Merge remote-tracking branch 'origin/master' into feat/todo-multi-in-progress
This commit is contained in:
Tianyi Cui committed
commit
d1d29ffba8
10 files changed
+143
-24
No files matched your search
@@ -24,11 +24,11 @@
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "# Bilingual documentation\n\nEnglish | [中文](README.zh.md)\n\nThis repo's documentation is read by people and agents both inside and outside the company, so every document in scope is maintained in English and Simplified Chinese. This page defines the pairing contract, enforcement gate, scope, and exclusions; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md).\n\n## The pairing contract\n\n- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first Agent Note is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing.\n- **A pair is three sibling files.** The English `foo.md`, the Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`, all in the same directory. No locale directories, no separate translation repo, no interleaved bilingual files. Pairs merge whole: a PR never lands one language without the other two files.\n- **The consistency record.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last time the two were confirmed to say the same thing:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n Blob hashes, not commit hashes, so the record is computable for files edited in the same PR (`git hash-object foo.md`) and consistency is a pure content comparison. The recorded hashes also recover the exact last-confirmed text of either side, so an out-of-sync pair is updated by patching the counterpart minimally against the edited side's diff — never by re-translating whole files. `pnpm run gen-translation-brief <pair>` assembles that update's working set mechanically at the narrowest safely aligned granularity — changed Markdown units, then heading sections, then whole document — with the edited side's diff since last confirmation, each changed span's three-way text, the terminology rows the change touches, and the binding update rules; a change confined to the pair's byte-identical code fences is computed outright, and `--apply` splices it into the counterpart after structural validation ([briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)). After bringing the pair back in line, `pnpm run verify-translation-pairing --write <pair>` re-records both hashes; that yaml diff is the reviewable act of confirming consistency, which is why `--write` requires naming the pairs you confirmed (`--write --all` is the explicit corpus-wide form).\n- **Language switcher.** Both files link to each other immediately after their H1 heading: the English file carries `English | [中文](foo.zh.md)` and the Chinese file carries `[English](foo.md) | 中文`.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).\n\n## The gate: verify-translation-pairing\n\n`pnpm run verify-translation-pairing` (part of `doc-sync`, which contributors run locally for documentation changes and CI runs exhaustively) enforces the contract mechanically:\n\n1. Every document in scope has a complete pair. README discovery is case-insensitive on the basename, so `missions/readme.md` is in scope alongside the other documentation roots.\n2. Every pair artifact that exists at all is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher.\n3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all. Frozen Agent Notes under `.agents/notes/archived/` are outside this evolving gate; their dedicated verifier requires and seals the complete existing triplet instead.\n\nSource-oriented code gates consume an exact `.zh.md` fence sequence as a derivative of its unsuffixed sibling instead of compiling or manifesting the same code twice. The sequence must match in length, order, fence kind, and byte-exact body; otherwise both copies remain independently checked and the pairing gate reports the structural mismatch.\n\n`pnpm run verify-translLine truncated
