106
View File
@@ -1,106 +0,0 @@
package imageprocessor
import (
"bytes"
"context"
"errors"
"io"
"testing"
"time"
)
// readerAfterDeadline is a Process input whose first Read waits until done
// is closed, so the deadline passes after Process has taken its slot and
// before it encodes.
type readerAfterDeadline struct {
data *bytes.Reader
done <-chan struct{}
waited bool
}
func (r *readerAfterDeadline) Read(p []byte) (int, error) {
if !r.waited {
r.waited = true
<-r.done
}
return r.data.Read(p)
}
// inputNotToBeRead is a Process input that fails the test when it is read.
type inputNotToBeRead struct {
t *testing.T
}
func (r inputNotToBeRead) Read([]byte) (int, error) {
r.t.Error("Process read its input although its deadline had passed")
return 0, io.EOF
}
// TestProcessStopsWhenDeadlinePassed checks that Process returns
// context.DeadlineExceeded, and holds no slot afterwards, when its context's
// deadline has passed before it starts, then without reading its input, or
// while it reads its input. govips gives pixa no way to stop libvips once an
// encode has begun, so Process must not begin one for a request that has
// ended.
func TestProcessStopsWhenDeadlinePassed(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, 50, 50)
t.Run("before Process starts", func(t *testing.T) {
t.Parallel()
ctx, cancel := context.WithDeadline(t.Context(),
time.Now().Add(-time.Second))
defer cancel()
// With a slot free, the select in acquireSlot takes the slot or sees
// the ended context at random, so Process is called many times
for range 100 {
checkProcessStopsAtDeadline(ctx, t, inputNotToBeRead{t: t})
}
})
t.Run("while Process reads its input", func(t *testing.T) {
t.Parallel()
ctx, cancel := context.WithTimeout(t.Context(), 100*time.Millisecond)
defer cancel()
checkProcessStopsAtDeadline(ctx, t, &readerAfterDeadline{
data: bytes.NewReader(input), done: ctx.Done(),
})
})
}
// checkProcessStopsAtDeadline runs Process on input with ctx, whose deadline
// has passed by the time Process could encode, and fails the test unless
// Process returns context.DeadlineExceeded and gives its slot back.
func checkProcessStopsAtDeadline(
ctx context.Context, t *testing.T, input io.Reader,
) {
t.Helper()
proc := New(Params{MaxConcurrentProcessing: 1})
result, err := proc.Process(ctx, input, smallJPEGTransform())
if result != nil {
t.Logf("Process() made a %dx%d image after its deadline passed",
result.Width, result.Height)
_ = result.Content.Close()
}
t.Logf("Process() error = %v", err)
if !errors.Is(err, context.DeadlineExceeded) {
t.Errorf("Process() error = %v, want context.DeadlineExceeded", err)
}
if held := len(proc.processingSemaphore); held != 0 {
t.Errorf("%d slots still held after Process() returned", held)
}
}
internal/imageprocessor/empty_format_internal_test.go
-24
View File
@@ -1,24 +0,0 @@
package imageprocessor
import (
"bytes"
"errors"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_EmptyFormatRefused verifies that a request with no format
// is refused, as both image routes give every request a format before it is
// processed.
func TestImageProcessor_EmptyFormatRefused(t *testing.T) {
t.Parallel()
_, err := New(Params{}).Process(
t.Context(), bytes.NewReader(createTestJPEG(t, 20, 20)),
&imagerequest.Transform{},
)
if !errors.Is(err, ErrUnsupportedOutputFormat) {
t.Errorf("Process() error = %v, want %v", err, ErrUnsupportedOutputFormat)
}
}
internal/imageprocessor/encoder_settings_internal_test.go
-178
View File
@@ -1,178 +0,0 @@
package imageprocessor
import (
"bytes"
"image"
"image/color"
"image/png"
"testing"
"github.com/davidbyttow/govips/v2/vips"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// processedSize runs input through Process and returns the output's size in
// bytes.
func processedSize(
t *testing.T, input []byte, transform *imagerequest.Transform,
) int64 {
t.Helper()
result, err := New(Params{}).Process(t.Context(), bytes.NewReader(input), transform)
if err != nil {
t.Fatalf("Process() error = %v", err)
}
_ = result.Content.Close()
return result.ContentLength
}
// encodePNG encodes img as PNG with Go's encoder.
func encodePNG(t *testing.T, img image.Image) []byte {
t.Helper()
var buf bytes.Buffer
err := png.Encode(&buf, img)
if err != nil {
t.Fatalf("failed to encode test PNG: %v", err)
}
return buf.Bytes()
}
// decode decodes input with vips, as Process does.
func decode(t *testing.T, input []byte) *vips.ImageRef {
t.Helper()
img, err := vips.NewImageFromBuffer(input)
if err != nil {
t.Fatalf("failed to decode input: %v", err)
}
t.Cleanup(img.Close)
return img
}
// TestImageProcessor_PNGIsCompressed verifies that a PNG output is
// compressed: a flat 200x150 image, 90,000 bytes of raw pixels, comes out at
// a small fraction of that.
func TestImageProcessor_PNGIsCompressed(t *testing.T) {
t.Parallel()
const width, height = 200, 150
flat := image.NewRGBA(image.Rect(0, 0, width, height))
for y := range height {
for x := range width {
flat.Set(x, y, color.RGBA{R: 40, G: 120, B: 200, A: 255})
}
}
size := processedSize(t, encodePNG(t, flat),
&imagerequest.Transform{Format: imagerequest.FormatPNG})
const rawBytes = width * height * 3
if size > rawBytes/10 {
t.Errorf("PNG output is %d bytes, want under a tenth of its %d raw",
size, rawBytes)
}
}
// TestImageProcessor_WebPAtEffort2 verifies that WebP is saved at effort 2,
// not libvips' default of 4: the output is the size of the same image saved
// at effort 2.
func TestImageProcessor_WebPAtEffort2(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, 200, 150)
size := processedSize(t, input,
&imagerequest.Transform{Format: imagerequest.FormatWebP, Quality: 85})
want, _, err := decode(t, input).ExportWebp(&vips.WebpExportParams{
StripMetadata: true,
Quality: 85,
ReductionEffort: 2,
})
if err != nil {
t.Fatalf("ExportWebp() error = %v", err)
}
if size != int64(len(want)) {
t.Errorf("WebP output is %d bytes, want %d, the size at effort 2",
size, len(want))
}
}
// TestImageProcessor_AVIFAtEffort1 verifies that AVIF is saved at effort 1
// with 8 bits per sample: the output is the size of the same image saved
// with those settings. The source is 16-bit, which libvips saves with 12
// bits when it is not given a bit depth, and 640x480: on a small image,
// such as 64x48, efforts 1 and 2 give the same output.
func TestImageProcessor_AVIFAtEffort1(t *testing.T) {
t.Parallel()
const width, height = 640, 480
source := image.NewRGBA64(image.Rect(0, 0, width, height))
for y := range height {
for x := range width {
source.Set(x, y, color.RGBA64{
R: uint16((x * 65535 / width) & 0xffff),
G: uint16((y * 65535 / height) & 0xffff),
B: 32768,
A: 65535,
})
}
}
input := encodePNG(t, source)
size := processedSize(t, input,
&imagerequest.Transform{Format: imagerequest.FormatAVIF, Quality: 85})
want, _, err := decode(t, input).ExportAvif(&vips.AvifExportParams{
StripMetadata: true,
Quality: 85,
Effort: 1,
Bitdepth: 8,
})
if err != nil {
t.Fatalf("ExportAvif() error = %v", err)
}
if size != int64(len(want)) {
t.Errorf("AVIF output is %d bytes, want %d, the size at effort 1 "+
"and 8 bits", size, len(want))
}
}
// TestImageProcessor_JPEGXLAtEffort4 verifies that JPEG XL is saved at
// effort 4, not libvips' default of 7: the output is the size of the same
// image saved at effort 4, with the distance exportJXL gives quality 85.
func TestImageProcessor_JPEGXLAtEffort4(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, 200, 150)
size := processedSize(t, input,
&imagerequest.Transform{Format: imagerequest.FormatJXL, Quality: 85})
params := vips.NewJxlExportParams()
params.Quality = 85
params.Distance = jxlDistance(85)
params.Effort = 4
want, _, err := decode(t, input).ExportJxl(params)
if err != nil {
t.Fatalf("ExportJxl() error = %v", err)
}
if size != int64(len(want)) {
t.Errorf("JPEG XL output is %d bytes, want %d, the size at effort 4",
size, len(want))
}
}
internal/imageprocessor/fit_cover_internal_test.go
-278
View File
@@ -1,278 +0,0 @@
package imageprocessor
import (
"bytes"
"image"
"image/color"
"image/png"
"math"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_FitCoverServesThinSource verifies that FitCover serves
// a thin source at the requested size. An 8192x1 source scaled to cover
// 8192x8192 is 8192 times as long as the output on its long side. The centre
// of an 8192x1 source with the proportions of 1x8192 is 1/8192 of a pixel
// wide. Each case is also turned on its side.
func TestImageProcessor_FitCoverServesThinSource(t *testing.T) {
t.Parallel()
tests := []struct {
name string
inputWidth, inputHeight int
size imagerequest.Size
}{
{"8192x1 at 8192x8192", 8192, 1, imagerequest.Size{Width: 8192, Height: 8192}},
{"8192x1 at 1x8192", 8192, 1, imagerequest.Size{Width: 1, Height: 8192}},
{"1x8192 at 8192x8192", 1, 8192, imagerequest.Size{Width: 8192, Height: 8192}},
{"1x8192 at 8192x1", 1, 8192, imagerequest.Size{Width: 8192, Height: 1}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{
Size: tt.size,
Format: imagerequest.FormatJPEG,
FitMode: imagerequest.FitCover,
})
if err != nil {
t.Fatalf("Process() error = %v", err)
}
defer func() { _ = result.Content.Close() }()
t.Logf("Process() made %dx%d", result.Width, result.Height)
if result.Width != tt.size.Width || result.Height != tt.size.Height {
t.Errorf("Process() made %dx%d, want %dx%d",
result.Width, result.Height, tt.size.Width, tt.size.Height)
}
})
}
}
// createBandsPNG creates a PNG of three equal bands, red, green and blue,
// side by side when it is wider than tall and top to bottom otherwise.
func createBandsPNG(t *testing.T, width, height int) []byte {
t.Helper()
bands := []color.RGBA{
{R: 255, A: 255},
{G: 255, A: 255},
{B: 255, A: 255},
}
img := image.NewRGBA(image.Rect(0, 0, width, height))
for y := range height {
for x := range width {
band := 3 * y / height
if width > height {
band = 3 * x / width
}
img.Set(x, y, bands[band])
}
}
return encodePNG(t, img)
}
// TestImageProcessor_FitCoverCropsTheCentre verifies that FitCover keeps the
// centre of the source: a 300x100 source of red, green and blue bands side
// by side, or a 100x300 one with them top to bottom, comes out at 50x50 as
// its green band.
func TestImageProcessor_FitCoverCropsTheCentre(t *testing.T) {
t.Parallel()
tests := []struct {
name string
inputWidth, inputHeight int
}{
{"bands side by side", 300, 100},
{"bands top to bottom", 100, 300},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
input := createBandsPNG(t, tt.inputWidth, tt.inputHeight)
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatPNG,
FitMode: imagerequest.FitCover,
})
if err != nil {
t.Fatalf("Process() error = %v", err)
}
defer func() { _ = result.Content.Close() }()
output, err := png.Decode(result.Content)
if err != nil {
t.Fatalf("failed to decode output: %v", err)
}
bounds := output.Bounds()
t.Logf("Process() made %dx%d", bounds.Dx(), bounds.Dy())
if bounds.Dx() != 50 || bounds.Dy() != 50 {
t.Fatalf("Process() made %dx%d, want 50x50",
bounds.Dx(), bounds.Dy())
}
// Resampling may blend a little of the bands beside the
// green one into the output's edges.
for y := bounds.Min.Y; y < bounds.Max.Y; y++ {
for x := bounds.Min.X; x < bounds.Max.X; x++ {
r, g, b, _ := output.At(x, y).RGBA()
if r>>8 > 64 || g>>8 < 192 || b>>8 > 64 {
t.Fatalf("output pixel %d,%d is %d,%d,%d, want green",
x, y, r>>8, g>>8, b>>8)
}
}
}
})
}
}
// The greys of createSquarePNG, and the grey halfway between them.
const (
backgroundGrey = 192
squareGrey = 64
halfwayGrey = (backgroundGrey + squareGrey) / 2
)
// createSquarePNG creates a grey PNG side pixels square with a darker grey
// square squareSide pixels wide in its centre.
func createSquarePNG(t *testing.T, side, squareSide int) []byte {
t.Helper()
first := (side - squareSide) / 2
last := first + squareSide - 1
img := image.NewGray(image.Rect(0, 0, side, side))
for y := range side {
for x := range side {
grey := uint8(backgroundGrey)
if x >= first && x <= last && y >= first && y <= last {
grey = squareGrey
}
img.SetGray(x, y, color.Gray{Y: grey})
}
}
return encodePNG(t, img)
}
// squareLength returns how long the square is along greys, the greys of a
// row or column of the output that crosses it: the distance between the
// first and the last point where greys passes halfwayGrey, or 0 when there
// is no such point. Resampling blurs the square's edges over several
// pixels, and each point is placed between the two pixels on either side
// of it in proportion to their greys, so the length is measured to a
// fraction of a pixel.
func squareLength(greys []float64) float64 {
first, last := -1.0, -1.0
for i := 1; i < len(greys); i++ {
before, after := greys[i-1], greys[i]
if (before > halfwayGrey) == (after > halfwayGrey) {
continue
}
point := float64(i-1) + (before-halfwayGrey)/(before-after)
if first < 0 {
first = point
}
last = point
}
return last - first
}
// TestImageProcessor_FitCoverKeepsProportions verifies that FitCover scales
// both sides of the source by the same amount: a square in the centre of
// the source comes out square. Its width and height are measured along the
// output's middle row and column.
func TestImageProcessor_FitCoverKeepsProportions(t *testing.T) {
t.Parallel()
tests := []struct {
name string
side, squareSide int
size imagerequest.Size
}{
{"16x16 at 100x60", 16, 8, imagerequest.Size{Width: 100, Height: 60}},
{"16x16 at 60x100", 16, 8, imagerequest.Size{Width: 60, Height: 100}},
{"10x10 at 100x35", 10, 2, imagerequest.Size{Width: 100, Height: 35}},
{"10x10 at 35x100", 10, 2, imagerequest.Size{Width: 35, Height: 100}},
{"64x64 at 300x100", 64, 16, imagerequest.Size{Width: 300, Height: 100}},
{"64x64 at 100x300", 64, 16, imagerequest.Size{Width: 100, Height: 300}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
input := createSquarePNG(t, tt.side, tt.squareSide)
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{
Size: tt.size,
Format: imagerequest.FormatPNG,
FitMode: imagerequest.FitCover,
})
if err != nil {
t.Fatalf("Process() error = %v", err)
}
defer func() { _ = result.Content.Close() }()
output, err := png.Decode(result.Content)
if err != nil {
t.Fatalf("failed to decode output: %v", err)
}
bounds := output.Bounds()
if bounds.Dx() != tt.size.Width || bounds.Dy() != tt.size.Height {
t.Fatalf("Process() made %dx%d, want %dx%d",
bounds.Dx(), bounds.Dy(), tt.size.Width, tt.size.Height)
}
row := make([]float64, bounds.Dx())
for x := range row {
r, _, _, _ := output.At(x, bounds.Dy()/2).RGBA()
row[x] = float64(r >> 8)
}
column := make([]float64, bounds.Dy())
for y := range column {
r, _, _, _ := output.At(bounds.Dx()/2, y).RGBA()
column[y] = float64(r >> 8)
}
width, height := squareLength(row), squareLength(column)
t.Logf("square is %.2f wide and %.2f high", width, height)
if width == 0 || math.Abs(width-height) > 0.5 {
t.Errorf("square is %.2f wide and %.2f high, want it square",
width, height)
}
})
}
}
internal/imageprocessor/fit_outside_internal_test.go
-119
View File
@@ -1,119 +0,0 @@
package imageprocessor
import (
"bytes"
"errors"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_RefusesFitOutsideAboveMaximum verifies that FitOutside,
// which scales the input to cover the requested size and so past it on one
// side, is refused with ErrOutputTooLarge when that side would come out above
// MaxOutputDimension, and otherwise makes the scaled size. A 1024x256 or
// 256x1024 input scaled by 8 has 8192 for its long side.
func TestImageProcessor_RefusesFitOutsideAboveMaximum(t *testing.T) {
t.Parallel()
tests := []struct {
name string
inputWidth, inputHeight int
size imagerequest.Size
// wantWidth and wantHeight are the output's, 0 for a refusal
wantWidth, wantHeight int
}{
{"width above the maximum", 3000, 600,
imagerequest.Size{Width: 1, Height: 8192}, 0, 0},
{"height above the maximum", 600, 3000,
imagerequest.Size{Width: 8192, Height: 1}, 0, 0},
{"width at the maximum", 1024, 256,
imagerequest.Size{Width: 1, Height: 2048}, 8192, 2048},
{"height at the maximum", 256, 1024,
imagerequest.Size{Width: 2048, Height: 1}, 2048, 8192},
{"within the maximum", 3000, 600,
imagerequest.Size{Width: 1, Height: 1200}, 6000, 1200},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{
Size: tt.size,
Format: imagerequest.FormatJPEG,
FitMode: imagerequest.FitOutside,
})
if result != nil {
t.Logf("Process() made %dx%d", result.Width, result.Height)
}
if tt.wantWidth == 0 {
if !errors.Is(err, ErrOutputTooLarge) {
t.Errorf("Process() error = %v, want %v", err, ErrOutputTooLarge)
}
return
}
if err != nil {
t.Fatalf("Process() error = %v", err)
}
if result.Width != tt.wantWidth || result.Height != tt.wantHeight {
t.Errorf("Process() made %dx%d, want %dx%d",
result.Width, result.Height, tt.wantWidth, tt.wantHeight)
}
})
}
}
// TestImageProcessor_FitOutsideSideIsAtLeastOne verifies that FitOutside
// keeps each side at 1 or more when it works both sides out again from the
// larger scale. A side of 49 scaled to 1 is 49 times 1/49, which in floating
// point is just under 1 and so rounded down to 0, a width libvips refuses.
func TestImageProcessor_FitOutsideSideIsAtLeastOne(t *testing.T) {
t.Parallel()
tests := []struct {
name string
inputWidth, inputHeight int
size imagerequest.Size
wantWidth, wantHeight int
}{
{"49x8192 at 0x100", 49, 8192, imagerequest.Size{Height: 100}, 1, 167},
{"49x49 at 1x1", 49, 49, imagerequest.Size{Width: 1, Height: 1}, 1, 1},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{
Size: tt.size,
Format: imagerequest.FormatJPEG,
FitMode: imagerequest.FitOutside,
})
if err != nil {
t.Fatalf("Process() error = %v", err)
}
defer func() { _ = result.Content.Close() }()
t.Logf("Process() made %dx%d", result.Width, result.Height)
if result.Width != tt.wantWidth || result.Height != tt.wantHeight {
t.Errorf("Process() made %dx%d, want %dx%d",
result.Width, result.Height, tt.wantWidth, tt.wantHeight)
}
})
}
}
internal/imageprocessor/imageprocessor.go
+210 -480
View File
@@ -7,12 +7,11 @@ import (
"errors"
"fmt"
"io"
"runtime"
"sync"
"time"
"github.com/davidbyttow/govips/v2/vips"
"sneak.berlin/go/pixa/internal/config"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// vipsOnce ensures vips is initialized exactly once.
@@ -21,10 +20,11 @@ import (
var vipsOnce sync.Once
// initVips initializes libvips with quiet logging, one worker thread per
// image and no operation cache. Each request decodes different source
// bytes, so the operation cache would rarely be hit and would hold memory
// outside MaxConcurrentProcessing; repeated requests are served from
// pixa's disk cache instead.
// image and no operation cache. Process already works on one image per CPU
// by default, so more threads per image would only compete for the CPUs.
// Each request decodes different source bytes, so the operation cache
// would rarely be hit and would hold memory outside MaxConcurrentProcessing;
// repeated requests are served from pixa's disk cache instead.
func initVips() {
vipsOnce.Do(func() {
vips.LoggingSettings(nil, vips.LogLevelError)
@@ -55,6 +55,48 @@ func CheckJPEGXLSupport() error {
return nil
}
// Format represents supported output image formats.
type Format string
// Supported image output formats.
const (
FormatOriginal Format = "orig"
FormatJPEG Format = "jpeg"
FormatPNG Format = "png"
FormatWebP Format = "webp"
FormatAVIF Format = "avif"
FormatGIF Format = "gif"
)
// FitMode represents how to fit an image into requested dimensions.
type FitMode string
// Supported image fit modes.
const (
FitCover FitMode = "cover"
FitContain FitMode = "contain"
FitFill FitMode = "fill"
FitInside FitMode = "inside"
FitOutside FitMode = "outside"
)
// ErrInvalidFitMode is returned when an invalid fit mode is provided.
var ErrInvalidFitMode = errors.New("invalid fit mode")
// Size represents requested image dimensions.
type Size struct {
Width int
Height int
}
// Request holds the parameters for image processing.
type Request struct {
Size Size
Format Format
Quality int
FitMode FitMode
}
// Result contains the output of image processing.
type Result struct {
// Content is the processed image data.
@@ -90,39 +132,10 @@ var ErrInputTooLarge = errors.New("input image dimensions exceed maximum")
// configured byte limit.
var ErrInputDataTooLarge = errors.New("input data exceeds maximum allowed size")
// MaxOutputDimension is the maximum width or height of an output image, and
// so of a requested size (imagerequest.MaxDimension).
const MaxOutputDimension = imagerequest.MaxDimension
// ErrOutputTooLarge is returned, before resizing, when the output would have a
// side above MaxOutputDimension: the side of a size with one side 0, computed
// from the input's proportions, or with FitOutside, the side scaled past the
// requested size.
var ErrOutputTooLarge = errors.New("output image dimensions exceed maximum")
// MaxAVIFOutputPixels is the most pixels an AVIF output may have, so that an
// encode takes at most 40 seconds of the default downstream_timeout of 60
// seconds; AVIF is already at the lowest effort govips can set (avifEffort).
// With one thread, as pixad runs libvips, saving 4096x4096, 8192x2048 or
// 2048x8192 random pixels with an alpha channel takes up to about 34
// seconds, the slowest at any quality and at 8 or 16 bits per sample, and
// 5120x4096 at 8 bits already takes about 36.
const MaxAVIFOutputPixels = 4096 * 4096
// ErrAVIFOutputTooLarge is returned, before anything is decoded, when an AVIF
// output would have more than MaxAVIFOutputPixels pixels.
var ErrAVIFOutputTooLarge = errors.New("AVIF output has too many pixels")
// ErrUnsupportedOutputFormat is returned when the requested output format is
// not supported.
var ErrUnsupportedOutputFormat = errors.New("unsupported output format")
// ErrUnsupportedInputFormat is returned, before the input is decoded, when
// libvips reads the input's first bytes as another format than the source
// formats, or as none: for example an SVG whose first bytes pass the
// first-bytes check for AVIF.
var ErrUnsupportedInputFormat = errors.New("unsupported input format")
// ErrTooManyImages is returned when MaxConcurrentProcessing images are being
// processed and none finishes within ProcessingWaitTimeout.
var ErrTooManyImages = errors.New("too many images being processed at once")
@@ -149,7 +162,7 @@ type Params struct {
// If <= 0, DefaultMaxInputBytes is used.
MaxInputBytes int64
// MaxConcurrentProcessing is the most images processed at once.
// If <= 0, config.DefaultMaxConcurrentProcessing() is used.
// If <= 0, the number of CPUs Go uses (runtime.GOMAXPROCS(0)) is used.
MaxConcurrentProcessing int
}
@@ -165,7 +178,7 @@ func New(params Params) *ImageProcessor {
maxConcurrentProcessing := params.MaxConcurrentProcessing
if maxConcurrentProcessing <= 0 {
maxConcurrentProcessing = config.DefaultMaxConcurrentProcessing()
maxConcurrentProcessing = runtime.GOMAXPROCS(0)
}
return &ImageProcessor{
@@ -175,18 +188,14 @@ func New(params Params) *ImageProcessor {
}
}
// Process transforms an image according to transform. When
// Process transforms an image according to the request. When
// MaxConcurrentProcessing images are already being processed, it waits up
// to ProcessingWaitTimeout for one to finish, then fails with
// ErrTooManyImages. When ctx has ended once Process has a slot, or before it
// encodes, it returns ctx's error and gives the slot back. govips gives pixa
// no way to stop libvips once an encode has begun, so an encode keeps its
// slot until it finishes. An AVIF output of more than MaxAVIFOutputPixels is
// refused with ErrAVIFOutputTooLarge before anything is decoded.
// ErrTooManyImages.
func (p *ImageProcessor) Process(
ctx context.Context,
input io.Reader,
transform *imagerequest.Transform,
req *Request,
) (*Result, error) {
release, err := p.acquireSlot(ctx)
if err != nil {
@@ -195,20 +204,18 @@ func (p *ImageProcessor) Process(
defer release()
data, err := p.readInput(input)
// Read input with a size limit to prevent unbounded memory consumption.
// We read at most maxInputBytes+1 so we can detect if the input exceeds
// the limit without consuming additional memory.
limited := io.LimitReader(input, p.maxInputBytes+1)
data, err := io.ReadAll(limited)
if err != nil {
return nil, err
return nil, fmt.Errorf("failed to read input: %w", err)
}
// govips picks the libvips loader from the input's first bytes with
// DetermineImageType. Input whose first bytes it reads as no source
// format, such as SVG, which librsvg would render, is refused before
// libvips reads it.
inputFormat := p.detectFormat(vips.DetermineImageType(data))
sourceFormat, err := p.formatFromString(inputFormat)
if err != nil {
return nil, err
if int64(len(data)) > p.maxInputBytes {
return nil, ErrInputDataTooLarge
}
// Decode image
@@ -229,42 +236,33 @@ func (p *ImageProcessor) Process(
origWidth := img.Width()
origHeight := img.Height()
// Detect input format
inputFormat := p.detectFormat(img)
// Validate input dimensions to prevent DoS via decompression bombs
if origWidth > MaxInputDimension || origHeight > MaxInputDimension {
return nil, ErrInputTooLarge
}
// Determine target dimensions; too large ones are refused before resizing
targetWidth, targetHeight, err := targetDimensions(transform.Size,
origWidth, origHeight)
if err != nil {
return nil, err
}
// orig is the source's own format; encode refuses an empty format
outputFormat := transform.Format
if outputFormat == imagerequest.FormatOriginal {
outputFormat = sourceFormat
}
// Determine output dimensions; too large ones are refused before
// resizing, which with FitCover already decodes the input
outputWidth, outputHeight, err := outputDimensions(origWidth, origHeight,
targetWidth, targetHeight, transform.FitMode, outputFormat)
if err != nil {
return nil, err
}
// Determine target dimensions
targetWidth, targetHeight := targetDimensions(req.Size, origWidth, origHeight)
// Resize if needed
if targetWidth != origWidth || targetHeight != origHeight {
err := p.resize(img, outputWidth, outputHeight, transform.FitMode)
err := p.resize(img, targetWidth, targetHeight, req.FitMode)
if err != nil {
return nil, fmt.Errorf("failed to resize: %w", err)
}
}
// Determine output format
outputFormat := req.Format
if outputFormat == FormatOriginal || outputFormat == "" {
outputFormat = p.formatFromString(inputFormat)
}
// Encode to target format
output, err := p.encode(ctx, img, outputFormat, transform.Quality)
output, err := p.encode(img, outputFormat, req.Quality)
if err != nil {
return nil, fmt.Errorf("failed to encode: %w", err)
}
@@ -283,33 +281,21 @@ func (p *ImageProcessor) Process(
// targetDimensions calculates the output dimensions for a requested size,
// scaling proportionally when only one dimension is given and keeping the
// original dimensions when both are zero. A side scaled proportionally is
// rounded down but kept at 1 or more, as for a thin image it would round
// down to 0, a side of no pixels. It can come out above MaxOutputDimension,
// which is ErrOutputTooLarge.
func targetDimensions(
size imagerequest.Size, origWidth, origHeight int,
) (int, int, error) {
width, height := size.Width, size.Height
// original dimensions when both are zero.
func targetDimensions(size Size, origWidth, origHeight int) (int, int) {
switch {
case width == 0 && height == 0:
case size.Width == 0 && size.Height == 0:
// Both are 0: keep original size
return origWidth, origHeight, nil
case width == 0:
return origWidth, origHeight
case size.Width == 0:
// Only height specified: calculate width proportionally
width = max(1, origWidth*height/origHeight)
case height == 0:
return origWidth * size.Height / origHeight, size.Height
case size.Height == 0:
// Only width specified: calculate height proportionally
height = max(1, origHeight*width/origWidth)
return size.Width, origHeight * size.Width / origWidth
default:
return size.Width, size.Height
}
if width > MaxOutputDimension || height > MaxOutputDimension {
return 0, 0, fmt.Errorf("%w: %dx%d is above %d", ErrOutputTooLarge,
width, height, MaxOutputDimension)
}
return width, height, nil
}
// MIME types for the supported image formats.
@@ -319,7 +305,6 @@ const (
mimeGIF = "image/gif"
mimeWebP = "image/webp"
mimeAVIF = "image/avif"
mimeJXL = "image/jxl"
)
// SupportedInputFormats returns MIME types this processor can read.
@@ -330,38 +315,34 @@ func (p *ImageProcessor) SupportedInputFormats() []string {
mimeGIF,
mimeWebP,
mimeAVIF,
mimeJXL,
}
}
// SupportedOutputFormats returns formats this processor can write.
func (p *ImageProcessor) SupportedOutputFormats() []imagerequest.Format {
return []imagerequest.Format{
imagerequest.FormatJPEG,
imagerequest.FormatPNG,
imagerequest.FormatGIF,
imagerequest.FormatWebP,
imagerequest.FormatAVIF,
imagerequest.FormatJXL,
func (p *ImageProcessor) SupportedOutputFormats() []Format {
return []Format{
FormatJPEG,
FormatPNG,
FormatGIF,
FormatWebP,
FormatAVIF,
}
}
// FormatToMIME converts a Format to its MIME type string.
func FormatToMIME(format imagerequest.Format) string {
func FormatToMIME(format Format) string {
switch format {
case imagerequest.FormatJPEG:
case FormatJPEG:
return mimeJPEG
case imagerequest.FormatPNG:
case FormatPNG:
return mimePNG
case imagerequest.FormatWebP:
case FormatWebP:
return mimeWebP
case imagerequest.FormatGIF:
case FormatGIF:
return mimeGIF
case imagerequest.FormatAVIF:
case FormatAVIF:
return mimeAVIF
case imagerequest.FormatJXL:
return mimeJXL
case imagerequest.FormatOriginal, imagerequest.FormatAuto:
case FormatOriginal:
return "application/octet-stream"
default:
return "application/octet-stream"
@@ -395,50 +376,31 @@ func (p *ImageProcessor) WaitForProcessing(ctx context.Context) int {
// acquireSlot takes a slot in processingSemaphore, waiting at most
// processingWaitTimeout for one to free up, and returns the func that gives
// it back. When ctx has ended by the time it has a slot, it gives the slot
// back and returns ctx's error.
// it back. A free slot is taken even when ctx has ended; only the wait for
// one stops when ctx ends, as the rest of Process does not check ctx.
func (p *ImageProcessor) acquireSlot(ctx context.Context) (func(), error) {
release := func() { <-p.processingSemaphore }
select {
case p.processingSemaphore <- struct{}{}:
return release, nil
default:
}
select {
case p.processingSemaphore <- struct{}{}:
return release, nil
case <-time.After(p.processingWaitTimeout):
return nil, ErrTooManyImages
case <-ctx.Done():
return nil, ctx.Err()
}
release := func() { <-p.processingSemaphore }
// select takes the slot even when ctx has ended at the same moment
err := ctx.Err()
if err != nil {
release()
return nil, err
}
return release, nil
}
// readInput reads input with a size limit to prevent unbounded memory
// consumption, refusing more than maxInputBytes with ErrInputDataTooLarge. It
// reads at most maxInputBytes+1 so it can detect if the input exceeds the
// limit without consuming additional memory.
func (p *ImageProcessor) readInput(input io.Reader) ([]byte, error) {
data, err := io.ReadAll(io.LimitReader(input, p.maxInputBytes+1))
if err != nil {
return nil, fmt.Errorf("failed to read input: %w", err)
}
if int64(len(data)) > p.maxInputBytes {
return nil, ErrInputDataTooLarge
}
return data, nil
}
// detectFormat returns the format string for a govips image type.
func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
switch imageType {
// detectFormat returns the format string from a vips image.
func (p *ImageProcessor) detectFormat(img *vips.ImageRef) string {
format := img.Format()
switch format {
case vips.ImageTypeJPEG:
return "jpeg"
case vips.ImageTypePNG:
@@ -448,346 +410,135 @@ func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
case vips.ImageTypeWEBP:
return "webp"
case vips.ImageTypeAVIF, vips.ImageTypeHEIF:
return string(imagerequest.FormatAVIF)
case vips.ImageTypeJXL:
return string(imagerequest.FormatJXL)
return string(FormatAVIF)
case vips.ImageTypeUnknown, vips.ImageTypeMagick, vips.ImageTypePDF,
vips.ImageTypeSVG, vips.ImageTypeTIFF, vips.ImageTypeBMP,
vips.ImageTypeJP2K:
vips.ImageTypeJP2K, vips.ImageTypeJXL:
return "unknown"
default:
return "unknown"
}
}
// outputDimensions returns the dimensions resize gives an image of imgWidth x
// imgHeight for the target dimensions and fit mode, without resizing it, and
// refuses an output too large for format. With FitOutside one side can come
// out larger than the target; when it would be above MaxOutputDimension,
// outputDimensions returns ErrOutputTooLarge. An AVIF output of more than
// MaxAVIFOutputPixels is ErrAVIFOutputTooLarge.
func outputDimensions(
imgWidth, imgHeight, width, height int,
fit imagerequest.Fit, format imagerequest.Format,
) (int, int, error) {
scaleW := float64(width) / float64(imgWidth)
scaleH := float64(height) / float64(imgHeight)
outputWidth, outputHeight := width, height
switch fit {
case imagerequest.FitCover, imagerequest.FitFill, "":
// Cover crops, and fill stretches, to exactly the target dimensions
case imagerequest.FitContain:
// Fit within the target dimensions, maintaining aspect ratio. Scaled
// by the smaller scale, the short side of a thin image can round
// down to 0, which libvips refuses as a width, so each side is at
// least 1.
scale := min(scaleW, scaleH)
outputWidth = max(1, int(float64(imgWidth)*scale))
outputHeight = max(1, int(float64(imgHeight)*scale))
case imagerequest.FitInside:
// Same as contain, but only shrink
scale := min(scaleW, scaleH, 1)
outputWidth = max(1, int(float64(imgWidth)*scale))
outputHeight = max(1, int(float64(imgHeight)*scale))
case imagerequest.FitOutside:
// The smallest dimension fits, the other may exceed the target. A
// side scaled to 1 can come out just under 1 in floating point, as
// 49 times 1/49 does, and round down to 0, which libvips refuses as
// a width, so each side is at least 1.
scale := max(scaleW, scaleH)
outputWidth = max(1, int(float64(imgWidth)*scale))
outputHeight = max(1, int(float64(imgHeight)*scale))
default:
return 0, 0, fmt.Errorf("%w: %s", imagerequest.ErrInvalidFitMode, fit)
}
// The side FitOutside scales past the target is held to the maximum too
if max(outputWidth, outputHeight) > MaxOutputDimension {
return 0, 0, fmt.Errorf("%w: %dx%d is above %d", ErrOutputTooLarge,
outputWidth, outputHeight, MaxOutputDimension)
}
if format == imagerequest.FormatAVIF &&
outputWidth*outputHeight > MaxAVIFOutputPixels {
return 0, 0, fmt.Errorf("%w: %dx%d is above %d pixels",
ErrAVIFOutputTooLarge, outputWidth, outputHeight, MaxAVIFOutputPixels)
}
return outputWidth, outputHeight, nil
}
// resize resizes the image to width x height, the dimensions
// outputDimensions gives for the fit mode.
// resize resizes the image according to the fit mode.
func (p *ImageProcessor) resize(
img *vips.ImageRef, width, height int, fit imagerequest.Fit,
img *vips.ImageRef, width, height int, fit FitMode,
) error {
switch fit {
case imagerequest.FitCover, "":
// Crop the centre and resize to fill exact dimensions (default)
return cropCentreAndResize(img, width, height)
case FitCover, "":
// Resize and crop to fill exact dimensions (default)
return img.Thumbnail(width, height, vips.InterestingCentre)
case imagerequest.FitFill:
case FitContain:
// Resize to fit within dimensions, maintaining aspect ratio
imgW, imgH := img.Width(), img.Height()
scaleW := float64(width) / float64(imgW)
scaleH := float64(height) / float64(imgH)
scale := min(scaleW, scaleH)
newW := int(float64(imgW) * scale)
newH := int(float64(imgH) * scale)
return img.Thumbnail(newW, newH, vips.InterestingNone)
case FitFill:
// Resize to exact dimensions (may distort)
return img.ThumbnailWithSize(width, height, vips.InterestingNone, vips.SizeForce)
case imagerequest.FitInside:
// outputDimensions keeps the dimensions of an image that already fits
if img.Width() == width && img.Height() == height {
return nil
case FitInside:
// Same as contain, but only shrink
if img.Width() <= width && img.Height() <= height {
return nil // Already fits
}
return img.Thumbnail(width, height, vips.InterestingNone)
imgW, imgH := img.Width(), img.Height()
scaleW := float64(width) / float64(imgW)
scaleH := float64(height) / float64(imgH)
scale := min(scaleW, scaleH)
newW := int(float64(imgW) * scale)
newH := int(float64(imgH) * scale)
case imagerequest.FitContain, imagerequest.FitOutside:
return img.Thumbnail(width, height, vips.InterestingNone)
return img.Thumbnail(newW, newH, vips.InterestingNone)
case FitOutside:
// Resize so smallest dimension fits, may exceed target on other dimension
imgW, imgH := img.Width(), img.Height()
scaleW := float64(width) / float64(imgW)
scaleH := float64(height) / float64(imgH)
scale := max(scaleW, scaleH)
newW := int(float64(imgW) * scale)
newH := int(float64(imgH) * scale)
return img.Thumbnail(newW, newH, vips.InterestingNone)
default:
return fmt.Errorf("%w: %s", imagerequest.ErrInvalidFitMode, fit)
return fmt.Errorf("%w: %s", ErrInvalidFitMode, fit)
}
}
// cropCentreAndResize scales img by the same amount on both sides, the
// least that makes it cover width x height, and cuts the centre width x
// height out of it, as libvips' thumbnail does with InterestingCentre.
// thumbnail alone scales the whole image and copies the result into memory
// before it cuts, and for a thin image that is far larger than the image or
// the output: 8192x64 at 8192x8192 is 1048576x8192, about 24 GiB. So the
// centre is cut from img first, widened to whole pixels of img, which adds
// less than one pixel of img on each side, and thumbnail scales and cuts
// only that.
func cropCentreAndResize(img *vips.ImageRef, width, height int) error {
imgW, imgH := img.Width(), img.Height()
// An image wider than the requested proportions keeps its height and
// loses width down to imgH*width/height, any other keeps its width and
// loses height down to imgW*height/width. Half of what is lost comes
// off each side, rounded down to whole pixels, so the part kept holds
// all of the centre.
left, top := 0, 0
if imgW*height > imgH*width {
left = (imgW*height - imgH*width) / (2 * height) //nolint:mnd // each side
} else {
top = (imgH*width - imgW*height) / (2 * width) //nolint:mnd // each side
}
err := img.ExtractArea(left, top, imgW-2*left, imgH-2*top)
if err != nil {
return err
}
return img.Thumbnail(width, height, vips.InterestingCentre)
}
const defaultQuality = 85
// encode encodes an image to the specified format. govips gives pixa no way
// to stop libvips once an encode has begun, so when ctx has ended encode
// returns ctx's error without beginning one.
