Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c64bbbb78e | ||
|
|
5900feb515 |
@@ -13,3 +13,6 @@ 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.
|
||||
|
||||
@@ -1,11 +1,20 @@
|
||||
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
|
||||
|
||||
+5
-3
@@ -27,7 +27,7 @@ node_modules/
|
||||
# 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 after these lines, for example `!.env.example`.
|
||||
# its own negation at the end of this file, for example `!.env.example`.
|
||||
*.[eE][nN][vV]
|
||||
.[eE][nN][vV].*
|
||||
.[eE][nN][vV][rR][cC]
|
||||
@@ -46,11 +46,13 @@ node_modules/
|
||||
[iI][dD]_[eE][dD]25519
|
||||
[iI][dD]_[eE][dD]25519_[sS][kK]
|
||||
|
||||
# This repository's own entries, kept after the canonical content above.
|
||||
# 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/`.
|
||||
/sfdupes
|
||||
*.log
|
||||
*.out
|
||||
*.test
|
||||
/sfdupes
|
||||
|
||||
# A scan database lists every path it scanned.
|
||||
*.sqlite
|
||||
|
||||
@@ -25,6 +25,8 @@ 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
|
||||
|
||||
+12
-36
@@ -1,6 +1,6 @@
|
||||
# Lint phase, built alone by script/lint. The tools are invoked directly
|
||||
# rather than through `make lint` or `make fmt-check`, which run docker
|
||||
# themselves and so cannot run inside a build step.
|
||||
# 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
|
||||
WORKDIR /src
|
||||
@@ -8,9 +8,9 @@ COPY go.mod go.sum ./
|
||||
RUN go mod download
|
||||
COPY . .
|
||||
|
||||
# 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.
|
||||
# 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="$(gofmt -s -l .)" && \
|
||||
if [ -n "$files" ]; then \
|
||||
echo "gofmt: files not formatted:" >&2; echo "$files" >&2; exit 1; \
|
||||
@@ -38,43 +38,19 @@ RUN go test -timeout 90s -race -cover ./... || \
|
||||
{ echo "--- Rerunning with -v for details ---"; \
|
||||
go test -timeout 90s -race -v ./...; exit 1; }
|
||||
|
||||
# Prettier stage: the prettier that formats this repository's Markdown,
|
||||
# never installed on a host. script/fmt and script/fmt-check build this
|
||||
# stage alone and run it with the repository mounted on /src. prettier
|
||||
# is installed in /tools so that the repository, mounted or copied onto
|
||||
# /src, cannot hide it.
|
||||
# node:22-alpine, 2026-02-22
|
||||
FROM node@sha256:e4bf2a82ad0a4037d28035ae71529873c069b13eb0455466ae0bc13363826e34 AS prettier
|
||||
WORKDIR /tools
|
||||
# yarn.lock pins prettier by hash, and --frozen-lockfile fails rather
|
||||
# than install anything yarn.lock does not name.
|
||||
COPY package.json yarn.lock ./
|
||||
RUN yarn install --frozen-lockfile
|
||||
ENV PATH=/tools/node_modules/.bin:$PATH
|
||||
WORKDIR /src
|
||||
|
||||
# Markdown stage: the Markdown half of `make fmt-check`, as a gate.
|
||||
FROM prettier AS markdown
|
||||
COPY . .
|
||||
RUN prettier --check '**/*.md' --tab-width 4 --prose-wrap always
|
||||
|
||||
# Build stage. Nothing is wanted from the lint, test and markdown stages;
|
||||
# the copies are what make BuildKit build them first, so this stage
|
||||
# cannot run unless all three passed.
|
||||
# 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.
|
||||
# golang:1.25-alpine, 2026-07-23
|
||||
FROM golang@sha256:56961d79ea8129efddcc0b8643fd8a5416b4e6228cfd477e3fd61deb2672c587 AS builder
|
||||
COPY --from=lint /src/go.sum /dev/null
|
||||
COPY --from=test /src/go.sum /dev/null
|
||||
COPY --from=markdown /src/go.sum /dev/null
|
||||
WORKDIR /src
|
||||
|
||||
# script/bootstrap installs the git and make this image lacks, and ends
|
||||
# in `go mod download`.
|
||||
COPY script/ script/
|
||||
COPY go.mod go.sum ./
|
||||
RUN script/bootstrap
|
||||
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
|
||||
WORKDIR /src
|
||||
COPY go.mod go.sum ./
|
||||
RUN go mod download
|
||||
COPY . .
|
||||
|
||||
# The version stamped into the binary: the VERSION build argument when
|
||||
|
||||
@@ -314,7 +314,8 @@ All three subcommands operate on a single SQLite database file:
|
||||
CREATE TABLE files (
|
||||
path BLOB PRIMARY KEY, -- absolute path, raw bytes
|
||||
size INTEGER NOT NULL, -- bytes, from lstat
|
||||
mtime INTEGER NOT NULL, -- Unix seconds, from lstat
|
||||
mtime INTEGER NOT NULL, -- whole Unix seconds of the mtime, from lstat
|
||||
mtime_nsec INTEGER NOT NULL, -- nanoseconds within that second, 0 to 999999999
|
||||
head TEXT NOT NULL, -- lowercase-hex SHA-256; first 64 KiB, or whole file under 10 MiB
|
||||
tail TEXT NOT NULL, -- lowercase-hex SHA-256; last 64 KiB, or whole file under 10 MiB
|
||||
content TEXT NOT NULL -- lowercase-hex SHA-256, whole file or samples
|
||||
@@ -323,18 +324,22 @@ All three subcommands operate on a single SQLite database file:
|
||||
```
|
||||
|
||||
Paths are stored as BLOBs because Unix paths are raw bytes, not guaranteed
|
||||
UTF-8. `mtime` is used only for change detection; it is not part of the
|
||||
duplicate key. For a file under 10 MiB `head`, `tail`, and `content` all
|
||||
hold the whole-file hash (that range is hashed in full, with no end
|
||||
windows); for a larger file `head` and `tail` hold the first- and last-64
|
||||
KiB hashes and `content` the whole-file or sampled hash. All three are empty
|
||||
strings when the file has never been hashed because its size was unique as
|
||||
of the last scan that covered it. For a file of 10 MiB or more, `content`
|
||||
stays empty until the content phase of a scan (see "`scan` mode" below) has
|
||||
read the file. A record with an empty `content` is never part of a duplicate
|
||||
group, though it still defines the file for tree reconstruction. The
|
||||
`files_signature` index lets SQLite group the records by signature for
|
||||
`report` without sorting the whole table.
