Merge other-review and self-review
This commit is contained in:
iacore
@@ -1,496 +0,0 @@
|
||||
---
|
||||
name: other-review
|
||||
description: Editorial polish for CN→EN Buddhist translations you did NOT translate — voice, flow, readability. Load self-review first for terminology/accuracy.
|
||||
inputs: bilingual.dj (or source.dj + target.dj), or Google Doc
|
||||
outputs: review-comments.dj
|
||||
---
|
||||
|
||||
{% Serves AGENTS.md Workflow B2 (Other-Review) %}
|
||||
|
||||
# Other-Review — Editorial Polish（审他稿）
|
||||
|
||||
Review someone else's CN→EN translation. Focus on voice, flow, readability.
|
||||
You did NOT translate this — suggest, don't command. Load `self-review` first
|
||||
for terminology/accuracy checks.
|
||||
|
||||
Do NOT edit `bilingual.dj` — output to `review-comments.dj` instead.
|
||||
Use `patch` (mode='replace') for any file edits — not regex-replace.
|
||||
|
||||
## Core Principles
|
||||
|
||||
Three principles drive all the specific rules below:
|
||||
|
||||
1. **Reader engagement** — the English should invite the reader in. Use "we," active
|
||||
voice, conversational tone. The original is an interview/dialogue; the translation
|
||||
should sound like one.
|
||||
2. **Simplicity over sophistication** — prefer everyday words over academic ones.
|
||||
If a construction feels heavy, stiff, or formal, simplify it.
|
||||
3. **Source faithfulness** — never add content not in the Chinese, and never drop
|
||||
content that is. But restructure freely for natural English flow — don't mirror
|
||||
Chinese word order when it produces awkward English.
|
||||
|
||||
These patterns were distilled from 473 editor comments across three manuscripts:
|
||||
|
||||
| Document | Comments | Period |
|
||||
|----------|----------|--------|
|
||||
| 61 人生佛教在当代的弘扬 | 121 | 2026-06-19–20 |
|
||||
| 附录 我的判教观 | 151 | 2026-06-13–16 |
|
||||
| 16 觉醒的艺术 | 201 | 2026-04-17–05-24 |
|
||||
|
||||
## Rule Checklist
|
||||
|
||||
Apply these in order. Each rule includes the signal (what to look for) and the fix
|
||||
pattern. Examples are drawn from actual editor comments.
|
||||
|
||||
---
|
||||
|
||||
### R1: Active Voice + "We" Subject
|
||||
|
||||
**Signal**: Passive voice, impersonal "one," "it," abstract subjects.
|
||||
|
||||
**Fix**: Use "we" or a concrete human subject.
|
||||
|
||||
```
|
||||
- "the propagation of Buddhism must move toward modernisation"
|
||||
+ "we must bring Buddhism into the modern age"
|
||||
|
||||
- "it becomes even harder to have an environment for further study"
|
||||
+ "students find it even harder to have a place for further study"
|
||||
|
||||
- "One must further develop the mind of renunciation"
|
||||
+ "We must further develop the mind of renunciation"
|
||||
```
|
||||
|
||||
**Check**: Scan for "one" (as pronoun), passive "be + past-participle," and sentences
|
||||
where the subject is an abstract noun phrase. Replace with "we" + active verb.
|
||||
|
||||
---
|
||||
|
||||
### R2: Noun → Verb Conversion
|
||||
|
||||
**Signal**: Heavy noun phrases where a verb would be lighter and clearer.
|
||||
Especially common with: propagation, promotion, engagement, commercialisation,
|
||||
modernisation, adjustment, continuation, cultivation, development.
|
||||
|
||||
**Fix**: Replace the noun with its verb form. Restructure the sentence around a
|
||||
human subject (usually "we").
|
||||
|
||||
```
|
||||
- "the adjustment of focus in" → delete entirely or rephrase
|
||||
- "for the propagation of the Dharma" → "to spread the Dharma"
|
||||
- "the promotion of Humanistic Buddhism" → "as we actively promote..."
|
||||
- "engagement with the worldly realm" → "it engages with worldly affairs"
|
||||
- "commercialisation" → "society has become increasingly commercialized"
|
||||
- "the continuation of" → "flow"
|
||||
```
|
||||
|
||||
**Check**: Search for `tion of`, `ment of`, `isation of`. Try deleting the phrase
|
||||
first — often the sentence flows fine without it.
|
||||
|
||||
---
|
||||
|
||||
### R3: Simplify Vocabulary
|
||||
|
||||
**Signal**: Formal, academic, or literary words that an everyday reader would trip on.
|
||||
|
||||
**Fix**: Replace with the simplest word that preserves the meaning.
|
||||
|
||||
```
|
||||
Academic → Everyday:
|
||||
"provisions" (资粮) → "spiritual resources" or rephrase
|
||||
"constitutes" → "is" / "forms" / "makes up"
|
||||
"cognizes" → "understands"
|
||||
"transient" → "changing" / "impermanent"
|
||||
"ancestral masters" → "great masters"
|
||||
"eminent monks and great masters" → pick one (redundant)
|
||||
"mode of existence" → "way of living"
|
||||
"the degree of this entrapment" → "how tightly we cling"
|
||||
"corresponding" → "proper" / "solid" or delete
|
||||
"uncritically" → delete (accepting covers it)
|
||||
"sublimated" → simpler word
|
||||
"encompassing" → simpler word
|
||||
"inherently unsustainable" → "they will not last"
|
||||
```
|
||||
|
||||
**Check**: For each sentence, ask: would I say this word in conversation? If not,
|
||||
find the everyday equivalent.
|
||||
|
||||
---
|
||||
|
||||
### R4: Break Long Sentences
|
||||
|
||||
**Signal**: Single sentence with 3+ clauses, especially with lists, parallel
|
||||
structures, or multiple "and"/"while"/"with" connectors.
|
||||
|
||||
**Fix**: Split into 2–3 shorter sentences. Each sentence should convey one idea.
|
||||
|
||||
```
|
||||
Before (one sentence):
|
||||
"Influenced by society, many within the Buddhist community have also become
|
||||
enthusiastic about power and economic gain, treating tourism and ritual services
|
||||
as the main focus programme of temples, while neglecting their proper
|
||||
responsibility of carrying on the Buddha's mission."
