fix(i18n): harden stopped-merge recovery

This commit is contained in:
Tianyi Cui
2026-08-08 21:49:23 +08:00
parent 75570ba31e
commit 9a4b70cf3b
14 changed files with 237 additions and 59 deletions

View File

@@ -38,5 +38,10 @@ try {
}
} catch (error) {
console.error(`merge-translation-pairing: ${error instanceof Error ? error.message : String(error)}`)
console.error(
'merge-translation-pairing: resolve owner conflicts, then confirm the pair with '
+ '`pnpm run verify-translation-pairing --write <pair>`; rerun '
+ '`pnpm run resolve-translation-pairing-conflicts` for other safe records',
)
process.exitCode = 1
}

File diff suppressed because one or more lines are too long

View File

@@ -5,6 +5,9 @@ import { createHash } from 'node:crypto'
const SNAPSHOT_REF_PREFIX = 'refs/dsh/translation-pairing/snapshots'
/** Maximum buffered stdout or stderr for repository-owned Git subprocesses. */
export const GIT_COMMAND_MAX_BUFFER = 1 << 26
/** Full SHA-1 Git blob hash (the 40-hex format used by pairing records). */
export function gitBlobHash(content: Buffer): string {
const hash = createHash('sha1')
@@ -13,10 +16,20 @@ export function gitBlobHash(content: Buffer): string {
return hash.digest('hex')
}
function runGit(root: string, args: string[], operation: string, input?: Buffer): Buffer {
/**
* Run one Git subprocess and return its exact stdout bytes.
*
* @param root - Repository root used as Git's working directory.
* @param args - Arguments following the `git` executable.
* @param operation - Human-readable operation for failure diagnostics.
* @param input - Optional stdin bytes.
* @returns Exact stdout bytes.
* @throws Error when Git cannot start or exits unsuccessfully.
*/
export function runGit(root: string, args: string[], operation: string, input?: Buffer): Buffer {
const result = spawnSync('git', ['-C', root, ...args], {
input,
maxBuffer: 1 << 26,
maxBuffer: GIT_COMMAND_MAX_BUFFER,
})
if (result.error) {
throw new Error(`${operation} failed: ${result.error.message}`, { cause: result.error })

