sneak/sfdupes
1
0
Fork 0
Code Issues 9 Pull Requests 2 Actions 6 Packages Projects Releases Wiki Activity

Compare commits

base: sneak/sfdupes:issue-113-trees-progress
Branches Tags
sneak/sfdupes:main sneak/sfdupes:issue-113-trees-progress sneak/sfdupes:next sneak/sfdupes:issue-19-markdown-fmt
sneak/sfdupes:v0.0.2 sneak/sfdupes:v1.0.0-rc2 sneak/sfdupes:v1.0.0-rc1 sneak/sfdupes:v0.0.1
..
compare: sneak/sfdupes:2ff22964f560cc3d5f35e07c7e819c9d9ce61567
Branches Tags
sneak/sfdupes:issue-113-trees-progress sneak/sfdupes:next sneak/sfdupes:main sneak/sfdupes:issue-19-markdown-fmt
sneak/sfdupes:v0.0.2 sneak/sfdupes:v1.0.0-rc2 sneak/sfdupes:v1.0.0-rc1 sneak/sfdupes:v0.0.1
1 Commits
issue-113-trees-progress .. 2ff22964f5
Author SHA1 Message Date
sneak 2ff22964f5 Open files to hash without blocking and reject non-regular ones (closes #100)
check / check (push) Canceled after 0s
Details 
A regular file replaced by a FIFO after the walk statted it made the
hash phase's open wait forever for a writer, so the scan never ended
and kept the lock. The hash and content phases now open each file with
O_NONBLOCK and check with fstat that it is still a regular file;
anything else is a per-path error, warned about and skipped. The new
test replaces a walked file with a FIFO before the hash phase reads it.

Model: opus-5-5
 2026-10-14 18:14:34 +00:00
36 changed files with 1097 additions and 3570 deletions
Expand all files Collapse all files
.claude/settings.json
+5
View File
@@ -0,0 +1,5 @@
{
"worktree": {
"bgIsolation": "none"
}
}
.dockerignore
+6 -73
View File
@@ -1,79 +1,12 @@
# .dockerignore does NOT use .gitignore semantics. Docker matches with
# moby/patternmatcher: filepath.Match plus `**`, so `*` does not cross
# `/` and an unprefixed pattern is anchored at the context root. Every
# depth-independent pattern therefore needs `**/`, or `config/.env` and
# `certs/server.key` still ship while this file reads as solved. Only
# genuinely root-anchored entries go unprefixed. Never transplant these
# into .gitignore, where `**/` is wrong.
#
# Matching is case-sensitive, so secrets use character ranges rather
# than an ALL-CAPS twin, which would still miss `Server.Key`.
#
# Extend with this repo's own host-built artifacts, written anchored:
# `/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
# 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.
# KNOWN GAP: a repo running agents in subdirectories still ships
# `services/api/.claude/` and must add its own anchored entry.
.claude
# Environment files. `*.env` covers bare `.env` and the `prod.env`
# convention. Re-include a committed template with a negation if the
# build needs one: `!docs/example.env`.
**/*.[eE][nN][vV]
**/.[eE][nN][vV].*
**/.[eE][nN][vV][rR][cC]
# Private keys and the bundles carrying them. Public certificates
# (*.crt, *.cer) are deliberately absent: they are legitimate inputs.
**/*.[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]
# Dependencies: restored inside the image, never copied in.
**/node_modules
# OS metadata.
**/.DS_Store
**/Thumbs.db
# Editor state: never a build input, and it churns COPY.
**/*.swp
**/*.swo
**/*~
**/*.bak
**/.idea
**/.vscode
**/*.sublime-*
# This repository's host-built artifacts: the binary `make build` writes,
# and test binaries, coverage output and logs.
/sfdupes
/*.test
/*.out
/*.log
.DS_Store
sfdupes
*.log
*.out
*.test
.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
-9
View File
@@ -1,20 +1,11 @@
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.
with:
persist-credentials: false
# All history and tags, so git describe finds the version tag.
fetch-depth: 0
- run: script/cibuild
.gitignore
+12 -37
View File
@@ -11,50 +11,25 @@ Thumbs.db
.vscode/
*.sublime-*
# Agent scratch (worktrees of this repo, created and destroyed by
# in-flight tooling). Unanchored: .gitignore patterns already match at
# every depth, so no prefix is wanted here. This is not a .dockerignore
# 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 / secrets
.env
.env.*
*.pem
*.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 build artifacts
/sfdupes
*.log
*.out
*.test
*.out
*.log
# A scan database lists every path it scanned.
# Local scan data
*.sqlite
*.sqlite-shm
*.sqlite-wal
# Agent worktrees
.claude/worktrees/
.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
Dockerfile
+136 -59
View File
@@ -1,80 +1,159 @@
# Every stage declares ARG CACHEBUST first: script/ passes a new value
# on every build, which reruns every RUN step after it. The steps that
# compile mount Go's build cache, which survives from build to build.
# Lint phase, built alone by script/lint. The tools are invoked directly
# rather than through `make lint`, which runs docker itself and so cannot
# run inside a build step.
# golangci/golangci-lint:v2.14.0, 2026-10-07
FROM golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
ARG CACHEBUST
# Lint stage — fast feedback on formatting and lint issues
# golangci/golangci-lint:v2.12.2, 2026-08-07
FROM golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240 AS lint
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
COPY . .
# The gofmt half of `make fmt-check`. gofmt's output is assigned to a
# variable first so that its own exit status, as when it cannot parse a
# file, still fails the step.
RUN files="$(gofmt -s -l .)" && \
# Cache-buster for the gate layers, and only for them: on an unchanged
# tree Docker would serve the gates below from cache and the build would
# exit 0 having run nothing. script/cibuild and script/docker pass a
# fresh CHECK_EPOCH; a build without one, such as a bare
# `docker build .`, fails at the check right after the ARG.
#
# ARG is per-stage, so the markdown and build stages declare it again.
# Each gate RUN must reference the value: BuildKit hashes the expanded
# command, so a declared but unreferenced ARG invalidates nothing. Keep
# it below the dependency layers so they stay cached.
ARG CHECK_EPOCH
RUN if [ -z "${CHECK_EPOCH}" ]; then \
echo "CHECK_EPOCH is unset; build via script/cibuild or script/docker" >&2; \
exit 1; \
fi
# These gates call the tools directly, not through `make lint` or
# `make fmt-check`: both run docker, which cannot run inside a docker
# build. This step is the gofmt half of `make fmt-check`; the markdown
# stage is its prettier half. gofmt's output is assigned to a variable
# first so that its own exit status, as when it cannot parse a file,
# still fails the step.
RUN echo "gate gofmt, epoch ${CHECK_EPOCH}" && \
files="$(gofmt -s -l .)" && \
if [ -n "$files" ]; then \
echo "gofmt: files not formatted:" >&2; echo "$files" >&2; exit 1; \
fi
# Validates .golangci.yml against the schema the pinned binary embeds.
RUN golangci-lint config verify --config .golangci.yml
RUN --mount=type=cache,target=/root/.cache/go-build \
# Fails the build when the FROM above and the one in Dockerfile.lint pin
# different linter images.
RUN echo "gate lint-image-pin, epoch ${CHECK_EPOCH}" && \
script/verify-lint-image-pin
# Same config-schema check Dockerfile.lint runs, kept here so this build
# gates on exactly what script/lint gates on. It validates against a
# schema the pinned binary embeds, so it needs no network.
RUN echo "gate config verify, epoch ${CHECK_EPOCH}" && \
golangci-lint config verify --config .golangci.yml
RUN echo "gate lint, epoch ${CHECK_EPOCH}" && \
golangci-lint run --config .golangci.yml ./...
# Test phase, built alone by script/test. -race needs cgo and so a C
# compiler, which the Debian Go image ships and the alpine one does not.
# -count=1 because the mounted cache also holds test results, which go
# test would otherwise replay.
#
# The tests run as nobody: several of them make a file unreadable and
# expect reading it to fail, and root reads it anyway. nobody has no home
# directory, so HOME is /tmp, and Go keeps its build cache in
# /tmp/.cache/go-build. That is where the cache is mounted, owned by
# nobody (65534) so the tests can write to it.
# golang:1.25-trixie, 2026-10-04
FROM golang@sha256:2c4c60ef415fbfa5e90300722293bef36c5e63fae17570ce18f580af933dbd73 AS test
ARG CACHEBUST
USER nobody
ENV HOME=/tmp
# Prettier stage: the prettier that formats this repository's Markdown,
# never installed on a host. script/fmt and script/fmt-check build this
# stage alone and run it with the repository mounted on /src. prettier
# is installed in /tools so that the repository, mounted or copied onto
# /src, cannot hide it.
# node:22-alpine, 2026-02-22
FROM node@sha256:e4bf2a82ad0a4037d28035ae71529873c069b13eb0455466ae0bc13363826e34 AS prettier
WORKDIR /tools
# yarn.lock pins prettier by hash, and --frozen-lockfile fails rather
# than install anything yarn.lock does not name.
COPY package.json yarn.lock ./
RUN yarn install --frozen-lockfile
ENV PATH=/tools/node_modules/.bin:$PATH
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
COPY . .
RUN --mount=type=cache,target=/tmp/.cache/go-build,uid=65534,gid=65534 \
go test -count=1 -timeout 90s -race -cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \
go test -count=1 -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 this stage cannot run unless
# lint and test passed.
# Markdown stage: the Markdown half of `make fmt-check`, as a gate.
FROM prettier AS markdown
COPY . .
# Second per-stage declaration of the gate cache-buster and its check;
# see the lint stage above.
ARG CHECK_EPOCH
RUN if [ -z "${CHECK_EPOCH}" ]; then \
echo "CHECK_EPOCH is unset; build via script/cibuild or script/docker" >&2; \
exit 1; \
fi
RUN echo "gate prettier, epoch ${CHECK_EPOCH}" && \
prettier --check '**/*.md' --tab-width 4 --prose-wrap always
# Build stage
# golang:1.25-alpine, 2026-07-23
FROM golang@sha256:56961d79ea8129efddcc0b8643fd8a5416b4e6228cfd477e3fd61deb2672c587 AS builder
ARG CACHEBUST
COPY --from=lint /src/go.sum /dev/null
COPY --from=test /src/go.sum /dev/null
RUN apk add --no-cache git make
# A tar-stream context keeps the sender's file owners, which git refuses.
RUN git config --system --add safe.directory /src
# We never build or run as root. Create an unprivileged user and point
# HOME and the build cache at its home so go build and go test can write
# it when we drop to it below.
#
# The module cache stays at the base image's default /go/pkg/mod and
# belongs to root: script/bootstrap fills it as root. Do not move it
# into the home and hand it over with `chown -R`: that walks every file
# in it, which took from about 80 s to over ten minutes on a shared
# host, depending on load.
RUN adduser -D -u 1000 builder
ENV HOME=/home/builder
ENV GOPATH=/home/builder/go
ENV GOMODCACHE=/go/pkg/mod
ENV GOCACHE=/home/builder/.cache/go-build
WORKDIR /src
# No-op file copies whose only purpose is the build-graph edge: they
# make this stage depend on the lint and markdown stages, so BuildKit
# finishes those gates before compilation and tests start. Remove one
# and the build silently stops gating on that stage and still exits 0.
COPY --from=lint /src/go.sum /dev/null
COPY --from=markdown /src/go.sum /dev/null
# Install development prerequisites the same way a developer does. Only
# script/ and the dependency manifests are copied first, so this layer
# stays cached until they change. Bootstrap ends in `go mod download`.
COPY script/ script/
COPY go.mod go.sum ./
RUN go mod download
COPY . .
RUN script/bootstrap
# Hand builder only what it writes to, without walking the module cache.
# This layer stays cached with bootstrap.
# - /src itself: make build writes the binary into it, and git refuses
# a repository whose top directory belongs to another user.
# - the module cache's cache/download directory itself, not what is in
# it: Go only reads the downloaded modules, but make build saves its
# lookup of this module's own version from git there, in a new
# directory named after the module path.
# - builder's home: the go commands bootstrap ran as root left Go's
# telemetry files there, a few small files.
RUN chown builder:builder /src /go/pkg/mod/cache/download && \
chown -R builder:builder /home/builder
# The sources are handed to builder as they are copied, so no layer has
# to walk them. Then drop root before running any checks or builds.
COPY --chown=builder:builder . .
USER builder
# Fail the build unless the branch is green. Runs as non-root: root
# would bypass the chmod(0) the permission-denied tests rely on.
#
# The gate is `make test`, not `make check`, which runs docker; lint and
# the format checks ran in the lint and markdown stages above. `make`,
# not the script directly, because the Makefile's
# `export CGO_ENABLED = 0` applies only to what it invokes.
#
# Third per-stage declaration of the gate cache-buster and its check;
# see the lint stage above. It is placed after USER so the drop to the
# unprivileged user still happens before the checks run.
ARG CHECK_EPOCH
RUN if [ -z "${CHECK_EPOCH}" ]; then \
echo "CHECK_EPOCH is unset; build via script/cibuild or script/docker" >&2; \
exit 1; \
fi
RUN echo "gate test, epoch ${CHECK_EPOCH}" && make test
# The version stamped into the binary: the VERSION build argument when
# one is given, otherwise `git describe --tags --always` of the .git in
# the build context. A context that carries .git and still yields no
# version fails the build; with neither, as from a source tarball, it is
# "dev". `make build` rather than `go build`, so the image and a host
# build share one compile recipe, cgo disabled included.
# the build context (git is installed by script/bootstrap above). A
# context that carries .git and still yields no version fails the build;
# with neither, as from a source tarball, it is "dev".
ARG VERSION
RUN --mount=type=cache,target=/root/.cache/go-build \
version="${VERSION:-$(git describe --tags --always || echo dev)}"; \
RUN version="${VERSION:-$(git describe --tags --always || echo dev)}"; \
if [ -e .git ] && { [ -z "$version" ] || [ "$version" = dev ] || \
[ "$version" = unknown ]; }; then \
echo "no version could be derived although the build context carries .git" >&2; \
@@ -82,11 +161,9 @@ RUN --mount=type=cache,target=/root/.cache/go-build \
fi; \
make build VERSION="$version"
# Runtime stage, and the last one: a plain `docker build .` builds this
# stage's chain and nothing else.
# Runtime stage
# alpine:3.22, 2026-07-23
FROM alpine@sha256:14358309a308569c32bdc37e2e0e9694be33a9d99e68afb0f5ff33cc1f695dce
ARG CACHEBUST
COPY --from=builder /src/sfdupes /usr/local/bin/sfdupes
Dockerfile.lint
+45
View File
@@ -0,0 +1,45 @@
# Lint-only image, built by script/lint: the repo is copied into the
# pinned golangci-lint image and the linter runs as a build step, so a
# successful build is a clean lint. No bind mount, so it works when the
# docker daemon is remote.
#
# It is separate from the main Dockerfile's lint stage because
# script/lint must not depend on the rest of that build; the two FROM
# lines are kept identical by script/verify-lint-image-pin, run as a
# gate below.
# golangci/golangci-lint:v2.12.2, 2026-08-07
FROM golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240
WORKDIR /src
# Dependency layers first, so they stay cached across lint runs.
COPY go.mod go.sum ./
RUN go mod download
COPY . .
# Cache-buster for the gate layers, and only for them; caching of the
# lint run is waived by ruling. On an unchanged tree the gates below
# would be served from cache and this build would exit 0 in under a
# second having run no linter. script/lint passes a fresh value on every
# invocation.
#
# Each gate RUN must reference the value: BuildKit hashes the expanded
# command, so a declared but unreferenced ARG invalidates nothing. Keep
# it below the dependency layers so they stay cached.
ARG CHECK_EPOCH
# Fails the build when the FROM above and the main Dockerfile's lint
# stage pin different linter images.
RUN echo "gate lint-image-pin, epoch ${CHECK_EPOCH}" && \
script/verify-lint-image-pin
# Validates .golangci.yml against golangci-lint's JSON schema, which the
# pinned binary embeds: measured under `--network none`, it passes a
# valid config and rejects an invalid one. No gate step makes a network
# call, but `go mod download` above needs the network on a cold cache.
RUN echo "gate config verify, epoch ${CHECK_EPOCH}" && \
golangci-lint config verify --config .golangci.yml
RUN echo "gate lint, epoch ${CHECK_EPOCH}" && \
golangci-lint run --config .golangci.yml ./...
Makefile
+4 -1
View File
@@ -6,7 +6,7 @@ BINARY := sfdupes
VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo dev)
LDFLAGS := -X main.Version=$(VERSION)
.PHONY: sfdupes build bootstrap setup test lint fmt fmt-check check docker hooks clean
.PHONY: sfdupes build bootstrap setup test test-race lint fmt fmt-check check docker hooks clean
# Standard targets are thin shims; the implementations live in script/
# per the scripts-to-rule-them-all pattern.
@@ -27,6 +27,9 @@ setup:
test:
@script/test
test-race:
@script/test-race
lint:
@script/lint
README.md
+141 -212
View File
@@ -96,12 +96,10 @@ As a file `/etc/cron.d/sfdupes`:
the first scan. To keep it elsewhere, set
`SFDUPES_DATABASE=/path/to/db.sqlite` before the command on the same line.
- `scan` writes nothing to stdout. Its stderr, appended here to
`/var/log/sfdupes.log`, holds a first line naming the database (see
"Database"), plain progress lines naming each phase and its place among the
five, as `[2/5] walk` (one as the phase starts, one every 5 seconds while it
runs, and one as it ends), a warning for each path it skips, and the summary
line (see "Progress" and "`scan` mode"). The log grows with every scan; rotate
it like any other.
`/var/log/sfdupes.log`, holds a plain progress line as each phase starts and
then at most every 5 seconds, a warning for each path it skips, and the
summary line (see "Progress" and "`scan` mode"). The log grows with every
scan; rotate it like any other.
- Skipped paths do not fail a scan: it still exits 0, and cron sends nothing. A
scan that fails, or is stopped by `SIGINT` or `SIGTERM`, exits 1 with the
reason among the last lines of the log; `tail` prints them, and cron mails
@@ -268,26 +266,6 @@ All three subcommands operate on a single SQLite database file:
command-line flag. The path names the file exactly, whatever characters it
holds (`?`, `#` and `%` included); a relative path is relative to the working
directory.
- Each subcommand first prints one line on stderr naming the database it uses,
before anything else it prints (progress displays included), whether or not
stderr is a terminal. The line gives the path with the working directory put
in front of it when it is relative, and otherwise as set (a `..` in it stays,
so the line names the same file), escaped like the paths in a report (see
"Report output format"), and says where the path came from:
```
scan: new database /var/lib/sfdupes/db.sqlite (default)
trees: database /srv/tmp/sfdupes/db.db (from SFDUPES_DATABASE)
```
The working directory put in front is the one `pwd -P` prints, with its
symlinks resolved. After a `cd` through a symlink to a directory, a path
starting `../` therefore names a file beside the directory the symlink leads
to, as it does for any other program. `scan` says `new database` when no
file is at that path as it starts. `report` and `trees` print the line
before they open the database, so the error for a missing database comes
after it.
- `scan` creates the database (and its parent directory) on first use. `report`
and `trees` require an existing database; a missing database file is a fatal
error (exit 1) telling the user to run `scan` first.
@@ -326,20 +304,6 @@ All three subcommands operate on a single SQLite database file:
in WAL mode until the next scan. `report` writes each row as it reads it, so
it is still reading while its output is paused (a pager, a stalled pipe), and
a `scan` started then fails after the busy timeout.
- A `scan` writes to the database and the files beside it at these points (its
phases are described under "`scan` mode"):
- As it starts, before the walk: the directory, an empty database file and
the `.lock` file, each only if missing.
- Then, still before the walk: the schema, in a new database, and the `-wal`
and `-shm` files, which stay beside the database while the scan runs.
- While it loads the existing records (`load`) and walks: no records. A
first scan's database holds none, however long its walk has run.
- During the hash phase: the first records, committed 10,000 at a time.
- In the update phase: the rest of the hashed records, the records for
size-unique files, and the deletions.
- In the content phase: content hashes, again committed 10,000 at a time.
- At the end, as it closes the database: the `-wal` and `-shm` files go
away, unless a report still has the database open (see above).
- `report` and `trees` open the database read-only and need only read access to
the database file, and no write access to its directory. While the database is
in WAL mode they also read the `-wal` and `-shm` files beside it, which SQLite
@@ -434,11 +398,7 @@ results do not depend on the working directory. All operands belong to a single
scan and are enumerated concurrently: every operand seeds the shared walk worker
pool. Overlapping operands are harmless — an operand that duplicates another or
lies under another is dropped before walking, so every file is reached exactly
once and produces one database record. With `-x`, though, an operand under
another one is kept and walked on its own when any directory from it (from its
directory, for a regular file) up to but not including the operand covering it
is on a different filesystem than that operand, because that operand's walk does
not enter such a directory and so does not reach it.
once and produces one database record.
An operand that is a symlink (never followed, not even as an operand), socket,
FIFO, or device node, or a directory named `.zfs`, is not scanned. `scan` prints
@@ -447,8 +407,9 @@ drops it from the scanned operands before reading the database. Another operand
beneath it is still scanned. The records stored beneath it are not deleted: they
are treated like any other record outside the scanned operands, including the
content-phase exception below. If it lies under another operand, they are under
that operand instead, and are treated like any other record there. This is not
an error: a scan whose every operand is dropped walks nothing and exits 0.
that operand instead, and are deleted like any other record there that this scan
did not verify. This is not an error: a scan whose every operand is dropped
walks nothing and exits 0.
`scan` synchronizes the database with the filesystem state under the scanned
operands:
@@ -486,22 +447,11 @@ operands:
a `content` hash is read for one, wherever it lies, once its size, `head`, and
`tail` match another record's. If that file is gone or has changed since its
record was written, the record is left as it is.
- With `-x`, a record below a directory the walk did not enter because that
directory is on another filesystem than its operand counts as outside the
scanned operands: it is not deleted, and its size joins the size census. A
filesystem mounted under an operand can therefore be scanned on its own
schedule into the same database. Records below an operand at or inside such a
directory are not kept this way, since that operand's own walk verifies them.
`scan` runs **five sequential phases over the whole scan**. Parallelism lives
inside the walk, hash and content phases; batched database writes begin during
the hash phase:
`scan` runs **four sequential phases over the whole scan**. Parallelism lives
inside each phase; batched database writes begin during the hash phase:
1. **load** — read the existing records. Each record under the operands is kept
in memory, by path, with its size, its mtime and whether it has hashes, for
the walk to compare each file with; the size of every other record joins the
size census.
2. **walk + stat** — enumerate the trees under all `PATH` operands concurrently
1. **walk + stat** — enumerate the trees under all `PATH` operands concurrently
with the walk worker pool: every operand seeds the shared queue, and each
worker reads one directory at a time, handing discovered subdirectories back
to the queue and running `lstat` on each regular file as it is discovered
@@ -511,7 +461,7 @@ the hash phase:
or busy pools. The walk builds the size census and resolves unchanged
already-hashed files on the fly; every other file is carried to the hash
phase as a (path, size, mtime) record.
3. **hash** — with the census complete, each carried file's size decides its
2. **hash** — with the census complete, each carried file's size decides its
fate. Size-unique files are never read: new or changed ones are recorded
without hashes in the update phase, unchanged unhashed ones simply keep
their records. Every file with a shared size is hashed by the worker pool as
@@ -527,10 +477,10 @@ the hash phase:
**while hashing runs**, so a scan interrupted after hours keeps everything
hashed so far and the next scan resumes cheaply, skipping records already
written.
4. **update** — commit the final partial batch, the hash-less records for
3. **update** — commit the final partial batch, the hash-less records for
size-unique new and changed files, and the deletions for records the scan
did not verify (vanished files, plus paths that failed to stat or hash).
5. **content** — find every record of 10 MiB or more without a `content` hash
4. **content** — find every record of 10 MiB or more without a `content` hash
whose size, `head`, and `tail` equal another record's, anywhere in the
database: records from this scan and records stored by earlier scans, inside
or outside the scanned operands. SQLite finds them, so only the records to
@@ -563,19 +513,15 @@ Rules for the walk:
- Filesystem boundaries are crossed by default. With `-x` (long form
`--one-file-system`, following the GNU `du`/`rsync` convention), never descend
into a directory on a different filesystem than its `PATH` operand; each
operand is bounded by its own filesystem. The records below such a directory,
unless they lie below an operand at or inside that directory, count as outside
the scanned operands, as described in "`scan` mode" above: they are not
deleted, and their sizes join the size census.
operand is bounded by its own filesystem.
- On any per-path error (permission denied, file vanished between passes,
unreadable): print a one-line warning to stderr, skip the path, and continue.
Per-file errors never abort the run; the final summary reports how many were
skipped. As specified above, a skipped path that has a database record from an
earlier scan loses that record, unless it failed only in the content phase, or
is an operand dropped before the database was read whose record counts as
outside the scanned operands; an unreadable directory subtree likewise loses
its records (accepted: the database mirrors what the latest scan could
actually verify).
is an operand dropped before the database was read that lies under no other
operand; an unreadable directory subtree likewise loses its records (accepted:
the database mirrors what the latest scan could actually verify).
