Author SHA1 Message Date
clawbot b2f599f35f Re-vendor the canonical files from sneak/prompts at dd4027b (closes #95)
check / check (push) Waiting to run
The shared files are the copies at sneak/prompts commit dd4027b, with this
repository's own entries kept after them. script/lint, script/test and
REPO_POLICIES.md come from its next at c55a0cb, so the lint and test
builds write no image. golangci-lint is v2.14.0 and raises no findings.
Lint and test are phases of the Dockerfile; the tests run under the race
detector as nobody, so Dockerfile.lint, script/verify-lint-image-pin and
make test-race are gone. Every docker build in script/ passes --no-cache.
Formatting runs on the host: script/bootstrap installs the pinned node and
yarn, and the prettier and markdown stages are gone. .claude/settings.json
is deleted.

Deviation: the workflow keeps fetch-depth: 0.
Deviation: .gitignore keeps the scan database patterns.
Over the cap: make test takes 82 to 100 seconds on this host.

Model: opus-5-5
2026-10-08 00:32:31 +00:00
18 changed files with 175 additions and 430 deletions
-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.
-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
+3 -5
View File
@@ -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 at the end of this file, for example `!.env.example`.
# its own negation after these lines, for example `!.env.example`.
*.[eE][nN][vV]
.[eE][nN][vV].*
.[eE][nN][vV][rR][cC]
@@ -46,13 +46,11 @@ node_modules/
[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/`.
/sfdupes
# This repository's own entries, kept after the canonical content above.
*.log
*.out
*.test
/sfdupes
# A scan database lists every path it scanned.
*.sqlite
-2
View File
@@ -25,8 +25,6 @@ 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
+26 -34
View File
@@ -312,34 +312,29 @@ All three subcommands operate on a single SQLite database file:
```sql
CREATE TABLE files (
path BLOB PRIMARY KEY, -- absolute path, raw bytes
size INTEGER NOT NULL, -- bytes, 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
path BLOB PRIMARY KEY, -- absolute path, raw bytes
size INTEGER NOT NULL, -- bytes, from lstat
mtime INTEGER NOT NULL, -- Unix seconds, from lstat
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
) WITHOUT ROWID;
CREATE INDEX files_signature ON files (size, head, tail, content);
```
Paths are stored as BLOBs because Unix paths are raw bytes, not guaranteed
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.
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.
### Duplicate detection
@@ -426,9 +421,6 @@ 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
@@ -748,12 +740,11 @@ entrypoints are:
come from the first of nix, apt, brew, or apk found on the host, and are
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`.
sha256 the script checks. yarn 1.22.22 comes through corepack, and
`yarn install --frozen-lockfile` 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
@@ -795,8 +786,9 @@ 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, 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.
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
+75 -50
View File
@@ -29,33 +29,24 @@
# Completed Steps
- re-vendor the canonical files and model scripts from `sneak/prompts` `next` at
- re-vendor the canonical files from `sneak/prompts` commit `dd4027b`, with
`script/lint`, `script/test` and `REPO_POLICIES.md` from its `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)
and `make` itself; `.claude/settings.json` is deleted (2026-10-08,
https://git.eeqj.de/sneak/sfdupes/issues/95)
- 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,
@@ -108,12 +99,9 @@
- 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)
@@ -177,45 +165,82 @@
- 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: 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`.
- 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. 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
- 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 `--no-cache` instead. Run as root, the tests fail
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
`TestScanHardlinkRunFailsTogether`, because root reads through the `chmod(0)`
the test relies on, so the `test` phase runs them as `nobody`
the test relies on, so they run as an unprivileged user
- 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
+28 -38
View File
@@ -11,7 +11,6 @@ import (
"path/filepath"
"slices"
"strconv"
"time"
"golang.org/x/sys/unix"
// The pure-Go SQLite driver, registered as "sqlite"; keeps cgo
@@ -41,18 +40,15 @@ 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. mtime
// holds whole Unix seconds and mtime_nsec the nanoseconds within that
// second.
// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8.
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
path BLOB PRIMARY KEY,
size INTEGER NOT NULL,
mtime INTEGER NOT NULL,
head TEXT NOT NULL,
tail TEXT NOT NULL,
content TEXT NOT NULL
) WITHOUT ROWID
`
@@ -65,11 +61,10 @@ 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, mtime_nsec, head, tail, content)
VALUES (?, ?, ?, ?, ?, ?, ?)