View File

@@ -85,6 +85,12 @@ const otherSource = baseSource.replace('Beta base.', 'Beta other.')
const otherZh = baseZh.replace('乙基础。', '乙对侧。')
const mergedSource = currentSource.replace('Beta base.', 'Beta other.')
const mergedZh = currentZh.replace('乙基础。', '乙对侧。')
const manualBaseSource = baseSource.replace('guide.zh.md', 'manual.zh.md')
const manualBaseZh = baseZh.replace('guide.md', 'manual.md')
const manualCurrentSource = manualBaseSource.replace('Alpha base.', 'Alpha current.')
const manualCurrentZh = manualBaseZh.replace('甲基础。', '甲当前。')
const manualOtherSource = manualBaseSource.replace('Alpha base.', 'Alpha other.')
const manualOtherZh = manualBaseZh.replace('甲基础。', '甲对侧。')
function commitPair(fixture: Fixture, source: string, zh: string, message: string): string {
const sidecar = record(fixture.root, 'docs/guide.md', source, zh)
@@ -113,6 +119,47 @@ function startStoppedPairingMerge(fixture: Fixture): void {
expect(git(fixture, ['diff', '--name-only', '--diff-filter=U'])).toBe('docs/guide.i18n.yaml')
}
function commitMixedPairs(
fixture: Fixture,
guide: { source: string; zh: string },
manual: { source: string; zh: string },
message: string,
): void {
record(fixture.root, 'docs/guide.md', guide.source, guide.zh)
record(fixture.root, 'docs/manual.md', manual.source, manual.zh)
git(fixture, ['add', '.'])
git(fixture, ['commit', '-m', message])
}
function startMixedPairingMerge(fixture: Fixture): void {
commitMixedPairs(
fixture,
{ source: baseSource, zh: baseZh },
{ source: manualBaseSource, zh: manualBaseZh },
'base',
)
git(fixture, ['switch', '-c', 'current'])
commitMixedPairs(
fixture,
{ source: currentSource, zh: currentZh },
{ source: manualCurrentSource, zh: manualCurrentZh },
'current',
)
git(fixture, ['switch', 'master'])
commitMixedPairs(
fixture,
{ source: otherSource, zh: otherZh },
{ source: manualOtherSource, zh: manualOtherZh },
'other',
)
git(fixture, ['switch', 'current'])
const merge = spawnSync('git', ['-C', fixture.root, 'merge', '--no-commit', 'master'], {
encoding: 'utf8',
env: fixture.env,
})
expect(merge.status).toBe(1)
}
function expectMergedPair(fixture: Fixture): void {
expect(readFileSync(join(fixture.root, 'docs/guide.md'), 'utf8')).toBe(mergedSource)
expect(readFileSync(join(fixture.root, 'docs/guide.zh.md'), 'utf8')).toBe(mergedZh)
@@ -139,6 +186,7 @@ describe('translation pairing merge composition', () => {
it('merges the owner blobs named by three valid records', () => {
const fixture = createFixture(false)
git(fixture, ['config', 'merge.default', 'text'])
const records = createDivergedPair(fixture)
const result = mergeTranslationPairingRecords(
@@ -214,6 +262,20 @@ describe('translation pairing merge composition', () => {
)).toThrow('docs/guide.md uses merge=custom-owner')
})
it('refuses unspecified owners affected by merge.default', () => {
const fixture = createFixture(false)
git(fixture, ['config', 'merge.default', 'custom-owner'])
const records = createDivergedPair(fixture)
expect(() => mergeTranslationPairingRecords(
fixture.root,
'docs/guide.i18n.yaml',
records.ancestor,
records.current,
records.other,
)).toThrow('merge.default=custom-owner')
})
it('runs as Git\'s custom driver and commits a clean composed record', () => {
const fixture = createFixture()
createDivergedPair(fixture)
@@ -231,6 +293,19 @@ describe('translation pairing merge composition', () => {
expectMergedPair(fixture)
})
it('prints the recovery path when driver input is not composable', () => {
const fixture = createFixture(false)
const result = spawnSync(process.execPath, ['--import', tsxLoader, driver], {
cwd: fixture.root,
encoding: 'utf8',
env: fixture.env,
})
expect(result.status).toBe(1)
expect(result.stderr).toContain('pnpm run verify-translation-pairing --write <pair>')
expect(result.stderr).toContain('pnpm run resolve-translation-pairing-conflicts')
})
it('resolves an already-stopped generated-only conflict from index stages', () => {
const fixture = createFixture(false)
startStoppedPairingMerge(fixture)
@@ -251,4 +326,32 @@ describe('translation pairing merge composition', () => {
)
expect(git(fixture, ['diff', '--name-only', '--diff-filter=U'])).toBe('docs/guide.i18n.yaml')
})
it('refuses to overwrite an edited sidecar after a stopped merge', () => {
const fixture = createFixture(false)
startStoppedPairingMerge(fixture)
write(fixture.root, 'docs/guide.i18n.yaml', 'manually resolved\n')
expect(() => resolveTranslationPairingConflicts(fixture.root)).toThrow(
'docs/guide.i18n.yaml has edited conflict content',
)
expect(readFileSync(join(fixture.root, 'docs/guide.i18n.yaml'), 'utf8')).toBe('manually resolved\n')
expect(git(fixture, ['diff', '--name-only', '--diff-filter=U'])).toBe('docs/guide.i18n.yaml')
})
it('resolves safe records while leaving an owner-conflicted pair untouched', () => {
const fixture = createFixture(false)
startMixedPairingMerge(fixture)
expect(() => resolveTranslationPairingConflicts(fixture.root)).toThrow(
'docs/manual.i18n.yaml: docs/manual.md has content conflicts',
)
expect(git(fixture, ['diff', '--name-only', '--diff-filter=U']).split('\n')).toEqual([
'docs/manual.i18n.yaml',
'docs/manual.md',
'docs/manual.zh.md',
])
expectMergedPair(fixture)
})
})