// encode encodes an image to the specified format.
func (p *ImageProcessor) encode(
ctx context.Context, img *vips.ImageRef, format imagerequest.Format,
quality int,
img *vips.ImageRef, format Format, quality int,
) ([]byte, error) {
err := ctx.Err()
if err != nil {
return nil, err
}
if quality <= 0 {
quality = defaultQuality
}
var params vips.ExportParams
switch format {
case FormatJPEG:
params = vips.ExportParams{
Format: vips.ImageTypeJPEG,
Quality: quality,
}
case FormatPNG:
params = vips.ExportParams{
Format: vips.ImageTypePNG,
}
case FormatGIF:
params = vips.ExportParams{
Format: vips.ImageTypeGIF,
}
case FormatWebP:
params = vips.ExportParams{
Format: vips.ImageTypeWEBP,
Quality: quality,
}
case FormatAVIF:
params = vips.ExportParams{
Format: vips.ImageTypeAVIF,
Quality: quality,
}
case FormatOriginal:
return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)
default:
return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)
}
// Stripping drops the ICC profile as well, and clients show an image
// with no profile as sRGB, so convert to sRGB first. "srgb" names
// libvips' built-in profile; govips' own sRGB path variable is set on
// first use but read without a lock, so concurrent requests race on it.
if img.HasICCProfile() {
err = img.TransformICCProfileWithFallback("srgb", "srgb")
err := img.TransformICCProfileWithFallback("srgb", "srgb")
if err != nil {
return nil, fmt.Errorf("failed to convert to sRGB: %w", err)
}
}
switch format {
case imagerequest.FormatJPEG:
return exportJPEG(img, quality)
// Drop EXIF, XMP, IPTC and the ICC profile. govips ignores this for
// GIF, which carries none of them.
params.StripMetadata = true
case imagerequest.FormatPNG:
return exportPNG(img)
case imagerequest.FormatGIF:
return exportGIF(img)
case imagerequest.FormatWebP:
return exportWebP(img, quality)
case imagerequest.FormatAVIF:
return exportAVIF(img, quality)
case imagerequest.FormatJXL:
return exportJXL(img, quality)
case imagerequest.FormatOriginal, imagerequest.FormatAuto:
return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)
default:
return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)
}
}
// govips sends libvips Go's zero value for some settings an export leaves
// out, such as no compression at all for PNG, so each export below sets
// every setting whose zero value is not what pixa wants. Stripping metadata
// drops EXIF, XMP, IPTC and the ICC profile.
// exportJPEG encodes img as JPEG at quality, without metadata. The settings
// it leaves out are at libvips' defaults.
func exportJPEG(img *vips.ImageRef, quality int) ([]byte, error) {
output, _, err := img.ExportJpeg(&vips.JpegExportParams{
StripMetadata: true,
Quality: quality,
})
return output, err
}
// pngCompression is libvips' default PNG compression, from 0 (none) to 9.
const pngCompression = 6
// exportPNG encodes img as PNG at libvips' default compression and row
// filter, without metadata.
func exportPNG(img *vips.ImageRef) ([]byte, error) {
output, _, err := img.ExportPng(&vips.PngExportParams{
StripMetadata: true,
Compression: pngCompression,
Filter: vips.PngFilterNone,
})
return output, err
}
// gifEffort is libvips' default GIF effort, from 1 to 10.
const gifEffort = 7
// exportGIF encodes img as GIF at libvips' default effort. govips cannot
// have libvips strip metadata from GIF, which carries none.
func exportGIF(img *vips.ImageRef) ([]byte, error) {
output, _, err := img.ExportGIF(&vips.GifExportParams{Effort: gifEffort})
return output, err
}
// webpEffort is the WebP effort, from 0 (fastest) to 6. It is below libvips'
// default of 4 so that an encode takes at most 40 seconds of the default
// downstream_timeout of 60 seconds. With one thread, as pixad runs libvips,
// saving an 8192x8192 image of random pixels with an alpha channel takes up
// to about 23 seconds at 2, and up to about 16 without one, at any quality;
// with an alpha channel, 3 takes about 50 seconds and 4 about 61.
const webpEffort = 2
// exportWebP encodes img as lossy WebP at quality and webpEffort, without
// metadata.
func exportWebP(img *vips.ImageRef, quality int) ([]byte, error) {
output, _, err := img.ExportWebp(&vips.WebpExportParams{
StripMetadata: true,
Quality: quality,
ReductionEffort: webpEffort,
})
return output, err
}
// avifEffort is the AVIF effort, from 0 (fastest) to 9; 1 is the lowest
// govips can set. With one thread, as pixad runs libvips, 1 takes about 52
// seconds to save an 8192x8192 RGB image of random pixels at quality 85,
// and about 96 with an alpha channel, against the default
// downstream_timeout of 60 seconds, so an AVIF output is held to
// MaxAVIFOutputPixels. On an image of milder noise, which 1 saves in about
// 12 seconds, 2 takes nearly a minute and libvips' default, 4, takes
// minutes.
const avifEffort = 1
// avifBitdepth is the AVIF bit depth, 8 bits per sample for every image.
// libvips would save a 16-bit image with 12, but at avifEffort that takes
// about 54 seconds for a 16-bit 8192x8192 image of milder noise, nearly all
// of the default downstream_timeout, and about 12 seconds with 8.
const avifBitdepth = 8
// exportAVIF encodes img as lossy AVIF at quality, avifEffort and
// avifBitdepth, without metadata.
func exportAVIF(img *vips.ImageRef, quality int) ([]byte, error) {
output, _, err := img.ExportAvif(&vips.AvifExportParams{
StripMetadata: true,
Quality: quality,
Effort: avifEffort,
Bitdepth: avifBitdepth,
})
return output, err
}
// jxlResolution is the resolution every JPEG XL image is saved with, in
// pixels per millimetre as libvips counts it: 72 dpi, what libvips gives a
// JPEG that names none.
const jxlResolution = 72 / 25.4
// jxlEffort is the JPEG XL effort, from 1 (fastest) to 9. It is below
// libvips' default of 7 so that an encode takes at most 40 seconds of the
// default downstream_timeout of 60 seconds. With one thread, as pixad runs
// libvips, saving an 8192x8192 image of random pixels with an alpha channel
// takes up to about 27 seconds at 4, and up to about 13 without one, at any
// quality; with an alpha channel, 5 takes about 43 seconds and 7 about 81.
const jxlEffort = 4
// exportJXL encodes img as JPEG XL at quality and jxlEffort, without
// metadata. govips sends libvips a distance, the JPEG XL encoder's own
// measure of quality, along with the quality, and libvips then uses the
// distance alone, so the quality is also given as a distance.
func exportJXL(img *vips.ImageRef, quality int) ([]byte, error) {
// libvips converts a CMYK image to sRGB before it saves WebP, AVIF or
// PNG, but cannot save one as JPEG XL. encode has already converted
// any image with an ICC profile to sRGB, so this is CMYK with none.
if img.Interpretation() == vips.InterpretationCMYK {
err := img.ToColorSpace(vips.InterpretationSRGB)
if err != nil {
return nil, fmt.Errorf("failed to convert CMYK to sRGB: %w", err)
}
}
// govips cannot make libvips strip metadata from JPEG XL, so it is
// removed from the image itself. RemoveMetadata removes EXIF, XMP and
// IPTC but keeps the ICC profile.
err := img.RemoveMetadata()
if err != nil {
return nil, err
}
err = img.RemoveICCProfile()
if err != nil {
return nil, err
}
// libvips 8.16 and later still write an EXIF block of their own, from
// the image's size, orientation and resolution, and fixed values. The
// image is upright, so its orientation is 1, but its resolution is still
// the source's.
toSave, err := img.CopyChangingResolution(jxlResolution, jxlResolution)
if err != nil {
return nil, err
}
defer toSave.Close()
params := vips.NewJxlExportParams()
params.Quality = quality
params.Distance = jxlDistance(quality)
params.Effort = jxlEffort
output, _, err := toSave.ExportJxl(params)
output, _, err := img.Export(&params)
if err != nil {
return nil, err
}
@@ -795,41 +546,20 @@ func exportJXL(img *vips.ImageRef, quality int) ([]byte, error) {
return output, nil
}
// jxlDistance turns a quality from 1 to 100 into the JPEG XL encoder's
// distance, with the formula libvips and libjxl use for their own quality
// setting, except that 100 stays lossy (distance 0.1) where libjxl makes it
// lossless.
//
//nolint:mnd // the constants of that formula
func jxlDistance(quality int) float64 {
q := float64(quality)
if quality >= 30 {
return 0.1 + (100-q)*0.09
}
return 53.0/3000.0*q*q - 23.0/20.0*q + 25.0
}
// formatFromString converts a format string from detectFormat to Format. A
// format detectFormat could not name is ErrUnsupportedInputFormat.
func (p *ImageProcessor) formatFromString(
format string,
) (imagerequest.Format, error) {
// formatFromString converts a format string to Format.
func (p *ImageProcessor) formatFromString(format string) Format {
switch format {
case "jpeg":
return imagerequest.FormatJPEG, nil
return FormatJPEG
case "png":
return imagerequest.FormatPNG, nil
return FormatPNG
case "gif":
return imagerequest.FormatGIF, nil
return FormatGIF
case "webp":
return imagerequest.FormatWebP, nil
case string(imagerequest.FormatAVIF):
return imagerequest.FormatAVIF, nil
case string(imagerequest.FormatJXL):
return imagerequest.FormatJXL, nil
return FormatWebP
case string(FormatAVIF):
return FormatAVIF
default:
return "", fmt.Errorf("%w: %s", ErrUnsupportedInputFormat, format)
return FormatJPEG
}
}
internal/imageprocessor/imageprocessor_internal_test.go
+72 -80
View File
@@ -15,7 +15,6 @@ import (
"testing"
"github.com/davidbyttow/govips/v2/vips"
"sneak.berlin/go/pixa/internal/imagerequest"
)
func TestMain(m *testing.M) {
@@ -88,7 +87,7 @@ func isAVIF(data []byte) bool {
brand := string(data[8:12])
return brand == string(imagerequest.FormatAVIF) || brand == "avis"
return brand == string(FormatAVIF) || brand == "avis"
}
// detectMIME is a minimal magic-byte detector for test assertions.
@@ -124,14 +123,14 @@ func TestImageProcessor_ResizeJPEG(t *testing.T) {
input := createTestJPEG(t, 800, 600)
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 400, Height: 300},
Format: imagerequest.FormatJPEG,
req := &Request{
Size: Size{Width: 400, Height: 300},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v", err)
}
@@ -170,13 +169,13 @@ func TestImageProcessor_ConvertToPNG(t *testing.T) {
input := createTestJPEG(t, 200, 150)
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 200, Height: 150},
Format: imagerequest.FormatPNG,
FitMode: imagerequest.FitCover,
req := &Request{
Size: Size{Width: 200, Height: 150},
Format: FormatPNG,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v", err)
}
@@ -197,7 +196,7 @@ func TestImageProcessor_ConvertToPNG(t *testing.T) {
// processAndCheckSize processes a test JPEG of the given input dimensions
// with the requested size and asserts the resulting dimensions.
func processAndCheckSize(
t *testing.T, inputW, inputH int, size imagerequest.Size, wantW, wantH int,
t *testing.T, inputW, inputH int, size Size, wantW, wantH int,
) {
t.Helper()
@@ -206,14 +205,14 @@ func processAndCheckSize(
input := createTestJPEG(t, inputW, inputH)
transform := &imagerequest.Transform{
req := &Request{
Size: size,
Format: imagerequest.FormatJPEG,
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v", err)
}
@@ -233,7 +232,7 @@ func TestImageProcessor_OriginalSize(t *testing.T) {
t.Parallel()
// Width and height 0: keep original size
processAndCheckSize(t, 640, 480, imagerequest.Size{Width: 0, Height: 0}, 640, 480)
processAndCheckSize(t, 640, 480, Size{Width: 0, Height: 0}, 640, 480)
}
func TestImageProcessor_FitContain(t *testing.T) {
@@ -246,14 +245,14 @@ func TestImageProcessor_FitContain(t *testing.T) {
// Should result in 400x200 (maintaining aspect ratio)
input := createTestJPEG(t, 800, 400)
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 400, Height: 400},
Format: imagerequest.FormatJPEG,
req := &Request{
Size: Size{Width: 400, Height: 400},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitContain,
FitMode: FitContain,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v", err)
}
@@ -271,7 +270,7 @@ func TestImageProcessor_ProportionalScale_WidthOnly(t *testing.T) {
// 800x600 image, request width=400 height=0
// Should scale proportionally to 400x300
processAndCheckSize(t, 800, 600, imagerequest.Size{Width: 400, Height: 0}, 400, 300)
processAndCheckSize(t, 800, 600, Size{Width: 400, Height: 0}, 400, 300)
}
func TestImageProcessor_ProportionalScale_HeightOnly(t *testing.T) {
@@ -279,7 +278,7 @@ func TestImageProcessor_ProportionalScale_HeightOnly(t *testing.T) {
// 800x600 image, request width=0 height=300
// Should scale proportionally to 400x300
processAndCheckSize(t, 800, 600, imagerequest.Size{Width: 0, Height: 300}, 400, 300)
processAndCheckSize(t, 800, 600, Size{Width: 0, Height: 300}, 400, 300)
}
func TestImageProcessor_ProcessPNG(t *testing.T) {
@@ -290,13 +289,13 @@ func TestImageProcessor_ProcessPNG(t *testing.T) {
input := createTestPNG(t, 400, 300)
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 200, Height: 150},
Format: imagerequest.FormatPNG,
FitMode: imagerequest.FitCover,
req := &Request{
Size: Size{Width: 200, Height: 150},
Format: FormatPNG,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v", err)
}
@@ -350,14 +349,14 @@ func TestImageProcessor_RejectsOversizedInput(t *testing.T) {
ctx := context.Background()
input := createTestJPEG(t, tt.width, tt.height)
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 100, Height: 100},
Format: imagerequest.FormatJPEG,
req := &Request{
Size: Size{Width: 100, Height: 100},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
_, err := proc.Process(ctx, bytes.NewReader(input), transform)
_, err := proc.Process(ctx, bytes.NewReader(input), req)
if err == nil {
t.Error("Process() should reject oversized input images")
}
@@ -378,14 +377,14 @@ func TestImageProcessor_AcceptsMaxDimensionInput(t *testing.T) {
// Create an image at exactly MaxInputDimension - should be accepted
input := createTestJPEG(t, MaxInputDimension, 100)
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 100, Height: 100},
Format: imagerequest.FormatJPEG,
req := &Request{
Size: Size{Width: 100, Height: 100},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf(
"Process() should accept images at MaxInputDimension, got error: %v",
@@ -398,9 +397,7 @@ func TestImageProcessor_AcceptsMaxDimensionInput(t *testing.T) {
// encodeAndCheck processes a 200x150 test JPEG into a 100x75 output of the
// given format and asserts the output MIME type and dimensions.
func encodeAndCheck(
t *testing.T, format imagerequest.Format, quality int, wantMIME string,
) {
func encodeAndCheck(t *testing.T, format Format, quality int, wantMIME string) {
t.Helper()
proc := New(Params{})
@@ -408,14 +405,14 @@ func encodeAndCheck(
input := createTestJPEG(t, 200, 150)
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 100, Height: 75},
req := &Request{
Size: Size{Width: 100, Height: 75},
Format: format,
Quality: quality,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v, want nil", err)
}
@@ -446,7 +443,7 @@ func encodeAndCheck(
func TestImageProcessor_EncodeWebP(t *testing.T) {
t.Parallel()
encodeAndCheck(t, imagerequest.FormatWebP, 80, mimeWebP)
encodeAndCheck(t, FormatWebP, 80, mimeWebP)
}
func TestImageProcessor_DecodeAVIF(t *testing.T) {
@@ -462,14 +459,14 @@ func TestImageProcessor_DecodeAVIF(t *testing.T) {
}
// Request resize and convert to JPEG
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 2, Height: 2},
Format: imagerequest.FormatJPEG,
req := &Request{
Size: Size{Width: 2, Height: 2},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v, want nil (AVIF decoding should work)", err)
}
@@ -503,14 +500,14 @@ func TestImageProcessor_RejectsOversizedInputData(t *testing.T) {
t.Fatalf("test JPEG must exceed %d bytes, got %d", limit, len(input))
}
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 100, Height: 75},
Format: imagerequest.FormatJPEG,
req := &Request{
Size: Size{Width: 100, Height: 75},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
_, err := proc.Process(ctx, bytes.NewReader(input), transform)
_, err := proc.Process(ctx, bytes.NewReader(input), req)
if err == nil {
t.Fatal("Process() should reject input exceeding maxInputBytes")
}
@@ -530,14 +527,14 @@ func TestImageProcessor_AcceptsInputWithinLimit(t *testing.T) {
proc := New(Params{MaxInputBytes: limit})
ctx := context.Background()
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 10, Height: 10},
Format: imagerequest.FormatJPEG,
req := &Request{
Size: Size{Width: 10, Height: 10},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
result, err := proc.Process(ctx, bytes.NewReader(input), transform)
result, err := proc.Process(ctx, bytes.NewReader(input), req)
if err != nil {
t.Fatalf("Process() error = %v, want nil", err)
}
@@ -564,18 +561,16 @@ func TestImageProcessor_DefaultMaxInputBytes(t *testing.T) {
func TestImageProcessor_EncodeAVIF(t *testing.T) {
t.Parallel()
encodeAndCheck(t, imagerequest.FormatAVIF, 85, mimeAVIF)
encodeAndCheck(t, FormatAVIF, 85, mimeAVIF)
}
// processAndDecode runs input through Process and decodes the output with
// vips, so a test can inspect the image a client would receive.
func processAndDecode(
t *testing.T, input []byte, transform *imagerequest.Transform,
) *vips.ImageRef {
func processAndDecode(t *testing.T, input []byte, req *Request) *vips.ImageRef {
t.Helper()
result, err := New(Params{}).Process(
context.Background(), bytes.NewReader(input), transform,
context.Background(), bytes.NewReader(input), req,
)
if err != nil {
t.Fatalf("Process() error = %v", err)
@@ -619,17 +614,15 @@ func TestImageProcessor_StripsEXIF(t *testing.T) {
t.Fatal("testdata/gps-exif.jpg has no GPS latitude")
}
formats := []imagerequest.Format{
imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatWebP,
imagerequest.FormatAVIF, imagerequest.FormatGIF, imagerequest.FormatOriginal,
formats := []Format{
FormatJPEG, FormatPNG, FormatWebP, FormatAVIF, FormatGIF, FormatOriginal,
}
for _, format := range formats {
t.Run(string(format), func(t *testing.T) {
t.Parallel()
output := processAndDecode(t, input,
&imagerequest.Transform{Format: format})
output := processAndDecode(t, input, &Request{Format: format})
if output.HasExif() {
t.Errorf("output has EXIF: %v", output.GetExif())
@@ -651,21 +644,21 @@ func TestImageProcessor_AppliesEXIFOrientation(t *testing.T) {
tests := []struct {
name string
size imagerequest.Size
size Size
wantW int
wantH int
}{
{name: "original size", size: imagerequest.Size{}, wantW: 8, wantH: 16},
{name: "width only", size: imagerequest.Size{Width: 4}, wantW: 4, wantH: 8},
{name: "original size", size: Size{}, wantW: 8, wantH: 16},
{name: "width only", size: Size{Width: 4}, wantW: 4, wantH: 8},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
output := processAndDecode(t, input, &imagerequest.Transform{
output := processAndDecode(t, input, &Request{
Size: tt.size,
Format: imagerequest.FormatPNG,
Format: FormatPNG,
})
if output.Width() != tt.wantW || output.Height() != tt.wantH {
@@ -701,8 +694,7 @@ func TestImageProcessor_ConvertsWideGamutToSRGB(t *testing.T) {
t.Fatalf("failed to read test JPEG: %v", err)
}
output := processAndDecode(t, input,
&imagerequest.Transform{Format: imagerequest.FormatPNG})
output := processAndDecode(t, input, &Request{Format: FormatPNG})
if output.HasICCProfile() {
t.Error("output has an ICC profile")
internal/imageprocessor/jpegxl_output_internal_test.go
-254
View File
@@ -1,254 +0,0 @@
package imageprocessor
import (
"bytes"
"io"
"math"
"os"
"testing"
"github.com/davidbyttow/govips/v2/vips"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_EncodeJPEGXL converts a JPEG to a smaller JPEG XL and
// checks the content type, and the format and size the output loads as.
func TestImageProcessor_EncodeJPEGXL(t *testing.T) {
t.Parallel()
transform := &imagerequest.Transform{
Size: imagerequest.Size{Width: 100, Height: 75},
Format: imagerequest.FormatJXL,
}
result, err := New(Params{}).Process(
t.Context(), bytes.NewReader(createTestJPEG(t, 200, 150)), transform,
)
if err != nil {
t.Fatalf("Process() error = %v", err)
}
defer func() { _ = result.Content.Close() }()
if result.ContentType != "image/jxl" {
t.Errorf("ContentType = %q, want image/jxl", result.ContentType)
}
data, err := io.ReadAll(result.Content)
if err != nil {
t.Fatalf("failed to read result: %v", err)
}
output, err := vips.NewImageFromBuffer(data)
if err != nil {
t.Fatalf("failed to load the output: %v", err)
}
defer output.Close()
if output.Format() != vips.ImageTypeJXL {
t.Errorf("output format = %s, want jxl", vips.ImageTypes[output.Format()])
}
if output.Width() != 100 || output.Height() != 75 {
t.Errorf("output size = %dx%d, want 100x75", output.Width(), output.Height())
}
}
// TestImageProcessor_JPEGXLQuality verifies that the quality reaches the JPEG
// XL encoder: the same image comes out smaller at quality 30 than at 90.
func TestImageProcessor_JPEGXLQuality(t *testing.T) {
t.Parallel()
input := createTestJPEG(t, 400, 300)
outputBytes := make(map[int]int64)
for _, quality := range []int{30, 90} {
result, err := New(Params{}).Process(t.Context(),
bytes.NewReader(input),
&imagerequest.Transform{Format: imagerequest.FormatJXL, Quality: quality})
if err != nil {
t.Fatalf("Process() at quality %d error = %v", quality, err)
}
_ = result.Content.Close()
outputBytes[quality] = result.ContentLength
}
if outputBytes[30] >= outputBytes[90] {
t.Errorf("%d bytes at quality 30, %d at 90, want fewer at 30",
outputBytes[30], outputBytes[90])
}
}
// TestImageProcessor_JPEGXLDropsSourceEXIF verifies that none of the source's
// EXIF reaches a JPEG XL output. libvips 8.16 and later write an EXIF block of
// their own into JPEG XL (orientation, resolution, size, colour space and
// fixed defaults), and govips cannot ask them to leave it out, so the test
// looks for the source's fields rather than for no EXIF at all.
func TestImageProcessor_JPEGXLDropsSourceEXIF(t *testing.T) {
t.Parallel()
input, err := os.ReadFile("testdata/gps-exif.jpg")
if err != nil {
t.Fatalf("failed to read test JPEG: %v", err)
}
exif := processAndDecode(t, input,
&imagerequest.Transform{Format: imagerequest.FormatJXL}).GetExif()
for _, field := range []string{
"exif-ifd0-Make", "exif-ifd0-Model", "exif-ifd2-BodySerialNumber",
"exif-ifd2-DateTimeOriginal", "exif-ifd3-GPSLatitude",
"exif-ifd3-GPSLongitude",
} {
if value, found := exif[field]; found {
t.Errorf("output has %s: %s", field, value)
}
}
}
// TestImageProcessor_JPEGXLDropsSourceResolution verifies that the source's
// resolution does not reach the EXIF block libvips 8.16 and later write into
// JPEG XL. A JPEG XL image holds its resolution in that block alone, so the
// resolution the output loads with is the block's.
func TestImageProcessor_JPEGXLDropsSourceResolution(t *testing.T) {
t.Parallel()
// dpi-300.jpg is a flat 8x8 grey image with a resolution of 300 dpi.
input, err := os.ReadFile("testdata/dpi-300.jpg")
if err != nil {
t.Fatalf("failed to read test JPEG: %v", err)
}
output := processAndDecode(t, input,
&imagerequest.Transform{Format: imagerequest.FormatJXL})
// libvips gives the resolution in pixels per millimetre.
xDPI := math.Round(output.ResX() * 25.4)
yDPI := math.Round(output.ResY() * 25.4)
if xDPI == 300 || yDPI == 300 {
t.Errorf("output resolution = %vx%v dpi, the source's", xDPI, yDPI)
}
}
// TestImageProcessor_JPEGXLAppliesEXIFOrientation verifies that a JPEG XL
// output is turned upright, as TestImageProcessor_AppliesEXIFOrientation does
// for PNG.
func TestImageProcessor_JPEGXLAppliesEXIFOrientation(t *testing.T) {
t.Parallel()
// orientation-6.jpg is stored 16x8, red on the left and blue on the
// right, with EXIF orientation 6 (turn 90 degrees clockwise to view).
// Upright it is 8x16, red on top and blue below.
input, err := os.ReadFile("testdata/orientation-6.jpg")
if err != nil {
t.Fatalf("failed to read test JPEG: %v", err)
}
output := processAndDecode(t, input,
&imagerequest.Transform{Format: imagerequest.FormatJXL})
if output.Width() != 8 || output.Height() != 16 {
t.Fatalf("output is %dx%d, want 8x16", output.Width(), output.Height())
}
top, err := output.GetPoint(4, 0)
if err != nil {
t.Fatalf("GetPoint() error = %v", err)
}
bottom, err := output.GetPoint(4, 15)
if err != nil {
t.Fatalf("GetPoint() error = %v", err)
}
if top[0] <= top[2] || bottom[2] <= bottom[0] {
t.Errorf("top pixel = %v, bottom pixel = %v, want red above blue",
top, bottom)
}
}
// TestImageProcessor_JPEGXLConvertsWideGamutToSRGB verifies that a JPEG XL
// output is converted to sRGB, as TestImageProcessor_ConvertsWideGamutToSRGB
// does for PNG. It does not check for an ICC profile, as libvips reports one
// for every JPEG XL image it loads.
func TestImageProcessor_JPEGXLConvertsWideGamutToSRGB(t *testing.T) {
t.Parallel()
// display-p3.jpg is a flat 8x8 image with the Display P3 profile
// embedded, filled with Display P3 (234, 51, 35), which is sRGB red.
input, err := os.ReadFile("testdata/display-p3.jpg")
if err != nil {
t.Fatalf("failed to read test JPEG: %v", err)
}
output := processAndDecode(t, input,
&imagerequest.Transform{Format: imagerequest.FormatJXL})
pixel, err := output.GetPoint(4, 4)
if err != nil {
t.Fatalf("GetPoint() error = %v", err)
}
want := []float64{255, 0, 0}
for i := range want {
if math.Abs(pixel[i]-want[i]) > 5 {
t.Fatalf("pixel = %v, want within 5 of %v", pixel, want)
}
}
}
// TestImageProcessor_JPEGXLFromCMYK verifies that a CMYK JPEG with no ICC
// profile can be served as JPEG XL, in sRGB.
func TestImageProcessor_JPEGXLFromCMYK(t *testing.T) {
t.Parallel()
// cmyk.jpg is a flat 8x8 CMYK image with no ICC profile, filled with
// full cyan and no magenta, yellow or black.
input, err := os.ReadFile("testdata/cmyk.jpg")
if err != nil {
t.Fatalf("failed to read test JPEG: %v", err)
}
output := processAndDecode(t, input,
&imagerequest.Transform{Format: imagerequest.FormatJXL})
if output.Bands() != 3 {
t.Fatalf("output has %d bands, want 3", output.Bands())
}
pixel, err := output.GetPoint(4, 4)
if err != nil {
t.Fatalf("GetPoint() error = %v", err)
}
// Cyan in sRGB: little red, much green and blue.
if pixel[0] > 50 || pixel[1] < 100 || pixel[2] < 200 {
t.Errorf("pixel = %v, want cyan", pixel)
}
}
// TestJXLDistance verifies the JPEG XL distance for a few qualities: 90 is
// distance 1, the encoder's own default, and 100 stays lossy.
func TestJXLDistance(t *testing.T) {
t.Parallel()
tests := []struct {
quality int
want float64
}{
{quality: 100, want: 0.1},
{quality: 90, want: 1},
{quality: 30, want: 6.4},
{quality: 20, want: 9.0667},
}
for _, tt := range tests {
got := jxlDistance(tt.quality)
if math.Abs(got-tt.want) > 0.0001 {
t.Errorf("jxlDistance(%d) = %v, want %v", tt.quality, got, tt.want)
}
}
}
internal/imageprocessor/max_concurrent_processing_internal_test.go
+33 -59
View File
@@ -11,8 +11,6 @@ import (
"testing"
"testing/iotest"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// errTestReadFailed is the error the unreadable test input returns.
@@ -78,13 +76,13 @@ func (r *gatedReader) Read(p []byte) (int, error) {
return n, err
}
// smallJPEGTransform asks for a 5x5 JPEG.
func smallJPEGTransform() *imagerequest.Transform {
return &imagerequest.Transform{
Size: imagerequest.Size{Width: 5, Height: 5},
Format: imagerequest.FormatJPEG,
// smallJPEGRequest asks for a 5x5 JPEG.
func smallJPEGRequest() *Request {
return &Request{
Size: Size{Width: 5, Height: 5},
Format: FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
FitMode: FitCover,
}
}
@@ -94,7 +92,7 @@ func processInBackground(
proc *ImageProcessor, reader *gatedReader, results chan<- error,
) {
go func() {
result, err := proc.Process(context.Background(), reader, smallJPEGTransform())
result, err := proc.Process(context.Background(), reader, smallJPEGRequest())
if err == nil {
_ = result.Content.Close()
}
@@ -117,14 +115,14 @@ func waitForEntries(t *testing.T, entered <-chan struct{}, count int) {
}
}
func TestNewDefaultsMaxConcurrentProcessingToHalfTheCPUs(t *testing.T) {
func TestNewDefaultsMaxConcurrentProcessingToCPUs(t *testing.T) {
t.Parallel()
for _, limit := range []int{0, -1} {
proc := New(Params{MaxConcurrentProcessing: limit})
if got := cap(proc.processingSemaphore); got != max(runtime.GOMAXPROCS(0)/2, 1) {
t.Errorf("MaxConcurrentProcessing %d: %d slots, want %d, half the CPUs",
limit, got, max(runtime.GOMAXPROCS(0)/2, 1))
if got := cap(proc.processingSemaphore); got != runtime.GOMAXPROCS(0) {
t.Errorf("MaxConcurrentProcessing %d: %d slots, want %d, one per CPU",
limit, got, runtime.GOMAXPROCS(0))
}
}
@@ -134,30 +132,6 @@ func TestNewDefaultsMaxConcurrentProcessingToHalfTheCPUs(t *testing.T) {
}
}
// TestNewDefaultIsHalfTheCPUsAndAtLeastOne checks that New, given no
// MaxConcurrentProcessing, makes one slot for every two CPUs Go uses,
// rounded down, and one slot when Go uses one CPU.
//
//nolint:paralleltest // it sets GOMAXPROCS, which other tests read
func TestNewDefaultIsHalfTheCPUsAndAtLeastOne(t *testing.T) {
cpusBefore := runtime.GOMAXPROCS(0)
t.Cleanup(func() { runtime.GOMAXPROCS(cpusBefore) })
for _, tc := range []struct{ cpus, want int }{
{1, 1}, {2, 1}, {3, 1}, {8, 4},
} {
runtime.GOMAXPROCS(tc.cpus)
got := cap(New(Params{}).processingSemaphore)
t.Logf("GOMAXPROCS %d: %d slots", tc.cpus, got)
if got != tc.want {
t.Errorf("GOMAXPROCS %d: %d slots, want %d", tc.cpus, got, tc.want)
}
}
}
// TestProcessNeverExceedsMaxConcurrentProcessing starts more Process calls
// than MaxConcurrentProcessing allows and holds the first ones inside
// Process until the test lets them go. No more than the limit may be
@@ -239,7 +213,7 @@ func TestProcessWaitsThenFailsWhenNoSlotFrees(t *testing.T) {
start := time.Now()
_, err := proc.Process(context.Background(), bytes.NewReader(input),
smallJPEGTransform())
smallJPEGRequest())
if !errors.Is(err, ErrTooManyImages) {
t.Fatalf("Process() error = %v, want ErrTooManyImages", err)
}
@@ -265,38 +239,38 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
valid := createTestJPEG(t, 10, 10)
unsupported := smallJPEGTransform()
unsupported := smallJPEGRequest()
unsupported.Format = "bmp"
cases := []struct {
name string
input io.Reader
transform *imagerequest.Transform
name string
input io.Reader
req *Request
// want is the error Process must return; nil means any error.
want error
}{
{
name: "input cannot be read",
input: iotest.ErrReader(errTestReadFailed),
transform: smallJPEGTransform(),
want: errTestReadFailed,
name: "input cannot be read",
input: iotest.ErrReader(errTestReadFailed),
req: smallJPEGRequest(),
want: errTestReadFailed,
},
{
name: "input over the byte limit",
input: bytes.NewReader(createTestJPEG(t, 800, 600)),
transform: smallJPEGTransform(),
want: ErrInputDataTooLarge,
name: "input over the byte limit",
input: bytes.NewReader(createTestJPEG(t, 800, 600)),
req: smallJPEGRequest(),
want: ErrInputDataTooLarge,
},
{
name: "input not an image",
input: strings.NewReader("not an image"),
transform: smallJPEGTransform(),
name: "input not an image",
input: strings.NewReader("not an image"),
req: smallJPEGRequest(),
},
{
name: "output format not supported",
input: bytes.NewReader(valid),
transform: unsupported,
want: ErrUnsupportedOutputFormat,
name: "output format not supported",
input: bytes.NewReader(valid),
req: unsupported,
want: ErrUnsupportedOutputFormat,
},
}
@@ -307,7 +281,7 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
proc := New(Params{MaxInputBytes: 4096, MaxConcurrentProcessing: 1})
proc.processingWaitTimeout = 100 * time.Millisecond
_, err := proc.Process(context.Background(), tc.input, tc.transform)
_, err := proc.Process(context.Background(), tc.input, tc.req)
if err == nil || (tc.want != nil && !errors.Is(err, tc.want)) {
t.Fatalf("Process() error = %v, want %v", err, tc.want)
}
@@ -317,7 +291,7 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
}
result, err := proc.Process(context.Background(), bytes.NewReader(valid),
smallJPEGTransform())
smallJPEGRequest())
if err != nil {
t.Fatalf("Process() after the error = %v, want nil", err)
}
internal/imageprocessor/orig_format_internal_test.go
-41
View File
@@ -1,41 +0,0 @@
package imageprocessor
import (
"bytes"
"errors"
"testing"
"github.com/davidbyttow/govips/v2/vips"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_OrigOfUnnamedFormatRefused verifies that orig of a TIFF
// input, which is not a source format, is refused with
// ErrUnsupportedInputFormat before it is decoded, and not saved as JPEG.
func TestImageProcessor_OrigOfUnnamedFormatRefused(t *testing.T) {
t.Parallel()
img, err := vips.NewImageFromBuffer(createTestPNG(t, 20, 20))
if err != nil {
t.Fatalf("failed to decode test PNG: %v", err)
}
t.Cleanup(img.Close)
tiff, _, err := img.ExportTiff(vips.NewTiffExportParams())
if err != nil {
t.Fatalf("failed to save test TIFF: %v", err)
}
result, err := New(Params{}).Process(
t.Context(), bytes.NewReader(tiff),
&imagerequest.Transform{Format: imagerequest.FormatOriginal},
)
if result != nil {
t.Logf("Process() returned %s", result.ContentType)
}
if !errors.Is(err, ErrUnsupportedInputFormat) {
t.Errorf("Process() error = %v, want %v", err, ErrUnsupportedInputFormat)
}
}
internal/imageprocessor/source_formats_internal_test.go
-50
View File
@@ -1,50 +0,0 @@
package imageprocessor
import (
"bytes"
"io"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestImageProcessor_LoadsEachSourceFormat verifies that an image in each of
// the six source formats, saved by the processor itself, is loaded and saved
// again in its own format (orig).
func TestImageProcessor_LoadsEachSourceFormat(t *testing.T) {
t.Parallel()
proc := New(Params{})
for _, format := range []imagerequest.Format{
imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatGIF,
imagerequest.FormatWebP, imagerequest.FormatAVIF, imagerequest.FormatJXL,
} {
saved, err := proc.Process(t.Context(),
bytes.NewReader(createTestPNG(t, 20, 20)),
&imagerequest.Transform{Format: format})
if err != nil {
t.Fatalf("saving the test image as %s: %v", format, err)
}
source, err := io.ReadAll(saved.Content)
if err != nil {
t.Fatalf("reading the %s image: %v", format, err)
}
result, err := proc.Process(t.Context(), bytes.NewReader(source),
&imagerequest.Transform{Format: imagerequest.FormatOriginal})
if err != nil {
t.Errorf("orig of the %s image: %v", format, err)
continue
}
t.Logf("orig of the %s image: %s", format, result.ContentType)
if result.ContentType != FormatToMIME(format) {
t.Errorf("orig of the %s image is %s, want %s",
format, result.ContentType, FormatToMIME(format))
}
}
}
internal/imageprocessor/testdata/cmyk.jpg
Vendored
BIN
View File
Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 352 B

internal/imageprocessor/testdata/dpi-300.jpg
Vendored
BIN
View File
Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 799 B

internal/imagerequest/imagerequest.go
-147
View File
@@ -1,147 +0,0 @@
// Package imagerequest holds the image request type, its parts, its checks,
// the parsing of the /v1/image/ path, the variant key and the source key. It
// imports no other package of this repo, so every package that handles an
// image request can import it.
package imagerequest
import (
"errors"
"net/url"
"time"
)
// ErrInvalidFitMode is returned when an invalid fit mode is provided.
var ErrInvalidFitMode = errors.New("invalid fit mode")
// Format represents supported output image formats.
type Format string
// Supported image output formats.
const (
FormatOriginal Format = "orig"
FormatJPEG Format = "jpeg"
FormatPNG Format = "png"
FormatWebP Format = "webp"
FormatAVIF Format = "avif"
FormatJXL Format = "jxl"
FormatGIF Format = "gif"
// FormatAuto stands for JPEG XL, AVIF, WebP or JPEG, chosen for each
// request from its Accept header once the URL's signature or token has
// been checked; it is never processed or cached as itself.
FormatAuto Format = "auto"
)
// Size represents requested image dimensions
type Size struct {
Width int
Height int
}
// OriginalSize returns true if this represents "keep original size"
func (s Size) OriginalSize() bool {
return s.Width == 0 && s.Height == 0
}
// Fit represents how to fit image into requested dimensions.
type Fit string
// Supported image fit modes.
const (
FitCover Fit = "cover"
FitContain Fit = "contain"
FitFill Fit = "fill"
FitInside Fit = "inside"
FitOutside Fit = "outside"
)
// ValidateFitMode checks if the given fit mode is valid.
// Returns ErrInvalidFitMode for unrecognized fit modes.
func ValidateFitMode(fit Fit) error {
switch fit {
case FitCover, FitContain, FitFill, FitInside, FitOutside, "":
return nil
default:
return ErrInvalidFitMode
}
}
// ValidateImageRequest checks a request's width and height with
// ValidateDimension and its fit mode with ValidateFitMode. Both the plain
// /v1/image/ route and the encrypted /v1/e/ route validate through this
// function so a request from either source enforces identical bounds.
func ValidateImageRequest(req *Request) error {
err := ValidateDimension("width", req.Transform.Size.Width)
if err != nil {
return err
}
err = ValidateDimension("height", req.Transform.Size.Height)
if err != nil {
return err
}
return ValidateFitMode(req.Transform.FitMode)
}
// Request represents a request for a processed image: the source to fetch
// and the transform to apply to it.
type Request struct {
// Source is what to fetch
Source Source
// Transform is what to do to it
Transform Transform
// Signature is the HMAC signature for non-allowlisted hosts
Signature string
// Expires is when the URL expires: the exp of a signed URL, or the expiry
// of an encrypted URL; the zero time if it has none
Expires time.Time
// AllowHTTP indicates whether HTTP (non-TLS) is allowed for this request
AllowHTTP bool
}
// Source is the image a request fetches from the origin.
type Source struct {
// Host is the origin host (e.g., "cdn.example.com")
Host string
// Path is the path on the origin with its percent-escapes decoded, as
// url.URL's Path holds it (e.g., "/photos/my cat.jpg")
Path string
// Query is the optional query string for the origin URL as the URL
// writes it, percent-escapes included, as url.URL's RawQuery holds it
Query string
}
// Transform is what a request does to its source; the image processor
// takes it alone.
type Transform struct {
// Size is the requested output dimensions
Size Size
// Format is the requested output format
Format Format
// Quality is the output quality (1-100) for lossy formats
Quality int
// FitMode is how to fit the image into requested dimensions
FitMode Fit
}
// SourceURL returns the full upstream URL to fetch: the source path
// percent-encoded again, as net/url writes a path, so each source path is one
// upstream path, and the source query as it is, with the characters
// escapeQuery encodes percent-encoded. Uses http:// scheme when AllowHTTP is
// true, otherwise https://.
func (r *Request) SourceURL() string {
scheme := "https"
if r.AllowHTTP {
scheme = "http"
}
sourceURL := url.URL{
Scheme: scheme,
Host: r.Source.Host,
Path: r.Source.Path,
RawQuery: escapeQuery(r.Source.Query),
}
return sourceURL.String()
}
internal/imagerequest/sourcekey.go
-26
View File
@@ -1,26 +0,0 @@
package imagerequest
import (
"crypto/sha256"
"encoding/hex"
"fmt"
)
// SourceKey is a SHA256 hash identifying a cached source image (hex-encoded).
type SourceKey string
// Key returns the key the source is cached under, made as CacheKey makes a
// variant key.
