diff --git a/tools/translate-test-dify/README.md b/tools/translate-test-dify/README.md index 3a06659c..4daa7c5f 100644 --- a/tools/translate-test-dify/README.md +++ b/tools/translate-test-dify/README.md @@ -87,56 +87,6 @@ See `example-model-comparison.md` for a complete example. | results/ | Output (gitignored) | | mock_docs/ | Temp test files (gitignored) | -## Testing Prompt Changes - -Prompts are stored in `../translate/prompt/` (1.md, 2.md, 3.md). - -### Prompt-to-Workflow Mapping - -| File | Dify Workflow Node | Trigger | -|------|-------------------|---------| -| `1.md` | Template (1) | New doc (`the_doc` only) | -| `2.md` | Template (2) | Update (`the_doc` + `the_doc_exist`) | -| `3.md` | Template (3) | Update + diff (all three params) | - -### Test All Scenarios - -```bash -# Scenario 1: New document -cat > test.md << 'EOF' -# Test -## keys -app-YOUR_KEY -test -## target_languages -zh -## test_file -en/use-dify/getting-started/introduction.mdx -EOF -python run_test.py test.md - -# Scenario 2: Add existing_file section -# Scenario 3: Add diff_content section - -# Verify URL mapping -grep -o 'href="[^"]*"' results/*/variant_A/*.md | head -10 -``` - -### Key Rule: URL Localization - -All prompts must map internal links: -- `/en/` → `/zh/` or `/ja/` -- `plugin-dev-en/` → `plugin-dev-zh/` or `plugin-dev-ja/` - -### API Parameters - -```bash -curl -H "Authorization: Bearer $KEY" https://api.dify.ai/v1/parameters -``` - -Required: `original_language`, `output_language1`, `the_doc`, `termbase` -Optional: `the_doc_exist` (→ prompt 2), `diff_original` (→ prompt 3) - ## Language Policy All code and documentation in **English** (international project). diff --git a/tools/translate-test-dify/run_test.py b/tools/translate-test-dify/run_test.py index 07ceddd8..62b93094 100644 --- a/tools/translate-test-dify/run_test.py +++ b/tools/translate-test-dify/run_test.py @@ -56,8 +56,6 @@ def parse_markdown_spec(file_path: Path) -> dict: "target_languages": ["cn"], "test_content": None, "test_file": None, - "existing_file": None, # For update scenario - "diff_content": None, # For update with diff scenario "variants": {} } @@ -98,16 +96,6 @@ def parse_markdown_spec(file_path: Path) -> dict: if file_match: config["test_file"] = file_match.group(1).strip().split('\n')[0].strip() - # Existing translation file (for update scenarios) - existing_match = re.search(r'##\s*existing_file\s*\n(.*?)(?=\n##|\Z)', content, re.DOTALL | re.IGNORECASE) - if existing_match: - config["existing_file"] = existing_match.group(1).strip().split('\n')[0].strip() - - # Diff content (for update with diff scenarios) - diff_match = re.search(r'##\s*diff_content\s*\n(.*?)(?=\n##|\Z)', content, re.DOTALL | re.IGNORECASE) - if diff_match: - config["diff_content"] = diff_match.group(1).strip() - return config @@ -131,24 +119,16 @@ async def save_file(file_path: Path, content: str): await f.write(content) -async def translate_text(content: str, api_key: str, target_language: str, termbase: str, - the_doc_exist: str = None, diff_original: str = None, max_retries: int = 3) -> str: - inputs = { - "original_language": "English", - "output_language1": target_language, - "the_doc": content, - "termbase": termbase - } - # Add optional params for update scenarios (triggers different prompts in Dify) - if the_doc_exist is not None: - inputs["the_doc_exist"] = the_doc_exist - if diff_original is not None: - inputs["diff_original"] = diff_original - +async def translate_text(content: str, api_key: str, target_language: str, termbase: str, max_retries: int = 3) -> str: payload = { "response_mode": "streaming", "user": "TranslationTest", - "inputs": inputs + "inputs": { + "original_language": "English", + "output_language1": target_language, + "the_doc": content, + "termbase": termbase + } } headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"} @@ -214,8 +194,6 @@ async def run_test(config_path: str, dry_run: bool = False): variants = config.get("variants", {}) test_content = config.get("test_content") test_file = config.get("test_file") - existing_file = config.get("existing_file") - diff_content = config.get("diff_content") if not variants: print("Error: No valid API keys found") @@ -238,18 +216,6 @@ async def run_test(config_path: str, dry_run: bool = False): print("Error: Need ## test_content or ## test_file section") sys.exit(1) - # Load existing translation (optional - for update scenarios) - existing_content = None - if existing_file: - existing_path = Path(existing_file) - if not existing_path.is_absolute(): - existing_path = SCRIPT_DIR.parent.parent / existing_file - if existing_path.exists(): - existing_content = await load_file(existing_path) - print(f"Loaded existing translation: {existing_file} ({len(existing_content)} chars)") - else: - print(f"Warning: existing_file not found: {existing_file}") - timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") result_dir = RESULTS_DIR / f"{timestamp}_{test_name}" @@ -263,24 +229,11 @@ async def run_test(config_path: str, dry_run: bool = False): termbase = await load_file(TERMBASE_PATH) if TERMBASE_PATH.exists() else "" - # Determine test mode - if existing_content and diff_content: - test_mode = "update+diff (prompt 3)" - elif existing_content: - test_mode = "update (prompt 2)" - else: - test_mode = "new (prompt 1)" - print(f"\n{'='*50}") print(f"Test: {test_name}") - print(f"Mode: {test_mode}") print(f"Variants: {', '.join(variants.keys())}") print(f"Languages: {', '.join(target_languages)}") print(f"Content: {doc_name} ({len(doc_content)} chars)") - if existing_content: - print(f"Existing: {len(existing_content)} chars") - if diff_content: - print(f"Diff: {len(diff_content)} chars") print(f"{'='*50}\n") all_results = {} @@ -301,8 +254,7 @@ async def run_test(config_path: str, dry_run: bool = False): lang_name = LANGUAGE_NAMES.get(lang, lang) print(f" → {lang_name}...", end=" ", flush=True) - translated = await translate_text(doc_content, api_key, lang_name, termbase, - the_doc_exist=existing_content, diff_original=diff_content) + translated = await translate_text(doc_content, api_key, lang_name, termbase) if translated: out_file = var_dir / f"{doc_name}_{lang}.md" await save_file(out_file, translated) diff --git a/tools/translate/prompt/1.md b/tools/translate/prompt/1.md deleted file mode 100644 index a99785cf..00000000 --- a/tools/translate/prompt/1.md +++ /dev/null @@ -1,114 +0,0 @@ -# Role Definition -You are an expert technical translator specializing in software documentation. Your specific task is to provide a precise, high-fidelity translation of **MDX documentation files intended for the Mintlify platform**. You must strictly adhere to a specific terminology glossary and preserve the complex structure of MDX files. - -*** - -# Context and Data -You will be provided with a mandatory terminology glossary and the source MDX file content. - -### Terminology Glossary -This glossary contains mandatory term-to-term translations. You MUST use these translations exactly as provided. - ------------- - - - -{{ termbase }} - - - ------------- - -### Source Text (MDX Format) -This is the MDX content you need to translate from {{ original_language }} to {{ output_language1 }}. - ------------- - - - -{{ the_doc }} - - - ------------- - -*** - -# Instructions and Rules -This is a comprehensive guide. Follow every rule meticulously. - -### Rule 1: Mandatory Glossary Adherence -For any term found in the **Terminology Glossary**, you **MUST** use its exact corresponding translation. There are no exceptions. - -### Rule 2: MDX Structural Integrity -You must distinguish between content that requires translation and structures that must be preserved. - -#### A. WHAT TO TRANSLATE: -- **General Text**: All standard paragraph text. -- **Frontmatter `title`**: In the `---` block at the top of the file, translate **only the value of the `title` and `description` fields**. -- **Markdown Content**: Translate text within headings (`#`), lists (`-`, `1.