|
||||
UTF-8. `mtime` and `mtime_nsec` hold the file's mtime to the nanosecond:
|
||||
`mtime` the whole Unix seconds, rounded down, and `mtime_nsec` the
|
||||
nanoseconds past that second. Split this way they hold any mtime a
|
||||
filesystem can record, one before 1678 or after 2262 included, which a
|
||||
single 64-bit count of nanoseconds cannot. They are used only for change
|
||||
detection and are not part of the duplicate key. For a file under 10 MiB
|
||||
`head`, `tail`, and `content` all hold the whole-file hash (that range is
|
||||
hashed in full, with no end windows); for a larger file `head` and `tail`
|
||||
hold the first- and last-64 KiB hashes and `content` the whole-file or
|
||||
sampled hash. All three are empty strings when the file has never been
|
||||
hashed because its size was unique as of the last scan that covered it. For
|
||||
a file of 10 MiB or more, `content` stays empty until the content phase of a
|
||||
scan (see "`scan` mode" below) has read the file. A record with an empty
|
||||
`content` is never part of a duplicate group, though it still defines the
|
||||
file for tree reconstruction. The `files_signature` index lets SQLite group
|
||||
the records by signature for `report` without sorting the whole table.
|
||||
|
||||
### Duplicate detection
|
||||
|
||||
@@ -421,6 +426,9 @@ operands:
|
||||
once its size, `head`, and `tail` match another record's.
|
||||
- A file whose mtime is newer than recorded, or whose size differs, is processed
|
||||
as if new: re-hashed, or recorded without hashes, per the shared-size rule.
|
||||
Change detection compares the mtime to the nanosecond, as finely as the
|
||||
filesystem records it, so a same-size rewrite counts as a change whenever the
|
||||
filesystem gives it a later mtime than recorded, even within the same second.
|
||||
- A database record whose path lies under one of the scanned operands but was
|
||||
not successfully processed this run is deleted. This removes records for
|
||||
deleted files. It also removes records for paths that failed to stat or hash
|
||||
@@ -738,50 +746,48 @@ 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. `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:
|
||||
`make build` works without it, and testing, linting, formatting and the image
|
||||
build need it. Ends with `go mod download`.
|
||||
presence-checked only. An installed node is used as it is; otherwise node
|
||||
22.17.0 is installed through nvm, which comes from a release archive whose
|
||||
sha256 the script checks. 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`.
|
||||
- `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, tagged
|
||||
`sfdupes-test`. 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.
|
||||
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, tagged `sfdupes-lint`: in the digest-pinned `golangci/golangci-lint`
|
||||
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/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). 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` phase, prettier in its `markdown` stage.
|
||||
indents, prose wrapped at 80 columns). Both run on the host, prettier through
|
||||
yarn at the version `yarn.lock` pins. When yarn is not on `PATH`, 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.
|
||||
- `script/check` — run `script/test`, `script/lint`, and `script/fmt-check`, in
|
||||
that order. Modifies nothing. Needs `docker`, because all three do.
|
||||
that order. Modifies nothing. The first two need `docker`, the third what
|
||||
`script/bootstrap` installs.
|
||||
- `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`, `test` and `markdown` stages, so this is also the check a developer or
|
||||
reviewer runs by hand.
|
||||
`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:
|
||||
@@ -789,16 +795,13 @@ entrypoints are:
|
||||
- `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 that runs
|
||||
`script/precommit`. The hook is written to the common git directory, so the
|
||||
main checkout and every worktree share it.
|
||||
- `script/install-precommit` — install the git pre-commit hook, as
|
||||
`.git/hooks/pre-commit`, that runs `script/precommit`.
|
||||
|
||||
Every `docker build` in `script/` passes `--no-cache`. On an unchanged tree
|
||||
Docker would serve the gate steps from its cache, and the build would pass
|
||||
having run no test and no linter. Every run therefore downloads the Go modules
|
||||
again and needs the network. `script/test` and `script/lint` send the daemon
|
||||
only a build context, so they work against a remote docker daemon; `script/fmt`
|
||||
and `script/fmt-check` mount the repository and need a local one.
|
||||
again and needs the network.
|
||||
|
||||
## Build
|
||||
|
||||
@@ -815,10 +818,10 @@ compile recipe:
|
||||
- `make lint` — run `golangci-lint` with the repo config and the gofmt check, in
|
||||
Docker (see `script/lint`); requires `docker`.
|
||||
- `make fmt` / `make fmt-check` — format the Go sources and the Markdown /
|
||||
verify formatting without writing; requires `docker`, for prettier (see
|
||||
`script/fmt`).
|
||||
verify formatting without writing, on the host; requires `go` and what
|
||||
`make bootstrap` installs (see `script/fmt`).
|
||||
- `make check` — `test`, `lint`, and `fmt-check`; modifies nothing. Requires
|
||||
`docker`.
|
||||
`docker` and what `make bootstrap` installs.
|
||||
- `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.
|
||||
|
||||
+58
-25
@@ -1,6 +1,6 @@
|
||||
---
|
||||
title: Repository Policies
|
||||
last_modified: 2026-10-04
|
||||
last_modified: 2026-10-07
|
||||
---
|
||||
|
||||
This document covers repository structure, tooling, and workflow standards. Code
|
||||
@@ -118,8 +118,8 @@ style conventions are in separate documents:
|
||||
and nothing else:
|
||||
|
||||
```sh
|
||||
docker build --no-cache --target lint -t "$(script/projectname)-lint" .
|
||||
docker build --no-cache --target test -t "$(script/projectname)-test" .
|
||||
docker build --no-cache --target lint --output type=cacheonly .
|
||||
docker build --no-cache --target test --output type=cacheonly .
|
||||
```
|
||||
|
||||
**A stage that is not the last one in the file is built only when the final
|
||||
@@ -129,10 +129,15 @@ style conventions are in separate documents:
|
||||
plain `docker build .` builds the last stage alone and exits 0 having linted
|
||||
and tested nothing.
|
||||
|
||||
**Every `docker build` in `script/` is tagged**, here and in
|
||||
`script/cibuild` and `script/docker`. An untagged build leaves a dangling
|
||||
image behind on every invocation, on every developer host and every CI
|
||||
runner; a tagged one replaces the previous image.
|
||||
**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 and every compiled package. 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
|
||||
@@ -278,20 +283,39 @@ style conventions are in separate documents:
|
||||
`.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.
|
||||
|
||||
- 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.
|
||||
That script bootstraps, runs the gate phases, and then builds the image, so a
|
||||
successful run means every check passed; a bare `docker build .` does not
|
||||
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 is uncached and so runs the gate phases a second time. That is the
|
||||
price of the rule above, and it is worth paying: the image that ships is built
|
||||
from a run of its own gates rather than from a cache entry. 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.
|
||||
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.
|
||||
|
||||
- Use platform-standard formatters: `black` for Python, `prettier` for
|
||||
JS/CSS/Markdown/HTML, `go fmt` for Go. Always use default configuration with
|
||||
@@ -384,9 +408,12 @@ style conventions are in separate documents:
|
||||
|
||||
- `.gitignore` should be comprehensive from the start: OS files (`.DS_Store`),
|
||||
editor files (`.swp`, `*~`), in-repo agent scratch directories (`.claude/`),
|
||||
language build artifacts, and `node_modules/`. Fetch the standard `.gitignore`
|
||||
from `https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` when
|
||||
setting up a new repo. These patterns are written to `.gitignore`'s own
|
||||
`node_modules/`, and the repo's own build outputs. Fetch the standard
|
||||
`.gitignore` from
|
||||
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` when setting up
|
||||
a new repo. A repo's `.gitignore` is the standard file followed by the repo's
|
||||
own entries, such as its binaries; a re-vendor replaces the standard part and
|
||||
keeps those entries. These patterns are written to `.gitignore`'s own
|
||||
semantics, in which an unanchored pattern already matches at every depth; they
|
||||
are not a `.dockerignore` and must not be transplanted into one unmodified.