Concurrency: the walk phase (which also stats files), the hash phase, and the
content phase each use a worker pool of `--workers` workers (default
@@ -584,9 +530,8 @@ files. `--workers` must be at least 1: a smaller value is a usage error,
reported in one line on stderr with exit 2 before anything is scanned. All three
phases are seek-bound on spinning disks, so raising `--workers` well past the
core count can help on pools with many spindles. The main goroutine owns
partitioning, database writes, and the progress counts, which each progress
display draws from a goroutine of its own; progress display must never block the
workers.
partitioning, database writes, and progress rendering; progress display must
never block the workers.
`scan` writes nothing to stdout. The summary line on stderr reports the files
seen this run broken down by disposition, plus skips:
@@ -695,12 +640,6 @@ Processing:
- Order groups by total tree size descending, tie-broken by `first` path
ascending. Output must be fully deterministic for a given input.
`trees` runs in four phases, each with its own progress display on stderr (see
"Progress"): `open` opens the database; `read` counts the records, then reads
them in path order, building the hierarchy and computing the digests as it goes;
`group` groups the directories by digest and picks the maximal groups; `write`
writes the groups to stdout.
#### Trees output format
TSV on stdout: a header line, then one row per duplicate tree (N-1 rows for a
@@ -721,94 +660,45 @@ units.
### Progress
Use the progress-bar library for all progress of `scan` and `trees`; rendering
in the style of `pv` is the model. All progress goes to stderr.
Use the progress-bar library for all scan progress; rendering in the style of
`pv` is the model. All progress goes to stderr.
`scan` and `trees` must always show that they are working and not hung. Each
phase gets its own display from the moment it starts, naming the phase and its
place among the command's phases and showing its progress, its elapsed time and
its estimated time remaining (ETA).
Each phase gets its own display, rendered the moment the phase starts — a scan
must never look hung. Loading the existing-record index (`load`) and the walk
have no known totals while running: show a live count, rate, and elapsed time
(spinner-style, no percentage or ETA). The content phase's display (`content`)
starts the same way, counting the records checked while SQLite finds the files
to read and `lstat` checks them, then shows a bar once reading starts. The hash
and update phases, and the content phase's reads, have exact totals — only files
that actually need hashing appear in the hash and content totals, so their ETAs
are meaningful. Required elements for the bars with known totals:
A scan has five phases (`[1/5] load`, `[2/5] walk`, `[3/5] hash`,
`[4/5] update`, `[5/5] content`):
- `load` counts the records first, then reads them against that count. While the
count runs, the display says it is counting the records.
- `walk` has no exact total. Its estimate is the number of records the last scan
left under the operands, known once `load` is done and shown with a `~`. Once
the walk passes the estimate, or when there are no such records, as on a first
scan, the ETA is unknown.
- `hash` and `update` have exact totals. Only files that actually need hashing
appear in the hash total, so its ETA is meaningful.
- `content` first counts the records whose files it checks with `lstat`, which
SQLite does by adding up the number of records with each matching size,
`head`, and `tail`, without fetching the records. It then says it is searching
the database until SQLite returns the first record; the checks, and their rate
and ETA, start there. The files to read then get a display of their own, with
their count as its total.
`trees` has four phases (`[1/4] open`, `[2/4] read`, `[3/4] group`,
`[4/4] write`, see "`trees` mode"):
- `open` has no total. While it opens the database, waiting on a busy one
included, the display says it is opening the database.
- `read` counts the records first, then reads them against that count. While the
count runs, the display says it is counting the records.
- `group` has the directories `read` found as its total, and `write` the
duplicate-tree groups.
Each display is one line holding:
- the phase and its place among the phases
- a `[m/n] x%` display (items processed / total items, percent); before a phase
has a total, the items processed, or what the phase is waiting for
- current rate (items/s), naming the items the phase counts: files, records,
directories or groups
- elapsed time
- estimated time remaining, or `unknown`
- estimated time remaining
- a `[m/n] x%` display (items processed / total items, percent)
- current rate (items/s)
Example shape (exact layout is flexible, content is not):
```
[3/5] hash: [12345/98765] 12% |████ | 92 files/s elapsed 2:32 eta 17:54
[2/5] walk: [1234567/~1200000] 103%, 5120 files/s, elapsed 4m1s, eta unknown
hash: [12345/98765] 12% |████ | 92 files/s elapsed 2:32 eta 17:54
```
Additional requirements:
- On a terminal, a phase with an exact total (every phase but `scan`'s `walk`
and `trees`' `open`, once it has counted what it will do) is drawn as its line
followed by the progress-bar library's bar, 10 columns wide, which shows the
percent in place of the line's own. Any other phase, and a phase whose bar has
no room, is drawn as the library's spinner followed by its line. Each display
is drawn again several times a second, so its elapsed time keeps moving while
a phase waits for its next item.
- On a terminal no line reaches the terminal's last column, however narrow the
terminal is. The phase and its place, the progress, the elapsed time and the
ETA are kept whole: a line too wide for the terminal leaves out its rate first
(or what the phase is waiting for), and a bar with no room beside those four
gives way to the spinner. Only when those four alone are too wide, as on a
terminal narrower than about 70 columns hours into a scan of millions of
files, is the line cut short at the terminal's edge, so the end of the ETA is
lost first. A terminal made narrower while a phase runs gets the same: the
next draw erases the line within the new width and fits the line to it, and
the display goes on redrawing in place.
- When stderr is not a terminal (a pipe, a file, `/dev/null`), do not emit ANSI
redraws: print the line the moment each phase starts, every 5 seconds while it
runs (whether or not an item has completed, and never more often), and once
more as the phase ends.
- Progress must be non-blocking with respect to the worker pool: the main
goroutine counts the items, and each display draws them from a goroutine of
its own.
redraws: print a plain one-line progress update the moment each phase starts,
then no more often than every 5 seconds.
- Progress updates are driven from the main goroutine and must be non-blocking
with respect to the worker pool. On a terminal the spinner-style displays also
redraw on their own several times a second, so their count and elapsed time
stay current while a phase waits for its next item.
- A warning printed during a phase always lands on a line of its own, never
inside the progress display. So does every line written to stdout when stdout
and stderr are the same file (the same device and inode): one terminal, as in
a plain `sfdupes trees`, or one pipe or file that both are sent to. When they
are not, stdout is written without waiting on the display, and the display
keeps being drawn while a slow reader of stdout holds up a write.
- A phase that stops short of its total, as an interrupted one does, is left
showing the count it stopped at rather than filled up.
- `report` mode needs no progress display, only its stderr summary.
inside the progress display.
- A bar whose phase stops short of its total, as an interrupted one does, is
left as last drawn rather than filled up.
- `report` and `trees` modes need no progress display, only their stderr
summaries.
### Error handling and exit codes
@@ -861,67 +751,104 @@ entrypoints are:
- `script/bootstrap` — install everything needed to build and develop this
repository, idempotently, assuming nothing is present. `git`, `make`, and `go`
come from the first of nix, apt, brew, or apk found on the host, and are
presence-checked only. An installed node is used when its major version is 22;
otherwise node 22.17.0 is installed through nvm, which comes from a release
archive whose sha256 the script checks, and yarn 1.22.22 is activated under it
through corepack. With an installed node 22, a yarn already on `PATH` is used
as it is; otherwise yarn 1.22.22 is activated through corepack, or installed
with `npm` when there is no corepack. `yarn install --frozen-lockfile` then
installs the prettier that `package.json` and `yarn.lock` pin. `golangci-lint`
is never installed: it runs in Docker (see `script/lint`). `docker` is not
installed either; testing, linting and the image build need it. Ends with
`go mod download`.
presence-checked only. `golangci-lint` and prettier are deliberately **not**
installed: they run in Docker (see `script/lint` and `script/fmt`) and never
from a host install, so there is no host copy to drift from the pin. A missing
`docker` is warned about rather than installed or treated as fatal —
everything except linting, formatting and `make test-race` works without it.
Ends with `go mod download`.
- `script/setup` — make a fresh clone ready for development: runs
`script/bootstrap`, then `script/install-precommit`.
- `script/projectname` — print this project's name (`sfdupes`). Scripts that
need the name call it, so they stay identical across repositories.
- `script/test` — run the test suite under the race detector, with a 90-second
timeout and coverage enabled, rerunning verbosely on failure so the logs show
which test failed. It builds the `Dockerfile`'s `test` phase alone and writes
no image. The race detector needs cgo and a C compiler, which the build never
uses, so the phase starts from a digest-pinned Debian `golang` image, which
has `gcc`. The tests run as `nobody`, because several of them make a file
unreadable and root reads it anyway.
- `script/lint` — run the linter. It builds the `Dockerfile`'s `lint` phase
alone and writes no image: in the digest-pinned `golangci/golangci-lint`
image, the gofmt check, `golangci-lint config verify` and `golangci-lint run`
run as build steps, so a successful build is a clean lint. The linter is never
run on the host, which makes a working `docker` the one prerequisite for
linting.
- `script/test` — run the test suite with a 30-second timeout and coverage
enabled, rerunning verbosely on failure so the logs show which test failed.
- `script/test-race` — run the test suite under the race detector with a
60-second timeout. The detector needs cgo and a C compiler, which the build
never uses, so the tests run in a digest-pinned Debian `golang` image that has
`gcc`, with the checkout mounted read-only; the container is removed when it
exits. They run as the calling user, or as `nobody` when that is root, because
several tests make a file unreadable and root reads it anyway; only then must
the checkout be readable by other users. Not part of `script/check`. Every run
starts with empty caches, so it needs the network and takes minutes, and the
mount needs a local docker daemon.
- `script/lint` — run the linter. It builds `Dockerfile.lint`, which copies the
repository into the digest-pinned `golangci/golangci-lint` image and runs
`golangci-lint config verify` and `golangci-lint run` as build steps, so a
successful build is a clean lint. That exit status is all it produces, so it
runs with `--output=type=cacheonly` and writes no image; a run leaves only
build cache. The linter is never run on the host, which makes a working
`docker` the one prerequisite for linting — and therefore for `make check` and
the pre-commit hook. Offline machines: the gate steps themselves make no
network calls. `golangci-lint run` does not, and neither does
`golangci-lint config verify` — it validates against a schema the pinned
binary embeds, measured under `--network none` to both pass a valid config and
reject an invalid one. The build around them does. `Dockerfile.lint` runs
`go mod download` before the gates and this module has external dependencies,
so a first lint on a machine with a cold BuildKit cache reaches the network
there (as well as pulling the pinned image); under `--network none` it fails
at that step, before any gate. That layer sits above the gates and stays
cached, so once it is warm `script/lint` — and with it `make check` — runs
entirely offline, until `go.mod` or `go.sum` changes and the download layer
goes cold again. Because the daemon only ever sees a build context, this works
when the docker daemon is remote and bind mounts are impossible.
- `script/fmt` — format in place: the Go sources with `gofmt -s -w`, and every
Markdown file with prettier, at the settings in `.prettierrc` (4-space
indents, prose wrapped at 80 columns). Both run on the host, prettier through
yarn at the version `yarn.lock` pins. When the node on `PATH` is not node 22,
this loads the node 22.17.0 that `script/bootstrap` installed through nvm.
- `script/fmt-check` — the read-only counterpart of `script/fmt`: prints any
unformatted file and exits non-zero instead of writing. gofmt and prettier
both run every time, and each names itself when it fails. The `Dockerfile`'s
`lint` phase runs the same gofmt check.
indents, prose wrapped at 80 columns). prettier is pinned by hash through
`package.json` and `yarn.lock` and never installed on the host: this builds
the `Dockerfile`'s `prettier` stage, a digest-pinned node image into which
`yarn install --frozen-lockfile` installs it, tagged `sfdupes-prettier`, and
runs that with the repository mounted, as the calling user. Needs `docker`,
and because of the mount, unlike `script/lint`, a local docker daemon.
- `script/fmt-check` — the read-only counterpart of `script/fmt`, with the
repository mounted read-only: prints any unformatted file and exits non-zero
instead of writing. gofmt and prettier both run every time, and each names
itself when it fails. The `Dockerfile` runs the same two checks as gates: the
gofmt check in its lint stage, prettier in its `markdown` stage.
- `script/check` — run `script/test`, `script/lint`, and `script/fmt-check`, in
that order. Modifies nothing. The first two need `docker`, the third what
`script/bootstrap` installs.
that order. Modifies nothing. Needs `docker`, because `script/lint` and
`script/fmt-check` do.
- `script/docker` — build the Docker image, tagged with the name from
`script/projectname`, passing the output of
`git describe --tags --always --dirty` (or `unknown` when that is empty) as
the `VERSION` build argument. The `Dockerfile`'s build stage depends on its
`lint` and `test` phases, so this also runs the tests and the linter.
- `script/cibuild` — run `script/bootstrap`, then `script/check`, then build the
image as `script/docker` does. This is what the Gitea workflow runs on push; a
successful run means every check passed. The tests and the linter run twice:
once in `script/check`, and again as stages of the image build.
`script/projectname`. The `Dockerfile` runs the gates as build steps, so this
is also the check a developer or reviewer runs by hand.
- `script/cibuild` — build the Docker image untagged. This is what the Gitea
workflow runs on push; because the gates run as build steps, a successful
build implies the repository is green.
- `script/precommit` — run by the git pre-commit hook: `go mod tidy` must be a
no-op (a resulting change to `go.mod` or `go.sum` fails the commit), then
`script/check`.
- `script/install-precommit` — install the git pre-commit hook, as
`.git/hooks/pre-commit`, that runs `script/precommit`.
- `script/install-precommit` — install the git pre-commit hook that runs
`script/precommit`. The hook is written to the common git directory, so the
main checkout and every worktree share it.
- `script/verify-lint-image-pin` — fail unless the `golangci/golangci-lint`
reference in `Dockerfile.lint` and the one in the `Dockerfile` lint stage are
the same image at the same digest, naming both if not. The linter is pinned in
those two files and nothing else keeps them in sync, so a bump applied to one
alone would leave `make lint` and the `Dockerfile`'s fail-fast lint stage
checking the same tree against different rulesets, both green. The guard
restates neither pin — a third copy would be the same drift one file further
out — and runs as a gate in both files, so `make lint`, `make check` and
`make docker` all catch it.
Every `docker build` in `script/` passes a new `CACHEBUST` build argument, which
every stage of the `Dockerfile` declares first, so every `RUN` step runs again
each time. On an unchanged tree Docker would otherwise serve the gate steps from
its cache, and the build would pass having run no test and no linter. Go's build
cache is kept between builds on the steps that compile, so only what changed is
compiled again; the tests run with `-count=1`, so none reports a stored result.
Every run downloads the Go modules again and needs the network.
`script/verify-linter-pin` used to live here. It compared a linter binary
against a version pin in `script/bootstrap`, and both of its subjects are gone:
no linter binary is copied between build stages any more, and bootstrap pins no
version because it installs no linter. The drift it existed to catch has moved
from binary-versus-pin to pin-versus-pin, which is what
`script/verify-lint-image-pin` above checks.
`script/lint`, `script/docker` and `script/cibuild` all pass a freshly computed
`CHECK_EPOCH` build argument, and the gate steps in `Dockerfile.lint` and
`Dockerfile` reference it. Without that, an unchanged tree lets Docker serve the
gate layers from cache and the build exits 0 having executed no tests and no
lint — a green it never earned, and one this repository has produced twice.
`CHECK_EPOCH` invalidates the gate layers on every run while leaving the pinned
base images and the dependency layers cached. Each script's value carries the
process id as well as the epoch, because two runs land inside the same second
easily and a bare epoch would cache the second one. Each `Dockerfile` stage with
gates fails when the value is empty, so a bare `docker build .` stops with
`CHECK_EPOCH is unset; build via script/cibuild or script/docker` instead of
serving the gates from cache.
## Build
@@ -933,15 +860,17 @@ compile recipe:
the default target.
- `make bootstrap` — install the build and development dependencies.
- `make setup` — prepare a fresh clone: `bootstrap` plus the pre-commit hook.
- `make test` — run the test suite under the race detector, in Docker (90-second
timeout; reruns with `-v` on failure; see `script/test`); requires `docker`.
- `make lint` — run `golangci-lint` with the repo config and the gofmt check, in
Docker (see `script/lint`); requires `docker`.
- `make test` — run the test suite (30-second timeout; reruns with `-v` on
failure).
- `make test-race` — run the test suite under the race detector, in Docker (see
`script/test-race`); requires `docker`. Not part of `make check`.
- `make lint` — run `golangci-lint` with the repo config, in Docker (see
`script/lint`); requires `docker`.
- `make fmt` / `make fmt-check` — format the Go sources and the Markdown /
verify formatting without writing, on the host; requires `go` and what
`make bootstrap` installs (see `script/fmt`).
verify formatting without writing; requires `docker`, for prettier (see
`script/fmt`).
- `make check` — `test`, `lint`, and `fmt-check`; modifies nothing. Requires
`docker` and what `make bootstrap` installs.
`docker`, via `lint` and `fmt-check`.
- `make docker` — build the Docker image, which runs the gates as build stages.
- `make hooks` — install the pre-commit hook.
- `make clean` — remove the binary.
REPO_POLICIES.md
+88 -436
View File
@@ -1,6 +1,6 @@
---
title: Repository Policies
last_modified: 2026-10-15
last_modified: 2026-07-06
---
This document covers repository structure, tooling, and workflow standards. Code
@@ -54,37 +54,21 @@ 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
`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
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 and runs `docker build .`; the Gitea workflow calls it. 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
@@ -105,257 +89,87 @@ style conventions are in separate documents:
contributor should be able to understand the entire development workflow by
reading the Makefile.
- Every repo should have a `Dockerfile`, and it carries the repo's gates: a
`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.
- Every repo should have a `Dockerfile`. All Dockerfiles must run `make check`
as a build step so the build fails if the branch is not green. For non-server
repos, the Dockerfile should bring up a development environment and run
`make check`. For server repos, `make check` should run as an early build
stage before the final image is assembled. 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 so the bootstrap
layer stays cached until dependencies change.
- **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:
- **Dockerfiles must use a separate lint stage for fail-fast feedback.** Go
repos use a multistage build where linting runs in an independent stage based
on the `golangci/golangci-lint` image (pinned by hash). This stage runs
`make fmt-check` and `make lint` before the full build begins. The build stage
then declares an explicit dependency on the lint stage via
`COPY --from=lint /src/go.sum /dev/null`, which forces BuildKit to complete
linting before proceeding to compilation and tests. This ensures lint failures
surface in seconds rather than minutes, without blocking on dependency
download or compilation in the build stage.
```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 .
```
**A stage that is not the last one in the file is built only when the final
stage's chain depends on it, or when `--target` names it.** That is why the
two gates are always invoked by name here, and why the final stage carries a
`COPY --from=` of a harmless file from each of them: without that edge a
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.
Inside a phase the tool is invoked directly — `golangci-lint`, `go test`,
`eslint`, `prettier` — never through `make lint` or `script/test`, which are
themselves a `docker build` and would recurse into a daemon that does not
exist in a build step. Formatting is the exception and stays on the host:
`script/fmt` writes the working tree, and `script/fmt-check` is its
read-only twin.
**No lint verdict may come from a host invocation of the linter.** On a
shared host golangci-lint reads a result cache keyed on file content rather
than location, so a second checkout of the same content is served the first
one's findings, and a host-global lock in `$TMPDIR` makes concurrent runs
exit non-zero with `parallel golangci-lint is running` — a status a caller
cannot tell from real findings. Both have produced wrong verdicts in this
org, in both directions. A container has its own golangci-lint cache, its
own `TMPDIR` and a digest-pinned binary, so neither is reachable.
- **Any build that runs checks is given a new `CACHEBUST` value.** Docker
invalidates a `COPY` layer only when the copied content changes, so on an
unchanged tree the check `RUN` is served from cache, nothing executes, and the
build still exits 0. Every `docker build` in `script/` therefore passes
`--build-arg CACHEBUST="$(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. Every
stage of the `Dockerfile` declares `ARG CACHEBUST` as its first line after
`FROM`, and a new value reruns every `RUN` step after that line; `COPY` steps
are compared by content and need nothing. 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 empties every cache mount, and Go's
build cache, which the canonical Go `Dockerfile` below mounts so that compiled
packages 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.
- **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
`Dockerfile`:
The standard pattern for a Go repo Dockerfile is:
```dockerfile
# Every stage declares ARG CACHEBUST first: script/ passes a new value
# on every build, which reruns every RUN step after it. The steps that
# compile mount Go's build cache, which survives from build to build.
# Lint phase
# Lint stage — fast feedback on formatting and lint issues
# golangci/golangci-lint:v2.x.x, YYYY-MM-DD
FROM golangci/golangci-lint@sha256:... AS lint
ARG CACHEBUST
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
COPY . .
RUN --mount=type=cache,target=/root/.cache/go-build \
golangci-lint run --config .golangci.yml ./...
RUN make fmt-check
RUN make lint
# 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
FROM golang@sha256:... AS test
ARG CACHEBUST
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
COPY . .
RUN --mount=type=cache,target=/root/.cache/go-build \
go test -count=1 -timeout 90s -race -cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \
go test -count=1 -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 this stage cannot run
# unless lint and test passed.
# Build stage
# golang:1.x-alpine, YYYY-MM-DD
FROM golang@sha256:... AS builder
ARG CACHEBUST
COPY --from=lint /src/go.sum /dev/null
COPY --from=test /src/go.sum /dev/null
RUN apk add --no-cache git
# A tar-stream context keeps the sender's file owners, which git refuses.
RUN git config --system --add safe.directory /src
WORKDIR /src
# Force BuildKit to run the lint stage before proceeding
COPY --from=lint /src/go.sum /dev/null
COPY go.mod go.sum ./
RUN go mod download
COPY . .
RUN make test
# 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
# Runtime stage
FROM alpine@sha256:...
ARG CACHEBUST
COPY --from=builder /app /usr/local/bin/app
ENTRYPOINT ["app"]
```
Key points:
- The lint phase uses the `golangci/golangci-lint` image directly (it has
both Go and the linter), so nothing needs installing.
- `COPY --from=<phase> /src/go.sum /dev/null` is a no-op copy whose only
purpose is the ordering edge. BuildKit runs stages in parallel by default,
and a stage nothing depends on is not built at all, so without these two
lines a red gate would not fail the build.
- 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.
- Only Go's build cache is mounted (`/root/.cache/go-build`, where Go keeps
it for root), and only on the steps that compile: `golangci-lint run`,
both `go test` runs and `go build`. It keeps compiled packages between
check builds, and Go reuses one only when all its inputs are unchanged, so
it saves the compile without skipping a check. Nothing else is kept:
golangci-lint's own cache would replay stored findings in place of a lint
run, and Go builds from whatever files a kept module cache holds without
checking them again (only `go mod verify` does), so a file changed there
would go unnoticed. Go's build cache also holds test results, which is why
both `go test` runs carry `-count=1`.
- The lint stage uses the `golangci/golangci-lint` image directly (it
includes both Go and the linter), so there is no need to install the
linter separately.
- `COPY --from=lint /src/go.sum /dev/null` is a no-op file copy that creates
a stage dependency. BuildKit runs stages in parallel by default; without
this line, the build stage would not wait for lint to finish and a lint
failure might not fail the overall build.
- 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
(e.g. a web frontend compiled in a separate stage), the lint stage 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:
```dockerfile
RUN apt-get update \
&& apt-get install -y --no-install-recommends libvips-dev \
&& rm -rf /var/lib/apt/lists/*
```
- `.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.
The lint stage should not depend on the actual build output — it exists to
fail fast.
- If the project requires CGO or system libraries for linting (e.g.
`vips-dev`), install them in the lint stage with `apk add`.
- The build stage runs `make test` after compilation setup. Tests run in the
build stage, not the lint stage, because they may require compiled
artifacts or heavier dependencies.
- 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
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.
runs `script/cibuild` (which runs `docker build .`) on push. Since the
Dockerfile already runs `make check`, a successful build implies all checks
pass.
- Use platform-standard formatters: `black` for Python, `prettier` for
JS/CSS/Markdown/HTML, `go fmt` for Go. Always use default configuration with
@@ -375,21 +189,14 @@ style conventions are in separate documents:
module under test to verify it compiles/parses. There is no excuse for
`make test` to be a no-op.
- `make test` must complete in under 60 seconds. That is the hard cap, and a
suite that exceeds it fails. Under 20 seconds is the target. A suite between
20 and 60 seconds is still green, but the overage must be filed as an
improvement bug against that repo. Add a 90-second timeout to the test
invocation (`go test -timeout 90s`). The backstop deliberately sits above the
hard cap so that it catches a genuinely hung test rather than a merely slow
one.
- `make test` must complete in under 20 seconds. Add a 30-second timeout in the
Makefile.