|
||||
"content": "# Bilingual documentation\n\nEnglish | [中文](README.zh.md)\n\nThis repo's documentation is read by people and agents both inside and outside the company, so every document in scope is maintained in English and Simplified Chinese. This page defines the pairing contract, enforcement gate, scope, and exclusions; [translation-rules.md](translation-rules.md) defines how to translate; [terminology.md](terminology.md) is the terminology source of truth. The committed agent workflow lives in [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md).\n\n## The pairing contract\n\n- **Both languages carry equal authority.** A document may be authored and reviewed in either language first — a Chinese-first Agent Note is as legitimate as an English-first one — and the counterpart is translated from it. Neither file outranks the other; what binds them is that they must say the same thing.\n- **A pair is three sibling files.** The English `foo.md`, the Chinese `foo.zh.md`, and a consistency record `foo.i18n.yaml`, all in the same directory. No locale directories, no separate translation repo, no interleaved bilingual files. Pairs merge whole: a PR never lands one language without the other two files.\n- **The consistency record.** `foo.i18n.yaml` holds the full git blob hash of each side as of the last time the two were confirmed to say the same thing:\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n Blob hashes, not commit hashes, so the record is computable for files edited in the same PR (`git hash-object foo.md`) and consistency is a pure content comparison. `--write` stores those snapshots in the local Git object database before recording them, including uncommitted working-tree contents, and pins every distinct stored blob under a content-addressed `refs/dsh/translation-pairing/snapshots/` ref so garbage collection cannot invalidate a recorded recovery pointer. The recorded hashes therefore recover the exact last-confirmed text of either side, so an out-of-sync pair is updated by patching the counterpart minimally against the edited side's diff — never by re-translating whole files. `pnpm run gen-translation-brief <pair>` assembles that update's working set mechanically at the narrowest safely aligned granularity — changed Markdown units, then heading sections, then whole document — with the edited side's diff since last confirmation, each changed span's three-way text, the terminology rows the change touches, and the binding update rules; a change confined to the pair's byte-identical code fences is computed outright, and `--apply` splices it into the counterpart after structural validation ([briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)). After bringing the pair back in line, `pnpm run verify-translation-pairing --write <pair>` re-records both hashes; that yaml diff is the reviewable act of confirming consistency, which is why `--write` requires naming the pairs you confirmed (`--write --all` is the explicit corpus-wide form).\n- **Language switcher.** Both files link to each other immediately after their H1 heading: the English file carries `English | [中文](foo.zh.md)` and the Chinese file carries `[English](foo.md) | 中文`.\n- **Structure mirrors the counterpart.** Heading depths and order, list kinds, ordered-list starts, list item counts, table row and column counts, link targets, and verbatim code blocks match one to one across the pair — see [translation-rules.md](translation-rules.md) for the full preservation rules. Existing Markdown gates apply to `.zh.md` files unchanged (`verify-md-wrap`, `verify-md-links`).