|
||||
|
||||
@@ -434,13 +461,15 @@ style conventions are in separate documents:
|
||||
byte-identically across repos:
|
||||
|
||||
```sh
|
||||
# Own line: a failing command substitution inside an argument does not
|
||||
# trip `set -e`, so the inline form degrades to an empty constant.
|
||||
# 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="$(script/projectname)"
|
||||
docker build --no-cache \
|
||||
--build-arg VERSION="$version" \
|
||||
-t "$(script/projectname)" .
|
||||
-t "$tag" .
|
||||
```
|
||||
|
||||
`--always` makes an untagged repo yield an abbreviated commit hash rather
|
||||
@@ -452,8 +481,8 @@ style conventions are in separate documents:
|
||||
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 a repo that embeds a
|
||||
tag-derived version must set `fetch-depth: 0` on its checkout step.
|
||||
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
|
||||
@@ -636,7 +665,11 @@ style conventions are in separate documents:
|
||||
Never edit existing migrations after release.
|
||||
|
||||
- All repos should have an `.editorconfig` enforcing the project's indentation
|
||||
settings.
|
||||
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.
|
||||
|
||||
- Avoid putting files in the repo root unless necessary. Root should contain
|
||||
only project-level config files (`README.md`, `AGENTS.md`, `Makefile`,
|
||||
|
||||
@@ -29,27 +29,43 @@
|
||||
|
||||
# Completed Steps
|
||||
|
||||
- re-vendor the canonical files from `sneak/prompts` commit `dd4027b`:
|
||||
golangci-lint v2.14.0; lint and test are phases of the `Dockerfile`, 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 `--no-cache`; `.claude/settings.json` is
|
||||
deleted (2026-10-07, https://git.eeqj.de/sneak/sfdupes/issues/95)
|
||||
- re-vendor the canonical files and model scripts from `sneak/prompts` `next` at
|
||||
`c55a0cb`: 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 `--no-cache`; 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
|
||||
(2026-10-08, https://git.eeqj.de/sneak/sfdupes/issues/95)
|
||||
|
||||
- `scan` records mtime to the nanosecond, as whole seconds in `mtime` plus
|
||||
`mtime_nsec`, and compares it at that resolution, so a same-size rewrite
|
||||
within the same second is re-hashed (2026-10-07,
|
||||
https://git.eeqj.de/sneak/sfdupes/issues/12)
|
||||
|
||||
- cut the narration from `TODO.md` Completed Steps and from the comments in
|
||||
`script/` and both Dockerfiles; §Workflow now branches from and merges to
|
||||
`next` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/49)
|
||||
`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)
|
||||
|
||||
- `make test-race` runs the test suite under the race detector in a cgo-enabled
|
||||
- `make test-race` ran 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)
|
||||
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
|
||||
|
||||
- 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)
|
||||
- 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 `--no-cache`, so theirs always run
|
||||
|
||||
- `make fmt` and `make fmt-check` run prettier over all Markdown, in Docker, and
|
||||
CI checks it; all Markdown reformatted (2026-10-04,
|
||||
- `make fmt` and `make fmt-check` run prettier over all Markdown, 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
|
||||
@@ -92,9 +108,12 @@
|
||||
- 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 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)
|
||||
- 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
|
||||
|
||||
- `--version` prints `sfdupes VERSION` to stdout; README documents it and
|
||||
`--help` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/15)
|
||||
@@ -158,82 +177,45 @@
|
||||
|
||||
- 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 are now the policy
|
||||
https://git.eeqj.de/sneak/sfdupes/issues/25): both pins became 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; 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.
|
||||
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.
|
||||
|
||||
- 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. `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: 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 (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`.
|
||||
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.
|
||||
|
||||
- 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):
|
||||
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. 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; 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
|
||||
`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
|
||||
- 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. Every
|
||||
`docker build` in `script/` now passes `--no-cache` instead
|
||||
(https://git.eeqj.de/sneak/sfdupes/issues/95). Run as root, the tests fail
|
||||
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 `--no-cache` instead. Run as root, the tests fail
|
||||
`TestScanHardlinkRunFailsTogether`, because root reads through the `chmod(0)`
|
||||
the test relies on, so they run as an unprivileged user
|
||||
the test relies on, so the `test` phase runs them as `nobody`
|
||||
- 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
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
"path/filepath"
|
||||
"slices"
|
||||
"strconv"
|
||||
"time"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
// The pure-Go SQLite driver, registered as "sqlite"; keeps cgo
|
||||
@@ -40,12 +41,15 @@ const dbDirPerm = 0o755
|
||||
const lockFilePerm = 0o600
|
||||
|
||||
// createTableSQL is the schema applied to a fresh database. Paths are
|
||||
// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8.
|
||||
// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8. mtime
|
||||
// holds whole Unix seconds and mtime_nsec the nanoseconds within that
|
||||
// second.
|
||||
const createTableSQL = `
|
||||
CREATE TABLE files (
|
||||
path BLOB PRIMARY KEY,
|
||||
size INTEGER NOT NULL,
|
||||
mtime INTEGER NOT NULL,
|
||||
mtime_nsec INTEGER NOT NULL,
|
||||
head TEXT NOT NULL,
|
||||
tail TEXT NOT NULL,
|
||||
content TEXT NOT NULL
|
||||
@@ -61,10 +65,11 @@ CREATE INDEX files_signature ON files (size, head, tail, content)
|
||||
// upsertSQL inserts one file record, replacing any existing record for
|
||||
// the same path.
|
||||
const upsertSQL = `
|
||||
INSERT INTO files (path, size, mtime, head, tail, content)
|
||||
VALUES (?, ?, ?, ?, ?, ?)
|
||||
INSERT INTO files (path, size, mtime, mtime_nsec, head, tail, content)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?)
