feat(i18n): unit-mapped briefings with mechanical --apply, adopting the #684 planner mechanics
The briefing now maps each update at the narrowest safely aligned granularity, widening deterministically on mapping failure: a change confined to the pair's byte-identical code fences is computed outright (--apply splices it into the counterpart and validates the result against the pairing gate's structural signature before writing); otherwise changed Markdown units — headings, paragraphs, table rows, list items, fences, block quotes, HTML blocks, thematic breaks, link definitions, matched by container-scoped kind sequences — each carry their last-confirmed source, current source, and current counterpart text; units that do not align fall back to depth-matched heading sections (depth only, so translated heading text still maps); and when sections do not align either, or both sides drifted, the briefing says so and withholds the mapping. Terminology rows now match the changed spans only, English terms on word boundaries with plural inflections, and Chinese-target briefings track each relevant term's document-wide first occurrence — a moved occurrence pulls the vacated and receiving spans into the briefing with an explanatory note. The unit mapping, mechanical code splice, and first-occurrence tracking adopt the planner design from the incremental prompt-pipeline PR (#684), whose provider-backed bake-off independently validated the same scope ladder; this PR carries those mechanics into the agent-facing briefing path so both consumers of the consistency records behave alike. The prior line-hunk section mapping and its heading-text alignment (which could not map cross-language sections) are replaced wholesale. Docs: SKILL.md update path, i18n README pair, development.md pair, and the briefed-updates Agent Note pair brought along; the development.md fence edit was applied with --apply itself, and the prose updates were made through the new unit/section briefings.
This commit is contained in:
Tianyi Cui
@@ -2,45 +2,18 @@
|
||||
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import {
|
||||
changedLinesOfDiff,
|
||||
extractCounterpartSections,
|
||||
headingSections,
|
||||
mapHunksToSections,
|
||||
matchTerminologyRows,
|
||||
parseUnifiedDiffHunks,
|
||||
changedSpanIndices,
|
||||
computeMechanicalUpdate,
|
||||
firstOccurrenceContext,
|
||||
markdownUnits,
|
||||
parseTerminologyRows,
|
||||
relevantTerminologyRows,
|
||||
renderTranslationBrief,
|
||||
sectionSpans,
|
||||
spansAligned,
|
||||
termOffsets,
|
||||
} from './translation-brief.ts'
|
||||
|
||||
const DIFF = [
|
||||
'@@ -3,3 +3,3 @@',
|
||||
' unchanged context',
|
||||
'-The agent loop retries once.',
|
||||
'+The agent loop retries twice.',
|
||||
'@@ -12 +12,2 @@',
|
||||
'+A new sentence about the session log.',
|
||||
].join('\n')
|
||||
|
||||
describe('unified diff parsing', () => {
|
||||
it('reads hunk starts and counts, defaulting count to 1', () => {
|
||||
expect(parseUnifiedDiffHunks(DIFF)).toEqual([
|
||||
{ start: 3, count: 3 },
|
||||
{ start: 12, count: 1 },
|
||||
])
|
||||
})
|
||||
|
||||
it('collects only changed lines, markers stripped', () => {
|
||||
expect(changedLinesOfDiff(DIFF)).toBe([
|
||||
'The agent loop retries once.',
|
||||
'The agent loop retries twice.',
|
||||
'A new sentence about the session log.',
|
||||
].join('\n'))
|
||||
})
|
||||
|
||||
it('ignores file header lines that also start with +/-', () => {
|
||||
expect(changedLinesOfDiff('--- a/foo.md\n+++ b/foo.md\n+added')).toBe('added')
|
||||
})
|
||||
})
|
||||
|
||||
const DOC = [
|
||||
'Preamble line.',
|
||||
'',
|
||||
@@ -52,57 +25,163 @@ const DOC = [
|
||||
'',
|
||||
'First body.',
|
||||
'',
|
||||
'```ts',
|
||||
'const value = 1',
|
||||
'```',
|
||||
'',
|
||||
'## Second',
|
||||
'',
|
||||
'Second body.',
|
||||
'| A | B |',
|
||||
'|---|---|',
|
||||
'| 1 | 2 |',