\n\n## The gate: verify-translation-pairing\n\n`pnpm run verify-translation-pairing` (part of `doc-sync`, which contributors run locally for documentation changes and CI runs exhaustively) enforces the contract mechanically:\n\n1. Every document in scope has a complete pair. README discovery is case-insensitive on the basename, so `missions/readme.md` is in scope alongside the other documentation roots.\n2. Every pair artifact that exists at all is complete and consistent: all three files present, each side's current blob hash equals the recorded one (editing either side without re-confirming the pair goes red), both sides carry the language switcher, and the structural signatures match in order — heading depths, verbatim code blocks (info string and content), table row and column counts, list kinds, ordered-list starts, item counts, and every link target apart from the switcher.\n3. Files listed as `excluded` have no `.zh.md` and no `.i18n.yaml` at all. Frozen Agent Notes under `.agents/notes/archived/` are outside this evolving gate; their dedicated verifier requires and seals the complete existing triplet instead.\n\nSource-oriented code gates consume an exact `.zh.md` fencLine truncated
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "# 双语文档\n\n[English](README.md) | 中文\n\n本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此范围内的每篇文档都以英文和简体中文维护。本页定义配对契约、强制门禁、范围与排除规则；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。\n\n## 配对契约\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审（先写中文的 Agent Note 与先写英文的一样正当），另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对必须整体合并：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash：\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash，这样同一个 PR 里改动的文件也能算出记录（`git hash-object foo.md`），一致性是纯内容比较。记录的 hash 还能还原任一侧上次确认时的确切文本，所以失去同步的配对是「按被改一侧的 diff 最小化地修补另一侧」，从不整篇重译。`pnpm run gen-translation-brief <pair>` 会以能安全对齐的最窄粒度——先是有改动的 Markdown 单元，再是标题小节，最后是整篇文档——机械地汇集这次更新的工作集：被改一侧自上次确认以来的 diff、每个改动块的三方文本、改动触及的术语表行，以及有约束力的更新规则；仅落在配对中逐字节一致的围栏代码块内的改动可以直接算出，`--apply` 则经结构签名校验后把它拼接进对侧文件（[briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)）。两侧对齐后，`pnpm run verify-translation-pairing --write <pair>` 重新记录两个 hash；那份 yaml diff 就是「确认一致」这个动作本身，可以被评审，也正因如此，`--write` 要求点名你确认过的配对（`--write --all` 是显式的全语料形式）。\n- **语言切换行。** 两个文件在各自 H1 标题之后立即互链：英文文件带 `English | [中文](foo.zh.md)`，中文文件带 `[English](foo.md) | 中文`。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应；完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。\n\n## 门禁：verify-translation-pairing\n\n`pnpm run verify-translation-pairing`（`doc-sync`（文档同步门禁）的一环，贡献者会针对文档变更在本地运行，CI 则会完整运行）机械地强制执行这份契约：\n\n1. 范围内的每篇文档都有完整配对。发现 README 时，basename 不区分大小写，因此 `missions/readme.md` 与其他文档根一样属于范围。\n2. 任何已存在的配对产物都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致：标题深度、逐字节一致的代码块（信息字符串与内容）、表格行列数、列表类型、有序列表起始编号、列表项数量，以及除切换行之外的每个链接目标。\n3. 列为 `excluded` 的文件完全没有 `.zh.md`，也没有 `.i18n.yaml`。`.agents/notes/archived/` 下冻结的 Agent Note 不受这个持续演进的门禁约束；专用校验器会要求其现有的三个配对文件完整，并将其封存。\n\n面向源码的代码门禁会把精确的 `.zh.md` 围栏序列视为其无后缀兄弟文件的派生内容，而不会再次编译相同代码或在 manifest 中重复登记。该序列必须在长度、顺序、围栏类型和按字节精确的正文上一致；否则两份副本仍会独立受检，配对门禁也会报告结构不匹配。\n\n`pnpm run verify-translation-pairing --list` 打印范围内每篇文档的当前配对状态（missing、out-of-sync 或 ok）。它从不失败；其中 missing 与 out-of-sync 行指出普通检查会拒绝的违规。\n\n`pnpm run verify-translation-pairing <pair...>` 只检查被点名的配对——配对的三个文件Line truncated
|
||||