- **The test command should use the conditional verbose rerun pattern.** Run
tests without `-v` (verbose) first. If tests fail, automatically rerun with
`-v` to show full output. This keeps CI logs and `docker build` output clean
on success (just package/suite summaries) while providing full diagnostic
detail on failure (every test case, every assertion). The command lives in the
`test` phase of the `Dockerfile`, since `script/test` builds that phase; the
Makefile form below is the same pattern for any repo-local invocation:
- **`make test` should use the conditional verbose rerun pattern.** Run tests
without `-v` (verbose) first. If tests fail, automatically rerun with `-v` to
show full output. This keeps CI logs and `docker build` output clean on
success (just package/suite summaries) while providing full diagnostic detail
on failure (every test case, every assertion). The general shell pattern:
```makefile
test:
@@ -402,25 +209,11 @@ style conventions are in separate documents:
```makefile
test:
@go test -count=1 -timeout 90s -race -cover ./... || \
@go test -timeout 30s -race -cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \
go test -count=1 -timeout 90s -race -v ./...; exit 1; }
go test -timeout 30s -race -v ./...; exit 1; }
```
`-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.
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.
Python example:
```makefile
@@ -446,89 +239,10 @@ style conventions are in separate documents:
must be in `.gitignore`. No exceptions.
- `.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
editor files (`.swp`, `*~`), 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. 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
semantics, in which an unanchored pattern already matches at every depth; they
are not a `.dockerignore` and must not be transplanted into one unmodified.
- **`.dockerignore` does not use `.gitignore` semantics, and copying patterns
across unmodified leaves secrets in the build context.** Docker matches with
`moby/patternmatcher`: `filepath.Match` semantics plus a `**` extension, so
`*` does not cross `/` and a pattern without a leading `**/` is anchored at
the build-context root. A `.dockerignore` listing `.env`, `*.pem` and `*.key`
therefore excludes only the copies at the repository root, while `config/.env`
and `certs/server.key` still reach the context and can land in an image layer
— 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
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
secret names use character ranges — `**/*.[kK][eE][yY]`, `**/*.[pP][eE][mM]`,
and likewise for `.envrc` and the extensionless SSH keys. Where such a pattern
also catches something the build needs, re-include it with a negation
(`!docs/example.env`); deleting the pattern reopens the exposure for every
other file it covers. Fetch the standard `.dockerignore` from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.dockerignore` and extend
it with the repo's own artifacts.
- **In-repo agent scratch belongs in both files, written to each file's own
semantics.** `.claude/` holds one worktree per in-flight agent — an entire
additional checkout of the repo — so under `COPY . .` the build context
inflates by a multiple of the repo and another session's unreviewed work can
be copied into an image layer. In `.gitignore` the entry is `.claude/`,
unanchored. In `.dockerignore` it is `.claude`, anchored and with **no** `**/`
prefix, because the prefixed form would also delete any nested directory of
that name from the build. Anchoring carries a known gap that the canonical
`.dockerignore` states in its own comment, since consuming repos receive the
file and not the tracker: the directory is created in the agent's working
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:
```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.
version="$(git describe --tags --always --dirty 2>/dev/null || true)"
[ -n "$version" ] || version="unknown"
tag="$(script/projectname)"
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
--build-arg VERSION="$version" \
-t "$tag" .
```
`--always` makes an untagged repo yield an abbreviated commit hash rather
than failing, and the `[ -n "$version" ]` line is the single place the
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
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.
- **Verify `.dockerignore` by enumerating the image, not by reading the
patterns.** Plant files at the root _and_ at least two directories deep, build
a probe image that does `COPY . .`, and list what actually landed
(`docker run --rm --entrypoint find IMAGE /app`). The `transferring context`
size is not a substitute: a nested secret is a few bytes, and BuildKit
transfers only the delta from the previous build.
a new repo.
- **No build artifacts in version control.** Code-derived data (compiled
bundles, minified output, generated assets) must never be committed to the
@@ -544,61 +258,9 @@ style conventions are in separate documents:
- Make all changes on a feature branch. You can do whatever you want on a
feature branch.
- `.golangci.yml` is standardized. The vendored copy in a consuming repo must
_NEVER_ be modified by an agent: fetch it from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.golangci.yml` and keep it
byte-identical, so that no repo can quietly loosen its own linting. Linter
configuration changes are made to the canonical copy in the `prompts` repo and
reach consuming repos by re-vendoring; an agent may open a PR against
canonical, which only the user merges. One list is exempt from byte-identity,
because it cannot be written once for every repo: the `deny` list of the
`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
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.
- **`script/bootstrap` installs a pinned tool by comparing versions, never by
testing presence.** An `if ! command -v <tool>; then install; fi` guard tests
`PATH` only, so on an already-provisioned machine the pin is inert and a
version bump is a silent no-op — while the Dockerfile, installing into a clean
image, gets the pinned version, so a local `make check` and `make docker` can
disagree about what the tool even is. The canonical form:
- compares the installed version against the pin over the **whole** version
token; a parser that stops at the first `-` reports `2.12.2` for a host
running `2.12.2-rc1` and skips the install;
- treats absent, non-zero, empty or unrecognised `--version` output as a
mismatch, so the failure direction is a redundant install and never a
skipped one;
- after installing, re-resolves the binary the way callers do — `hash -r`,
then through `PATH`, not through the directory the installer wrote to —
and fails naming the resolved path, since an install that a shadowing
binary hides succeeds while changing nothing any caller sees;
- is actually called, and prints the version on both success paths: a
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`.
- `.golangci.yml` is standardized and must _NEVER_ be modified by an agent, only
manually by the user. Fetch from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.golangci.yml`.
- When pinning images or packages by hash, add a comment above the reference
with the version and date (YYYY-MM-DD).
@@ -709,21 +371,15 @@ 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
`cmd/`
- `cmd/` — Go command entrypoints
- `configs/` — configuration templates and examples
- `deploy/` — deployment manifests (k8s, compose, terraform)
- `docs/` — documentation and markdown (README.md stays in root)
@@ -750,7 +406,3 @@ 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
+95 -109
View File
@@ -29,64 +29,6 @@
# Completed Steps
- `trees` shows its work on stderr in four phases, `[1/4] open`, `[2/4] read`,
`[3/4] group` and `[4/4] write`, each with the progress display `scan` uses,
from the moment it starts until the summary line: `open` says it is opening
the database, also while it waits on a busy one; `read` counts the records,
then reads them against that count; `group` counts the directories it groups,
and `write` the groups it writes. A display's rate names what its phase
counts: files, records, directories or groups. stdout and the summary line are
unchanged. When stdout and stderr are the same file, as one terminal is, none
of stdout's lines shares a line with the display; when they are not, the
display keeps being drawn while stdout waits on a slow reader (2026-10-16,
https://git.eeqj.de/sneak/sfdupes/issues/113)
- each `scan` phase's progress display names the phase and its place among the
five, as `[2/5] walk`, from the moment it starts, with its progress, elapsed
time and ETA: `load` counts the records first, the walk's total is estimated
from the records under the operands, and the content phase counts the records
it checks from SQLite's grouping alone, then says it is searching the database
until the first one is returned. On a terminal a phase with an exact total
draws its line followed by the library's bar, and any other a spinner followed
by the line; every display is drawn again several times a second. No line
reaches the terminal's last column, however narrow, also after the terminal is
made narrower during a phase: a line too wide leaves out its rate, then its
bar, keeping the phase, progress, elapsed time and ETA whole, and is cut short
only when those alone do not fit, as below about 70 columns late in a large
scan. In plain mode the line is printed every 5 seconds whether or not an item
completed (2026-10-16, https://git.eeqj.de/sneak/sfdupes/issues/112)
- `scan`, `report` and `trees` first print a line on stderr naming the database
they use, as an absolute path, and whether that path is the default or comes
from `SFDUPES_DATABASE`; `scan` says when the database is new. README
"Database" says when `scan` writes each file (2026-10-16,
https://git.eeqj.de/sneak/sfdupes/issues/111)
- re-vendor the canonical files and model scripts from `sneak/prompts` `next` at
`e3f79c4`: golangci-lint v2.14.0; lint and test are phases of the `Dockerfile`
that write no image, and `make test` runs the suite under the race detector,
so `Dockerfile.lint`, `script/verify-lint-image-pin` and `make test-race` are
gone; every `docker build` in `script/` passes a new `CACHEBUST` value, which
every stage of the `Dockerfile` declares first, so every `RUN` step runs on
every build, while the steps that compile keep Go's build cache and the tests
run with `-count=1`; prettier runs on the host, from the node and yarn
`script/bootstrap` installs, so the `prettier` and `markdown` stages are gone
and the build stage installs `git` and `make` itself; a new push cancels the
workflow's older run on the same branch, and a run stops after 20 minutes;
`.claude/settings.json` is deleted (2026-10-15,
https://git.eeqj.de/sneak/sfdupes/issues/95)
- with `-x`, an operand under another operand is walked on its own instead of
being dropped when a directory from it (from its directory, for a regular
file) up to but not including that operand is on a different filesystem than
that operand, whose walk then cannot reach it, and the records of files gone
from below it are deleted (2026-10-14,
https://git.eeqj.de/sneak/sfdupes/issues/106)
- with `-x`, `scan` keeps the records below a directory on another filesystem
under its operand, and counts their sizes in the size census, instead of
deleting them (2026-10-14, https://git.eeqj.de/sneak/sfdupes/issues/99)
- the hash and content phases open each file without blocking and check that it
is still a regular file, so one replaced by a FIFO or device node after it was
statted is warned about and skipped instead of hanging the scan (2026-10-14,
@@ -107,26 +49,19 @@
https://git.eeqj.de/sneak/sfdupes/issues/12)
- cut the narration from `TODO.md` Completed Steps and from the comments in
`script/`, `Dockerfile` and `Dockerfile.lint` (gone since
https://git.eeqj.de/sneak/sfdupes/issues/95); §Workflow now branches from and
merges to `next` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/49)
`script/` and both Dockerfiles; §Workflow now branches from and merges to
`next` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/49)
- `make test-race` ran the test suite under the race detector in a cgo-enabled
- `make test-race` runs the test suite under the race detector in a cgo-enabled
container, outside `make check` (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/18). Since
https://git.eeqj.de/sneak/sfdupes/issues/95 `make test` itself runs the suite
under the race detector, in the `Dockerfile`'s Debian-based `test` phase, and
`make test-race` is gone
https://git.eeqj.de/sneak/sfdupes/issues/18)
- a bare `docker build .` failed, naming `script/cibuild` and `script/docker`,
rather than serve the gates from cache (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/39). Since
https://git.eeqj.de/sneak/sfdupes/issues/95 a bare build succeeds, as
`REPO_POLICIES.md` requires, and may serve the gates from cache; the builds in
`script/` pass a new `CACHEBUST` value, so theirs always run
- a bare `docker build .` fails with a message naming `script/cibuild` and
`script/docker` instead of serving the gates from cache (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/39)
- `make fmt` and `make fmt-check` run prettier over all Markdown, and CI checks
it; all Markdown reformatted (2026-10-04,
- `make fmt` and `make fmt-check` run prettier over all Markdown, in Docker, and
CI checks it; all Markdown reformatted (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/19)
- `script/lint` writes no image, so a run no longer leaves an untagged one
@@ -169,12 +104,9 @@
- README documents install, Docker, a daily cron scan and how to read and check
the reports (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/54)
- the `Dockerfile` build stage kept the Go module cache out of `builder`'s home
and copied the sources with `--chown`, so no `chown -R` walked them
(2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/43). Since
https://git.eeqj.de/sneak/sfdupes/issues/95 there is no `builder` user and
nothing changes owner: the build stage only compiles, as root, and the tests
run as `nobody` in the `test` phase
- the `Dockerfile` build stage keeps the Go module cache out of `builder`'s home
and copies the sources with `--chown`, so no `chown -R` walks them
(2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/43)
- `--version` prints `sfdupes VERSION` to stdout; README documents it and
`--help` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/15)
@@ -238,46 +170,97 @@
- fix the lint-image pin comments and `FROM` form in `Dockerfile` and
`Dockerfile.lint` (2026-08-10, branch `next`, closes
https://git.eeqj.de/sneak/sfdupes/issues/25): both pins became the policy
https://git.eeqj.de/sneak/sfdupes/issues/25): both pins are now the policy
`# image:vX.Y.Z, YYYY-MM-DD` comment over a bare `FROM image@sha256:...`,
without the false `(Debian-based)` note or the tag. Since
https://git.eeqj.de/sneak/sfdupes/issues/95 the `Dockerfile`'s `lint` phase
holds the only golangci-lint pin, in that form, so `Dockerfile.lint` and
`script/verify-lint-image-pin`, which compared the two pins, are gone.
without the false `(Debian-based)` note or the tag; digest unchanged.
`script/verify-lint-image-pin` still matches the tagless form, and a tag on
one side only is caught as a plain mismatch.
- run all linting in Docker via `Dockerfile.lint` and `script/lint` (2026-08-10,
branch `next`, closes https://git.eeqj.de/sneak/sfdupes/issues/46): per the
owner ruling the linter is never installed on a host, and
`golangci-lint config verify` runs before `golangci-lint run`.
`script/bootstrap` stopped installing or pinning the linter, and
`script/verify-linter-pin` was retired. Since
https://git.eeqj.de/sneak/sfdupes/issues/95 both commands run in the
`Dockerfile`'s `lint` phase, which `script/lint` builds alone and the build
stage depends on through `COPY --from=lint /src/go.sum /dev/null`;
`Dockerfile.lint` and `script/verify-lint-image-pin` are gone. Nothing inside
an image build may run docker, so the phase calls `golangci-lint` directly.
owner ruling the linter is never installed on a host. `Dockerfile.lint` copies
the repo into the digest-pinned `golangci/golangci-lint:v2.12.2` image and
runs `golangci-lint config verify` and `golangci-lint run` as build steps;
`script/lint` builds it. `script/bootstrap` no longer installs or pins the
linter, and warns rather than fails when `docker` is absent;
`ENV PATH=/home/builder/go/bin:$PATH` went with its `go install`.
`script/verify-linter-pin` is retired; `script/verify-lint-image-pin`, a gate
in both files, compares their two `FROM` lines and restates neither pin.
Traps: an unchanged tree lets a lint build pass in under a second having run
no linter, so every gate `RUN` references `ARG CHECK_EPOCH` (BuildKit hashes
the expanded command) and `script/lint` passes `"$(date +%s)-$$"`, the PID
because two runs land in the same second easily. Nothing inside an image build
may shell out to docker, so the `Dockerfile` lint stage calls `golangci-lint`
directly and the build stage runs `make test` and `make fmt-check` instead of
`make check`, through `make` because the Makefile's `export CGO_ENABLED = 0`
only reaches what it invokes. `COPY --from=lint /src/go.sum /dev/null`
replaces the copied linter binary as the only edge making the build stage wait
for lint; dropping it would end fail-fast linting under a still-green build.
`golangci-lint config verify`, included per the ruling, validates from an
embedded schema with no network call, but `go mod download` above the gates
still needs the network on a cold cache. Verified: `make lint` green with no
`golangci-lint` on `PATH`; two back-to-back `script/lint` runs on an untouched
tree both ran the linter (27.7s and 28.7s in the lint step, `COPY . .`
`CACHED` above); a planted unused variable failed `script/lint`, and failed
`make docker` at `[lint 9/9]` with the build stage stopped at
`[builder 3/12]`; the drift guard fails on a tag-only, a digest-only and an
unreadable reference, naming both sides; under `--network none` config verify
passes a valid config and rejects an invalid one; `make docker` green in 5m35s
with all six gates run under one epoch (lint 37.6s, test 25.2s reporting
`ok sneak.berlin/go/sfdupes 1.938s coverage: 88.5%`, not `(cached)`); in the
builder image with the Go test cache off, `--user 0:0` still fails
`TestScanHardlinkRunFailsTogether` where the unprivileged user passes. Noted
for follow-up, not fixed here: `golangci-lint` warns that `gomodguard` is
deprecated since v2.12.0 in favour of `gomodguard_v2`.
- install the Docker build stage's prerequisites by running `script/bootstrap`
instead of `apk add --no-cache make` inline (2026-08-09, branch
`dockerfile-bootstrap`, closes https://git.eeqj.de/sneak/sfdupes/issues/42),
with `script/verify-linter-pin` failing the build unless the linter copied
from the lint stage was the version `script/bootstrap` pinned. Builds then
took up to 5m14s cold, mostly in a `chown -R` of the module cache, filed as
https://git.eeqj.de/sneak/sfdupes/issues/43. Since
https://git.eeqj.de/sneak/sfdupes/issues/95 the build stage installs `git` and
`make` with `apk add --no-cache` and only compiles; the `lint` and `test`
phases are the gates
`dockerfile-bootstrap`, closes https://git.eeqj.de/sneak/sfdupes/issues/42):
the stage copies `script/` plus `go.mod`/`go.sum` and runs `script/bootstrap`,
which ends in `go mod download`, so the separate call to it is gone.
`COPY --from=lint /usr/bin/golangci-lint` stays and moves above the bootstrap
layer: it is the only edge making this stage depend on the lint stage, so
deleting it would end fail-fast linting silently. A new
`script/verify-linter-pin`, run in the build stage before bootstrap, fails the
build naming both versions unless that copied binary is the version
`script/bootstrap` pins; a pin it cannot read is a hard failure, not a skip.
`$GOPATH/bin` joins `PATH`, where bootstrap's `go install` lands. Everything
added sits above `ARG CHECK_EPOCH`, and the `chown` and `USER builder` still
precede `make check`. Verified: the guard fails the build with both versions
named when the lint stage's linter is faked to another version, and passes an
unmodified build; bootstrap runs clean under Alpine's `sh` and `apk`, finding
the copied linter already at the pin; a second build served the bootstrap and
dependency layers `CACHED` while both gates ran with a fresh epoch; a planted
`unused` finding failed the build at the lint gate in 48.9s with the build
stage's `make check` never starting; and the suite run in the image as
`--user 0:0` fails `TestScanHardlinkRunFailsTogether`, so the drop to the
unprivileged user is still needed. That last check needs the Go test cache
off: as root it first reported `ok ... (cached)`, reusing the build-time
result. Build times on a noisy shared host: 2m13s on an unchanged tree, 2m17s
and 4m29s after a source change, 5m14s cold, which breaches the policy
ceiling; `chown -R builder:builder /src /home/builder` walks the module cache
and alone varied from 77s to 210s across those builds, and `main` measured
5m03s cold with a 209s `chown`. Filed as
https://git.eeqj.de/sneak/sfdupes/issues/43
- bust the Docker layer cache for the gate steps, so `script/cibuild` and
`script/docker` cannot report a green they did not earn (2026-08-09, branch
`cibuild-cache-bust`, closes https://git.eeqj.de/sneak/sfdupes/issues/32): the
`Dockerfile` copies the tree before its gates, so on an unchanged tree Docker
served them from cache and the build exited 0 having run nothing. The fix was
a `CHECK_EPOCH` build argument; since
https://git.eeqj.de/sneak/sfdupes/issues/95 every `docker build` in `script/`
passes a new `CACHEBUST` value instead, which every stage of the `Dockerfile`
declares first. Run as root, the tests fail
`TestScanHardlinkRunFailsTogether`, because root reads through the `chmod(0)`
the test relies on, so the `test` phase runs them as `nobody`
served them from cache and the build exited 0 having run nothing. Both scripts
now pass `--build-arg CHECK_EPOCH="$(date +%s)"`. `ARG` is per stage and the
gates span two stages, so it is declared in both; BuildKit hashes the expanded
command, so each gate `RUN` echoes the epoch, which also logs it as evidence
the layer ran. It sits below the dependency layers so they stay cached.
Verified under `BUILDKIT_PROGRESS=plain`, each script run twice back to back
on an unchanged tree: all three gates ran on all four runs with a fresh epoch
(`script/cibuild` 78.8s then 61.1s; `script/docker` 61.1s then 53.4s), and
thirteen steps were still served `CACHED`. With a planted `unused` finding the
build failed at `make lint` in 36.1s and the build-stage `make check` never
started. Run as root, the same image fails `TestScanHardlinkRunFailsTogether`,
because root reads through the `chmod(0)` the test relies on, so the build
stage must drop to the unprivileged `builder` user. Local fix only;
propagating it to the canonical templates is
https://git.eeqj.de/sneak/prompts/issues/26
- check the installed golangci-lint version in `script/bootstrap` instead of
only its presence (2026-08-09, branch `bootstrap-version-check`, closes
https://git.eeqj.de/sneak/sfdupes/issues/24): the version lives only in
@@ -433,3 +416,6 @@ Accepted divergences (no action):
- flat single-package layout with `.go` files in the repo root — fine for a
small single-binary tool per the Go styleguide; the tracker audit agrees
- `make test` runs without `-race` — the repo mandates `CGO_ENABLED=0` (pure-Go
builds) and the race detector requires cgo, so the detector runs in a separate
cgo-enabled container, `make test-race`, which is not part of `make check`
cancel_test.go
+4 -6
View File
@@ -344,10 +344,9 @@ func storedPaths(t *testing.T, path string) []string {
// TestRunScanInterrupted calls the scan entrypoint with a context that
// is already cancelled, as when a signal arrives at once. It must return
// errInterrupted promptly, with its line on stderr after the one naming
// the database and nothing on stdout, leave the database valid and as
// it was, and leave nothing in the way of the next scan, which must
// bring the database up to date.
// errInterrupted promptly with its one line on stderr and nothing on
// stdout, leave the database valid and as it was, and leave nothing in
// the way of the next scan, which must bring the database up to date.
func TestRunScanInterrupted(t *testing.T) {
path := testDBPath(t)
t.Setenv(databaseEnv, path)
@@ -390,8 +389,7 @@ func TestRunScanInterrupted(t *testing.T) {
err, errInterrupted)
}
want := "scan: database " + path + " (from " + databaseEnv + ")\n" +
"scan: interrupted after 0 files\n"
want := "scan: interrupted after 0 files\n"
if got := stderr()[shown:]; got != want {
t.Errorf("stderr = %q, want %q", got, want)
}
db.go
+22 -100
View File
@@ -11,7 +11,6 @@ import (
"path/filepath"
"slices"
"strconv"
"strings"
"time"
"golang.org/x/sys/unix"
@@ -92,36 +91,13 @@ var errSchemaVersion = errors.New("unsupported database schema version")
var errScanRunning = errors.New("another scan is running")
// databasePath resolves the database location: SFDUPES_DATABASE when
// set and non-empty, the compiled-in default otherwise. It returns the
// path, with the working directory, its symlinks resolved, put in front
// of it when it is relative, and where the path came from, "default" or
// "from SFDUPES_DATABASE", for the line each subcommand prints first on
// stderr.
func databasePath() (string, string, error) {
path, source := defaultDatabasePath, "default"
// set and non-empty, the compiled-in default otherwise.
func databasePath() string {
if p := os.Getenv(databaseEnv); p != "" {
path, source = p, "from "+databaseEnv
return p
}
if filepath.IsAbs(path) {
return path, source, nil
}
// The working directory as the kernel reports it, with no symlink
// in it. os.Getwd may return PWD instead, which can name it through
// a symlink; a ".." after that symlink then leads somewhere else
// once the path is cleaned, as scan cleans it to create the
// database's directory.
wd, err := unix.Getwd()
if err != nil {
return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
}
// Not filepath.Abs or filepath.Join: they clean the path, which
// drops each ".." together with the directory name before it. When
// that directory is a symlink, the cleaned path names another file.
// The working directory ends in "/" only when it is the root.
return strings.TrimSuffix(wd, "/") + "/" + path, source, nil
return defaultDatabasePath
}
// scanParams are the connection parameters for scan: read-write, with
@@ -403,32 +379,10 @@ func userVersion(ctx context.Context, db *sql.DB) (int, error) {
return v, nil
}
// loadFileRows gives total the number of records, then streams every
// record to fn in path order: byte order, which is the order of the
// primary key, so SQLite does not sort. The count and the records are
// read in one transaction, so they agree while a scan is committing.
func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
fn func(r scanRec),
) error {
// Everything goes through tx: db has one connection, so a query on
// db would wait for tx forever.
tx, err := db.BeginTx(ctx, &sql.TxOptions{ReadOnly: true})
if err != nil {
return fmt.Errorf("read records: %w", err)
}
defer func() { _ = tx.Rollback() }()
var n int64
err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
if err != nil {
return fmt.Errorf("count records: %w", err)
}
total(n)
rows, err := tx.QueryContext(ctx,
// loadFileRows streams every record to fn in path order: byte order,
// which is the order of the primary key, so SQLite does not sort.
func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
rows, err := db.QueryContext(ctx,
"SELECT path, size, mtime, mtime_nsec, head, tail, content "+
"FROM files ORDER BY path")
if err != nil {
@@ -536,18 +490,6 @@ func loadDupeRows(ctx context.Context, db *sql.DB,
return records, nil
}
// countRecords returns the number of records in the database.
func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
var n int64
err := db.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
if err != nil {
return 0, fmt.Errorf("count records: %w", err)
}
return n, nil
}
// loadFileMeta streams every record's path, size, mtime, and whether
// it carries hashes to fn. Scan change detection needs no hash
// values, and skipping the hash columns keeps the scan's in-memory
@@ -586,46 +528,26 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
return nil
}
// contentGroupsSQL selects each group (the records sharing a size,
// head, and tail) of records of at least headTailMin bytes that has more
// than one record and at least one record without a content hash, with
// the number of its records.
const contentGroupsSQL = `
SELECT size, head, tail, COUNT(*) AS records
FROM files
WHERE size >= ? AND head <> ''
GROUP BY size, head, tail
HAVING COUNT(*) > 1 AND SUM(content = '') > 0
`
// contentCandidatesSQL selects every record of the groups
// contentGroupsSQL selects, with whether each record has a content
// hash. SQLite does the grouping, so no other record's hashes are
// loaded into memory; the rows come ordered by size, head, and tail, so
// each group's rows arrive together.