|
||||
'',
|
||||
'- item one',
|
||||
'- item two',
|
||||
].join('\n')
|
||||
|
||||
describe('section mapping', () => {
|
||||
it('lists headings with lines, depths, and labels', () => {
|
||||
expect(headingSections(DOC)).toEqual([
|
||||
{ line: 3, depth: 1, label: 'Title' },
|
||||
{ line: 7, depth: 2, label: 'First' },
|
||||
{ line: 11, depth: 2, label: 'Second' },
|
||||
describe('markdown spans', () => {
|
||||
it('lists units with container-scoped kinds in document order', () => {
|
||||
const kinds = markdownUnits(DOC).map(span => span.kind)
|
||||
expect(kinds).toEqual([
|
||||
'root.0:paragraph',
|
||||
'root.1:heading:1',
|
||||
'root.2:paragraph',
|
||||
'root.3:heading:2',
|
||||
'root.4:paragraph',
|
||||
'root.5:code',
|
||||
'root.6:heading:2',
|
||||
'root.7.0:tableRow',
|
||||
'root.7.1:tableRow',
|
||||
'root.8.0:listItem',
|
||||
'root.8.1:listItem',
|
||||
])
|
||||
})
|
||||
|
||||
it('maps hunks to the sections they span, including the preamble', () => {
|
||||
const headings = headingSections(DOC)
|
||||
expect(mapHunksToSections([{ start: 1, count: 1 }], headings)).toEqual([0])
|
||||
expect(mapHunksToSections([{ start: 9, count: 1 }], headings)).toEqual([2])
|
||||
expect(mapHunksToSections([{ start: 9, count: 4 }], headings)).toEqual([2, 3])
|
||||
expect(mapHunksToSections([{ start: 0, count: 0 }], headings)).toEqual([0])
|
||||
it('lists heading sections with a preamble span and heading labels', () => {
|
||||
const sections = sectionSpans(DOC)
|
||||
expect(sections.map(span => span.label)).toEqual([
|
||||
'(preamble before the first heading)',
|
||||
'Title',
|
||||
'First',
|
||||
'Second',
|
||||
])
|
||||
expect(sections[0]).toMatchObject({ startLine: 1, endLine: 2 })
|
||||
expect(sections[2]).toMatchObject({ startLine: 7, endLine: 14 })
|
||||
})
|
||||
|
||||
it('extracts counterpart section text with start lines and labels', () => {
|
||||
expect(extractCounterpartSections(DOC, [0, 2])).toEqual([
|
||||
{ label: '(preamble before the first heading)', startLine: 1, text: 'Preamble line.' },
|
||||
{ label: '## First', startLine: 7, text: '## First\n\nFirst body.' },
|
||||
])
|
||||
it('labels units by their node type', () => {
|
||||
const units = markdownUnits(DOC)
|
||||
expect(units[0]!.label).toBe('paragraph')
|
||||
expect(units[1]!.label).toBe('heading')
|
||||
expect(units[7]!.label).toBe('tableRow')
|
||||
})
|
||||
|
||||
it('aligns sections by depth only, so translated heading text still maps', () => {
|
||||
const zh = DOC.replace('## First', '## 第一节').replace('## Second', '## 第二节').replace('# Title', '# 标题')
|
||||
expect(spansAligned(sectionSpans(DOC), sectionSpans(zh))).toBe(true)
|
||||
})
|
||||
|
||||
it('aligns span lists only on equal non-empty kind sequences', () => {
|
||||
const zh = DOC.replace('First body.', '第一段。').replace('item one', '第一项').replace('Intro paragraph.', '导语。')
|
||||
expect(spansAligned(markdownUnits(DOC), markdownUnits(zh))).toBe(true)
|
||||
const reshaped = DOC.replace('- item one\n- item two', 'merged paragraph')
|
||||
expect(spansAligned(markdownUnits(DOC), markdownUnits(reshaped))).toBe(false)
|
||||
expect(spansAligned([], [])).toBe(false)
|
||||
})
|
||||
|
||||
it('reports the indices whose text changed', () => {
|
||||
const edited = DOC.replace('First body.', 'First body, revised.').replace('| 1 | 2 |', '| 1 | 3 |')
|
||||
expect(changedSpanIndices(markdownUnits(DOC), markdownUnits(edited))).toEqual([4, 8])
|
||||
})
|
||||
})
|
||||
|
||||
describe('mechanical code updates', () => {
|
||||
const en = '# T\n\nProse.\n\n```sh\nrun one\n```\n'
|
||||
const zh = '# T\n\n中文。\n\n```sh\nrun one\n```\n'
|
||||
|
||||
it('splices a fence-only edit into the counterpart', () => {
|
||||
const edited = en.replace('run one', 'run two')
|
||||
expect(computeMechanicalUpdate(en, edited, zh)).toBe(zh.replace('run one', 'run two'))
|
||||
})
|
||||
|