|
||||
|
||||
After (two sentences):
|
||||
"Influenced by society, some in the Buddhist community have also become
|
||||
enthusiastic about power and money. They make tourism and ritual services the
|
||||
main focus of temple activities, while neglecting their true duty to carry on
|
||||
the Buddha's mission."
|
||||
```
|
||||
|
||||
**Check**: Count clauses. If >2, consider splitting. Especially split:
|
||||
- When a list starts mid-sentence
|
||||
- When "while" / "with" introduces a new subject
|
||||
- When a long parenthetical could stand alone
|
||||
|
||||
---
|
||||
|
||||
### R5: Remove Unnecessary Words
|
||||
|
||||
**Signal**: Modifiers that don't add meaning, filler words, redundant pairs.
|
||||
|
||||
**Fix**: Delete them. The sentence should stand without them.
|
||||
|
||||
```
|
||||
Common deletions:
|
||||
"so-called" — almost always deletable
|
||||
"generally" — deletable unless making a specific contrast
|
||||
"phenomenon" — "this phenomenon" → "this"
|
||||
"fundamentally" — deletable
|
||||
"necessarily" — deletable
|
||||
"solely" — deletable
|
||||
"briefly summarise" — "briefly" is redundant with "summarise"
|
||||
"and influenced" — deletable
|
||||
"the practice of" — often deletable
|
||||
"The development of"— often deletable
|
||||
"and investigating" — if already "studying," drop
|
||||
"practical" (in "practical methods") — "methods" alone covers it
|
||||
```
|
||||
|
||||
**Check**: For each word: does removing it change the meaning? If not, remove it.
|
||||
|
||||
---
|
||||
|
||||
### R6: Conversational / Interview Tone
|
||||
|
||||
**Signal**: Formal register, stiff constructions, academic phrasing in a dialogue
|
||||
context. The Chinese originals are interviews; the English should read as spoken word.
|
||||
|
||||
**Fix**: Imagine you're saying it aloud. Adjust accordingly.
|
||||
|
||||
```
|
||||
Formal → Conversational:
|
||||
"What do you think is the → "Why do you think that is?"
|
||||
reason for this?"
|
||||
"outdated" → "old-fashioned" (in spoken context)
|
||||
"It is summarised in the → Use direct speech
|
||||
famous expression: ..."
|
||||
"the common point of the → "what all these issues have
|
||||
above-mentioned issues" in common"
|
||||
"From the perspective of → "Looking at Buddhist history,"
|
||||
Buddhist history,"
|
||||
"besides remaining grounded → "In the modernisation of Buddhism,
|
||||
in the principle of adapting while we must stay true to..."
|
||||
both to Buddhist teachings
|
||||
and to the needs of the people"
|
||||
```
|
||||
|
||||
**Check**: Read the passage aloud (mentally). Does it flow like speech? If it feels
|
||||
like a lecture transcript, lighten it.
|
||||
|
||||
---
|
||||
|
||||
### R7: No -ly Adverbs
|
||||
|
||||
**Signal**: Adverbs ending in -ly.
|
||||
|
||||
**Fix**: Delete them, or restructure to avoid them. Modern English style avoids
|
||||
adverb clutter.
|
||||
|
||||
```
|
||||
- "briefly summarise" → "summarise"
|
||||
- "fundamentally new" → "new"
|
||||
- "truly able to" → "able to"
|
||||
- "extremely limited" → "very small number" (restructure)
|
||||
- "gradually established" → "established" (ok in context)
|
||||
```
|
||||
|
||||
**Check**: Search for `\w+ly\b`. Evaluate each — most can be dropped.
|
||||
|
||||
---
|
||||
|
||||
### R8: Concrete over Abstract
|
||||
|
||||
**Signal**: Abstract noun phrases that could be expressed more directly.
|
||||
|
||||
**Fix**: Make the idea concrete. Use examples, metaphors, or simpler terms.
|
||||
|
||||
```
|
||||
Abstract → Concrete:
|
||||
"the mistaken identification → "the mistaken belief in a fixed
|
||||
and attachment to the self" self and our clinging to it"
|
||||
"corresponding mental functions" → "the mindset that aligns with them"
|
||||
"discern the universal sequence → "understand how the teachings
|
||||
from shallow to deep" progress from basic to advanced"
|
||||
"mode of existence centered → "a life centered on the Three Jewels"
|
||||
on the Three Jewels"
|
||||
"a field of specialisation" → delete (unnecessary abstraction)
|
||||
"ideological content" → "ideas"
|
||||
```
|
||||
|
||||
**Check**: If a noun phrase has 3+ words and feels like jargon, find a plainer way.
|
||||
|
||||
---
|
||||
|
||||
### R9: Terminology Alignment
|
||||
|
||||
**Signal**: Terms that have established translations in the MPI terms database or
|
||||
prior publications (坐看云起, etc.).
|
||||
|
||||
**Fix**: Use the established translation. Load `terms-search` skill and check:
|
||||
`python3 $MPI_PROJECT_ROOT/terms-search/search.py <term>`
|
||||
|
||||
```
|
||||
Key distinctions from the 3 manuscripts:
|
||||
人生佛教 → "Buddhism of Human Life" (NOT "Humanistic Buddhism")
|
||||
人间佛教 → "Humanistic Buddhism"
|
||||
禅宗 → "Chan" (not "Zen")
|
||||
根机 → "faculties" (not "dispositions", not "root")
|
||||
高僧大德 → pick one: "eminent monks" or "great masters" (not both)
|
||||
假 (三性) → "false" (from emptiness perspective)
|
||||
monks → "monastics" (includes both monks and nuns — 含比丘比丘尼)
|
||||
惑业苦 → "delusion, karma, and suffering" (logical order preserved)
|
||||
出世乐 → keep consistent with "supreme bliss of Nirvana" used earlier
|
||||
戒体 → don't use "precept essence" (hard to understand); expand to
|
||||
"the mind of upholding the precepts"
|
||||
```
|
||||
|
||||
**Check**: For any Buddhist technical term, verify against the terms DB before
|
||||
using a new translation. Consistency across manuscripts matters.
|
||||
|
||||
---
|
||||
|
||||
### R10: Missing Content Detection
|
||||
|
||||
**Signal**: Chinese paragraph has multiple clauses/ideas, but English stops after
|
||||
1–2 sentences. Quoted speech, poems, rhetorical climaxes in CN are absent from EN.