View File

@@ -4,7 +4,13 @@ import { spawnSync } from 'node:child_process'
import { mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { basename, isAbsolute, join, relative, resolve, sep } from 'node:path'
import { gitBlobHash, readGitIndexBlob, storeGitBlob } from './translation-pairing-git.ts'
import {
GIT_COMMAND_MAX_BUFFER,
gitBlobHash,
readGitIndexBlob,
runGit,
storeGitBlob,
} from './translation-pairing-git.ts'
import {
linksTo,
isTranslationScopeFile,
@@ -20,7 +26,6 @@ import {
type TranslationPairingRecord,
} from './translation-pairing-record.ts'
const MAX_GIT_OUTPUT = 1 << 26
const UNMERGED_ENTRY = /^(\d+) ([0-9a-f]+) ([123])\t([\s\S]+)$/
/** A mechanically composed record and the exact merged owner contents it names. */
@@ -39,18 +44,6 @@ interface UnmergedStages {
other?: string
}
function runGit(root: string, args: string[], operation: string, input?: Buffer): Buffer {
const result = spawnSync('git', ['-C', root, ...args], {
input,
maxBuffer: MAX_GIT_OUTPUT,
})
if (result.error) throw new Error(`${operation} failed: ${result.error.message}`, { cause: result.error })
if (result.status !== 0) {
throw new Error(`${operation} failed with status ${String(result.status)}: ${result.stderr.toString('utf8').trim()}`)
}
return result.stdout
}
function readGitBlob(root: string, objectId: string, owner: string): Buffer {
const content = runGit(root, ['cat-file', 'blob', objectId], `reading ${owner} blob ${objectId}`)
if (gitBlobHash(content) !== objectId) {
@@ -59,6 +52,22 @@ function readGitBlob(root: string, objectId: string, owner: string): Buffer {
return content
}
function readMergeDefault(root: string): string | undefined {
const result = spawnSync('git', ['-C', root, 'config', '--get', 'merge.default'], {
maxBuffer: GIT_COMMAND_MAX_BUFFER,
})
if (result.error) {
throw new Error(`reading merge.default failed: ${result.error.message}`, { cause: result.error })
}
if (result.status === 1) return undefined
if (result.status !== 0) {
throw new Error(
`reading merge.default failed with status ${String(result.status)}: ${result.stderr.toString('utf8').trim()}`,
)
}
return result.stdout.toString('utf8').trim()
}
function assertDefaultTextMerge(root: string, paths: TranslationPairPaths): void {
const output = runGit(
root,
@@ -67,6 +76,7 @@ function assertDefaultTextMerge(root: string, paths: TranslationPairPaths): void
).toString('utf8')
const fields = output.split('\0')
fields.pop()
let mergeDefault: string | undefined
for (let index = 0; index < fields.length; index += 3) {
const path = fields[index]
const value = fields[index + 2]
@@ -76,6 +86,14 @@ function assertDefaultTextMerge(root: string, paths: TranslationPairPaths): void
if (!['unspecified', 'set', 'text'].includes(value)) {
throw new Error(`${path} uses merge=${value}; the pairing driver only composes Git's default text merge`)
}
if (value === 'unspecified') {
mergeDefault ??= readMergeDefault(root)
if (mergeDefault !== undefined && mergeDefault !== 'text') {
throw new Error(
`${path} inherits merge.default=${mergeDefault}; the pairing driver only composes Git's default text merge`,
)
}
}
}
}
@@ -101,7 +119,7 @@ function mergeBlobTriplet(
'-L', `${owner}:ancestor`,
'-L', `${owner}:other`,
currentPath, ancestorPath, otherPath,
], { maxBuffer: MAX_GIT_OUTPUT })
], { maxBuffer: GIT_COMMAND_MAX_BUFFER })
if (result.error) {
throw new Error(`merging ${owner} failed: ${result.error.message}`, { cause: result.error })
}
@@ -222,46 +240,85 @@ function unmergedSidecars(root: string): Map<string, UnmergedStages> {
return records
}
function assertUneditedSidecar(
root: string,
metaPath: string,
currentRecord: string,
otherRecord: string,
): void {
const worktreeRecord = readFileSync(join(root, metaPath), 'utf8')
if (worktreeRecord === currentRecord || worktreeRecord === otherRecord) return
const stageDataLines = [currentRecord, otherRecord]
.flatMap(record => record.split(/\r?\n/))
.filter(line => line !== '' && !line.startsWith('#'))
const hasUneditedConflict = worktreeRecord.includes('<<<<<<<')
&& worktreeRecord.includes('=======')
&& worktreeRecord.includes('>>>>>>>')
&& stageDataLines.every(line => worktreeRecord.includes(line))
if (!hasUneditedConflict) {
throw new Error(`${metaPath} has edited conflict content; refusing to overwrite manual work`)