||||
it('refuses when prose changed too', () => {
|
||||
const edited = en.replace('Prose.', 'Prose!').replace('run one', 'run two')
|
||||
expect(computeMechanicalUpdate(en, edited, zh)).toBeUndefined()
|
||||
})
|
||||
|
||||
it('refuses when the counterpart fences already diverge from last-confirmed', () => {
|
||||
const edited = en.replace('run one', 'run two')
|
||||
expect(computeMechanicalUpdate(en, edited, zh.replace('run one', 'run stale'))).toBeUndefined()
|
||||
})
|
||||
|
||||
it('refuses when fence counts differ or nothing changed', () => {
|
||||
expect(computeMechanicalUpdate(en, `${en}\n\`\`\`sh\nextra\n\`\`\`\n`, zh)).toBeUndefined()
|
||||
expect(computeMechanicalUpdate(en, en, zh)).toBeUndefined()
|
||||
})
|
||||
})
|
||||
|
||||
const TERMINOLOGY = [
|
||||
'| English | 中文 | 首次出现 | 不要译作 | 备注 |',
|
||||
'|---|---|---|---|---|',
|
||||
'| agent loop | agent loop | agent loop（智能体循环） | | |',
|
||||
'| agent | agent | agent（智能体） | 智能体 | |',
|
||||
'| session log | 会话日志 | | 会话记录 | |',
|
||||
'| gate | 门禁 | | | |',
|
||||
'| registry | 注册表 | | | |',
|
||||
].join('\n')
|
||||
|
||||
describe('terminology matching', () => {
|
||||
it('selects rows whose English term appears on a word boundary', () => {
|
||||
const matches = matchTerminologyRows(TERMINOLOGY, 'The agent loop retries twice.')
|
||||
expect(matches.rows).toEqual(['| agent loop | agent loop | agent loop（智能体循环） | | |'])
|
||||
expect(matches.header).toContain('English')
|
||||
describe('terminology', () => {
|
||||
it('parses data rows and skips the header and separator', () => {
|
||||
const rows = parseTerminologyRows(TERMINOLOGY)
|
||||
expect(rows.map(row => row.english)).toEqual(['agent', 'session log', 'gate', 'registry'])
|
||||
expect(rows[0]).toMatchObject({ chinese: 'agent', first: 'agent（智能体）' })
|
||||
})
|
||||
|
||||
it('selects rows whose Chinese term appears when the source is Chinese', () => {
|
||||
expect(matchTerminologyRows(TERMINOLOGY, '门禁在提交时运行。').rows).toEqual(['| gate | 门禁 | | | |'])
|
||||
it('matches English terms on word boundaries with plural inflections', () => {
|
||||
expect(termOffsets('two agents met', 'agent', true)).toEqual([4])
|
||||
expect(termOffsets('two registries', 'registry', true)).toEqual([4])
|
||||
expect(termOffsets('reagents', 'agent', true)).toEqual([])
|
||||
expect(termOffsets('', 'agent', true)).toEqual([])
|
||||
})
|
||||
|
||||
it('does not match substrings inside larger words', () => {
|
||||
expect(matchTerminologyRows(TERMINOLOGY, 'delegate the work').rows).toEqual([])
|
||||
it('selects rows for the changed text per direction', () => {
|
||||
expect(relevantTerminologyRows(TERMINOLOGY, 'en-to-zh', 'All agents write a session log.').map(row => row.english))
|
||||
.toEqual(['agent', 'session log'])
|
||||
expect(relevantTerminologyRows(TERMINOLOGY, 'zh-to-en', '门禁在提交时运行。').map(row => row.english))
|
||||
.toEqual(['gate'])
|
||||
expect(relevantTerminologyRows(TERMINOLOGY, 'en-to-zh', 'delegate the work')).toEqual([])
|
||||
})
|
||||
})
|
||||
|
||||
describe('first-occurrence tracking', () => {
|
||||
const before = '# T\n\nAlpha paragraph.\n\nThe agent runs.\n'
|
||||
const after = '# T\n\nAlpha paragraph with an agent.\n\nThe agent runs.\n'
|
||||
const rows = parseTerminologyRows(TERMINOLOGY).filter(row => row.english === 'agent')
|
||||
|
||||
it('flags a moved first occurrence and pulls the vacated span in', () => {
|
||||
const context = firstOccurrenceContext(
|
||||
before, after, markdownUnits(before), markdownUnits(after), rows, new Set([1]),
|
||||
)
|
||||
expect(context.notes).toHaveLength(1)
|
||||
expect(context.notes[0]).toContain('moved from #2 to #1')
|
||||
expect(context.extraSpanIndices).toEqual([2])
|
||||
})
|
||||
|
||||
it('stays silent when the first occurrence does not move', () => {
|
||||
const unmoved = before.replace('Alpha paragraph.', 'Alpha paragraph, revised.')