|
||||
|
||||
**Fix**: Flag as "Missing Content." Translate the missing portion.
|
||||
|
||||
```
|
||||
Common patterns:
|
||||
- 中文有4-5个短句，英文只有1-2句 → 漏翻了
|
||||
- CN has a paragraph with quoted speech → EN paragraph ends before the quote
|
||||
- 一些具有相当成就的前辈高僧... → entire passage skipped
|
||||
- 内修与外弘也是同样... → entire paragraph missing
|
||||
- 民众在接受教育期间，无法从教科书上对佛教获得正面了解 → line missing
|
||||
```
|
||||
|
||||
**Check**: Compare CN and EN paragraph lengths. If CN is substantially longer but
|
||||
EN seems complete, re-read the CN carefully — something was likely dropped.
|
||||
|
||||
---
|
||||
|
||||
### R11: Source Faithfulness
|
||||
|
||||
**Signal**: English adds concepts, metaphors, or explanations not present in the
|
||||
Chinese. Or English drops specific details that the Chinese includes.
|
||||
|
||||
**Fix**: Remove additions. Translate dropped content. But restructure freely for
|
||||
natural English — don't mirror Chinese word order if it produces awkward results.
|
||||
|
||||
```
|
||||
Additions to remove:
|
||||
- "this addresses one of the most fundamental philosophical questions"
|
||||
(not in CN → delete)
|
||||
- "preserving the potential for future expression" (not in CN → delete)
|
||||
- "making this school widely known in China" (not in CN → delete)
|
||||
|
||||
Things to preserve:
|
||||
- Quoted speech, idioms, and rhetorical questions — translate fully
|
||||
- Logical connectors between sentences — don't skip them
|
||||
- The speaker's distinctive voice and argument structure
|
||||
- 讲法风格 — the master's teaching style should come through
|
||||
```
|
||||
|
||||
**Check**: For each paragraph, ask: is there content in EN that has no basis in CN?
|
||||
Is there content in CN that has no corresponding EN? Fix both.
|
||||
|
||||
---
|
||||
|
||||
### R12: Sentence Structure Clarity
|
||||
|
||||
**Signal**: English reads as "translationese" — word order follows Chinese,
|
||||
parallel structures are misaligned, logical flow is broken.
|
||||
|
||||
**Fix**: Restructure for natural English. Reorder clauses. Align parallel items.
|
||||
|
||||
```
|
||||
- "Despite different methods, your focus has always been Humanistic Buddhism"
|
||||
→ "Although the methods vary, they all center on Humanistic Buddhism"
|
||||
(methods vs. focus — misaligned comparison)
|
||||
|
||||
- "the root cannot be established"
|
||||
→ "we cannot establish the root" (add human subject)
|
||||
|
||||
- Lists: keep verb forms parallel
|
||||
"First, focus on building... Second, keep liberation at the center...
|
||||
Third, highlight the unique spirit..."
|
||||
(imperative verbs aligned)
|
||||
```
|
||||
|
||||
**Check**: Read each sentence and ask: would a native English speaker structure it
|
||||
this way? If not, reorder.
|
||||
|
||||
---
|
||||
|
||||
### R13: Specific Word Fixes
|
||||
|
||||
**Signal**: Certain English words have wrong connotations for the context.
|
||||
|
||||
**Fix**: Use the recommended replacement.
|
||||
|
||||
```
|
||||
"comeback" → "return" (comeback = return to popularity, not return to roots)
|
||||
"evokes" → "brings" / "gives rise to" (evokes is too formal)
|
||||
"entertain" → "have" (entertain thoughts → have thoughts)
|
||||
"falls" → "fades" (faith falls → faith fades)
|
||||
"reverse" → "transform" (gentler)
|
||||
"escape" → softer word in context
|
||||
"dismantle" → "challenges" / "undoes" (dismantle is too aggressive)
|
||||
"head" → "beginning" (head of the Eightfold Path → beginning)
|
||||
"none" → "not many" (when the claim is "未提供多少" not "none at all")
|
||||
"function" → "purpose" (in non-technical contexts)
|
||||
"object" → "focus" (object of practice → focus of practice)
|
||||
"uncommon" → "unique" / "distinctive" (不共 = not shared with other paths)
|
||||
"conduct and propagate" → "uphold and spread"
|
||||
"attainment of Buddhahood" → "enlightenment" (in some contexts, to avoid
|
||||
Buddha/Buddhahood repetition)
|
||||
"liberation" → "liberation" is fine, but check if context means "解脱" or "出世"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### R14: Positive Feedback — Praise the Translator (随喜)
|
||||
|
||||
**Signal**: A passage reads well — accurate, natural, fluent. Or the translation
|
||||
as a whole shows consistent quality.
|
||||
|
||||
**Action**: Praise the first-pass translator by name. The editor consistently opens
|
||||
or closes review sections with affirmations directed at the translator:
|
||||
|
||||
```
|
||||
"随喜师兄整体翻译还是很好的，前后连贯，清晰"
|
||||
"随喜师兄翻译 准确流畅！"
|
||||
"随喜师兄上段和本段翻译 准确流畅"
|
||||
"随喜师兄查证出处"
|
||||
"整段翻译的很好"
|
||||
"整段翻译还是很棒的"
|
||||
"翻译一气呵成 很精彩"
|
||||
"很赞叹 简洁有力！"
|
||||
"这个功不唐捐翻译的真好"
|
||||
"随喜这个翻译！衔接的很好"
|
||||
"这个翻译很赞！"
|
||||
"这段翻译也很好"
|
||||
"整段翻译的还是很好的"
|
||||
"翻译的意思都表达出来了"
|
||||
"本段翻译的都很好，随喜赞叹！"
|
||||
```
|
||||
|
||||
This matters for three reasons:
|
||||
1. It tells the translator what to preserve — don't accidentally "fix" what works
|
||||
2. It follows the deliberation protocol — rejoicing (随喜) comes first, before
|
||||
any criticism. The translator should feel their effort is seen and valued
|
||||
3. It names the translator explicitly — "随喜师兄" — making the praise personal,
|
||||
not generic. When reviewing, use the translator's name from the document title
|
||||
(e.g. from the document title)
|
||||
|
||||
## Workflow
|
||||
|
||||
Two output modes depending on target format:
|
||||
|
||||
### Mode A: .dj file review (use `patch`)
|
||||
|
||||
```
|
||||
1. Read source.dj + target.dj (full files)
|
||||
2. Apply R1–R13 in order, scanning the English line by line
|
||||
3. For each issue found, apply with patch or write to translation-findings.dj
|
||||
4. Note well-translated passages (R14)
|
||||
5. Final pass: read the full English aloud — does it flow?
|
||||
```
|
||||
|
||||
### Mode B: Google Docs review (output to review-comments.dj)
|
||||
|
||||
Use when the translation manuscript is a Google Doc and you must add comments
|
||||
without editing the original text. The agent reads the document, produces a
|
||||
comment file, and the user manually inserts comments into the Google Doc.