INSERT INTO files (path, size, mtime, 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
`
@@ -361,8 +356,8 @@ 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, mtime_nsec, head, tail, content "+
"FROM files ORDER BY path")
"SELECT path, size, mtime, head, tail, content FROM files "+
"ORDER BY path")
if err != nil {
return fmt.Errorf("read records: %w", err)
}
@@ -371,19 +366,17 @@ func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
for rows.Next() {
var (
path []byte
sec, nsec int64
r scanRec
path []byte
r scanRec
)
err = rows.Scan(&path, &r.size, &sec, &nsec, &r.head, &r.tail,
err = rows.Scan(&path, &r.size, &r.mtime, &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)
}
@@ -473,10 +466,10 @@ 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 int64, mtime time.Time, hashed bool),
fn func(path string, size, mtime int64, hashed bool),
) error {
rows, err := db.QueryContext(ctx,
"SELECT path, size, mtime, mtime_nsec, head <> '' FROM files")
"SELECT path, size, mtime, head <> '' FROM files")
if err != nil {
return fmt.Errorf("read records: %w", err)
}
@@ -485,17 +478,17 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
for rows.Next() {
var (
path []byte
size, sec, nsec int64
hashed int64
path []byte
size, mtime int64
hashed int64
)
err = rows.Scan(&path, &size, &sec, &nsec, &hashed)
err = rows.Scan(&path, &size, &mtime, &hashed)
if err != nil {
return fmt.Errorf("read record: %w", err)
}
fn(string(path), size, time.Unix(sec, nsec), hashed != 0)
fn(string(path), size, mtime, hashed != 0)
}
err = rows.Err()
@@ -514,7 +507,7 @@ 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.mtime_nsec, f.head, f.tail, f.content <> ''
SELECT f.path, f.size, f.mtime, f.head, f.tail, f.content <> ''
FROM files AS f
JOIN (
SELECT size, head, tail
@@ -540,20 +533,17 @@ func loadContentCandidates(ctx context.Context, db *sql.DB,
for rows.Next() {
var (
path []byte
sec, nsec int64
r scanRec
hashed int64
path []byte
r scanRec
hashed int64
)
err = rows.Scan(&path, &r.size, &sec, &nsec, &r.head, &r.tail,
&hashed)
err = rows.Scan(&path, &r.size, &r.mtime, &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)
}
@@ -637,8 +627,8 @@ 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.Unix(), r.mtime.Nanosecond(), r.head, r.tail, r.content)
_, err = st.ExecContext(ctx,
[]byte(r.path), r.size, r.mtime, r.head, r.tail, r.content)
if err != nil {
return fmt.Errorf("upsert %s: %w", r.path, err)
}
+5 -10
View File
@@ -10,7 +10,6 @@ import (
"slices"
"strings"
"testing"
"time"
)
// testDBPath returns a database path inside a fresh temp dir.
@@ -261,13 +260,10 @@ func TestApplyChangesRoundTrip(t *testing.T) {
// written.
recs := []scanRec{
{
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: 2, mtime: 20, head: "h2", tail: "t2", content: "c2",
path: "/a/tab\tnew\nline",
},
{size: 1, mtime: 10, head: "h1", tail: "t1", content: "c1", path: "/a/x"},
}
err := applyChanges(t.Context(), db, recs, nil,
@@ -285,8 +281,7 @@ 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: time.Unix(30, 0), head: "h3", tail: "t3", content: "c3",
path: "/a/x",
size: 3, mtime: 30, head: "h3", tail: "t3", content: "c3", path: "/a/x",
}
err = applyChanges(t.Context(), db, []scanRec{upd},
@@ -313,7 +308,7 @@ func TestApplyChangesBatching(t *testing.T) {
recs := make([]scanRec, 0, n)
for i := range n {
recs = append(recs, scanRec{
size: int64(i), mtime: time.Unix(1, 0), head: "h", tail: "t",
size: int64(i), mtime: 1, head: "h", tail: "t",
path: fmt.Sprintf("/batch/%07d", i),
})
}
+1 -2
View File
@@ -7,7 +7,6 @@ import (
"io"
"os"
"strings"
"time"
)
// ioBufSize is the buffer size for the buffered stdout writers.
@@ -22,7 +21,7 @@ const minGroupSize = 2
// only and used by scan for change detection.
type scanRec struct {
size int64
mtime time.Time
mtime int64
head string
tail string
content string
+2 -9
View File
@@ -11,7 +11,6 @@ import (
"slices"
"strings"
"testing"
"time"
)
// awkwardDir is a directory name holding every byte the reports escape.