|
||||
ON CONFLICT (path) DO UPDATE SET
|
||||
size = excluded.size, mtime = excluded.mtime,
|
||||
mtime_nsec = excluded.mtime_nsec,
|
||||
head = excluded.head, tail = excluded.tail,
|
||||
content = excluded.content
|
||||
`
|
||||
@@ -356,8 +361,8 @@ func userVersion(ctx context.Context, db *sql.DB) (int, error) {
|
||||
// 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, head, tail, content FROM files "+
|
||||
"ORDER BY path")
|
||||
"SELECT path, size, mtime, mtime_nsec, head, tail, content "+
|
||||
"FROM files ORDER BY path")
|
||||
if err != nil {
|
||||
return fmt.Errorf("read records: %w", err)
|
||||
}
|
||||
@@ -367,16 +372,18 @@ func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
|
||||
for rows.Next() {
|
||||
var (
|
||||
path []byte
|
||||
sec, nsec int64
|
||||
r scanRec
|
||||
)
|
||||
|
||||
err = rows.Scan(&path, &r.size, &r.mtime, &r.head, &r.tail,
|
||||
err = rows.Scan(&path, &r.size, &sec, &nsec, &r.head, &r.tail,
|
||||
&r.content)
|
||||
if err != nil {
|
||||
return fmt.Errorf("read record: %w", err)
|
||||
}
|
||||
|
||||
r.path = string(path)
|
||||
r.mtime = time.Unix(sec, nsec)
|
||||
fn(r)
|
||||
}
|
||||
|
||||
@@ -466,10 +473,10 @@ func loadDupeRows(ctx context.Context, db *sql.DB,
|
||||
// values, and skipping the hash columns keeps the scan's in-memory
|
||||
// index small on multi-million-file databases.
|
||||
func loadFileMeta(ctx context.Context, db *sql.DB,
|
||||
fn func(path string, size, mtime int64, hashed bool),
|
||||
fn func(path string, size int64, mtime time.Time, hashed bool),
|
||||
) error {
|
||||
rows, err := db.QueryContext(ctx,
|
||||
"SELECT path, size, mtime, head <> '' FROM files")
|
||||
"SELECT path, size, mtime, mtime_nsec, head <> '' FROM files")
|
||||
if err != nil {
|
||||
return fmt.Errorf("read records: %w", err)
|
||||
}
|
||||
@@ -479,16 +486,16 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
|
||||
for rows.Next() {
|
||||
var (
|
||||
path []byte
|
||||
size, mtime int64
|
||||
size, sec, nsec int64
|
||||
hashed int64
|
||||
)
|
||||
|
||||
err = rows.Scan(&path, &size, &mtime, &hashed)
|
||||
err = rows.Scan(&path, &size, &sec, &nsec, &hashed)
|
||||
if err != nil {
|
||||
return fmt.Errorf("read record: %w", err)
|
||||
}
|
||||
|
||||
fn(string(path), size, mtime, hashed != 0)
|
||||
fn(string(path), size, time.Unix(sec, nsec), hashed != 0)
|
||||
}
|
||||
|
||||
err = rows.Err()
|
||||
@@ -507,7 +514,7 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
|
||||
// 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.head, f.tail, f.content <> ''
|
||||
SELECT f.path, f.size, f.mtime, f.mtime_nsec, f.head, f.tail, f.content <> ''
|
||||
FROM files AS f
|
||||
JOIN (
|
||||
SELECT size, head, tail
|
||||
@@ -534,16 +541,19 @@ func loadContentCandidates(ctx context.Context, db *sql.DB,
|
||||
for rows.Next() {
|
||||
var (
|
||||
path []byte
|
||||
sec, nsec int64
|
||||
r scanRec
|
||||
hashed int64
|
||||
)
|
||||
|
||||
err = rows.Scan(&path, &r.size, &r.mtime, &r.head, &r.tail, &hashed)
|
||||
err = rows.Scan(&path, &r.size, &sec, &nsec, &r.head, &r.tail,
|
||||
&hashed)
|
||||
if err != nil {
|
||||
return fmt.Errorf("read record: %w", err)
|
||||
}
|
||||
|
||||
r.path = string(path)
|
||||
r.mtime = time.Unix(sec, nsec)
|
||||
fn(r, hashed != 0)
|
||||
}
|
||||
|
||||
@@ -627,8 +637,8 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
|
||||
defer func() { _ = st.Close() }()
|
||||
|
||||
for _, r := range upserts {
|
||||
_, err = st.ExecContext(ctx,
|
||||
[]byte(r.path), r.size, r.mtime, r.head, r.tail, r.content)
|
||||
_, err = st.ExecContext(ctx, []byte(r.path), r.size,
|
||||
r.mtime.Unix(), r.mtime.Nanosecond(), r.head, r.tail, r.content)
|
||||
if err != nil {
|
||||
return fmt.Errorf("upsert %s: %w", r.path, err)
|
||||
}
|
||||
|
||||
+10
-5
@@ -10,6 +10,7 @@ import (
|
||||
"slices"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// testDBPath returns a database path inside a fresh temp dir.
|
||||
@@ -260,10 +261,13 @@ func TestApplyChangesRoundTrip(t *testing.T) {
|
||||
// written.
|
||||
recs := []scanRec{
|
||||
{
|
||||
size: 2, mtime: 20, head: "h2", tail: "t2", content: "c2",
|
||||
path: "/a/tab\tnew\nline",
|
||||
size: 2, mtime: time.Unix(20, 999_999_999), head: "h2", tail: "t2",
|
||||
content: "c2", path: "/a/tab\tnew\nline",
|
||||
},
|
||||
{
|
||||
size: 1, mtime: time.Unix(10, 0), head: "h1", tail: "t1",
|
||||
content: "c1", path: "/a/x",
|
||||
},
|
||||
{size: 1, mtime: 10, head: "h1", tail: "t1", content: "c1", path: "/a/x"},
|
||||
}
|
||||
|
||||
err := applyChanges(t.Context(), db, recs, nil,
|
||||
@@ -281,7 +285,8 @@ func TestApplyChangesRoundTrip(t *testing.T) {
|
||||
// An upsert for an existing path updates in place; a delete
|
||||
// removes exactly its path.
|
||||
upd := scanRec{
|
||||
size: 3, mtime: 30, head: "h3", tail: "t3", content: "c3", path: "/a/x",
|
||||
size: 3, mtime: time.Unix(30, 0), head: "h3", tail: "t3", content: "c3",
|
||||
path: "/a/x",
|
||||
}
|
||||
|
||||
err = applyChanges(t.Context(), db, []scanRec{upd},
|
||||
@@ -308,7 +313,7 @@ func TestApplyChangesBatching(t *testing.T) {
|
||||
recs := make([]scanRec, 0, n)
|
||||
for i := range n {
|
||||
recs = append(recs, scanRec{
|
||||
size: int64(i), mtime: 1, head: "h", tail: "t",
|
||||
size: int64(i), mtime: time.Unix(1, 0), head: "h", tail: "t",
|
||||
path: fmt.Sprintf("/batch/%07d", i),
|
||||
})
|
||||
}
|
||||
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"io"
|
||||
"os"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
// ioBufSize is the buffer size for the buffered stdout writers.
|
||||
@@ -21,7 +22,7 @@ const minGroupSize = 2
|
||||
// only and used by scan for change detection.
|
||||
type scanRec struct {
|
||||
size int64
|
||||
mtime int64
|
||||
mtime time.Time
|
||||
head string
|
||||
tail string
|
||||
content string
|
||||
|
||||
+9
-2
@@ -11,6 +11,7 @@ import (
|
||||
"slices"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// awkwardDir is a directory name holding every byte the reports escape.