|
||||
|
||||
**Why manual insertion is required**: The Google Drive API `comments.create`
|
||||
with an `anchor` field is silently ignored by Google Docs editor apps. The
|
||||
kix anchor format used by the Google Docs UI is an undocumented internal
|
||||
format that has never been reverse-engineered. Line-based anchors
|
||||
(`{"region": {"kind": "drive#commentRegion", "line": N, "rev": "head"}}`)
|
||||
also do not display as anchored in the Google Docs UI. This is a known
|
||||
limitation since 2016 with no resolution. The only reliable way to add
|
||||
anchored comments is through the browser UI (select text → Insert → Comment).
|
||||
|
||||
**Workflow**:
|
||||
|
||||
```
|
||||
1. Load google-workspace skill (ensure OAuth is set up)
|
||||
2. Read the Google Doc body via Docs API: documents.get
|
||||
3. Read existing comments via Drive API: comments.list (paginate fully)
|
||||
4. Identify the translator from the document title (e.g., "maple 初翻")
|
||||
5. Review per R1–R14, scanning the English paragraphs
|
||||
6. For each issue, extract the EXACT quoted text from the document:
|
||||
- Use the full document body to find the precise, case-exact string
|
||||
- Each quoted snippet must be UNIQUE — long enough to find with Ctrl+F
|
||||
(at minimum 10+ words or a complete short sentence)
|
||||
- Test: can you find exactly one match when searching the document?
|
||||
7. Write review-comments.dj to the article directory:
|
||||
$MPI_PROJECT_ROOT/translate-files/<article>/review-comments.dj
|
||||
8. Format each entry:
|
||||
Quoted text: `<exact text from document>`
|
||||
<comment content>
|
||||
9. Tell the user: "Comments written to <path>. For each, select the quoted
|
||||
text in the Google Doc → Insert → Comment → paste the content."
|
||||
```
|
||||
|
||||
**Quoted text rules** (critical — the user must be able to find the text):
|
||||
- Must match the document text EXACTLY: same case, same punctuation,
|
||||
same whitespace (including non-breaking spaces like `\xa0`)
|
||||
- Must be UNIQUE within the document — verify by searching the full body
|
||||
- Must be long enough to disambiguate: prefer a full short sentence or a
|
||||
10+ word phrase over single words like "Consequently"
|
||||
- Capitalize as it appears in the source. If the source has
|
||||
"Consequently, while countless...", quote that, not "consequently"
|
||||
|
||||
**Example output format**:
|
||||
|
||||
```
|
||||
## 10. Conversational Tone (R6)
|
||||
|
||||
Quoted text: `even discarded. Consequently, while countless companies emerged, they collapsed just as quickly.`
|
||||
|
||||
整体语气适合对话场景。个别词可以更口语化：'Consequently' → 'So'...
|
||||
```
|
||||
|
||||
## Pitfalls
|
||||
|
||||
- Don't apply this skill before `self-review` — terminology must be correct first.
|
||||
- Don't over-correct: some formal constructions are appropriate for certain passages.
|
||||
Judge per context.
|
||||
- When converting nouns to verbs, keep the meaning intact — don't simplify away
|
||||
doctrinal nuance.
|
||||
- The "we" subject is generally preferred but not absolute. If a passage describes
|
||||
a general principle without a specific agent, passive/impersonal may be correct.
|
||||
- Positive feedback (R14) is not optional fluff — it guides what to preserve.
|
||||
- **Google Docs anchor limitation**: The Drive API cannot create anchored comments
|
||||
on Google Docs. Use Mode B (output to review-comments.dj) for Google Doc targets.
|
||||
The user manually inserts comments in the browser UI. See the journey log at
|
||||
`references/google-docs-comment-journey.dj` for full details.
|
||||
- **Quoted text must be exact and unique**: when writing review-comments.dj, each
|
||||
quoted snippet must match the document text case-exactly and be long enough to
|
||||
find unambiguously with Ctrl+F. Short words like "consequently" are unacceptable
|
||||
— quote the full sentence or a 10+ word phrase.
|
||||
- **Mine review comments for reusable patterns**: when a review-comments.dj is produced, scan it for recurring calques and Buddhist term register issues and add them to `../self-review/references/translation-pitfalls.md` and `../self-review/references/buddhist-terminology.md`. The *人生百问* review produced a reusable pattern library — follow that example.
|
||||
@@ -1,252 +0,0 @@
|
||||
---
|
||||
name: self-review
|
||||
description: Review your own CN→EN translations — three-pass review (terminology → mechanical → flow). Edit commented.dj with patch. For reviewing someone else's work, load other-review.
|
||||
inputs: bilingual.dj, or CSV/XLSX (Chinese + English columns)
|
||||
outputs: commented.dj, translation-findings.dj (optional)
|
||||
---
|
||||
|
||||
{% Serves AGENTS.md Workflow B1 (Self-Review) %}
|
||||
|
||||
# Self-Review（自审）
|
||||
|
||||
Review YOUR OWN translations. You created the English — you can edit freely.
|
||||
For reviewing someone else's work, load `other-review` instead.
|
||||
|
||||
Two input formats: CSV/XLSX batch, or `.dj` comparison file.
|
||||
|
||||
`bilingual.dj` is script-generated ground truth — **never edit it.**
|
||||
Copy to `commented.dj` for all review work. Always use `patch` (mode='replace')
|
||||
for edits — not regex-based string replacement in `execute_code`.
|
||||
|
||||
## Workflow A: CSV/XLSX batch review
|
||||
|
||||
Use when input is a CSV/XLSX with `Chinese`/`English` columns. Produces an `edit-suggestions.dj` file.