// Format: sha256(host:path:query)
// The path and query go through escapePercentAndColon, so that a ":" in
// either cannot be taken for the one between them.
func (s Source) Key() SourceKey {
data := fmt.Sprintf("%s:%s:%s",
s.Host,
escapePercentAndColon(s.Path),
escapePercentAndColon(s.Query),
)
h := sha256.Sum256([]byte(data))
return SourceKey(hex.EncodeToString(h[:]))
}
internal/imagerequest/sourcekey_internal_test.go
-40
View File
@@ -1,40 +0,0 @@
package imagerequest
import "testing"
// TestSourceKey_DiffersForEachSource checks that each source gets a key of
// 64 hex characters, the same each time, and that no two of these sources
// share one, also when they differ only by a ":" or "%" in the path or query.
func TestSourceKey_DiffersForEachSource(t *testing.T) {
t.Parallel()
sources := []Source{
{Host: testHostCDN, Path: testPathCat},
{Host: testHostCDN, Path: testPathCat, Query: "v=2"},
{Host: "other.example.com", Path: testPathCat},
{Host: testHostCDN, Path: "/c:d"},
{Host: testHostCDN, Path: "/c", Query: "d:"},
{Host: testHostCDN, Path: "/c%3Ad"},
}
seen := make(map[SourceKey]Source)
for _, source := range sources {
key := source.Key()
t.Logf("Key() of %+v = %s", source, key)
if len(key) != 64 {
t.Errorf("Key() of %+v length = %d, want 64", source, len(key))
}
if again := source.Key(); again != key {
t.Errorf("Key() of %+v not deterministic: %s vs %s", source, key, again)
}
if earlier, found := seen[key]; found {
t.Errorf("Key() gave %+v and %+v the same key", earlier, source)
}
seen[key] = source
}
}
internal/imagerequest/urlparser.go
-357
View File
@@ -1,357 +0,0 @@
package imagerequest
import (
"errors"
"fmt"
"net/netip"
"net/url"
"regexp"
"strconv"
"strings"
)
// URL parsing errors.
var (
ErrInvalidPath = errors.New("invalid image path")
ErrMissingHost = errors.New("missing source host")
ErrInvalidHost = errors.New("invalid source host")
ErrMissingSize = errors.New("missing size specification")
ErrInvalidSize = errors.New("invalid size format")
ErrInvalidFormat = errors.New("invalid or unsupported format")
ErrDimensionTooLarge = errors.New("dimension exceeds maximum")
ErrPathTraversal = errors.New("path traversal detected")
)
// MaxDimension is the maximum allowed width or height, the same as the image
// processor's maximum for an output image (imageprocessor.MaxOutputDimension).
const MaxDimension = 8192
// ValidateDimension checks one requested width or height; name ("width" or
// "height") appears in the error. 0 is valid: that side is then worked out from
// the source's proportions and the other requested side, rounded down but at
// least 1, or is the source's own side when the other side is 0 too.
func ValidateDimension(name string, value int) error {
if value < 0 {
return fmt.Errorf("%w: %s is negative", ErrInvalidSize, name)
}
if value > MaxDimension {
return fmt.Errorf("%w: %s is above %d",
ErrDimensionTooLarge, name, MaxDimension)
}
return nil
}
// sizeFormatRegex matches patterns like "800x600.webp", "0x0.jpeg", "orig.png",
// and a size with no format, such as "800x600" or "orig"
var sizeFormatRegex = regexp.MustCompile(
`^(\d+)x(\d+)(?:\.(\w+))?$|^(orig)(?:\.(\w+))?$`)
// percentEscapeRegex matches one percent-escape, such as "%2e"
var percentEscapeRegex = regexp.MustCompile(`%[0-9A-Fa-f]{2}`)
// queryEscapeRegex matches a percent-escape, or one character that a browser
// percent-encodes in the query of an http or https URL: one outside the
// printable ASCII characters "!" to "~", such as a space, a control character
// or a character outside ASCII, or one of `"#'<>`. A "%" that does not begin a
// percent-escape matches too.
var queryEscapeRegex = regexp.MustCompile(`%[0-9A-Fa-f]{2}|[^!-~]|["#'<>%]`)
// hostRegex matches the forms the host of an image URL may take: a host name
// or an IPv4 address (letters, digits, "-", "_" and "."), or an IPv6 address
// in brackets (hex digits, ":" and "."), either one optionally followed by ":"
// and a port, which may be empty. Its one group holds the text in brackets,
// which parseImageComponents also checks is an IPv6 address.
var hostRegex = regexp.MustCompile(
`^(?:[A-Za-z0-9_.-]+|\[([0-9A-Fa-f:.]+)\])(?::[0-9]*)?$`)
// ParseImagePath parses an image URL's path after /v1/image/, decoded once:
// <host>/<path>/<size>.<format>, or <host>/<path>/<size> for JPEG XL.
// Examples:
// - cdn.example.com/photos/cat.jpg/800x600.webp
// - cdn.example.com/photos/cat.jpg/0x0.jpeg
// - cdn.example.com/photos/cat.jpg/orig.png
// - cdn.example.com/photos/cat.jpg/800x600
func ParseImagePath(path string) (*Request, error) {
// Strip leading slash if present (chi may include it)
path = strings.TrimPrefix(path, "/")
if path == "" {
return nil, ErrMissingHost
}
return parseImageComponents(path)
}
// ParseImageURL parses an image URL's path, decoded once as r.URL.Path holds
// it: /v1/image/<host>/<path>/<size>.<format>, or /v1/image/<host>/<path>/<size>
// for JPEG XL. A source query follows the source path after a "?", which the
// URL writes as %3F.
func ParseImageURL(urlPath string) (*Request, error) {
// Remove the /v1/image/ prefix
const prefix = "/v1/image/"
if !strings.HasPrefix(urlPath, prefix) {
return nil, ErrInvalidPath
}
remainder := strings.TrimPrefix(urlPath, prefix)
if remainder == "" {
return nil, ErrMissingHost
}
return parseImageComponents(remainder)
}
// parseImageComponents parses <host>/<path>/<size>.<format>, or
// <host>/<path>/<size> for JPEG XL.
func parseImageComponents(remainder string) (*Request, error) {
// Find the last path segment, which holds "size" or "size.format"
lastSlash := strings.LastIndex(remainder, "/")
if lastSlash == -1 {
return nil, ErrMissingSize
}
sizeFormat := remainder[lastSlash+1:]
hostAndPath := remainder[:lastSlash]
if hostAndPath == "" {
return nil, ErrMissingHost
}
// Parse size and format from the last segment
size, format, err := parseSizeFormat(sizeFormat)
if err != nil {
return nil, err
}
// Split host from path
// The first segment is the host, everything after is the path
firstSlash := strings.Index(hostAndPath, "/")
var host, path, query string
if firstSlash == -1 {
// No path, just host (unusual but valid)
host = hostAndPath
path = "/"
} else {
host = hostAndPath[:firstSlash]
path = hostAndPath[firstSlash:]
}
if host == "" {
return nil, ErrMissingHost
}
// Only the forms hostRegex describes are accepted. A "?", "#" or "@" in
// the host would make Go's URL parser, which the allowlist check and the
// fetcher use, read a different host from the one allowlisted and cached
hostMatch := hostRegex.FindStringSubmatch(host)
if hostMatch == nil {
return nil, fmt.Errorf("%w: %q", ErrInvalidHost, host)
}
// Go's URL parser refuses brackets around anything but an IPv6 address
if inBrackets := hostMatch[1]; inBrackets != "" {
addr, err := netip.ParseAddr(inBrackets)
if err != nil || !addr.Is6() {
return nil, fmt.Errorf("%w: %q", ErrInvalidHost, host)
}
}
// Host names do not depend on letter case, so the allowlist, the upstream
// connection limits, the cache and the signature see one spelling of each
// host
host = strings.ToLower(host)
// Go's URL parser, which the fetcher uses, reads a "#" as the start of a
// fragment and drops the rest, so each text after it would be another
// spelling, cached under its own keys, of one upstream request
if strings.Contains(path, "#") {
return nil, fmt.Errorf(
`%w: the source path or query holds a "#"`, ErrInvalidPath)
}
// Extract query string if present in path. It is the source URL's query
// as that URL writes it. A character a URL's query cannot hold as it is,
// such as a space written %20 in the image URL, is percent-encoded here,
// so the query is signed and cached as it is sent upstream
if qIndex := strings.Index(path, "?"); qIndex != -1 {
query = escapeQuery(path[qIndex+1:])
path = path[:qIndex]
}
// The source query names no file on the upstream, so only the host and
// the source path are checked for path traversal
err = checkPathTraversal(host + path)
if err != nil {
return nil, err
}
// Ensure path starts with /
if !strings.HasPrefix(path, "/") {
path = "/" + path
}
return &Request{
Source: Source{Host: host, Path: path, Query: query},
Transform: Transform{Size: size, Format: format},
}, nil
}
// checkPathTraversal detects path traversal attempts in a URL path.
// It checks for various attack vectors including:
// - Direct ../ sequences
// - URL-encoded variants (%2e%2e, %252e%252e)
// - Backslash variants (..\)
// - Null byte injection (%00)
func checkPathTraversal(path string) error {
// First, URL-decode the path to catch encoded attacks
// Decode multiple times to catch double-encoding
decoded := path
for range 3 {
newDecoded := decodePercentEscapes(decoded)
if newDecoded == decoded {
break
}
decoded = newDecoded
}
// Normalize backslashes to forward slashes
normalized := strings.ReplaceAll(decoded, "\\", "/")
// Check for null bytes
if strings.Contains(normalized, "\x00") {
return ErrPathTraversal
}
// Check for parent directory traversal
// Look for "/.." or "../" patterns
if strings.Contains(normalized, "/../") ||
strings.Contains(normalized, "/..") ||
strings.HasPrefix(normalized, "../") ||
strings.HasSuffix(normalized, "/..") ||
normalized == ".." {
return ErrPathTraversal
}
// Also check for ".." as a path segment in the original path
// This catches cases where the path hasn't been normalized
for seg := range strings.SplitSeq(path, "/") {
// URL decode the segment
decodedSeg, _ := url.PathUnescape(seg)
decodedSeg = strings.ReplaceAll(decodedSeg, "\\", "/")
if decodedSeg == ".." {
return ErrPathTraversal
}
}
return nil
}
// decodePercentEscapes decodes every percent-escape in s, such as %2e, and
// keeps a "%" that does not start one as it is, where url.PathUnescape would
// refuse the whole string. A source path holding %25, a literal "%", has such
// a "%" after one more decoding.
func decodePercentEscapes(s string) string {
return percentEscapeRegex.ReplaceAllStringFunc(s, func(escape string) string {
decoded, _ := url.PathUnescape(escape)
return decoded
})
}
// escapeQuery returns a source query as a URL's query holds it: each
// character that queryEscapeRegex names, such as a space, percent-encoded,
// and the rest, the query's percent-escapes included, kept as they are. The
// result is unchanged by a second escapeQuery.
func escapeQuery(query string) string {
return queryEscapeRegex.ReplaceAllStringFunc(query, func(match string) string {
if percentEscapeRegex.MatchString(match) {
return match
}
return url.PathEscape(match)
})
}
// parseSizeFormat parses strings like "800x600.webp", "orig.png" or "800x600"
func parseSizeFormat(s string) (Size, Format, error) {
matches := sizeFormatRegex.FindStringSubmatch(s)
if matches == nil {
return Size{}, "", ErrInvalidSize
}
var (
size Size
formatStr string
)
if matches[4] == "orig" {
// "orig" or "orig.format" pattern
size = Size{Width: 0, Height: 0}
formatStr = matches[5]
} else {
// "WxH" or "WxH.format" pattern
width, err := strconv.Atoi(matches[1])
if err != nil {
return Size{}, "", ErrInvalidSize
}
height, err := strconv.Atoi(matches[2])
if err != nil {
return Size{}, "", ErrInvalidSize
}
size = Size{Width: width, Height: height}
formatStr = matches[3]
}
err := ValidateDimension("width", size.Width)
if err != nil {
return Size{}, "", err
}
err = ValidateDimension("height", size.Height)
if err != nil {
return Size{}, "", err
}
// A URL that names no format is served, and signed, as JPEG XL
if formatStr == "" {
return size, FormatJXL, nil
}
format, err := parseFormat(formatStr)
if err != nil {
return Size{}, "", err
}
return size, format, nil
}
// parseFormat converts a format string to Format.
func parseFormat(s string) (Format, error) {
switch strings.ToLower(s) {
case "orig", "original":
return FormatOriginal, nil
case "jpg", "jpeg":
return FormatJPEG, nil
case "png":
return FormatPNG, nil
case "webp":
return FormatWebP, nil
case "avif":
return FormatAVIF, nil
case "jxl":
return FormatJXL, nil
case "gif":
return FormatGIF, nil
case "auto":
return FormatAuto, nil
default:
return "", fmt.Errorf("%w: %s", ErrInvalidFormat, s)
}
}
internal/imagerequest/variantkey.go
-39
View File
@@ -1,39 +0,0 @@
package imagerequest
import (
"crypto/sha256"
"encoding/hex"
"fmt"
"strings"
)
// VariantKey is a SHA256 hash identifying a specific image variant (hex-encoded).
type VariantKey string
// CacheKey generates a unique key for a request variant.
// Format: sha256(host:path:query:width:height:format:quality:fit_mode)
// The path and query go through escapePercentAndColon, so that a ":" in
// either cannot be taken for the one between them.
func CacheKey(req *Request) VariantKey {
data := fmt.Sprintf("%s:%s:%s:%d:%d:%s:%d:%s",
req.Source.Host,
escapePercentAndColon(req.Source.Path),
escapePercentAndColon(req.Source.Query),
req.Transform.Size.Width,
req.Transform.Size.Height,
req.Transform.Format,
req.Transform.Quality,
req.Transform.FitMode,
)
h := sha256.Sum256([]byte(data))
return VariantKey(hex.EncodeToString(h[:]))
}
// escapePercentAndColon returns s with each "%" written as "%25" and each
// ":" as "%3A", so that the result holds no ":".
func escapePercentAndColon(s string) string {
s = strings.ReplaceAll(s, "%", "%25")
return strings.ReplaceAll(s, ":", "%3A")
}
internal/imagerequest/variantkey_internal_test.go
-142
View File
@@ -1,142 +0,0 @@
package imagerequest
import "testing"
func TestCacheKey(t *testing.T) {
t.Parallel()
req1 := &Request{
Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
Transform: Transform{
Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
Quality: 85, FitMode: FitCover,
},
}
req2 := &Request{
Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
Transform: Transform{
Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
Quality: 85, FitMode: FitCover,
},
}
// Same request should produce same key
key1 := CacheKey(req1)
key2 := CacheKey(req2)
if key1 != key2 {
t.Errorf("CacheKey() not deterministic: %s vs %s", key1, key2)
}
// Key should be 64 hex chars
if len(string(key1)) != 64 {
t.Errorf("CacheKey() length = %d, want 64", len(string(key1)))
}
// Different size should produce different key
req3 := &Request{
Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
Transform: Transform{
Size: Size{Width: 400, Height: 300}, Format: FormatWebP, // Different size
Quality: 85, FitMode: FitCover,
},
}
key3 := CacheKey(req3)
if key1 == key3 {
t.Error("CacheKey() produced same key for different sizes")
}
// Different format should produce different key
req4 := &Request{
Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
Transform: Transform{
Size: Size{Width: 800, Height: 600}, Format: FormatPNG, // Different format
Quality: 85, FitMode: FitCover,
},
}
key4 := CacheKey(req4)
if key1 == key4 {
t.Error("CacheKey() produced same key for different formats")
}
// Different quality should produce different key
req5 := &Request{
Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
Transform: Transform{
Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
Quality: 50, FitMode: FitCover, // Different quality
},
}
key5 := CacheKey(req5)
if key1 == key5 {
t.Error("CacheKey() produced same key for different quality")
}
}
// TestCacheKey_ColonOrPercentInPathOrQuery checks that two different source
// URLs whose path or query holds ":" or "%" get different keys.
func TestCacheKey_ColonOrPercentInPathOrQuery(t *testing.T) {
t.Parallel()
cases := []struct {
name string
path1, query1 string
path2, query2 string
}{
{
name: "colon moved from path to query",
path1: "/a:b", query1: "",
path2: "/a", query2: "b:",
},
{
name: "colon in path and its percent-encoding",
path1: "/a:b", query1: "",
path2: "/a%3Ab", query2: "",
},
}
for _, tt := range cases {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
key1 := CacheKey(&Request{
Source: Source{
Host: testHostCDN,
Path: tt.path1,
Query: tt.query1,
},
Transform: Transform{
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
},
})
key2 := CacheKey(&Request{
Source: Source{
Host: testHostCDN,
Path: tt.path2,
Query: tt.query2,
},
Transform: Transform{
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
},
})
t.Logf("CacheKey() of path %q query %q = %s", tt.path1, tt.query1, key1)
t.Logf("CacheKey() of path %q query %q = %s", tt.path2, tt.query2, key2)
if key1 == key2 {
t.Errorf("CacheKey() gave path %q query %q and path %q query %q "+
"the same key", tt.path1, tt.query1, tt.path2, tt.query2)
}
})
}
}
internal/imgcache/cache.go
+371 -229
View File
@@ -2,17 +2,19 @@ package imgcache
import (
"context"
"crypto/sha256"
"database/sql"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
"io"
"log/slog"
"path/filepath"
"sync"
"sync/atomic"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
lru "github.com/hashicorp/golang-lru/v2"
"sneak.berlin/go/pixa/internal/httpfetcher"
)
// Cache errors.
@@ -21,21 +23,17 @@ var (
ErrNegativeCache = errors.New("negative cache hit")
)
// maxPendingAccessTimes is how many access times of variants served from
// the cache, and how many of cached sources a miss used, may each wait to be
// written, at about 80 bytes each. An access time handed over while that
// many of its kind wait is dropped.
const maxPendingAccessTimes = 10000
// HTTP status code for successful fetch.
const httpStatusOK = 200
// cleanExpiredBatchSize is the most expired negative cache rows one
// statement of CleanExpired deletes. Each batch is a statement of its
// own, so a request waits behind one batch at most, however many rows
// have expired.
const cleanExpiredBatchSize = 1000
// metaCacheSize is how many variants' content types metaCache holds. A
// variant not among them is served as before, reading its .meta file.
const metaCacheSize = 10000
// CacheConfig holds cache configuration.
type CacheConfig struct {
StateDir string
CacheTTL time.Duration
NegativeTTL time.Duration
// MaxBytes is the disk cache size limit in bytes that eviction
@@ -51,9 +49,8 @@ type CacheConfig struct {
// DisableDiskCache turns the disk cache off entirely: no cache
// directories are created, lookups always miss, stores are
// no-ops, and the eviction goroutine only removes the expired
// negative cache rows. The config layer sets this when the
// operator configures cache_max_bytes: 0.
// no-ops, and no eviction machinery runs. The config layer sets
// this when the operator configures cache_max_bytes: 0.
DisableDiskCache bool
// Logger receives accounting and eviction log output. A nil
@@ -63,11 +60,12 @@ type CacheConfig struct {
// Cache implements the caching layer for the image proxy.
type Cache struct {
db *sql.DB
srcContent *ContentStorage // source images by source key
variants *VariantStorage // processed variants by cache key
config CacheConfig
log *slog.Logger
db *sql.DB
srcContent *ContentStorage // source images by content hash
variants *VariantStorage // processed variants by cache key
srcMetadata *MetadataStorage // source metadata by host/path
config CacheConfig
log *slog.Logger
// disabled means the disk cache is turned off entirely: lookups
// always miss, stores are no-ops, and no eviction runs.
@@ -81,41 +79,23 @@ type Cache struct {
evictionDone chan struct{}
evictionCancel context.CancelFunc
// The pending counts: hits, misses, upstream fetches and transforms
// that requests counted, kept here until they are written by the
// goroutine that StartPendingCountWrites starts, so that no request
// waits for the database to count it. pendingVariantAccessTimes holds
// the variants served from the cache, and pendingSourceAccessTimes the
// cached sources a miss used, whose access time is still to be written
// by that goroutine. As for eviction, the channels are created in
// NewCache, so that requests can hand over access times before that
// goroutine starts; pendingCountsDone is closed when it returns.
// pendingCountsCancel, set by StartPendingCountWrites, cancels its
// context, which tells it to finish.
pendingHits atomic.Int64
pendingMisses atomic.Int64
pendingUpstreamFetches atomic.Int64
pendingUpstreamFetchBytes atomic.Int64
pendingTransforms atomic.Int64
pendingVariantAccessTimes chan imagerequest.VariantKey
pendingSourceAccessTimes chan imagerequest.SourceKey
pendingCountsDone chan struct{}
pendingCountsCancel context.CancelFunc
// metaCache holds the content types of the variants most recently
// stored or served, so a hit does not read the variant's .meta file.
// It never stands in for the variant file, which is always opened.
metaCache *lru.Cache[VariantKey, string]
// Held through each write of the pending counts, and by
// readHitAndMissCounts to read them
pendingCountsWriteMutex sync.Mutex
// contentLocks serializes StoreSource and evictSourceBlob per
// content hash, closing the race window between an eviction's row
// deletion and its file unlink against a concurrent store of
// identical content.
contentLocks *contentLock
// reconciliationPageSize is the most rows one read of a content table
// returns in the reconciliation pass and in Stats. newCache sets it to
// defaultReconciliationPageSize; tests set it smaller.
reconciliationPageSize int
// reconciliationReadTestHook, when set, is called after each of those
// reads with the number of rows the read covered, so tests can check
// that no read covers more than one page; production code leaves it
// nil.
reconciliationReadTestHook func(rows int)
// evictSourceBlobTestHook, when set, is invoked by evictSourceBlob
// after its row-deletion transaction commits and before the
// content file is unlinked. It exists solely so tests can
// deterministically pause inside that window to exercise
// concurrent stores against it; production code leaves it nil.
evictSourceBlobTestHook func(ContentHash)
}
// NewCache creates a new cache instance.
@@ -133,6 +113,11 @@ func newCache(
log = slog.Default()
}
metaCache, err := lru.New[VariantKey, string](metaCacheSize)
if err != nil {
return nil, fmt.Errorf("failed to create variant content type cache: %w", err)
}
c := &Cache{
db: db,
config: config,
@@ -140,12 +125,8 @@ func newCache(
disabled: config.DisableDiskCache,
evictionPressure: make(chan struct{}, 1),
evictionDone: make(chan struct{}),
pendingVariantAccessTimes: make(chan imagerequest.VariantKey, maxPendingAccessTimes),
pendingSourceAccessTimes: make(chan imagerequest.SourceKey, maxPendingAccessTimes),
pendingCountsDone: make(chan struct{}),
reconciliationPageSize: defaultReconciliationPageSize,
metaCache: metaCache,
contentLocks: newContentLock(),
}
if c.disabled {
@@ -160,14 +141,22 @@ func newCache(
}
variants, err := NewVariantStorage(
filepath.Join(config.StateDir, "cache", "variants"),
filepath.Join(config.StateDir, "cache", "variants"), log,
)
if err != nil {
return nil, fmt.Errorf("failed to create variant storage: %w", err)
}
srcMetadata, err := NewMetadataStorage(
filepath.Join(config.StateDir, "cache", "metadata"),
)
if err != nil {
return nil, fmt.Errorf("failed to create source metadata storage: %w", err)
}
c.srcContent = srcContent
c.variants = variants
c.srcMetadata = srcMetadata
if config.UseDefaultMaxBytes {
limit, err := c.computeDefaultMaxBytes(context.Background(), probe)
@@ -186,68 +175,146 @@ func newCache(
return c, nil
}
// GetVariant opens a cached variant and returns a reader, its size and its
// content type, read from the variant file's first bytes. It opens that one
// file and makes no database call. A variant not in the cache, or any
// variant of a disabled cache, is ErrNotFound; a variant file whose first
// bytes are not those of an output format is another error.
func (c *Cache) GetVariant(
cacheKey imagerequest.VariantKey,
) (io.ReadCloser, int64, string, error) {
// LookupResult contains the result of a cache lookup.
type LookupResult struct {
Hit bool
CacheKey VariantKey
ContentType string
SizeBytes int64
CacheStatus CacheStatus
}
// Lookup checks if a processed variant exists on disk. Hits touch the
// variant's LRU timestamp; a disabled cache always misses.
func (c *Cache) Lookup(ctx context.Context, req *ImageRequest) (*LookupResult, error) {
cacheKey := CacheKey(req)
// Check variant storage directly - no DB needed for cache hits
if !c.disabled && c.variants.Exists(cacheKey) {
c.touchVariant(ctx, cacheKey)
return &LookupResult{
Hit: true,
CacheKey: cacheKey,
CacheStatus: CacheHit,
}, nil
}
return &LookupResult{
Hit: false,
CacheKey: cacheKey,
CacheStatus: CacheMiss,
}, nil
}
// GetVariant returns a reader, size, and content type for a cached
// variant. The content type comes from metaCache, or else from the
// variant's .meta file and is then kept in metaCache. A variant with
// no .meta file is served as application/octet-stream, which is not
// kept.
func (c *Cache) GetVariant(cacheKey VariantKey) (io.ReadCloser, int64, string, error) {
if c.disabled {
return nil, 0, "", ErrNotFound
}
return c.variants.LoadWithContentType(cacheKey)
contentType, known := c.metaCache.Get(cacheKey)
if !known {
return c.loadVariantWithMeta(cacheKey)
}
reader, size, err := c.variants.LoadWithSize(cacheKey)
if err != nil {
// The file is gone, e.g. deleted outside pixa
c.metaCache.Remove(cacheKey)
return nil, 0, "", err
}
return reader, size, contentType, nil
}
// StoreSource stores fetched source content: it writes the file named by
// the source's key, then the source's row. When the row cannot be written
// the file is removed and the store fails, as a file with no row is never
// served or evicted; if that removal fails too, the next reconciliation
// pass removes the file. On a disabled cache it is a no-op returning an
// empty key.
// StoreSource stores fetched source content and metadata. On a
// disabled cache it is a no-op returning an empty hash.
func (c *Cache) StoreSource(
ctx context.Context,
req *imagerequest.Request,
req *ImageRequest,
content io.Reader,
) (imagerequest.SourceKey, error) {
result *httpfetcher.FetchResult,
) (ContentHash, error) {
if c.disabled {
return "", nil
}
// Hash the content ourselves (rather than via srcContent.Store,
// which would hash internally) so the content hash is known before
// any file or database work happens: that lets the entire store be
// serialized, per hash, against a concurrent eviction of the same
// content below.
data, err := io.ReadAll(content)
if err != nil {
return "", fmt.Errorf("failed to read source content: %w", err)
}
key := req.Source.Key()
sum := sha256.Sum256(data)
contentHash := ContentHash(hex.EncodeToString(sum[:]))
size, err := c.srcContent.Store(key, data)
// Hold the content hash's lock for the whole store operation. A
// concurrent eviction of this exact hash (the real SHA-256 dedup
// case: a different source path whose bytes hash identically)
// deletes the accounting rows and unlinks the file inside the same
// lock, so the two can never interleave: either this store
// completes first (and a subsequent eviction removes it together
// with its rows and file, correctly), or eviction completes first
// (and this store finds the file already gone and recreates it
// fresh) — never a fresh row left pointing at a file eviction is
// mid-unlink on.
unlock := c.contentLocks.Lock(string(contentHash))
defer unlock()
size, err := c.srcContent.StoreHashed(contentHash, data)
if err != nil {
return "", fmt.Errorf("failed to store source content: %w", err)
}
_, err = c.db.ExecContext(ctx, `
INSERT INTO source_content (source_key, size_bytes)
VALUES (?, ?)
ON CONFLICT(source_key) DO UPDATE SET
size_bytes = excluded.size_bytes,
last_accessed_at = CURRENT_TIMESTAMP
`, string(key), size)
if err != nil {
deleteErr := c.srcContent.Delete(key)
if deleteErr != nil {
c.log.Warn("failed to remove source file whose row was not written",
"source_key", key, "error", deleteErr)
}
// Store in database
pathHash := HashPath(req.SourcePath + "?" + req.SourceQuery)
headersJSON, err := json.Marshal(result.Headers)
if err != nil {
return "", fmt.Errorf("failed to marshal response headers: %w", err)
}
_, err = c.db.ExecContext(ctx, `
INSERT INTO source_content (content_hash, content_type, size_bytes)
VALUES (?, ?, ?)
ON CONFLICT(content_hash) DO NOTHING
`, contentHash, result.ContentType, size)
if err != nil {
return "", fmt.Errorf("failed to insert source content: %w", err)
}
_, err = c.db.ExecContext(ctx, `
INSERT INTO source_metadata
(source_host, source_path, source_query, path_hash,
content_hash, status_code, content_type, response_headers)
VALUES (?, ?, ?, ?, ?, ?, ?, ?)
ON CONFLICT(source_host, source_path, source_query) DO UPDATE SET
content_hash = excluded.content_hash,
status_code = excluded.status_code,
content_type = excluded.content_type,
response_headers = excluded.response_headers,
fetched_at = CURRENT_TIMESTAMP
`, req.SourceHost, req.SourcePath, req.SourceQuery, pathHash,
contentHash, httpStatusOK, result.ContentType, string(headersJSON))
if err != nil {
return "", fmt.Errorf("failed to insert source metadata: %w", err)
}
c.writeMetadataSidecar(req, pathHash, contentHash, result)
c.notifyWritePressure()
return key, nil
return contentHash, nil
}
// StoreVariant stores a processed variant by its cache key and records
@@ -255,24 +322,27 @@ func (c *Cache) StoreSource(
// accounting insert is best-effort (the startup reconciliation pass
// adopts any variant file that misses its accounting row).
func (c *Cache) StoreVariant(
ctx context.Context, cacheKey imagerequest.VariantKey, content io.Reader,
ctx context.Context, cacheKey VariantKey, content io.Reader, contentType string,
) error {
if c.disabled {
return nil
}
size, err := c.variants.Store(cacheKey, content)
size, err := c.variants.Store(cacheKey, content, contentType)
if err != nil {
return err
}
c.metaCache.Add(cacheKey, contentType)
_, err = c.db.ExecContext(ctx, `
INSERT INTO variant_content (cache_key, size_bytes)
VALUES (?, ?)
INSERT INTO variant_content (cache_key, size_bytes, content_type)
VALUES (?, ?, ?)
ON CONFLICT(cache_key) DO UPDATE SET
size_bytes = excluded.size_bytes,
content_type = excluded.content_type,
last_accessed_at = CURRENT_TIMESTAMP
`, string(cacheKey), size)
`, string(cacheKey), size, contentType)
if err != nil {
c.log.Warn("failed to record variant in size accounting",
"cache_key", cacheKey, "error", err)
@@ -284,54 +354,60 @@ func (c *Cache) StoreVariant(
}
// LookupSource checks if we have cached source content for a request.
// Returns the source key if found, or an empty key if not; a row whose
// file is missing is not found. A source found has its access time
// handed to the background writer without waiting (see
// touchSourceContent); a disabled cache always reports no cached source.
// Returns the content hash and content type if found, or empty values
// if not. Hits touch the blob's LRU timestamp; a disabled cache always
// reports no cached source.
func (c *Cache) LookupSource(
ctx context.Context, req *imagerequest.Request,
) (imagerequest.SourceKey, error) {
ctx context.Context, req *ImageRequest,
) (ContentHash, string, error) {
if c.disabled {
return "", nil
return "", "", nil
}
key := req.Source.Key()
var foundKey string
var hashStr, contentType string
err := c.db.QueryRowContext(ctx, `
SELECT source_key FROM source_content WHERE source_key = ?
`, string(key)).Scan(&foundKey)
SELECT content_hash, content_type FROM source_metadata
WHERE source_host = ? AND source_path = ? AND source_query = ?
`, req.SourceHost, req.SourcePath, req.SourceQuery).Scan(&hashStr, &contentType)
if errors.Is(err, sql.ErrNoRows) {
return "", nil
return "", "", nil
}
if err != nil {
return "", fmt.Errorf("failed to lookup source: %w", err)
return "", "", fmt.Errorf("failed to lookup source: %w", err)
}
contentHash := ContentHash(hashStr)
// Verify the content file exists
if !c.srcContent.Exists(key) {
return "", nil
if !c.srcContent.Exists(contentHash) {
return "", "", nil
}
c.touchSourceContent(key)
c.touchSourceContent(ctx, contentHash)
return key, nil
return contentHash, contentType, nil
}
// StoreNegative stores a negative cache entry for a failed fetch.
func (c *Cache) StoreNegative(ctx context.Context, req *imagerequest.Request) error {
func (c *Cache) StoreNegative(
ctx context.Context, req *ImageRequest, statusCode int, errMsg string,
) error {
expiresAt := time.Now().UTC().Add(c.config.NegativeTTL)
_, err := c.db.ExecContext(ctx, `
INSERT INTO negative_cache
(source_host, source_path, source_query, expires_at)
VALUES (?, ?, ?, ?)
(source_host, source_path, source_query, status_code,
error_message, expires_at)
VALUES (?, ?, ?, ?, ?, ?)
ON CONFLICT(source_host, source_path, source_query) DO UPDATE SET
status_code = excluded.status_code,
error_message = excluded.error_message,
fetched_at = CURRENT_TIMESTAMP,
expires_at = excluded.expires_at
`, req.Source.Host, req.Source.Path, req.Source.Query, expiresAt)
`, req.SourceHost, req.SourcePath, req.SourceQuery, statusCode, errMsg, expiresAt)
if err != nil {
return fmt.Errorf("failed to insert negative cache: %w", err)
}
@@ -339,53 +415,64 @@ func (c *Cache) StoreNegative(ctx context.Context, req *imagerequest.Request) er
return nil
}
// GetSourceContent returns a reader for cached source content by its key,
// GetSourceMetadataID returns the source metadata ID for a request.
func (c *Cache) GetSourceMetadataID(
ctx context.Context, req *ImageRequest,
) (int64, error) {
var id int64
err := c.db.QueryRowContext(ctx, `
SELECT id FROM source_metadata
WHERE source_host = ? AND source_path = ? AND source_query = ?
`, req.SourceHost, req.SourcePath, req.SourceQuery).Scan(&id)
if err != nil {
return 0, fmt.Errorf("failed to get source metadata ID: %w", err)
}
return id, nil
}
// GetSourceContent returns a reader for cached source content by its hash,
// and the content's size in bytes.
func (c *Cache) GetSourceContent(
key imagerequest.SourceKey,
contentHash ContentHash,
) (io.ReadCloser, int64, error) {
if c.disabled {
return nil, 0, ErrNotFound
}
return c.srcContent.LoadWithSize(key)
return c.srcContent.LoadWithSize(contentHash)
}
// CleanExpired removes the negative cache rows past their expiry, one
// batch per statement, until none is left. Once ctx ends it starts no
// further batch and returns ctx's error. The eviction goroutine calls it
// at startup and on every periodic tick, so a row stays about
// NegativeTTL plus one eviction interval, whether or not its URL is
// requested again.
// CleanExpired removes expired entries from the cache.
func (c *Cache) CleanExpired(ctx context.Context) error {
for {
if ctx.Err() != nil {
return ctx.Err()
}
deleted, err := c.cleanExpiredBatch(ctx)
if err != nil {
return err
}
if deleted < cleanExpiredBatchSize {
return nil
}
// Clean expired negative cache entries
_, err := c.db.ExecContext(ctx, `
DELETE FROM negative_cache WHERE expires_at < CURRENT_TIMESTAMP
`)
if err != nil {
return fmt.Errorf("failed to clean negative cache: %w", err)
}
return nil
}
// Stats returns cache statistics.
func (c *Cache) Stats(ctx context.Context) (*CacheStats, error) {
var stats CacheStats
err := c.readHitAndMissCounts(ctx, &stats)
// Fetch hit/miss counts from the stats table
err := c.db.QueryRowContext(ctx, `
SELECT hit_count, miss_count
FROM cache_stats WHERE id = 1
`).Scan(&stats.HitCount, &stats.MissCount)
if err != nil && !errors.Is(err, sql.ErrNoRows) {
return nil, fmt.Errorf("failed to get cache stats: %w", err)
}
// Count and size the cached source images and processed variants from
// their tables. A disabled cache holds none, whatever rows an earlier
// run left.
// Count and size the cached source images and processed variants. A
// disabled cache holds none, whatever rows an earlier run left.
if !c.disabled {
err = c.db.QueryRowContext(ctx, `
SELECT (SELECT COUNT(*) FROM source_content)
@@ -395,7 +482,7 @@ func (c *Cache) Stats(ctx context.Context) (*CacheStats, error) {
c.log.Warn("failed to count cache items for stats", "error", err)
}
stats.TotalSizeBytes, err = c.sumContentSizeBytes(ctx)
stats.TotalSizeBytes, err = c.UsageBytes(ctx)
if err != nil {
c.log.Warn("failed to sum cache size for stats", "error", err)
}
@@ -410,91 +497,157 @@ func (c *Cache) Stats(ctx context.Context) (*CacheStats, error) {
}
// IncrementStats counts a cache hit or miss, and an upstream fetch that read
// fetchBytes bytes, as IncrementUpstreamFetch does. Like the other Increment
// methods, it only adds to the pending counts, which the goroutine
// StartPendingCountWrites starts writes to the database, so it never waits
// for the database or fails.
func (c *Cache) IncrementStats(hit bool, fetchBytes int64) {
// fetchBytes bytes, as IncrementUpstreamFetch does.
func (c *Cache) IncrementStats(ctx context.Context, hit bool, fetchBytes int64) {
var err error
if hit {
c.pendingHits.Add(1)
_, err = c.db.ExecContext(ctx, `
UPDATE cache_stats
SET hit_count = hit_count + 1,
last_updated_at = CURRENT_TIMESTAMP
WHERE id = 1
`)
} else {
c.pendingMisses.Add(1)
_, err = c.db.ExecContext(ctx, `
UPDATE cache_stats
SET miss_count = miss_count + 1,
last_updated_at = CURRENT_TIMESTAMP
WHERE id = 1
`)
}
c.IncrementUpstreamFetch(fetchBytes)
if err != nil {
c.log.Warn("failed to count cache hit or miss", "hit", hit, "error", err)
}
c.IncrementUpstreamFetch(ctx, fetchBytes)
}
// IncrementUpstreamFetch counts one upstream fetch that read fetchBytes bytes.
// A fetch that read no bytes is not counted.
func (c *Cache) IncrementUpstreamFetch(fetchBytes int64) {
func (c *Cache) IncrementUpstreamFetch(ctx context.Context, fetchBytes int64) {
if fetchBytes <= 0 {
return
}
c.pendingUpstreamFetches.Add(1)
c.pendingUpstreamFetchBytes.Add(fetchBytes)
_, err := c.db.ExecContext(ctx, `
UPDATE cache_stats
SET upstream_fetch_count = upstream_fetch_count + 1,
upstream_fetch_bytes = upstream_fetch_bytes + ?,
last_updated_at = CURRENT_TIMESTAMP
WHERE id = 1
`, fetchBytes)
if err != nil {
c.log.Warn("failed to count upstream fetch",
"fetch_bytes", fetchBytes, "error", err)
}
}
// IncrementTransformCount counts one image transcoded by the image processor.
func (c *Cache) IncrementTransformCount() {
c.pendingTransforms.Add(1)
}
// readHitAndMissCounts sets the hit and miss counts of stats to those of the
// cache_stats row plus the pending hits and misses (see
// StartPendingCountWrites). It holds pendingCountsWriteMutex, so that no
// write of the pending counts falls between the two reads.
func (c *Cache) readHitAndMissCounts(ctx context.Context, stats *CacheStats) error {
c.pendingCountsWriteMutex.Lock()
defer c.pendingCountsWriteMutex.Unlock()
err := c.db.QueryRowContext(ctx, `
SELECT hit_count, miss_count
FROM cache_stats WHERE id = 1
`).Scan(&stats.HitCount, &stats.MissCount)
stats.HitCount += c.pendingHits.Load()
stats.MissCount += c.pendingMisses.Load()
return err
}
// touchVariant hands the access time of a variant served from the cache to
// the goroutine StartPendingCountWrites starts, which writes it in its next
// batch. It never waits: while maxPendingAccessTimes access times of
// variants wait to be written, this one is dropped, and the variant only
// looks colder to eviction.
func (c *Cache) touchVariant(cacheKey imagerequest.VariantKey) {
select {
case c.pendingVariantAccessTimes <- cacheKey:
default:
func (c *Cache) IncrementTransformCount(ctx context.Context) {
_, err := c.db.ExecContext(ctx, `
UPDATE cache_stats
SET transform_count = transform_count + 1,
last_updated_at = CURRENT_TIMESTAMP
WHERE id = 1
`)
if err != nil {
c.log.Warn("failed to count transform", "error", err)
}
}
// touchSourceContent hands the access time of a cached source a miss used to
// the goroutine StartPendingCountWrites starts, which writes it in its next
// batch. It never waits: while maxPendingAccessTimes access times of sources
// wait to be written, this one is dropped, and the source only looks colder
// to eviction.
func (c *Cache) touchSourceContent(key imagerequest.SourceKey) {
select {
case c.pendingSourceAccessTimes <- key:
default:
// loadVariantWithMeta is GetVariant for a variant metaCache does not
// hold: it reads the content type from the variant's .meta file and
// keeps it in metaCache, unless a StoreVariant has put one there
// meanwhile, as the store's is newer. A read that finds no .meta file,
// as one can between a store's writing of the variant file and of its
// .meta file, serves application/octet-stream and keeps nothing, so
// metaCache only ever holds a type read from a .meta file or passed to
// StoreVariant.
func (c *Cache) loadVariantWithMeta(
cacheKey VariantKey,
) (io.ReadCloser, int64, string, error) {
reader, size, contentType, err := c.variants.LoadWithMeta(cacheKey)
if err != nil {
return nil, 0, "", err
}
if contentType == "" {
return reader, size, fallbackContentType, nil
}
c.metaCache.ContainsOrAdd(cacheKey, contentType)
return reader, size, contentType, nil
}
// writeMetadataSidecar writes the JSON metadata sidecar of a stored source.