}
}
/**
* Resolve every mechanically composable `.i18n.yaml` conflict in the index.
*
* The command first proves that Git's already-staged owner merges match the
* independently composed contents, then writes and stages all sidecars as one
* batch. Other conflicts remain untouched.
* batch. Other conflicts remain untouched; after staging the safe records, an
* aggregate error reports any pairing conflicts that still need manual work.
*
* @param root - Repository root with an in-progress merge-like operation.
* @returns Repository-relative sidecar paths resolved and staged.
*/
export function resolveTranslationPairingConflicts(root: string): string[] {
const resolutions: { path: string; record: string }[] = []
const failures: { path: string; reason: string }[] = []
for (const [metaPath, stages] of [...unmergedSidecars(root)].sort(([left], [right]) => left.localeCompare(right))) {
if (stages.ancestor === undefined || stages.current === undefined || stages.other === undefined) {
throw new Error(`${metaPath} is an add/delete or incomplete-stage conflict and requires manual resolution`)
}
const result = mergeTranslationPairingRecords(
root,
metaPath,
readGitBlob(root, stages.ancestor, `ancestor ${metaPath}`).toString('utf8'),
readGitBlob(root, stages.current, `current ${metaPath}`).toString('utf8'),
readGitBlob(root, stages.other, `other ${metaPath}`).toString('utf8'),
)
const paths = translationPairPathsFromMeta(metaPath)
if (readGitIndexBlob(root, paths.source)?.objectId !== result.sourceHash) {
throw new Error(`${paths.source} staged merge does not match the pairing driver's clean merge`)
}
if (readGitIndexBlob(root, paths.zh)?.objectId !== result.zhHash) {
throw new Error(`${paths.zh} staged merge does not match the pairing driver's clean merge`)
}
for (const [path, expected] of [[paths.source, result.sourceHash], [paths.zh, result.zhHash]] as const) {
if (gitBlobHash(readFileSync(join(root, path))) !== expected) {
throw new Error(`${path} has unstaged content; refusing to confirm bytes outside the merge result`)
try {
if (stages.ancestor === undefined || stages.current === undefined || stages.other === undefined) {
throw new Error('is an add/delete or incomplete-stage conflict and requires manual resolution')
}
const ancestorRecord = readGitBlob(root, stages.ancestor, `ancestor ${metaPath}`).toString('utf8')
const currentRecord = readGitBlob(root, stages.current, `current ${metaPath}`).toString('utf8')
const otherRecord = readGitBlob(root, stages.other, `other ${metaPath}`).toString('utf8')
assertUneditedSidecar(root, metaPath, currentRecord, otherRecord)
const result = mergeTranslationPairingRecords(
root,
metaPath,
ancestorRecord,
currentRecord,
otherRecord,
)
const paths = translationPairPathsFromMeta(metaPath)
if (readGitIndexBlob(root, paths.source)?.objectId !== result.sourceHash) {
throw new Error(`${paths.source} staged merge does not match the pairing driver's clean merge`)
}
if (readGitIndexBlob(root, paths.zh)?.objectId !== result.zhHash) {
throw new Error(`${paths.zh} staged merge does not match the pairing driver's clean merge`)
}
for (const [path, expected] of [[paths.source, result.sourceHash], [paths.zh, result.zhHash]] as const) {
if (gitBlobHash(readFileSync(join(root, path))) !== expected) {
throw new Error(`${path} has unstaged content; refusing to confirm bytes outside the merge result`)
}
}
resolutions.push({ path: metaPath, record: result.record })
} catch (error) {
failures.push({ path: metaPath, reason: error instanceof Error ? error.message : String(error) })
}
resolutions.push({ path: metaPath, record: result.record })
}
for (const resolution of resolutions) writeFileSync(join(root, resolution.path), resolution.record)
if (resolutions.length > 0) {
runGit(root, ['add', '--', ...resolutions.map(resolution => resolution.path)], 'staging resolved pairing records')
}
if (failures.length > 0) {
const resolved = resolutions.length === 0
? ''
: `resolved and staged ${resolutions.map(resolution => resolution.path).join(', ')}; `
throw new Error(
`${resolved}left ${String(failures.length)} pairing conflict(s) unresolved:\n`
+ failures.map(failure => `- ${failure.path}: ${failure.reason}`).join('\n'),
)
}
return resolutions.map(resolution => resolution.path)
}