// contentCandidatesSQL selects every record of at least headTailMin
// bytes whose size, head, and tail equal another record's, in each
// group (the records sharing a size, head, and tail) where at least one
// record has no content hash, with whether each record has one. SQLite
// does the grouping, so no other record's hashes are loaded into
// memory; the rows come ordered by size, head, and tail, so each
// group's rows arrive together.
const contentCandidatesSQL = `
SELECT f.path, f.size, f.mtime, f.mtime_nsec, f.head, f.tail, f.content <> ''
FROM files AS f
JOIN (` + contentGroupsSQL + `) AS g USING (size, head, tail)
JOIN (
SELECT size, head, tail
FROM files
WHERE size >= ? AND head <> ''
GROUP BY size, head, tail
HAVING COUNT(*) > 1 AND SUM(content = '') > 0
) AS g USING (size, head, tail)
ORDER BY size, head, tail
`
// countContentCandidates returns the number of rows of
// contentCandidatesSQL, adding up the records of the groups
// contentGroupsSQL selects, so it neither joins nor sorts.
func countContentCandidates(ctx context.Context, db *sql.DB) (int64, error) {
var n int64
err := db.QueryRowContext(ctx,
"SELECT COALESCE(SUM(records), 0) FROM ("+contentGroupsSQL+")",
headTailMin).Scan(&n)
if err != nil {
return 0, fmt.Errorf("count content candidates: %w", err)
}
return n, nil
}
// loadContentCandidates streams the rows of contentCandidatesSQL to fn:
// each record, without its content hash, and whether it has one.
func loadContentCandidates(ctx context.Context, db *sql.DB,
db_test.go
+15 -159
View File
@@ -43,47 +43,16 @@ func openTestDB(t *testing.T) *sql.DB {
}
func TestDatabasePath(t *testing.T) {
// README §Database: SFDUPES_DATABASE when set and non-empty, the
// default otherwise, with the working directory, its symlinks
// resolved, put in front of a relative path. Nothing is cleaned, so
// a ".." stays.
dir, err := filepath.EvalSymlinks(t.TempDir())
if err != nil {
t.Fatal(err)
t.Setenv(databaseEnv, "")
if got := databasePath(); got != defaultDatabasePath {
t.Errorf("databasePath() = %q, want %q", got, defaultDatabasePath)
}
t.Chdir(dir)
t.Setenv(databaseEnv, "/custom/place.sqlite")
fromEnv := "from " + databaseEnv
cases := []struct {
env, path, source string
}{
{"", defaultDatabasePath, "default"},
{"/custom/place.sqlite", "/custom/place.sqlite", fromEnv},
{"/custom/link/../place.sqlite", "/custom/link/../place.sqlite",
fromEnv},
{"sub/place.sqlite", dir + "/sub/place.sqlite", fromEnv},
{"link/../place.sqlite", dir + "/link/../place.sqlite", fromEnv},
}
for _, tc := range cases {
t.Setenv(databaseEnv, tc.env)
path, source, err := databasePath()
if err != nil || path != tc.path || source != tc.source {
t.Errorf("databasePath() with %s=%q = %q, %q, %v; want %q, %q",
databaseEnv, tc.env, path, source, err, tc.path, tc.source)
}
}
// In the root directory the path gets one slash in front, not two.
t.Chdir("/")
t.Setenv(databaseEnv, "place.sqlite")
path, _, err := databasePath()
if err != nil || path != "/place.sqlite" {
t.Errorf("databasePath() in / = %q, %v; want %q",
path, err, "/place.sqlite")
if got := databasePath(); got != "/custom/place.sqlite" {
t.Errorf("databasePath() = %q, want the env override", got)
}
}
@@ -284,63 +253,12 @@ func TestCloseScanDatabaseWhileReportOpen(t *testing.T) {
defer func() { _ = reportDB.Close() }()
err = loadFileRows(t.Context(), reportDB, func(int64) {},
func(scanRec) {})
err = loadFileRows(t.Context(), reportDB, func(scanRec) {})
if err != nil {
t.Fatalf("loadFileRows: %v", err)
}
}
// TestLoadFileRowsCountAgreesDuringScan has a scan commit records after
// loadFileRows has counted the records and before it reads them, as
// when trees runs during a scan: it must read exactly as many records
// as it counted.
func TestLoadFileRowsCountAgreesDuringScan(t *testing.T) {
t.Parallel()
path := testDBPath(t)
scanDB, err := openScanDatabase(t.Context(), path)
if err != nil {
t.Fatal(err)
}
defer func() { _ = scanDB.Close() }()
recs := smokeTreeRecs()
err = applyChanges(t.Context(), scanDB, recs[:3], nil, nil)
if err != nil {
t.Fatal(err)
}
reportDB, err := openReportDatabase(t.Context(), path)
if err != nil {
t.Fatal(err)
}
defer func() { _ = reportDB.Close() }()
var counted, read int64
err = loadFileRows(t.Context(), reportDB, func(n int64) {
counted = n
err := applyChanges(t.Context(), scanDB, recs[3:], nil, nil)
if err != nil {
t.Error(err)
}
}, func(scanRec) { read++ })
if err != nil {
t.Fatal(err)
}
if counted != 3 || read != counted {
t.Errorf("counted %d records and read %d, want 3 and 3",
counted, read)
}
}
func TestApplyChangesRoundTrip(t *testing.T) {
t.Parallel()
@@ -360,10 +278,8 @@ func TestApplyChangesRoundTrip(t *testing.T) {
},
}
prog := newProgress(progressParams{label: "update", total: 4})
defer prog.finish()
err := applyChanges(t.Context(), db, recs, nil, prog)
err := applyChanges(t.Context(), db, recs, nil,
newProgress("update", 2))
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
@@ -382,7 +298,7 @@ func TestApplyChangesRoundTrip(t *testing.T) {
}
err = applyChanges(t.Context(), db, []scanRec{upd},
[]string{"/a/tab\tnew\nline"}, prog)
[]string{"/a/tab\tnew\nline"}, newProgress("update", 2))
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
@@ -410,10 +326,8 @@ func TestApplyChangesBatching(t *testing.T) {
})
}
prog := newProgress(progressParams{label: "update", total: int64(2 * n)})
defer prog.finish()
err := applyChanges(t.Context(), db, recs, nil, prog)
err := applyChanges(t.Context(), db, recs, nil,
newProgress("update", int64(n)))
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
@@ -427,7 +341,8 @@ func TestApplyChangesBatching(t *testing.T) {
deletes = append(deletes, r.path)
}
err = applyChanges(t.Context(), db, nil, deletes, prog)
err = applyChanges(t.Context(), db, nil, deletes,
newProgress("update", int64(n)))
if err != nil {
t.Fatalf("applyChanges deletes: %v", err)
}
@@ -436,62 +351,3 @@ func TestApplyChangesBatching(t *testing.T) {
t.Fatalf("records = %d, want 0", len(got))
}
}
// TestCountContentCandidates checks that countContentCandidates counts
// the records the content phase's search returns: those of each group
// of two or more records of headTailMin or more with a head, where at
// least one has no content hash.
func TestCountContentCandidates(t *testing.T) {
t.Parallel()
db := openTestDB(t)
// Each group's records: size, head, and content, one per record.
groups := []struct {
size int64
head string
contents []string
}{
{headTailMin, "h", []string{"", "c", "c"}}, // returned
{headTailMin + 1, "h", []string{"", ""}}, // returned
{headTailMin + 2, "h", []string{"c", "c"}}, // all hashed
{headTailMin + 3, "h", []string{""}}, // one record
{headTailMin - 1, "h", []string{"", ""}}, // too small
{headTailMin + 4, "", []string{"", ""}}, // no head
}
var recs []scanRec
for _, g := range groups {
for _, content := range g.contents {
recs = append(recs, scanRec{
size: g.size, mtime: time.Unix(1, 0), head: g.head,
tail: "t", content: content,
path: fmt.Sprintf("/r/%d", len(recs)),
})
}
}
err := applyChanges(t.Context(), db, recs, nil, nil)
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
got, err := countContentCandidates(t.Context(), db)
if err != nil {
t.Fatalf("countContentCandidates: %v", err)
}
var returned int64
err = loadContentCandidates(t.Context(), db,
func(scanRec, bool) { returned++ })
if err != nil {
t.Fatalf("loadContentCandidates: %v", err)
}
if got != 5 || returned != 5 {
t.Errorf("count = %d, records returned = %d, want 5 and 5",
got, returned)
}
}
main_test.go
+10 -272
View File
@@ -285,36 +285,22 @@ func assertFatalOutput(t *testing.T, stderr, stdout string) {
func TestRunMissingDatabaseIsFatal(t *testing.T) {
// README §Database: report and trees need an existing database; a
// missing one exits 1 with a message telling the user to run scan,
// after the line naming the database.
// missing one exits 1 with a message telling the user to run scan.
for _, name := range []string{cmdReport, cmdTrees} {
t.Run(name, func(t *testing.T) {
path := testDBPath(t)
t.Setenv(databaseEnv, path)
var stdout bytes.Buffer
var stdout, stderr bytes.Buffer
// run gets os.Stderr, where the subcommand prints its line,
// so the capture shows the two in the order printed.
stderr := captureStderr(t)
code := run([]string{name}, &stdout, os.Stderr)
code := run([]string{name}, &stdout, &stderr)
if code != exitFatal {
t.Errorf("run(%s) = %d, want %d", name, code, exitFatal)
}
// trees shows its open phase, as it starts and as it ends,
// before the error.
opening := ""
if name == cmdTrees {
opening = treesOpenLine + "\n" + treesOpenLine + "\n"
}
want := name + ": database " + path + " (from " + databaseEnv +
")\n" + opening +
"sfdupes: " + path + ": no database (run \"sfdupes " +
want := "sfdupes: " + path + ": no database (run \"sfdupes " +
"scan\" first, or set " + databaseEnv + ")\n"
if got := stderr(); got != want {
if got := stderr.String(); got != want {
t.Errorf("stderr = %q, want %q", got, want)
}
@@ -325,247 +311,6 @@ func TestRunMissingDatabaseIsFatal(t *testing.T) {
}
}
func TestRunNamesRelativeDatabase(t *testing.T) {
// README §Database: each subcommand's first line on stderr names the
// database, a relative SFDUPES_DATABASE made absolute against the
// working directory. scan calls it new until a scan has created it.
path := testDBPath(t)
t.Chdir(filepath.Dir(path))
t.Setenv(databaseEnv, filepath.Base(path))
dir := t.TempDir()
from := " (from " + databaseEnv + ")\n"
want := "scan: new database " + path + from
if got := scanOK(t, dir); !strings.HasPrefix(got, want) {
t.Errorf("first scan stderr = %q, want it to start %q", got, want)
}
want = "scan: database " + path + from
if got := scanOK(t, dir); !strings.HasPrefix(got, want) {
t.Errorf("second scan stderr = %q, want it to start %q", got, want)
}
for _, name := range []string{cmdReport, cmdTrees} {
stderr := captureStderr(t)
code := run([]string{name}, io.Discard, os.Stderr)
want = name + ": database " + path + from
if got := stderr(); code != exitOK || !strings.HasPrefix(got, want) {
t.Errorf("run(%s) = %d with stderr %q, want %d and it to "+
"start %q", name, code, got, exitOK, want)
}
}
}
func TestRunUsesDatabaseThroughSymlinkedDirectory(t *testing.T) {
// README §Database: the path names the file exactly. With link a
// symlink to the directory real/sub, link/../db.sqlite names
// real/db.sqlite, not db.sqlite beside link. Every subcommand must
// use that file, relative or absolute, and its first line must name
// the path as set, with the working directory put in front of a
// relative one.
dir, err := filepath.EvalSymlinks(t.TempDir())
if err != nil {
t.Fatal(err)
}
t.Chdir(dir)
err = os.MkdirAll(filepath.Join(dir, "real", "sub"), 0o750)
if err != nil {
t.Fatal(err)
}
err = os.Symlink(filepath.Join(dir, "real", "sub"),
filepath.Join(dir, "link"))
if err != nil {
t.Fatal(err)
}
named := dir + "/link/../db.sqlite"
from := " (from " + databaseEnv + ")\n"
tree := t.TempDir()
t.Setenv(databaseEnv, "link/../db.sqlite")
want := "scan: new database " + named + from
if got := scanOK(t, tree); !strings.HasPrefix(got, want) {
t.Errorf("relative scan stderr = %q, want it to start %q", got, want)
}
// The absolute path names the database the relative one created.
t.Setenv(databaseEnv, named)
want = "scan: database " + named + from
if got := scanOK(t, tree); !strings.HasPrefix(got, want) {
t.Errorf("absolute scan stderr = %q, want it to start %q", got, want)
}
for _, name := range []string{cmdReport, cmdTrees} {
stderr := captureStderr(t)
code := run([]string{name}, io.Discard, os.Stderr)
want = name + ": database " + named + from
if got := stderr(); code != exitOK || !strings.HasPrefix(got, want) {
t.Errorf("run(%s) = %d with stderr %q, want %d and it to "+
"start %q", name, code, got, exitOK, want)
}
}
_, err = os.Stat(filepath.Join(dir, "real", "db.sqlite"))
if err != nil {
t.Errorf("database the path names: %v", err)
}
// With no file at the cleaned path, report and trees succeeded on
// the database in real.
_, err = os.Stat(filepath.Join(dir, "db.sqlite"))
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("database at the cleaned path: stat error %v, want it "+
"missing", err)
}
}
func TestRunScanFromSymlinkedWorkingDirectory(t *testing.T) {
// README §Database: a relative path gets the working directory, its
// symlinks resolved, put in front of it. With home/proj a symlink
// to data/proj, entered as the working directory through the
// symlink, ../new/db.sqlite names data/new/db.sqlite. scan must
// create that directory and file, and nothing beside home/proj.
dir, err := filepath.EvalSymlinks(t.TempDir())
if err != nil {
t.Fatal(err)
}
err = os.MkdirAll(filepath.Join(dir, "data", "proj"), 0o750)
if err != nil {
t.Fatal(err)
}
err = os.Mkdir(filepath.Join(dir, "home"), 0o750)
if err != nil {
t.Fatal(err)
}
err = os.Symlink(filepath.Join(dir, "data", "proj"),
filepath.Join(dir, "home", "proj"))
if err != nil {
t.Fatal(err)
}
// t.Chdir also sets PWD to the path through the symlink, as a
// shell does after cd.
t.Chdir(filepath.Join(dir, "home", "proj"))
t.Setenv(databaseEnv, "../new/db.sqlite")
want := "scan: new database " + dir + "/data/proj/../new/db.sqlite" +
" (from " + databaseEnv + ")\n"
if got := scanOK(t, t.TempDir()); !strings.HasPrefix(got, want) {
t.Errorf("scan stderr = %q, want it to start %q", got, want)
}
_, err = os.Stat(filepath.Join(dir, "data", "new", "db.sqlite"))
if err != nil {
t.Errorf("database the path names: %v", err)
}
_, err = os.Lstat(filepath.Join(dir, "home", "new"))
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("home/new: stat error %v, want it missing", err)
}
}
func TestRunEscapesDatabasePath(t *testing.T) {
// README §Database: each subcommand's first line escapes the
// database path like the paths in a report, so a tab, newline or
// backslash in it keeps the line one line.
dir := t.TempDir()
t.Setenv(databaseEnv, dir+"/a\tb\nc\\d.sqlite")
escaped := dir + `/a\tb\nc\\d.sqlite`
from := " (from " + databaseEnv + ")\n"
want := "scan: new database " + escaped + from
if got := scanOK(t, t.TempDir()); !strings.HasPrefix(got, want) {
t.Errorf("scan stderr = %q, want it to start %q", got, want)
}
for _, name := range []string{cmdReport, cmdTrees} {
stderr := captureStderr(t)
code := run([]string{name}, io.Discard, os.Stderr)
want = name + ": database " + escaped + from
if got := stderr(); code != exitOK || !strings.HasPrefix(got, want) {
t.Errorf("run(%s) = %d with stderr %q, want %d and it to "+
"start %q", name, code, got, exitOK, want)
}
}
}
func TestRunNamesDefaultDatabase(t *testing.T) {
// README §Database: with SFDUPES_DATABASE empty, each subcommand's
// first line on stderr names the default database. A database may
// exist at the default path on the machine running the test, so
// nothing here may create or read one: scan gets an operand that
// does not exist, which stops it before it takes the lock, and
// report and trees a cancelled context, which stops them before
// they read anything. trees shows its open phase after the line.
t.Setenv(databaseEnv, "")
// Whether scan calls the database new depends on that machine too.
scanWant := "scan: database " + defaultDatabasePath + " (default)\n"
_, err := os.Stat(defaultDatabasePath)
if errors.Is(err, fs.ErrNotExist) {
scanWant = "scan: new database " + defaultDatabasePath +
" (default)\n"
}
missing := filepath.Join(t.TempDir(), "nope")
cases := map[string]struct {
run func() error
want string
}{
cmdScan: {
run: func() error {
return runScan(t.Context(), []string{missing}, 1, false)
},
want: scanWant,
},
cmdReport: {
run: func() error {
return runReport(cancelledContext(t), io.Discard)
},
want: "report: database " + defaultDatabasePath + " (default)\n",
},
cmdTrees: {
run: func() error {
return runTrees(cancelledContext(t), io.Discard)
},
want: "trees: database " + defaultDatabasePath + " (default)\n" +
treesOpenLine + "\n" + treesOpenLine + "\n",
},
}
for name, tc := range cases {
stderr := captureStderr(t)
err = tc.run()
if err == nil {
t.Errorf("%s: error = nil, want it stopped", name)
}
if got := stderr(); got != tc.want {
t.Errorf("%s stderr = %q, want %q", name, got, tc.want)
}
}
}
func TestRunUsageErrors(t *testing.T) {
// Usage errors keep exiting 2 with cobra's own report on stderr.
cases := map[string]struct {
@@ -916,8 +661,7 @@ func TestRunReportSucceeds(t *testing.T) {
t.Errorf("stdout = %q, want %q", got, want)
}
want = "report: database " + path + " (from " + databaseEnv + ")\n" +
"report: 2 records read, 1 duplicate groups, 1 dupe files, " +
want = "report: 2 records read, 1 duplicate groups, 1 dupe files, " +
"300 B reclaimable\n"
if got := stderr(); got != want {
t.Errorf("stderr = %q, want %q", got, want)
@@ -950,16 +694,10 @@ func TestRunTreesSucceeds(t *testing.T) {
t.Errorf("stdout = %q, want %q", got, want)
}
// Its phases come between the two lines; see
// TestRunTreesProgressNamesEachPhase.
first := "trees: database " + path + " (from " + databaseEnv + ")\n"
last := "\ntrees: 2 records read, 1 duplicate tree groups, " +
"1 dupe trees, 300 B reclaimable\n"
if got := stderr(); !strings.HasPrefix(got, first) ||
!strings.HasSuffix(got, last) {
t.Errorf("stderr = %q, want it to start %q and end %q",
got, first, last)
want = "trees: 2 records read, 1 duplicate tree groups, 1 dupe trees, " +
"300 B reclaimable\n"
if got := stderr(); got != want {
t.Errorf("stderr = %q, want %q", got, want)
}
assertNoSidecars(t, path)
progress.go
+115 -385
View File
@@ -2,277 +2,122 @@ package main
import (
"fmt"
"io"
"math"
"os"
"slices"
"strings"
"sync"
"time"
"github.com/schollz/progressbar/v3"
"golang.org/x/term"
)
// plainInterval is the time between progress lines while a phase runs,
// when stderr is not a TTY.
// plainInterval is the minimum time between progress lines when stderr
// is not a TTY.
const plainInterval = 5 * time.Second
// redrawInterval is the time between redraws of the progress display on
// a TTY.
const redrawInterval = 100 * time.Millisecond
// barThrottle caps how often the TTY progress bar redraws.
const barThrottle = 100 * time.Millisecond
// spinnerType selects the progressbar library's spinner style.
const spinnerType = 14
// barWidth is the width of the progressbar library's bar between its
// two ends, as in the example line in README "Progress".
const barWidth = 10
// walkSpinnerType selects the progressbar library's spinner style used
// for the walk pass, which has no known total.
const walkSpinnerType = 14
// percentScale converts a fraction to a percentage.
const percentScale = 100
// fallbackWidth is the width taken for a terminal whose width cannot be
// read, as the progressbar library takes it.
const fallbackWidth = 80
// spinnerMargin is the columns of a spinner's line besides its text:
// the spinner and the three spaces the library draws around the text,
// and the terminal's last column, which every line stays clear of so
// that no terminal wraps it.
const spinnerMargin = 5
// barMargin is the columns of a bar's line besides its text: the
// percent and the bar the library draws after the text, the spaces
// around them, and the terminal's last column.
const barMargin = barWidth + 11
// stderrIsTTY reports whether stderr is attached to a terminal.
func stderrIsTTY() bool {
return term.IsTerminal(int(os.Stderr.Fd()))
}
// terminalWidth returns the width of the terminal on stderr, or
// fallbackWidth, as the progressbar library does, when it cannot read
// one.
func terminalWidth() int {
width, _, err := term.GetSize(int(os.Stderr.Fd()))
if err != nil || width <= 0 {
return fallbackWidth
}
return width
}
// phaseLabel names phase with its place among phases, as "[2/5] walk".
func phaseLabel(phases []string, phase string) string {
return fmt.Sprintf("[%d/%d] %s",
slices.Index(phases, phase)+1, len(phases), phase)
}
// progressParams describe one phase's progress display as it starts.
type progressParams struct {
label string // the phase and its place, from phaseLabel
unit string // what the phase counts, as "files"
total int64 // the items the phase will complete; -1 when not known
estimate bool // total is an estimate, which the count may pass
waitingFor string // what the phase waits for until setTotal is called
}
// progress renders one phase's progress on stderr. On a TTY the
// progressbar library draws line, fitted to the terminal's width: after
// the library's spinner, or, for a phase with an exact total, before the
// library's bar when the terminal has room for the bar beside it. It is
// drawn again every redrawInterval, so its elapsed time keeps moving
// while the phase waits for its next item. When stderr is not a TTY it
// emits no ANSI redraws: it prints line as the phase starts, every
// plainInterval while it runs, and as it ends.
// progress renders one scan pass's progress on stderr. On a TTY it
// delegates to the progressbar library (spinner style when the total is
// unknown, full bar with count/percent/rate/elapsed/ETA otherwise). When
// stderr is not a TTY it emits no ANSI redraws: it prints a plain
// one-line update as the pass starts, then no more often than every
// plainInterval.
//
// The draws come from a goroutine of their own, so mu guards the fields
// below it. Every method must be called from the main goroutine. A nil
// *progress is a valid no-display receiver: every method is a no-op, so
// batched database flushes during the hash phase can reuse the update
// phase's helpers without rendering anything, and its writer writes
// with no display to clear.