`), tables, blockquotes (`>`), bold (`**`), and italics (`*`). -- **Mintlify Component Content**: Translate the text content inside components like ``, ``, and ``. -- **Component Attributes**: Translate the string values of component attributes. For example, in ``, you must translate "Related Resources". - -#### B. WHAT TO PRESERVE (DO NOT TRANSLATE): -- **All Other Frontmatter Fields**: **Do not** translate the values of other fields like `slug`, `description`, `icon`, etc., inside the `---` block. -- **Code Blocks & Inline Code**: **Do not** translate any content inside triple backticks (```` ``` ````) or single backticks (` `). This includes code examples and commands. -- **Tags and Components**: **Do not** translate the names of MDX/JSX components or HTML tags themselves (e.g., ``, ``, `
`). -- **Component Attribute Names**: **Do not** translate the names of attributes (e.g., the word `title` in `title="..."`). -- **JSX-style Comments**: Preserve JSX comments exactly as they are: `{/* This is a comment */}`. -- **Placeholders & Variables**: **Do not** translate any text inside placeholders (e.g., `{{VARIABLE_NAME}}`, `%s`). -- **External URLs**: Preserve external URLs (starting with https://). In Markdown links like `[display text](url)`, only translate the `display text`. - -### Rule 3: URL Localization - -**You must update all internal documentation links to match the target language.** - -Our documentation uses these language codes: -- English: `en` -- Chinese: `zh` -- Japanese: `ja` - -**Replace ALL occurrences of source language codes with target language codes:** - -For standard paths: -- `/en/` → `/zh/` (when translating to Chinese) -- `/en/` → `/ja/` (when translating to Japanese) -- `/zh/` → `/en/` (when translating to English) -- `/zh/` → `/ja/` (when translating to Japanese) -- `/ja/` → `/en/` (when translating to English) -- `/ja/` → `/zh/` (when translating to Chinese) - -For plugin-dev paths: -- `plugin-dev-en/` → `plugin-dev-zh/` (when translating to Chinese) -- `plugin-dev-en/` → `plugin-dev-ja/` (when translating to Japanese) -- `plugin-dev-zh/` → `plugin-dev-en/` (when translating to English) -- `plugin-dev-zh/` → `plugin-dev-ja/` (when translating to Japanese) -- `plugin-dev-ja/` → `plugin-dev-en/` (when translating to English) -- `plugin-dev-ja/` → `plugin-dev-zh/` (when translating to Chinese) - -**Examples:** -- `/en/documentation/pages/llm` → `/zh/documentation/pages/llm` -- `plugin-dev-en/setup` → `plugin-dev-zh/setup` -- `[Guide](/en/docs/guide)` → `[指南](/zh/docs/guide)` - -**Do NOT change:** -- External URLs (https://...) -- Anchor links (#section) -- Asset paths without language codes - -### Rule 4: Professional Translation Quality -For all translatable text not covered by the glossary, provide an accurate, clear, and natural-sounding translation appropriate for a professional, technical audience in {{ output_language1 }}. - -*** - -# Task Execution -Proceed with the translation of the **Source Text** from **{{ original_language }}** to **{{ output_language1 }}**. - -Ensure your output strictly follows all rules defined above, paying special attention to these critical requirements: -- **Mandatory Glossary Usage** -- **MDX Frontmatter & Component Integrity** -- **Preservation of Code and Placeholders** -- **Output content directly, do not use any wrapper such as '```mdx' ** - - -Provide only the final, translated MDX text as your response. \ No newline at end of file diff --git a/tools/translate/prompt/2.md b/tools/translate/prompt/2.md deleted file mode 100644 index bcd01c7b..00000000 --- a/tools/translate/prompt/2.md +++ /dev/null @@ -1,163 +0,0 @@ -# Role Definition - -You are an expert technical translator specializing in updating translated MDX documentation files for the Mintlify platform. Your task is to intelligently update an existing translation based on an updated source document, preserving unchanged translations while applying mandatory terminology. - -*** - -# Context and Data - -## Translation Parameters -- Source language: **{{ original_language }}** -- Target language: **{{ output_language1 }}** - -## Document Inputs - -### Updated Source Document -The latest version in {{ original_language }}: - - -{{ the_doc }} - - -### Existing Translation -The current translation in {{ output_language1 }} that needs updating: - - -{{ the_doc_exist }} - - -### Terminology Database -Mandatory term translations: - - -{{ termbase }} - - -*** - -# Translation Rules - -## Rule 1: Mandatory Termbase Adherence -For any term found in the termbase, you **MUST** use its exact corresponding translation. No exceptions. - -## Rule 2: MDX Structural Integrity - -### A. WHAT TO TRANSLATE: -- **General Text**: All standard paragraph text -- **Frontmatter Values**: Only the values of `title` and `description` fields -- **Markdown Content**: Text within headings (`#`), lists, tables, blockquotes -- **Mintlify Components**: Text content inside ``, ``, ``, etc. -- **Component Attribute Values**: String values like `title="Related Resources"` -- **Link Display Text**: In `[display text](url)`, translate only "display text" - -### B. WHAT TO PRESERVE (DO NOT TRANSLATE): -- **All Other Frontmatter Fields**: Keep `slug`, `icon`, etc. unchanged -- **Code Blocks & Inline Code**: Content within ` ``` ` or ` ` ` -- **Component Names**: MDX/JSX components and HTML tags -- **Attribute Names**: The attribute name itself (e.g., `title` in `title="..."`) -- **JSX Comments**: `{/* comments */}` -- **Variables**: `{{VARIABLE}}`, `%s`, and similar placeholders -- **External URLs**: Starting with https:// - -**Important**: Ensure all XML/JSX tags are properly closed (e.g., `` must have ``). - -### C. CRITICAL XML/JSX RULES: -**ALL XML/JSX tags MUST be properly closed. This is non-negotiable.** -- Self-closing tags must end with `/>`： `` or `` -- Paired tags must have matching open/close: `content` -- **NEVER** leave tags unclosed: ❌ `content` without `` -- **NEVER** mismatch tags: ❌ `content` -- Component names must be identical in open/close tags (case-sensitive) - -**Examples of CORRECT tag usage:** -``` -This is a note. ✅ Paired tags - ✅ Self-closing - - Important content here. - ✅ Multi-line paired -description ✅ Self-closing -``` - -**Examples of INCORRECT tag usage:** -``` -This is a note. ❌ Missing closing tag - ❌ Should be self-closing -Content ❌ Case mismatch -Content ❌ Tag mismatch -``` - -## Rule 3: URL Localization - -**You must update all internal documentation links to match the target language.** - -Our documentation uses these language codes: -- English: `en` -- Chinese: `zh` -- Japanese: `ja` - -**Replace ALL occurrences of source language codes with target language codes:** - -For standard paths: -- `/en/` → `/zh/` (when translating to Chinese) -- `/en/` → `/ja/` (when translating to Japanese) -- `/zh/` → `/en/` (when translating to English) -- `/zh/` → `/ja/` (when translating to Japanese) -- `/ja/` → `/en/` (when translating to English) -- `/ja/` → `/zh/` (when translating to Chinese) - -For plugin-dev paths: -- `plugin-dev-en/` → `plugin-dev-zh/` (when translating to Chinese) -- `plugin-dev-en/` → `plugin-dev-ja/` (when translating to Japanese) -- `plugin-dev-zh/` → `plugin-dev-en/` (when translating to English) -- `plugin-dev-zh/` → `plugin-dev-ja/` (when translating to Japanese) -- `plugin-dev-ja/` → `plugin-dev-en/` (when translating to English) -- `plugin-dev-ja/` → `plugin-dev-zh/` (when translating to Chinese) - -**Examples:** -- `/en/documentation/pages/llm` → `/zh/documentation/pages/llm` -- `plugin-dev-en/setup` → `plugin-dev-zh/setup` -- `[Guide](/en/docs/guide)` → `[指南](/zh/docs/guide)` - -**Do NOT change:** -- External URLs (https://...) -- Anchor links (#section) -- Asset paths without language codes - -## Rule 4: Translation Priority -1. **Termbase** (highest): Use exact glossary translations -2. **Existing Translation**: Preserve unchanged content from current translation -3. **Professional Translation**: Create new translations for modified content - -## Rule 5: Quality Standards -- Maintain technical accuracy and natural fluency in {{target_lang}} -- **Preserve exact MDX structure - EVERY tag must be properly closed** -- Ensure all XML/JSX components have matching open/close tags -- Verify self-closing tags end with `/>` - -*** - -# Task