|
||||
const context = firstOccurrenceContext(
|
||||
before, unmoved, markdownUnits(before), markdownUnits(unmoved), rows, new Set([1]),
|
||||
)
|
||||
expect(context.notes).toEqual([])
|
||||
expect(context.extraSpanIndices).toEqual([])
|
||||
})
|
||||
|
||||
it('ignores rows without a first-occurrence rendering', () => {
|
||||
const bare = parseTerminologyRows(TERMINOLOGY).filter(row => row.english === 'gate')
|
||||
const withGate = after.replace('The agent runs.', 'The gate runs.')
|
||||
const context = firstOccurrenceContext(
|
||||
before, withGate, markdownUnits(before), markdownUnits(withGate), bare, new Set([2]),
|
||||
)
|
||||
expect(context.notes).toEqual([])
|
||||
})
|
||||
})
|
||||
|
||||
@@ -111,29 +190,71 @@ describe('brief rendering', () => {
|
||||
sourcePath: 'docs/foo.md',
|
||||
counterpartPath: 'docs/foo.zh.md',
|
||||
direction: 'en-to-zh' as const,
|
||||
diff: DIFF,
|
||||
counterpartSections: [{ label: '## First', startLine: 7, text: '## First\n\n正文。' }],
|
||||
bothDrifted: false,
|
||||
terminology: matchTerminologyRows(TERMINOLOGY, changedLinesOfDiff(DIFF)),
|
||||
diff: '@@ -5 +5 @@\n-old text about the agent\n+new text about the agent',
|
||||
terminology: relevantTerminologyRows(TERMINOLOGY, 'en-to-zh', 'the agent'),
|
||||
}
|
||||
const bundle = {
|
||||
index: 4,
|
||||
label: 'paragraph',
|
||||
confirmedSourceText: 'old text about the agent\n',
|
||||
currentSourceText: 'new text about the agent\n',
|
||||
counterpartText: '关于 agent 的旧文本\n',
|
||||
counterpartStartLine: 9,
|
||||
}
|
||||
|
||||
it('renders diff, aligned sections, terminology, digest, and finish steps', () => {
|
||||
const brief = renderTranslationBrief(base)
|
||||
it('renders unit bundles with three-way context and line anchors', () => {
|
||||
const brief = renderTranslationBrief({
|
||||
...base,
|
||||
scope: { kind: 'units', bundles: [bundle], firstOccurrenceNotes: ['agent: the document-wide first occurrence moved from #2 to #1; the agent（智能体） form moves with it (later occurrences drop the annotation).'] },
|
||||
})
|
||||
expect(brief).toContain('# Translation update briefing: docs/foo.md')
|
||||
expect(brief).toContain('```diff')
|
||||
expect(brief).toContain('docs/foo.zh.md:7')
|
||||
expect(brief).toContain('agent loop（智能体循环）')
|
||||
expect(brief).toContain('| 会话日志 |')
|
||||
expect(brief).toContain('Rules digest')
|
||||
expect(brief).toContain('## Changed units')
|
||||
expect(brief).toContain('### #4 paragraph — counterpart at docs/foo.zh.md:9')
|
||||
expect(brief).toContain('Last-confirmed English:')
|
||||
expect(brief).toContain('Current Chinese (bring this along):')
|
||||
expect(brief).toContain('## First-occurrence notes')
|
||||
expect(brief).toContain('agent（智能体）')
|
||||
expect(brief).toContain('首次出现 annotations attach to the document-wide first occurrence only')
|
||||
expect(brief).toContain('verify-translation-pairing --write docs/foo.md')
|
||||
expect(brief).toContain('smallest edit that covers the diff')
|
||||
})
|
||||
|
||||
it('warns instead of showing sections when both sides drifted', () => {
|
||||