// All methods must be called from the main goroutine only. On a TTY
// the library also redraws a spinner from its own goroutine, several
// times a second, so its count and elapsed time stay current while a
// pass waits for its next item. A nil *progress is a valid
// no-display receiver: every method is a no-op, so batched database
// flushes during the streaming pass can reuse the update-pass helpers
// without rendering anything.
type progress struct {
width func() int // reads the terminal's width; nil when not a TTY
stop chan struct{} // closed by finish to end the draws
done chan struct{} // closed once the draws have ended
mu sync.Mutex
bar *progressbar.ProgressBar // what the library draws; nil until then
withBar bool // bar is the library's bar, not its spinner
widest int // the widest line bar has drawn, in columns
label string
unit string
total int64
estimate bool
waitingFor string
count int64
start time.Time // when the phase started, for the elapsed time
rateStart time.Time // when the count started, for the rate
label string
total int64 // -1 when unknown (walk pass)
bar *progressbar.ProgressBar
count int64
start time.Time
last time.Time
}
// newProgress starts the display of one phase on stderr.
func newProgress(params progressParams) *progress {
func newProgress(label string, total int64) *progress {
p := &progress{label: label, total: total, start: time.Now()}
if stderrIsTTY() {
return startProgress(params, terminalWidth, redrawInterval)
p.bar = newBar(label, total)
return p
}
return startProgress(params, nil, plainInterval)
}
// startProgress shows the phase params describes at once, and again
// every interval until finish: with the progressbar library on a
// terminal, whose width each draw reads by calling width, or as a plain
// line when width is nil.
func startProgress(params progressParams, width func() int,
interval time.Duration,
) *progress {
now := time.Now()
p := &progress{
width: width, stop: make(chan struct{}), done: make(chan struct{}),
label: params.label, unit: params.unit, total: params.total,
estimate: params.estimate, waitingFor: params.waitingFor,
start: now, rateStart: now,
}
// Show the zero state at once: the first item may take minutes,
// and a phase must never look hung.
p.draw()
go func() {
defer close(p.done)
ticker := time.NewTicker(interval)
defer ticker.Stop()
for {
select {
case <-p.stop:
return
case <-ticker.C:
p.draw()
}
}
}()
// Print the zero state at once: the first item may take minutes,
// and a pass must never look hung.
p.last = p.start
fmt.Fprintln(os.Stderr, p.plainLine())
return p
}
// draw shows the phase's progress: on a TTY in place of the line
// before, and otherwise as a plain line.
func (p *progress) draw() {
p.mu.Lock()
defer p.mu.Unlock()
if p.width == nil {
text, _ := p.line(math.MaxInt, true)
fmt.Fprintln(os.Stderr, text)
return
}
width := p.width()
// A phase with an exact total gets the library's bar when its line,
// without the percent the bar shows, fits whole beside the bar. A
// total of 0 leaves the bar nothing to fill.
text, withBar := "", false
if p.total > 0 && !p.estimate {
text, withBar = p.line(width-barMargin, false)
}
margin := barMargin
if !withBar {
margin = spinnerMargin
text, _ = p.line(width-margin, true)
}
// The library makes a bar or a spinner, and before each draw erases
// its line with as many spaces as the widest line it has drawn. A
// display gets a new one when it turns from one to the other, as its
// line grows or the terminal is resized, and when the terminal has
// been made too narrow for that erase, which would wrap and leave a
// line behind at every draw.
if p.bar == nil || p.withBar != withBar || p.widest >= width {
p.newBar(withBar, width)
}
if withBar {
_ = p.bar.Set64(p.count)
}
p.bar.Describe(text)
// The library drew the text and its margin, less the terminal's last
// column, which the margin keeps clear.
p.widest = max(p.widest, len(text)+margin-1)
}
// newBar has the library make what draw draws: a bar for the phase's
// total when withBar is set, and a spinner when not. Either shows the
// text draw gives it, and nothing of its own besides the spinner, or
// the bar and its percent. p.mu must be held.
func (p *progress) newBar(withBar bool, width int) {
if p.bar != nil {
// Erase what was drawn before, short of the last column of a
// terminal that may have been made narrower since: the library's
// own erase is as wide as the widest line it drew.
blank := strings.Repeat(" ", min(p.widest, width-1))
fmt.Fprint(os.Stderr, "\r"+blank+"\r")
}
total := int64(-1) // the library's spinner
if withBar {
total = p.total
}
p.bar = progressbar.NewOptions64(total,
// newBar builds the TTY display for newProgress.
func newBar(label string, total int64) *progressbar.ProgressBar {
opts := []progressbar.Option{
progressbar.OptionSetWriter(os.Stderr),
progressbar.OptionSetWidth(barWidth),
progressbar.OptionSpinnerType(spinnerType),
// The spinner turns at each draw, not on a timer of the
// library's own.
progressbar.OptionSetSpinnerChangeInterval(0),
// The text carries the elapsed time and the ETA.
progressbar.OptionSetElapsedTime(false),
progressbar.OptionSetPredictTime(false),
)
p.withBar, p.widest = withBar, 0
}
// setTotal gives a phase that started without a total its total, once
// it is known. The rate, and so the ETA, count from then on: the time
// spent waiting for the total says nothing about how fast items go.
func (p *progress) setTotal(total int64) {
if p == nil {
return
progressbar.OptionSetDescription(label),
progressbar.OptionShowCount(),
progressbar.OptionShowIts(),
progressbar.OptionSetItsString("files"),
progressbar.OptionSetElapsedTime(true),
progressbar.OptionThrottle(barThrottle),
// Render at zero immediately: a phase must be visible the
// moment it starts, even before its first item completes.
progressbar.OptionSetRenderBlankState(true),
}
if total >= 0 {
opts = append(opts,
progressbar.OptionSetPredictTime(true),
progressbar.OptionShowElapsedTimeOnFinish(),
)
} else {
opts = append(opts,
progressbar.OptionSetPredictTime(false),
progressbar.OptionSpinnerType(walkSpinnerType),
)
}
p.mu.Lock()
defer p.mu.Unlock()
p.total = total
p.rateStart = time.Now()
return progressbar.NewOptions64(total, opts...)
}
// increment records one completed item, which the display shows at its
// next draw.
// increment records one completed item and refreshes the display.
func (p *progress) increment() {
if p == nil {
return
}
p.mu.Lock()
defer p.mu.Unlock()
p.count++
if p.bar != nil {
_ = p.bar.Add(1)
return
}
if time.Since(p.last) >= plainInterval {
p.last = time.Now()
fmt.Fprintln(os.Stderr, p.plainLine())
}
}
// warnf prints a one-line warning to stderr without corrupting the
// display. The whole message is escaped like a report's path columns,
// so a path holding a newline cannot split the warning.
// warnf prints a one-line warning to stderr without corrupting the bar.
// The whole message is escaped like a report's path columns, so a path
// holding a newline cannot split the warning.
func (p *progress) warnf(format string, args ...any) {
if p == nil {
return
@@ -280,168 +125,58 @@ func (p *progress) warnf(format string, args ...any) {
msg := escapePath(fmt.Sprintf(format, args...))
p.mu.Lock()
defer p.mu.Unlock()
if p.bar != nil && p.total < 0 {
// The library also redraws a spinner from its own goroutine, so
// a direct write could land inside a redraw. The bar prints the
// warning itself, just before its next redraw.
_, _ = progressbar.Bprintln(p.bar, msg)
return
}
if p.bar != nil {
// The warning takes the display's line; the next draw shows
// the display again, on the line below.
_ = p.bar.Clear()
}
fmt.Fprintln(os.Stderr, msg)
}
// progressWriter writes a phase's output to out, which may be the file
// the phase's display is drawn on, as stdout is in a plain "sfdupes
// trees" on a terminal. It holds what is written to it and writes that
// to out in pieces of about ioBufSize bytes. When out is the file
// stderr is, each piece is written under the display's lock with the
// display cleared first, as warnf does for a warning: no draw lands in
// the middle of a piece, and the next draw shows the display again, on
// the line below. Every write to it must end with a newline, as a row
// written with one fmt.Fprintf does, so that each piece ends a line.
// Flush writes what it holds once the last row is written.
type progressWriter struct {
// p is the display to clear, nil unless out is the file stderr is.
p *progress
out io.Writer
buf []byte
}
// writer returns a progressWriter writing to out around p's display.
// It clears the display and takes its lock only when out is the file
// stderr is: the same device and inode, as os.SameFile compares them,
// which is one terminal, or one pipe or file that both are sent to.
// Otherwise it writes to out without the lock, so the display keeps
// being drawn while a write to out waits for a slow reader.
func (p *progress) writer(out io.Writer) *progressWriter {
w := &progressWriter{out: out}
if f, ok := out.(*os.File); ok {
outInfo, outErr := f.Stat()
errInfo, errErr := os.Stderr.Stat()
if outErr == nil && errErr == nil && os.SameFile(outInfo, errInfo) {
w.p = p
}
// The library never draws a finished bar again, so the warning for
// a pass's last item would erase it for good: draw its last frame
// again below the warning.
if p.bar != nil && p.bar.IsFinished() {
fmt.Fprint(os.Stderr, p.bar.String())
}
return w
}
// Write holds b, and writes what it holds to out once that comes to
// ioBufSize bytes.
func (w *progressWriter) Write(b []byte) (int, error) {
w.buf = append(w.buf, b...)
if len(w.buf) < ioBufSize {
return len(b), nil
}
return len(b), w.Flush()
}
// Flush writes what w holds to out. When out is the file stderr is, the
// display is cleared first and not drawn again until it is written.
func (w *progressWriter) Flush() error {
if w.p != nil {
w.p.mu.Lock()
defer w.p.mu.Unlock()
if w.p.bar != nil {
_ = w.p.bar.Clear()
}
}
_, err := w.out.Write(w.buf)
w.buf = w.buf[:0]
return err
}
// finish ends the phase's display, drawn once more as the phase ends.
// A phase stopped short of its total, as an interrupted one is, shows
// the count it stopped at rather than a full bar.
// finish terminates the pass's display. A bar whose pass stopped short
// of its total, as an interrupted one does, is left as last drawn; the
// library's Finish would fill it up.
func (p *progress) finish() {
if p == nil {
return
}
close(p.stop)
<-p.done
p.draw()
if p.width != nil {
// The display stays on the TTY as drawn; what follows starts
// on a line of its own.
fmt.Fprintln(os.Stderr)
}
}
// line formats the phase's progress in at most room columns, as
//
// [3/5] hash: [1234/5000] 25%, 300 files/s, elapsed 4s, eta 13s
//
// where "files" is the phase's unit, without the percent when percent
// is false, as before the library's bar, which shows its own. A phase
// with no total shows the items done instead, or what it waits for.
//
// The phase and its place, the progress, the elapsed time and the ETA
// are kept whole. A line wider than room leaves out the rate, or what
// the phase waits for; only if it is still wider is it cut at room, and
// line reports that it does not fit. Every part is ASCII, so its length
// is its width in columns. p.mu must be held.
func (p *progress) line(room int, percent bool) (string, bool) {
elapsed := time.Since(p.start).Round(time.Second)
// head and tail hold the parts kept whole; extra, between them, is
// the part left out.
var head, extra, tail string
if p.total < 0 && p.waitingFor != "" {
head, extra = p.label+": ", p.waitingFor
tail = fmt.Sprintf("elapsed %s, eta unknown", elapsed)
} else {
rate := 0.0
if s := time.Since(p.rateStart).Seconds(); s > 0 {
rate = float64(p.count) / s
if p.bar != nil {
if p.total >= 0 && p.count < p.total {
_ = p.bar.Exit()
} else {
_ = p.bar.Finish()
}
head = p.label + ": " + p.itemsDone(percent) + ", "
extra = fmt.Sprintf("%.0f %s/s", rate, p.unit)
tail = fmt.Sprintf("elapsed %s, eta %s", elapsed, p.eta(rate))
fmt.Fprintln(os.Stderr)
return
}
full, kept := head+extra+", "+tail, head+tail
switch {
case len(full) <= room:
return full, true
case len(kept) <= room:
return kept, true
}
return kept[:max(room, 0)], false
fmt.Fprintln(os.Stderr, p.plainLine())
}
// itemsDone formats the items done, as "[1234/5000] 25%", with "~"
// before a total that is an estimate and without the percent when
// percent is false, or as "1234 files", in the phase's unit, when the
// phase has no total. p.mu must be held.
func (p *progress) itemsDone(percent bool) string {
// plainLine formats a non-TTY progress line.
func (p *progress) plainLine() string {
elapsed := time.Since(p.start)
if p.total < 0 {
return fmt.Sprintf("%d %s", p.count, p.unit)
}
approx := ""
if p.estimate {
approx = "~"
}
done := fmt.Sprintf("[%d/%s%d]", p.count, approx, p.total)
if !percent {
return done
return fmt.Sprintf("%s: %d files, elapsed %s",
p.label, p.count, elapsed.Round(time.Second))
}
pct := float64(percentScale)
@@ -449,24 +184,19 @@ func (p *progress) itemsDone(percent bool) string {
pct = percentScale * float64(p.count) / float64(p.total)
}
return fmt.Sprintf("%s %.0f%%", done, pct)
}
// eta returns the time the phase has left at rate items a second, or
// "unknown": with no total, before the first item, and once the count
// passes an estimate. p.mu must be held.
func (p *progress) eta(rate float64) string {
switch {
case p.total < 0, p.estimate && p.count > p.total:
return "unknown"
case p.count >= p.total:
return "0s"
case rate <= 0:
return "unknown"
rate := 0.0
if s := elapsed.Seconds(); s > 0 {
rate = float64(p.count) / s
}
remaining := time.Duration(
float64(p.total-p.count) / rate * float64(time.Second))
eta := "?"
return remaining.Round(time.Second).String()
if rate > 0 && p.count <= p.total {
remaining := time.Duration(float64(p.total-p.count) / rate * float64(time.Second))
eta = remaining.Round(time.Second).String()
}
return fmt.Sprintf("%s: [%d/%d] %.0f%% %.0f files/s elapsed %s eta %s",
p.label, p.count, p.total, pct, rate,
elapsed.Round(time.Second), eta)
}
progress_test.go
+78 -588
View File
@@ -1,24 +1,16 @@
package main
import (
"fmt"
"io"
"math"
"os"
"path/filepath"
"strings"
"testing"
"time"
"unicode/utf8"
)
// testRedraw is the redraw interval the tests give a display, so that
// many redraws fit in a few milliseconds.
const testRedraw = time.Millisecond
// testDeadline bounds how long a test waits for a display to draw what
// it expects.
const testDeadline = 5 * time.Second
// spinnerIdle comfortably outlasts the 100ms interval at which the
// progressbar library redraws a spinner from its own goroutine.
const spinnerIdle = 500 * time.Millisecond
//nolint:paralleltest // replaces the process-wide os.Stderr
func TestStderrIsTTYFalseForNonTerminals(t *testing.T) {
@@ -62,483 +54,60 @@ func TestStderrIsTTYFalseForNonTerminals(t *testing.T) {
}
}
func TestPhaseLabel(t *testing.T) {
t.Parallel()
// TestNewProgressPrintsBeforeFirstItem checks that each pass shows its
// zero state the moment it starts when stderr is not a terminal, and
// that the next line still waits for plainInterval.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestNewProgressPrintsBeforeFirstItem(t *testing.T) {
stderr := captureStderr(t)
phases := []string{"load", "walk", "hash"}
if got := phaseLabel(phases, "walk"); got != "[2/3] walk" {
t.Errorf("phaseLabel = %q, want %q", got, "[2/3] walk")
newProgress("walk", -1).increment()
newProgress("hash", 10).increment()
want := "walk: 0 files, elapsed 0s\n" +
"hash: [0/10] 0% 0 files/s elapsed 0s eta ?\n"
if got := stderr(); got != want {
t.Errorf("stderr = %q, want %q", got, want)
}
}
// TestProgressLine checks the line a display shows in each state, ten
// seconds into the phase.
func TestProgressLine(t *testing.T) {
t.Parallel()
ago := time.Now().Add(-10 * time.Second)
cases := []struct {
p *progress
want string
}{{
p: &progress{
label: scanPhase("load"), total: -1,
waitingFor: "counting the records",
},
want: "[1/5] load: counting the records, elapsed 10s, eta unknown",
}, {
p: &progress{
label: scanPhase("hash"), unit: scanUnit, total: 100, count: 20,
},
want: "[3/5] hash: [20/100] 20%, 2 files/s, elapsed 10s, eta 40s",
}, {
p: &progress{label: scanPhase("hash"), unit: scanUnit, total: 100},
want: "[3/5] hash: [0/100] 0%, 0 files/s, elapsed 10s, eta unknown",
}, {
p: &progress{label: scanPhase("update"), unit: scanUnit, total: 0},
want: "[4/5] update: [0/0] 100%, 0 files/s, elapsed 10s, eta 0s",
}, {
p: &progress{
label: scanPhase("walk"), unit: scanUnit, total: 100,
estimate: true, count: 20,
},
want: "[2/5] walk: [20/~100] 20%, 2 files/s, elapsed 10s, eta 40s",
}, {
// Past the estimate the walk cannot tell how long it has left.
p: &progress{
label: scanPhase("walk"), unit: scanUnit, total: 100,
estimate: true, count: 120,
},
want: "[2/5] walk: [120/~100] 120%, 12 files/s, elapsed 10s, " +
"eta unknown",
}, {
// A first scan's walk has no estimate.
p: &progress{
label: scanPhase("walk"), unit: scanUnit, total: -1, count: 20,
},
want: "[2/5] walk: 20 files, 2 files/s, elapsed 10s, eta unknown",
}, {
// The rate is in what the phase counts.
p: &progress{
label: treesPhase("group"), unit: "directories", total: 100,
count: 20,
},
want: "[3/4] group: [20/100] 20%, 2 directories/s, elapsed 10s, " +
"eta 40s",
}}
for _, tc := range cases {
tc.p.start, tc.p.rateStart = ago, ago
if got, _ := tc.p.line(math.MaxInt, true); got != tc.want {
t.Errorf("line = %q, want %q", got, tc.want)
}
}
}
// TestLineFitsRoom checks how a line is fitted to the room it has, ten
// seconds into the phase: it leaves out the rate, or what the phase
// waits for, and is cut only when what is left is still too wide.
func TestLineFitsRoom(t *testing.T) {
t.Parallel()
ago := time.Now().Add(-10 * time.Second)
hash := &progress{
label: scanPhase("hash"), unit: scanUnit, total: 100, count: 20,
start: ago, rateStart: ago,
}
content := &progress{
label: scanPhase("content"), total: -1,
waitingFor: "searching the database", start: ago, rateStart: ago,
}
cases := []struct {
p *progress
room int
percent bool
want string
fits bool
}{{
p: hash, room: 57, percent: true,
want: "[3/5] hash: [20/100] 20%, 2 files/s, elapsed 10s, eta 40s",
fits: true,
}, {
p: hash, room: 56, percent: true,
want: "[3/5] hash: [20/100] 20%, elapsed 10s, eta 40s",
fits: true,
}, {
p: hash, room: 45, percent: true,
want: "[3/5] hash: [20/100] 20%, elapsed 10s, eta 40",
fits: false,
}, {
// Before the library's bar, which shows the percent.
p: hash, room: 57, percent: false,
want: "[3/5] hash: [20/100], 2 files/s, elapsed 10s, eta 40s",
fits: true,
}, {
p: content, room: 40, percent: true,
want: "[5/5] content: elapsed 10s, eta unknown",
fits: true,
}}
for _, tc := range cases {
got, fits := tc.p.line(tc.room, tc.percent)
if got != tc.want || fits != tc.fits {
t.Errorf("line(%d, %t) = %q, %t, want %q, %t",
tc.room, tc.percent, got, fits, tc.want, tc.fits)
}
}
}
// TestSetTotalStartsRate checks that setTotal starts a phase's rate,
// and so its ETA, from when the total becomes known, not from when the
// phase started waiting for it.
func TestSetTotalStartsRate(t *testing.T) {
t.Parallel()
waited := time.Now().Add(-20 * time.Second)
p := &progress{
label: scanPhase("load"), unit: scanUnit, total: -1, start: waited,
rateStart: waited,
}
p.setTotal(100)
// Ten seconds after the total came, without waiting ten seconds,
// 20 records are read.
p.start = p.start.Add(-10 * time.Second)
p.rateStart = p.rateStart.Add(-10 * time.Second)
p.count = 20
want := "[1/5] load: [20/100] 20%, 2 files/s, elapsed 30s, eta 40s"
if got, _ := p.line(math.MaxInt, true); got != want {
t.Errorf("line = %q, want %q", got, want)
}
}
// awaitOutput waits until stderr holds want at least times times, and
// fails the test if it never does.
func awaitOutput(t *testing.T, stderr func() string, want string,
times int,
) {
// newWalkSpinner returns the walk pass's terminal display, writing to
// os.Stderr whether or not it is a terminal, and stops the library's
// redraws when the test ends.
func newWalkSpinner(t *testing.T) *progress {
t.Helper()
deadline := time.Now().Add(testDeadline)
for strings.Count(stderr(), want) < times {
if time.Now().After(deadline) {
t.Fatalf("stderr = %q, want %q at least %d times",
stderr(), want, times)
}
time.Sleep(testRedraw)
p := &progress{
label: "walk", total: -1, start: time.Now(),
bar: newBar("walk", -1),
}
t.Cleanup(p.finish)
return p
}
// TestPlainProgressPrintsAtStartAndEnd checks that when stderr is not a
// terminal a phase prints its line the moment it starts, before its
// first item, nothing for the items it completes before plainInterval
// has passed, and its line again as it ends.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestPlainProgressPrintsAtStartAndEnd(t *testing.T) {
stderr := captureStderr(t)
p := newProgress(progressParams{
label: scanPhase("hash"), unit: scanUnit, total: 1000,
})
for range 1000 {
p.increment()
}
p.finish()
lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
want := "[3/5] hash: [0/1000] 0%, 0 files/s, elapsed 0s, eta unknown"
if len(lines) != 2 || lines[0] != want ||
!strings.HasPrefix(lines[1], "[3/5] hash: [1000/1000] 100%, ") {
t.Errorf("stderr lines = %q, want %q, then the line at 1000",
lines, want)
}
}
// TestPlainProgressPrintsWhileWaiting checks that a phase waiting with
// no completed items still prints a line every interval.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestPlainProgressPrintsWhileWaiting(t *testing.T) {
stderr := captureStderr(t)
p := startProgress(progressParams{
label: scanPhase("load"), total: -1,
waitingFor: "counting the records",
}, nil, testRedraw)
awaitOutput(t, stderr,
"[1/5] load: counting the records, elapsed 0s, eta unknown\n", 3)
p.finish()
}
// lastFrame returns what a terminal shows of the frames a display drew:
// the last one. The library starts each frame with a carriage return
// and erases the previous one with spaces first.
func lastFrame(out string) string {
var shown string
for frame := range strings.SplitSeq(out, "\r") {
if strings.TrimSpace(frame) != "" {
shown = frame
}
}
return shown
}
// TestTerminalRedrawsWhileWaiting checks that the terminal display of a
// phase, spinner or bar, keeps being drawn while the phase waits for its
// next item, with the elapsed time as of now, and shows every item
// completed before the wait. stderr is not a terminal here, so the
// displays take it to be fallbackWidth wide.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestTerminalRedrawsWhileWaiting(t *testing.T) {
stderr := captureStderr(t)
cases := []struct {
params progressParams
want string // how the line shows a count of 50
}{
{
progressParams{label: scanPhase("walk"), unit: scanUnit, total: -1},
"50 files,",
},
{
progressParams{label: scanPhase("hash"), unit: scanUnit, total: 100},
"[50/100],",
},
}
for _, tc := range cases {
before := len(stderr())
since := func() string { return stderr()[before:] }
p := startProgress(tc.params, terminalWidth, testRedraw)
for range 50 {
p.increment()
}
// An hour into the phase, without waiting an hour.
p.mu.Lock()
p.start = p.start.Add(-time.Hour)
p.mu.Unlock()
awaitOutput(t, since, "elapsed 1h0m0s", 1)
p.finish()
if shown := lastFrame(since()); !strings.Contains(shown, tc.want) {
t.Errorf("terminal shows %q, want %q", shown, tc.want)
}
}
}
// drawLate draws the display params describes on a terminal width
// columns wide as it starts and once more as it ends, with count items
// done two and a half hours into the phase, and returns what it wrote
// to stderr.
func drawLate(stderr func() string, params progressParams, width int,
count int64,
) string {
before := len(stderr())
// No timed draws come between the two.
p := startProgress(params, func() int { return width }, time.Hour)
// Without counting the items one by one or waiting the hours.
p.mu.Lock()
p.count = count
p.start = p.start.Add(-150 * time.Minute)
p.rateStart = p.start
p.mu.Unlock()
p.finish()
return stderr()[before:]
}
// TestTerminalLinesKeepETA checks the line each display shows on an
// 80-column terminal at a large scan's counts and times, and the line
// of trees' read phase at the same counts: the rate is left out, so
// that the elapsed time and the ETA stay whole.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestTerminalLinesKeepETA(t *testing.T) {
stderr := captureStderr(t)
cases := []struct {
params progressParams
want string
}{{
// Past its estimate, the walk cannot tell how long it has left.
params: progressParams{
label: scanPhase("walk"), unit: scanUnit, total: 1200000,
estimate: true,
},
want: "[2/5] walk: [1234567/~1200000] 103%, elapsed 2h30m0s, " +
"eta unknown",
}, {
params: progressParams{
label: scanPhase("hash"), unit: scanUnit, total: 9876543,
},
want: "[3/5] hash: [1234567/9876543] 12%, elapsed 2h30m0s, " +
"eta 17h30m0s",
}, {
params: progressParams{
label: scanPhase("content"), unit: scanUnit, total: 9876543,
},
want: "[5/5] content: [1234567/9876543] 12%, elapsed 2h30m0s, " +
"eta 17h30m0s",
}, {
params: progressParams{
label: treesPhase("read"), unit: "records", total: 9876543,
},
want: "[2/4] read: [1234567/9876543] 12%, elapsed 2h30m0s, " +
"eta 17h30m0s",
}}
for _, tc := range cases {
out := drawLate(stderr, tc.params, 80, 1234567)
if shown := lastFrame(out); !strings.Contains(shown, tc.want) {
t.Errorf("terminal shows %q, want %q", shown, tc.want)
}
}
}
// TestTerminalLinesFitWidth draws a large scan's bar display and a small
// scan's, two and a half hours into the phase, on terminals from 120
// columns down to 40, and checks that every line stays clear of the
// terminal's last column. A line that reaches it wraps, and every
// redraw then leaves a line behind. The bar is drawn where it has room,
// as at 120 columns, and left out where it has none.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestTerminalLinesFitWidth(t *testing.T) {
stderr := captureStderr(t)
for _, width := range []int{120, 100, 80, 72, 60, 50, 40} {
for _, total := range []int64{9876543, 20000} {
params := progressParams{
label: scanPhase("content"), unit: scanUnit, total: total,
}
out := drawLate(stderr, params, width, total/8)
if width == 120 && !strings.Contains(out, "% |") {
t.Errorf("no bar on a terminal %d wide: %q", width, out)
}
lines := strings.FieldsFuncSeq(out, func(r rune) bool {
return r == '\r' || r == '\n'
})
for line := range lines {
if n := utf8.RuneCountInString(line); n >= width {
t.Errorf("a line of %d columns on a terminal %d wide: %q",
n, width, line)
}
}
}
}
}
// TestTerminalNarrowedRedrawsInPlace draws a large scan's display, two
// and a half hours into the phase, on a terminal 120 columns wide, then
// makes the terminal narrower than that line and draws it again a few
// times. Nothing written after that, the erase before each redraw
// included, may reach the narrower terminal's last column: it would
// wrap, and every redraw would leave a line behind. At these widths the
// spinner stays a spinner and the bar stays a bar.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
stderr := captureStderr(t)
cases := []struct {
params progressParams
narrow int
}{
{
progressParams{label: scanPhase("walk"), unit: scanUnit, total: -1},
60,
},
{
progressParams{
label: scanPhase("hash"), unit: scanUnit, total: 9876543,
},
90,
},
}
for _, tc := range cases {
width := 120
// No timed draws: the test draws.
p := startProgress(tc.params, func() int { return width }, time.Hour)
p.mu.Lock()
p.count = 1234567
p.start = p.start.Add(-150 * time.Minute)
p.rateStart = p.start
p.mu.Unlock()
p.draw()
width = tc.narrow
before := len(stderr())
p.draw()
p.draw()
p.finish()
lines := strings.FieldsFuncSeq(stderr()[before:], func(r rune) bool {
return r == '\r' || r == '\n'
})
for line := range lines {
if n := utf8.RuneCountInString(line); n >= width {
t.Errorf("%d columns written on a terminal made %d wide: %q",
n, width, line)
}
}
}
}
// TestProgressWarningsOnOwnLines drives the terminal displays, spinner
// and bar, through a run of warnings with no items between them, as when
// the walk meets many unreadable paths, for many redraws: every warning
// must land on a line of its own, never inside a redraw.