// A failure is logged and is otherwise non-fatal; the metadata is in the
// database.
func (c *Cache) writeMetadataSidecar(
req *ImageRequest,
pathHash PathHash,
contentHash ContentHash,
result *httpfetcher.FetchResult,
) {
meta := &SourceMetadata{
Host: req.SourceHost,
Path: req.SourcePath,
Query: req.SourceQuery,
ContentHash: string(contentHash),
StatusCode: result.StatusCode,
ContentType: result.ContentType,
ContentLength: result.ContentLength,
ResponseHeaders: result.Headers,
FetchedAt: time.Now().UTC().Unix(),
FetchDurationMs: result.FetchDurationMs,
RemoteAddr: result.RemoteAddr,
}
err := c.srcMetadata.Store(req.SourceHost, pathHash, meta)
if err != nil {
c.log.Warn("failed to write metadata sidecar",
"host", req.SourceHost, "path_hash", pathHash, "error", err)
}
}
// checkNegativeCache checks if a request is in the negative cache. It only
// reads: a row past its expiry is not a hit, and the eviction goroutine
// deletes it with the other expired rows (see CleanExpired).
// touchVariant updates the LRU timestamp of a variant, best-effort:
// a failed touch only makes the entry look colder to eviction.
func (c *Cache) touchVariant(ctx context.Context, cacheKey VariantKey) {
_, err := c.db.ExecContext(ctx, `
UPDATE variant_content SET last_accessed_at = CURRENT_TIMESTAMP
WHERE cache_key = ?
`, string(cacheKey))
if err != nil {
c.log.Debug("failed to touch variant LRU timestamp",
"cache_key", cacheKey, "error", err)
}
}
// touchSourceContent updates the LRU timestamp of a source content
// blob, best-effort: a failed touch only makes the blob look colder.
func (c *Cache) touchSourceContent(ctx context.Context, contentHash ContentHash) {
_, err := c.db.ExecContext(ctx, `
UPDATE source_content SET last_accessed_at = CURRENT_TIMESTAMP
WHERE content_hash = ?
`, string(contentHash))
if err != nil {
c.log.Debug("failed to touch source content LRU timestamp",
"content_hash", contentHash, "error", err)
}
}
// checkNegativeCache checks if a request is in the negative cache.
func (c *Cache) checkNegativeCache(
ctx context.Context, req *imagerequest.Request,
ctx context.Context, req *ImageRequest,
) (bool, error) {
var expiresAt time.Time
err := c.db.QueryRowContext(ctx, `
SELECT expires_at FROM negative_cache
WHERE source_host = ? AND source_path = ? AND source_query = ?
`, req.Source.Host, req.Source.Path, req.Source.Query).Scan(&expiresAt)
`, req.SourceHost, req.SourcePath, req.SourceQuery).Scan(&expiresAt)
if errors.Is(err, sql.ErrNoRows) {
return false, nil
@@ -504,31 +657,20 @@ func (c *Cache) checkNegativeCache(
return false, fmt.Errorf("failed to check negative cache: %w", err)
}
expired := time.Now().After(expiresAt)
// Check if expired
if time.Now().After(expiresAt) {
// Clean up expired entry
_, err = c.db.ExecContext(ctx, `
DELETE FROM negative_cache
WHERE source_host = ? AND source_path = ? AND source_query = ?
`, req.SourceHost, req.SourcePath, req.SourceQuery)
if err != nil {
c.log.Warn("failed to delete expired negative cache entry",
"host", req.SourceHost, "path", req.SourcePath, "error", err)
}
return !expired, nil
}
// cleanExpiredBatch deletes up to cleanExpiredBatchSize negative cache
// rows past their expiry in one statement, and returns how many it
// deleted. DELETE ... LIMIT needs a SQLite build option, so the subquery
// picks the rows.
func (c *Cache) cleanExpiredBatch(ctx context.Context) (int64, error) {
result, err := c.db.ExecContext(ctx, `
DELETE FROM negative_cache WHERE id IN (
SELECT id FROM negative_cache
WHERE expires_at < CURRENT_TIMESTAMP
LIMIT ?
)
`, cleanExpiredBatchSize)
if err != nil {
return 0, fmt.Errorf("failed to clean negative cache: %w", err)
return false, nil
}
deleted, err := result.RowsAffected()
if err != nil {
return 0, fmt.Errorf("failed to count cleaned negative cache rows: %w", err)
}
return deleted, nil
return true, nil
}
internal/imgcache/cache_hit_internal_test.go
-298
View File
@@ -1,298 +0,0 @@
package imgcache
import (
"bytes"
"errors"
"fmt"
"image/color"
"io"
"os"
"testing"
"time"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/magic"
)
// TestGetVariant_ContentTypeFromFirstBytes stores an image in each output
// format as a variant and checks that GetVariant serves it whole with the
// content type of its format, read from the file.
func TestGetVariant_ContentTypeFromFirstBytes(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
processor := imageprocessor.New(imageprocessor.Params{})
source := generateTestJPEG(t, 40, 30, color.RGBA{200, 40, 40, 255})
for _, format := range []imagerequest.Format{
imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatGIF,
imagerequest.FormatWebP, imagerequest.FormatAVIF, imagerequest.FormatJXL,
} {
result, err := processor.Process(t.Context(), bytes.NewReader(source),
&imagerequest.Transform{
Size: imagerequest.Size{Width: 20, Height: 15},
Format: format,
Quality: 85,
FitMode: imagerequest.FitCover,
})
if err != nil {
t.Fatalf("making a %s image: %v", format, err)
}
image, err := io.ReadAll(result.Content)
if err != nil {
t.Fatalf("reading the %s image: %v", format, err)
}
key := imagerequest.VariantKey("aabbccdd10" + string(format))
err = cache.StoreVariant(t.Context(), key, bytes.NewReader(image))
if err != nil {
t.Fatalf("StoreVariant(%s) error = %v", format, err)
}
reader, size, contentType, err := cache.GetVariant(key)
if err != nil {
t.Fatalf("GetVariant(%s) error = %v", format, err)
}
served, err := io.ReadAll(reader)
_ = reader.Close()
if err != nil {
t.Fatalf("reading the %s variant: %v", format, err)
}
t.Logf("%s: %d bytes served as %s", format, size, contentType)
if want := imageprocessor.FormatToMIME(format); contentType != want {
t.Errorf("%s variant content type = %q, want %q", format, contentType, want)
}
if size != int64(len(image)) || !bytes.Equal(served, image) {
t.Errorf("%s variant served %d bytes, size %d, want the %d bytes stored",
format, len(served), size, len(image))
}
}
}
// TestGetVariant_RefusesFileOfNoOutputFormat checks that GetVariant refuses
// a variant file whose first bytes are not those of an output format, with
// an error other than ErrNotFound, and that a variant with no file, or any
// variant of a disabled cache, is ErrNotFound.
func TestGetVariant_RefusesFileOfNoOutputFormat(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
jpegImage := generateTestJPEG(t, 10, 10, color.RGBA{0, 0, 255, 255})
tests := []struct {
name string
content []byte
wantErr error
}{
{"text", []byte("this is text, not an image"), magic.ErrUnknownFormat},
{"SVG", []byte(`<svg xmlns="http://www.w3.org/2000/svg"></svg>`),
errNotAnOutputFormat},
{"JPEG cut to 10 bytes", jpegImage[:10], io.EOF},
{"empty", nil, io.EOF},
}
for i, tt := range tests {
key := imagerequest.VariantKey(fmt.Sprintf("aabbccdd20%02d", i))
_, err := cache.variants.Store(key, bytes.NewReader(tt.content))
if err != nil {
t.Fatalf("%s: storing the variant file: %v", tt.name, err)
}
reader, _, contentType, err := cache.GetVariant(key)
t.Logf("%s: GetVariant() error = %v", tt.name, err)
if reader != nil || contentType != "" || !errors.Is(err, tt.wantErr) {
t.Errorf("%s: GetVariant() = reader %v, content type %q, error %v; "+
"want no reader and %v", tt.name, reader, contentType, err, tt.wantErr)
}
}
reader, _, _, err := cache.GetVariant(testVariantKeyFour)
if reader != nil || !errors.Is(err, ErrNotFound) {
t.Errorf("GetVariant() of a variant with no file = reader %v, error %v; "+
"want no reader and %v", reader, err, ErrNotFound)
}
disabled, _ := newEvictionTestCache(t, 0)
reader, _, _, err = disabled.GetVariant(testVariantKeyOne)
if reader != nil || !errors.Is(err, ErrNotFound) {
t.Errorf("GetVariant() on a disabled cache = reader %v, error %v; "+
"want no reader and %v", reader, err, ErrNotFound)
}
}
// TestService_Get_MakesAgainVariantOfNoOutputFormat replaces a cached
// variant's file with text, and checks that the next request is a miss
// answered with the variant made again, and the one after a hit.
func TestService_Get_MakesAgainVariantOfNoOutputFormat(t *testing.T) {
t.Parallel()
svc, fixtures := SetupTestService(t)
req := photoVariant(fixtures, 85, imagerequest.FitCover)
want, _ := getImage(t, svc, req)
path := svc.cache.variants.keyToPath(imagerequest.CacheKey(req))
err := os.WriteFile(path, []byte("this is text, not an image"), StorageFilePerm)
if err != nil {
t.Fatalf("replacing the variant file: %v", err)
}
got, status := getImage(t, svc, req)
t.Logf("after the replacement: %d bytes, %s", len(got), status)
if status != CacheMiss || !bytes.Equal(got, want) {
t.Errorf("after the replacement: Get() = %d bytes, %s; want the %d bytes "+
"made again, %s", len(got), status, len(want), CacheMiss)
}
got, status = getImage(t, svc, req)
if status != CacheHit || !bytes.Equal(got, want) {
t.Errorf("next request: Get() = %d bytes, %s; want the %d bytes, %s",
len(got), status, len(want), CacheHit)
}
}
// TestService_Get_HitWaitsForNoDatabaseWrite holds the database's one
// connection while a cached variant is requested. The hit must be answered
// while the connection is still held, and its access time and hit count
// must reach the database once it is free.
func TestService_Get_HitWaitsForNoDatabaseWrite(t *testing.T) {
t.Parallel()
svc, fixtures := SetupTestService(t)
req := photoVariant(fixtures, 85, imagerequest.FitCover)
key := imagerequest.CacheKey(req)
getImage(t, svc, req)
waitForPendingCountsWritten(t, svc.cache)
anHourAgo := time.Now().Add(-time.Hour)
setVariantLastAccessed(t, svc.cache, key, anHourAgo)
want := readCacheStatsCounters(t, svc.cache)
want.hitCount++
releaseDatabase := holdDatabase(t, svc.cache)
defer releaseDatabase()
results := startGet(t.Context(), svc, req)
select {
case got := <-results:
if got.err != nil {
t.Fatalf("Get() of the cached variant error = %v", got.err)
}
case <-time.After(pendingCountsWait):
t.Fatal("the cache hit waited for the database")
}
releaseDatabase()
waitForCounters(t, svc.cache, want)
deadline := time.Now().Add(pendingCountsWait)
for countRows(t, svc.cache, `
SELECT COUNT(*) FROM variant_content
WHERE cache_key = ? AND last_accessed_at > ?
`, string(key), anHourAgo.UTC().Format(sqliteTimestampFormat)) == 0 {
if time.Now().After(deadline) {
t.Fatal("the hit's access time was not written")
}
time.Sleep(10 * time.Millisecond)
}
}
// TestTouchVariantAndTouchSourceContent_DropAccessTimesPastTheLimit hands one
// more access time of a variant, and one more of a source, than may wait to
// be written. touchVariant and touchSourceContent must return each time
// without waiting, and the last of each must be dropped.
func TestTouchVariantAndTouchSourceContent_DropAccessTimesPastTheLimit(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
done := make(chan struct{})
go func() {
defer close(done)
for range maxPendingAccessTimes + 1 {
cache.touchVariant(testVariantKeyOne)
cache.touchSourceContent("aabbccdd3001")
}
}()
select {
case <-done:
case <-time.After(pendingCountsWait):
t.Fatal("touchVariant or touchSourceContent waited once the access " +
"times reached the limit")
}
if waiting := len(cache.pendingVariantAccessTimes); waiting != maxPendingAccessTimes {
t.Errorf("%d access times of variants wait to be written, want %d",
waiting, maxPendingAccessTimes)
}
if waiting := len(cache.pendingSourceAccessTimes); waiting != maxPendingAccessTimes {
t.Errorf("%d access times of sources wait to be written, want %d",
waiting, maxPendingAccessTimes)
}
}
// TestStopPendingCountWrites_WritesPendingAccessTimes hands the access time
// of one of two variants, three times, then stops the goroutine that writes
// them, which never started. The stop must write that access time and
// leave the other variant's.
func TestStopPendingCountWrites_WritesPendingAccessTimes(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
anHourAgo := time.Now().Add(-time.Hour)
for _, key := range []imagerequest.VariantKey{testVariantKeyOne, testVariantKeyTwo} {
storeEvictionTestVariant(t, cache, key, []byte("variant bytes"))
setVariantLastAccessed(t, cache, key, anHourAgo)
}
for range 3 {
cache.touchVariant(testVariantKeyOne)
}
err := cache.StopPendingCountWrites(t.Context())
if err != nil {
t.Fatalf("StopPendingCountWrites() error = %v", err)
}
for key, wantTouched := range map[imagerequest.VariantKey]int{
testVariantKeyOne: 1, testVariantKeyTwo: 0,
} {
touched := countRows(t, cache, `
SELECT COUNT(*) FROM variant_content
WHERE cache_key = ? AND last_accessed_at > ?
`, string(key), anHourAgo.UTC().Format(sqliteTimestampFormat))
if touched != wantTouched {
t.Errorf("variant %s: %d rows with a new access time, want %d",
key, touched, wantTouched)
}
}
if waiting := len(cache.pendingVariantAccessTimes); waiting != 0 {
t.Errorf("%d access times still wait to be written, want 0", waiting)
}
}
internal/imgcache/cache_internal_test.go
+364 -7
View File
@@ -1,6 +1,7 @@
package imgcache
import (
"bytes"
"context"
"database/sql"
"os"
@@ -8,6 +9,7 @@ import (
"time"
_ "modernc.org/sqlite"
"sneak.berlin/go/pixa/internal/httpfetcher"
)
func setupTestDB(t *testing.T) *sql.DB {
@@ -21,15 +23,54 @@ func setupTestDB(t *testing.T) *sql.DB {
// Create schema
schema := `
CREATE TABLE source_content (
source_key TEXT PRIMARY KEY,
content_hash TEXT PRIMARY KEY,
content_type TEXT NOT NULL,
size_bytes INTEGER NOT NULL,
last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE source_metadata (
id INTEGER PRIMARY KEY AUTOINCREMENT,
source_host TEXT NOT NULL,
source_path TEXT NOT NULL,
source_query TEXT NOT NULL DEFAULT '',
path_hash TEXT NOT NULL,
content_hash TEXT,
status_code INTEGER NOT NULL,
content_type TEXT,
response_headers TEXT,
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
expires_at DATETIME,
etag TEXT,
last_modified TEXT,
UNIQUE(source_host, source_path, source_query)
);
CREATE TABLE output_content (
content_hash TEXT PRIMARY KEY,
content_type TEXT NOT NULL,
size_bytes INTEGER NOT NULL,
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE request_cache (
id INTEGER PRIMARY KEY AUTOINCREMENT,
cache_key TEXT NOT NULL UNIQUE,
source_metadata_id INTEGER NOT NULL,
output_hash TEXT NOT NULL,
width INTEGER NOT NULL,
height INTEGER NOT NULL,
format TEXT NOT NULL,
quality INTEGER NOT NULL DEFAULT 85,
fit_mode TEXT NOT NULL DEFAULT 'cover',
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
access_count INTEGER NOT NULL DEFAULT 1
);
CREATE TABLE negative_cache (
id INTEGER PRIMARY KEY AUTOINCREMENT,
source_host TEXT NOT NULL,
source_path TEXT NOT NULL,
source_query TEXT NOT NULL DEFAULT '',
status_code INTEGER NOT NULL,
error_message TEXT,
fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
expires_at DATETIME NOT NULL,
UNIQUE(source_host, source_path, source_query)
);
@@ -61,6 +102,7 @@ func setupTestCache(t *testing.T) *Cache {
cache, err := NewCache(db, CacheConfig{
StateDir: tmpDir,
CacheTTL: time.Hour,
NegativeTTL: 5 * time.Minute,
})
if err != nil {
@@ -70,6 +112,320 @@ func setupTestCache(t *testing.T) *Cache {
return cache
}
func TestCache_LookupMiss(t *testing.T) {
t.Parallel()
cache := setupTestCache(t)
ctx := context.Background()
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: testPathCat,
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
}
result, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() error = %v", err)
}
if result.Hit {
t.Error("Lookup() hit = true, want false for cache miss")
}
if result.CacheStatus != CacheMiss {
t.Errorf("Lookup() status = %v, want %v", result.CacheStatus, CacheMiss)
}
}
func TestCache_StoreAndLookup(t *testing.T) {
t.Parallel()
cache := setupTestCache(t)
ctx := context.Background()
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: testPathCat,
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
}
// Store source content
sourceContent := []byte("fake jpeg data")
fetchResult := &httpfetcher.FetchResult{
ContentType: testContentTypeJPEG,
Headers: map[string][]string{testHeaderContentType: {testContentTypeJPEG}},
}
contentHash, err := cache.StoreSource(
ctx, req, bytes.NewReader(sourceContent), fetchResult)
if err != nil {
t.Fatalf("StoreSource() error = %v", err)
}
if contentHash == "" {
t.Error("StoreSource() returned empty hash")
}
// Store variant
cacheKey := CacheKey(req)
outputContent := []byte("fake webp data")
err = cache.StoreVariant(
t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
if err != nil {
t.Fatalf("StoreVariant() error = %v", err)
}
// Now lookup should hit
result, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() error = %v", err)
}
if !result.Hit {
t.Error("Lookup() hit = false, want true after store")
}
if result.CacheStatus != CacheHit {
t.Errorf("Lookup() status = %v, want %v", result.CacheStatus, CacheHit)
}
if result.CacheKey == "" {
t.Error("Lookup() returned empty cache key")
}
}
func TestCache_NegativeCache(t *testing.T) {
t.Parallel()
cache := setupTestCache(t)
ctx := context.Background()
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: "/photos/notfound.jpg",
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
}
// Store negative cache entry
err := cache.StoreNegative(ctx, req, 404, "not found")
if err != nil {
t.Fatalf("StoreNegative() error = %v", err)
}
// Lookup should return miss (negative cache is checked at service level)
result, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() error = %v", err)
}
if result.Hit {
t.Error("Lookup() hit = true, want false for negative cache entry")
}
}
func TestCache_NegativeCacheExpiry(t *testing.T) {
t.Parallel()
tmpDir := t.TempDir()
db := setupTestDB(t)
// Very short negative TTL for testing
cache, err := NewCache(db, CacheConfig{
StateDir: tmpDir,
CacheTTL: time.Hour,
NegativeTTL: 1 * time.Millisecond,
})
if err != nil {
t.Fatalf("failed to create cache: %v", err)
}
ctx := context.Background()
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: "/photos/expired.jpg",
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
}
// Store negative cache entry
err = cache.StoreNegative(ctx, req, 404, "not found")
if err != nil {
t.Fatalf("StoreNegative() error = %v", err)
}
// Wait for expiry
time.Sleep(10 * time.Millisecond)
// Lookup should return miss after expiry
result, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() error = %v, want nil after expiry", err)
}
if result.Hit {
t.Error("Lookup() hit = true, want false after negative cache expiry")
}
}
func TestCache_VariantLookup(t *testing.T) {
t.Parallel()
cache := setupTestCache(t)
ctx := context.Background()
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: "/photos/variant.jpg",
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
}
// Store variant
cacheKey := CacheKey(req)
outputContent := []byte("output data")
err := cache.StoreVariant(
t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
if err != nil {
t.Fatalf("StoreVariant() error = %v", err)
}
// First lookup
result1, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() first error = %v", err)
}
if !result1.Hit {
t.Error("Lookup() first hit = false")
}
// Second lookup should also hit (from disk)
result2, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() second error = %v", err)
}
if !result2.Hit {
t.Error("Lookup() second hit = false")
}
if result1.CacheKey != result2.CacheKey {
t.Error("Lookup() returned different cache keys")
}
}
func TestCache_GetVariant_ReturnsContentType(t *testing.T) {
t.Parallel()
cache := setupTestCache(t)
ctx := context.Background()
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: "/photos/variantct.jpg",
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
}
// Store variant
cacheKey := CacheKey(req)
outputContent := []byte("output webp data")
err := cache.StoreVariant(
t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
if err != nil {
t.Fatalf("StoreVariant() error = %v", err)
}
// Lookup
result, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() error = %v", err)
}
if !result.Hit {
t.Fatal("Lookup() hit = false, want true")
}
// GetVariant should return content type
reader, size, contentType, err := cache.GetVariant(result.CacheKey)
if err != nil {
t.Fatalf("GetVariant() error = %v", err)
}
defer func() { _ = reader.Close() }()
if contentType != "image/webp" {
t.Errorf("GetVariant() ContentType = %q, want %q", contentType, "image/webp")
}
if size != int64(len(outputContent)) {
t.Errorf("GetVariant() size = %d, want %d", size, len(outputContent))
}
}
func TestCache_GetVariant(t *testing.T) {
t.Parallel()
cache := setupTestCache(t)
ctx := context.Background()
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: "/photos/output.jpg",
Size: Size{Width: 800, Height: 600},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
}
// Store variant
cacheKey := CacheKey(req)
outputContent := []byte("the actual output content")
err := cache.StoreVariant(
t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
if err != nil {
t.Fatalf("StoreVariant() error = %v", err)
}
// Lookup to get cache key
result, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup() error = %v", err)
}
// Get variant content
reader, _, _, err := cache.GetVariant(result.CacheKey)
if err != nil {
t.Fatalf("GetVariant() error = %v", err)
}
defer func() { _ = reader.Close() }()
buf := make([]byte, 100)
n, _ := reader.Read(buf)
if !bytes.Equal(buf[:n], outputContent) {
t.Errorf("GetVariant() content = %q, want %q", buf[:n], outputContent)
}
}
func TestCache_Stats(t *testing.T) {
t.Parallel()
@@ -77,9 +433,9 @@ func TestCache_Stats(t *testing.T) {
ctx := context.Background()
// Increment some stats
cache.IncrementStats(true, 0)
cache.IncrementStats(true, 0)
cache.IncrementStats(false, 1024)
cache.IncrementStats(ctx, true, 0)
cache.IncrementStats(ctx, true, 0)
cache.IncrementStats(ctx, false, 1024)
stats, err := cache.Stats(ctx)
if err != nil {
@@ -111,8 +467,8 @@ func TestCache_CleanExpired(t *testing.T) {
// Insert expired negative cache entry directly
_, err := db.ExecContext(ctx, `
INSERT INTO negative_cache
(source_host, source_path, source_query, expires_at)
VALUES ('example.com', '/old.jpg', '', datetime('now', '-1 hour'))
(source_host, source_path, source_query, status_code, expires_at)
VALUES ('example.com', '/old.jpg', '', 404, datetime('now', '-1 hour'))
`)
if err != nil {
t.Fatalf("failed to insert test data: %v", err)
@@ -164,6 +520,7 @@ func TestCache_StorageDirectoriesCreated(t *testing.T) {
dirs := []string{
"cache/sources",
"cache/variants",
"cache/metadata",
}
for _, dir := range dirs {
internal/imgcache/cache_usage_internal_test.go
-270
View File
@@ -1,270 +0,0 @@
package imgcache
import (
"bytes"
"strconv"
"strings"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestEvictionReadsTheUsageTotal adds, stores again, resizes and evicts
// cache content, then drops both content tables. UsageBytes must still
// report what the tables held, and an eviction pass under the limit must
// still succeed: neither may sum the tables.
func TestEvictionReadsTheUsageTotal(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
ctx := t.Context()
kept := storeEvictionTestSource(t, cache, "total.example.com", "/kept.jpg",
bytes.Repeat([]byte{0x71}, 1000))
evicted := storeEvictionTestSource(t, cache, "total.example.com", "/evicted.jpg",
bytes.Repeat([]byte{0x72}, 700))
storeEvictionTestVariant(t, cache, testVariantKeyOne,
bytes.Repeat([]byte{0x73}, 500))
storeEvictionTestVariant(t, cache, testVariantKeyOne,
bytes.Repeat([]byte{0x74}, 300))
storeEvictionTestVariant(t, cache, testVariantKeyTwo,
bytes.Repeat([]byte{0x75}, 200))
// Storing a source URL again changes its size, so the total must
// follow a statement that changes it.
_, err := cache.db.ExecContext(ctx,
`UPDATE source_content SET size_bytes = 900 WHERE source_key = ?`,
string(kept))
if err != nil {
t.Fatalf("failed to change the source's size: %v", err)
}
err = cache.evictSourceBlob(ctx, evicted)
if err != nil {
t.Fatalf("evictSourceBlob failed: %v", err)
}
err = cache.evictVariant(ctx, testVariantKeyTwo)
if err != nil {
t.Fatalf("evictVariant failed: %v", err)
}
_, err = cache.db.ExecContext(ctx,
`DROP TABLE source_content; DROP TABLE variant_content`)
if err != nil {
t.Fatalf("failed to drop the content tables: %v", err)
}
usage, err := cache.UsageBytes(ctx)
t.Logf("UsageBytes() = %d, error = %v", usage, err)
if err != nil {
t.Fatalf("UsageBytes() error = %v, want nil: it read a content table", err)
}
if usage != 1200 {
t.Errorf("UsageBytes() = %d, want 1200 (900 + 300)", usage)
}
err = cache.EvictToLimit(ctx)
if err != nil {
t.Errorf("EvictToLimit() error = %v, want nil: it read a content table", err)
}
}
// TestReconciliationCorrectsTheUsageTotal sets the total cache usage to a
// wrong value and checks that a reconciliation pass, which sums both
// content tables, puts it right.
func TestReconciliationCorrectsTheUsageTotal(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
ctx := t.Context()
storeEvictionTestSource(t, cache, "total.example.com", "/a.jpg",
bytes.Repeat([]byte{0x76}, 1000))
storeEvictionTestVariant(t, cache, testVariantKeyOne,
bytes.Repeat([]byte{0x77}, 500))
_, err := cache.db.ExecContext(ctx,
`UPDATE cache_usage SET total_size_bytes = 1 WHERE id = 1`)
if err != nil {
t.Fatalf("failed to set a wrong total: %v", err)
}
err = cache.reconcileAccounting(ctx)
if err != nil {
t.Fatalf("reconcileAccounting failed: %v", err)
}
usage, err := cache.UsageBytes(ctx)
if err != nil {
t.Fatalf("UsageBytes failed: %v", err)
}
if usage != 1500 {
t.Errorf("UsageBytes() after reconciliation = %d, want 1500 (1000 + 500)",
usage)
}
}
// TestUsageTotalNotCorrectedFromAnOlderSum stores a variant after the
// change count was read, then offers a sum taken before the store as the
// correction: the total must keep the stored variant, as that sum may
// have missed it.
func TestUsageTotalNotCorrectedFromAnOlderSum(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
ctx := t.Context()
var changeCount int64
err := cache.db.QueryRowContext(ctx,
`SELECT change_count FROM cache_usage WHERE id = 1`,
).Scan(&changeCount)
if err != nil {
t.Fatalf("failed to read the change count: %v", err)
}
storeEvictionTestVariant(t, cache, testVariantKeyOne,
bytes.Repeat([]byte{0x78}, 500))
corrected, err := cache.correctUsageTotal(ctx, 0, changeCount)
if err != nil {
t.Fatalf("correctUsageTotal failed: %v", err)
}
if corrected {
t.Error("correctUsageTotal() = true, want false: content changed since the sum")
}
usage, err := cache.UsageBytes(ctx)
if err != nil {
t.Fatalf("UsageBytes failed: %v", err)
}
if usage != 500 {
t.Errorf("UsageBytes() = %d, want 500", usage)
}
}
// TestReconciliationReadsAPageAtATime stores five source images and five
// variants, sets the page size to two rows and runs a reconciliation
// pass. No read the pass makes of a content table, to check its rows or
// to sum them, may cover more than two rows, so a request's query waits
// for one page at most. Between them the reads must still cover every
// variant row twice, once to check it and once to sum it, and every
// source row once, as source rows are read only to sum them, and the sum
// must put a wrong total right.
func TestReconciliationReadsAPageAtATime(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
ctx := t.Context()
const pageSize = 2
cache.reconciliationPageSize = pageSize
// Sources of 100 bytes and variants of 10, five of each.
for i := range 5 {
content := []byte(strconv.Itoa(i))
storeEvictionTestSource(t, cache, "pages.example.com",
"/"+strconv.Itoa(i)+".jpg", bytes.Repeat(content, 100))
storeEvictionTestVariant(t, cache,
imagerequest.VariantKey("aabbccdd000"+strconv.Itoa(i)),
bytes.Repeat(content, 10))
}
_, err := cache.db.ExecContext(ctx,
`UPDATE cache_usage SET total_size_bytes = 1 WHERE id = 1`)
if err != nil {
t.Fatalf("failed to set a wrong total: %v", err)
}
var rowsPerRead []int
cache.reconciliationReadTestHook = func(rows int) {
rowsPerRead = append(rowsPerRead, rows)
}
err = cache.reconcileAccounting(ctx)
if err != nil {
t.Fatalf("reconcileAccounting failed: %v", err)
}
t.Logf("rows covered by each read, in order: %v", rowsPerRead)
coveredRows := 0
for _, rows := range rowsPerRead {
if rows > pageSize {
t.Errorf("a read covered %d rows, want at most %d", rows, pageSize)
}
coveredRows += rows
}
// Five variant rows, each read once to check it and once to sum it,
// and five source rows, read only to sum them.
if coveredRows != 15 {
t.Errorf("the reads covered %d rows in all, want 15", coveredRows)
}
usage, err := cache.UsageBytes(ctx)
if err != nil {
t.Fatalf("UsageBytes failed: %v", err)
}
if usage != 550 {
t.Errorf("UsageBytes() after reconciliation = %d, want 550 (5*100 + 5*10)",
usage)
}
}
// TestSourceEvictionCandidatesComeFromTheIndex checks that the query
// choosing source images to evict reads source_content in last access
// order from its index, instead of reading and sorting the whole table.
func TestSourceEvictionCandidatesComeFromTheIndex(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
rows, err := cache.db.QueryContext(t.Context(),
`EXPLAIN QUERY PLAN `+sourceCandidatesQuery, evictionBatchSize)
if err != nil {
t.Fatalf("EXPLAIN QUERY PLAN failed: %v", err)
}
defer func() { _ = rows.Close() }()
var plan []string
for rows.Next() {
var id, parent, unused int
var detail string
err := rows.Scan(&id, &parent, &unused, &detail)
if err != nil {
t.Fatalf("failed to scan the query plan: %v", err)
}
plan = append(plan, detail)
}
err = rows.Err()
if err != nil {
t.Fatalf("query plan iteration failed: %v", err)
}
t.Logf("query plan: %q", plan)
if !strings.Contains(strings.Join(plan, "\n"), "idx_source_content_last_accessed") {
t.Errorf("the source candidate query does not use "+
"idx_source_content_last_accessed; plan: %q", plan)
}
}
internal/imgcache/cachesize.go
+5 -1
View File
@@ -72,12 +72,16 @@ func (c *Cache) computeDefaultMaxBytes(
}
// Both terms are at most math.MaxInt64, so the sum cannot overflow.
//nolint:gosec // G115: UsageBytes returns the total cache usage, never negative
//nolint:gosec // G115: UsageBytes sums file sizes, never negative
spaceBytes := min(freeBytes, math.MaxInt64) + uint64(usedBytes)
computed := spaceBytes / freeSpaceFractionDenominator * freeSpaceFractionNumerator
computed = min(computed, math.MaxInt64)
// gosec cannot see that min() above bounds computed, so it reads
// this conversion as potentially overflowing. It cannot: computed is
// at most math.MaxInt64 on every path here.
//nolint:gosec // G115: clamped to MaxInt64 by min above
limit := int64(computed)
limit = max(limit, DefaultCacheMaxBytesFloor)
internal/imgcache/cachesize_internal_test.go
+3 -2
View File
@@ -39,8 +39,9 @@ func TestComputeDefaultMaxBytesCountsWhatTheCacheHolds(t *testing.T) {
// The cache now holds those 3 GiB, which leaves 1 GiB free.
_, err = cache.db.ExecContext(t.Context(),
`INSERT INTO variant_content (cache_key, size_bytes) VALUES (?, ?)`,
string(testVariantKeyOne), 3221225472,
`INSERT INTO variant_content (cache_key, size_bytes, content_type)
VALUES (?, ?, ?)`,
string(testVariantKeyOne), 3221225472, testContentTypeWebP,
)
if err != nil {
t.Fatalf("failed to insert variant accounting row: %v", err)
internal/imgcache/concurrent_misses_internal_test.go
+28 -80
View File
@@ -15,8 +15,6 @@ import (
"github.com/getsentry/sentry-go"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/magic"
)
@@ -81,20 +79,14 @@ func setupHeldFetchService(t *testing.T) (*Service, *TestFixtures, *heldFetcher)
// photoVariant asks for the test photo, 100x100, at 50x25 as a JPEG of the
// given quality and fit mode. Each call returns a new request, as Get writes
// to the request it is given.
func photoVariant(
fixtures *TestFixtures, quality int, fit imagerequest.Fit,
) *imagerequest.Request {
return &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 25},
Format: imagerequest.FormatJPEG,
Quality: quality,
FitMode: fit,
},
func photoVariant(fixtures *TestFixtures, quality int, fit FitMode) *ImageRequest {
return &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 50, Height: 25},
Format: FormatJPEG,
Quality: quality,
FitMode: fit,
}
}
@@ -107,7 +99,7 @@ type getResult struct {
// startGet calls Get in a goroutine of its own and delivers what it returned
// on the channel.
func startGet(
ctx context.Context, svc *Service, req *imagerequest.Request,
ctx context.Context, svc *Service, req *ImageRequest,
) <-chan getResult {
results := make(chan getResult, 1)
@@ -153,7 +145,7 @@ func TestService_Get_ConcurrentMissesShareOneFetch(t *testing.T) {
pending := make([]<-chan getResult, 0, requests)
for range requests {
pending = append(pending,
startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover)))
startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover)))
}
<-fetcher.started
@@ -193,8 +185,6 @@ func TestService_Get_ConcurrentMissesShareOneFetch(t *testing.T) {
want := cacheStatsCounters{0, requests, 1, int64(len(photo)), 1}
waitForPendingCountsWritten(t, svc.cache)
if got := readCacheStatsCounters(t, svc.cache); got != want {
t.Errorf("counters = %+v, want %+v", got, want)
}
@@ -208,11 +198,9 @@ func TestService_Get_ConcurrentVariantsStayApart(t *testing.T) {
svc, fixtures, fetcher := setupHeldFetchService(t)
cover := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
lowQuality := startGet(t.Context(), svc,
photoVariant(fixtures, 40, imagerequest.FitCover))
contain := startGet(t.Context(), svc,
photoVariant(fixtures, 85, imagerequest.FitContain))
cover := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover))
lowQuality := startGet(t.Context(), svc, photoVariant(fixtures, 40, FitCover))
contain := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitContain))
for range 3 {
select {
@@ -264,12 +252,12 @@ func TestService_Get_WaiterStopsWhenItsContextEnds(t *testing.T) {
svc, fixtures, fetcher := setupHeldFetchService(t)
first := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
first := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover))
<-fetcher.started
waiterCtx, cancelWaiter := context.WithCancel(t.Context())
waiter := startGet(waiterCtx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
waiter := startGet(waiterCtx, svc, photoVariant(fixtures, 85, FitCover))
time.Sleep(arrivalWait)
cancelWaiter()
@@ -311,11 +299,11 @@ func TestService_Get_FirstRequestLeavingKeepsTheWork(t *testing.T) {
svc, fixtures, fetcher := setupHeldFetchService(t)
firstCtx, cancelFirst := context.WithCancel(t.Context())
first := startGet(firstCtx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
first := startGet(firstCtx, svc, photoVariant(fixtures, 85, FitCover))
<-fetcher.started
second := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
second := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover))
time.Sleep(arrivalWait)
cancelFirst()
@@ -342,7 +330,8 @@ func TestService_Get_FirstRequestLeavingKeepsTheWork(t *testing.T) {
// TestService_Get_ConcurrentMissesShareAFailure has several requests for an
// image that cannot be served arrive while its fetch is held: the one fetch
// answers all of them with its error. The request after them is answered from
// the negative cache, where the failure is kept.