Execution - -## Internal Process (Do Not Output) -Mentally analyze the documents to identify: -- Content to preserve from existing translation -- New or modified content requiring translation -- Applicable termbase entries -- URLs requiring language code updates - -## Critical Output Requirements - -**Output ONLY the complete translated MDX document:** - -- Start with the **first character** of the MDX content -- **No preamble, explanations, or wrapper** -- **No code blocks** (` ``` `) -- Response **IS** the MDX file content -- Output will be **piped directly** to a file - -**First character must be `---` (frontmatter) or actual content. Nothing before it.** - -*** - -Proceed with updating the translation from {{source_lang}} to {{target_lang}}. \ No newline at end of file diff --git a/tools/translate/prompt/3.md b/tools/translate/prompt/3.md deleted file mode 100644 index 40c940ef..00000000 --- a/tools/translate/prompt/3.md +++ /dev/null @@ -1,186 +0,0 @@ -# Role Definition - -You are an expert technical translator specializing in updating translated MDX documentation files for the Mintlify platform. Your task is to intelligently update an existing translation based on an updated source document, preserving unchanged translations while applying mandatory terminology. - -*** - -# Context and Data - -## Translation Parameters -- Source language: **{{ original_language }}** -- Target language: **{{ output_language1 }}** - -## Document Inputs - -### Updated Source Document -The latest version in {{ original_language }}: - - -{{ the_doc }} - - -### Existing Translation -The current translation in {{ output_language1 }} that needs updating: - - -{{ the_doc_exist }} - - -### Change Checklist -GitHub Diff exported Todo checklist (Markdown) indicating scope and change types (Add/Update/Delete/Move): - - -{{ text }} - - -### Terminology Database -Mandatory term translations: - - -{{ termbase }} - - -*** - -# Translation Rules - -## Rule 1: Mandatory Termbase Adherence -For any term found in the termbase, you **MUST** use its exact corresponding translation. No exceptions. - -## Rule 2: MDX Structural Integrity - -### A. WHAT TO TRANSLATE: -- **General Text**: All standard paragraph text -- **Frontmatter Values**: Only the values of `title` and `description` fields -- **Markdown Content**: Text within headings (`#`), lists, tables, blockquotes -- **Mintlify Components**: Text content inside ``, ``, ``, etc. -- **Component Attribute Values**: String values like `title="Related Resources"` -- **Link Display Text**: In `[display text](url)`, translate only "display text" - -### B. WHAT TO PRESERVE (DO NOT TRANSLATE): -- **All Other Frontmatter Fields**: Keep `slug`, `icon`, etc. unchanged -- **Code Blocks & Inline Code**: Content within ` ``` ` or ` ` ` -- **Component Names**: MDX/JSX components and HTML tags -- **Attribute Names**: The attribute name itself (e.g., `title` in `title="..."`) -- **JSX Comments**: `{/* comments */}` -- **Variables**: `{{VARIABLE}}`, `%s`, and similar placeholders -- **External URLs**: Starting with https:// - -**Important**: Ensure all XML/JSX tags are properly closed (e.g., `` must have ``). - -### C. CRITICAL XML/JSX RULES: -**ALL XML/JSX tags MUST be properly closed. This is non-negotiable.** -- Self-closing tags must end with `/>`： `` or `` -- Paired tags must have matching open/close: `content` -- **NEVER** leave tags unclosed: ❌ `content` without `` -- **NEVER** mismatch tags: ❌ `content` -- Component names must be identical in open/close tags (case-sensitive) - -**Examples of CORRECT tag usage:** -``` -This is a note. ✅ Paired tags - ✅ Self-closing - - Important content here. - ✅ Multi-line paired -description ✅ Self-closing -``` - -**Examples of INCORRECT tag usage:** -``` -This is a note. ❌ Missing closing tag - ❌ Should be self-closing -Content ❌ Case mismatch -Content ❌ Tag mismatch -``` - -## Rule 3: URL Localization - -**You must update all internal documentation links to match the target language.