// TestProgressWarningsOnOwnLines drives the terminal display of the walk
// pass through a run of warnings with no items between them, as when the
// walk meets many unreadable paths, for several of the spinner's
// redraws: every warning must land on a line of its own, never inside a
// redraw.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestProgressWarningsOnOwnLines(t *testing.T) {
stderr := captureStderr(t)
p := newWalkSpinner(t)
cases := []progressParams{
{label: scanPhase("walk"), total: -1},
{label: scanPhase("hash"), total: 10},
}
// No pause between warnings: one written straight to stderr is
// garbled only if a redraw lands while it is being written.
issued := 0
for _, params := range cases {
p := startProgress(params, terminalWidth, testRedraw)
// No pause between warnings: one written straight to stderr is
// garbled only if a redraw lands while it is being written.
for start := time.Now(); time.Since(start) < 50*testRedraw; issued++ {
p.warnf("warning")
}
p.finish()
for start := time.Now(); time.Since(start) < spinnerIdle; issued++ {
p.warnf("warning")
}
// The spinner prints the warnings at its next redraw.
time.Sleep(spinnerIdle)
// A terminal shows each line as the text after its last carriage
// return.
shown := 0
@@ -560,162 +129,83 @@ func TestProgressWarningsOnOwnLines(t *testing.T) {
}
}
// TestProgressWriterRowsOnOwnLines drives the terminal displays,
// spinner and bar, through a run of rows written through the display's
// writer to the same terminal, as stdout is in a plain "sfdupes trees",
// each written out at once, for many redraws: the terminal must show
// every row whole, in order, on a line of its own.
// TestSpinnerShowsCountAfterBurst checks that once a burst of items
// faster than the redraw limit is over, the walk display shows every
// item completed while it waits for the next one.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestProgressWriterRowsOnOwnLines(t *testing.T) {
func TestSpinnerShowsCountAfterBurst(t *testing.T) {
stderr := captureStderr(t)
p := newWalkSpinner(t)
cases := []progressParams{
{
label: treesPhase("open"), total: -1,
waitingFor: "opening the database",
},
{label: treesPhase("write"), unit: "groups", total: 10},
for range 50 {
p.increment()
}
var want []string
time.Sleep(spinnerIdle)
for _, params := range cases {
p := startProgress(params, terminalWidth, testRedraw)
out := p.writer(os.Stderr)
// No pause between rows: one is garbled only if a redraw lands
// on its line.
for start := time.Now(); time.Since(start) < 50*testRedraw; {
row := fmt.Sprintf("row %d", len(want))
want = append(want, row)
_, err := fmt.Fprintln(out, row)
if err == nil {
err = out.Flush()
}
if err != nil {
t.Fatal(err)
}
}
p.finish()
}
// A terminal shows each line as the text after its last carriage
// return.
var shown []string
for line := range strings.SplitSeq(stderr(), "\n") {
if strings.Contains(line, "row ") {
shown = append(shown, line[strings.LastIndex(line, "\r")+1:])
}
}
if len(shown) != len(want) {
t.Fatalf("terminal shows %d rows, want %d", len(shown), len(want))
}
for i := range want {
if shown[i] != want[i] {
t.Fatalf("terminal shows %q, want %q", shown[i], want[i])
}
if shown := lastFrame(stderr()); !strings.Contains(shown, "(50/-,") {
t.Errorf("terminal shows %q, want a count of 50", shown)
}
}
// TestProgressWriterStalledStdoutKeepsLines writes a row larger than a
// pipe holds through the display's writer to a pipe nobody reads yet,
// as stdout is when its reader has stopped while stderr goes to a file:
// while the write waits, the display must go on printing its line.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestProgressWriterStalledStdoutKeepsLines(t *testing.T) {
stderr := captureStderr(t)
// lastFrame returns what a terminal shows of the frames a bar drew: the
// last one. The library starts each frame with a carriage return and
// erases the previous one with spaces first.
func lastFrame(out string) string {
var shown string
r, w, err := os.Pipe()
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() {
_ = w.Close()
_ = r.Close()
})
p := startProgress(progressParams{label: treesPhase("write"), total: 1},
nil, testRedraw)
out := p.writer(w)
written := make(chan error, 1)
go func() {
_, writeErr := fmt.Fprintln(out, strings.Repeat("x", ioBufSize))
written <- writeErr
}()
// Pass or fail, the pipe is then read so that the write ends, and
// the display ends before stderr is put back.
t.Cleanup(func() {
go func() {
_, _ = io.Copy(io.Discard, r)
}()
writeErr := <-written
if writeErr != nil {
t.Error(writeErr)
for frame := range strings.SplitSeq(out, "\r") {
if strings.TrimSpace(frame) != "" {
shown = frame
}
p.finish()
})
// The first byte read shows that the write has started; the rest
// of the row waits until the pipe is read.
_, err = r.Read(make([]byte, 1))
if err != nil {
t.Fatal(err)
}
line := "[4/4] write: "
awaitOutput(t, stderr, line, strings.Count(stderr(), line)+3)
return shown
}
// TestTerminalStoppedShortKeepsCount checks that the terminal display
// of a phase that stops before its total, as an interrupted one does,
// is left showing the count it stopped at rather than a full bar.
// TestBarStoppedShortKeepsCount checks that the terminal display of a
// pass that stops before its total, as an interrupted one does, is left
// as last drawn instead of being filled up.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestTerminalStoppedShortKeepsCount(t *testing.T) {
func TestBarStoppedShortKeepsCount(t *testing.T) {
stderr := captureStderr(t)
p := startProgress(progressParams{label: scanPhase("hash"), total: 10},
terminalWidth, redrawInterval)
p := &progress{
label: "hash", total: 10, start: time.Now(),
bar: newBar("hash", 10),
}
p.increment()
// Past the redraw limit, so the bar draws the next count.
time.Sleep(2 * barThrottle)
p.increment()
p.finish()
if shown := lastFrame(stderr()); !strings.Contains(shown, "[2/10],") {
if shown := lastFrame(stderr()); !strings.Contains(shown, "(2/10,") {
t.Errorf("terminal shows %q, want a count of 2 of 10", shown)
}
}
// TestWarningAfterLastItemKeepsBar checks that a warning printed after
// a phase's last item, as for a failed read of the last file, leaves the
// phase's full bar on the terminal below the warning.
// a pass's last item, as for a failed read of the last file, leaves the
// pass's finished bar on the terminal below the warning.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestWarningAfterLastItemKeepsBar(t *testing.T) {
stderr := captureStderr(t)
p := startProgress(progressParams{label: scanPhase("hash"), total: 2},
terminalWidth, testRedraw)
p := &progress{
label: "hash", total: 2, start: time.Now(),
bar: newBar("hash", 2),
}
p.increment()
p.increment()
awaitOutput(t, stderr, "[2/2],", 1)
p.warnf("warning")
p.finish()
if shown := lastFrame(stderr()); !strings.Contains(shown, "[2/2],") {
if shown := lastFrame(stderr()); !strings.Contains(shown, "(2/2,") {
t.Errorf("terminal shows %q, want a count of 2 of 2", shown)
}
}
report.go
+2 -9
View File
@@ -34,16 +34,9 @@ type scanRec struct {
// records, and each row is written as it is read, so no group is held
// in memory. It never touches the scanned filesystem; its only I/O is
// the database (with SQLite's temporary sort file), stdout, and stderr.
// It names the database on stderr before it opens it. Any database
// problem, including a missing database, is fatal.
// Any database problem, including a missing database, is fatal.
func runReport(ctx context.Context, stdout io.Writer) error {
dbPath, source, err := databasePath()
if err != nil {
return err
}
fmt.Fprintf(os.Stderr, "report: database %s (%s)\n",
escapePath(dbPath), source)
dbPath := databasePath()
db, err := openReportDatabase(ctx, dbPath)
if err != nil {
scan.go
+62 -238
View File
@@ -84,28 +84,14 @@ type fileMeta struct {
hashed bool
}
// scanUnit is what every scan phase counts, as its progress display
// names it.
const scanUnit = "files"
// scanPhase names one phase of a scan with its place among all of them,
// as "[2/5] walk", for the phase's progress display. The list here is
// the one place the phases are counted.
func scanPhase(name string) string {
return phaseLabel(
[]string{"load", "walk", "hash", "update", "content"}, name)
}
// runScan implements the scan subcommand: five sequential phases —
// load (which reads the existing records), walk (which stats each file
// as it is discovered), hash, update, content — that synchronize the
// persistent database with the filesystem state under the PATH
// operands. Only files whose size at least one other file shares are
// ever hashed: a size-unique file cannot be a duplicate. A file of
// headTailMin or more gets its content hash only when its size, head,
// and tail match another file's. Flag parsing and the
// at-least-one-operand check are done by cobra. Before anything else,
// the scan names the database on stderr, saying whether it is new. The
// runScan implements the scan subcommand: four sequential phases —
// walk (which stats each file as it is discovered), hash, update,
// content — that synchronize the persistent database with the
// filesystem state under the PATH operands. Only files whose size at
// least one other file shares are ever hashed: a size-unique file
// cannot be a duplicate. A file of headTailMin or more gets its content
// hash only when its size, head, and tail match another file's. Flag
// parsing and the at-least-one-operand check are done by cobra. The
// scan holds the lock on the database for its whole run, so a second
// scan fails before it walks the filesystem or opens the database.
// Errors are returned rather than exiting, so that the deferred close —
@@ -118,26 +104,12 @@ func scanPhase(name string) string {
func runScan(ctx context.Context, roots []string, workers int,
oneFS bool,
) error {
dbPath, source, err := databasePath()
roots, err := resolveRoots(roots)
if err != nil {
return err
}
// A database file missing now is created by lockScanDatabase below.
what := "database"
_, err = os.Stat(dbPath)
if errors.Is(err, fs.ErrNotExist) {
what = "new database"
}
fmt.Fprintf(os.Stderr, "scan: %s %s (%s)\n", what, escapePath(dbPath),
source)
roots, err = resolveRoots(roots)
if err != nil {
return err
}
dbPath := databasePath()
lock, err := lockScanDatabase(dbPath)
if err != nil {
@@ -231,16 +203,10 @@ func resolveRoots(roots []string) ([]string, error) {
}
// pruneRoots drops operands already covered by another operand:
// duplicates and any operand lying under another one. With -x, an
// operand under another one is kept when the walk of the deepest kept
// operand above it cannot reach it: when device puts any directory from
// it (from its directory, for a regular file) up to but not including
// that operand on a different filesystem than that operand. Every
// remaining file is then reachable through exactly one root, so walked
// paths are unique without keeping a scan-wide set of every path seen.
func pruneRoots(roots []string, oneFS bool,
device func(path string) (uint64, bool),
) []string {
// duplicates and any operand lying under another one. Every remaining
// file is then reachable through exactly one root, so walked paths are
// unique without keeping a scan-wide set of every path seen.
func pruneRoots(roots []string) []string {
// Shorter-first ordering guarantees an ancestor is kept before any
// operand under it is considered.
sorted := slices.Clone(roots)
@@ -255,58 +221,14 @@ func pruneRoots(roots []string, oneFS bool,
kept := make([]string, 0, len(sorted))
for _, r := range sorted {
above := deepestRoot(r, kept)
if above == "" {
if !underAnyRoot(r, kept) {
kept = append(kept, r)
continue
}
// Without -x, and always for a duplicate, r is dropped.
if !oneFS || above == r {
continue
}
aboveDev, aboveOK := device(above)
if !aboveOK {
continue
}
// The walk of above enters a directory only when it is on
// above's filesystem, and then reaches every regular file in it
// whatever device the file reports, so for a regular-file
// operand the directories checked start at its directory.
dir := r
fi, err := os.Lstat(r)
if err == nil && fi.Mode().IsRegular() {
dir = filepath.Dir(r)
}
for ; dir != above; dir = filepath.Dir(dir) {
dev, ok := device(dir)
if ok && dev != aboveDev {
kept = append(kept, r)
break
}
}
}
return kept
}
// deviceOfPath returns the filesystem device ID of the file at path,
// when lstat succeeds and the platform exposes one.
func deviceOfPath(path string) (uint64, bool) {
fi, err := os.Lstat(path)
if err != nil {
return 0, false
}
return deviceOfInfo(fi)
}
// scanStats summarizes one scan's database synchronization for the
// final stderr summary, or for the line an interrupted scan prints.
type scanStats struct {
@@ -356,32 +278,31 @@ func syncScan(ctx context.Context, db *sql.DB, roots []string,
}
// runPhases synchronizes the database with the filesystem under roots
// in five sequential phases: load (read the existing records), walk
// (enumerate and stat every file, building a complete size census),
// hash (read only the new or changed — or previously unhashed — files
// whose size at least one other file shares, committing results in
// batches as they arrive), update (record the size-unique files without
// reading them, and delete the records the scan no longer verifies),
// and content (fill in the content hash of every record of headTailMin
// or more whose size, head, and tail match another record's). Records
// outside the roots are never touched, except that the content phase
// fills in their content hash. Operands the walk cannot start from are
// dropped first, so the records beneath them are treated as if those
// operands had not been given.
// in four sequential phases: walk (enumerate and stat every file,
// building a complete size census), hash (read only the new or
// changed — or previously unhashed — files whose size at least one
// other file shares, committing results in batches as they arrive),
// update (record the size-unique files without reading them, and
// delete the records the scan no longer verifies), and content (fill
// in the content hash of every record of headTailMin or more whose
// size, head, and tail match another record's). Records outside the
// roots are never touched, except that the content phase fills in
// their content hash. Operands the walk cannot start from are dropped
// first, so the records beneath them count as outside the roots unless
// they lie under another root.
func (s *scanState) runPhases(ctx context.Context, roots []string,
workers int, oneFS bool,
) error {
// Types are checked before pruning so that an operand under a
// dropped one is still scanned, not dropped as lying under it.
roots = pruneRoots(s.walkableRoots(roots), oneFS, deviceOfPath)
roots = pruneRoots(s.walkableRoots(roots))
err := s.loadIndex(ctx, roots)
if err != nil {
return err
}
changed, unhashed := s.walkPhase(
startWalk(ctx, roots, oneFS, workers), roots)
changed, unhashed := s.walkPhase(startWalk(ctx, roots, oneFS, workers))
// A cancelled walk stops early, so its size census covers only part
// of the roots, and every file it never reached would look vanished
@@ -409,10 +330,10 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
// walkableRoots returns the operands the walk can start from: regular
// files, and directories not named .zfs. Every other operand is warned
// about, counted as skipped, and dropped. A dropped operand is no
// longer a root, so the records stored beneath it are treated as if it
// had not been given: those under no other root count as outside the
// roots and are not deleted as unverified. An operand that fails lstat
// here is kept, and the walk warns about it.
// longer a root, so the records stored beneath it count as outside the
// roots and are not deleted as unverified, unless it lies under another
// root. An operand that fails lstat here is kept, and the walk warns
// about it.
func (s *scanState) walkableRoots(roots []string) []string {
kept := make([]string, 0, len(roots))
@@ -442,21 +363,10 @@ func (s *scanState) walkableRoots(roots []string) []string {
// separately into the same database.
func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
// Indexing tens of millions of records takes real time; without a
// display the scan looks hung before the walk begins. Counting them
// first gives the display its total.
prog := newProgress(progressParams{
label: scanPhase("load"), unit: scanUnit, total: -1,
waitingFor: "counting the records",
})
// display the scan looks hung before the walk begins.
prog := newProgress("load", -1)
defer prog.finish()
total, err := countRecords(ctx, s.db)
if err != nil {
return err
}
prog.setTotal(total)
s.existing = make(map[string]fileMeta)
return loadFileMeta(ctx, s.db,
@@ -481,37 +391,15 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
// (the content phase may still fill in its content hash). It returns
// the new-or-changed files and the unchanged files whose records lack
// hashes; both remain candidates until the census decides whether
// their sizes are shared. A record below a directory -x did not enter
// counts as outside the roots: it is not deleted, and its size joins
// the census. That does not hold below a root at or inside that
// directory, since that root's own walk verifies the records below it.
// their sizes are shared.
func (s *scanState) walkPhase(
events <-chan walkEvent, roots []string,
events <-chan walkEvent,
) ([]fileRec, []fileRec) {
// The records the last scan left under the roots estimate how many
// files the walk will find. A first scan has none, and no estimate.
estimate := int64(len(s.existing))
if estimate == 0 {
estimate = -1
}
prog := newProgress("walk", -1)
prog := newProgress(progressParams{
label: scanPhase("walk"), unit: scanUnit, total: estimate,
estimate: true,
})
var (
changed, unhashed []fileRec
otherFSDirs []string
)
var changed, unhashed []fileRec
for ev := range events {
if ev.otherFSDir != "" {
otherFSDirs = append(otherFSDirs, ev.otherFSDir)
continue
}
if ev.fail {
s.st.skipped++
@@ -541,19 +429,6 @@ func (s *scanState) walkPhase(
prog.finish()
for path, old := range s.existing {
// Kept only when a directory -x did not enter lies below the
// deepest root above the record. A root at or below that
// directory was walked on its own and did not find the file.
// Both contain the record, so the longer path is the deeper.
otherFSDir := deepestRoot(path, otherFSDirs)
if len(otherFSDir) > len(deepestRoot(path, roots)) {
delete(s.existing, path)
s.sizes = append(s.sizes, old.size)
}
}
return changed, unhashed
}
@@ -669,11 +544,10 @@ func (s *scanState) hashPhase(ctx context.Context, workers int) error {
}
// readRuns reads runs with the worker pool, one read per inode run, in
// the order given, under the progress display of the phase named label.
// The workers compute each run's hashes with hash, and each result goes
// to record; a run that fails to read is warned about and counted as
// skipped instead. The total counts actual reads, so the display shows
// a real ETA.
// the order given, under a progress display named label. The workers
// compute each run's hashes with hash, and each result goes to record;
// a run that fails to read is warned about and counted as skipped
// instead. The total counts actual reads, so the bar shows a real ETA.
//
// Returning early — a failed database write, or a cancelled scan — must
// not strand the pool: the feeder would park forever on a full jobs
@@ -687,9 +561,7 @@ func (s *scanState) readRuns(ctx context.Context, workers int,
pool := startHashPool(ctx, runs, workers, hash)
defer pool.stop()
prog := newProgress(progressParams{
label: scanPhase(label), unit: scanUnit, total: int64(len(runs)),
})
prog := newProgress(label, int64(len(runs)))
defer prog.finish()
for range runs {
@@ -776,9 +648,7 @@ func (s *scanState) updatePhase(ctx context.Context) error {
s.st.removed = len(deletes)
total := len(s.batch) + len(s.sentinels) + len(deletes)
prog := newProgress(progressParams{
label: scanPhase("update"), unit: scanUnit, total: int64(total),
})
prog := newProgress("update", int64(total))
defer prog.finish()
@@ -859,28 +729,16 @@ func (s *scanState) contentPhase(ctx context.Context, workers int) error {
func (s *scanState) contentCandidates(
ctx context.Context,
) ([]fileRec, map[string]scanRec, error) {
// The search and the checks take real time on a large database;
// The query and the checks take real time on a large database;
// without a display the scan looks hung before the reads begin.
// The display says it is searching until SQLite returns the first
// record. The checks start there, against a count of the records
// the search returns, and so do their rate and ETA.
prog := newProgress(progressParams{
label: scanPhase("content"), unit: scanUnit, total: -1,
waitingFor: "searching the database",
})
prog := newProgress("content", -1)
defer prog.finish()
total, err := countContentCandidates(ctx, s.db)
if err != nil {
return nil, nil, err
}
var (
searching = true // no record has been returned yet
toRead []fileRec
first scanRec // the current group's first record
passed int // the current group's files that passed the check
unread []fileRec // those of them without a content hash
toRead []fileRec
first scanRec // the current group's first record
passed int // the current group's files that passed the check
unread []fileRec // those of them without a content hash
)
recs := make(map[string]scanRec)
@@ -899,13 +757,7 @@ func (s *scanState) contentCandidates(
passed, unread = 0, nil
}
err = loadContentCandidates(ctx, s.db, func(r scanRec, hashed bool) {
if searching {
searching = false
prog.setTotal(total)
}
err := loadContentCandidates(ctx, s.db, func(r scanRec, hashed bool) {
prog.increment()
if r.size != first.size || r.head != first.head || r.tail != first.tail {
@@ -936,11 +788,6 @@ func (s *scanState) contentCandidates(
return nil, nil, err
}
// A search that returned no record still ends showing its count.
if searching {
prog.setTotal(total)
}
endGroup()
return toRead, recs, nil
@@ -1009,20 +856,6 @@ func underRoot(path, root string) bool {
return strings.HasPrefix(path, prefix)
}
// deepestRoot returns the longest of the roots that path is or lies
// under, or "" when it lies under none.
func deepestRoot(path string, roots []string) string {
deepest := ""
for _, root := range roots {
if underRoot(path, root) && len(root) > len(deepest) {
deepest = root
}
}
return deepest
}
// dirJob is one directory awaiting traversal by the walk workers. It
// carries its operand's filesystem device so -x can stop at
// filesystem boundaries.
@@ -1033,23 +866,19 @@ type dirJob struct {
}
// walkEvent is one walk result delivered to the walk phase: a regular
// file's statted record, a warning when fail is set, or, when
// otherFSDir is set, a directory -x did not enter because it is on
// another filesystem than its operand.
// file's statted record, or a warning when fail is set.
type walkEvent struct {
rec fileRec
warn string
fail bool
otherFSDir string
rec fileRec
warn string
fail bool
}
// startWalk seeds every root into the shared walk worker pool and
// returns the event stream: one record per regular file, one warning
// event per per-path error, and one event per directory -x did not
// enter. The channel is closed when the walk completes, and also when
// ctx is cancelled — every goroutine in the pool abandons its blocking
// send in that case, so the consumer sees a truncated but properly
// terminated stream instead of a stalled one.
// event per per-path error. The channel is closed when the walk
// completes, and also when ctx is cancelled — every goroutine in the
// pool abandons its blocking send in that case, so the consumer sees a
// truncated but properly terminated stream instead of a stalled one.
func startWalk(ctx context.Context, roots []string, oneFS bool,
workers int,
) <-chan walkEvent {
@@ -1116,8 +945,7 @@ func operandWarning(root string, fi fs.FileInfo) string {
// operand becomes an initial job. walkableRoots has already dropped
// every other operand. One that has changed into something else since
// is warned about and skipped here; it is still a root, so the records
// stored beneath it, other than those under another root, are deleted
// as unverified.