"content": "# 双语文档\n\n[English](README.md) | 中文\n\n本仓库的文档会被公司内外的人和 agent（智能体）阅读，因此范围内的每篇文档都以英文和简体中文维护。本页定义配对契约、强制门禁、范围与排除规则；[translation-rules.md](translation-rules.md) 定义如何翻译；[terminology.md](terminology.md) 是术语真源。仓库内置的 agent 工作流见 [.agents/skills/dsh-translate-docs](../../.agents/skills/dsh-translate-docs/SKILL.md)。\n\n## 配对契约\n\n- **两种语言同权。** 一篇文档可以先用任一语言撰写和评审（先写中文的 Agent Note 与先写英文的一样正当），另一侧由它翻译而来。两个文件谁也不高于谁；约束它们的是二者必须说同样的话。\n- **一对文档是三个同目录文件。** 英文 `foo.md`、中文 `foo.zh.md`，加一份一致性记录 `foo.i18n.yaml`，都在同一目录。不用语言目录，不用独立翻译仓库，不用中英混排的单文件。配对必须整体合并：PR（Pull Request）永远不会只带一种语言而缺其余两个文件。\n- **一致性记录。**`foo.i18n.yaml` 保存两侧文件在上一次被确认「说同样的话」时各自的完整 git blob hash：\n\n ```yaml\n foo.md: 3f786850e387550fdab836ed7e6dc881de23001b\n foo.zh.md: 89e6c98d92887913cadf06b2adb97f26cde4849b\n ```\n\n 用 blob hash 而不是 commit hash，这样同一个 PR 里改动的文件也能算出记录（`git hash-object foo.md`），一致性是纯内容比较。`--write` 会先把这些快照存入本地 Git 对象库再写下记录，未提交的工作树内容也不例外；它还会在内容寻址的 `refs/dsh/translation-pairing/snapshots/` ref 下固定每个不同的已存 blob，使垃圾回收无法让已记录的恢复指针失效。因此记录的 hash 能还原任一侧上次确认时的确切文本，所以失去同步的配对是「按被改一侧的 diff 最小化地修补另一侧」，从不整篇重译。`pnpm run gen-translation-brief <pair>` 会以能安全对齐的最窄粒度——先是有改动的 Markdown 单元，再是标题小节，最后是整篇文档——机械地汇集这次更新的工作集：被改一侧自上次确认以来的 diff、每个改动块的三方文本、改动触及的术语表行，以及有约束力的更新规则；仅落在配对中逐字节一致的围栏代码块内的改动可以直接算出，`--apply` 则经结构签名校验后把它拼接进对侧文件（[briefed-updates Agent Note](../../.agents/notes/implemented/process/2026-07-26-briefed-minimal-translation-updates.md)）。两侧对齐后，`pnpm run verify-translation-pairing --write <pair>` 重新记录两个 hash；那份 yaml diff 就是「确认一致」这个动作本身，可以被评审，也正因如此，`--write` 要求点名你确认过的配对（`--write --all` 是显式的全语料形式）。\n- **语言切换行。** 两个文件在各自 H1 标题之后立即互链：英文文件带 `English | [中文](foo.zh.md)`，中文文件带 `[English](foo.md) | 中文`。\n- **结构与另一侧一一对应。** 标题深度与顺序、列表类型、有序列表起始编号、列表项数量、表格行列数、链接目标与逐字节一致的代码块在配对两侧一一对应；完整保持规则见 [translation-rules.md](translation-rules.md)。既有 Markdown 门禁对 `.zh.md` 文件原样生效（`verify-md-wrap`、`verify-md-links`）。\n\n## 门禁：verify-translation-pairing\n\n`pnpm run verify-translation-pairing`（`doc-sync`（文档同步门禁）的一环，贡献者会针对文档变更在本地运行，CI 则会完整运行）机械地强制执行这份契约：\n\n1. 范围内的每篇文档都有完整配对。发现 README 时，basename 不区分大小写，因此 `missions/readme.md` 与其他文档根一样属于范围。\n2. 任何已存在的配对产物都完整且一致：三个文件齐全、每一侧的当前 blob hash 等于记录值（改了任一侧而没重新确认配对就变红）、双方都带语言切换行、结构签名按序一致：标题深度、逐字节一致的代码块（信息字符串与内容）、表格行列数、列表类型、有序列表起始编号、列表项数量，以及除切换行之外的每个链接目标。\n3. 列为 `excluded` 的文件完全没有 `.zh.md`，也没有 `.i18n.yaml`。`.agents/notes/archived/` 下冻结的 Agent Note 不受这个持续演进的门禁约束；专用校验器会要求其现有的三个配对文件完整，并将其封存。\n\n面向源码的代码门禁会把精确的 `.zh.md` 围栏序列视为其无后缀兄弟文件的派生内容，而不会再次编译相同代码或在 manifest 中重复登记。该序列必须在长度、顺序、围栏类型和按字节精确的正文上一致；否则两份副本仍会独立受检，配对门禁也会报告结构不匹配。\n\n`pnpm run verify-translation-pairing --lLine truncated
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
/** Git-blob operations owned by the bilingual pairing workflow. */
|
||||
|
||||
import { spawnSync } from 'node:child_process'
|
||||
import { createHash } from 'node:crypto'
|
||||
|
||||
const SNAPSHOT_REF_PREFIX = 'refs/dsh/translation-pairing/snapshots'
|
||||
|
||||
/** Full SHA-1 Git blob hash (the 40-hex format used by pairing records). */
|
||||
export function gitBlobHash(content: Buffer): string {
|
||||
const hash = createHash('sha1')
|
||||
hash.update(`blob ${content.byteLength}\0`)
|
||||
hash.update(content)
|
||||
return hash.digest('hex')
|
||||
}
|
||||
|
||||
function runGit(root: string, args: string[], operation: string, input?: Buffer): Buffer {
|
||||
const result = spawnSync('git', ['-C', root, ...args], {
|
||||
input,
|
||||
maxBuffer: 1 << 26,
|
||||
})
|
||||
if (result.error) {
|
||||
throw new Error(`${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
|
||||
}
|
||||
|
||||
/**
|
||||
* Persist exact working-tree bytes so a pairing record can later recover them
|
||||
* with `git cat-file`, even when they have never appeared in the index or a
|
||||
* commit. The returned object ID is checked against the pairing format's own
|
||||
* content hash before the caller writes a sidecar.