|
||||
@@ -313,8 +314,14 @@ func TestDupeGroupsMtimeExcluded(t *testing.T) {
|
||||
// mtime is informational only; records differing only in mtime
|
||||
// still group together.
|
||||
recs := []scanRec{
|
||||
{size: 9, mtime: 100, head: "h", tail: "t", content: "c", path: "/m/1"},
|
||||
{size: 9, mtime: 200, head: "h", tail: "t", content: "c", path: "/m/2"},
|
||||
{
|
||||
size: 9, mtime: time.Unix(100, 0), head: "h", tail: "t",
|
||||
content: "c", path: "/m/1",
|
||||
},
|
||||
{
|
||||
size: 9, mtime: time.Unix(200, 0), head: "h", tail: "t",
|
||||
content: "c", path: "/m/2",
|
||||
},
|
||||
}
|
||||
|
||||
groups := dupeGroupsOf(t, recs)
|
||||
|
||||
@@ -17,6 +17,7 @@ import (
|
||||
"strings"
|
||||
"sync"
|
||||
"syscall"
|
||||
"time"
|
||||
)
|
||||
|
||||
// The duplicate ladder (see hashSignature and README "Duplicate
|
||||
@@ -68,7 +69,7 @@ var errInterrupted = errors.New("scan interrupted")
|
||||
type fileRec struct {
|
||||
path string
|
||||
size int64
|
||||
mtime int64
|
||||
mtime time.Time
|
||||
dev uint64
|
||||
ino uint64
|
||||
}
|
||||
@@ -79,7 +80,7 @@ type fileRec struct {
|
||||
// they would dominate the scan's memory.
|
||||
type fileMeta struct {
|
||||
size int64
|
||||
mtime int64
|
||||
mtime time.Time
|
||||
hashed bool
|
||||
}
|
||||
|
||||
@@ -369,7 +370,7 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
|
||||
s.existing = make(map[string]fileMeta)
|
||||
|
||||
return loadFileMeta(ctx, s.db,
|
||||
func(path string, size, mtime int64, hashed bool) {
|
||||
func(path string, size int64, mtime time.Time, hashed bool) {
|
||||
prog.increment()
|
||||
|
||||
if underAnyRoot(path, roots) {
|
||||
@@ -415,7 +416,7 @@ func (s *scanState) walkPhase(
|
||||
old, ok := s.existing[ev.rec.path]
|
||||
|
||||
switch {
|
||||
case !ok || old.size != ev.rec.size || old.mtime < ev.rec.mtime:
|
||||
case !ok || old.size != ev.rec.size || mtimeAfter(ev.rec.mtime, old.mtime):
|
||||
changed = append(changed, ev.rec)
|
||||
case old.hashed:
|
||||
delete(s.existing, ev.rec.path)
|
||||
@@ -807,7 +808,7 @@ func unchangedFile(r scanRec) (fileRec, bool, error) {
|
||||
}
|
||||
|
||||
if !fi.Mode().IsRegular() || fi.Size() != r.size ||
|
||||
fi.ModTime().Unix() > r.mtime {
|
||||
mtimeAfter(fi.ModTime(), r.mtime) {
|
||||
return fileRec{}, false, nil
|
||||
}
|
||||
|
||||
@@ -818,6 +819,16 @@ func unchangedFile(r scanRec) (fileRec, bool, error) {
|
||||
}, true, nil
|
||||
}
|
||||
|
||||
// mtimeAfter reports whether mtime a is later than mtime b.
|
||||
// Not a.After(b): time.Time wraps an mtime past year 292 billion; Unix() undoes it.
|
||||
func mtimeAfter(a, b time.Time) bool {
|
||||
if a.Unix() != b.Unix() {
|
||||
return a.Unix() > b.Unix()
|
||||
}
|
||||
|
||||
return a.Nanosecond() > b.Nanosecond()
|
||||
}
|
||||
|
||||
// underAnyRoot reports whether path is any of the roots or lies under
|
||||
// one of them.
|
||||
func underAnyRoot(path string, roots []string) bool {
|
||||
@@ -966,7 +977,7 @@ func seedRoot(ctx context.Context, root string,
|
||||
sendEvent(ctx, events, walkEvent{rec: fileRec{
|
||||
path: root,
|
||||
size: fi.Size(),
|
||||
mtime: fi.ModTime().Unix(),
|
||||
mtime: fi.ModTime(),
|
||||
dev: dev,
|
||||
ino: ino,
|
||||
}})
|
||||
@@ -1124,7 +1135,7 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
|
||||
sendEvent(ctx, events, walkEvent{rec: fileRec{
|
||||
path: p,
|
||||
size: info.Size(),
|
||||
mtime: info.ModTime().Unix(),
|
||||
mtime: info.ModTime(),
|
||||
dev: dev,
|
||||
ino: ino,
|
||||
}})
|
||||
|
||||
+227
-7
@@ -20,6 +20,8 @@ import (
|
||||
"syscall"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
// writeFile creates a file with the given content and returns its path.
|
||||
@@ -581,6 +583,65 @@ func TestScanContentHashedStalePartners(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestScanContentSameSecondRewrite is TestScanContentStalePartners for
|
||||
// a stored file rewritten in place at the same size with an mtime later
|
||||
// in the same second than recorded: the file counts as changed, so
|
||||
// neither it nor its match inside the operand is read.
|
||||
func TestScanContentSameSecondRewrite(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
db := openTestDB(t)
|
||||
dirA := t.TempDir()
|
||||
changed := sparseFileWithoutMatch(t, dirA, "changed", headTailMin)
|
||||
|
||||
first := time.Date(2026, 1, 2, 3, 4, 5, 100_000_000, time.UTC)
|
||||
|
||||
err := os.Chtimes(changed, first, first)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
syncTree(t, db, dirA)
|
||||
|
||||
before := dbRecords(t, db)
|
||||
|
||||
// Rewrite one byte in place, keeping the size.
|
||||
pokeAt(t, changed, headTailMin/2, []byte{1})
|
||||
|
||||
later := first.Add(500 * time.Millisecond)
|
||||
|
||||
err = os.Chtimes(changed, later, later)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
dirB := t.TempDir()
|
||||
sparseFile(t, dirB, "changed-copy", headTailMin)
|
||||
|
||||
st := syncTree(t, db, dirB)
|
||||
if st != (scanStats{walked: 1, added: 1}) {
|
||||
t.Errorf("stats = %+v, want 1 added and nothing skipped", st)
|
||||
}
|
||||
|
||||
recs := dbRecords(t, db)
|
||||
for _, r := range recs {
|
||||
if r.content != "" {
|
||||
t.Errorf("%s: content = %q, want none: its only match is stale",
|
||||
r.path, r.content)
|
||||
}
|
||||
}
|
||||
|
||||
for _, old := range before {
|
||||
if r := recordByPath(t, recs, old.path); r != old {
|
||||
t.Errorf("record = %+v, want it left as %+v", r, old)
|
||||
}
|
||||
}
|
||||
|
||||
if groups := dupeGroups(t, db); len(groups) != 0 {
|
||||
t.Errorf("groups = %+v, want none", groups)
|
||||
}
|
||||
}
|
||||
|
||||
// TestScanContentReadFailure checks that a failed content read is
|
||||
// counted as skipped and leaves the record without a content hash, and
|
||||
// that a later scan tries the read again.