** - -Our documentation uses these language codes: -- English: `en` -- Chinese: `zh` -- Japanese: `ja` - -**Replace ALL occurrences of source language codes with target language codes:** - -For standard paths: -- `/en/` → `/zh/` (when translating to Chinese) -- `/en/` → `/ja/` (when translating to Japanese) -- `/zh/` → `/en/` (when translating to English) -- `/zh/` → `/ja/` (when translating to Japanese) -- `/ja/` → `/en/` (when translating to English) -- `/ja/` → `/zh/` (when translating to Chinese) - -For plugin-dev paths: -- `plugin-dev-en/` → `plugin-dev-zh/` (when translating to Chinese) -- `plugin-dev-en/` → `plugin-dev-ja/` (when translating to Japanese) -- `plugin-dev-zh/` → `plugin-dev-en/` (when translating to English) -- `plugin-dev-zh/` → `plugin-dev-ja/` (when translating to Japanese) -- `plugin-dev-ja/` → `plugin-dev-en/` (when translating to English) -- `plugin-dev-ja/` → `plugin-dev-zh/` (when translating to Chinese) - -**Examples:** -- `/en/documentation/pages/llm` → `/zh/documentation/pages/llm` -- `plugin-dev-en/setup` → `plugin-dev-zh/setup` -- `[Guide](/en/docs/guide)` → `[指南](/zh/docs/guide)` - -**Do NOT change:** -- External URLs (https://...) -- Anchor links (#section) -- Asset paths without language codes - -## Rule 4: Translation Priority -1. **Termbase** (highest): Use exact glossary translations -2. **Existing Translation**: Preserve unchanged content from current translation -3. **Professional Translation**: Create new translations for modified content - -Checklist Usage: Use the “Change Checklist” only to define the scope and type of updates; it is lower priority than the updated source and termbase and must not override actual source content. - -## Rule 5: Quality Standards -- Maintain technical accuracy and natural fluency in {{ output_language1 }} -- **Preserve exact MDX structure - EVERY tag must be properly closed** -- Ensure all XML/JSX components have matching open/close tags -- Verify self-closing tags end with `/>` -- For unchanged content, preserve it character-for-character, including whitespace, punctuation, and casing - -## Rule 6: Checklist-Guided Partial Update -- Purpose: The checklist is used to locate differences and constrain the update scope; it must not serve as an independent content source -- Change types covered: - - Add: New paragraphs/sentences/components → translate per rules and insert at correct position - - Update: Only update the marked paragraphs → precise replacement - - Delete: Remove corresponding content from the existing translation - - Move/Reorder: Reorder according to the updated source; identical text is treated as preserved -- Conflict handling: If the checklist conflicts with the Updated Source, the Updated Source prevails -- Exclusion: Do not include the checklist or any summary of it in the final output -- Location method: Prefer matching via headings, anchors, component attributes (e.g., title), and unique phrases; if not uniquely matchable, align by source structure and context - -*** - -# Task Execution - -## Internal Process (Do Not Output) -Mentally analyze the documents to identify: -- Content to preserve from existing translation -- New or modified content requiring translation -- Applicable termbase entries -- URLs requiring language code updates -- Use the Change Checklist to confine modifications to marked areas: map each item to source structure (headings/paragraphs/components) and apply Add/Update/Delete/Move accordingly -- If a checklist item cannot be located or conflicts with the source, rely on the source and termbase; leave unaffected areas unchanged - -## Critical Output Requirements - -**Output ONLY the complete translated MDX document:** - -- Start with the **first character** of the MDX content -- **No preamble, explanations, or wrapper** -- **No code blocks** (` ``` `) -- Response **IS** the MDX file content -- Output will be **piped directly** to a file - -**First character must be `---` (frontmatter) or actual content. Nothing before it.** - -*** - -Proceed with updating the translation from {{ original_language }} to {{ output_language1 }}. \ No newline at end of file