// the negative cache when the failure is kept there, and fetches again when it
// is not.
func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
t.Parallel()
@@ -356,8 +345,8 @@ func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
{"upstream answers 404, kept in the negative cache",
"/images/missing.jpg", httpfetcher.ErrUpstreamError,
ErrNegativeCached, 1},
{"source fails the magic byte check, kept in the negative cache",
"/images/text.png", magic.ErrUnknownFormat, ErrNegativeCached, 1},
{"source fails the magic byte check, not kept",
"/images/text.png", magic.ErrUnknownFormat, magic.ErrUnknownFormat, 2},
}
for _, tc := range tests {
@@ -366,9 +355,9 @@ func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
svc, fixtures, fetcher := setupHeldFetchService(t)
request := func() *imagerequest.Request {
req := photoVariant(fixtures, 85, imagerequest.FitCover)
req.Source.Path = tc.path
request := func() *ImageRequest {
req := photoVariant(fixtures, 85, FitCover)
req.SourcePath = tc.path
return req
}
@@ -410,7 +399,7 @@ func TestService_Get_EndedRequestFetchesNothing(t *testing.T) {
ctx, cancel := context.WithCancel(t.Context())
cancel()
_, err := svc.Get(ctx, photoVariant(fixtures, 85, imagerequest.FitCover))
_, err := svc.Get(ctx, photoVariant(fixtures, 85, FitCover))
if !errors.Is(err, context.Canceled) {
t.Errorf("Get() error = %v, want %v", err, context.Canceled)
}
@@ -434,7 +423,7 @@ func TestService_Get_ReturnsByItsDeadline(t *testing.T) {
ctx, cancel := context.WithTimeout(t.Context(), timeout)
defer cancel()
results := startGet(ctx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
results := startGet(ctx, svc, photoVariant(fixtures, 85, FitCover))
select {
case got := <-results:
@@ -446,47 +435,6 @@ func TestService_Get_ReturnsByItsDeadline(t *testing.T) {
}
}
// TestService_Get_WaiterGetsProcessingTimedOut has a request with no deadline
// join the held fetch of a first request with a short one. With the only
// processing slot held, the first request's transcode waits for it until the
// first request's deadline ends, and stops then. The waiting request, whose
// own context has not ended, must get ErrProcessingTimedOut, which the image
// routes answer 503 as when pixa is busy.
func TestService_Get_WaiterGetsProcessingTimedOut(t *testing.T) {
t.Parallel()
svc, fixtures, fetcher := setupHeldFetchService(t)
svc.processor = imageprocessor.New(
imageprocessor.Params{MaxConcurrentProcessing: 1},
)
holdProcessingSlot(t, svc.processor)
const firstTimeout = 500 * time.Millisecond
firstCtx, cancelFirst := context.WithTimeout(t.Context(), firstTimeout)
defer cancelFirst()
first := startGet(firstCtx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
<-fetcher.started
waiter := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
time.Sleep(arrivalWait)
fetcher.releaseFetches()
t.Logf("first request: Get() error = %v", (<-first).err)
got := <-waiter
t.Logf("waiting request: Get() error = %v", got.err)
if !errors.Is(got.err, ErrProcessingTimedOut) {
t.Errorf("waiting request: Get() error = %v, want %v",
got.err, ErrProcessingTimedOut)
}
}
// panickingFetcher panics on every fetch.
type panickingFetcher struct{}
@@ -514,7 +462,7 @@ func TestService_Get_PanicBecomesAnError(t *testing.T) {
}
}()
_, err = svc.Get(t.Context(), photoVariant(fixtures, 85, imagerequest.FitCover))
_, err = svc.Get(t.Context(), photoVariant(fixtures, 85, FitCover))
}()
if err == nil || !strings.Contains(err.Error(), "upstream fetcher panicked") {
@@ -551,7 +499,7 @@ func TestService_Get_PanicIsReportedToSentry(t *testing.T) {
}
}()
_, _ = svc.Get(ctx, photoVariant(fixtures, 85, imagerequest.FitCover))
_, _ = svc.Get(ctx, photoVariant(fixtures, 85, FitCover))
}()
events := transport.Events()
internal/imgcache/contentlock.go
+64
View File
@@ -0,0 +1,64 @@
package imgcache
import "sync"
// contentLock provides per-key mutual exclusion for content-hash keyed
// operations. StoreSource and evictSourceBlob each hold a content
// hash's lock for the full duration of their file-plus-accounting-row
// work, so a store and an eviction racing on identical content bytes
// (the real SHA-256 content-addressed dedup case, not a contrived one)
// can never interleave: the unlink of an evicted blob's file can never
// race the creation of a fresh database row for a concurrently
// re-stored copy of the same content. Entries are removed once no
// goroutine holds or is waiting for them, so a long-running process
// does not accumulate memory proportional to the number of distinct
// content hashes it has ever seen.
type contentLock struct {
mu sync.Mutex
entries map[string]*contentLockEntry
}
// contentLockEntry is one key's exclusion lock plus a count of
// goroutines currently holding or waiting to acquire it, used to know
// when it is safe to remove the entry from the map.
type contentLockEntry struct {
mu sync.Mutex
count int
}
// newContentLock creates an empty contentLock.
func newContentLock() *contentLock {
return &contentLock{entries: make(map[string]*contentLockEntry)}
}
// Lock acquires exclusive access for key, blocking until it is
// available, and returns a function that releases it. The caller must
// invoke the returned function exactly once to release the lock.
func (c *contentLock) Lock(key string) func() {
c.mu.Lock()
entry, ok := c.entries[key]
if !ok {
entry = &contentLockEntry{}
c.entries[key] = entry
}
entry.count++
c.mu.Unlock()
entry.mu.Lock()
return func() {
entry.mu.Unlock()
c.mu.Lock()
entry.count--
if entry.count == 0 {
delete(c.entries, key)
}
c.mu.Unlock()
}
}
internal/imgcache/contentlock_internal_test.go
+142
View File
@@ -0,0 +1,142 @@
package imgcache
import (
"sync"
"sync/atomic"
"testing"
"time"
)
// TestContentLockExcludesSameKey verifies that two goroutines locking
// the same key never run their critical sections concurrently.
func TestContentLockExcludesSameKey(t *testing.T) {
t.Parallel()
lock := newContentLock()
var (
active atomic.Int32
maxSeen int32
wg sync.WaitGroup
)
const goroutines = 20
wg.Add(goroutines)
for range goroutines {
go func() {
defer wg.Done()
unlock := lock.Lock("same-key")
defer unlock()
n := active.Add(1)
for {
seen := atomic.LoadInt32(&maxSeen)
if n <= seen || atomic.CompareAndSwapInt32(&maxSeen, seen, n) {
break
}
}
time.Sleep(time.Millisecond)
active.Add(-1)
}()
}
wg.Wait()
if maxSeen != 1 {
t.Errorf("max concurrent holders of the same key = %d, want 1", maxSeen)
}
}
// TestContentLockAllowsDifferentKeys verifies that locking distinct
// keys does not serialize unrelated work: all goroutines must be able
// to enter their critical sections at once, proven by every one of
// them reaching the rendezvous point before any is allowed to
// proceed.
func TestContentLockAllowsDifferentKeys(t *testing.T) {
t.Parallel()
lock := newContentLock()
const goroutines = 20
var (
wg sync.WaitGroup
inside atomic.Int32
reached = make(chan struct{}, goroutines)
)
wg.Add(goroutines)
release := make(chan struct{})
for i := range goroutines {
key := string(rune('a' + i))
go func() {
defer wg.Done()
unlock := lock.Lock(key)
defer unlock()
inside.Add(1)
reached <- struct{}{}
<-release
}()
}
// Every goroutine must reach the rendezvous point (i.e. acquire its
// own key's lock) without needing any other to release first. If
// keys were incorrectly serialized onto one underlying lock, only
// one would get here and this would time out.
for i := range goroutines {
select {
case <-reached:
case <-time.After(2 * time.Second):
t.Fatalf("only %d/%d goroutines locking distinct keys made progress; "+
"keys may be incorrectly serialized", i, goroutines)
}
}
if n := inside.Load(); n != goroutines {
t.Errorf("goroutines inside their critical section = %d, want %d",
n, goroutines)
}
close(release)
wg.Wait()
}
// TestContentLockRemovesEntryAfterUnlock verifies that the internal
// entries map does not grow without bound: once no goroutine holds or
// awaits a key, its entry is removed.
func TestContentLockRemovesEntryAfterUnlock(t *testing.T) {
t.Parallel()
lock := newContentLock()
unlock := lock.Lock("k")
lock.mu.Lock()
if _, ok := lock.entries["k"]; !ok {
lock.mu.Unlock()
t.Fatal("entry missing while lock is held")
}
lock.mu.Unlock()
unlock()
lock.mu.Lock()
defer lock.mu.Unlock()
if _, ok := lock.entries["k"]; ok {
t.Error("entry for key still present after the last holder unlocked")
}
}
internal/imgcache/eviction.go
+335 -391
View File
@@ -3,15 +3,13 @@ package imgcache
import (
"context"
"database/sql"
"errors"
"encoding/json"
"fmt"
"io/fs"
"os"
"path/filepath"
"strings"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// DefaultEvictionInterval is how often the background evictor checks
@@ -19,24 +17,10 @@ import (
// write-pressure wakeups triggered by stores.
const DefaultEvictionInterval = 5 * time.Minute
// reconciliationWaitFactor is how many times as long as a
// reconciliation pass took the eviction loop waits at least, after that
// pass ends, before it starts the next one. A pass reads a row and stats a
// file for every cached file, so its time grows with the cache; waiting
// ten times as long keeps reconciliation to at most a tenth of the time,
// however large the cache is.
const reconciliationWaitFactor = 10
// evictionBatchSize is how many LRU candidates of each class (variants
// and source blobs) one eviction pass fetches from the database.
const evictionBatchSize = 100
// defaultReconciliationPageSize is the most rows one read of the
// reconciliation pass returns, unless a test sets
// Cache.reconciliationPageSize smaller. Each read is a query of its own,
// so a request waits for one page at most, however large the cache is.
const defaultReconciliationPageSize = 1000
// staleTempFileAge is how old an orphaned temp file (left behind by a
// crashed write) must be before reconciliation removes it. Fresh temp
// files may still belong to an in-flight store.
@@ -51,11 +35,17 @@ const sqliteTimestampLayout = "2006-01-02 15:04:05"
// writes (".tmp-*" patterns in the storage layer).
const tempFilePrefix = ".tmp-"
// variantMetaSuffix is the sidecar suffix VariantStorage writes next
// to each variant file.
const variantMetaSuffix = ".meta"
// fallbackContentType is the content type given to a variant file that
// has no readable .meta sidecar, when it is served or reconciled.
const fallbackContentType = "application/octet-stream"
// UsageBytes returns the total number of bytes of cache content
// tracked in the database (source content blobs plus processed
// variants). It reads the total the database keeps up to date as rows
// are added and removed, so it neither scans the cache directories nor
// sums the tables.
// variants). It never scans the cache directories.
func (c *Cache) UsageBytes(ctx context.Context) (int64, error) {
if c.disabled {
return 0, nil
@@ -63,11 +53,12 @@ func (c *Cache) UsageBytes(ctx context.Context) (int64, error) {
var total int64
err := c.db.QueryRowContext(ctx,
`SELECT total_size_bytes FROM cache_usage WHERE id = 1`,
).Scan(&total)
err := c.db.QueryRowContext(ctx, `
SELECT (SELECT COALESCE(SUM(size_bytes), 0) FROM source_content)
+ (SELECT COALESCE(SUM(size_bytes), 0) FROM variant_content)
`).Scan(&total)
if err != nil {
return 0, fmt.Errorf("failed to read cache usage: %w", err)
return 0, fmt.Errorf("failed to compute cache usage: %w", err)
}
return total, nil
@@ -75,11 +66,11 @@ func (c *Cache) UsageBytes(ctx context.Context) (int64, error) {
// evictionCandidate is one LRU eviction victim candidate: either a
// processed variant (isVariant true, identified by cacheKey) or a
// source content blob (identified by sourceKey).
// source content blob (identified by contentHash).
type evictionCandidate struct {
isVariant bool
cacheKey imagerequest.VariantKey
sourceKey imagerequest.SourceKey
cacheKey VariantKey
contentHash ContentHash
sizeBytes int64
lastAccessedAt string
}
@@ -151,7 +142,7 @@ func (c *Cache) evictBatch(ctx context.Context, excessBytes int64) (int64, error
c.log.Warn("failed to evict cache entry",
"cache_key", candidate.cacheKey,
"source_key", candidate.sourceKey,
"content_hash", candidate.contentHash,
"error", err,
)
@@ -170,7 +161,7 @@ func (c *Cache) evictCandidate(ctx context.Context, candidate evictionCandidate)
return c.evictVariant(ctx, candidate.cacheKey)
}
return c.evictSourceBlob(ctx, candidate.sourceKey)
return c.evictSourceBlob(ctx, candidate.contentHash)
}
// evictionCandidates returns up to evictionBatchSize variants and
@@ -233,7 +224,7 @@ func (c *Cache) variantCandidates(ctx context.Context) ([]evictionCandidate, err
return nil, fmt.Errorf("failed to scan variant candidate: %w", err)
}
candidate.cacheKey = imagerequest.VariantKey(key)
candidate.cacheKey = VariantKey(key)
candidates = append(candidates, candidate)
}
@@ -245,19 +236,16 @@ func (c *Cache) variantCandidates(ctx context.Context) ([]evictionCandidate, err
return candidates, nil
}
// sourceCandidatesQuery selects the least recently used source blobs. It
// orders by the last_accessed_at column itself, not by an expression, so
// SQLite reads the rows in order from that column's index instead of
// sorting the whole table.
const sourceCandidatesQuery = `
SELECT source_key, size_bytes, last_accessed_at
FROM source_content
ORDER BY last_accessed_at ASC, source_key ASC
LIMIT ?`
// sourceCandidates returns the least recently used source blobs.
// sourceCandidates returns the least recently used source blobs. Rows
// written before the LRU column existed fall back to fetched_at.
func (c *Cache) sourceCandidates(ctx context.Context) ([]evictionCandidate, error) {
rows, err := c.db.QueryContext(ctx, sourceCandidatesQuery, evictionBatchSize)
rows, err := c.db.QueryContext(ctx, `
SELECT content_hash, size_bytes,
COALESCE(last_accessed_at, fetched_at, '1970-01-01 00:00:00') AS lru
FROM source_content
ORDER BY lru ASC, content_hash ASC
LIMIT ?
`, evictionBatchSize)
if err != nil {
return nil, fmt.Errorf("failed to query source eviction candidates: %w", err)
}
@@ -269,14 +257,14 @@ func (c *Cache) sourceCandidates(ctx context.Context) ([]evictionCandidate, erro
for rows.Next() {
var candidate evictionCandidate
var key string
var hash string
err := rows.Scan(&key, &candidate.sizeBytes, &candidate.lastAccessedAt)
err := rows.Scan(&hash, &candidate.sizeBytes, &candidate.lastAccessedAt)
if err != nil {
return nil, fmt.Errorf("failed to scan source candidate: %w", err)
}
candidate.sourceKey = imagerequest.SourceKey(key)
candidate.contentHash = ContentHash(hash)
candidates = append(candidates, candidate)
}
@@ -289,16 +277,19 @@ func (c *Cache) sourceCandidates(ctx context.Context) ([]evictionCandidate, erro
}
// evictVariant removes one variant: accounting row first, then the
// file, so the database never references a deleted file.
func (c *Cache) evictVariant(
ctx context.Context, cacheKey imagerequest.VariantKey,
) error {
// content and .meta files, so the database never references a deleted
// file. The metaCache entry goes before the files; a GetVariant that
// read them just before may put it back, and the next GetVariant then
// fails to open the file and removes it again.
func (c *Cache) evictVariant(ctx context.Context, cacheKey VariantKey) error {
_, err := c.db.ExecContext(ctx,
`DELETE FROM variant_content WHERE cache_key = ?`, string(cacheKey))
if err != nil {
return fmt.Errorf("failed to delete variant accounting row: %w", err)
}
c.metaCache.Remove(cacheKey)
err = c.variants.Delete(cacheKey)
if err != nil {
return err
@@ -307,18 +298,117 @@ func (c *Cache) evictVariant(
return nil
}
// evictSourceBlob removes one source: its row first, then its file, as
// evictVariant does for a variant. It holds no lock: a store of the same
// source in between can leave the source's row with no file, which
// LookupSource treats as a miss.
func (c *Cache) evictSourceBlob(ctx context.Context, key imagerequest.SourceKey) error {
_, err := c.db.ExecContext(ctx,
`DELETE FROM source_content WHERE source_key = ?`, string(key))
// sourceReference identifies one source_metadata row's JSON sidecar.
type sourceReference struct {
host string
pathHash PathHash
}
// evictSourceBlob removes one source content blob. All source_metadata
// rows referencing the blob are deleted together with its
// source_content row in a single transaction BEFORE the file is
// unlinked: a blob referenced by multiple source paths is only ever
// removed together with all of its references, and database rows never
// point at deleted files. The JSON metadata sidecars for the removed
// rows are deleted afterwards.
//
// The whole operation holds the content hash's lock (the same one
// StoreSource holds for its full store), so a concurrent store of
// identical content bytes can never observe the file gone but a row
// still present, or insert a fresh row between this transaction's
// commit and the file unlink below: it either runs entirely before
// this eviction starts, or is blocked until this eviction (row
// deletion and unlink together) has fully completed.
func (c *Cache) evictSourceBlob(ctx context.Context, contentHash ContentHash) error {
unlock := c.contentLocks.Lock(string(contentHash))
defer unlock()
references, err := c.sourceReferences(ctx, contentHash)
if err != nil {
return err
}
tx, err := c.db.BeginTx(ctx, nil)
if err != nil {
return fmt.Errorf("failed to begin eviction transaction: %w", err)
}
defer func() { _ = tx.Rollback() }()
_, err = tx.ExecContext(ctx,
`DELETE FROM source_metadata WHERE content_hash = ?`, string(contentHash))
if err != nil {
return fmt.Errorf("failed to delete source metadata rows: %w", err)
}
_, err = tx.ExecContext(ctx,
`DELETE FROM source_content WHERE content_hash = ?`, string(contentHash))
if err != nil {
return fmt.Errorf("failed to delete source content row: %w", err)
}
return c.srcContent.Delete(key)
err = tx.Commit()
if err != nil {
return fmt.Errorf("failed to commit eviction transaction: %w", err)
}
if c.evictSourceBlobTestHook != nil {
c.evictSourceBlobTestHook(contentHash)
}
// Only after the rows are gone may the files be removed.
for _, reference := range references {
err := c.srcMetadata.Delete(reference.host, reference.pathHash)
if err != nil {
c.log.Warn("failed to delete metadata sidecar",
"host", reference.host, "path_hash", reference.pathHash, "error", err)
}
}
err = c.srcContent.Delete(contentHash)
if err != nil {
return err
}
return nil
}
// sourceReferences lists the metadata sidecar locations of every
// source_metadata row referencing the given blob.
func (c *Cache) sourceReferences(
ctx context.Context, contentHash ContentHash,
) ([]sourceReference, error) {
rows, err := c.db.QueryContext(ctx, `
SELECT source_host, path_hash FROM source_metadata WHERE content_hash = ?
`, string(contentHash))
if err != nil {
return nil, fmt.Errorf("failed to query source references: %w", err)
}
defer func() { _ = rows.Close() }()
var references []sourceReference
for rows.Next() {
var reference sourceReference
var pathHash string
err := rows.Scan(&reference.host, &pathHash)
if err != nil {
return nil, fmt.Errorf("failed to scan source reference: %w", err)
}
reference.pathHash = PathHash(pathHash)
references = append(references, reference)
}
err = rows.Err()
if err != nil {
return nil, fmt.Errorf("source reference iteration failed: %w", err)
}
return references, nil
}
// notifyWritePressure wakes the background evictor after a store, so
@@ -337,18 +427,14 @@ func (c *Cache) notifyWritePressure() {
}
// StartEviction launches the background eviction goroutine, which
// removes the expired negative cache rows at startup and again on every
// periodic tick thereafter, reconciles the database accounting with the
// cache directories at startup and again on the first periodic tick
// that comes at least ten times as long after a reconciliation pass
// ended as that pass took, and evicts to the configured limit on the given
// periodic interval and on write-pressure notifications. On a
// disabled cache it only removes the expired negative cache rows, as
// the negative cache is used either way. It is a no-op when already
// started. The goroutine outlives the caller, so it runs with its own
// context, which StopEviction cancels.
// reconciles the database accounting with the cache directories at
// startup and again on every periodic tick thereafter, and evicts to
// the configured limit on the given periodic interval and on
// write-pressure notifications. It is a no-op on a disabled cache or
// when already started. The goroutine outlives the caller, so it runs
// with its own context, which StopEviction cancels.
func (c *Cache) StartEviction(interval time.Duration) {
if c.evictionCancel != nil {
if c.disabled || c.evictionCancel != nil {
return
}
@@ -383,8 +469,7 @@ func (c *Cache) StopEviction(ctx context.Context) error {
func (c *Cache) evictionLoop(ctx context.Context, interval time.Duration) {
defer close(c.evictionDone)
nextReconciliation := c.runReconciliationPass(ctx)
c.runCleanExpired(ctx)
c.runReconciliationPass(ctx)
c.runEvictionPass(ctx)
ticker := time.NewTicker(interval)
@@ -395,21 +480,16 @@ func (c *Cache) evictionLoop(ctx context.Context, interval time.Duration) {
case <-ctx.Done():
return
case <-ticker.C:
// Reconciliation walks the cache directories and reads a
// row for every file, so it runs only on the periodic
// ticker rather than on every write-pressure wakeup, and
// only on the first tick at or after nextReconciliation,
// which is ten times as long after the last pass ended as
// that pass took. Passes then never run back to back,
// however long one takes. A file whose best-effort
// accounting insert failed in a store stays unaccounted for
// until the next pass, up to about one eviction interval
// plus ten times the last pass's time.
if !time.Now().Before(nextReconciliation) {
nextReconciliation = c.runReconciliationPass(ctx)
}
c.runCleanExpired(ctx)
// Reconciliation walks the cache directories, so it only
// runs on the periodic ticker rather than on every
// write-pressure wakeup, keeping it off the per-store hot
// path. Reusing the eviction interval itself (rather than a
// separate, longer one) is a deliberate choice: it is the
// simplest option that still bounds how long a store's
// best-effort accounting insert can stay silently
// unaccounted for to one interval, on a process that is
// already running this loop regardless.
c.runReconciliationPass(ctx)
case <-c.evictionPressure:
}
@@ -432,58 +512,31 @@ func (c *Cache) runEvictionPass(ctx context.Context) {
}
// runReconciliationPass runs one reconciliation pass, logging failures
// instead of propagating them (the loop must keep running), and returns
// the earliest time the next pass may start: reconciliationWaitFactor
// times as long after this pass ended as it took. It does nothing once
// ctx is cancelled.
func (c *Cache) runReconciliationPass(ctx context.Context) time.Time {
// instead of propagating them (the loop must keep running). It does
// nothing once ctx is cancelled.
func (c *Cache) runReconciliationPass(ctx context.Context) {
if ctx.Err() != nil {
return time.Now()
return
}
started := time.Now()
err := c.reconcileAccounting(ctx)
if err != nil {
c.log.Warn("cache accounting reconciliation failed", "error", err)
}
ended := time.Now()
return ended.Add(reconciliationWaitFactor * ended.Sub(started))
}
// runCleanExpired runs CleanExpired, logging a failure instead of
// propagating it (the loop must keep running). It does nothing once ctx
// is cancelled.
func (c *Cache) runCleanExpired(ctx context.Context) {
if ctx.Err() != nil {
return
}
err := c.CleanExpired(ctx)
if err != nil {
c.log.Warn("negative cache cleanup failed", "error", err)
}
}
// reconcileAccounting synchronizes the database size accounting with
// the actual contents of the cache directories. It runs at startup and
// then on the first periodic eviction tick that comes at least ten times
// as long after the last pass ended as that pass took, off the request
// again on every periodic eviction tick thereafter, off the request
// hot path: it adopts variant files that predate the accounting table
// (or whose accounting insert failed, e.g. StoreVariant's best-effort
// insert under transient DB contention), drops variant accounting rows
// whose files are missing, removes source blob files the database does
// not know, removes source and variant files that are empty or not the
// size their rows record, sweeps stale temp files left behind by crashed
// writes, and last checks the total cache usage against the tables. It
// reads the tables a page at a time.
// Running it periodically, not just once, bounds how long such drift can
// accumulate unaccounted for on a long-running process to about one
// eviction interval plus ten times the last pass's time.
// Once ctx is cancelled, it stops at the next file or row and returns
// ctx's error.
// insert under transient DB contention), drops accounting rows whose
// files are missing, removes source blob files the database does not
// know (and rows whose files are gone), and sweeps stale temp files
// left behind by crashed writes. Running it periodically, not just
// once, bounds how long such drift can accumulate unaccounted for on a
// long-running process to one eviction interval. Once ctx is cancelled,
// it stops at the next file or row and returns ctx's error.
func (c *Cache) reconcileAccounting(ctx context.Context) error {
if c.disabled {
return nil
@@ -504,19 +557,19 @@ func (c *Cache) reconcileAccounting(ctx context.Context) error {
return err
}
return c.reconcileUsageTotal(ctx)
err = c.reconcileSourceRows(ctx)
if err != nil {
return err
}
return nil
}
// reconcileFiles walks baseDir, one of the cache's storage directories,
// sweeping stale temp files and passing each other file, with its name, to
// reconcileFile. Once ctx is cancelled it stops at the next file and
// returns ctx's error.
func (c *Cache) reconcileFiles(
ctx context.Context, baseDir string,
reconcileFile func(path string, entry fs.DirEntry, name string) error,
) error {
// reconcileVariantFiles walks the variant storage directory, adopting
// files without accounting rows and sweeping stale temp files.
func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
return filepath.WalkDir(
baseDir,
c.variants.baseDir,
func(path string, entry fs.DirEntry, err error) error {
if ctx.Err() != nil {
return ctx.Err()
@@ -534,67 +587,46 @@ func (c *Cache) reconcileFiles(
return nil
}
return reconcileFile(path, entry, name)
if strings.HasSuffix(name, variantMetaSuffix) {
return nil
}
return c.adoptVariantFile(ctx, path, entry, VariantKey(name))
},
)
}
// reconcileVariantFiles walks the variant storage directory, checking
// each variant file against its accounting row (reconcileVariantFile)
// and sweeping stale temp files.
func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
return c.reconcileFiles(ctx, c.variants.baseDir,
func(path string, entry fs.DirEntry, name string) error {
return c.reconcileVariantFile(ctx, path, entry, imagerequest.VariantKey(name))
})
}
// reconcileVariantFile checks one variant file against its accounting
// row. A file without a row is adopted into the accounting, unless it is
// empty. A file that is empty, or not the size its row records, as a
// crash or a restored snapshot can leave it, is removed with its row and
// a warning naming it, so the variant is converted again.
func (c *Cache) reconcileVariantFile(
ctx context.Context, path string, entry fs.DirEntry, cacheKey imagerequest.VariantKey,
) error {
info, err := entry.Info()
if err != nil {
return fmt.Errorf("failed to stat variant file: %w", err)
}
var recordedSize int64
err = c.db.QueryRowContext(ctx,
`SELECT size_bytes FROM variant_content WHERE cache_key = ?`, string(cacheKey),
).Scan(&recordedSize)
switch {
case errors.Is(err, sql.ErrNoRows) && info.Size() > 0:
return c.adoptVariantFile(ctx, info, cacheKey)
case err != nil && !errors.Is(err, sql.ErrNoRows):
return fmt.Errorf("failed to check variant accounting row: %w", err)
case info.Size() > 0 && info.Size() == recordedSize:
return nil
}
// The file is empty, or not the size its row records
c.log.Warn("removing damaged cached variant file", "path", path,
"file_bytes", info.Size(), "recorded_bytes", recordedSize)
return c.evictVariant(ctx, cacheKey)
}
// adoptVariantFile inserts an accounting row for a variant file that
// has none, using the file's size and modification time.
func (c *Cache) adoptVariantFile(
ctx context.Context, info fs.FileInfo, cacheKey imagerequest.VariantKey,
ctx context.Context, path string, entry fs.DirEntry, cacheKey VariantKey,
) error {
modTime := info.ModTime().UTC().Format(sqliteTimestampLayout)
var rowExists int
_, err := c.db.ExecContext(ctx, `
INSERT INTO variant_content (cache_key, size_bytes, last_accessed_at)
VALUES (?, ?, ?)
`, string(cacheKey), info.Size(), modTime)
err := c.db.QueryRowContext(ctx,
`SELECT COUNT(*) FROM variant_content WHERE cache_key = ?`, string(cacheKey),
).Scan(&rowExists)
if err != nil {
return fmt.Errorf("failed to check variant accounting row: %w", err)
}
if rowExists > 0 {
return nil
}
info, err := entry.Info()
if err != nil {
return fmt.Errorf("failed to stat variant file: %w", err)
}
modTime := info.ModTime().UTC().Format(sqliteTimestampLayout)
contentType := c.variantContentTypeFromSidecar(path)
_, err = c.db.ExecContext(ctx, `
INSERT INTO variant_content
(cache_key, size_bytes, content_type, created_at, last_accessed_at)
VALUES (?, ?, ?, ?, ?)
`, string(cacheKey), info.Size(), contentType, modTime, modTime)
if err != nil {
return fmt.Errorf("failed to adopt variant file into accounting: %w", err)
}
@@ -605,66 +637,66 @@ func (c *Cache) adoptVariantFile(
return nil
}
// variantContentTypeFromSidecar reads the content type from a variant
// .meta sidecar, falling back to application/octet-stream.
func (c *Cache) variantContentTypeFromSidecar(variantPath string) string {
//nolint:gosec // path from cache walk
metaData, err := os.ReadFile(variantPath + variantMetaSuffix)
if err != nil {
return fallbackContentType
}
var meta VariantMeta
if json.Unmarshal(metaData, &meta) != nil || meta.ContentType == "" {
return fallbackContentType
}
return meta.ContentType
}
// reconcileVariantRows drops accounting rows whose variant files are
// missing, so the database never references deleted content.
func (c *Cache) reconcileVariantRows(ctx context.Context) error {
var after imagerequest.VariantKey
for {
keys, err := c.variantKeysAfter(ctx, after)
if err != nil {
return err
}
if c.reconciliationReadTestHook != nil {
c.reconciliationReadTestHook(len(keys))
}
if len(keys) == 0 {
return nil
}
for _, key := range keys {
if ctx.Err() != nil {
return ctx.Err()
}
if c.variants.Exists(key) {
continue
}
_, err := c.db.ExecContext(ctx,
`DELETE FROM variant_content WHERE cache_key = ?`, string(key))
if err != nil {
return fmt.Errorf("failed to drop stale variant accounting row: %w", err)
}
c.log.Info("dropped accounting row for missing variant file", "cache_key", key)
}
after = keys[len(keys)-1]
keys, err := c.allVariantKeys(ctx)
if err != nil {
return err
}
for _, key := range keys {
if ctx.Err() != nil {
return ctx.Err()
}
if c.variants.Exists(key) {
continue
}
_, err := c.db.ExecContext(ctx,
`DELETE FROM variant_content WHERE cache_key = ?`, string(key))
if err != nil {
return fmt.Errorf("failed to drop stale variant accounting row: %w", err)
}
c.log.Info("dropped accounting row for missing variant file", "cache_key", key)
}
return nil
}
// variantKeysAfter returns, in order, up to c.reconciliationPageSize
// tracked variant cache keys that sort after the given one.
func (c *Cache) variantKeysAfter(
ctx context.Context, after imagerequest.VariantKey,
) ([]imagerequest.VariantKey, error) {
return queryStringColumn[imagerequest.VariantKey](ctx, c.db, `
SELECT cache_key FROM variant_content
WHERE cache_key > ? ORDER BY cache_key LIMIT ?
`, "variant keys", "variant key", string(after), c.reconciliationPageSize)
// allVariantKeys returns every tracked variant cache key.
func (c *Cache) allVariantKeys(ctx context.Context) ([]VariantKey, error) {
return queryStringColumn[VariantKey](ctx, c.db,
`SELECT cache_key FROM variant_content`, "variant keys", "variant key")
}
// queryStringColumn runs a single-column query with args and returns the
// column values as T. plural names the set for the query and scan
// failure messages; singular names one row for the scan and iteration
// failure messages.
// queryStringColumn runs a single-column query and returns the column
// values as T. plural names the set for the query and scan failure
// messages; singular names one row for the scan and iteration failure
// messages.
func queryStringColumn[T ~string](
ctx context.Context, db *sql.DB, query, plural, singular string, args ...any,
ctx context.Context, db *sql.DB, query, plural, singular string,
) ([]T, error) {
rows, err := db.QueryContext(ctx, query, args...)
rows, err := db.QueryContext(ctx, query)
if err != nil {
return nil, fmt.Errorf("failed to query %s: %w", plural, err)
}
@@ -692,193 +724,105 @@ func queryStringColumn[T ~string](
return values, nil
}
// reconcileSourceFiles walks the source content directory, checking
// each blob file against its source_content row (reconcileSourceFile)
// and sweeping stale temp files.
// reconcileSourceFiles walks the source content directory, removing
// blob files the database does not track (they are unreachable: source
// lookups always go through source_metadata) and sweeping stale temp
// files.
func (c *Cache) reconcileSourceFiles(ctx context.Context) error {
return c.reconcileFiles(ctx, c.srcContent.baseDir,
func(path string, entry fs.DirEntry, name string) error {
return c.reconcileSourceFile(ctx, path, entry, imagerequest.SourceKey(name))
})
}
return filepath.WalkDir(
c.srcContent.baseDir,
func(path string, entry fs.DirEntry, err error) error {
if ctx.Err() != nil {
return ctx.Err()
}
// reconcileSourceFile checks one source blob file against its
// source_content row. A file without a row is removed, as no lookup
// serves it and no eviction removes it. A file that is empty, or not the
// size its row records, as a crash or a restored snapshot can leave it,
// is removed with its row and a warning naming it, so the source is
// fetched again.
func (c *Cache) reconcileSourceFile(
ctx context.Context, path string, entry fs.DirEntry, key imagerequest.SourceKey,
) error {
info, err := entry.Info()
if err != nil {
return fmt.Errorf("failed to stat source content file: %w", err)
}
if err != nil || entry.IsDir() {
return err
}
var recordedSize int64
name := entry.Name()
err = c.db.QueryRowContext(ctx,
`SELECT size_bytes FROM source_content WHERE source_key = ?`,
string(key),
).Scan(&recordedSize)
if strings.HasPrefix(name, tempFilePrefix) {
c.sweepStaleTempFile(path, entry)
switch {
case errors.Is(err, sql.ErrNoRows):
return c.removeUntrackedSourceFile(path, key)
case err != nil:
return fmt.Errorf("failed to check source content row: %w", err)
case info.Size() > 0 && info.Size() == recordedSize:
return nil
}
return nil
}
// The file is empty, or not the size its row records
c.log.Warn("removing damaged cached source file", "path", path,
"file_bytes", info.Size(), "recorded_bytes", recordedSize)
return c.evictSourceBlob(ctx, key)
return c.removeUntrackedSourceFile(ctx, path, ContentHash(name))
},
)
}
// removeUntrackedSourceFile deletes a source blob file that has no
// source_content row.
// source_content row. Any source_metadata rows referencing the hash
// are removed first so no row ever points at a deleted file.
func (c *Cache) removeUntrackedSourceFile(
path string, key imagerequest.SourceKey,
ctx context.Context, path string, contentHash ContentHash,
) error {
err := os.Remove(path)
var rowExists int
err := c.db.QueryRowContext(ctx,
`SELECT COUNT(*) FROM source_content WHERE content_hash = ?`, string(contentHash),
).Scan(&rowExists)
if err != nil {
return fmt.Errorf("failed to check source content row: %w", err)
}
if rowExists > 0 {
return nil
}
_, err = c.db.ExecContext(ctx,
`DELETE FROM source_metadata WHERE content_hash = ?`, string(contentHash))
if err != nil {
return fmt.Errorf("failed to delete metadata rows for untracked blob: %w", err)
}
err = os.Remove(path)
if err != nil && !os.IsNotExist(err) {
return fmt.Errorf("failed to remove untracked source file: %w", err)
}
c.log.Info("removed untracked source content file", "source_key", key)
c.log.Info("removed untracked source content file", "content_hash", contentHash)
return nil
}
// Each of these queries sums size_bytes over the next page of rows of
// one content table, the rows that sort after a key, and returns the
// page's last key, the sum and the number of rows in the page. Past the
// last row the page has no rows and the key is NULL.
const (
sourceSizePageQuery = `
SELECT MAX(source_key), COALESCE(SUM(size_bytes), 0), COUNT(*)
FROM (
SELECT source_key, size_bytes FROM source_content
WHERE source_key > ? ORDER BY source_key LIMIT ?
)`
variantSizePageQuery = `
SELECT MAX(cache_key), COALESCE(SUM(size_bytes), 0), COUNT(*)
FROM (
SELECT cache_key, size_bytes FROM variant_content
WHERE cache_key > ? ORDER BY cache_key LIMIT ?
)`
)
// sumContentSizeBytes sums size_bytes over both content tables, a page
// of rows per query.
func (c *Cache) sumContentSizeBytes(ctx context.Context) (int64, error) {
sourceBytes, err := c.sumSizeBytesInPages(ctx, sourceSizePageQuery)
// reconcileSourceRows removes source_content rows (and their metadata
// references and sidecars) whose blob files are missing on disk.
func (c *Cache) reconcileSourceRows(ctx context.Context) error {
hashes, err := c.allSourceContentHashes(ctx)
if err != nil {
return 0, err
return err
}
variantBytes, err := c.sumSizeBytesInPages(ctx, variantSizePageQuery)
if err != nil {
return 0, err
}
for _, hash := range hashes {
if ctx.Err() != nil {
return ctx.Err()
}
return sourceBytes + variantBytes, nil
}
if c.srcContent.Exists(hash) {
continue
}
// sumSizeBytesInPages runs pageQuery, one of the size page queries
// above, from the first page to the last and adds up the page sums.
func (c *Cache) sumSizeBytesInPages(
ctx context.Context, pageQuery string,
) (int64, error) {
var total int64
after := ""
for {
var lastKey sql.NullString
var pageBytes int64
var pageRows int
err := c.db.QueryRowContext(ctx, pageQuery, after, c.reconciliationPageSize).
Scan(&lastKey, &pageBytes, &pageRows)
// The blob file is already gone; evictSourceBlob removes the
// rows and sidecars and tolerates the missing file.
err := c.evictSourceBlob(ctx, hash)
if err != nil {
return 0, fmt.Errorf("failed to sum cache content sizes: %w", err)
return err
}
if c.reconciliationReadTestHook != nil {
c.reconciliationReadTestHook(pageRows)
}
if pageRows == 0 {
return total, nil
}
total += pageBytes
after = lastKey.String
c.log.Info("dropped rows for missing source content file", "content_hash", hash)
}
}
// reconcileUsageTotal checks the total cache usage the database keeps
// against size_bytes summed over both content tables, and corrects the
// total when they differ.
func (c *Cache) reconcileUsageTotal(ctx context.Context) error {
var totalBytes, changeCount int64
err := c.db.QueryRowContext(ctx,
`SELECT total_size_bytes, change_count FROM cache_usage WHERE id = 1`,
).Scan(&totalBytes, &changeCount)
if err != nil {
return fmt.Errorf("failed to read cache usage: %w", err)
}
sumBytes, err := c.sumContentSizeBytes(ctx)
if err != nil {
return err
}
if sumBytes == totalBytes {
return nil
}
corrected, err := c.correctUsageTotal(ctx, sumBytes, changeCount)
if err != nil || !corrected {
return err
}
c.log.Warn("corrected total cache usage to the sum of the content tables",
"previous_usage_bytes", totalBytes, "usage_bytes", sumBytes)
return nil
}
// correctUsageTotal sets the total cache usage to sumBytes, a sum of the
// content tables taken when the change count was changeCount, and
// reports whether it did. If a row was added, removed or resized since,
// the count has moved and the total is left alone: the sum may have
// missed that change, and the next pass checks again.
func (c *Cache) correctUsageTotal(
ctx context.Context, sumBytes, changeCount int64,
) (bool, error) {
result, err := c.db.ExecContext(ctx, `
UPDATE cache_usage SET total_size_bytes = ?
WHERE id = 1 AND change_count = ?
`, sumBytes, changeCount)
if err != nil {
return false, fmt.Errorf("failed to correct cache usage: %w", err)
}
affected, err := result.RowsAffected()
if err != nil {
return false, fmt.Errorf("failed to read cache usage correction: %w", err)
}
return affected > 0, nil
// allSourceContentHashes returns every tracked source content hash.
func (c *Cache) allSourceContentHashes(ctx context.Context) ([]ContentHash, error) {
return queryStringColumn[ContentHash](ctx, c.db,
`SELECT content_hash FROM source_content`,
"source content hashes", "content hash")
}
// sweepStaleTempFile removes a temp file left behind by a crashed
internal/imgcache/eviction_internal_test.go
+373 -284
View File
@@ -10,13 +10,12 @@ import (
"os"
"path/filepath"
"strings"
"sync"
"testing"
"time"
"modernc.org/sqlite"
_ "modernc.org/sqlite"
"sneak.berlin/go/pixa/internal/database"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/httpfetcher"
)
// sqliteTimestampFormat matches the format SQLite's CURRENT_TIMESTAMP
@@ -28,10 +27,10 @@ const sqliteTimestampFormat = "2006-01-02 15:04:05"
// keys reused across the eviction tests, in the order the tests store
// them.
const (
testVariantKeyOne imagerequest.VariantKey = "aabbccdd0001"
testVariantKeyTwo imagerequest.VariantKey = "aabbccdd0002"
testVariantKeyThree imagerequest.VariantKey = "aabbccdd0003"
testVariantKeyFour imagerequest.VariantKey = "aabbccdd0004"
testVariantKeyOne VariantKey = "aabbccdd0001"
testVariantKeyTwo VariantKey = "aabbccdd0002"
testVariantKeyThree VariantKey = "aabbccdd0003"
testVariantKeyFour VariantKey = "aabbccdd0004"
)
// evictionTestDB creates an in-memory SQLite database with the real
@@ -71,6 +70,7 @@ func newEvictionTestCache(t *testing.T, maxBytes int64) (*Cache, string) {
// backwards compatibility with existing fixtures.
cache, err := NewCache(db, CacheConfig{
StateDir: tmpDir,
CacheTTL: time.Hour,
NegativeTTL: 5 * time.Minute,
MaxBytes: maxBytes,
DisableDiskCache: maxBytes == 0,
@@ -83,42 +83,47 @@ func newEvictionTestCache(t *testing.T, maxBytes int64) (*Cache, string) {
}
// storeEvictionTestSource stores content as a fetched source for
// host/path and returns the resulting source key.