|
||||
|
||||
### 1. Get the data into CSV
|
||||
|
||||
If XLSX, export to CSV (or use `openpyxl`). CSV is faster.
|
||||
|
||||
### 2. Read the full file
|
||||
|
||||
Use `read_file` with offsets for complete coverage. Don't sample.
|
||||
|
||||
### 3. Write a systematic analysis script
|
||||
|
||||
Write to `/tmp/script.py`, run with `python3 /tmp/script.py`. No heredocs or `-c`.
|
||||
The script should:
|
||||
- Parse CSV with `csv.DictReader`
|
||||
- Apply detection rules per category
|
||||
- Collect issues: row number, CN text, EN text, problem, suggested fix
|
||||
- Group/deduplicate identical issues
|
||||
|
||||
Common detection categories:
|
||||
- **Buddhist terminology**: 正念→mindfulness (not "righteous thoughts"), 布施→generosity (not "alms")
|
||||
- **Identity terms**: 学士/修士/胜士/智士 are practice stages, not titles
|
||||
- **Literal machine translations**: "hard drive" for 硬盘 (endurance)
|
||||
- **四摄法 terms**: 同事→"acting in harmony", 爱语→"kind speech"
|
||||
- **Grammar**: subject-verb agreement, unbalanced quotes
|
||||
- **Typos/formatting**: Chinese punctuation in English, "IOS"→"iOS"
|
||||
- **Inconsistency**: same CN term translated differently across rows
|
||||
|
||||
### 4. Write edit-suggestions.dj
|
||||
|
||||
Format:
|
||||
```
|
||||
# 1
|
||||
|
||||
original: <Chinese text or key term>
|
||||
translated: <current English>
|
||||
|
||||
<Explanation and suggested fix.>
|
||||
|
||||
# 2
|
||||
...
|
||||
```
|
||||
|
||||
One entry per problem category, not per row. Mention affected row numbers.
|
||||
|
||||
## Workflow B: .dj file review (self-review)
|
||||
|
||||
Use when you translated the text and want to review your own work.
|
||||
|
||||
### File rules
|
||||
|
||||
1. `bilingual.dj` — extracted from script. **Never edit.**
|
||||
2. `cp bilingual.dj commented.dj` — all edits go here
|
||||
3. `{% ... %}` comments document non-obvious translation choices
|
||||
|
||||
### 1. Read the full file
|
||||
|
||||
Use `read_file` with `offset` and `limit` for full coverage of large files
|
||||
(this session had 322 lines, 93KB). For files >200 lines, paginate
|
||||
explicitly rather than reading the whole thing at once.
|
||||
|
||||
If you have already read part of the file with `read_file` earlier in the
|
||||
session, use `terminal: cat` (or `sed -n 'A,Bp'`) to get an un-deduped view
|
||||
of the rest. `read_file` deduplicates within a session.
|
||||
|
||||
### 2. Scan for problems — three passes, in order
|
||||
|
||||
The review is best done in three distinct passes, each catching a different
|
||||
category of error. Don't try to catch everything in one scan.
|
||||
|
||||
**Pass 1 — terminology + consistency + line count** (fast, mechanical):
|
||||
- **Line count**: source and target must match exactly. Mismatch means paragraphs were dropped, merged, or split.
|
||||
- Same CN term translated differently across the file (e.g. 人生佛教/人间佛教 conflation, 恨→resentment, 修行/修学)
|
||||
- Buddhist terminology against the MPI terms DB (see terms-db-alignment below)
|
||||
- Mistranslation of key terms, wrong proper names, garbled text
|
||||
- Mid-paragraph truncation: CN covers 3–5 clauses but EN stops after 1–2 sentences. Signal: CN has quoted speech, poems, or a rhetorical climax absent from EN. Flag as "Missing Content" not "Incomplete."
|
||||
- Use `references/common-issues-taxonomy.md` as a structured checklist for accuracy issues
|
||||
|
||||
**Pass 2 — mechanical/formatting** (also mechanical, but easy to skip):
|
||||
- TOC format: AGENTS.md says TOC must be plain bullet list, no link targets. Strip `[I. Heading](#...)` markdown links if present.
|
||||
- Double words, double punctuation, capitalisation typos, processing artifacts, stray spacing in Chinese text
|
||||
- Numbering mismatches between CN and EN headings
|
||||
- Redundant English calques: when the target mirrors a Chinese grammar pattern literally, it can read as a typo (e.g. "mind of death-mindfulness" for 念死之心 — should be "mindfulness of death"). Clunky idioms: 一念之差 → "a single thought of difference" is unidiomatic. Standard renderings exist (e.g. "a single errant thought," "a moment's carelessness," or rephrase as "a single thought can make all the difference").
|
||||
|
||||
**Pass 3 — flow/tonal/calques** (read the whole English as prose):
|
||||
- Re-read the full English target. Does it hang together as prose, or does it read as "translationese"?
|
||||
- Dramatic verbs that are calques of Chinese: "draw forth," "into full play," "shoulder," "look to with hope." See `references/translation-pitfalls.md` for the full calque checklist.
|
||||
- New: review the *人生百问* pattern tables in `translation-pitfalls.md` for stiff calques ("keen on," "wisdom culture," "more ultimate," "choice difficulty," "serve as reference") and idiom renderings ("tree wishing stillness," "straddling two boats").
|
||||
- Subject-shift calques: English substitutes a concrete agent (practitioners, people) for an abstract system noun (Buddhism, religion) — see pitfalls.
|
||||
- Factual inconsistencies across paired descriptions of the same person/place/thing.
|
||||
- Tonal coherence inside parallel lists: verb choice should be identical across First/Second/Third items.
|
||||
- Intensifier drift: same intensifier ("profoundly important") used 3+ times in one section reads as over-translation.
|
||||
- The user may explicitly request this pass ("are the words together nicely?", "does it read well?"). Treat such prompts as a signal to do the full re-read, not just spot-check.
|
||||
|
||||
**Terms database drift** (cross-cutting — apply during Pass 1):
|
||||
- Cross-reference glossary terms against the MPI terms database
|
||||
- CLI preferred: `python3 $MPI_PROJECT_ROOT/terms-search/search.py <query>`. For a review, batch many queries in one `execute_code` script (subprocess loop) — one terminal call per term is slow and noisy.