|
||||
*/
|
||||
export function storeGitBlob(root: string, content: Buffer): string {
|
||||
const expected = gitBlobHash(content)
|
||||
const stored = runGit(root, ['hash-object', '-w', '--stdin'], 'git hash-object -w --stdin', content)
|
||||
.toString('utf8')
|
||||
.trim()
|
||||
if (stored !== expected) {
|
||||
throw new Error(`git hash-object -w --stdin returned unexpected object ID ${JSON.stringify(stored)}; expected ${expected}`)
|
||||
}
|
||||
runGit(
|
||||
root,
|
||||
['update-ref', `${SNAPSHOT_REF_PREFIX}/${stored}`, stored],
|
||||
'git update-ref for translation snapshot',
|
||||
)
|
||||
return stored
|
||||
}
|
||||
@@ -1,6 +1,11 @@
|
||||
/** Regression tests for the bilingual corpus scope and structural signature. */
|
||||
/** Regression tests for bilingual snapshots, corpus scope, and structure. */
|
||||
|
||||
import { execFileSync, spawnSync } from 'node:child_process'
|
||||
import { mkdtempSync, rmSync } from 'node:fs'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { gitBlobHash, storeGitBlob } from './translation-pairing-git.ts'
|
||||
import {
|
||||
isTranslationScopeFile,
|
||||
pairAnchorOfArgument,
|
||||
@@ -15,6 +20,71 @@ function signature(markdown: string) {
|
||||
return translationStructureSignature(parseTranslationMarkdown(markdown), 'counterpart.zh.md')
|
||||
}
|
||||
|
||||
function gitSupportsObjectFormat(format: 'sha256'): boolean {
|
||||
const root = mkdtempSync(join(tmpdir(), 'dsh-git-object-format-'))
|
||||
try {
|
||||
return spawnSync('git', ['init', '--quiet', `--object-format=${format}`, root], {
|
||||
stdio: 'ignore',
|
||||
}).status === 0
|
||||
} finally {
|
||||
rmSync(root, { recursive: true, force: true })
|
||||
}
|
||||
}
|
||||
|
||||
const supportsSha256ObjectFormat = gitSupportsObjectFormat('sha256')
|
||||
|
||||
describe('translation pairing snapshots', () => {
|
||||
it('stores exact uncommitted bytes for later recovery by object ID', () => {
|
||||
const root = mkdtempSync(join(tmpdir(), 'dsh-translation-pairing-'))
|
||||
try {
|
||||
execFileSync('git', ['init', '--quiet', root], {
|
||||
env: { ...process.env, GIT_DEFAULT_HASH: 'sha1' },
|
||||
})
|
||||
const content = Buffer.from([0x75, 0x6e, 0x63, 0x6f, 0x6d, 0x6d, 0x69, 0x74, 0x74, 0x65, 0x64, 0x0a, 0xff])
|
||||
|
||||
const objectId = storeGitBlob(root, content)
|
||||
|
||||
expect(objectId).toBe(gitBlobHash(content))
|
||||
expect(execFileSync('git', [
|
||||
'-C', root, 'rev-parse', `refs/dsh/translation-pairing/snapshots/${objectId}`,
|
||||
], { encoding: 'utf8' }).trim()).toBe(objectId)
|
||||
execFileSync('git', ['-C', root, 'gc', '--prune=now'])
|
||||
expect(execFileSync('git', ['-C', root, 'cat-file', '-p', objectId])).toEqual(content)
|
||||
} finally {
|
||||
rmSync(root, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
|
||||
it('fails before a sidecar can reference an unavailable object', () => {
|
||||
const root = mkdtempSync(join(tmpdir(), 'dsh-translation-pairing-'))
|
||||
try {
|
||||
expect(() => storeGitBlob(root, Buffer.from('snapshot'))).toThrow('git hash-object -w --stdin failed')
|
||||
} finally {
|
||||
rmSync(root, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
|
||||
it('fails clearly when Git cannot be started', () => {
|
||||
const previousPath = process.env.PATH
|
||||
try {
|
||||
process.env.PATH = ''
|
||||
expect(() => storeGitBlob('.', Buffer.from('snapshot'))).toThrow('git hash-object -w --stdin failed')
|
||||
} finally {
|
||||
process.env.PATH = previousPath
|
||||
}
|
||||
})
|
||||
|
||||
it.skipIf(!supportsSha256ObjectFormat)('rejects an object format that pairing records cannot represent', () => {
|
||||
const root = mkdtempSync(join(tmpdir(), 'dsh-translation-pairing-'))
|
||||
try {
|
||||
execFileSync('git', ['init', '--quiet', '--object-format=sha256', root])
|
||||
expect(() => storeGitBlob(root, Buffer.from('snapshot'))).toThrow('returned unexpected object ID')
|
||||
} finally {
|
||||
rmSync(root, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
describe('translation pairing manifest', () => {
|
||||
it('accepts an exclusions-only manifest', () => {
|
||||
expect(parseTranslationPairingManifest(JSON.stringify({
|
||||
|
||||
@@ -9,9 +9,9 @@
|
||||
* See `docs/i18n/README.md` for the owning contract.