|
||||
@@ -783,8 +844,8 @@ func TestWalk(t *testing.T) {
|
||||
t.Errorf("%s: size = %d, want 1..3", r.path, r.size)
|
||||
}
|
||||
|
||||
if r.mtime <= 0 {
|
||||
t.Errorf("%s: mtime = %d, want positive", r.path, r.mtime)
|
||||
if r.mtime.Unix() <= 0 {
|
||||
t.Errorf("%s: mtime = %v, want after 1970", r.path, r.mtime)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1285,11 +1346,172 @@ func TestSyncScanMtimeBump(t *testing.T) {
|
||||
t.Fatalf("mtime-bump stats = %+v, want 1 updated", st)
|
||||
}
|
||||
|
||||
if r := recordByPath(t, dbRecords(t, db), a); r.mtime != future.Unix() {
|
||||
t.Fatalf("mtime = %d, want %d", r.mtime, future.Unix())
|
||||
if r := recordByPath(t, dbRecords(t, db), a); !r.mtime.Equal(future) {
|
||||
t.Fatalf("mtime = %v, want %v", r.mtime, future)
|
||||
}
|
||||
}
|
||||
|
||||
// assertWholeFileHashed fails unless the record for path holds the
|
||||
// whole-file hash of data as its head, tail, and content.
|
||||
func assertWholeFileHashed(t *testing.T, db *sql.DB, path string,
|
||||
data []byte,
|
||||
) {
|
||||
t.Helper()
|
||||
|
||||
r := recordByPath(t, dbRecords(t, db), path)
|
||||
if want := hexSum(data); r.head != want || r.tail != want ||
|
||||
r.content != want {
|
||||
t.Fatalf("head, tail, content = %q, %q, %q, want %q for each",
|
||||
r.head, r.tail, r.content, want)
|
||||
}
|
||||
}
|
||||
|
||||
// TestSyncScanSameSecondRewrite rewrites a file in place at the same
|
||||
// size with an mtime later in the same second as the recorded one: the
|
||||
// next scan must notice the change and re-hash the file.
|
||||
func TestSyncScanSameSecondRewrite(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
dir := t.TempDir()
|
||||
db := openTestDB(t)
|
||||
a := writeFile(t, dir, "a.bin", pattern(1, 500))
|
||||
|
||||
// b.bin shares the size of a.bin, so a.bin is hashed.
|
||||
writeFile(t, dir, "b.bin", pattern(2, 500))
|
||||
|
||||
first := time.Date(2026, 1, 2, 3, 4, 5, 100_000_000, time.UTC)
|
||||
|
||||
err := os.Chtimes(a, first, first)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
syncTree(t, db, dir)
|
||||
|
||||
rewritten := pattern(3, 500)
|
||||
writeFile(t, dir, "a.bin", rewritten)
|
||||
|
||||
later := first.Add(500 * time.Millisecond)
|
||||
|
||||
err = os.Chtimes(a, later, later)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
st := syncTree(t, db, dir)
|
||||
if st != (scanStats{walked: 2, updated: 1, unchanged: 1}) {
|
||||
t.Fatalf("rescan stats = %+v, want 1 updated 1 unchanged", st)
|
||||
}
|
||||
|
||||
assertWholeFileHashed(t, db, a, rewritten)
|
||||
}
|
||||
|
||||
// TestSyncScanOperandSameSecondRewrite is TestSyncScanSameSecondRewrite
|
||||
// for files given to scan as operands, which scan stats without reading
|
||||
// their directory.
|
||||
func TestSyncScanOperandSameSecondRewrite(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
dir := t.TempDir()
|
||||
db := openTestDB(t)
|
||||
a := writeFile(t, dir, "a.bin", pattern(1, 500))
|
||||
|
||||
// b.bin shares the size of a.bin, so a.bin is hashed.
|
||||
b := writeFile(t, dir, "b.bin", pattern(2, 500))
|
||||
|
||||
first := time.Date(2026, 1, 2, 3, 4, 5, 100_000_000, time.UTC)
|
||||
|
||||
err := os.Chtimes(a, first, first)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
syncTree(t, db, a, b)
|
||||
|
||||
rewritten := pattern(3, 500)
|
||||
writeFile(t, dir, "a.bin", rewritten)
|
||||
|
||||
later := first.Add(500 * time.Millisecond)
|
||||
|
||||
err = os.Chtimes(a, later, later)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
st := syncTree(t, db, a, b)
|
||||
if st != (scanStats{walked: 2, updated: 1, unchanged: 1}) {
|
||||
t.Fatalf("rescan stats = %+v, want 1 updated 1 unchanged", st)
|
||||
}
|
||||
|
||||
assertWholeFileHashed(t, db, a, rewritten)
|
||||
}
|
||||
|
||||
// TestSyncScanRewriteAfter2262 runs assertLateRewriteRehashed with an
|
||||
// mtime after 2262, a time too late to count in nanoseconds in an int64.
|
||||
func TestSyncScanRewriteAfter2262(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
assertLateRewriteRehashed(t, time.Date(2300, 1, 2, 3, 4, 5, 0, time.UTC))
|
||||
}
|
||||
|
||||
// TestSyncScanRewritePastTimeLimit runs assertLateRewriteRehashed with an
|
||||
// mtime one second past the latest a time.Time holds without wrapping it
|
||||
// to a time far in the past.
|
||||
func TestSyncScanRewritePastTimeLimit(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
assertLateRewriteRehashed(t, time.Unix(9223371974719179008, 0))
|
||||
}
|
||||
|
||||
// assertLateRewriteRehashed scans a directory, rewrites a file in it in
|
||||
// place at the same size, sets its mtime to late, and fails unless the
|
||||
// next scan re-hashes the file. It skips where late does not fit the
|
||||
// platform's timespec or the filesystem does not store it.
|
||||
func assertLateRewriteRehashed(t *testing.T, late time.Time) {
|
||||
t.Helper()
|
||||
|
||||
dir := t.TempDir()
|
||||
db := openTestDB(t)
|
||||
a := writeFile(t, dir, "a.bin", pattern(1, 500))
|
||||
|
||||
// b.bin shares the size of a.bin, so a.bin is hashed.
|
||||
writeFile(t, dir, "b.bin", pattern(2, 500))
|
||||
|
||||
syncTree(t, db, dir)
|
||||
|
||||
rewritten := pattern(3, 500)
|
||||
writeFile(t, dir, "a.bin", rewritten)
|
||||
|
||||
// os.Chtimes cannot set such a time: it converts through UnixNano.