@@ -314,14 +313,8 @@ func TestDupeGroupsMtimeExcluded(t *testing.T) {
// mtime is informational only; records differing only in mtime
// still group together.
recs := []scanRec{
{
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",
},
{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"},
}
groups := dupeGroupsOf(t, recs)
+7 -18
View File
@@ -17,7 +17,6 @@ import (
"strings"
"sync"
"syscall"
"time"
)
// The duplicate ladder (see hashSignature and README "Duplicate
@@ -69,7 +68,7 @@ var errInterrupted = errors.New("scan interrupted")
type fileRec struct {
path string
size int64
mtime time.Time
mtime int64
dev uint64
ino uint64
}
@@ -80,7 +79,7 @@ type fileRec struct {
// they would dominate the scan's memory.
type fileMeta struct {
size int64
mtime time.Time
mtime int64
hashed bool
}
@@ -370,7 +369,7 @@ 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 int64, mtime time.Time, hashed bool) {
func(path string, size, mtime int64, hashed bool) {
prog.increment()
if underAnyRoot(path, roots) {
@@ -416,7 +415,7 @@ func (s *scanState) walkPhase(
old, ok := s.existing[ev.rec.path]
switch {
case !ok || old.size != ev.rec.size || mtimeAfter(ev.rec.mtime, old.mtime):
case !ok || old.size != ev.rec.size || old.mtime < ev.rec.mtime:
changed = append(changed, ev.rec)
case old.hashed:
delete(s.existing, ev.rec.path)
@@ -808,7 +807,7 @@ func unchangedFile(r scanRec) (fileRec, bool, error) {
}
if !fi.Mode().IsRegular() || fi.Size() != r.size ||
mtimeAfter(fi.ModTime(), r.mtime) {
fi.ModTime().Unix() > r.mtime {
return fileRec{}, false, nil
}
@@ -819,16 +818,6 @@ 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 {
@@ -977,7 +966,7 @@ func seedRoot(ctx context.Context, root string,
sendEvent(ctx, events, walkEvent{rec: fileRec{
path: root,
size: fi.Size(),
mtime: fi.ModTime(),
mtime: fi.ModTime().Unix(),
dev: dev,
ino: ino,
}})
@@ -1135,7 +1124,7 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
sendEvent(ctx, events, walkEvent{rec: fileRec{
path: p,
size: info.Size(),
mtime: info.ModTime(),
mtime: info.ModTime().Unix(),
dev: dev,
ino: ino,
}})
+7 -227
View File
@@ -20,8 +20,6 @@ import (
"syscall"
"testing"
"time"
"golang.org/x/sys/unix"
)
// writeFile creates a file with the given content and returns its path.
@@ -583,65 +581,6 @@ 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.
@@ -844,8 +783,8 @@ func TestWalk(t *testing.T) {
t.Errorf("%s: size = %d, want 1..3", r.path, r.size)
}
if r.mtime.Unix() <= 0 {
t.Errorf("%s: mtime = %v, want after 1970", r.path, r.mtime)
if r.mtime <= 0 {
t.Errorf("%s: mtime = %d, want positive", r.path, r.mtime)
}
}
}
@@ -1346,172 +1285,11 @@ 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.Equal(future) {
t.Fatalf("mtime = %v, want %v", r.mtime, future)
if r := recordByPath(t, dbRecords(t, db), a); r.mtime != future.Unix() {
t.Fatalf("mtime = %d, want %d", r.mtime, future.Unix())
}
}
// 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()
@@ -1557,7 +1335,9 @@ func TestSyncScanSizeChange(t *testing.T) {
writeFile(t, dir, "f", pattern(1, 200))
err := os.Chtimes(p, old.mtime, old.mtime)
mt := time.Unix(old.mtime, 0)
err := os.Chtimes(p, mt, mt)
if err != nil {
t.Fatal(err)
}
+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 "$0")" && pwd -P)"
+5 -7
View File
@@ -14,17 +14,15 @@ main() {
cd "$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.
# 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="$version" \
-t "$tag" .
-t "$("$SCRIPT_DIR/projectname")" .
}
main "$@"
+5 -7
View File
@@ -10,17 +10,15 @@ ROOT="$(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.
# 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="$version" \
-t "$tag" .
-t "$("$SCRIPT_DIR/projectname")" .
}
main "$@"
+7 -3
View File
@@ -1,15 +1,19 @@
#!/bin/sh
# script/install-precommit: install the git pre-commit hook that runs
# script/precommit. Our own extension to scripts-to-rule-them-all.
# Hooks are shared between the main checkout and all worktrees, so
# resolve the common git dir instead of assuming .git is a directory.
set -eu
ROOT="$(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 "$hook"
echo "pre-commit hook installed: runs script/precommit"
}
+2 -2
View File
@@ -1,13 +1,13 @@
#!/bin/sh
# script/precommit: run by the git pre-commit hook; fails the commit if
# checks fail. Our own extension to scripts-to-rule-them-all.
# checks fail. Our own extension to scripts-to-rule-them-all. Go extra:
# go mod tidy must be a no-op before the checks run.
set -eu
SCRIPT_DIR="$(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
+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)"