// stored beneath it are deleted as unverified.
func seedRoot(ctx context.Context, root string,
events chan<- walkEvent,
) []dirJob {
@@ -1316,9 +1144,7 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
// subdirJob applies the descent rules to directory p: never enter
// .zfs (ZFS snapshot pseudo-dirs would list every file once per
// snapshot), and with -x never enter a directory on a different
// filesystem than its operand, sending an event that names it so the
// scan keeps the records below it, except those below an operand at or
// inside it.
// filesystem than its operand.
func subdirJob(ctx context.Context, p string, e fs.DirEntry,
parent dirJob, oneFS bool, events chan<- walkEvent,
) (dirJob, bool) {
@@ -1342,8 +1168,6 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
}
if dev, ok := deviceOfInfo(info); ok && dev != parent.rootDev {
sendEvent(ctx, events, walkEvent{otherFSDir: p})
return dirJob{}, false
}
scan_test.go
+7 -396
View File
@@ -997,7 +997,7 @@ func dirEntryFor(t *testing.T, dir, name string) fs.DirEntry {
}
// callSubdirJob runs subdirJob against e under parent, collecting any
// events it emits (subdirJob emits at most one).
// warning events it emits (subdirJob emits at most one).
func callSubdirJob(t *testing.T, p string, e fs.DirEntry,
parent dirJob, oneFS bool,
) (dirJob, bool, []walkEvent) {
@@ -1075,15 +1075,8 @@ func TestSubdirJobOneFilesystem(t *testing.T) {
t.Fatalf("accepted = %v, want %v", ok, tc.wantOK)
}
// A refused descent names the directory, so the scan keeps
// the records below it.
var wantEvs []walkEvent
if !ok {
wantEvs = []walkEvent{{otherFSDir: sub}}
}
if !slices.Equal(evs, wantEvs) {
t.Fatalf("events = %+v, want %+v", evs, wantEvs)
if len(evs) != 0 {
t.Fatalf("unexpected events: %+v", evs)
}
// The accepted job must carry the operand's device down, or -x
@@ -1135,296 +1128,6 @@ func TestSubdirJobStatError(t *testing.T) {
}
}
// syncOneFilesystem scans roots into db with -x and returns the scan
// stats. Every device pruneRoots looks up, and the device each
// operand's walk compares its subdirectories with, comes from devices
// instead of from lstat, so a test can put a path on a filesystem that
// no directory here is on. Unlike runPhases, it skips walkableRoots,
// the check for a cancelled walk, and the content phase.
func syncOneFilesystem(t *testing.T, db *sql.DB, roots []string,
devices map[string]uint64,
) scanStats {
t.Helper()
device := func(path string) (uint64, bool) {
dev, ok := devices[path]
return dev, ok
}
roots = pruneRoots(roots, true, device)
ctx := t.Context()
s := &scanState{db: db}
err := s.loadIndex(ctx, roots)
if err != nil {
t.Fatal(err)
}
jobs, subdirs, events := startWalkWorkers(ctx, 2, true)
// seedRoot emits a regular-file operand itself and returns a job
// only for a directory operand.
var initial []dirJob
for _, root := range roots {
for _, job := range seedRoot(ctx, root, events) {
job.rootDev = devices[root]
initial = append(initial, job)
}
}
dispatchDirs(ctx, initial, jobs, subdirs)
changed, unhashed := s.walkPhase(events, roots)
s.partition(changed, unhashed)
err = s.hashPhase(ctx, 2)
if err != nil {
t.Fatal(err)
}
err = s.updatePhase(ctx)
if err != nil {
t.Fatal(err)
}
return s.st
}
// TestScanOneFilesystemKeepsOtherFilesystemRecords checks that with -x a
// record below a directory the walk does not enter, because it is on
// another filesystem than its operand, counts as outside the operands:
// it is not deleted, and its size joins the size census. The record of
// a gone file that is not below that directory is still deleted, even
// when its path begins with the directory's name. The operand is given
// a device that no directory here is on, so no second real filesystem
// is needed.
func TestScanOneFilesystemKeepsOtherFilesystemRecords(t *testing.T) {
t.Parallel()
dir := t.TempDir()
db := openTestDB(t)
// A scan without -x records the file below mnt, and mnt2, which is
// beside mnt, not below it.
mounted := writeFile(t, dir, "mnt/f", pattern(1, 100))
gone := writeFile(t, dir, "mnt2", pattern(3, 50))
syncTree(t, db, dir)
err := os.Remove(gone)
if err != nil {
t.Fatal(err)
}
// The same size as mnt/f, so it is hashed only if mnt/f's size is
// in the census.
added := writeFile(t, dir, "added", pattern(2, 100))
info, err := os.Lstat(dir)
if err != nil {
t.Fatal(err)
}
dev, ok := deviceOfInfo(info)
if !ok {
t.Skip("platform exposes no device id")
}
syncOneFilesystem(t, db, []string{dir}, map[string]uint64{dir: dev + 1})
recs := dbRecords(t, db)
recordByPath(t, recs, mounted)
if recordByPath(t, recs, added).head == "" {
t.Errorf("%s not hashed: the census lacks the size of %s",
added, mounted)
}
if slices.Contains(recordPaths(recs), gone) {
t.Errorf("record for %s kept: the file is gone and not below mnt",
gone)
}
}
// TestScanOneFilesystemWalksNestedOperand checks that with -x an
// operand under another one, on a different filesystem than it, is
// walked on its own: a file added below it is recorded, and the record
// of a file gone from below it is deleted. A record below a directory
// that its own walk does not enter is still kept. Each operand is given
// a device that no directory here is on, so neither walk enters a
// subdirectory.
func TestScanOneFilesystemWalksNestedOperand(t *testing.T) {
t.Parallel()
dir := t.TempDir()
db := openTestDB(t)
// A scan without -x records both files below mnt.
gone := writeFile(t, dir, "mnt/gone", pattern(1, 10))
kept := writeFile(t, dir, "mnt/sub/kept", pattern(2, 20))
syncTree(t, db, dir)
err := os.Remove(gone)
if err != nil {
t.Fatal(err)
}
added := writeFile(t, dir, "mnt/added", pattern(3, 30))
info, err := os.Lstat(dir)
if err != nil {
t.Fatal(err)
}
dev, ok := deviceOfInfo(info)
if !ok {
t.Skip("platform exposes no device id")
}
mnt := filepath.Join(dir, "mnt")
syncOneFilesystem(t, db, []string{dir, mnt},
map[string]uint64{dir: dev + 1, mnt: dev + 2})
paths := recordPaths(dbRecords(t, db))
if !slices.Contains(paths, added) {
t.Errorf("no record for %s: the walk did not reach %s", added, mnt)
}
if slices.Contains(paths, gone) {
t.Errorf("record for %s kept: the file is gone", gone)
}
if !slices.Contains(paths, kept) {
t.Errorf("record for %s deleted: the walk of %s did not enter %s",
kept, mnt, filepath.Dir(kept))
}
}
// TestScanOneFilesystemWalksOperandBelowOtherFilesystem checks that
// with -x an operand on the same filesystem as the operand covering it
// is walked on its own when a directory between them is on another
// filesystem, since the walk of the covering operand does not enter
// that directory: a file added below the nested operand is recorded,
// and the record of a file gone from below it is deleted. A record
// below that directory but outside the nested operand is still kept.
// Both operands are given one device that no directory here is on,
// while mnt keeps its own.
func TestScanOneFilesystemWalksOperandBelowOtherFilesystem(t *testing.T) {
t.Parallel()
dir := t.TempDir()
db := openTestDB(t)
// A scan without -x records both files below mnt.
gone := writeFile(t, dir, "mnt/back/gone", pattern(1, 10))
kept := writeFile(t, dir, "mnt/kept", pattern(2, 20))
syncTree(t, db, dir)
err := os.Remove(gone)
if err != nil {
t.Fatal(err)
}
added := writeFile(t, dir, "mnt/back/added", pattern(3, 30))
info, err := os.Lstat(dir)
if err != nil {
t.Fatal(err)
}
dev, ok := deviceOfInfo(info)
if !ok {
t.Skip("platform exposes no device id")
}
mnt := filepath.Join(dir, "mnt")
back := filepath.Join(mnt, "back")
syncOneFilesystem(t, db, []string{dir, back},
map[string]uint64{dir: dev + 1, mnt: dev, back: dev + 1})
paths := recordPaths(dbRecords(t, db))
if !slices.Contains(paths, added) {
t.Errorf("no record for %s: the walk did not reach %s", added, back)
}
if slices.Contains(paths, gone) {
t.Errorf("record for %s kept: the file is gone", gone)
}
if !slices.Contains(paths, kept) {
t.Errorf("record for %s deleted: the walk of %s did not enter %s",
kept, dir, mnt)
}
}
// TestScanOneFilesystemRecordsNestedFileOnce checks that with -x a
// regular-file operand under another operand is dropped when the file
// reports a different device than that operand but its directory does
// not, as a file bind-mounted into the tree does: the walk of the other
// operand enters the directory and reaches the file, so the file is
// recorded once.
func TestScanOneFilesystemRecordsNestedFileOnce(t *testing.T) {
t.Parallel()
dir := t.TempDir()
db := openTestDB(t)
file := writeFile(t, dir, "sub/f", pattern(1, 10))
info, err := os.Lstat(dir)
if err != nil {
t.Fatal(err)
}
dev, ok := deviceOfInfo(info)
if !ok {
t.Skip("platform exposes no device id")
}
st := syncOneFilesystem(t, db, []string{dir, file}, map[string]uint64{
dir: dev, filepath.Dir(file): dev, file: dev + 1,
})
if st.added != 1 {
t.Errorf("%s recorded %d times, want once", file, st.added)
}
}
// TestScanOneFilesystemWalksNestedFileOperand checks that with -x a
// regular-file operand under another operand is kept when its directory
// is on a different filesystem than that operand: the walk of the other
// operand does not enter the directory, so the file is recorded once,
// as its own operand. The other operand is given a device that no
// directory here is on.
func TestScanOneFilesystemWalksNestedFileOperand(t *testing.T) {
t.Parallel()
dir := t.TempDir()
db := openTestDB(t)
file := writeFile(t, dir, "sub/f", pattern(1, 10))
info, err := os.Lstat(dir)
if err != nil {
t.Fatal(err)
}
dev, ok := deviceOfInfo(info)
if !ok {
t.Skip("platform exposes no device id")
}
st := syncOneFilesystem(t, db, []string{dir, file}, map[string]uint64{
dir: dev + 1, filepath.Dir(file): dev,
})
if st.added != 1 {
t.Errorf("%s recorded %d times, want once", file, st.added)
}
}
// buildSmokeTree recreates the README smoke-test filesystem layout
// with deterministic content and returns the tree root.
func buildSmokeTree(t *testing.T) string {
@@ -1478,7 +1181,7 @@ func dbRecords(t *testing.T, db *sql.DB) []scanRec {
var recs []scanRec
err := loadFileRows(t.Context(), db, func(int64) {}, func(r scanRec) {
err := loadFileRows(t.Context(), db, func(r scanRec) {
recs = append(recs, r)
})
if err != nil {
@@ -1550,7 +1253,7 @@ func assertSmokeTreeGroups(t *testing.T, dir string, db *sql.DB) {
super, dirs := dbTree(t, db)
tg := collectTreeGroups(dirs, super, nil)
tg := collectTreeGroups(dirs, super)
if len(tg) != 1 {
t.Fatalf("len(tree groups) = %d, want 1", len(tg))
}
@@ -1586,69 +1289,6 @@ func TestScanPipeline(t *testing.T) {
assertSmokeTreeGroups(t, dir, db)
}
// TestScanProgressNamesEachPhase checks the plain progress lines of a
// first scan, and of a rescan of one operand holding two of the
// database's records. Each phase's first line names it with its place
// among the five: load counts the records before reading them, the
// content phase searches the database, and the walk estimates its total
// from the records under its operand, or says its ETA is unknown when
// there are none.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestScanProgressNamesEachPhase(t *testing.T) {
stderr := captureStderr(t)
dir := buildSmokeTree(t)
db := openTestDB(t)
syncTree(t, db, dir)
first := stderr()
syncTree(t, db, filepath.Join(dir, "a"))
rescan := stderr()[len(first):]
load := "[1/5] load: counting the records, elapsed 0s, eta unknown"
content := "[5/5] content: searching the database, elapsed 0s, eta unknown"
cases := map[string][]string{
first: {
load, "[2/5] walk: 0 files, 0 files/s, elapsed 0s, eta unknown",
"[3/5] hash: [0/", "[4/5] update: [0/", content,
},
rescan: {
load, "[2/5] walk: [0/~2] 0%, 0 files/s, elapsed 0s, eta unknown",
"[3/5] hash: [0/", "[4/5] update: [0/", content,
},
}
for out, want := range cases {
var got []string
for line := range strings.Lines(out) {
label, _, _ := strings.Cut(line, ":")
if len(got) == 0 || !strings.HasPrefix(got[len(got)-1], label) {
got = append(got, line)
}
}
if len(got) != len(want) {
t.Fatalf("first lines of the phases = %q, want %q", got, want)
}
for i := range want {
if !strings.HasPrefix(got[i], want[i]) {
t.Errorf("phase %d starts %q, want %q", i+1, got[i], want[i])
}
}
}
// The load phase's total is the count of the records.
loaded := fmt.Sprintf("\n[1/5] load: [%d/%d] 100%%, ",
smokeTreeFiles, smokeTreeFiles)
if !strings.Contains(rescan, loaded) {
t.Errorf("rescan stderr = %q, want %q", rescan, loaded)
}
}
func TestSyncScanUnchangedReuse(t *testing.T) {
t.Parallel()
@@ -2092,7 +1732,7 @@ func TestTreesUnhashedNeverEqual(t *testing.T) {
for name, unknown := range cases {
super, dirs := treeOf(t, append(slices.Clone(shared), unknown...))
if tg := collectTreeGroups(dirs, super, nil); len(tg) != 0 {
if tg := collectTreeGroups(dirs, super); len(tg) != 0 {
t.Errorf("%s: tree groups = %d, want 0 (the files may differ)",
name, len(tg))
}
@@ -2398,43 +2038,14 @@ func TestHashRuns(t *testing.T) {
func TestPruneRoots(t *testing.T) {
t.Parallel()
const pqRoot = "/p/q"
// /p/q is on another filesystem than /p; /p/q/r is on the same one as
// /p/q, /p/s as /p, and /p/t has no known device.
devices := map[string]uint64{"/p": 1, pqRoot: 2, "/p/q/r": 2, "/p/s": 1}
device := func(path string) (uint64, bool) {
dev, ok := devices[path]
return dev, ok
}
// Duplicates and operands under other operands are dropped; /cc is
// not under /c (sibling with a shared prefix).
got := pruneRoots([]string{"/a/b", "/a", "/c", "/a", "/a/b/c", "/cc"},
false, device)
got := pruneRoots([]string{"/a/b", "/a", "/c", "/a", "/a/b/c", "/cc"})
want := []string{"/a", "/c", "/cc"}
if !slices.Equal(got, want) {
t.Fatalf("pruneRoots = %q, want %q", got, want)
}
nested := []string{"/p/q/r", pqRoot, "/p", "/p", "/p/s", "/p/t"}
got = pruneRoots(nested, false, device)
want = []string{"/p"}
if !slices.Equal(got, want) {
t.Fatalf("pruneRoots without -x = %q, want %q", got, want)
}
// With -x, /p/q, on another filesystem than /p, is kept as well.
got = pruneRoots(nested, true, device)
want = []string{"/p", pqRoot}
if !slices.Equal(got, want) {
t.Fatalf("pruneRoots with -x = %q, want %q", got, want)
}
}
func TestReportsNeverTouchFilesystem(t *testing.T) {
script/bootstrap
+16 -107
View File
@@ -1,24 +1,13 @@
#!/bin/sh
# script/bootstrap: install all dependencies needed to build and develop
# this repo. Idempotent: every install is guarded by a check so already
# installed tools are skipped. Base tooling comes from nix, apt, brew,
# or apk (detected in that order); assumes nothing is present. The
# installed node is used only when its major version is the pinned one;
# otherwise (node missing, or another major) the pinned version is
# installed via nvm (installing nvm itself first, from a hash-verified
# release archive, never curl | sh), and yarn and the packages are
# installed under it.
# this repo. Idempotent; assumes nothing is present (not git, make, or
# go). Base tooling comes from nix, apt, brew, or apk (detected in that
# order). golangci-lint and prettier are never installed: they run via
# docker only (script/lint, script/fmt, script/fmt-check).
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
# Pinned versions, 2026-07-06
NODE_VERSION="22.17.0"
NVM_VERSION="0.40.3"
# sha256 of https://github.com/nvm-sh/nvm/archive/refs/tags/v0.40.3.tar.gz
NVM_SHA256="5f4d6aaa04a177dc93c985e31dbc411ab6b8c6e1e21d8015dbc1372625fcd1d0"
YARN_VERSION="1.22.22"
PKGMGR=""
SUDO=""
APT_UPDATED=""
@@ -51,7 +40,6 @@ pkg_install() {
case "$PKGMGR" in
nix) nix-env -iA "nixpkgs.$1" ;;
apt)
# Package lists may be empty (fresh images); refresh once per run.
if [ -z "$APT_UPDATED" ]; then
$SUDO env DEBIAN_FRONTEND=noninteractive apt-get update
APT_UPDATED=1
@@ -67,103 +55,24 @@ missing() {
! command -v "$1" >/dev/null 2>&1
}
# verify_sha256 <file> <expected-hash>
verify_sha256() {
if command -v sha256sum >/dev/null 2>&1; then
actual="$(sha256sum "$1" | cut -d' ' -f1)"
else
actual="$(shasum -a 256 "$1" | cut -d' ' -f1)"
fi
if [ "$actual" != "$2" ]; then
echo "bootstrap: sha256 mismatch for $1" >&2
echo " expected: $2" >&2
echo " actual: $actual" >&2
exit 1
fi
}
# nvm is a bash script; run a command in a bash with nvm loaded
nvm_sh() {
bash -c ". \"\$HOME/.nvm/nvm.sh\" && $*"
}
ensure_nvm() {
[ -s "$HOME/.nvm/nvm.sh" ] && return 0
# nvm prerequisites; nvm itself requires bash
if missing bash; then pkg_install bash bash bash bash; fi
if missing curl; then pkg_install curl curl curl curl; fi
if missing git; then pkg_install git git git git; fi
tmp="$(mktemp -d)"
curl -fsSL -o "$tmp/nvm.tar.gz" \
"https://github.com/nvm-sh/nvm/archive/refs/tags/v${NVM_VERSION}.tar.gz"
verify_sha256 "$tmp/nvm.tar.gz" "$NVM_SHA256"
mkdir -p "$HOME/.nvm"
tar -xzf "$tmp/nvm.tar.gz" -C "$HOME/.nvm" --strip-components=1
rm -rf "$tmp"
}
# True when the node on PATH has the pinned major version. Only the
# major is compared: the Dockerfile stages start from a node 22 alpine
# image whose exact version is not the pin, and nvm cannot install a
# prebuilt node on alpine. Another major is not used: the pinned yarn 1
# prints a deprecation warning under node 24. script/fmt and
# script/fmt-check carry this function unchanged, to run the yarn
# installed here.
node_is_pinned_major() {
if ! command -v node >/dev/null 2>&1; then return 1; fi
installed="$(node --version)"
installed="${installed#v}"
[ "${installed%%.*}" = "${NODE_VERSION%%.*}" ]
}
ensure_node() {
if node_is_pinned_major; then
echo "bootstrap: using node $(node --version)"
return 0
fi
ensure_nvm
nvm_sh "nvm install $NODE_VERSION"
nvm_sh "nvm use $NODE_VERSION >/dev/null && \
echo \"bootstrap: using node \$(node --version)\""
}
ensure_yarn() {
if ! node_is_pinned_major; then
nvm_sh "nvm use $NODE_VERSION >/dev/null && corepack enable && \
corepack prepare yarn@$YARN_VERSION --activate"
return 0
fi
if ! missing yarn; then return 0; fi
if ! missing corepack; then
corepack enable
corepack prepare "yarn@$YARN_VERSION" --activate
else
npm install -g "yarn@$YARN_VERSION"
fi
}
install_js_deps() {
if node_is_pinned_major; then
yarn install --frozen-lockfile
else
nvm_sh "nvm use $NODE_VERSION >/dev/null && cd \"$ROOT\" && \
yarn install --frozen-lockfile"
fi
}
main() {
cd "$ROOT"
if missing make; then pkg_install gnumake make make make; fi
# Deliberately unpinned, so presence is the whole check: go.mod
# governs the Go version, and reproducible builds run in the
# digest-pinned Docker images.
if missing git; then pkg_install git git git git; fi
# Go builds the binary and runs gofmt. Presence is the whole check:
# go.mod names the Go version, and the tests and the linter run in
# digest-pinned images.
if missing make; then pkg_install gnumake make make make; fi
if missing go; then pkg_install go golang go go; fi
ensure_node
ensure_yarn
install_js_deps
# Warn, do not fail: only the targets named below, and the
# pre-commit hook, need docker.
if missing docker; then
echo "bootstrap: WARNING: docker not found; make lint, make fmt," >&2
echo "bootstrap: make fmt-check, make check, make docker and" >&2
echo "bootstrap: make test-race require it." >&2
fi
go mod download
echo "bootstrap complete"
script/check
+1 -3
View File
@@ -1,8 +1,6 @@
#!/bin/sh
# script/check: run all checks (test, lint, fmt-check). Our own
# extension to scripts-to-rule-them-all. test and lint are Docker
# phases; fmt-check is native, because a formatter writes the working
# tree. Must not modify any files.
# extension to scripts-to-rule-them-all. Must not modify any files.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
script/cibuild
+10 -23
View File
@@ -1,32 +1,19 @@
#!/bin/sh
# script/cibuild: run the CI build. It bootstraps first: a CI runner
# checks out and runs this and nothing else, and script/fmt-check runs
# the formatter on the host, which a pristine checkout cannot do.
# A new CACHEBUST value reruns every RUN step, since a cached gate phase
# is a check that did not run; unlike --no-cache, it keeps Go's build cache.
# This relies on every stage of the Dockerfile declaring ARG CACHEBUST
# first; a stage without that line is served from cache on an unchanged
# tree, with no warning.
# script/cibuild: run the CI build. The Gitea workflow runs this on
# push. The Dockerfile runs every gate make check runs, as build steps,
# so a successful build means the repo is green.
#
# Without a fresh CHECK_EPOCH, a rebuild of an unchanged checkout serves
# the gate layers from cache and passes having run none of them. The
# process id goes in with the epoch so two runs started in the same
# second still differ.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
"$SCRIPT_DIR/bootstrap"
"$SCRIPT_DIR/check"
# 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 silently to an empty constant. The
# VERSION build argument takes precedence over the version a build
# stage derives from the .git in the context.
version="$(git describe --tags --always --dirty 2>/dev/null || true)"
[ -n "$version" ] || version="unknown"
tag="$("$SCRIPT_DIR/projectname")"
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
--build-arg VERSION="$version" \
-t "$tag" .
docker build --build-arg CHECK_EPOCH="$(date +%s)-$$" .
}
main "$@"
script/docker
+8 -17
View File
@@ -1,11 +1,9 @@
#!/bin/sh
# script/docker: build the Docker image tagged with the project name.
# Identical in all repos; the tag comes from script/projectname.
# A new CACHEBUST value reruns every RUN step, since a cached gate phase
# is a check that did not run; unlike --no-cache, it keeps Go's build cache.
# This relies on every stage of the Dockerfile declaring ARG CACHEBUST
# first; a stage without that line is served from cache on an unchanged
# tree, with no warning.
# The tag comes from script/projectname. CHECK_EPOCH is passed for the
# same reason script/cibuild passes it: without a fresh value an
# unchanged tree is served from cache and this exits 0 having run no
# gate.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
@@ -13,17 +11,10 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
main() {
cd "$ROOT"
# The version and the tag each get their own line: a failing
# command substitution inside an argument does not trip `set -e`,
# so the inline form degrades silently to an empty constant. The
# VERSION build argument takes precedence over the version a build
# stage derives from the .git in the context.
version="$(git describe --tags --always --dirty 2>/dev/null || true)"
[ -n "$version" ] || version="unknown"
tag="$("$SCRIPT_DIR/projectname")"
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
--build-arg VERSION="$version" \
-t "$tag" .
docker build \
--build-arg CHECK_EPOCH="$(date +%s)-$$" \
-t "$("$SCRIPT_DIR/projectname")" \
.