|
||||
ts, err := unix.TimeToTimespec(late)
|
||||
if err != nil {
|
||||
t.Skipf("an mtime %d seconds after 1970 does not fit this platform's "+
|
||||
"timespec: %v", late.Unix(), err)
|
||||
}
|
||||
|
||||
err = unix.UtimesNano(a, []unix.Timespec{ts, ts})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
fi, err := os.Lstat(a)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
if fi.ModTime().Unix() != late.Unix() {
|
||||
t.Skipf("the filesystem stored the mtime as %d seconds after 1970, "+
|
||||
"not %d", fi.ModTime().Unix(), late.Unix())
|
||||
}
|
||||
|
||||
st := syncTree(t, db, dir)
|
||||
if st != (scanStats{walked: 2, updated: 1, unchanged: 1}) {
|
||||
t.Fatalf("rescan stats = %+v, want 1 updated 1 unchanged", st)
|
||||
}
|
||||
|
||||
assertWholeFileHashed(t, db, a, rewritten)
|
||||
}
|
||||
|
||||
func TestSyncScanAddRemove(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
@@ -1335,9 +1557,7 @@ func TestSyncScanSizeChange(t *testing.T) {
|
||||
|
||||
writeFile(t, dir, "f", pattern(1, 200))
|
||||
|
||||
mt := time.Unix(old.mtime, 0)
|
||||
|
||||
err := os.Chtimes(p, mt, mt)
|
||||
err := os.Chtimes(p, old.mtime, old.mtime)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
+84
-16
@@ -1,13 +1,22 @@
|
||||
#!/bin/sh
|
||||
# script/bootstrap: install all dependencies needed to build and develop
|
||||
# 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).
|
||||
# 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. Node is
|
||||
# used directly if installed; otherwise it is installed at a pinned
|
||||
# version via nvm (installing nvm itself first, from a hash-verified
|
||||
# release archive, never curl | sh).
|
||||
set -eu
|
||||
|
||||
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
|
||||
|
||||
# Pinned versions, 2026-07-06
|
||||
NODE_VERSION="22.17.0"
|
||||
NVM_VERSION="0.40.3"
|
||||
# sha256 of https://github.com/nvm-sh/nvm/archive/refs/tags/v0.40.3.tar.gz
|
||||
NVM_SHA256="5f4d6aaa04a177dc93c985e31dbc411ab6b8c6e1e21d8015dbc1372625fcd1d0"
|
||||
YARN_VERSION="1.22.22"
|
||||
|
||||
PKGMGR=""
|
||||
SUDO=""
|
||||
APT_UPDATED=""
|
||||
@@ -40,6 +49,7 @@ pkg_install() {
|
||||
case "$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
|
||||
@@ -55,24 +65,82 @@ 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"
|
||||
}
|
||||
|
||||
ensure_node() {
|
||||
if ! missing node; then return 0; fi
|
||||
ensure_nvm
|
||||
nvm_sh "nvm install $NODE_VERSION"
|
||||
}
|
||||
|
||||
ensure_yarn() {
|
||||
if ! missing yarn; then return 0; fi
|
||||
if ! missing corepack; then
|
||||
corepack enable
|
||||
corepack prepare "yarn@$YARN_VERSION" --activate
|
||||
elif [ -s "$HOME/.nvm/nvm.sh" ]; then
|
||||
nvm_sh "nvm use $NODE_VERSION >/dev/null && corepack enable && \
|
||||
corepack prepare yarn@$YARN_VERSION --activate"
|
||||
else
|
||||
npm install -g "yarn@$YARN_VERSION"
|
||||
fi
|
||||
}
|
||||
|
||||
install_js_deps() {
|
||||
if missing yarn && [ -s "$HOME/.nvm/nvm.sh" ]; then
|
||||
nvm_sh "nvm use $NODE_VERSION >/dev/null && cd \"$ROOT\" && \
|
||||
yarn install --frozen-lockfile"
|
||||
else
|
||||
yarn install --frozen-lockfile
|
||||
fi
|
||||
}
|
||||
|
||||
main() {
|
||||
cd "$ROOT"
|
||||
|
||||
# Deliberately unpinned, so presence is the whole check: go.mod
|
||||
# governs the Go version, and reproducible builds run in the
|
||||
# digest-pinned Docker images.
|
||||
if missing git; then pkg_install git git git git; fi
|
||||
if missing make; then pkg_install gnumake make make make; fi
|
||||
if missing git; then pkg_install git git git git; fi
|
||||
# Go builds the binary and runs gofmt. Presence is the whole check:
|
||||
# go.mod names the Go version, and the tests and the linter run in
|
||||
# digest-pinned images.
|
||||
if missing go; then pkg_install go golang go go; fi
|
||||
|
||||
# Warn, do not fail: only the targets named below, and the
|
||||
# pre-commit hook, need docker.
|
||||
if missing docker; then
|
||||
echo "bootstrap: WARNING: docker not found; make test, make lint," >&2
|
||||
echo "bootstrap: make fmt, make fmt-check, make check and" >&2
|
||||
echo "bootstrap: make docker require it." >&2
|
||||
fi
|
||||
|
||||
ensure_node
|
||||
ensure_yarn
|
||||
install_js_deps
|
||||
go mod download
|
||||
|
||||
echo "bootstrap complete"
|
||||
|
||||
+3
-1
@@ -1,6 +1,8 @@
|
||||
#!/bin/sh
|
||||
# script/check: run all checks (test, lint, fmt-check). Our own
|
||||
# extension to scripts-to-rule-them-all. Must not modify any files.
|
||||
# extension to scripts-to-rule-them-all. test and lint are Docker
|
||||
# phases; fmt-check is native, because a formatter writes the working
|
||||
# tree. Must not modify any files.
|
||||
set -eu
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
|
||||
|
||||
+7
-5
@@ -14,15 +14,17 @@ main() {
|
||||
cd "$ROOT"
|
||||
"$SCRIPT_DIR/bootstrap"
|
||||
"$SCRIPT_DIR/check"
|
||||
# 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.
|
||||
# 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 --no-cache \
|
||||
--build-arg VERSION="$version" \
|
||||
-t "$("$SCRIPT_DIR/projectname")" .
|
||||
-t "$tag" .
|
||||
}
|
||||
|
||||
main "$@"
|
||||
|
||||
+7
-5
@@ -10,15 +10,17 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
|
||||
|
||||
main() {
|
||||
cd "$ROOT"
|
||||
# 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.
|
||||
# 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 --no-cache \
|
||||
--build-arg VERSION="$version" \
|
||||
-t "$("$SCRIPT_DIR/projectname")" .
|
||||
-t "$tag" .