|
||||
- Source priority: DoT定稿 > 内部特色词 > 佛教术语 > 经论名
|
||||
- Fix both glossary comments AND body text
|
||||
- See `references/terms-db-alignment.md` for batch-lookup patterns
|
||||
|
||||
### 3. Dump findings
|
||||
|
||||
Write to `translation-findings.dj` for issues that don't fit as inline fixes:
|
||||
|
||||
```
|
||||
Finding N — Title (line numbers)
|
||||
Chinese: ...
|
||||
English: ...
|
||||
Issue: description
|
||||
```
|
||||
|
||||
### 4. Apply fixes with `patch`
|
||||
|
||||
Surgical string replacement in `commented.dj` with `patch` (mode='replace').
|
||||
Never use regex-based string replacement in `execute_code` for .dj edits.
|
||||
`patch` is safer, surfaces conflicts, and produces a reviewable diff.
|
||||
Verify with `cat` — never rely on `read_file` (session dedup).
|
||||
|
||||
### 5. Add inline edit suggestions
|
||||
|
||||
Copy `bilingual.dj` → `commented.dj`, then apply inline corrections + `{% %}` comments.
|
||||
|
||||
### 6. Final sweep
|
||||
|
||||
Run `python3 scripts/sweep.py <source.dj> <target.dj> [--stale term1,term2] [--new term1,term2]`. This runs all mechanical checks in one call: line parity, heading parity, Unicode em/en-dashes, Markdown bold, Chinese punctuation, TOC link artifacts, unbalanced quotes, and stale/new term assertions. Run even when no content patches were needed — it serves as final validation.
|
||||
|
||||
## Buddhist terminology reference
|
||||
|
||||
See `references/buddhist-terminology.md` for Chinese-English term mappings and common pitfalls.
|
||||
|
||||
## Workflow C: Typeset proofread (DOCX manuscript vs PDF layout)
|
||||
|
||||
Use when the user gives a manuscript DOCX and a typeset PDF and asks to proofread.
|
||||
Goal: catch typesetting errors (missing text, typos, wrong special characters, bad line
|
||||
breaks), not translation quality.
|
||||
|
||||
### 0. Clarify scope FIRST
|
||||
|
||||
Before any extraction: ask what they want checked. "Proofread" can mean:
|
||||
- Text accuracy (missing/doubled words, typos introduced by typesetter)
|
||||
- Special characters (quotes, dashes, ellipses)
|
||||
- Formatting (page numbers, headers, TOC layout)
|
||||
- All of the above
|
||||
|
||||
Do not run extraction pipelines until scope is clear.
|
||||
|
||||
### 1. Extract text
|
||||
|
||||
- DOCX → plain: `pandoc file.docx -f docx -t plain --wrap=none`
|
||||
- PDF → plain: `pdftotext -layout file.pdf` (preserves positional info)
|
||||
|
||||
### 2. Clean PDF artifacts
|
||||
|
||||
- Strip InDesign slug lines, page headers, page numbers
|
||||
- Join hyphenated line breaks (line ending `-` + next line starting lowercase)
|
||||
- Fix drop-cap artifacts (e.g. `L iving` → `Living`)
|
||||
|
||||
### 3. Compare
|
||||
|
||||
- Extract English paragraphs from DOCX (skip Chinese lines, match blank-line pattern)
|
||||
- Check each DOCX paragraph exists as substring in PDF body text
|
||||
- Flag paragraphs not found; investigate each (may be heading renumbering, not missing)
|
||||
|
||||
### Pitfalls specific to this workflow
|
||||
|
||||
- **PDF paragraph joining is lossy** — page breaks split paragraphs. Don't expect
|
||||
perfect paragraph matching; check content coverage, not paragraph identity.
|
||||
- **Heading numbering differs** — DOCX has `1.`, `(1)`; PDF has `I`, `1)`. Ignore
|
||||
heading-only differences.
|
||||
- **InDesign PDFs insert extra spaces** around drop caps and special characters.
|
||||
Normalize multi-space to single space before comparison.
|
||||
|
||||
### Pitfalls
|
||||
|
||||
- **Never edit `bilingual.dj`** — it's script-generated ground truth. Copy to `commented.dj` first.
|
||||
- **Use `patch`, not regex** — for all `.dj` edits. `patch` surfaces conflicts and produces diffs.
|
||||
- **`commented.dj` comments must not split paragraphs** — always place `{% %}` after the FULL EN paragraph, not mid-sentence. Scan for merged comments after insertions and split them. Collapse triple+ blank lines created by comment insertions.
|
||||
- **Clarify scope before diving into extraction pipelines** — if the user says
|
||||
"proofread this" or "校对这篇文章", ask what specifically they want checked
|
||||
before running pandoc/pdftotext. Getting interrupted mid-pipeline wastes
|
||||
context.
|
||||
- **Don't use heredocs or `-c`** — write to `/tmp/script.py` first
|
||||
- **Deduplicate aggressively** — group by problem type, not per-row
|
||||
- **Buddhist terminology is technical** — don't guess. When uncertain, flag for review
|
||||
- **Never delete .dj comparison files** — intentional work artifacts
|
||||
- **Verify patches with `cat`** — `read_file` dedup makes it unreliable
|
||||
- **Re-read before fixing** — user may have made interim edits
|
||||
- **Batch terminology lookups** — when checking many terms against the terms DB, run them in one `execute_code` script that loops over a query list and calls `search.py` via `subprocess.run`. One terminal call per term floods the context with repetitive output.
|
||||
- **Mine review comments for patterns** — when a `review-comments.dj` is produced, scan it for recurring calques and term choices and add them to `references/translation-pitfalls.md` and `references/buddhist-terminology.md` so the skill improves with each review.
|
||||
|
||||
## Human Review Protocol (审议)
|
||||
|
||||
When giving feedback to human translators — whether in a review team or as an AI
|
||||
assistant flagging issues — follow the Oriental Translation Workshop protocol.
|
||||
See `references/deliberation-protocol.md` for full guidance.
|
||||
|
||||
Key points:
|
||||
- **Rejoice first** (随喜): affirm what works before flagging issues
|
||||
- **Three-tier issues**: Level 1 (spelling/grammar/format) — fix directly. Level 2
|
||||
(omission/mistranslation/wordiness) — suggest or fix with tracked changes. Level 3
|
||||
(citation versions / marginal wording) — discuss with translator
|
||||
- **Tone**: questions, not commands; collaborative inquiry, not correction
|
||||
- **Address translator as 菩萨** (Bodhisattva) — respectful peer
|
||||
|
||||
## Common Issues Taxonomy
|
||||
|
||||
Use `references/common-issues-taxonomy.md` as a structured checklist when reviewing.