// host/path and returns the resulting content hash.
func storeEvictionTestSource(
t *testing.T, cache *Cache, host, path string, content []byte,
) imagerequest.SourceKey {
) ContentHash {
t.Helper()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: host,
Path: path,
},
Transform: imagerequest.Transform{
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
req := &ImageRequest{
SourceHost: host,
SourcePath: path,
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
result := &httpfetcher.FetchResult{
StatusCode: 200,
ContentType: testContentTypeJPEG,
ContentLength: int64(len(content)),
Headers: map[string][]string{
testHeaderContentType: {testContentTypeJPEG},
},
}
key, err := cache.StoreSource(
context.Background(), req, bytes.NewReader(content),
hash, err := cache.StoreSource(
context.Background(), req, bytes.NewReader(content), result,
)
if err != nil {
t.Fatalf("StoreSource(%s%s) failed: %v", host, path, err)
}
return key
return hash
}
// storeEvictionTestVariant stores content as a processed variant under
// the given cache key.
func storeEvictionTestVariant(
t *testing.T, cache *Cache, key imagerequest.VariantKey, content []byte,
t *testing.T, cache *Cache, key VariantKey, content []byte,
) {
t.Helper()
err := cache.StoreVariant(t.Context(), key, bytes.NewReader(content))
err := cache.StoreVariant(t.Context(), key, bytes.NewReader(content), "image/webp")
if err != nil {
t.Fatalf("StoreVariant(%s) failed: %v", key, err)
}
@@ -127,7 +132,7 @@ func storeEvictionTestVariant(
// setVariantLastAccessed backdates the last access time of a tracked
// variant, to make LRU ordering deterministic in tests.
func setVariantLastAccessed(
t *testing.T, cache *Cache, key imagerequest.VariantKey, when time.Time,
t *testing.T, cache *Cache, key VariantKey, when time.Time,
) {
t.Helper()
@@ -153,13 +158,13 @@ func setVariantLastAccessed(
// setSourceLastAccessed backdates the last access time of a tracked
// source content blob.
func setSourceLastAccessed(
t *testing.T, cache *Cache, key imagerequest.SourceKey, when time.Time,
t *testing.T, cache *Cache, hash ContentHash, when time.Time,
) {
t.Helper()
res, err := cache.db.ExecContext(t.Context(),
`UPDATE source_content SET last_accessed_at = ? WHERE source_key = ?`,
when.UTC().Format(sqliteTimestampFormat), string(key),
`UPDATE source_content SET last_accessed_at = ? WHERE content_hash = ?`,
when.UTC().Format(sqliteTimestampFormat), string(hash),
)
if err != nil {
t.Fatalf("failed to set source last_accessed_at: %v", err)
@@ -171,7 +176,7 @@ func setSourceLastAccessed(
}
if affected != 1 {
t.Fatalf("source %s has no accounting row (affected=%d)", key, affected)
t.Fatalf("source %s has no accounting row (affected=%d)", hash, affected)
}
}
@@ -196,31 +201,32 @@ func assertNoDanglingReferences(t *testing.T, cache *Cache) {
t.Helper()
rows, err := cache.db.QueryContext(t.Context(),
`SELECT source_key FROM source_content`,
`SELECT content_hash FROM source_metadata
WHERE content_hash IS NOT NULL AND content_hash != ''`,
)
if err != nil {
t.Fatalf("failed to query source_content: %v", err)
t.Fatalf("failed to query source_metadata: %v", err)
}
defer func() { _ = rows.Close() }()
for rows.Next() {
var key string
var hash string
err := rows.Scan(&key)
err := rows.Scan(&hash)
if err != nil {
t.Fatalf("failed to scan source_key: %v", err)
t.Fatalf("failed to scan content_hash: %v", err)
}
if !cache.srcContent.Exists(imagerequest.SourceKey(key)) {
t.Errorf("source_content references content %s but the file is missing",
key)
if !cache.srcContent.Exists(ContentHash(hash)) {
t.Errorf("source_metadata references content %s but the file is missing",
hash)
}
}
err = rows.Err()
if err != nil {
t.Fatalf("source_content iteration failed: %v", err)
t.Fatalf("source_metadata iteration failed: %v", err)
}
variantRows, err := cache.db.QueryContext(t.Context(),
@@ -239,7 +245,7 @@ func assertNoDanglingReferences(t *testing.T, cache *Cache) {
t.Fatalf("failed to scan cache_key: %v", err)
}
if !cache.variants.Exists(imagerequest.VariantKey(key)) {
if !cache.variants.Exists(VariantKey(key)) {
t.Errorf("variant_content references key %s but the file is missing", key)
}
}
@@ -303,6 +309,33 @@ func TestUsageBytesAccountsSourceAndVariantBytes(t *testing.T) {
}
}
func TestUsageBytesCountsMultiReferencedBlobOnce(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
content := bytes.Repeat([]byte{0xCC}, 1200)
hashOne := storeEvictionTestSource(t, cache,
"src.example.com", "/one.jpg", content)
hashTwo := storeEvictionTestSource(t, cache,
"src.example.com", "/two.jpg", content)
if hashOne != hashTwo {
t.Fatalf("identical content produced different hashes: %s vs %s",
hashOne, hashTwo)
}
usage, err := cache.UsageBytes(context.Background())
if err != nil {
t.Fatalf("UsageBytes failed: %v", err)
}
if usage != 1200 {
t.Errorf("UsageBytes = %d, want 1200 (deduplicated blob counted once)", usage)
}
}
func TestEvictToLimitEvictsLeastRecentlyUsedFirst(t *testing.T) {
t.Parallel()
@@ -311,7 +344,7 @@ func TestEvictToLimitEvictsLeastRecentlyUsedFirst(t *testing.T) {
cache, _ := newEvictionTestCache(t, limit)
now := time.Now()
keys := []imagerequest.VariantKey{
keys := []VariantKey{
testVariantKeyOne, testVariantKeyTwo,
testVariantKeyThree, testVariantKeyFour,
}
@@ -356,15 +389,102 @@ func TestEvictToLimitEvictsLeastRecentlyUsedFirst(t *testing.T) {
assertNoDanglingReferences(t, cache)
}
func TestEvictionRemovesMultiReferencedBlobTogetherWithAllReferences(t *testing.T) {
t.Parallel()
const limit = 1000
cache, _ := newEvictionTestCache(t, limit)
now := time.Now()
// One 800-byte blob referenced by two source paths.
sharedContent := bytes.Repeat([]byte{0xDD}, 800)
sharedHash := storeEvictionTestSource(t, cache,
"src.example.com", "/a.jpg", sharedContent)
h := storeEvictionTestSource(t, cache,
"src.example.com", "/b.jpg", sharedContent)
if h != sharedHash {
t.Fatalf("identical content produced different hashes: %s vs %s",
h, sharedHash)
}
// A newer 600-byte blob referenced by one source path.
recentHash := storeEvictionTestSource(t, cache, "src.example.com", "/c.jpg",
bytes.Repeat([]byte{0xEE}, 600))
setSourceLastAccessed(t, cache, sharedHash, now.Add(-2*time.Hour))
setSourceLastAccessed(t, cache, recentHash, now.Add(-time.Minute))
err := cache.EvictToLimit(context.Background())
if err != nil {
t.Fatalf("EvictToLimit failed: %v", err)
}
usage, err := cache.UsageBytes(context.Background())
if err != nil {
t.Fatalf("UsageBytes failed: %v", err)
}
if usage > limit {
t.Errorf("usage after eviction = %d, want <= %d", usage, limit)
}
// The multi-referenced blob must be gone from disk, from
// source_content, and from BOTH source_metadata rows: references
// are removed together with the blob, never left dangling.
if cache.srcContent.Exists(sharedHash) {
t.Errorf("evicted blob %s still exists on disk", sharedHash)
}
if n := countRows(t, cache,
`SELECT COUNT(*) FROM source_content WHERE content_hash = ?`, string(sharedHash),
); n != 0 {
t.Errorf("evicted blob %s still has %d source_content rows", sharedHash, n)
}
if n := countRows(t, cache,
`SELECT COUNT(*) FROM source_metadata WHERE content_hash = ?`, string(sharedHash),
); n != 0 {
t.Errorf("evicted blob %s still has %d source_metadata references", sharedHash, n)
}
// The JSON metadata sidecars for both referencing paths must be
// removed along with the rows.
for _, path := range []string{"/a.jpg", "/b.jpg"} {
pathHash := HashPath(path + "?")
if cache.srcMetadata.Exists("src.example.com", pathHash) {
t.Errorf("metadata sidecar for %s must be removed with its row", path)
}
}
// The more recently used blob survives fully intact.
if !cache.srcContent.Exists(recentHash) {
t.Errorf("recently used blob %s must survive eviction", recentHash)
}
if n := countRows(t, cache,
`SELECT COUNT(*) FROM source_metadata WHERE content_hash = ?`, string(recentHash),
); n != 1 {
t.Errorf("recently used blob %s has %d source_metadata rows, want 1",
recentHash, n)
}
assertNoDanglingReferences(t, cache)
}
func TestEvictionKeepsEverythingWhenUnderLimit(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
content := bytes.Repeat([]byte{0xDF}, 800)
keys := []imagerequest.SourceKey{
storeEvictionTestSource(t, cache, "src.example.com", "/a.jpg", content),
storeEvictionTestSource(t, cache, "src.example.com", "/b.jpg", content),
hash := storeEvictionTestSource(t, cache, "src.example.com", "/a.jpg", content)
h := storeEvictionTestSource(t, cache, "src.example.com", "/b.jpg", content)
if h != hash {
t.Fatalf("identical content produced different hashes: %s vs %s", h, hash)
}
storeEvictionTestVariant(t, cache, testVariantKeyOne,
@@ -375,16 +495,14 @@ func TestEvictionKeepsEverythingWhenUnderLimit(t *testing.T) {
t.Fatalf("EvictToLimit failed: %v", err)
}
for _, key := range keys {
if !cache.srcContent.Exists(key) {
t.Errorf("source %s must not be evicted while usage is under the limit", key)
}
if !cache.srcContent.Exists(hash) {
t.Errorf("blob %s must not be evicted while usage is under the limit", hash)
}
if n := countRows(t, cache,
`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(key),
); n != 1 {
t.Errorf("source %s has %d source_content rows, want 1", key, n)
}
if n := countRows(t, cache,
`SELECT COUNT(*) FROM source_metadata WHERE content_hash = ?`, string(hash),
); n != 2 {
t.Errorf("blob %s has %d source_metadata rows, want 2", hash, n)
}
if !cache.variants.Exists(testVariantKeyOne) {
@@ -399,16 +517,12 @@ func TestZeroMaxBytesDisablesDiskCache(t *testing.T) {
cache, tmpDir := newEvictionTestCache(t, 0)
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: "src.example.com",
Path: "/a.jpg",
},
Transform: imagerequest.Transform{
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: "src.example.com",
SourcePath: "/a.jpg",
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
assertDisabledCacheWritesAreNoOps(t, cache, req)
@@ -420,45 +534,62 @@ func TestZeroMaxBytesDisablesDiskCache(t *testing.T) {
// assertDisabledCacheWritesAreNoOps verifies that stores against a
// disabled cache report success without recording anything.
func assertDisabledCacheWritesAreNoOps(
t *testing.T, cache *Cache, req *imagerequest.Request,
t *testing.T, cache *Cache, req *ImageRequest,
) {
t.Helper()
ctx := t.Context()
err := cache.StoreVariant(
ctx, imagerequest.CacheKey(req), bytes.NewReader([]byte("data")),
ctx, CacheKey(req), bytes.NewReader([]byte("data")), "image/webp",
)
if err != nil {
t.Fatalf("StoreVariant on disabled cache must be a no-op, got error: %v", err)
}
key, err := cache.StoreSource(ctx, req, bytes.NewReader([]byte("data")))
result := &httpfetcher.FetchResult{
StatusCode: 200,
ContentType: testContentTypeJPEG,
ContentLength: 4,
Headers: map[string][]string{},
}
hash, err := cache.StoreSource(ctx, req, bytes.NewReader([]byte("data")), result)
if err != nil {
t.Fatalf("StoreSource on disabled cache must be a no-op, got error: %v", err)
}
if key != "" {
t.Errorf("StoreSource on disabled cache returned key %q, want empty", key)
if hash != "" {
t.Errorf("StoreSource on disabled cache returned hash %q, want empty", hash)
}
}
// assertDisabledCacheReadsAlwaysMiss verifies that lookups against a
// disabled cache never report a hit.
func assertDisabledCacheReadsAlwaysMiss(
t *testing.T, cache *Cache, req *imagerequest.Request,
t *testing.T, cache *Cache, req *ImageRequest,
) {
t.Helper()
ctx := t.Context()
key, err := cache.LookupSource(ctx, req)
lookup, err := cache.Lookup(ctx, req)
if err != nil {
t.Fatalf("Lookup on disabled cache failed: %v", err)
}
if lookup.Hit {
t.Error("Lookup on disabled cache must always miss")
}
srcHash, srcType, err := cache.LookupSource(ctx, req)
if err != nil {
t.Fatalf("LookupSource on disabled cache failed: %v", err)
}
if key != "" {
t.Errorf("LookupSource on disabled cache = %q, want empty", key)
if srcHash != "" || srcType != "" {
t.Errorf("LookupSource on disabled cache = (%q, %q), want empty",
srcHash, srcType)
}
}
@@ -479,6 +610,10 @@ func assertDisabledCacheTracksNothing(t *testing.T, cache *Cache) {
if n := countRows(t, cache, `SELECT COUNT(*) FROM source_content`); n != 0 {
t.Errorf("disabled cache wrote %d source_content rows, want 0", n)
}
if n := countRows(t, cache, `SELECT COUNT(*) FROM source_metadata`); n != 0 {
t.Errorf("disabled cache wrote %d source_metadata rows, want 0", n)
}
}
// assertDisabledCacheWroteNothingToDisk verifies that a disabled cache
@@ -527,7 +662,7 @@ func TestEvictionRunsUnderWritePressure(t *testing.T) {
cache.StartEviction(time.Hour)
defer func() { _ = cache.StopEviction(t.Context()) }()
keys := []imagerequest.VariantKey{
keys := []VariantKey{
testVariantKeyOne, testVariantKeyTwo, testVariantKeyThree,
}
fills := []byte{0x11, 0x12, 0x13}
@@ -581,7 +716,7 @@ func TestEvictionRunsOnPeriodicSchedule(t *testing.T) {
time.Sleep(10 * time.Millisecond)
}
keys := []imagerequest.VariantKey{
keys := []VariantKey{
testVariantKeyOne, testVariantKeyTwo, testVariantKeyThree,
}
fills := []byte{0x21, 0x22, 0x23}
@@ -589,7 +724,7 @@ func TestEvictionRunsOnPeriodicSchedule(t *testing.T) {
for i, key := range keys {
content := bytes.Repeat([]byte{fills[i]}, 1000)
_, err = cache.variants.Store(key, bytes.NewReader(content))
_, err = cache.variants.Store(key, bytes.NewReader(content), "image/webp")
if err != nil {
t.Fatalf("failed to store variant file: %v", err)
}
@@ -641,7 +776,7 @@ func TestStartEvictionReconcilesAccountingWithDisk(t *testing.T) {
untracked := bytes.Repeat([]byte{0x31}, 1000)
_, err := cache.variants.Store(
testVariantKeyOne, bytes.NewReader(untracked),
testVariantKeyOne, bytes.NewReader(untracked), "image/webp",
)
if err != nil {
t.Fatalf("failed to store untracked variant file: %v", err)
@@ -649,8 +784,9 @@ func TestStartEvictionReconcilesAccountingWithDisk(t *testing.T) {
// An accounting row whose file is missing must be dropped.
_, err = cache.db.ExecContext(t.Context(),
`INSERT INTO variant_content (cache_key, size_bytes) VALUES (?, ?)`,
"deadbeef0001", 700,
`INSERT INTO variant_content (cache_key, size_bytes, content_type)
VALUES (?, ?, ?)`,
"deadbeef0001", 700, "image/webp",
)
if err != nil {
t.Fatalf("failed to insert stale variant accounting row: %v", err)
@@ -742,7 +878,7 @@ func TestPeriodicReconciliationAdoptsFileThatAppearsAfterStartup(t *testing.T) {
untracked := bytes.Repeat([]byte{0x41}, 900)
_, err = cache.variants.Store(
"aabbccdd0099", bytes.NewReader(untracked),
"aabbccdd0099", bytes.NewReader(untracked), "image/webp",
)
if err != nil {
t.Fatalf("failed to store untracked variant file: %v", err)
@@ -783,89 +919,6 @@ func TestPeriodicReconciliationAdoptsFileThatAppearsAfterStartup(t *testing.T) {
}
}
// TestReconciliationPassesAreSpacedByTenTimesTheirTime makes the hook
// called after every read of the reconciliation pass sleep 10 ms, runs
// the eviction loop on a 10 ms interval, and records when each of those
// calls starts and ends. A pass starts before its first call and ends
// after its last, so the time from the first call's start to the last
// call's end is at most the pass's time. The next pass's first call must
// start at least ten times that long after the last call ended.
func TestReconciliationPassesAreSpacedByTenTimesTheirTime(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
// A pass made here, before the loop starts, counts the reads one
// pass makes on this empty cache, so the reads recorded below can be
// split into passes.
readsPerPass := 0
cache.reconciliationReadTestHook = func(int) { readsPerPass++ }
err := cache.reconcileAccounting(t.Context())
if err != nil {
t.Fatalf("reconcileAccounting failed: %v", err)
}
t.Logf("one reconciliation pass makes %d reads", readsPerPass)
if readsPerPass == 0 {
t.Fatal("a reconciliation pass made no read")
}
// The pass at startup and two after it.
const passes = 3
type read struct{ start, end time.Time }
// The channel holds every read the test looks at, so none of those
// is dropped; reads after them are, and never block the loop.
reads := make(chan read, passes*readsPerPass)
cache.reconciliationReadTestHook = func(int) {
start := time.Now()
time.Sleep(10 * time.Millisecond)
select {
case reads <- read{start: start, end: time.Now()}:
default:
}
}
cache.StartEviction(10 * time.Millisecond)
defer func() { _ = cache.StopEviction(t.Context()) }()
recorded := make([]read, 0, passes*readsPerPass)
timeout := time.After(15 * time.Second)
for len(recorded) < passes*readsPerPass {
select {
case r := <-reads:
recorded = append(recorded, r)
case <-timeout:
t.Fatalf("saw %d reconciliation reads in 15 s, want %d (%d passes)",
len(recorded), passes*readsPerPass, passes)
}
}
for pass := range passes - 1 {
first := recorded[pass*readsPerPass]
last := recorded[(pass+1)*readsPerPass-1]
next := recorded[(pass+1)*readsPerPass]
passTime := last.end.Sub(first.start)
wait := next.start.Sub(last.end)
t.Logf("pass %d took at least %v, and the next pass started %v after it",
pass+1, passTime, wait)
if wait < 10*passTime {
t.Errorf("pass %d took at least %v, and the next pass started %v "+
"after it, want at least %v", pass+1, passTime, wait, 10*passTime)
}
}
}
// TestStopEvictionInterruptsPassInProgress holds the test database's
// only connection, so the startup reconciliation pass waits for it, and
// checks that StopEviction stops that pass instead of waiting for the
@@ -920,15 +973,9 @@ func TestStopEvictionInterruptsPassInProgress(t *testing.T) {
}
// TestEvictToLimitStopsAtNextCandidateOnceCancelled cancels the context
// once the oldest of three sources is evicted, while the next one waits
// for the database, and checks that EvictToLimit then returns
// context.Canceled, with that source gone and the other two kept, and
// logs no warning. The test database has one connection. When the
// deletion of the oldest source's row commits, a commit hook holds the
// deletion until the test waits for the connection, so the test takes it
// as soon as the deletion is done. The eviction of the next source then
// waits for the connection, and the test cancels the context while it
// waits.
// while the oldest of three source blobs is being evicted, and checks that
// EvictToLimit then returns context.Canceled without evicting the other
// two or logging a warning for either of them.
func TestEvictToLimitStopsAtNextCandidateOnceCancelled(t *testing.T) {
t.Parallel()
@@ -938,7 +985,7 @@ func TestEvictToLimitStopsAtNextCandidateOnceCancelled(t *testing.T) {
cache.log = slog.New(slog.NewJSONHandler(&logBuf, nil))
keys := []imagerequest.SourceKey{
hashes := []ContentHash{
storeEvictionTestSource(t, cache, "cancel.example.com", "/a.jpg",
bytes.Repeat([]byte{0x61}, 1000)),
storeEvictionTestSource(t, cache, "cancel.example.com", "/b.jpg",
@@ -949,155 +996,69 @@ func TestEvictToLimitStopsAtNextCandidateOnceCancelled(t *testing.T) {
base := time.Now().Add(-time.Hour)
for i, key := range keys {
setSourceLastAccessed(t, cache, key, base.Add(time.Duration(i)*time.Minute))
for i, hash := range hashes {
setSourceLastAccessed(t, cache, hash, base.Add(time.Duration(i)*time.Minute))
}
waitsBefore := cache.db.Stats().WaitCount
oldestRowDeleted := make(chan struct{})
var oldestRowDeletedOnce sync.Once
setCommitHook(t, cache, func() int32 {
oldestRowDeletedOnce.Do(func() {
close(oldestRowDeleted)
deadline := time.Now().Add(5 * time.Second)
for cache.db.Stats().WaitCount == waitsBefore && time.Now().Before(deadline) {
time.Sleep(time.Millisecond)
}
})
return 0
})
ctx, cancel := context.WithCancel(t.Context())
defer cancel()
evicted := make(chan error, 1)
cache.evictSourceBlobTestHook = func(ContentHash) { cancel() }
go func() { evicted <- cache.EvictToLimit(ctx) }()
select {
case <-oldestRowDeleted:
case err := <-evicted:
t.Fatalf("EvictToLimit() returned %v without deleting a row", err)
case <-time.After(5 * time.Second):
t.Fatal("EvictToLimit never deleted a row")
}
releaseDatabase := holdDatabase(t, cache)
defer releaseDatabase()
waitForConnectionWaits(t, cache.db, waitsBefore+2)
cancel()
err := <-evicted
err := cache.EvictToLimit(ctx)
t.Logf("EvictToLimit() error = %v", err)
t.Logf("log output: %s", logBuf.String())
// The checks below read the database, so the connection goes back.
releaseDatabase()
setCommitHook(t, cache, nil)
if !errors.Is(err, context.Canceled) {
t.Errorf("EvictToLimit() error = %v, want context.Canceled", err)
}
assertOnlyOldestSourceEvicted(t, cache, keys)
if cache.srcContent.Exists(hashes[0]) {
t.Errorf("source blob %s, evicted when the context was cancelled, "+
"is still on disk", hashes[0])
}
for _, hash := range hashes[1:] {
if !cache.srcContent.Exists(hash) {
t.Errorf("source blob %s was evicted after the context was cancelled", hash)
}
}
if strings.Contains(logBuf.String(), `"level":"WARN"`) {
t.Errorf("EvictToLimit logged a warning after the context was cancelled")
}
}
// setCommitHook makes the SQLite driver call hook each time a write on
// the test database's one connection commits, or stops it when hook is
// nil.
func setCommitHook(t *testing.T, cache *Cache, hook sqlite.CommitHookFn) {
t.Helper()
conn, err := cache.db.Conn(t.Context())
if err != nil {
t.Fatalf("failed to take the database connection: %v", err)
}
defer func() { _ = conn.Close() }()
err = conn.Raw(func(driverConn any) error {
hooks, ok := driverConn.(sqlite.HookRegisterer)
if !ok {
t.Fatalf("the database connection is a %T, which takes no hooks",
driverConn)
}
hooks.RegisterCommitHook(hook)
return nil
})
if err != nil {
t.Fatalf("failed to set the commit hook: %v", err)
}
}
// assertOnlyOldestSourceEvicted checks that the first of keys has neither
// its file nor its row, and that every other one has both.
func assertOnlyOldestSourceEvicted(
t *testing.T, cache *Cache, keys []imagerequest.SourceKey,
) {
t.Helper()
if cache.srcContent.Exists(keys[0]) {
t.Errorf("source %s, evicted when the context was cancelled, "+
"is still on disk", keys[0])
}
for _, key := range keys[1:] {
if !cache.srcContent.Exists(key) {
t.Errorf("source %s was evicted after the context was cancelled", key)
}
if n := countRows(t, cache,
`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(key),
); n != 1 {
t.Errorf("source %s, kept, has %d source_content rows, want 1", key, n)
}
}
assertNoDanglingReferences(t, cache)
}
// TestStopEvictionReturnsWhenItsContextEnds pauses the startup
// reconciliation pass in the hook called after each of its reads, where
// cancellation cannot reach it, and checks that StopEviction returns an
// error wrapping its context's error when that context ends, instead of
// waiting for the pass. Once the pass goes on, the goroutine exits, and a
// second StopEviction returns nil.
// TestStopEvictionReturnsWhenItsContextEnds pauses an eviction pass where
// cancellation cannot reach it, after a source blob's rows are deleted and
// before its file is removed, and checks that StopEviction returns its
// context's error when that context ends instead of waiting for the pass.
// Once the pass goes on, the goroutine exits and no row points at a
// missing file.
func TestStopEvictionReturnsWhenItsContextEnds(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
cache, _ := newEvictionTestCache(t, 1)
paused := make(chan struct{})
resume := make(chan struct{})
var pauseOnce sync.Once
cache.reconciliationReadTestHook = func(int) {
pauseOnce.Do(func() {
close(paused)
<-resume
})
cache.evictSourceBlobTestHook = func(ContentHash) {
close(paused)
<-resume
}
hash := storeEvictionTestSource(t, cache, "stop.example.com", "/a.jpg",
bytes.Repeat([]byte{0x61}, 1000))
cache.StartEviction(time.Hour)
select {
case <-paused:
case <-time.After(5 * time.Second):
t.Fatal("the reconciliation pass never made a read")
t.Fatal("the eviction pass never reached the source blob")
}
ctx, cancel := context.WithTimeout(t.Context(), 50*time.Millisecond)
@@ -1116,6 +1077,12 @@ func TestStopEvictionReturnsWhenItsContextEnds(t *testing.T) {
if err != nil {
t.Fatalf("second StopEviction() error = %v, want nil", err)
}
assertNoDanglingReferences(t, cache)
if cache.srcContent.Exists(hash) {
t.Errorf("source blob %s is still on disk after its rows were deleted", hash)
}
}
// TestReconciliationWalksStopOnceCancelled checks that both directory
@@ -1187,3 +1154,125 @@ func TestReconciliationPassLogsNoWarningOnceCancelled(t *testing.T) {
t.Errorf("runReconciliationPass logged a warning with a cancelled context")
}
}
// TestEvictSourceBlobExcludesConcurrentStoreOfIdenticalContent exercises
// the exact TOCTOU window between evictSourceBlob's row-deletion
// transaction commit and its content file unlink: a concurrent
// StoreSource for a different source path whose content hashes to the
// same value (real SHA-256 dedup, not a contrived case) must not be
// able to insert a fresh row referencing the file while eviction is
// mid-unlink, and must not lose its own store once eviction has fully
// released the content hash.
func TestEvictSourceBlobExcludesConcurrentStoreOfIdenticalContent(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
ctx := context.Background()
content := bytes.Repeat([]byte{0x55}, 400)
hash := storeEvictionTestSource(t, cache,
"race.example.com", "/first.jpg", content)
proceed := make(chan struct{})
storeAttempted := make(chan struct{})
cache.evictSourceBlobTestHook = func(gotHash ContentHash) {
if gotHash != hash {
t.Errorf("test hook invoked for hash %s, want %s", gotHash, hash)
}
close(storeAttempted)
<-proceed
}
evictDone := make(chan error, 1)
go func() {
evictDone <- cache.evictSourceBlob(ctx, hash)
}()
// Wait until eviction has committed its delete transaction and is
// paused (inside the test hook) immediately before unlinking the
// content file: exactly the window the review flagged.
<-storeAttempted
storeDone := storeIdenticalContentConcurrently(ctx, cache, content)
// The concurrent store must not be able to complete while eviction
// still holds the content hash (i.e. before the file is unlinked):
// if it could, it would insert a row referencing a file about to be
// removed out from under it.
select {
case err := <-storeDone:
t.Fatalf("StoreSource for identical content completed (err=%v) while eviction "+
"still held the content hash open between commit and unlink; the store and "+
"the evict of identical content are not mutually exclusive", err)
case <-time.After(200 * time.Millisecond):
// Expected: the store is blocked behind eviction's exclusion.
}
close(proceed)
err := <-evictDone
if err != nil {
t.Fatalf("evictSourceBlob failed: %v", err)
}
err = <-storeDone
if err != nil {
t.Fatalf("StoreSource failed: %v", err)
}
assertNoDanglingReferences(t, cache)
dupHash, _, err := cache.LookupSource(ctx, &ImageRequest{
SourceHost: "race.example.com",
SourcePath: "/dup.jpg",
})
if err != nil {
t.Fatalf("LookupSource failed: %v", err)
}
if dupHash == "" {
t.Fatal("re-stored blob was lost: the store legitimately ran after eviction " +
"released the content hash and must have recreated the file and row")
}
if !cache.srcContent.Exists(dupHash) {
t.Errorf("source_content/source_metadata references %s but its file is missing",
dupHash)
}
}
// storeIdenticalContentConcurrently starts a StoreSource for a second
// source path whose body hashes to the same content hash, returning the
// channel its error is delivered on.
func storeIdenticalContentConcurrently(
ctx context.Context, cache *Cache, content []byte,
) chan error {
storeDone := make(chan error, 1)
go func() {
req := &ImageRequest{
SourceHost: "race.example.com",
SourcePath: "/dup.jpg",
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
result := &httpfetcher.FetchResult{
StatusCode: 200,
ContentType: testContentTypeJPEG,
ContentLength: int64(len(content)),
Headers: map[string][]string{
testHeaderContentType: {testContentTypeJPEG},
},
}
_, err := cache.StoreSource(ctx, req, bytes.NewReader(content), result)
storeDone <- err
}()
return storeDone
}
internal/imgcache/imgcache.go
+117 -4
View File
@@ -3,12 +3,125 @@ package imgcache
import (
"context"
"errors"
"io"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// ErrInvalidFitMode is returned when an invalid fit mode is provided.
var ErrInvalidFitMode = errors.New("invalid fit mode")
// ImageFormat represents supported output image formats.
type ImageFormat string
// Supported image output formats.
const (
FormatOriginal ImageFormat = "orig"
FormatJPEG ImageFormat = "jpeg"
FormatPNG ImageFormat = "png"
FormatWebP ImageFormat = "webp"
FormatAVIF ImageFormat = "avif"
FormatGIF ImageFormat = "gif"
// FormatAuto stands for AVIF, WebP or JPEG, chosen for each request
// from its Accept header once the URL's signature or token has been
// checked; it is never processed or cached as itself.
FormatAuto ImageFormat = "auto"
)
// Size represents requested image dimensions
type Size struct {
Width int
Height int
}
// OriginalSize returns true if this represents "keep original size"
func (s Size) OriginalSize() bool {
return s.Width == 0 && s.Height == 0
}
// FitMode represents how to fit image into requested dimensions.
type FitMode string
// Supported image fit modes.
const (
FitCover FitMode = "cover"
FitContain FitMode = "contain"
FitFill FitMode = "fill"
FitInside FitMode = "inside"
FitOutside FitMode = "outside"
)
// ValidateFitMode checks if the given fit mode is valid.
// Returns ErrInvalidFitMode for unrecognized fit modes.
func ValidateFitMode(fit FitMode) error {
switch fit {
case FitCover, FitContain, FitFill, FitInside, FitOutside, "":
return nil
default:
return ErrInvalidFitMode
}
}
// ValidateImageRequest checks a request's width and height with
// ValidateDimension and its fit mode with ValidateFitMode. Both the plain
// /v1/image/ route and the encrypted /v1/e/ route validate through this
// function so a request from either source enforces identical bounds.
func ValidateImageRequest(req *ImageRequest) error {
err := ValidateDimension("width", req.Size.Width)
if err != nil {
return err
}
err = ValidateDimension("height", req.Size.Height)
if err != nil {
return err
}
return ValidateFitMode(req.FitMode)
}
// ImageRequest represents a request for a processed image
type ImageRequest struct {
// SourceHost is the origin host (e.g., "cdn.example.com")
SourceHost string
// SourcePath is the path on the origin (e.g., "/photos/cat.jpg")
SourcePath string
// SourceQuery is the optional query string for the origin URL
SourceQuery string
// Size is the requested output dimensions
Size Size
// Format is the requested output format
Format ImageFormat
// Quality is the output quality (1-100) for lossy formats
Quality int
// FitMode is how to fit the image into requested dimensions
FitMode FitMode
// Signature is the HMAC signature for non-allowlisted hosts
Signature string
// Expires is when the URL expires: the exp of a signed URL, or the expiry
// of an encrypted URL; the zero time if it has none
Expires time.Time
// AllowHTTP indicates whether HTTP (non-TLS) is allowed for this request
AllowHTTP bool
}
// SourceURL returns the full upstream URL to fetch.
// Uses http:// scheme when AllowHTTP is true, otherwise https://.
func (r *ImageRequest) SourceURL() string {
scheme := "https"
if r.AllowHTTP {
scheme = "http"
}
url := scheme + "://" + r.SourceHost + r.SourcePath
if r.SourceQuery != "" {
url += "?" + r.SourceQuery
}
return url
}
// ImageResponse represents a processed image ready to serve
type ImageResponse struct {
// Content is the image data reader
@@ -40,10 +153,10 @@ const (
// ImageCache is the main interface for the image caching proxy
type ImageCache interface {
// Get retrieves a processed image, fetching and processing if necessary
Get(ctx context.Context, req *imagerequest.Request) (*ImageResponse, error)
Get(ctx context.Context, req *ImageRequest) (*ImageResponse, error)
// Warm pre-fetches and caches an image without returning it
Warm(ctx context.Context, req *imagerequest.Request) error
Warm(ctx context.Context, req *ImageRequest) error
// Stats returns cache statistics
Stats(ctx context.Context) (*CacheStats, error)
internal/imgcache/max_concurrent_processing_internal_test.go
+13 -18
View File
@@ -9,23 +9,18 @@ import (
"time"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// widthOnlyRequest asks for the test photo at width, its height scaled to
// keep the photo's aspect ratio.
func widthOnlyRequest(fixtures *TestFixtures, width int) *imagerequest.Request {
return &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: width},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
func widthOnlyRequest(fixtures *TestFixtures, width int) *ImageRequest {
return &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: width},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
}
@@ -41,7 +36,7 @@ func holdProcessingSlot(
input, feed := io.Pipe()
go func() {
_, _ = proc.Process(t.Context(), input, &imagerequest.Transform{})
_, _ = proc.Process(t.Context(), input, &imageprocessor.Request{})
}()
_, err := feed.Write([]byte{0})
@@ -77,11 +72,11 @@ func TestService_Get_WaitsForSlotBeforeReadingCachedSource(t *testing.T) {
_ = resp.Content.Close()
sourceKey, err := svc.cache.LookupSource(t.Context(),
contentHash, _, err := svc.cache.LookupSource(t.Context(),
widthOnlyRequest(fixtures, 50))
if err != nil || sourceKey == "" {
if err != nil || contentHash == "" {
t.Fatalf("LookupSource() = %q, %v; want the cached source",
sourceKey, err)
contentHash, err)
}
release := holdProcessingSlot(t, svc.processor)
@@ -103,7 +98,7 @@ func TestService_Get_WaitsForSlotBeforeReadingCachedSource(t *testing.T) {
// before waiting, it would have read it by now.
time.Sleep(100 * time.Millisecond)
err = os.WriteFile(svc.cache.srcContent.keyToPath(sourceKey),
err = os.WriteFile(svc.cache.srcContent.hashToPath(contentHash),
generateTestJPEG(t, 100, 50, color.RGBA{0, 0, 255, 255}), 0o600)
if err != nil {
t.Fatalf("failed to rewrite the cached source: %v", err)
internal/imgcache/metacache_internal_test.go
+349
View File
@@ -0,0 +1,349 @@
package imgcache
import (
"bytes"
"encoding/json"
"errors"
"fmt"
"io"
"os"
"sync"
"testing"
"time"
)
// webpRequest returns a request for a 100x100 WebP variant of path.
func webpRequest(path string) *ImageRequest {
return &ImageRequest{
SourceHost: testHostCDN,
SourcePath: path,
Size: Size{Width: 100, Height: 100},
Format: FormatWebP,
Quality: 85,
FitMode: FitCover,
}
}
// assertVariantServed checks that GetVariant serves key with the given
// content and the image/webp content type storeEvictionTestVariant stores.
func assertVariantServed(t *testing.T, cache *Cache, key VariantKey, content []byte) {
t.Helper()
reader, size, contentType, err := cache.GetVariant(key)
if err != nil {
t.Fatalf("GetVariant(%s) error = %v", key, err)
}
defer func() { _ = reader.Close() }()
got, err := io.ReadAll(reader)
if err != nil {
t.Fatalf("reading variant %s: %v", key, err)
}
if !bytes.Equal(got, content) {
t.Errorf("GetVariant(%s) content = %q, want %q", key, got, content)
}
if size != int64(len(content)) {
t.Errorf("GetVariant(%s) size = %d, want %d", key, size, len(content))
}
if contentType != testContentTypeWebP {
t.Errorf("GetVariant(%s) content type = %q, want %q",
key, contentType, testContentTypeWebP)
}
}
// assertVariantNotFound checks that GetVariant refuses key with
// ErrNotFound.
func assertVariantNotFound(t *testing.T, cache *Cache, key VariantKey) {
t.Helper()
reader, _, _, err := cache.GetVariant(key)
if err == nil {
_ = reader.Close()
}
if !errors.Is(err, ErrNotFound) {
t.Errorf("GetVariant(%s) error = %v, want ErrNotFound", key, err)
}
}
// assertLookupMisses checks that Lookup reports request as a miss.
func assertLookupMisses(t *testing.T, cache *Cache, request *ImageRequest) {
t.Helper()
lookup, err := cache.Lookup(t.Context(), request)
if err != nil {
t.Fatalf("Lookup(%s) error = %v", request.SourcePath, err)
}
if lookup.Hit {
t.Errorf("Lookup(%s) is a hit, want a miss", request.SourcePath)
}
}
// renameFile renames the file at from to to.
func renameFile(t *testing.T, from, to string) {
t.Helper()
err := os.Rename(from, to)
if err != nil {
t.Fatalf("renaming %s: %v", from, err)
}
}
// TestSecondHitDoesNotReadMetaFile checks that once a variant has been
// stored or read, a hit takes its content type from memory: with the
// .meta file deleted, GetVariant must still return the stored content
// type rather than the application/octet-stream it uses without one.
func TestSecondHitDoesNotReadMetaFile(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<20)
content := []byte("webp variant bytes")
storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
// A second Cache on the same state directory starts with nothing in
// memory, as pixad does after a restart, so its first read uses the
// .meta file.
restarted, err := NewCache(cache.db, cache.config)
if err != nil {
t.Fatalf("NewCache() error = %v", err)
}
assertVariantServed(t, restarted, testVariantKeyOne, content)
err = os.Remove(cache.variants.keyToPath(testVariantKeyOne) + ".meta")
if err != nil {
t.Fatalf("removing .meta file: %v", err)
}
assertVariantServed(t, cache, testVariantKeyOne, content)
assertVariantServed(t, restarted, testVariantKeyOne, content)
}
// TestReadDuringStoreKeepsStoredContentType checks that a GetVariant
// which began before StoreVariant finished cannot replace the content
// type the store kept in memory. Such a read can find the variant file
// but not yet its .meta file, and so gets application/octet-stream. The
// test deletes the .meta file after the store, then runs the part of
// GetVariant that comes after its check of memory.
func TestReadDuringStoreKeepsStoredContentType(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<20)
content := []byte("webp variant bytes")
storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
err := os.Remove(cache.variants.keyToPath(testVariantKeyOne) + ".meta")
if err != nil {
t.Fatalf("removing .meta file: %v", err)
}
reader, _, contentType, err := cache.loadVariantWithMeta(testVariantKeyOne)
if err != nil {
t.Fatalf("loadVariantWithMeta(%s) error = %v", testVariantKeyOne, err)
}
_ = reader.Close()
t.Logf("the read without a .meta file got content type %q", contentType)
assertVariantServed(t, cache, testVariantKeyOne, content)
}
// TestReadOfOlderMetaFileKeepsStoredContentType checks that a read
// which got its content type from a .meta file that StoreVariant had
// not yet rewritten cannot replace the type the store kept in memory.