|
||||
}
|
||||
|
||||
main "$@"
|
||||
|
||||
+22
-13
@@ -1,23 +1,32 @@
|
||||
#!/bin/sh
|
||||
# script/fmt: format all files (writes): the Go sources with gofmt, the
|
||||
# Markdown with prettier. prettier is never installed on the host: it
|
||||
# runs from the Dockerfile's prettier stage with the repository mounted,
|
||||
# as the calling user so the files it rewrites keep their owner. The
|
||||
# build passes --no-cache, as every docker build in script/ does. The tag
|
||||
# makes each build replace the previous image instead of leaving another
|
||||
# one behind.
|
||||
# script/fmt: format all files (writes).
|
||||
set -eu
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
|
||||
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
|
||||
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
|
||||
|
||||
# Must match the pin in script/bootstrap.
|
||||
NODE_VERSION="22.17.0"
|
||||
|
||||
# script/bootstrap installs node and yarn under nvm and leaves neither
|
||||
# on the PATH of the shell that called it, so resolve the pinned
|
||||
# toolchain here the way bootstrap's own install step does. nvm is a
|
||||
# bash script, hence the subshell.
|
||||
run_yarn() {
|
||||
if command -v yarn >/dev/null 2>&1; then
|
||||
exec yarn "$@"
|
||||
fi
|
||||
if [ ! -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 "$NODE_VERSION" "$@"
|
||||
}
|
||||
|
||||
main() {
|
||||
cd "$ROOT"
|
||||
gofmt -s -w .
|
||||
image="$("$SCRIPT_DIR/projectname")-prettier"
|
||||
docker build -q --no-cache --target prettier -t "$image" . >/dev/null
|
||||
docker run --rm --user "$(id -u):$(id -g)" -v "$ROOT:/src" "$image" \
|
||||
prettier --write '**/*.md' --tab-width 4 --prose-wrap always
|
||||
run_yarn run prettier --write '**/*.md' --tab-width 4 --prose-wrap always
|
||||
}
|
||||
|
||||
main "$@"
|
||||
|
||||
+26
-15
@@ -1,19 +1,35 @@
|
||||
#!/bin/sh
|
||||
# script/fmt-check: check formatting (read-only). Same scope as
|
||||
# script/fmt, but fails instead of writing. gofmt and prettier both run
|
||||
# every time and each reports its own failure, so the output says which
|
||||
# one failed.
|
||||
# script/fmt-check: check formatting (read-only).
|
||||
set -eu
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
|
||||
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
|
||||
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
|
||||
|
||||
# Must match the pin in script/bootstrap.
|
||||
NODE_VERSION="22.17.0"
|
||||
|
||||
# script/bootstrap installs node and yarn under nvm and leaves neither
|
||||
# on the PATH of the shell that called it, so resolve the pinned
|
||||
# toolchain here the way bootstrap's own install step does. nvm is a
|
||||
# bash script, hence the subshell.
|
||||
run_yarn() {
|
||||
if command -v yarn >/dev/null 2>&1; then
|
||||
exec yarn "$@"
|
||||
fi
|
||||
if [ ! -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 "$NODE_VERSION" "$@"
|
||||
}
|
||||
|
||||
main() {
|
||||
cd "$ROOT"
|
||||
status=0
|
||||
|
||||
# Under set -e a bare assignment would end the script when gofmt
|
||||
# fails (a Go file it cannot parse), and prettier would never run.
|
||||
# gofmt and prettier both run every time, so the output names each
|
||||
# one that fails. Under set -e a bare assignment would end the
|
||||
# script when gofmt fails (a Go file it cannot parse).
|
||||
if ! files="$(gofmt -s -l .)"; then
|
||||
echo "gofmt: failed; see its errors above" >&2
|
||||
status=1
|
||||
@@ -24,14 +40,9 @@ main() {
|
||||
status=1
|
||||
fi
|
||||
|
||||
# Same image as script/fmt; see there.
|
||||
image="$("$SCRIPT_DIR/projectname")-prettier"
|
||||
docker build -q --no-cache --target prettier -t "$image" . >/dev/null
|
||||
if ! docker run --rm -v "$ROOT:/src:ro" "$image" \
|
||||
prettier --check '**/*.md' --tab-width 4 --prose-wrap always; then
|
||||
echo "prettier: Markdown not formatted; run make fmt" >&2
|
||||
# run_yarn ends in exec; the subshell returns here afterwards.
|
||||
(run_yarn run prettier --check '**/*.md' --tab-width 4 --prose-wrap always) ||
|
||||
status=1
|
||||
fi
|
||||
|
||||
exit "$status"
|
||||
}
|
||||
|
||||
@@ -1,19 +1,15 @@
|
||||
#!/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"
|
||||
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 "$hook"
|
||||
hook=".git/hooks/pre-commit"
|
||||
printf '#!/bin/sh\nset -e\nscript/precommit\n' > .git/hooks/pre-commit
|
||||
chmod +x .git/hooks/pre-commit
|
||||
echo "pre-commit hook installed: runs script/precommit"
|
||||
}
|
||||
|
||||
|
||||
+3
-3
@@ -6,8 +6,8 @@
|
||||
#
|
||||
# The phase is not the last stage in the file, so it is built only when
|
||||
# --target names it. --no-cache because a cached lint layer is a lint
|
||||
# that did not run. The tag makes each build replace the previous image
|
||||
# instead of leaving a dangling one behind.
|
||||
# that did not run. --output type=cacheonly writes no image, since
|
||||
# nothing uses one.
|
||||
set -eu
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
|
||||
@@ -17,7 +17,7 @@ main() {
|
||||
cd "$ROOT"
|
||||
docker build --no-cache \
|
||||
--target lint \
|
||||
-t "$("$SCRIPT_DIR/projectname")-lint" .
|
||||
--output type=cacheonly .
|
||||
}
|
||||
|
||||
main "$@"
|
||||
|
||||
+2
-2
@@ -1,13 +1,13 @@
|
||||
#!/bin/sh
|
||||
# script/precommit: run by the git pre-commit hook; fails the commit if
|
||||
# checks fail. Our own extension to scripts-to-rule-them-all. Go extra:
|
||||
# go mod tidy must be a no-op before the checks run.
|
||||
# checks fail. Our own extension to scripts-to-rule-them-all.
|
||||
set -eu
|
||||
|
||||
SCRIPT_DIR="$(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
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
#!/bin/sh
|
||||
# script/setup: set up the repo for development after a fresh clone:
|
||||
# installs dependencies (script/bootstrap) and the git pre-commit hook.
|
||||
# installs dependencies and the git pre-commit hook.
|
||||
set -eu
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
|
||||
|
||||
+3
-3
@@ -2,8 +2,8 @@
|
||||
# script/test: run the test suite. Testing is a phase of the Dockerfile
|
||||
# and this builds that phase alone, on the same terms as script/lint:
|
||||
# --target because a phase that is not the last stage is built only when
|
||||
# named, --no-cache because a cached test layer is a test that did not
|
||||
# run, and a tag so each build replaces the previous image.
|
||||
# named, and --no-cache because a cached test layer is a test that did
|
||||
# not run. --output type=cacheonly writes no image, since nothing uses one.
|
||||
set -eu
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
|
||||
@@ -13,7 +13,7 @@ main() {
|
||||
cd "$ROOT"
|
||||
docker build --no-cache \
|
||||
--target test \
|
||||
-t "$("$SCRIPT_DIR/projectname")-test" .
|
||||
--output type=cacheonly .
|
||||
}
|
||||
|
||||
main "$@"
|
||||
|
||||
Reference in New Issue
Block a user