|
||||
Categories:
|
||||
|
||||
- **Accuracy**: omission, mistranslation (over-free, over-literal, misunderstanding,
|
||||
wrong word choice), overtranslation, terminology errors
|
||||
- **Readability**: redundancy (long sentences, passive voice, nominalization),
|
||||
poor structure (top-heavy sentences), wrong register, weak transitions
|
||||
|
||||
## References
|
||||
|
||||
- `references/buddhist-terminology.md` — Chinese-English Buddhist term mappings and pitfalls
|
||||
- `references/terms-db-alignment.md` — Batch-aligning glossary terms against the MPI terms database
|
||||
- `references/translation-pitfalls.md` — Recurring CN→EN mistranslation patterns (关爱→compassion, 生生增上, etc.)
|
||||
- `references/proofreading-patterns.md` — DOCX/PDF extraction techniques, block-based pairing, common manuscript issues
|
||||
- `references/docx-md-extraction.md` — Extracting `.docx.md` (pandoc markdown) to bilingual, TOC guards, CN/EN boundary regex
|
||||
- `references/edit-suggestions-in-bilingual.md` — Inline edit suggestions + `{% %}` comments, two-file comparison (commented.dj / bilingual.dj)
|
||||
- `references/deliberation-protocol.md` — Oriental Translation Workshop review protocol: tiers, rejoicing, tone
|
||||
- `references/common-issues-taxonomy.md` — Structured taxonomy of accuracy and readability issues with examples
|
||||
|
||||
## Scripts
|
||||
|
||||
- `scripts/sweep.py` — Mechanical validation sweep for completed reviews
|
||||
- `scripts/review_csv.py` — Batch CSV/XLSX translation review
|
||||
@@ -1,78 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Reference: reusable detection rules for Chinese→English translation review.
|
||||
Adapt the rules list for each project's domain vocabulary."""
|
||||
|
||||
import csv, re, sys
|
||||
|
||||
def review_csv(csv_path):
|
||||
rows = []
|
||||
with open(csv_path) as f:
|
||||
reader = csv.DictReader(f)
|
||||
for r in reader:
|
||||
rows.append((r.get('page', '') or '', r['Chinese'] or '', r['English'] or ''))
|
||||
|
||||
issues = []
|
||||
|
||||
def add(row_idx, cn, en, problem, suggestion):
|
||||
issues.append({
|
||||
'row': row_idx + 2,
|
||||
'page': rows[row_idx][0],
|
||||
'cn': cn, 'en': en,
|
||||
'problem': problem,
|
||||
'suggestion': suggestion
|
||||
})
|
||||
|
||||
for i, (page, cn, en) in enumerate(rows):
|
||||
if not cn or not en:
|
||||
continue
|
||||
|
||||
# ── Add project-specific detection rules below ──
|
||||
|
||||
# Example: "Is we" → machine translation artifact
|
||||
if re.search(r'\bIs we\b', en):
|
||||
add(i, cn, en,
|
||||
"'Is we' — literal MT of 是否/如果. Should be 'if we' or 'whether we'",
|
||||
re.sub(r'\bIs we\b', 'if we', en))
|
||||
|
||||
# Example: Chinese punctuation in English text
|
||||
if re.search(r'[，。；：！？、]', en):
|
||||
add(i, cn, en,
|
||||
"Chinese punctuation in English text",
|
||||
"[Replace with English punctuation]")
|
||||
|
||||
# Example: unbalanced HTML tags
|
||||
if en.count('<b>') != en.count('</b>'):
|
||||
add(i, cn, en,
|
||||
f"Unbalanced <b> tags (open={en.count('<b>')}, close={en.count('</b>')})",
|
||||
"[Balance tags]")
|
||||
|
||||
# Example: unbalanced double quotes
|
||||
if en.count('"') % 2 != 0:
|
||||
add(i, cn, en,
|
||||
f"Unbalanced quotes ({en.count(chr(34))} total)",
|
||||
"[Balance quotation marks]")
|
||||
|
||||
# Example: term inconsistency check
|
||||
# if re.search(r'TermA', en) and re.search(r'TermB', en) and ...
|
||||
|
||||
# ── Sanity checks ──
|
||||
for i, (page, cn, en) in enumerate(rows):
|
||||
if cn and not en:
|
||||
print(f"WARNING row {i+2}: CN present but EN empty: {cn[:80]}")
|
||||
cn_chars = re.findall(r'[\u4e00-\u9fff]', en)
|
||||
if cn_chars:
|
||||
print(f"WARNING row {i+2}: Chinese chars in EN: {cn_chars}")
|
||||
if cn and en and cn.strip() == en.strip():
|
||||
print(f"WARNING row {i+2}: CN==EN (untranslated): {cn[:60]}")
|
||||
|
||||
return issues
|
||||
|
||||
if __name__ == '__main__':
|
||||
issues = review_csv(sys.argv[1])
|
||||
print(f"Issues found: {len(issues)}")
|
||||
for iss in issues:
|
||||
print(f"\nCSV_ROW_{iss['row']} [{iss['page']}]")
|
||||
print(f" CN: {iss['cn'][:120]}")
|
||||
print(f" EN: {iss['en'][:120]}")
|
||||
print(f" PROBLEM: {iss['problem']}")
|
||||
print(f" SUGGEST: {iss['suggestion'][:150]}")
|
||||
@@ -1,139 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Mechanical sweep for .dj translation review — run after patches or as final verification.