// The test writes such a .meta file, with a different content type,
// after the store, then runs the part of GetVariant that comes after
// its check of memory.
func TestReadOfOlderMetaFileKeepsStoredContentType(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<20)
content := []byte("webp variant bytes")
storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
olderMeta, err := json.Marshal(VariantMeta{
ContentType: testContentTypeJPEG,
Size: int64(len(content)),
})
if err != nil {
t.Fatalf("encoding .meta file: %v", err)
}
metaPath := cache.variants.keyToPath(testVariantKeyOne) + ".meta"
err = os.WriteFile(metaPath, olderMeta, StorageFilePerm)
if err != nil {
t.Fatalf("writing .meta file: %v", err)
}
reader, _, contentType, err := cache.loadVariantWithMeta(testVariantKeyOne)
if err != nil {
t.Fatalf("loadVariantWithMeta(%s) error = %v", testVariantKeyOne, err)
}
_ = reader.Close()
if contentType != testContentTypeJPEG {
t.Fatalf("loadVariantWithMeta(%s) content type = %q, want %q from the .meta file",
testVariantKeyOne, contentType, testContentTypeJPEG)
}
kept, _ := cache.metaCache.Get(testVariantKeyOne)
if kept != testContentTypeWebP {
t.Errorf("content type in memory = %q, want the stored %q",
kept, testContentTypeWebP)
}
}
// TestFailedReadDuringStoreKeepsStoredContentType checks that a read
// which found no .meta file cannot leave application/octet-stream in
// memory, even when another read has removed the content type
// StoreVariant kept there. In this order: the store; a read that finds
// the variant in memory but cannot open its file, and so removes it
// from memory; a read that opened the variant file before the store
// wrote its .meta file. Later hits must get the stored content type.
func TestFailedReadDuringStoreKeepsStoredContentType(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<20)
content := []byte("webp variant bytes")
variantPath := cache.variants.keyToPath(testVariantKeyOne)
metaPath := variantPath + ".meta"
storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
renameFile(t, variantPath, variantPath+".hidden")
assertVariantNotFound(t, cache, testVariantKeyOne)
renameFile(t, variantPath+".hidden", variantPath)
renameFile(t, metaPath, metaPath+".hidden")
reader, _, contentType, err := cache.GetVariant(testVariantKeyOne)
if err != nil {
t.Fatalf("GetVariant(%s) error = %v", testVariantKeyOne, err)
}
_ = reader.Close()
t.Logf("the read without a .meta file got content type %q", contentType)
renameFile(t, metaPath+".hidden", metaPath)
assertVariantServed(t, cache, testVariantKeyOne, content)
}
// TestEvictedVariantIsNotServed checks that a variant the evictor
// removed is a miss and cannot be read, although it had been stored
// and served before.
func TestEvictedVariantIsNotServed(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1500)
oldRequest := webpRequest("/old.jpg")
newRequest := webpRequest("/new.jpg")
oldKey := CacheKey(oldRequest)
newKey := CacheKey(newRequest)
oldContent := bytes.Repeat([]byte{0x01}, 1000)
newContent := bytes.Repeat([]byte{0x02}, 1000)
storeEvictionTestVariant(t, cache, oldKey, oldContent)
storeEvictionTestVariant(t, cache, newKey, newContent)
assertVariantServed(t, cache, oldKey, oldContent)
setVariantLastAccessed(t, cache, oldKey, time.Now().Add(-time.Hour))
err := cache.EvictToLimit(t.Context())
if err != nil {
t.Fatalf("EvictToLimit() error = %v", err)
}
assertLookupMisses(t, cache, oldRequest)
assertVariantNotFound(t, cache, oldKey)
assertVariantServed(t, cache, newKey, newContent)
}
// TestVariantDeletedFromDiskIsNotServed checks that a variant whose
// file was deleted by something other than the evictor cannot be read,
// and is a miss afterwards.
func TestVariantDeletedFromDiskIsNotServed(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<20)
request := webpRequest("/deleted.jpg")
key := CacheKey(request)
content := []byte("webp variant bytes")
storeEvictionTestVariant(t, cache, key, content)
assertVariantServed(t, cache, key, content)
err := os.Remove(cache.variants.keyToPath(key))
if err != nil {
t.Fatalf("removing variant file: %v", err)
}
assertVariantNotFound(t, cache, key)
assertLookupMisses(t, cache, request)
}
// TestConcurrentVariantStoreReadAndEvict stores, reads and evicts
// variants from several goroutines at once, for the race detector.
func TestConcurrentVariantStoreReadAndEvict(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<20)
ctx := t.Context()
var wg sync.WaitGroup
for goroutine := range 8 {
wg.Go(func() {
key := VariantKey(fmt.Sprintf("aabbccdd01%02d", goroutine))
content := []byte(key)
for range 20 {
err := cache.StoreVariant(
ctx, key, bytes.NewReader(content), testContentTypeWebP)
if err != nil {
t.Errorf("StoreVariant(%s) error = %v", key, err)
return
}
reader, _, contentType, err := cache.GetVariant(key)
if err != nil {
t.Errorf("GetVariant(%s) error = %v", key, err)
return
}
_ = reader.Close()
if contentType != testContentTypeWebP {
t.Errorf("GetVariant(%s) content type = %q, want %q",
key, contentType, testContentTypeWebP)
}
err = cache.evictVariant(ctx, key)
if err != nil {
t.Errorf("evictVariant(%s) error = %v", key, err)
return
}
assertVariantNotFound(t, cache, key)
}
})
}
wg.Wait()
}
internal/imgcache/module.go
+1
View File
@@ -4,5 +4,6 @@ import "time"
// CacheConfig defaults.
const (
DefaultCacheTTL = 24 * time.Hour
DefaultNegativeTTL = 5 * time.Minute
)
internal/imgcache/negative_cache_internal_test.go
+10 -316
View File
@@ -3,11 +3,8 @@ package imgcache
import (
"context"
"errors"
"strconv"
"testing"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
)
func TestNegativeCache_StoreAndCheck(t *testing.T) {
@@ -18,6 +15,7 @@ func TestNegativeCache_StoreAndCheck(t *testing.T) {
cache, err := NewCache(db, CacheConfig{
StateDir: dir,
CacheTTL: time.Hour,
NegativeTTL: 5 * time.Minute,
})
if err != nil {
@@ -25,11 +23,9 @@ func TestNegativeCache_StoreAndCheck(t *testing.T) {
}
ctx := context.Background()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: testHostExample,
Path: "/missing.jpg",
},
req := &ImageRequest{
SourceHost: testHostExample,
SourcePath: "/missing.jpg",
}
// Initially should not be in negative cache
@@ -43,7 +39,7 @@ func TestNegativeCache_StoreAndCheck(t *testing.T) {
}
// Store a negative entry
err = cache.StoreNegative(ctx, req)
err = cache.StoreNegative(ctx, req, 404, "not found")
if err != nil {
t.Fatal(err)
}
@@ -67,6 +63,7 @@ func TestNegativeCache_Expired(t *testing.T) {
cache, err := NewCache(db, CacheConfig{
StateDir: dir,
CacheTTL: time.Hour,
NegativeTTL: 1 * time.Millisecond, // very short TTL
})
if err != nil {
@@ -74,15 +71,13 @@ func TestNegativeCache_Expired(t *testing.T) {
}
ctx := context.Background()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: testHostExample,
Path: "/expired.jpg",
},
req := &ImageRequest{
SourceHost: testHostExample,
SourcePath: "/expired.jpg",
}
// Store a negative entry with very short TTL
err = cache.StoreNegative(ctx, req)
err = cache.StoreNegative(ctx, req, 500, "server error")
if err != nil {
t.Fatal(err)
}
@@ -101,307 +96,6 @@ func TestNegativeCache_Expired(t *testing.T) {
}
}
// TestService_Get_ServesCachedVariantOfNegativeCachedURL caches a variant of
// the test photo, then keeps a failed fetch of the photo's URL in the negative
// cache, as a failed fetch for another variant does once the source has been
// evicted. The cached variant is still served, and a variant not in the cache
// is made from the cached source. Once the source is evicted, a variant not in
// the cache needs a fetch and is refused.
func TestService_Get_ServesCachedVariantOfNegativeCachedURL(t *testing.T) {
t.Parallel()
svc, fixtures := SetupTestService(t)
resp, err := svc.Get(t.Context(), photoVariant(fixtures, 85, imagerequest.FitCover))
if err != nil {
t.Fatalf("Get() first request error = %v", err)
}
_ = resp.Content.Close()
err = svc.cache.StoreNegative(t.Context(),
photoVariant(fixtures, 85, imagerequest.FitCover))
if err != nil {
t.Fatalf("StoreNegative() error = %v", err)
}
resp, err = svc.Get(t.Context(), photoVariant(fixtures, 85, imagerequest.FitCover))
if err != nil {
t.Fatalf("Get() of the cached variant error = %v", err)
}
_ = resp.Content.Close()
if resp.CacheStatus != CacheHit {
t.Errorf("cached variant CacheStatus = %q, want %q",
resp.CacheStatus, CacheHit)
}
resp, err = svc.Get(t.Context(), photoVariant(fixtures, 40, imagerequest.FitCover))
t.Logf("Get() of a variant made from the cached source: error = %v", err)
if err != nil {
t.Fatalf("Get() of a variant made from the cached source error = %v", err)
}
_ = resp.Content.Close()
sourceKey, err := svc.cache.LookupSource(t.Context(),
photoVariant(fixtures, 85, imagerequest.FitCover))
if err != nil || sourceKey == "" {
t.Fatalf("LookupSource() = %q, %v, want the cached source", sourceKey, err)
}
err = svc.cache.evictSourceBlob(t.Context(), sourceKey)
if err != nil {
t.Fatalf("evictSourceBlob() error = %v", err)
}
_, err = svc.Get(t.Context(), photoVariant(fixtures, 60, imagerequest.FitCover))
t.Logf("Get() of a variant whose source was evicted: error = %v", err)
if !errors.Is(err, ErrNegativeCached) {
t.Errorf("Get() of a variant whose source was evicted error = %v, want %v",
err, ErrNegativeCached)
}
}
// TestEvictionLoopRemovesExpiredNegativeCacheRows stores a failed fetch
// that expires a second later and starts the eviction loop with a short
// interval: a later tick must remove its row although its URL is never
// requested again, and must keep a row that has not expired. It runs
// with the disk cache enabled and disabled, as the negative cache is
// used either way.
func TestEvictionLoopRemovesExpiredNegativeCacheRows(t *testing.T) {
t.Parallel()
tests := []struct {
name string
disableDiskCache bool
}{
{name: "disk cache enabled", disableDiskCache: false},
{name: "disk cache disabled", disableDiskCache: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
cache, err := NewCache(evictionTestDB(t), CacheConfig{
StateDir: t.TempDir(),
NegativeTTL: time.Second,
DisableDiskCache: tt.disableDiskCache,
})
if err != nil {
t.Fatalf("failed to create cache: %v", err)
}
expired := &imagerequest.Request{
Source: imagerequest.Source{Host: testHostExample, Path: "/gone.jpg"},
}
err = cache.StoreNegative(t.Context(), expired)
if err != nil {
t.Fatalf("StoreNegative failed: %v", err)
}
const notExpiredPath = "/later.jpg"
_, err = cache.db.ExecContext(t.Context(), `
INSERT INTO negative_cache
(source_host, source_path, expires_at)
VALUES (?, ?, datetime('now', '+1 hour'))
`, testHostExample, notExpiredPath)
if err != nil {
t.Fatalf("failed to insert a row that has not expired: %v", err)
}
started := time.Now()
cache.StartEviction(100 * time.Millisecond)
defer func() { _ = cache.StopEviction(t.Context()) }()
for negativeCacheRowCount(t, cache, expired.Source.Path) > 0 {
if time.Since(started) > 10*time.Second {
t.Fatal("the expired row is still in negative_cache")
}
time.Sleep(50 * time.Millisecond)
}
t.Logf("the expired row was removed %s after the loop started",
time.Since(started))
if negativeCacheRowCount(t, cache, notExpiredPath) != 1 {
t.Error("the row that has not expired was removed")
}
})
}
}
// negativeCacheRowCount returns how many negative_cache rows hold
// sourcePath.
func negativeCacheRowCount(tb testing.TB, cache *Cache, sourcePath string) int {
tb.Helper()
var count int
err := cache.db.QueryRowContext(tb.Context(),
`SELECT COUNT(*) FROM negative_cache WHERE source_path = ?`,
sourcePath,
).Scan(&count)
if err != nil {
tb.Fatalf("failed to count negative_cache rows: %v", err)
}
return count
}
// TestCleanExpiredDeletesInBatches stores one expired negative cache row
// more than one batch holds, and one row that has not expired. One
// statement must delete one batch and no more, so a request waits behind
// one batch at most; CleanExpired must then remove the expired row left
// over and keep the row that has not expired.
func TestCleanExpiredDeletesInBatches(t *testing.T) {
t.Parallel()
cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
if err != nil {
t.Fatalf("failed to create cache: %v", err)
}
ctx := t.Context()
insertExpiredNegativeCacheRows(t, cache, cleanExpiredBatchSize+1)
const notExpiredPath = "/later.jpg"
_, err = cache.db.ExecContext(ctx, `
INSERT INTO negative_cache
(source_host, source_path, expires_at)
VALUES (?, ?, datetime('now', '+1 hour'))
`, testHostExample, notExpiredPath)
if err != nil {
t.Fatalf("failed to insert a row that has not expired: %v", err)
}
deleted, err := cache.cleanExpiredBatch(ctx)
if err != nil {
t.Fatalf("cleanExpiredBatch failed: %v", err)
}
t.Logf("one statement deleted %d of %d expired rows",
deleted, cleanExpiredBatchSize+1)
if deleted != cleanExpiredBatchSize {
t.Errorf("one statement deleted %d rows, want %d",
deleted, cleanExpiredBatchSize)
}
err = cache.CleanExpired(ctx)
if err != nil {
t.Fatalf("CleanExpired failed: %v", err)
}
if count := negativeCacheTableRowCount(t, cache); count != 1 {
t.Errorf("negative_cache holds %d rows after CleanExpired, want 1", count)
}
if negativeCacheRowCount(t, cache, notExpiredPath) != 1 {
t.Error("the row that has not expired was removed")
}
}
// TestCleanExpiredRemovesMoreThanOneBatch stores one expired negative
// cache row more than one batch holds and calls CleanExpired once: it
// must remove them all, so it fails if CleanExpired stops after its
// first batch.
func TestCleanExpiredRemovesMoreThanOneBatch(t *testing.T) {
t.Parallel()
cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
if err != nil {
t.Fatalf("failed to create cache: %v", err)
}
insertExpiredNegativeCacheRows(t, cache, cleanExpiredBatchSize+1)
before := negativeCacheTableRowCount(t, cache)
err = cache.CleanExpired(t.Context())
if err != nil {
t.Fatalf("CleanExpired failed: %v", err)
}
after := negativeCacheTableRowCount(t, cache)
t.Logf("CleanExpired removed %d of %d expired rows, %d per batch",
before-after, before, cleanExpiredBatchSize)
if after != 0 {
t.Errorf("negative_cache holds %d rows after CleanExpired, want 0", after)
}
}
// TestCleanExpiredStopsOnceContextEnds runs CleanExpired with a context
// that has already ended: it must return the context's error and delete
// no row.
func TestCleanExpiredStopsOnceContextEnds(t *testing.T) {
t.Parallel()
cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
if err != nil {
t.Fatalf("failed to create cache: %v", err)
}
insertExpiredNegativeCacheRows(t, cache, 1)
ctx, cancel := context.WithCancel(t.Context())
cancel()
err = cache.CleanExpired(ctx)
if !errors.Is(err, context.Canceled) {
t.Errorf("CleanExpired() error = %v, want context.Canceled", err)
}
if count := negativeCacheTableRowCount(t, cache); count != 1 {
t.Errorf("negative_cache holds %d rows, want the expired row kept", count)
}
}
// insertExpiredNegativeCacheRows inserts count negative_cache rows that
// expired an hour ago, each for a different source path.
func insertExpiredNegativeCacheRows(t *testing.T, cache *Cache, count int) {
t.Helper()
for i := range count {
_, err := cache.db.ExecContext(t.Context(), `
INSERT INTO negative_cache
(source_host, source_path, expires_at)
VALUES (?, ?, datetime('now', '-1 hour'))
`, testHostExample, "/expired/"+strconv.Itoa(i)+".jpg")
if err != nil {
t.Fatalf("failed to insert an expired row: %v", err)
}
}
}
// negativeCacheTableRowCount returns how many rows negative_cache holds.
func negativeCacheTableRowCount(tb testing.TB, cache *Cache) int {
tb.Helper()
var count int
err := cache.db.QueryRowContext(tb.Context(),
`SELECT COUNT(*) FROM negative_cache`,
).Scan(&count)
if err != nil {
tb.Fatalf("failed to count negative_cache rows: %v", err)
}
return count
}
func TestService_Get_ReturnsErrorForNegativeCachedURL(t *testing.T) {
t.Parallel()
internal/imgcache/partial_cache_files_internal_test.go
-312
View File
@@ -1,312 +0,0 @@
package imgcache
import (
"bytes"
"io"
"log/slog"
"os"
"path/filepath"
"strings"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// getImage calls Get for req and returns the image it answered with and
// its cache status.
func getImage(
t *testing.T, svc *Service, req *imagerequest.Request,
) ([]byte, CacheStatus) {
t.Helper()
resp, err := svc.Get(t.Context(), req)
if err != nil {
t.Fatalf("Get() of quality %d error = %v", req.Transform.Quality, err)
}
defer func() { _ = resp.Content.Close() }()
body, err := io.ReadAll(resp.Content)
if err != nil {
t.Fatalf("reading the image of quality %d: %v", req.Transform.Quality, err)
}
return body, resp.CacheStatus
}
// fileSize returns the size of the file at path.
func fileSize(t *testing.T, path string) int64 {
t.Helper()
info, err := os.Stat(path)
if err != nil {
t.Fatalf("stat %s: %v", path, err)
}
return info.Size()
}
// truncateFile cuts the file at path down to size bytes.
func truncateFile(t *testing.T, path string, size int64) {
t.Helper()
t.Logf("cutting %s from %d to %d bytes",
filepath.Base(path), fileSize(t, path), size)
err := os.Truncate(path, size)
if err != nil {
t.Fatalf("truncating %s: %v", path, err)
}
}
// cachedSourcePath returns the path of the cached source file req uses.
func cachedSourcePath(
t *testing.T, svc *Service, req *imagerequest.Request,
) string {
t.Helper()
sourceKey, err := svc.cache.LookupSource(t.Context(), req)
if err != nil || sourceKey == "" {
t.Fatalf("LookupSource() = %q, %v; want the cached source", sourceKey, err)
}
return svc.cache.srcContent.keyToPath(sourceKey)
}
// reconcileAsAtStartup runs the cache's reconciliation pass, as pixa does
// when it starts, and returns what the pass logged.
func reconcileAsAtStartup(t *testing.T, cache *Cache) string {
t.Helper()
var logBuf bytes.Buffer
cache.log = slog.New(slog.NewJSONHandler(&logBuf, nil))
err := cache.reconcileAccounting(t.Context())
if err != nil {
t.Fatalf("reconcileAccounting() error = %v", err)
}
t.Logf("reconciliation log: %s", logBuf.String())
return logBuf.String()
}
// assertWarningNames checks that logs hold a warning naming the file at
// path.
func assertWarningNames(t *testing.T, logs, path string) {
t.Helper()
for line := range strings.Lines(logs) {
if strings.Contains(line, `"level":"WARN"`) &&
strings.Contains(line, `"path":"`+path+`"`) {
return
}
}
t.Errorf("reconciliation logged no warning naming %s", path)
}
// TestService_Get_FetchesAgainForEmptyCachedSource empties the cached source
// file, as a crash or a restored snapshot could, and runs the reconciliation
// pass, which must remove it with a warning naming it. It then asks for two
// new sizes of the source: the first must fetch it again and cache it whole,
// so that the second is made from the cache without a third fetch.
func TestService_Get_FetchesAgainForEmptyCachedSource(t *testing.T) {
t.Parallel()
svc, fixtures := SetupTestService(t)
getImage(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
path := cachedSourcePath(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
wholeSize := fileSize(t, path)
truncateFile(t, path, 0)
assertWarningNames(t, reconcileAsAtStartup(t, svc.cache), path)
getImage(t, svc, photoVariant(fixtures, 40, imagerequest.FitCover))
getImage(t, svc, photoVariant(fixtures, 30, imagerequest.FitCover))
waitForPendingCountsWritten(t, svc.cache)
fetches := readCacheStatsCounters(t, svc.cache).upstreamFetchCount
t.Logf("upstream fetches = %d", fetches)
if fetches != 2 {
t.Errorf("upstream fetches = %d, want 2: the empty cached source "+
"was kept and fetched again on every new size", fetches)
}
size := fileSize(t, path)
if size != wholeSize {
t.Errorf("cached source is %d bytes, want %d", size, wholeSize)
}
}
// TestService_Get_FetchesAgainForPartialCachedSource cuts the cached source
// file to half its size, as a crash or a restored snapshot could, and runs
// the reconciliation pass, which must remove it with a warning naming it.
// It then asks for two new sizes of the source: the first must fetch it
// again rather than fail to decode the partial file, and the second is
// made from the cache.
func TestService_Get_FetchesAgainForPartialCachedSource(t *testing.T) {
t.Parallel()
svc, fixtures := SetupTestService(t)
getImage(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
path := cachedSourcePath(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
wholeSize := fileSize(t, path)
truncateFile(t, path, wholeSize/2)
assertWarningNames(t, reconcileAsAtStartup(t, svc.cache), path)
getImage(t, svc, photoVariant(fixtures, 40, imagerequest.FitCover))
getImage(t, svc, photoVariant(fixtures, 30, imagerequest.FitCover))
waitForPendingCountsWritten(t, svc.cache)
fetches := readCacheStatsCounters(t, svc.cache).upstreamFetchCount
t.Logf("upstream fetches = %d", fetches)
if fetches != 2 {
t.Errorf("upstream fetches = %d, want 2", fetches)
}
size := fileSize(t, path)
if size != wholeSize {
t.Errorf("cached source is %d bytes, want %d", size, wholeSize)
}
}
// assertConvertedAgain caches a variant of the photo, cuts its file to size
// bytes and runs the reconciliation pass, which must remove it with a
// warning naming it. It then checks that Get converts the image again
// instead of serving the file, and that the next Get serves the whole
// variant from the cache.
func assertConvertedAgain(t *testing.T, size int64) {
t.Helper()
svc, fixtures := SetupTestService(t)
req := photoVariant(fixtures, 85, imagerequest.FitCover)
want, _ := getImage(t, svc, req)
path := svc.cache.variants.keyToPath(imagerequest.CacheKey(req))
truncateFile(t, path, size)
assertWarningNames(t, reconcileAsAtStartup(t, svc.cache), path)
got, status := getImage(t, svc, req)
t.Logf("after the cut: %d bytes, %s", len(got), status)
if status != CacheMiss || !bytes.Equal(got, want) {
t.Errorf("after the cut: Get() = %d bytes, %s; want the %d bytes "+
"converted again, %s", len(got), status, len(want), CacheMiss)
}
got, status = getImage(t, svc, req)
t.Logf("next request: %d bytes, %s", len(got), status)
if status != CacheHit || !bytes.Equal(got, want) {
t.Errorf("next request: Get() = %d bytes, %s; want the %d bytes, %s",
len(got), status, len(want), CacheHit)
}
}
// TestService_Get_ConvertsAgainForEmptyCachedVariant empties a cached
// variant file, as a crash or a restored snapshot could, and checks that it
// is converted again rather than served empty.
func TestService_Get_ConvertsAgainForEmptyCachedVariant(t *testing.T) {
t.Parallel()
assertConvertedAgain(t, 0)
}
// TestService_Get_ConvertsAgainForPartialCachedVariant cuts a cached
// variant file to ten bytes, as a crash or a restored snapshot could, and
// checks that it is converted again rather than served cut short.
func TestService_Get_ConvertsAgainForPartialCachedVariant(t *testing.T) {
t.Parallel()
assertConvertedAgain(t, 10)
}
// TestReconciliationRemovesEmptyVariantFileWithoutRow checks that the
// reconciliation pass removes an empty variant file that has no
// accounting row, with a warning naming it, instead of adding a row for
// it that would have it served empty.
func TestReconciliationRemovesEmptyVariantFileWithoutRow(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
_, err := cache.variants.Store(testVariantKeyOne, bytes.NewReader(nil))
if err != nil {
t.Fatalf("failed to store an empty variant file: %v", err)
}
logs := reconcileAsAtStartup(t, cache)
assertWarningNames(t, logs, cache.variants.keyToPath(testVariantKeyOne))
if cache.variants.Exists(testVariantKeyOne) {
t.Error("the empty variant file is still on disk")
}
rows := countRows(t, cache,
`SELECT COUNT(*) FROM variant_content WHERE cache_key = ?`,
string(testVariantKeyOne))
if rows != 0 {
t.Errorf("the empty variant file got %d accounting rows, want 0", rows)
}
}
// TestContentStorage_StoreReplacesFileOfAnotherSize checks that a
// store over a file of another size at the source's path, such as a
// partial file a crash left, replaces it with the content.
func TestContentStorage_StoreReplacesFileOfAnotherSize(t *testing.T) {
t.Parallel()
storage, err := NewContentStorage(t.TempDir())
if err != nil {
t.Fatalf("NewContentStorage() error = %v", err)
}
content := []byte("the whole source image")
key := imagerequest.Source{Host: testHostCDN, Path: testPathCat}.Key()
path := storage.keyToPath(key)
err = os.MkdirAll(filepath.Dir(path), StorageDirPerm)
if err != nil {
t.Fatalf("creating the source's directory: %v", err)
}
err = os.WriteFile(path, content[:5], StorageFilePerm)
if err != nil {
t.Fatalf("writing a partial file: %v", err)
}
_, err = storage.Store(key, content)
if err != nil {
t.Fatalf("Store() error = %v", err)
}
stored, err := storage.Load(key)
if err != nil {
t.Fatalf("Load() error = %v", err)
}
defer func() { _ = stored.Close() }()
got, err := io.ReadAll(stored)
if err != nil {
t.Fatalf("reading the stored content: %v", err)
}
if !bytes.Equal(got, content) {
t.Errorf("stored file = %q, want %q", got, content)
}
}
internal/imgcache/pendingcounts.go
-221
View File
@@ -1,221 +0,0 @@
package imgcache
import (
"context"
"errors"
"fmt"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// pendingWriteInterval is how often the goroutine StartPendingCountWrites
// starts writes the pending access times and counts. SQLite's
// CURRENT_TIMESTAMP, which an access time is written as, counts whole
// seconds.
const pendingWriteInterval = time.Second
// StartPendingCountWrites starts the goroutine that writes, every
// pendingWriteInterval, the pending access times in one transaction and then
// the pending counts in one UPDATE. Requests only hand these to it, so none
// waits for the database to record what it did, and only this goroutine's
// write ever waits for it. It is a no-op when already started. The goroutine
// outlives the caller, so it runs with its own context, which
// StopPendingCountWrites cancels to tell it to finish.
func (c *Cache) StartPendingCountWrites() {
if c.pendingCountsCancel != nil {
return
}
ctx, cancel := context.WithCancel(context.Background())
c.pendingCountsCancel = cancel
go func() {
c.pendingCountWriteLoop(ctx)
}()
}
// StopPendingCountWrites tells the goroutine StartPendingCountWrites
// started, if it did, to finish, and waits for its write under way to end
// and for it to return. It then writes the pending access times and counts
// left, once, so that they are written before the database closes. It waits
// for all of this at most until ctx ends. It logs what was not written,
// access times or counts, and returns an error.
func (c *Cache) StopPendingCountWrites(ctx context.Context) error {
var accessTimesErr, countsErr error
if c.pendingCountsCancel != nil {
c.pendingCountsCancel()
select {
case <-c.pendingCountsDone:
case <-ctx.Done():
// The write given up on here, of access times or of counts,
// may not reach the database: database/sql closes without
// waiting for a query, and a write still waiting for the
// connection fails when the database closes. Neither is
// written here.
accessTimesErr = fmt.Errorf("access times still being written: %w", ctx.Err())
countsErr = fmt.Errorf("pending counts still being written: %w", ctx.Err())
}
}
if accessTimesErr == nil && countsErr == nil {
accessTimesErr = c.writePendingAccessTimes(ctx)
countsErr = c.writePendingCounts(ctx)
}
if accessTimesErr != nil {
c.log.Error("access times not written at shutdown", "error", accessTimesErr)
}
if countsErr != nil {
c.log.Error("counts not written at shutdown",
"hits", c.pendingHits.Load(),
"misses", c.pendingMisses.Load(),
"upstream_fetches", c.pendingUpstreamFetches.Load(),
"upstream_fetch_bytes", c.pendingUpstreamFetchBytes.Load(),
"transforms", c.pendingTransforms.Load(),
"error", countsErr,
)
}
return errors.Join(accessTimesErr, countsErr)
}
// pendingCountWriteLoop is the body of the goroutine
// StartPendingCountWrites starts. Once ctx is cancelled it starts no write
// and returns, but does not cut off a write under way then. Counts whose
// write fails stay pending, for the next write; access times whose write
// fails are dropped.
func (c *Cache) pendingCountWriteLoop(ctx context.Context) {
defer close(c.pendingCountsDone)
ticker := time.NewTicker(pendingWriteInterval)
defer ticker.Stop()
for {
select {
case <-ctx.Done():
return
case <-ticker.C:
}
// select picks at random when ctx is cancelled and a tick waits
// too.
if ctx.Err() != nil {
return
}
err := c.writePendingAccessTimes(context.WithoutCancel(ctx))
if err != nil {
c.log.Warn("failed to write access times", "error", err)
}
err = c.writePendingCounts(context.WithoutCancel(ctx))
if err != nil {
c.log.Warn("failed to write pending counts", "error", err)
}
}
}
// writePendingAccessTimes takes out the variants waiting in
// pendingVariantAccessTimes and the sources waiting in
// pendingSourceAccessTimes, and sets their last_accessed_at to now in one
// transaction, once for each however often it was used. Nothing else takes
// from those channels while it runs: only the goroutine
// StartPendingCountWrites starts calls it, or StopPendingCountWrites once
// that goroutine has returned.
func (c *Cache) writePendingAccessTimes(ctx context.Context) error {
variants := make(map[imagerequest.VariantKey]struct{})
for range len(c.pendingVariantAccessTimes) {
variants[<-c.pendingVariantAccessTimes] = struct{}{}
}
sources := make(map[imagerequest.SourceKey]struct{})
for range len(c.pendingSourceAccessTimes) {
sources[<-c.pendingSourceAccessTimes] = struct{}{}
}
accessTimes := len(variants) + len(sources)
if accessTimes == 0 {
return nil
}
tx, err := c.db.BeginTx(ctx, nil)
if err != nil {
return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
}
// Does nothing once the transaction is committed
defer func() { _ = tx.Rollback() }()
for cacheKey := range variants {
_, err = tx.ExecContext(ctx, `
UPDATE variant_content SET last_accessed_at = CURRENT_TIMESTAMP
WHERE cache_key = ?
`, string(cacheKey))
if err != nil {
return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
}
}
for sourceKey := range sources {
_, err = tx.ExecContext(ctx, `
UPDATE source_content SET last_accessed_at = CURRENT_TIMESTAMP
WHERE source_key = ?
`, string(sourceKey))
if err != nil {
return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
}
}
err = tx.Commit()
if err != nil {
return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
}
return nil
}
// writePendingCounts adds the pending counts to the cache_stats row in one
// UPDATE, then takes what it wrote out of them, leaving any added
// meanwhile. When the UPDATE fails, they all stay pending.
func (c *Cache) writePendingCounts(ctx context.Context) error {
c.pendingCountsWriteMutex.Lock()
defer c.pendingCountsWriteMutex.Unlock()
hits := c.pendingHits.Load()
misses := c.pendingMisses.Load()
upstreamFetches := c.pendingUpstreamFetches.Load()
upstreamFetchBytes := c.pendingUpstreamFetchBytes.Load()
transforms := c.pendingTransforms.Load()
if hits+misses+upstreamFetches+upstreamFetchBytes+transforms == 0 {
return nil
}
_, err := c.db.ExecContext(ctx, `
UPDATE cache_stats
SET hit_count = hit_count + ?,
miss_count = miss_count + ?,
upstream_fetch_count = upstream_fetch_count + ?,
upstream_fetch_bytes = upstream_fetch_bytes + ?,
transform_count = transform_count + ?,
last_updated_at = CURRENT_TIMESTAMP
WHERE id = 1
`, hits, misses, upstreamFetches, upstreamFetchBytes, transforms)
if err != nil {
return fmt.Errorf("failed to write pending counts: %w", err)
}
c.pendingHits.Add(-hits)
c.pendingMisses.Add(-misses)
c.pendingUpstreamFetches.Add(-upstreamFetches)
c.pendingUpstreamFetchBytes.Add(-upstreamFetchBytes)
c.pendingTransforms.Add(-transforms)
return nil
}
internal/imgcache/pendingcounts_internal_test.go
-431
View File
@@ -1,431 +0,0 @@
package imgcache
import (
"bytes"
"context"
"database/sql"
"errors"
"log/slog"
"strings"
"testing"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// pendingCountsWait is how long a test waits for the database's connection,
// for a count to reach the database, for a write to start waiting for the
// connection, for a request to return past its deadline, or for
// StopPendingCountWrites to return.
const pendingCountsWait = 5 * time.Second
// otherWritesWait is how long a test gives other writes, once one write waits
// for the database's connection, to start waiting for it too.
const otherWritesWait = 100 * time.Millisecond
// holdDatabase takes the one connection of cache's database, so that every
// other query waits for it, and returns the func that frees it.
func holdDatabase(t *testing.T, cache *Cache) func() {
t.Helper()
ctx, cancel := context.WithTimeout(t.Context(), pendingCountsWait)
defer cancel()
conn, err := cache.db.Conn(ctx)
if err != nil {
t.Fatalf("failed to take the database connection: %v", err)
}
return func() { _ = conn.Close() }
}
// waitForConnectionWaits waits until db.Stats().WaitCount, the number of
// times a caller has waited for a connection, reaches waits.
func waitForConnectionWaits(t *testing.T, db *sql.DB, waits int64) {
t.Helper()
deadline := time.Now().Add(pendingCountsWait)
for db.Stats().WaitCount < waits {
if time.Now().After(deadline) {
t.Fatalf("callers waited for the database connection %d times, want %d",
db.Stats().WaitCount, waits)
}
time.Sleep(10 * time.Millisecond)
}
}
// waitForCounters waits until the cache_stats row holds want.
func waitForCounters(t *testing.T, cache *Cache, want cacheStatsCounters) {
t.Helper()
deadline := time.Now().Add(pendingCountsWait)
for {
got := readCacheStatsCounters(t, cache)
if got == want {
return
}
if time.Now().After(deadline) {
t.Fatalf("counters = %+v, want %+v", got, want)
}
time.Sleep(10 * time.Millisecond)
}
}
// waitForPendingCountsWritten starts the goroutine that writes cache's
// pending counts, unless it is running, and waits until it has written them
// all, so that the database holds every count made so far. The goroutine is
// stopped when the test ends. The database is limited to one connection
// first: each connection to an in-memory SQLite database opens a new, empty
// one, so the goroutine must share the connection that holds the schema.
func waitForPendingCountsWritten(t *testing.T, cache *Cache) {
t.Helper()
if cache.pendingCountsCancel == nil {
cache.db.SetMaxOpenConns(1)
cache.StartPendingCountWrites()
t.Cleanup(func() { _ = cache.StopPendingCountWrites(context.Background()) })
}
deadline := time.Now().Add(pendingCountsWait)
for cache.pendingHits.Load()+cache.pendingMisses.Load()+
cache.pendingUpstreamFetches.Load()+cache.pendingUpstreamFetchBytes.Load()+
cache.pendingTransforms.Load() > 0 {
if time.Now().After(deadline) {
t.Fatal("the pending counts were not written")
}
time.Sleep(10 * time.Millisecond)
}
}
// TestService_Get_ReturnsByItsDeadlineWhileTheDatabaseIsBusy holds the
// database's one connection while a request whose fetch is held reaches its
// deadline. The request must return with the deadline's error while the
// connection is still held, as it waits for no database write past its
// deadline, and its miss must reach the database once the connection is free.
func TestService_Get_ReturnsByItsDeadlineWhileTheDatabaseIsBusy(t *testing.T) {
t.Parallel()
svc, fixtures, fetcher := setupHeldFetchService(t)
svc.cache.StartPendingCountWrites()
defer func() { _ = svc.cache.StopPendingCountWrites(t.Context()) }()
// Room for the request to reach its fetch on a busy host
const timeout = 2 * time.Second
ctx, cancel := context.WithTimeout(t.Context(), timeout)
defer cancel()
deadline, _ := ctx.Deadline()
results := startGet(ctx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
// The request has made its database reads by the time it fetches.
select {
case <-fetcher.started:
case <-time.After(timeout):
t.Fatal("request did not reach its fetch by its deadline")
}
releaseDatabase := holdDatabase(t, svc.cache)
defer releaseDatabase()
select {
case got := <-results:
t.Logf("Get() returned %v after its deadline, error = %v",
time.Since(deadline), got.err)
if !errors.Is(got.err, context.DeadlineExceeded) {
t.Errorf("Get() error = %v, want %v", got.err, context.DeadlineExceeded)
}
case <-time.After(time.Until(deadline) + pendingCountsWait):
t.Fatal("request did not return while the database was busy")
}
releaseDatabase()
waitForCounters(t, svc.cache, cacheStatsCounters{missCount: 1})
}
// TestIncrementStats_ManyCountsLeaveOneWriteWaiting holds the database's one
// connection while many misses are added to the pending counts, which the
// goroutine StartPendingCountWrites starts writes to the database. At most one
// write may then wait for the connection, and every miss must reach the
// database once it is free.
func TestIncrementStats_ManyCountsLeaveOneWriteWaiting(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
cache.StartPendingCountWrites()
defer func() { _ = cache.StopPendingCountWrites(t.Context()) }()
releaseDatabase := holdDatabase(t, cache)
defer releaseDatabase()
waitsBefore := cache.db.Stats().WaitCount
const misses = 20
for range misses {
cache.IncrementStats(false, 0)
}
// Once one write waits for the connection, any others start waiting too.
waitForConnectionWaits(t, cache.db, waitsBefore+1)
time.Sleep(otherWritesWait)
waits := cache.db.Stats().WaitCount - waitsBefore
t.Logf("%d writes waited for the database", waits)
if waits > 1 {
t.Errorf("%d writes waited for the database, want at most 1", waits)
}
releaseDatabase()
waitForCounters(t, cache, cacheStatsCounters{missCount: misses})
}
// TestStats_IncludesPendingCounts adds hits and misses to the pending counts,
// with no goroutine started to write them, and checks that Stats adds them to
// the database's counts before they are written.
func TestStats_IncludesPendingCounts(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
_, err := cache.db.ExecContext(t.Context(),
`UPDATE cache_stats SET hit_count = 75, miss_count = 25 WHERE id = 1`)
if err != nil {
t.Fatal(err)
}
cache.IncrementStats(true, 0)
cache.IncrementStats(true, 0)
cache.IncrementStats(false, 0)
stats, err := cache.Stats(t.Context())
if err != nil {
t.Fatalf("Stats() error = %v", err)
}
if stats.HitCount != 77 || stats.MissCount != 26 {
t.Errorf("HitCount = %d, MissCount = %d, want 77 and 26",
stats.HitCount, stats.MissCount)
}
want := cacheStatsCounters{hitCount: 75, missCount: 25}
if got := readCacheStatsCounters(t, cache); got != want {
t.Errorf("counters in the database = %+v, want %+v", got, want)
}
}
// TestStopPendingCountWrites_WritesPendingCounts holds the database's one
// connection while the goroutine that writes the pending counts waits for it,
// counts more, then stops that goroutine. The stop must leave the write under
// way to finish rather than cut it off, and once the connection is free it
// must write the counts that write left.
func TestStopPendingCountWrites_WritesPendingCounts(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
cache.StartPendingCountWrites()
defer func() { _ = cache.StopPendingCountWrites(t.Context()) }()
releaseDatabase := holdDatabase(t, cache)
defer releaseDatabase()
waitsBefore := cache.db.Stats().WaitCount
cache.IncrementStats(true, 0)
// The goroutine's write waits for the connection.
waitForConnectionWaits(t, cache.db, waitsBefore+1)
// Counted after that write read the pending counts
cache.IncrementStats(false, 0)
cache.IncrementUpstreamFetch(1024)
cache.IncrementTransformCount()
// The goroutine is told to finish here as well as by the stop, so that it
// is told before its write under way ends, however late the stop runs.
// The counts above then reach the database only through the stop's own
// write.
cache.pendingCountsCancel()
stopped := make(chan error, 1)
go func() {
stopped <- cache.StopPendingCountWrites(t.Context())
}()
// Had the stop cut off the write under way, its own write would wait for
// the connection too.
time.Sleep(otherWritesWait)
waits := cache.db.Stats().WaitCount - waitsBefore
t.Logf("%d writes waited for the database", waits)
if waits > 1 {
t.Errorf("%d writes waited for the database, want 1: "+
"the stop cut off the write under way", waits)
}
releaseDatabase()
select {
case err := <-stopped:
if err != nil {
t.Fatalf("StopPendingCountWrites() error = %v", err)
}
case <-time.After(pendingCountsWait):
t.Fatal("StopPendingCountWrites() did not return once the database was free")
}
want := cacheStatsCounters{1, 1, 1, 1024, 1}
if got := readCacheStatsCounters(t, cache); got != want {
t.Errorf("counters = %+v, want %+v", got, want)
}
}
// TestStopPendingCountWrites_ReturnsWhenItsContextEnds holds the database's
// one connection while the goroutine that writes the pending counts waits for
// it, then stops that goroutine with a context that ends first. The stop must
// return the context's error, and the write under way must still reach the
// database once the connection is free.
func TestStopPendingCountWrites_ReturnsWhenItsContextEnds(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
cache.StartPendingCountWrites()
defer func() { _ = cache.StopPendingCountWrites(t.Context()) }()
releaseDatabase := holdDatabase(t, cache)
defer releaseDatabase()
waitsBefore := cache.db.Stats().WaitCount
cache.IncrementStats(true, 0)
// The goroutine's write waits for the connection.
waitForConnectionWaits(t, cache.db, waitsBefore+1)
stopCtx, cancelStop := context.WithCancel(t.Context())
cancelStop()
stopped := make(chan error, 1)
go func() {
stopped <- cache.StopPendingCountWrites(stopCtx)
}()
select {
case err := <-stopped:
if !errors.Is(err, context.Canceled) {
t.Errorf("StopPendingCountWrites() error = %v, want %v",
err, context.Canceled)
}
case <-time.After(pendingCountsWait):
t.Fatal("StopPendingCountWrites() did not return once its context ended")
}
releaseDatabase()
waitForCounters(t, cache, cacheStatsCounters{hitCount: 1})
}
// TestLookupSource_HandsAccessTimeToTheBackgroundWriter finds a cached source
// whose access time is an hour old. LookupSource must not write the access
// time itself but hand it over to be written, and StopPendingCountWrites must
// then write it.
func TestLookupSource_HandsAccessTimeToTheBackgroundWriter(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
key := storeEvictionTestSource(t, cache, "example.com", "/photo.jpg",
[]byte("source bytes"))
anHourAgo := time.Now().Add(-time.Hour)
setSourceLastAccessed(t, cache, key, anHourAgo)
touchedQuery := `
SELECT COUNT(*) FROM source_content
WHERE source_key = ? AND last_accessed_at > ?