const brief = renderTranslationBrief({ ...base, bothDrifted: true, counterpartSections: undefined })
|
||||
it('marks first-occurrence bundles and omits their unchanged confirmed text', () => {
|
||||
const brief = renderTranslationBrief({
|
||||
...base,
|
||||
scope: {
|
||||
kind: 'units',
|
||||
bundles: [{ ...bundle, reason: 'first-occurrence', confirmedSourceText: bundle.currentSourceText }],
|
||||
firstOccurrenceNotes: [],
|
||||
},
|
||||
})
|
||||
expect(brief).toContain('unchanged; included for a first-occurrence move')
|
||||
expect(brief).not.toContain('Last-confirmed English:')
|
||||
})
|
||||
|
||||
it('renders the mechanical scope with the --apply command', () => {
|
||||
const brief = renderTranslationBrief({ ...base, scope: { kind: 'mechanical' } })
|
||||
expect(brief).toContain('## Mechanical update — no translation judgment involved')
|
||||
expect(brief).toContain('gen-translation-brief --apply docs/foo.md')
|
||||
expect(brief).not.toContain('## Changed units')
|
||||
})
|
||||
|
||||
it('renders the section fallback under its own heading', () => {
|
||||
const brief = renderTranslationBrief({
|
||||
...base,
|
||||
scope: { kind: 'sections', bundles: [bundle], firstOccurrenceNotes: [] },
|
||||
})
|
||||
expect(brief).toContain('## Changed sections')
|
||||
expect(brief).toContain('fine-grained units do not align')
|
||||
})
|
||||
|
||||
it('renders the document fallback with its reason and no bundles', () => {
|
||||
const brief = renderTranslationBrief({
|
||||
...base,
|
||||
scope: { kind: 'document', reason: 'BOTH sides changed since the pair was last confirmed consistent, so no side is a trustworthy mapping anchor; decide which side owns each divergence.' },
|
||||
})
|
||||
expect(brief).toContain('## Whole-document update required')
|
||||
expect(brief).toContain('BOTH sides changed')
|
||||
expect(brief).toContain('locate the regions yourself')
|
||||
expect(brief).not.toContain('docs/foo.zh.md:7')
|
||||
expect(brief).toContain('locate the affected regions yourself')
|
||||
})
|
||||
|
||||
it('renders the English-target digest for zh-to-en updates', () => {
|
||||
@@ -142,15 +263,20 @@ describe('brief rendering', () => {
|
||||
direction: 'zh-to-en',
|
||||
sourcePath: 'docs/foo.zh.md',
|
||||
counterpartPath: 'docs/foo.md',
|
||||
scope: { kind: 'units', bundles: [bundle], firstOccurrenceNotes: [] },
|
||||
})
|
||||
expect(brief).toContain('exactly what the new Chinese states')
|
||||
expect(brief).toContain('verify-translation-pairing --write docs/foo.md')
|
||||
})
|
||||
|
||||
it('grows the section fence past tilde runs in the body', () => {
|
||||
it('grows bundle fences past tilde runs in the text', () => {
|
||||
const brief = renderTranslationBrief({
|
||||
...base,
|
||||
counterpartSections: [{ label: '## First', startLine: 7, text: '~~~~\ninner\n~~~~' }],
|
||||
scope: {
|
||||
kind: 'units',
|
||||
bundles: [{ ...bundle, counterpartText: '~~~~\ninner\n~~~~\n' }],
|
||||
firstOccurrenceNotes: [],
|
||||
},
|
||||
})
|
||||
expect(brief).toContain('~~~~~markdown')
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user