|
||||
|
||||
Usage: python3 sweep.py <source.dj> <target.dj> [--stale term1,term2] [--new term1,term2]
|
||||
|
||||
Checks:
|
||||
1. Non-empty line count parity (source == target)
|
||||
2. Heading count parity
|
||||
3. Zero Markdown bold (**) in target (djot uses single *)
|
||||
5. Zero common Chinese punctuation in target
|
||||
6. Zero [text](#anchor) link artifacts in target TOC area (first 15 lines)
|
||||
7. Zero unbalanced double-quotes in target
|
||||
8. --stale: each listed string must appear ZERO times in target
|
||||
9. --new: each listed string must appear at least once in target
|
||||
"""
|
||||
|
||||
import re
|
||||
import sys
|
||||
|
||||
|
||||
CN_PUNCT = re.compile(r'[\u3000-\u303f\uff00-\uffef\u201c\u201d\u2018\u2019]')
|
||||
|
||||
def read_nonempty(path):
|
||||
with open(path) as f:
|
||||
return [l for l in f.read().rstrip('\n').split('\n') if l.strip()]
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) < 3:
|
||||
print("Usage: sweep.py <source.dj> <target.dj> [--stale a,b,c] [--new x,y,z]")
|
||||
sys.exit(2)
|
||||
|
||||
src_path = sys.argv[1]
|
||||
tgt_path = sys.argv[2]
|
||||
|
||||
stale_terms = []
|
||||
new_terms = []
|
||||
i = 3
|
||||
while i < len(sys.argv):
|
||||
if sys.argv[i] == '--stale' and i + 1 < len(sys.argv):
|
||||
stale_terms = [t.strip() for t in sys.argv[i+1].split(',') if t.strip()]
|
||||
i += 2
|
||||
elif sys.argv[i] == '--new' and i + 1 < len(sys.argv):
|
||||
new_terms = [t.strip() for t in sys.argv[i+1].split(',') if t.strip()]
|
||||
i += 2
|
||||
else:
|
||||
i += 1
|
||||
|
||||
src_lines = read_nonempty(src_path)
|
||||
tgt_lines = read_nonempty(tgt_path)
|
||||
tgt_raw = open(tgt_path).read()
|
||||
|
||||
errors = 0
|
||||
|
||||
# 1. Line count
|
||||
if len(src_lines) != len(tgt_lines):
|
||||
print(f"[FAIL] Line count: src={len(src_lines)} tgt={len(tgt_lines)}")
|
||||
errors += 1
|
||||
else:
|
||||
print(f"[OK] Line count: {len(src_lines)}")
|
||||
|
||||
# 2. Heading count
|
||||
src_h = sum(1 for l in src_lines if l.startswith('## '))
|
||||
tgt_h = sum(1 for l in tgt_lines if l.startswith('## '))
|
||||
if src_h != tgt_h:
|
||||
print(f"[FAIL] Headings: src={src_h} tgt={tgt_h}")
|
||||
errors += 1
|
||||
else:
|
||||
print(f"[OK] Headings: {src_h}")
|
||||
|
||||
# 3. Unicode em/en-dash
|
||||
em = tgt_raw.count('\u2014')
|
||||
en = tgt_raw.count('\u2013')
|
||||
if em or en:
|
||||
print(f"[FAIL] Unicode dashes: em-dash={em} en-dash={en}")
|
||||
errors += 1
|
||||
else:
|
||||
print("[OK] No Unicode em/en-dashes")
|
||||
|
||||
# 4. Markdown bold
|
||||
bold = sum(1 for l in tgt_lines if '**' in l)
|
||||
if bold:
|
||||
print(f"[FAIL] Markdown bold (**): {bold} lines")
|
||||
errors += 1
|
||||
else:
|
||||
print("[OK] No Markdown bold")
|
||||
|
||||
# 5. Chinese punctuation
|
||||
cn = [(i+1, l[:60]) for i, l in enumerate(tgt_lines) if CN_PUNCT.search(l)]
|
||||
if cn:
|
||||
print(f"[FAIL] Chinese/smart punct: {len(cn)} lines")
|
||||
for ln, snippet in cn[:5]:
|
||||
print(f" L{ln}: {snippet}")
|
||||
errors += 1
|
||||
else:
|
||||
print("[OK] No Chinese punctuation")
|
||||
|
||||
# 6. TOC link artifacts (first 15 lines)
|
||||
toc_links = sum(1 for l in tgt_lines[:15] if re.search(r'\[.*?\]\(#', l))
|
||||
if toc_links:
|
||||
print(f"[FAIL] TOC has [text](#anchor) links: {toc_links}")
|
||||
errors += 1
|
||||
else:
|
||||
print("[OK] TOC clean (no link artifacts)")
|
||||
|
||||
# 7. Unbalanced quotes
|
||||
for i, l in enumerate(tgt_lines):
|
||||
if l.count('"') % 2 != 0:
|
||||
print(f"[FAIL] L{i+1}: Unbalanced quotes: {l[:80]}")
|
||||
errors += 1
|
||||
if errors == sum(1 for l in tgt_lines if l.count('"') % 2 != 0):
|
||||
pass # errors already counted above
|
||||
elif not any(l.count('"') % 2 != 0 for l in tgt_lines):
|
||||
print("[OK] No unbalanced quotes")
|
||||
|
||||
# 8. Stale terms (must be absent)
|
||||
for term in stale_terms:
|
||||
count = tgt_raw.count(term)
|
||||
if count > 0:
|
||||
print(f"[FAIL] Stale term '{term}' still present: {count}")
|
||||
errors += 1
|
||||
else:
|
||||
print(f"[OK] Stale term '{term}' absent")
|
||||
|
||||
# 9. New terms (must be present)
|
||||
for term in new_terms:
|
||||
count = tgt_raw.count(term)
|
||||
if count == 0:
|
||||
print(f"[FAIL] New term '{term}' not found")
|
||||
errors += 1
|
||||
else:
|
||||
print(f"[OK] New term '{term}' found: {count}")
|
||||
|
||||
print(f"\n{'ALL CLEAN' if errors == 0 else f'{errors} ISSUE(S) FOUND'}")
|
||||
sys.exit(0 if errors == 0 else 1)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -10,6 +10,10 @@ outputs: target.dj (English djot), bilingual.dj, edit-suggestions.dj
|
||||
Core translation technique for Buddhist/Dharma content. Conventions (djot format,
|
||||
terms DB query, workflows, output format) are in AGENTS.md.
|
||||
|
||||
## Source context
|
||||
|
||||
Before translating, understand the source's format and delivery context. Is it a transcript of an oral talk, a book excerpt, a guided meditation script, a Q&A, a written article, or another genre? The register shapes the translation. If the context is not clear from the file path or source content, ask the user before proceeding.
|
||||
|
||||
## Mindfulness Bell Corpus
|
||||
|
||||
English Buddhist prose — register/style reference for translation.
|
||||
|
||||
Reference in New Issue
Block a user