`
anHourAgoInDatabase := anHourAgo.UTC().Format(sqliteTimestampFormat)
found, err := cache.LookupSource(t.Context(), &imagerequest.Request{
Source: imagerequest.Source{Host: "example.com", Path: "/photo.jpg"},
})
if err != nil || found != key {
t.Fatalf("LookupSource() = %q, %v; want %q", found, err, key)
}
if countRows(t, cache, touchedQuery, string(key), anHourAgoInDatabase) != 0 {
t.Error("LookupSource wrote the source's access time itself")
}
if waiting := len(cache.pendingSourceAccessTimes); waiting != 1 {
t.Errorf("%d access times of sources wait to be written, want 1", waiting)
}
err = cache.StopPendingCountWrites(t.Context())
if err != nil {
t.Fatalf("StopPendingCountWrites() error = %v", err)
}
if countRows(t, cache, touchedQuery, string(key), anHourAgoInDatabase) != 1 {
t.Error("the source's access time was not written")
}
}
// TestStopPendingCountWrites_LogsWhatWasNotWritten makes the write of the
// access times fail at shutdown, by dropping the table they are written to,
// while a hit count is written. The stop must return an error and log that
// access times were not written, and must not log the counts as not written.
func TestStopPendingCountWrites_LogsWhatWasNotWritten(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
var logs bytes.Buffer
cache.log = slog.New(slog.NewJSONHandler(&logs, nil))
cache.touchVariant(testVariantKeyOne)
cache.IncrementStats(true, 0)
_, err := cache.db.ExecContext(t.Context(), `DROP TABLE variant_content`)
if err != nil {
t.Fatalf("dropping variant_content: %v", err)
}
err = cache.StopPendingCountWrites(t.Context())
t.Logf("StopPendingCountWrites() error = %v; logged:\n%s", err, logs.String())
if err == nil {
t.Error("StopPendingCountWrites() error = nil, want the access times' error")
}
if !strings.Contains(logs.String(), "access times not written at shutdown") {
t.Error("the access times not written were not logged")
}
if strings.Contains(logs.String(), "counts not written at shutdown") {
t.Error("the counts, which were written, were logged as not written")
}
if got := readCacheStatsCounters(t, cache); got.hitCount != 1 {
t.Errorf("hit count in the database = %d, want 1", got.hitCount)
}
}
internal/imgcache/service.go
+145 -148
View File
@@ -9,7 +9,6 @@ import (
"log/slog"
"net/url"
"runtime/debug"
"strings"
"time"
"github.com/dustin/go-humanize"
@@ -19,7 +18,6 @@ import (
"sneak.berlin/go/pixa/internal/allowlist"
"sneak.berlin/go/pixa/internal/httpfetcher"
"sneak.berlin/go/pixa/internal/imageprocessor"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/magic"
"sneak.berlin/go/pixa/internal/signature"
)
@@ -54,7 +52,7 @@ type ServiceConfig struct {
// Allowlist is the list of hosts that don't require signatures
Allowlist []string
// MaxConcurrentProcessing is the most images processed at once; zero
// uses the image processor's default, half the CPUs
// uses the image processor's default, one per CPU
MaxConcurrentProcessing int
// Logger for logging
Logger *slog.Logger
@@ -102,8 +100,8 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
allowHTTP = cfg.FetcherConfig.AllowHTTP
}
// JPEG XL is the default output format, so pixad does not start
// without it.
// JPEG XL is to become the default output format, so pixad does not
// start without it.
err := imageprocessor.CheckJPEGXLSupport()
if err != nil {
return nil, err
@@ -130,47 +128,50 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
// ErrNegativeCached is returned when a URL is in the negative cache (recently failed).
var ErrNegativeCached = errors.New("request is in negative cache (recently failed)")
// ErrProcessingTimedOut is returned when processing an image stopped because
// the downstream_timeout of the request doing it ended, to that request and to
// every request that waited for its image.
var ErrProcessingTimedOut = errors.New(
"image processing stopped at the deadline of the request doing it")
// Get retrieves a processed image, fetching and processing if necessary.
// While its source URL is in the negative cache, a cached variant is still
// served and a variant not in the cache is still made from a cached source;
// only a request that needs the source fetched is refused.
//
// A cache hit opens the variant file and makes no database call: its access
// time and its hit count are handed to the goroutine that
// StartPendingCountWrites starts, without waiting for it. A variant file
// that cannot be served, such as one whose first bytes are not those of an
// output format, is a miss, and the variant is made again.
func (s *Service) Get(
ctx context.Context, req *imagerequest.Request,
) (*ImageResponse, error) {
func (s *Service) Get(ctx context.Context, req *ImageRequest) (*ImageResponse, error) {
// Propagate AllowHTTP setting to the request
req.AllowHTTP = s.allowHTTP
cacheKey := imagerequest.CacheKey(req)
reader, size, contentType, err := s.cache.GetVariant(cacheKey)
if err == nil {
s.cache.touchVariant(cacheKey)
s.cache.IncrementStats(true, 0)
return &ImageResponse{
Content: reader,
ContentLength: size,
ContentType: contentType,
CacheStatus: CacheHit,
ETag: formatETag(cacheKey),
}, nil
// Check negative cache first - skip fetching for recently-failed URLs
negHit, err := s.cache.checkNegativeCache(ctx, req)
if err != nil {
s.log.Warn("negative cache check failed", "error", err)
}
if !errors.Is(err, ErrNotFound) {
s.log.Warn("cached variant not served, making it again",
"cache_key", cacheKey, "error", err)
if negHit {
s.log.Debug("negative cache hit",
"host", req.SourceHost,
"path", req.SourcePath,
)
return nil, fmt.Errorf("%w: %w", httpfetcher.ErrUpstreamError, ErrNegativeCached)
}
// Check variant cache first (disk only, no DB)
result, err := s.cache.Lookup(ctx, req)
if err != nil {
s.log.Warn("cache lookup failed", "error", err)
}
// Cache hit - serve directly from disk
if result != nil && result.Hit {
reader, size, contentType, err := s.cache.GetVariant(result.CacheKey)
if err != nil {
s.log.Error("failed to get cached variant", "key", result.CacheKey, "error", err)
// Fall through to re-process
} else {
// Counted also when the request context has ended meanwhile
s.cache.IncrementStats(context.WithoutCancel(ctx), true, 0)
return &ImageResponse{
Content: reader,
ContentLength: size,
ContentType: contentType,
CacheStatus: CacheHit,
ETag: formatETag(result.CacheKey),
}, nil
}
}
// Cache miss - get the variant, processed once for all the requests that
@@ -178,7 +179,7 @@ func (s *Service) Get(
// failed or the request context has ended meanwhile
response, err := s.processOrWait(ctx, req)
s.cache.IncrementStats(false, 0)
s.cache.IncrementStats(context.WithoutCancel(ctx), false, 0)
if err != nil {
return nil, err
@@ -190,7 +191,7 @@ func (s *Service) Get(
}
// Warm pre-fetches and caches an image without returning it.
func (s *Service) Warm(ctx context.Context, req *imagerequest.Request) error {
func (s *Service) Warm(ctx context.Context, req *ImageRequest) error {
_, err := s.Get(ctx, req)
return err
@@ -208,7 +209,7 @@ func (s *Service) WaitForProcessing(ctx context.Context) int {
}
// ValidateRequest validates the request signature if required.
func (s *Service) ValidateRequest(req *imagerequest.Request) error {
func (s *Service) ValidateRequest(req *ImageRequest) error {
// Check if host is allowed (no signature required)
sourceURL := req.SourceURL()
@@ -217,21 +218,12 @@ func (s *Service) ValidateRequest(req *imagerequest.Request) error {
return fmt.Errorf("invalid source URL: %w", err)
}
// An allowlist entry names no port, so a host followed by ":", with or
// without a port, needs a signature. The port is read from the parsed
// URL, as the fetcher reads it: in an IPv6 address written without
// brackets, such as 2001:db8::1:8443, it is what follows the last ":".
// This is checked here and not in allowlist.IsAllowed, which also matches
// referer_blocklist, where a Referer must be blocked whatever its port.
hostHasPort := parsedURL.Port() != "" ||
strings.HasSuffix(parsedURL.Host, ":")
if !hostHasPort && s.allowlist.IsAllowed(parsedURL) {
if s.allowlist.IsAllowed(parsedURL) {
return nil
}
// Signature required for non-allowed hosts
return s.signer.Verify(req)
return s.signer.Verify(signatureRequest(req))
}
// GenerateSignedURL generates a signed URL for the given request. The URL
@@ -240,22 +232,26 @@ func (s *Service) ValidateRequest(req *imagerequest.Request) error {
// set to 85 or cover, the values the route uses when a URL has no q or fit.
func (s *Service) GenerateSignedURL(
baseURL string,
req *imagerequest.Request,
req *ImageRequest,
ttl time.Duration,
) (string, error) {
if req.Transform.Quality == 0 {
req.Transform.Quality = 85
if req.Quality == 0 {
req.Quality = 85
}
if req.Transform.FitMode == "" {
req.Transform.FitMode = imagerequest.FitCover
if req.FitMode == "" {
req.FitMode = FitCover
}
// Sets the request's Expires and Signature
path, sig, exp := s.signer.GenerateSignedURL(req, ttl)
sigReq := signatureRequest(req)
path, sig, exp := s.signer.GenerateSignedURL(sigReq, ttl)
// Propagate the generated signature and expiration back onto the request.
req.Expires = sigReq.Expires
req.Signature = sigReq.Signature
return fmt.Sprintf("%s%s?sig=%s&exp=%d&q=%d&fit=%s",
baseURL, path, sig, exp, req.Transform.Quality, req.Transform.FitMode), nil
baseURL, path, sig, exp, req.Quality, req.FitMode), nil
}
// errPanicked is returned when processing a variant panicked.
@@ -268,14 +264,14 @@ var errPanicked = errors.New("panic while processing image")
// the first request's cancellation, so the others are still served if that
// client goes away, but keeps its deadline.
func (s *Service) processOrWait(
ctx context.Context, req *imagerequest.Request,
ctx context.Context, req *ImageRequest,
) (*ImageResponse, error) {
// A request that has already ended starts no processing
if ctx.Err() != nil {
return nil, ctx.Err()
}
cacheKey := imagerequest.CacheKey(req)
cacheKey := CacheKey(req)
// Closed when this request's own function runs, which singleflight does
// only when no other request is processing the variant
@@ -293,7 +289,7 @@ func (s *Service) processOrWait(
recovered := recover()
if recovered != nil {
s.log.Error("panic while processing image",
"host", req.Source.Host, "path", req.Source.Path,
"host", req.SourceHost, "path", req.SourcePath,
"panic", recovered, "stack", string(debug.Stack()))
if hub := sentry.GetHubFromContext(ctx); hub != nil {
@@ -304,8 +300,14 @@ func (s *Service) processOrWait(
}
}()
processingCtx, cancel := withoutCancelKeepingDeadline(ctx)
defer cancel()
processingCtx := context.WithoutCancel(ctx)
if deadline, ok := ctx.Deadline(); ok {
var cancel context.CancelFunc
processingCtx, cancel = context.WithDeadline(processingCtx, deadline)
defer cancel()
}
return s.processFromSourceOrFetch(processingCtx, req, cacheKey)
})
@@ -342,27 +344,13 @@ func (s *Service) processOrWait(
}, nil
}
// withoutCancelKeepingDeadline returns ctx without its cancellation but with
// its deadline, if it has one, and the func that releases the returned
// context.
func withoutCancelKeepingDeadline(
ctx context.Context,
) (context.Context, context.CancelFunc) {
deadline, hasDeadline := ctx.Deadline()
if !hasDeadline {
return context.WithoutCancel(ctx), func() {}
}
return context.WithDeadline(context.WithoutCancel(ctx), deadline)
}
// loadCachedSource opens source content from cache, without reading it, and
// returns it with its size; nil if the cached data is unavailable, empty or
// exceeds maxResponseSize.
func (s *Service) loadCachedSource(
sourceKey imagerequest.SourceKey,
contentHash ContentHash,
) (io.ReadCloser, int64) {
reader, size, err := s.cache.GetSourceContent(sourceKey)
reader, size, err := s.cache.GetSourceContent(contentHash)
if err != nil {
s.log.Warn("failed to load cached source, fetching", "error", err)
@@ -373,7 +361,7 @@ func (s *Service) loadCachedSource(
_ = reader.Close()
s.log.Warn("cached source exceeds max response size, discarding",
"source_key", sourceKey,
"hash", contentHash,
"max_bytes", s.maxResponseSize,
)
@@ -393,11 +381,11 @@ func (s *Service) loadCachedSource(
// if available.
func (s *Service) processFromSourceOrFetch(
ctx context.Context,
req *imagerequest.Request,
cacheKey imagerequest.VariantKey,
req *ImageRequest,
cacheKey VariantKey,
) (*processedVariant, error) {
// Check if we have cached source content
sourceKey, err := s.cache.LookupSource(ctx, req)
contentHash, _, err := s.cache.LookupSource(ctx, req)
if err != nil {
s.log.Warn("source lookup failed", "error", err)
}
@@ -407,9 +395,9 @@ func (s *Service) processFromSourceOrFetch(
sourceSize int64
)
if sourceKey != "" {
s.log.Debug("using cached source", "source_key", sourceKey)
source, sourceSize = s.loadCachedSource(sourceKey)
if contentHash != "" {
s.log.Debug("using cached source", "hash", contentHash)
source, sourceSize = s.loadCachedSource(contentHash)
}
// Fetch from upstream if we don't have source data or it's empty
@@ -427,28 +415,12 @@ func (s *Service) processFromSourceOrFetch(
// fetchAndProcess fetches from upstream, processes, and caches the result.
// It counts the fetch with the bytes read from upstream, including when
// reading the response or a later step fails. It fetches nothing while the
// source URL is in the negative cache.
// reading the response or a later step fails.
func (s *Service) fetchAndProcess(
ctx context.Context,
req *imagerequest.Request,
cacheKey imagerequest.VariantKey,
req *ImageRequest,
cacheKey VariantKey,
) (*processedVariant, error) {
// Check negative cache - skip fetching for recently-failed URLs
negHit, err := s.cache.checkNegativeCache(ctx, req)
if err != nil {
s.log.Warn("negative cache check failed", "error", err)
}
if negHit {
s.log.Debug("negative cache hit",
"host", req.Source.Host,
"path", req.Source.Path,
)
return nil, fmt.Errorf("%w: %w", httpfetcher.ErrUpstreamError, ErrNegativeCached)
}
// Fetch from upstream
sourceURL := req.SourceURL()
@@ -458,7 +430,13 @@ func (s *Service) fetchAndProcess(
if err != nil {
// Store negative cache for certain errors
if isNegativeCacheable(err) {
s.storeNegative(ctx, req)
statusCode := extractStatusCode(err)
storeErr := s.cache.StoreNegative(ctx, req, statusCode, err.Error())
if storeErr != nil {
s.log.Warn("failed to store negative cache entry",
"host", req.SourceHost, "path", req.SourcePath, "error", storeErr)
}
}
return nil, fmt.Errorf("upstream fetch failed: %w", err)
@@ -475,7 +453,7 @@ func (s *Service) fetchAndProcess(
fetchBytes := int64(len(sourceData))
// Counted also when the request context has ended meanwhile
s.cache.IncrementUpstreamFetch(fetchBytes)
s.cache.IncrementUpstreamFetch(context.WithoutCancel(ctx), fetchBytes)
if err != nil {
return nil, fmt.Errorf("failed to read upstream response: %w", err)
@@ -493,8 +471,8 @@ func (s *Service) fetchAndProcess(
// Log upstream fetch details
s.log.Info("upstream fetched",
"request_id", middleware.GetReqID(ctx),
"host", req.Source.Host,
"path", req.Source.Path,
"host", req.SourceHost,
"path", req.SourcePath,
"bytes", fetchBytes,
"fetch_ms", fetchResult.FetchDurationMs,
"rate", downloadRate,
@@ -504,21 +482,14 @@ func (s *Service) fetchAndProcess(
"cipher", fetchResult.TLSCipherSuite,
)
// Validate magic bytes match content type. A body that does not is the
// upstream's error, so it gets a negative cache entry, as an upstream
// error status does.
// Validate magic bytes match content type
err = magic.ValidateMagicBytes(sourceData, fetchResult.ContentType)
if err != nil {
s.log.Warn("source refused", "request_id", middleware.GetReqID(ctx),
"host", req.Source.Host, "path", req.Source.Path,
"content_type", fetchResult.ContentType, "error", err)
s.storeNegative(ctx, req)
return nil, fmt.Errorf("content validation failed: %w", err)
}
// Store source content
_, err = s.cache.StoreSource(ctx, req, bytes.NewReader(sourceData))
_, err = s.cache.StoreSource(ctx, req, bytes.NewReader(sourceData), fetchResult)
if err != nil {
s.log.Warn("failed to store source content", "error", err)
// Continue even if caching fails
@@ -529,17 +500,6 @@ func (s *Service) fetchAndProcess(
)
}
// storeNegative stores a negative cache entry for req's source, whose fetch
// failed, so the source is not fetched again until the entry expires. A
// failure to store the entry is only logged.
func (s *Service) storeNegative(ctx context.Context, req *imagerequest.Request) {
err := s.cache.StoreNegative(ctx, req)
if err != nil {
s.log.Warn("failed to store negative cache entry",
"host", req.Source.Host, "path", req.Source.Path, "error", err)
}
}
// processedVariant is a variant as processAndStore made it. Each request that
// shared its processing serves it through a reader of its own.
type processedVariant struct {
@@ -552,21 +512,22 @@ type processedVariant struct {
// result.
func (s *Service) processAndStore(
ctx context.Context,
req *imagerequest.Request,
cacheKey imagerequest.VariantKey,
req *ImageRequest,
cacheKey VariantKey,
source io.Reader,
fetchBytes int64,
) (*processedVariant, error) {
// Process the image
processStart := time.Now()
// ctx has the deadline of the request doing the processing, which can
// end while a request waiting for its image has time left
processResult, err := s.processor.Process(ctx, source, &req.Transform)
if errors.Is(err, context.DeadlineExceeded) {
return nil, fmt.Errorf("%w: %w", ErrProcessingTimedOut, err)
processReq := &imageprocessor.Request{
Size: imageprocessor.Size{Width: req.Size.Width, Height: req.Size.Height},
Format: imageprocessor.Format(req.Format),
Quality: req.Quality,
FitMode: imageprocessor.FitMode(req.FitMode),
}
processResult, err := s.processor.Process(ctx, source, processReq)
if err != nil {
return nil, fmt.Errorf("image processing failed: %w", err)
}
@@ -574,7 +535,7 @@ func (s *Service) processAndStore(
processDuration := time.Since(processStart)
// Counted also when the request context has ended meanwhile
s.cache.IncrementTransformCount()
s.cache.IncrementTransformCount(context.WithoutCancel(ctx))
// Read processed content
processedData, err := io.ReadAll(processResult.Content)
@@ -595,10 +556,10 @@ func (s *Service) processAndStore(
s.log.Info("image converted",
"request_id", middleware.GetReqID(ctx),
"host", req.Source.Host,
"path", req.Source.Path,
"host", req.SourceHost,
"path", req.SourcePath,
"src_format", processResult.InputFormat,
"dst_format", req.Transform.Format,
"dst_format", req.Format,
"src_bytes", fetchBytes,
"dst_bytes", outputSize,
"src_dimensions", fmt.Sprintf("%dx%d",
@@ -607,12 +568,14 @@ func (s *Service) processAndStore(
processResult.Width, processResult.Height),
"size_ratio", fmt.Sprintf("%.1f%%", sizePercent),
"convert_ms", processDuration.Milliseconds(),
"quality", req.Transform.Quality,
"fit", req.Transform.FitMode,
"quality", req.Quality,
"fit", req.FitMode,
)
// Store variant to cache
err = s.cache.StoreVariant(ctx, cacheKey, bytes.NewReader(processedData))
err = s.cache.StoreVariant(
ctx, cacheKey, bytes.NewReader(processedData), processResult.ContentType,
)
if err != nil {
s.log.Warn("failed to store variant", "error", err)
// Continue even if caching fails
@@ -625,16 +588,50 @@ func (s *Service) processAndStore(
}, nil
}
// signatureRequest projects an ImageRequest onto the standalone
// signature.Request type used by the signature package. This keeps the
// import edge one-way: imgcache depends on signature, never the reverse.
func signatureRequest(req *ImageRequest) *signature.Request {
return &signature.Request{
SourceHost: req.SourceHost,
SourcePath: req.SourcePath,
SourceQuery: req.SourceQuery,
Width: req.Size.Width,
Height: req.Size.Height,
Format: string(req.Format),
Quality: req.Quality,
FitMode: string(req.FitMode),
Signature: req.Signature,
Expires: req.Expires,
}
}
// HTTP status codes for error responses.
const (
httpStatusBadGateway = 502
httpStatusInternalError = 500
)
// isNegativeCacheable returns true if the error should be cached.
func isNegativeCacheable(err error) bool {
return errors.Is(err, httpfetcher.ErrUpstreamError)
}
// extractStatusCode extracts HTTP status code from error message.
func extractStatusCode(err error) int {
// Default to 502 Bad Gateway for upstream errors
if errors.Is(err, httpfetcher.ErrUpstreamError) {
return httpStatusBadGateway
}
return httpStatusInternalError
}
// etagHashLength is the number of hash characters to use for ETags.
const etagHashLength = 16
// formatETag formats a VariantKey as a quoted ETag value.
func formatETag(key imagerequest.VariantKey) string {
func formatETag(key VariantKey) string {
hash := string(key)
// Use first 16 characters of hash for a shorter but still unique ETag
if len(hash) > etagHashLength {
internal/imgcache/service_internal_test.go
+141 -379
View File
@@ -3,11 +3,9 @@ package imgcache
import (
"context"
"io"
"os"
"testing"
"time"
"sneak.berlin/go/pixa/internal/imagerequest"
"sneak.berlin/go/pixa/internal/magic"
"sneak.berlin/go/pixa/internal/signature"
)
@@ -25,17 +23,13 @@ func TestService_Get_AllowlistedHost(t *testing.T) {
svc, fixtures := SetupTestService(t)
ctx := context.Background()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
resp, err := svc.Get(ctx, req)
@@ -65,17 +59,13 @@ func TestService_Get_NonAllowlistedHost_NoSignature(t *testing.T) {
svc, fixtures := SetupTestService(t, WithSigningKey("test-key"))
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.OtherHost,
Path: testPathUpload,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.OtherHost,
SourcePath: testPathUpload,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
// Should fail validation - not allowlisted and no signature
@@ -92,23 +82,19 @@ func TestService_Get_NonAllowlistedHost_ValidSignature(t *testing.T) {
svc, fixtures := SetupTestService(t, WithSigningKey(signingKey))
ctx := context.Background()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.OtherHost,
Path: testPathUpload,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.OtherHost,
SourcePath: testPathUpload,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
// Generate a valid signature
signer := signature.New(signingKey)
req.Expires = time.Now().Add(time.Hour)
req.Signature = signer.Sign(req)
req.Signature = signer.Sign(signatureRequest(req))
// Should pass validation
err := svc.ValidateRequest(req)
@@ -140,23 +126,19 @@ func TestService_Get_NonAllowlistedHost_ExpiredSignature(t *testing.T) {
signingKey := testSigningKey
svc, fixtures := SetupTestService(t, WithSigningKey(signingKey))
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.OtherHost,
Path: testPathUpload,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.OtherHost,
SourcePath: testPathUpload,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
// Generate an expired signature
signer := signature.New(signingKey)
req.Expires = time.Now().Add(-time.Hour) // Already expired
req.Signature = signer.Sign(req)
req.Signature = signer.Sign(signatureRequest(req))
// Should fail validation
err := svc.ValidateRequest(req)
@@ -171,17 +153,13 @@ func TestService_Get_NonAllowlistedHost_InvalidSignature(t *testing.T) {
signingKey := testSigningKey
svc, fixtures := SetupTestService(t, WithSigningKey(signingKey))
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.OtherHost,
Path: testPathUpload,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.OtherHost,
SourcePath: testPathUpload,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
// Set an invalid signature
@@ -211,20 +189,16 @@ func TestService_ValidateRequest_SignatureExactHostMatch(t *testing.T) {
signer := signature.New(signingKey)
// Sign a request for "cdn.example.com"
signedReq := &imagerequest.Request{
Source: imagerequest.Source{
Host: testHostCDN,
Path: testPathCat,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
Expires: time.Now().Add(time.Hour),
signedReq := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: testPathCat,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
Expires: time.Now().Add(time.Hour),
}
signedReq.Signature = signer.Sign(signedReq)
signedReq.Signature = signer.Sign(signatureRequest(signedReq))
// The original request should pass validation
t.Run("exact host passes", func(t *testing.T) {
@@ -252,121 +226,23 @@ func TestService_ValidateRequest_SignatureExactHostMatch(t *testing.T) {
t.Run(tt.name+" rejected", func(t *testing.T) {
t.Parallel()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: tt.host,
Path: signedReq.Source.Path,
Query: signedReq.Source.Query,
},
Transform: signedReq.Transform,
Expires: signedReq.Expires,
Signature: signedReq.Signature,
req := &ImageRequest{
SourceHost: tt.host,
SourcePath: signedReq.SourcePath,
SourceQuery: signedReq.SourceQuery,
Size: signedReq.Size,
Format: signedReq.Format,
Quality: signedReq.Quality,
FitMode: signedReq.FitMode,
Expires: signedReq.Expires,
Signature: signedReq.Signature,
}
err := svc.ValidateRequest(req)
if err == nil {
t.Errorf(
"ValidateRequest() should reject signature for host %q (signed for %q)",
tt.host, signedReq.Source.Host)
}
})
}
}
// TestService_ValidateRequest_HostWithPortNeedsSignature verifies that a host
// followed by a port, or by a colon with no port, matches no allowlist entry,
// so that a request for it without a signature is refused, while the same
// host with no port is allowlisted.
func TestService_ValidateRequest_HostWithPortNeedsSignature(t *testing.T) {
t.Parallel()
svc, _ := SetupTestService(t,
WithSigningKey(testSigningKey),
WithAllowlist(testHostCDN, "203.0.113.5", "2001:db8::1"),
)
tests := []struct {
host string
allowlisted bool
}{
{testHostCDN, true},
{"cdn.example.com:8443", false},
{"cdn.example.com:443", false},
{"cdn.example.com:", false},
{"203.0.113.5", true},
{"203.0.113.5:8080", false},
{"[2001:db8::1]", true},
{"[2001:db8::1]:8443", false},
}
for _, tt := range tests {
t.Run(tt.host, func(t *testing.T) {
t.Parallel()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: tt.host,
Path: testPathCat,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
}
err := svc.ValidateRequest(req)
t.Logf("ValidateRequest() for host %q with no signature: %v",
tt.host, err)
if allowlisted := err == nil; allowlisted != tt.allowlisted {
t.Errorf("host %q served without a signature = %v, want %v",
tt.host, allowlisted, tt.allowlisted)
}
})
}
}
// TestService_ValidateRequest_UnbracketedIPv6PortNeedsSignature verifies that
// an allowlisted IPv6 address written without brackets and followed by a
// port, or by a colon with no port, needs a signature. Go's URL parser, which
// the fetcher uses, reads 2001:db8::1:8443 as the host 2001:db8::1 with the
// port 8443.
func TestService_ValidateRequest_UnbracketedIPv6PortNeedsSignature(
t *testing.T,
) {
t.Parallel()
svc, _ := SetupTestService(t,
WithSigningKey(testSigningKey),
WithAllowlist("2001:db8::1"),
)
for _, host := range []string{"2001:db8::1:8443", "2001:db8::1:"} {
t.Run(host, func(t *testing.T) {
t.Parallel()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: host,
Path: testPathCat,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
}
err := svc.ValidateRequest(req)
t.Logf("ValidateRequest() for host %q with no signature: %v",
host, err)
if err == nil {
t.Errorf("host %q served without a signature, want refused",
host)
tt.host, signedReq.SourceHost)
}
})
}
@@ -378,9 +254,14 @@ func TestService_Get_InvalidFile(t *testing.T) {
svc, fixtures := SetupTestService(t)
ctx := context.Background()
req := photoVariant(fixtures, 85, imagerequest.FitCover)
req.Source.Path = "/images/fake.jpg"
req.Transform.Size = imagerequest.Size{Width: 50, Height: 50}
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: "/images/fake.jpg",
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
// Should fail because magic bytes don't match
_, err := svc.Get(ctx, req)
@@ -395,9 +276,14 @@ func TestService_Get_NotFound(t *testing.T) {
svc, fixtures := SetupTestService(t)
ctx := context.Background()
req := photoVariant(fixtures, 85, imagerequest.FitCover)
req.Source.Path = "/images/nonexistent.jpg"
req.Transform.Size = imagerequest.Size{Width: 50, Height: 50}
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: "/images/nonexistent.jpg",
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
_, err := svc.Get(ctx, req)
if err == nil {
@@ -414,25 +300,25 @@ func TestService_Get_FormatConversion(t *testing.T) {
tests := []struct {
name string
sourcePath string
outFormat imagerequest.Format
outFormat ImageFormat
wantMIME string
}{
{
name: "JPEG to PNG",
sourcePath: testPathPhoto,
outFormat: imagerequest.FormatPNG,
outFormat: FormatPNG,
wantMIME: "image/png",
},
{
name: "PNG to JPEG",
sourcePath: "/images/logo.png",
outFormat: imagerequest.FormatJPEG,
outFormat: FormatJPEG,
wantMIME: testContentTypeJPEG,
},
{
name: "GIF to PNG",
sourcePath: "/images/animation.gif",
outFormat: imagerequest.FormatPNG,
outFormat: FormatPNG,
wantMIME: "image/png",
},
}
@@ -441,12 +327,13 @@ func TestService_Get_FormatConversion(t *testing.T) {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
req := &imagerequest.Request{
Source: imagerequest.Source{Host: fixtures.GoodHost, Path: tt.sourcePath},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: tt.outFormat, Quality: 85, FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: tt.sourcePath,
Size: Size{Width: 50, Height: 50},
Format: tt.outFormat,
Quality: 85,
FitMode: FitCover,
}
resp, err := svc.Get(ctx, req)
@@ -494,17 +381,13 @@ func TestService_Get_Caching(t *testing.T) {
svc, fixtures := SetupTestService(t)
ctx := context.Background()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
// First request - should be a cache miss
@@ -547,99 +430,6 @@ func TestService_Get_Caching(t *testing.T) {
}
}
// TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo caches a source and
// a variant of it and sets back two days every time pixa stored for them.
// For the source: last_accessed_at in source_content, and the access and
// modification times of its file. For the variant: last_accessed_at in
// variant_content, and the access and modification times of its file. It
// then checks that the variant is still served from the cache and that a new
// variant is made from the cached source without fetching it again.
//
// Left at the present: the files' status change and birth times, which a
// program cannot set, and the times of the directories holding the files,
// which other entries share.
func TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo(t *testing.T) {
t.Parallel()
svc, fixtures := SetupTestService(t)
variant := photoVariant(fixtures, 85, imagerequest.FitCover)
resp, err := svc.Get(t.Context(), variant)
if err != nil {
t.Fatalf("Get() first request error = %v", err)
}
_ = resp.Content.Close()
twoDaysAgo := time.Now().AddDate(0, 0, -2)
backdateSource(t, svc.cache, variant, twoDaysAgo)
backdateVariant(t, svc.cache, variant, twoDaysAgo)
resp, err = svc.Get(t.Context(), variant)
if err != nil {
t.Fatalf("Get() of the cached variant error = %v", err)
}
_ = resp.Content.Close()
if resp.CacheStatus != CacheHit {
t.Errorf("cached variant CacheStatus = %q, want %q",
resp.CacheStatus, CacheHit)
}
// Another quality is a new variant, made from the cached source
resp, err = svc.Get(t.Context(), photoVariant(fixtures, 40, imagerequest.FitCover))
if err != nil {
t.Fatalf("Get() of a new variant error = %v", err)
}
_ = resp.Content.Close()
waitForPendingCountsWritten(t, svc.cache)
fetches := readCacheStatsCounters(t, svc.cache).upstreamFetchCount
if fetches != 1 {
t.Errorf("upstream fetches = %d, want 1", fetches)
}
}
// backdateSource sets every time pixa stored for req's cached source to when,
// as listed on TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo.
func backdateSource(
t *testing.T, cache *Cache, req *imagerequest.Request, when time.Time,
) {
t.Helper()
key := req.Source.Key()
setSourceLastAccessed(t, cache, key, when)
path := cache.srcContent.keyToPath(key)
err := os.Chtimes(path, when, when)
if err != nil {
t.Fatalf("setting back the times of %s: %v", path, err)
}
}
// backdateVariant sets every time pixa stored for the cached variant req asks
// for to when, as listed on
// TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo.
func backdateVariant(
t *testing.T, cache *Cache, req *imagerequest.Request, when time.Time,
) {
t.Helper()
key := imagerequest.CacheKey(req)
path := cache.variants.keyToPath(key)
setVariantLastAccessed(t, cache, key, when)
err := os.Chtimes(path, when, when)
if err != nil {
t.Fatalf("setting back the times of %s: %v", path, err)
}
}
func TestService_Get_DifferentSizes(t *testing.T) {
t.Parallel()
@@ -647,7 +437,7 @@ func TestService_Get_DifferentSizes(t *testing.T) {
ctx := context.Background()
// Request same image at different sizes
sizes := []imagerequest.Size{
sizes := []Size{
{Width: 25, Height: 25},
{Width: 50, Height: 50},
{Width: 75, Height: 75},
@@ -656,17 +446,13 @@ func TestService_Get_DifferentSizes(t *testing.T) {
responses := make([][]byte, 0, len(sizes))
for _, size := range sizes {
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: size,
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: size,
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
resp, err := svc.Get(ctx, req)
@@ -700,17 +486,13 @@ func TestService_ValidateRequest_NoSigningKey(t *testing.T) {
// Service with no signing key - all non-allowlisted requests should fail
svc, fixtures := SetupTestService(t, WithNoAllowlist())
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.OtherHost,
Path: testPathUpload,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.OtherHost,
SourcePath: testPathUpload,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
err := svc.ValidateRequest(req)
@@ -729,17 +511,13 @@ func TestService_Get_ContextCancellation(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
cancel() // Cancel immediately
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
_, err := svc.Get(ctx, req)
@@ -754,17 +532,13 @@ func TestService_Get_ReturnsETag(t *testing.T) {
svc, fixtures := SetupTestService(t)
ctx := context.Background()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
resp, err := svc.Get(ctx, req)
@@ -791,17 +565,13 @@ func TestService_Get_ETagConsistency(t *testing.T) {
svc, fixtures := SetupTestService(t)
ctx := context.Background()
req := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
// First request
@@ -837,30 +607,22 @@ func TestService_Get_DifferentETagsForDifferentContent(t *testing.T) {
ctx := context.Background()
// Request same image at different sizes - should get different ETags
req1 := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 25, Height: 25},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req1 := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 25, Height: 25},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
req2 := &imagerequest.Request{
Source: imagerequest.Source{
Host: fixtures.GoodHost,
Path: testPathPhoto,
},
Transform: imagerequest.Transform{
Size: imagerequest.Size{Width: 50, Height: 50},
Format: imagerequest.FormatJPEG,
Quality: 85,
FitMode: imagerequest.FitCover,
},
req2 := &ImageRequest{
SourceHost: fixtures.GoodHost,
SourcePath: testPathPhoto,
Size: Size{Width: 50, Height: 50},
Format: FormatJPEG,
Quality: 85,
FitMode: FitCover,
}
resp1, err := svc.Get(ctx, req1)
internal/imgcache/source_content_internal_test.go
-141
View File
@@ -1,141 +0,0 @@
package imgcache
import (
"bytes"
"io"
"os"
"path/filepath"
"testing"
"sneak.berlin/go/pixa/internal/imagerequest"
)
// TestStoreSource_StoresIdenticalBytesOfTwoURLsTwice stores the same bytes
// for two source URLs and checks that each URL has a source_content row of
// its own and a file of its own, named by its source key under
// cache/sources/<ab>/<cd>/.
func TestStoreSource_StoresIdenticalBytesOfTwoURLsTwice(t *testing.T) {
t.Parallel()
cache, stateDir := newEvictionTestCache(t, 1<<30)
content := bytes.Repeat([]byte{0x5A}, 400)
keys := map[string]imagerequest.SourceKey{
"/a.jpg": storeEvictionTestSource(t, cache, testHostCDN, "/a.jpg", content),
"/b.jpg": storeEvictionTestSource(t, cache, testHostCDN, "/b.jpg", content),
}
t.Logf("source keys: %v", keys)
if keys["/a.jpg"] == keys["/b.jpg"] {
t.Fatalf("both source URLs got the key %s", keys["/a.jpg"])
}
for sourcePath, key := range keys {
rows := countRows(t, cache,
`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(key))
if rows != 1 {
t.Errorf("%s has %d source_content rows, want 1", sourcePath, rows)
}
name := string(key)
file := filepath.Join(stateDir, "cache", "sources", name[0:2], name[2:4], name)
stored, err := os.ReadFile(file) //nolint:gosec // path in the test's state dir
if err != nil || !bytes.Equal(stored, content) {
t.Errorf("file of %s at %s holds %d bytes (error %v), want the %d stored",
sourcePath, file, len(stored), err, len(content))
}
}
usage, err := cache.UsageBytes(t.Context())
if err != nil {
t.Fatalf("UsageBytes() error = %v", err)
}
if usage != 800 {
t.Errorf("UsageBytes() = %d, want 800, the 400 bytes once for each URL", usage)
}
}
// TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed stores the same
// bytes for two source URLs and evicts the first. Its row and file must be
// gone, and the second must still be found and read from the cache.
func TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
content := bytes.Repeat([]byte{0x5B}, 400)
evicted := storeEvictionTestSource(t, cache, testHostCDN, "/evicted.jpg", content)
storeEvictionTestSource(t, cache, testHostCDN, "/kept.jpg", content)
err := cache.evictSourceBlob(t.Context(), evicted)
if err != nil {
t.Fatalf("evictSourceBlob() error = %v", err)
}
if cache.srcContent.Exists(evicted) {
t.Error("the evicted source's file is still on disk")
}
if n := countRows(t, cache,
`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(evicted),
); n != 0 {
t.Errorf("the evicted source still has %d source_content rows", n)
}
kept, err := cache.LookupSource(t.Context(), &imagerequest.Request{
Source: imagerequest.Source{Host: testHostCDN, Path: "/kept.jpg"},
})
t.Logf("LookupSource() of the kept source = %q, error %v", kept, err)
if err != nil || kept == "" {
t.Fatalf("LookupSource() of the kept source = %q, %v; want it cached", kept, err)
}
reader, _, err := cache.GetSourceContent(kept)
if err != nil {
t.Fatalf("GetSourceContent() of the kept source error = %v", err)
}
defer func() { _ = reader.Close() }()
served, err := io.ReadAll(reader)
if err != nil {
t.Fatalf("reading the kept source: %v", err)
}
if !bytes.Equal(served, content) {
t.Errorf("the kept source reads as %d bytes, want the %d stored",
len(served), len(content))
}
}
// TestStoreSource_FailedRowWriteLeavesNoFile drops source_content, so that
// StoreSource cannot write the source's row, and checks that the store fails
// and leaves no file under the source's key.
func TestStoreSource_FailedRowWriteLeavesNoFile(t *testing.T) {
t.Parallel()
cache, _ := newEvictionTestCache(t, 1<<30)
_, err := cache.db.ExecContext(t.Context(), `DROP TABLE source_content`)
if err != nil {
t.Fatalf("failed to drop source_content: %v", err)
}
req := &imagerequest.Request{
Source: imagerequest.Source{Host: testHostCDN, Path: testPathCat},
}
key, err := cache.StoreSource(t.Context(), req,
bytes.NewReader([]byte("source bytes")))
t.Logf("StoreSource() = %q, error = %v", key, err)
if err == nil {
t.Error("StoreSource() error = nil, want the failed row write")
}
if cache.srcContent.Exists(req.Source.Key()) {
t.Error("the source's file is on disk although its row was not written")
}
}
internal/imagerequest/sourceurl_internal_test.go → internal/imgcache/sourceurl_internal_test.go
+16 -22
View File
@@ -1,16 +1,14 @@
package imagerequest
package imgcache
import "testing"
func TestRequest_SourceURL_DefaultHTTPS(t *testing.T) {
func TestImageRequest_SourceURL_DefaultHTTPS(t *testing.T) {
t.Parallel()
req := &Request{
Source: Source{
Host: testHostCDN,
Path: testPathCat,
Query: "v=2",
},
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: testPathCat,
SourceQuery: "v=2",
}
got := req.SourceURL()
@@ -21,15 +19,13 @@ func TestRequest_SourceURL_DefaultHTTPS(t *testing.T) {
}
}
func TestRequest_SourceURL_AllowHTTP(t *testing.T) {
func TestImageRequest_SourceURL_AllowHTTP(t *testing.T) {
t.Parallel()
req := &Request{
Source: Source{
Host: "localhost:8080",
Path: testPathCat,
},
AllowHTTP: true,
req := &ImageRequest{
SourceHost: "localhost:8080",
SourcePath: testPathCat,
AllowHTTP: true,
}
got := req.SourceURL()
@@ -40,15 +36,13 @@ func TestRequest_SourceURL_AllowHTTP(t *testing.T) {
}
}
func TestRequest_SourceURL_AllowHTTPFalse(t *testing.T) {
func TestImageRequest_SourceURL_AllowHTTPFalse(t *testing.T) {
t.Parallel()
req := &Request{
Source: Source{
Host: testHostCDN,
Path: "/img.jpg",
},
AllowHTTP: false,
req := &ImageRequest{
SourceHost: testHostCDN,
SourcePath: "/img.jpg",
AllowHTTP: false,
}
got := req.SourceURL()

Some files were not shown because too many files have changed in this diff Show More