}
main "$@"
script/fmt
+12 -32
View File
@@ -1,42 +1,22 @@
#!/bin/sh
# script/fmt: format all files (writes).
# script/fmt: format all files (writes): the Go sources with gofmt, the
# Markdown with prettier. prettier is never installed on the host: it
# runs from the Dockerfile's prettier stage with the repository mounted,
# as the calling user so the files it rewrites keep their owner. The tag
# makes each build replace the previous image instead of leaving another
# one behind.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
# Must match the pin in script/bootstrap.
NODE_VERSION="22.17.0"
# True when the node on PATH has the pinned major version: the same
# function as in script/bootstrap, which uses it to decide where it
# installs yarn.
node_is_pinned_major() {
if ! command -v node >/dev/null 2>&1; then return 1; fi
installed="$(node --version)"
installed="${installed#v}"
[ "${installed%%.*}" = "${NODE_VERSION%%.*}" ]
}
# Run the yarn script/bootstrap installed: the yarn on PATH when the
# node on PATH has the pinned major version, and otherwise yarn under
# the pinned node in nvm, which bootstrap leaves off the PATH of the
# shell that called it. nvm is a bash script, hence the subshell.
run_yarn() {
if node_is_pinned_major && command -v yarn >/dev/null 2>&1; then
exec yarn "$@"
fi
if node_is_pinned_major || [ ! -s "$HOME/.nvm/nvm.sh" ]; then
echo "fmt: no yarn; run script/bootstrap first" >&2
exit 1
fi
exec bash -c '. "$HOME/.nvm/nvm.sh" && nvm use "$1" >/dev/null &&
shift && exec yarn "$@"' bash "$NODE_VERSION" "$@"
}
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
main() {
cd "$ROOT"
gofmt -s -w .
run_yarn run prettier --write '**/*.md' --tab-width 4 --prose-wrap always
image="$("$SCRIPT_DIR/projectname")-prettier"
docker build -q --target prettier -t "$image" . >/dev/null
docker run --rm --user "$(id -u):$(id -g)" -v "$ROOT:/src" "$image" \
prettier --write '**/*.md' --tab-width 4 --prose-wrap always
}
main "$@"
script/fmt-check
+15 -36
View File
@@ -1,45 +1,19 @@
#!/bin/sh
# script/fmt-check: check formatting (read-only).
# script/fmt-check: check formatting (read-only). Same scope as
# script/fmt, but fails instead of writing. gofmt and prettier both run
# every time and each reports its own failure, so the output says which
# one failed.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
# Must match the pin in script/bootstrap.
NODE_VERSION="22.17.0"
# True when the node on PATH has the pinned major version: the same
# function as in script/bootstrap, which uses it to decide where it
# installs yarn.
node_is_pinned_major() {
if ! command -v node >/dev/null 2>&1; then return 1; fi
installed="$(node --version)"
installed="${installed#v}"
[ "${installed%%.*}" = "${NODE_VERSION%%.*}" ]
}
# Run the yarn script/bootstrap installed: the yarn on PATH when the
# node on PATH has the pinned major version, and otherwise yarn under
# the pinned node in nvm, which bootstrap leaves off the PATH of the
# shell that called it. nvm is a bash script, hence the subshell.
run_yarn() {
if node_is_pinned_major && command -v yarn >/dev/null 2>&1; then
exec yarn "$@"
fi
if node_is_pinned_major || [ ! -s "$HOME/.nvm/nvm.sh" ]; then
echo "fmt-check: no yarn; run script/bootstrap first" >&2
exit 1
fi
exec bash -c '. "$HOME/.nvm/nvm.sh" && nvm use "$1" >/dev/null &&
shift && exec yarn "$@"' bash "$NODE_VERSION" "$@"
}
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
main() {
cd "$ROOT"
status=0
# gofmt and prettier both run every time, so the output names each
# one that fails. Under set -e a bare assignment would end the
# script when gofmt fails (a Go file it cannot parse).
# Under set -e a bare assignment would end the script when gofmt
# fails (a Go file it cannot parse), and prettier would never run.
if ! files="$(gofmt -s -l .)"; then
echo "gofmt: failed; see its errors above" >&2
status=1
@@ -50,9 +24,14 @@ main() {
status=1
fi
# run_yarn ends in exec; the subshell returns here afterwards.
(run_yarn run prettier --check '**/*.md' --tab-width 4 --prose-wrap always) ||
# Same image as script/fmt; see there.
image="$("$SCRIPT_DIR/projectname")-prettier"
docker build -q --target prettier -t "$image" . >/dev/null
if ! docker run --rm -v "$ROOT:/src:ro" "$image" \
prettier --check '**/*.md' --tab-width 4 --prose-wrap always; then
echo "prettier: Markdown not formatted; run make fmt" >&2
status=1
fi
exit "$status"
}
script/install-precommit
+7 -3
View File
@@ -1,15 +1,19 @@
#!/bin/sh
# script/install-precommit: install the git pre-commit hook that runs
# script/precommit. Our own extension to scripts-to-rule-them-all.
# Hooks are shared between the main checkout and all worktrees, so
# resolve the common git dir instead of assuming .git is a directory.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
hook=".git/hooks/pre-commit"
printf '#!/bin/sh\nset -e\nscript/precommit\n' > .git/hooks/pre-commit
chmod +x .git/hooks/pre-commit
hooks_dir="$(git rev-parse --git-common-dir)/hooks"
mkdir -p "$hooks_dir"
hook="$hooks_dir/pre-commit"
printf '#!/bin/sh\nset -e\nscript/precommit\n' > "$hook"
chmod +x "$hook"
echo "pre-commit hook installed: runs script/precommit"
}
script/lint
+18 -16
View File
@@ -1,26 +1,28 @@
#!/bin/sh
# script/lint: run the linter. Linting is a phase of the Dockerfile and
# this builds that phase alone; the linter is never installed or run on
# a developer host, where a shared result cache and a host-global lock
# make its answer untrustworthy.
# script/lint: run the linter. golangci-lint is never installed on a
# host: this builds Dockerfile.lint, which copies the repo into the
# digest-pinned golangci-lint image and lints as a build step, so a
# successful build is a clean lint. A cold cache needs the network to
# pull the image and for `go mod download`; once warm this runs offline
# until go.mod or go.sum changes.
#
# The phase is not the last stage in the file, so it is built only when
# --target names it. A new CACHEBUST value reruns every RUN step, since
# a cached lint layer is a lint that did not run; unlike --no-cache, it
# keeps Go's build cache. This relies on every stage of the Dockerfile
# declaring ARG CACHEBUST first; a stage without that line is served
# from cache on an unchanged tree, with no warning.
# --output type=cacheonly writes no image, since nothing uses one.
# Without a fresh CHECK_EPOCH docker serves the gate layers from cache
# on an unchanged tree and this exits 0 having run no linter. The PID is
# in the value because two lint runs land inside the same second easily.
#
# The image is never used, so --output=type=cacheonly writes none;
# without it every run leaves an untagged image behind.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
--target lint \
--output type=cacheonly .
docker build \
--build-arg CHECK_EPOCH="$(date +%s)-$$" \
--output=type=cacheonly \
-f Dockerfile.lint \
.
}
main "$@"
script/precommit
+2 -2
View File
@@ -1,13 +1,13 @@
#!/bin/sh
# script/precommit: run by the git pre-commit hook; fails the commit if
# checks fail. Our own extension to scripts-to-rule-them-all.
# checks fail. Our own extension to scripts-to-rule-them-all. Go extra:
# go mod tidy must be a no-op before the checks run.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
main() {
# Go extra: go mod tidy must be a no-op before the checks run.
cd "$ROOT"
go mod tidy
if ! git diff --exit-code -- go.mod go.sum; then
script/setup
+1 -1
View File
@@ -1,6 +1,6 @@
#!/bin/sh
# script/setup: set up the repo for development after a fresh clone:
# installs dependencies and the git pre-commit hook.
# installs dependencies (script/bootstrap) and the git pre-commit hook.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
script/test
+8 -14
View File
@@ -1,23 +1,17 @@
#!/bin/sh
# script/test: run the test suite. Testing is a phase of the Dockerfile
# and this builds that phase alone, on the same terms as script/lint:
# --target because a phase that is not the last stage is built only when
# named, and a new CACHEBUST value because a cached test layer is a test
# that did not run; unlike --no-cache, it keeps Go's build cache. This
# relies on every stage of the Dockerfile declaring ARG CACHEBUST first;
# a stage without that line is served from cache on an unchanged tree,
# with no warning. --output type=cacheonly writes no image, since
# nothing uses one.
# script/test: run the test suite. Reruns verbosely on failure so CI
# logs show which test failed.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
docker build --build-arg CACHEBUST="$(date +%s)-$$" \
--target test \
--output type=cacheonly .
go test -timeout 30s -cover ./... || {
echo "--- Rerunning with -v for details ---"
go test -timeout 30s -v ./...
exit 1
}
}
main "$@"
script/test-race
Executable
+40
View File
@@ -0,0 +1,40 @@
#!/bin/sh
# script/test-race: run the test suite under the race detector. Not part
# of script/check.
#
# The race detector needs cgo and a C compiler, which the host build
# never uses, so the tests run in a golang image that has gcc. The
# checkout is mounted read-only, so the docker daemon must be local. The
# container starts with empty caches every time: each run downloads the
# dependencies and compiles them with the detector, which needs the
# network and takes minutes.
#
# The tests run as the calling user, never as root: several of them make
# a file unreadable and expect reading it to fail, and root reads it
# anyway. When the caller is root they run as nobody, and then the
# checkout must be readable by other users. Neither user has a home
# directory in the image, so HOME is /tmp, where Go puts its build cache.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
# golang:1.25-trixie, 2026-10-04. Debian rather than the Alpine image the
# Dockerfile builds with, because this one includes gcc.
IMAGE="golang@sha256:2c4c60ef415fbfa5e90300722293bef36c5e63fae17570ce18f580af933dbd73"
main() {
user="$(id -u):$(id -g)"
if [ "$(id -u)" -eq 0 ]; then
user=65534:65534
fi
docker run --rm \
--user "$user" \
--env HOME=/tmp \
--env CGO_ENABLED=1 \
--volume "$ROOT:/src:ro" \
--workdir /src \
"$IMAGE" \
go test -race -timeout 60s ./...
}
main "$@"
script/verify-lint-image-pin
Executable
+77
View File
@@ -0,0 +1,77 @@
#!/bin/sh
# script/verify-lint-image-pin: fail unless the golangci-lint image
# referenced by Dockerfile.lint and the one referenced by the main
# Dockerfile's lint stage are the same image at the same digest. Our own
# extension to scripts-to-rule-them-all, not one of its entrypoints; run
# as a gate in both files. Nothing else keeps the two pins in sync, and
# a bump applied to one alone would lint the same tree against different
# rulesets, both green.
#
# Do not hardcode the expected digest here: that is a third copy to keep
# in sync.
#
# A reference that cannot be read is a hard failure, not a skip: two
# empty strings compare equal.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
LINT_DOCKERFILE="Dockerfile.lint"
MAIN_DOCKERFILE="Dockerfile"
# Echo the single golangci-lint image reference in the named Dockerfile.
# Scans every argument of every FROM instruction rather than assuming a
# field position, so `FROM --platform=... img AS stage` reads correctly.
# Exits non-zero, with a diagnosis, unless there is exactly one.
lint_image_ref() {
file="$1"
if [ ! -f "$file" ]; then
echo "verify-lint-image-pin: $file: not found" >&2
return 1
fi
refs="$(
awk '
toupper($1) == "FROM" {
for (i = 2; i <= NF; i++) {
if ($i ~ /^golangci\/golangci-lint[:@]/) {
print $i
}
}
}
' "$file"
)"
count="$(printf '%s' "$refs" | grep -c . || true)"
if [ "$count" -ne 1 ]; then
echo "verify-lint-image-pin: $file: expected exactly one" \
"golangci/golangci-lint FROM reference, found $count" >&2
return 1
fi
printf '%s\n' "$refs"
}
main() {
cd "$ROOT"
lint_ref="$(lint_image_ref "$LINT_DOCKERFILE")"
main_ref="$(lint_image_ref "$MAIN_DOCKERFILE")"
if [ "$lint_ref" != "$main_ref" ]; then
echo "verify-lint-image-pin: the linter image is pinned twice and" \
"the two pins disagree:" >&2
echo "verify-lint-image-pin: $LINT_DOCKERFILE: $lint_ref" >&2
echo "verify-lint-image-pin: $MAIN_DOCKERFILE: $main_ref" >&2
echo "verify-lint-image-pin: bump both FROM lines together so" \
"script/lint and the Dockerfile lint stage keep running the" \
"same linter" >&2
exit 1
fi
echo "verify-lint-image-pin: $LINT_DOCKERFILE and $MAIN_DOCKERFILE" \
"agree on $lint_ref"
}
main "$@"
trees.go
+28 -114
View File
@@ -1,9 +1,9 @@
package main
import (
"bufio"
"context"
"crypto/sha256"
"database/sql"
"fmt"
"io"
"os"
@@ -24,129 +24,44 @@ type treeNode struct {
totalSize int64
}
// treesPhase names one phase of trees with its place among all of them,
// as "[2/4] read", for the phase's progress display. The list here is
// the one place the phases are counted.
func treesPhase(name string) string {
return phaseLabel([]string{"open", "read", "group", "write"}, name)
}
// runTrees implements the trees subcommand: it reads every record from
// the database in path order, reconstructs the directory hierarchy from
// the record paths, computes a Merkle-style digest per directory, and
// prints maximal duplicate-tree groups as TSV on stdout. It never
// touches the scanned filesystem; its only I/O is the database, stdout,
// and stderr. It names the database on stderr before it opens it. Any
// database problem, including a missing database, is fatal.
//
// The work runs in four phases, each under a progress display of its
// own on stderr: open (open the database), read (count the records,
// then read them into the hierarchy), group (group the directories by
// digest) and write (write the groups to stdout). Each display ends
// before the next phase starts, and before an error is returned to be
// printed.
// and stderr. Any database problem, including a missing database, is
// fatal.
func runTrees(ctx context.Context, stdout io.Writer) error {
dbPath, source, err := databasePath()
if err != nil {
return err
}
dbPath := databasePath()
fmt.Fprintf(os.Stderr, "trees: database %s (%s)\n",
escapePath(dbPath), source)
// Opening can wait on a busy database for as long as the busy
// timeout.
prog := newProgress(progressParams{
label: treesPhase("open"), total: -1,
waitingFor: "opening the database",
})
db, err := openReportDatabase(ctx, dbPath)
prog.finish()
if err != nil {
return err
}
defer func() { _ = db.Close() }()
prog = newProgress(progressParams{
label: treesPhase("read"), unit: "records", total: -1,
waitingFor: "counting the records",
records := 0
tree := newTreeBuilder()
err = loadFileRows(ctx, db, func(r scanRec) {
records++
tree.add(r)
})
records, super, allDirs, err := readTree(ctx, db, prog)
prog.finish()
if err != nil {
return fmt.Errorf("database %s: %w", dbPath, err)
}
prog = newProgress(progressParams{
label: treesPhase("group"), unit: "directories",
total: int64(len(allDirs)),
})
dupes := collectTreeGroups(allDirs, super, prog)
prog.finish()
prog = newProgress(progressParams{
label: treesPhase("write"), unit: "groups", total: int64(len(dupes)),
})
dupeTrees, reclaimable, err := writeTreeGroups(stdout, dupes, prog)
prog.finish()
if err != nil {
return err
}
fmt.Fprintf(os.Stderr,
"trees: %d records read, %d duplicate tree groups, %d dupe trees, "+
"%s reclaimable\n",
records, len(dupes), dupeTrees, humanBytes(reclaimable))
return nil
}
// readTree gives prog the number of records in db as its total, then
// reads every record in path order into the directory hierarchy,
// counting each on prog. It returns the number of records read, the
// super-root and every directory.
func readTree(ctx context.Context, db *sql.DB,
prog *progress,
) (int, *treeNode, []*treeNode, error) {
records := 0
tree := newTreeBuilder()
err := loadFileRows(ctx, db, prog.setTotal, func(r scanRec) {
records++
prog.increment()
tree.add(r)
})
if err != nil {
return 0, nil, nil, err
}
super, allDirs := tree.finish()
return records, super, allDirs, nil
}
dupes := collectTreeGroups(allDirs, super)
// writeTreeGroups writes dupes to stdout as TSV, a header line and then
// a row for every member of each group but its first, counting each
// group on prog once its rows are written. stdout may be the terminal
// prog is drawn on, so the lines go through prog's writer. It returns
// the number of rows (dupe trees) and the bytes they could reclaim.
func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
prog *progress,
) (int, int64, error) {
out := prog.writer(stdout)
out := bufio.NewWriterSize(stdout, ioBufSize)
_, err := fmt.Fprintln(out, "first\tdupe\tfiles\tsize")
_, err = fmt.Fprintln(out, "first\tdupe\tfiles\tsize")
if err != nil {
return 0, 0, fmt.Errorf("write stdout: %w", err)
return fmt.Errorf("write stdout: %w", err)
}
dupeTrees := 0
@@ -160,22 +75,25 @@ func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
escapePath(first.path), escapePath(n.path),
first.fileCount, first.totalSize)
if err != nil {
return 0, 0, fmt.Errorf("write stdout: %w", err)
return fmt.Errorf("write stdout: %w", err)
}
dupeTrees++
reclaimable += first.totalSize
}
prog.increment()
}
err = out.Flush()
if err != nil {
return 0, 0, fmt.Errorf("write stdout: %w", err)
return fmt.Errorf("write stdout: %w", err)
}
return dupeTrees, reclaimable, nil
fmt.Fprintf(os.Stderr,
"trees: %d records read, %d duplicate tree groups, %d dupe trees, "+
"%s reclaimable\n",
records, len(dupes), dupeTrees, humanBytes(reclaimable))
return nil
}
// treeBuilder reconstructs the directory hierarchy from records added
@@ -297,18 +215,14 @@ func fileEntry(name string, r scanRec) string {
"\x00" + r.head + "\x00" + r.tail + "\x00" + content
}
// collectTreeGroups groups directories by digest, counting each one on
// prog as it is grouped, and returns every maximal group with two or
// more members, each group's members sorted by path, groups ordered by
// tree size descending then by first path ascending.
func collectTreeGroups(allDirs []*treeNode, super *treeNode,
prog *progress,
) [][]*treeNode {
// collectTreeGroups groups directories by digest and returns every
// maximal group with two or more members, each group's members sorted
// by path, groups ordered by tree size descending then by first path
// ascending.
func collectTreeGroups(allDirs []*treeNode, super *treeNode) [][]*treeNode {
groups := make(map[[sha256.Size]byte][]*treeNode)
for _, d := range allDirs {
groups[d.digest] = append(groups[d.digest], d)
prog.increment()
}
var dupes [][]*treeNode
trees_test.go
+7 -107
View File
@@ -3,11 +3,8 @@ package main
import (
"bytes"
"database/sql"
"os"
"slices"
"strings"
"testing"
"time"
)
// Signature hashes shared by the smoke-test records.
@@ -20,11 +17,6 @@ const (
f2Content = "f2c"
)
// treesOpenLine is the plain line of trees' open phase when it opens
// the database at once; it prints it as the phase starts and as it ends.
const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
"eta unknown"
// smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
// /d/t2 are identical, /d/t3 differs from them only by one filename.
func smokeTreeRecs() []scanRec {
@@ -46,7 +38,7 @@ func dbTree(t *testing.T, db *sql.DB) (*treeNode, []*treeNode) {
tree := newTreeBuilder()
err := loadFileRows(t.Context(), db, func(int64) {}, tree.add)
err := loadFileRows(t.Context(), db, tree.add)
if err != nil {
t.Fatal(err)
}
@@ -178,7 +170,7 @@ func TestTreeNamesSortingBeforeSlash(t *testing.T) {
t.Fatalf("directory paths = %q, want %q", got, want)
}
groups := collectTreeGroups(dirs, super, nil)
groups := collectTreeGroups(dirs, super)
gotGroups := groupPaths(groups)
wantGroups := [][]string{{"/a", "/c"}}
@@ -211,98 +203,6 @@ func TestRunTreesEscapesPaths(t *testing.T) {
}
}
// TestRunTreesProgressNamesEachPhase runs trees on the smoke-test
// records with stderr not a terminal, and checks every line it prints
// there. After the line naming the database, each phase prints a line
// naming it with its place among the four as it starts and another as
// it ends. read counts the 6 records before it reads them, group counts
// the 8 directories, and write the 1 group. The summary comes last, and
// stdout holds the report alone.
func TestRunTreesProgressNamesEachPhase(t *testing.T) {
path := seedDatabase(t, smokeTreeRecs())
t.Setenv(databaseEnv, path)
stderr := captureStderr(t)
var stdout bytes.Buffer
code := run([]string{cmdTrees}, &stdout, os.Stderr)
if code != exitOK {
t.Fatalf("run(trees) = %d, want %d; stderr: %s",
code, exitOK, stderr())
}
report := "first\tdupe\tfiles\tsize\n/d/t1\t/d/t2\t2\t3100\n"
if got := stdout.String(); got != report {
t.Errorf("stdout = %q, want %q", got, report)
}
// How each line starts; the rate at the end of a phase varies.
want := []string{
"trees: database " + path + " (from " + databaseEnv + ")",
treesOpenLine,
treesOpenLine,
"[2/4] read: counting the records, elapsed 0s, eta unknown",
"[2/4] read: [6/6] 100%, ",
"[3/4] group: [0/8] 0%, 0 directories/s, elapsed 0s, eta unknown",
"[3/4] group: [8/8] 100%, ",
"[4/4] write: [0/1] 0%, 0 groups/s, elapsed 0s, eta unknown",
"[4/4] write: [1/1] 100%, ",
"trees: 6 records read, 1 duplicate tree groups, 1 dupe trees, ",
}
lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
if len(lines) != len(want) {
t.Fatalf("stderr lines = %q, want %d lines starting %q",
lines, len(want), want)
}
for i := range want {
if !strings.HasPrefix(lines[i], want[i]) {
t.Errorf("stderr line %d = %q, want it to start %q",
i+1, lines[i], want[i])
}
}
}
// TestWriteTreeGroupsOnTerminal writes the smoke-test report to the
// terminal its write phase's display is drawn on, as a plain "sfdupes
// trees" does: the terminal must show the header and the row whole,
// each on a line of its own.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestWriteTreeGroupsOnTerminal(t *testing.T) {
stderr := captureStderr(t)
super, dirs := treeOf(t, smokeTreeRecs())
dupes := collectTreeGroups(dirs, super, nil)
// No timed draws: the display is drawn as it starts and as it ends.
p := startProgress(progressParams{
label: treesPhase("write"), unit: "groups", total: int64(len(dupes)),
}, terminalWidth, time.Hour)
_, _, err := writeTreeGroups(os.Stderr, dupes, p)
p.finish()
if err != nil {
t.Fatal(err)
}
// A terminal shows each line as the text after its last carriage
// return.
var shown []string
for line := range strings.SplitSeq(stderr(), "\n") {
shown = append(shown, line[strings.LastIndex(line, "\r")+1:])
}
want := []string{"first\tdupe\tfiles\tsize", "/d/t1\t/d/t2\t2\t3100"}
if len(shown) < len(want) || !slices.Equal(shown[:len(want)], want) {
t.Errorf("terminal shows lines %q, want %q first", shown, want)
}
}
func TestTreeDigests(t *testing.T) {
t.Parallel()
@@ -354,7 +254,7 @@ func TestCollectTreeGroupsMaximal(t *testing.T) {
super, dirs := treeOf(t, smokeTreeRecs())
groups := collectTreeGroups(dirs, super, nil)
groups := collectTreeGroups(dirs, super)
want := [][]string{{"/d/t1", "/d/t2"}}
if got := groupPaths(groups); !slices.EqualFunc(got, want,
@@ -378,14 +278,14 @@ func TestCollectTreeGroupsDeterministic(t *testing.T) {
super, dirs := treeOf(t, recs)
forward := groupPaths(collectTreeGroups(dirs, super, nil))
forward := groupPaths(collectTreeGroups(dirs, super))
reversed := slices.Clone(recs)
slices.Reverse(reversed)
superR, dirsR := treeOf(t, reversed)
backward := groupPaths(collectTreeGroups(dirsR, superR, nil))
backward := groupPaths(collectTreeGroups(dirsR, superR))
if !slices.EqualFunc(forward, backward, slices.Equal) {
t.Fatalf("output depends on record order: %v vs %v",
forward, backward)
@@ -404,7 +304,7 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
super, dirs := treeOf(t, recs)
got := groupPaths(collectTreeGroups(dirs, super, nil))
got := groupPaths(collectTreeGroups(dirs, super))
want := [][]string{{"/p/x1", "/p/x2"}}
if !slices.EqualFunc(got, want, slices.Equal) {
@@ -426,7 +326,7 @@ func TestCollectTreeGroupsDifferingParents(t *testing.T) {
super, dirs := treeOf(t, recs)
got := groupPaths(collectTreeGroups(dirs, super, nil))
got := groupPaths(collectTreeGroups(dirs, super))
want := [][]string{{"/p/a/x", "/q/b/x"}}
if !slices.EqualFunc(got, want, slices.Equal) {