|
||||
*/
|
||||
|
||||
import { createHash } from 'node:crypto'
|
||||
import { existsSync, globSync, readFileSync, writeFileSync } from 'node:fs'
|
||||
import { basename, join, resolve, sep } from 'node:path'
|
||||
import { gitBlobHash, storeGitBlob } from './translation-pairing-git.ts'
|
||||
import {
|
||||
linksTo,
|
||||
parseTranslationMarkdown,
|
||||
@@ -54,14 +54,6 @@ function isExcluded(file: string): boolean {
|
||||
return manifest.excluded.some(entry => (entry.endsWith('/') ? file.startsWith(entry) : file === entry))
|
||||
}
|
||||
|
||||
/** Full git blob hash (what `git hash-object` prints). */
|
||||
function blobHash(content: Buffer): string {
|
||||
const hash = createHash('sha1')
|
||||
hash.update(`blob ${content.byteLength}\0`)
|
||||
hash.update(content)
|
||||
return hash.digest('hex')
|
||||
}
|
||||
|
||||
/** The three paths of a pair, derived from the English-file path. */
|
||||
function pairPaths(source: string): { zh: string; meta: string } {
|
||||
return { zh: source.replace(/\.md$/, '.zh.md'), meta: source.replace(/\.md$/, '.i18n.yaml') }
|
||||
@@ -148,7 +140,12 @@ if (writeMode) {
|
||||
}
|
||||
continue
|
||||
}
|
||||
const record = renderMeta(source, blobHash(readFileSync(join(root, source))), zh, blobHash(readFileSync(join(root, zh))))
|
||||
const sourceContent = readFileSync(join(root, source))
|
||||
const zhContent = readFileSync(join(root, zh))
|
||||
// A consistency record is also a recovery pointer for the briefing
|
||||
// generator. Persist both snapshots even when the sidecar text is already
|
||||
// current, because the bytes may exist only in this working tree.
|
||||
const record = renderMeta(source, storeGitBlob(root, sourceContent), zh, storeGitBlob(root, zhContent))
|
||||
if (existsSync(join(root, meta)) && readFileSync(join(root, meta), 'utf8') === record) continue
|
||||
writeFileSync(join(root, meta), record)
|
||||
console.log(`verify-translation-pairing: recorded ${meta}`)
|
||||
@@ -203,7 +200,7 @@ for (const source of [...pairAnchors].sort()) {
|
||||
|
||||
let consistent = true
|
||||
for (const [file, content] of [[source, sourceContent], [zh, zhContent]] as const) {
|
||||
const current = blobHash(content)
|
||||
const current = gitBlobHash(content)
|
||||
if (record.get(basename(file)) !== current) {
|
||||
errors.push(`${file}: out of sync — content no longer matches the pair's last confirmed-consistent state in ${meta} (bring the other side along, then re-record with --write)`)
|
||||
consistent = false
|
||||
|
||||
Reference in new issue
Block a user