kai/epub_bilingual_translator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Feat: v0.12 Pipeline Separation, Spacing Fix, and Idempotent Restoration

Browse Source
This commit is contained in:
谭凯
2026-02-01 10:39:07 +08:00
parent 7a93c52b42
commit 8e58415173
42 changed files with 3741 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/OPERATION_MANUAL.md
+26 -8
View File
@@ -34,16 +34,25 @@ python pipeline/02_translate.py --input-epub inputs/my_book.epub
```
Translates entries in `manifest.json`. ensuring `.env` has `OPENAI_API_KEY`.
### Step 3: Assembly
### Step 3: Assembly
### Step 3: Restore Format (NEW)
```bash
# Bilingual Output (Default: output/bilingual_my_book.epub)
python pipeline/03_assemble.py inputs/my_book.epub --bilingual
# Target Language Output (Default: output/translated_my_book.epub)
python pipeline/03_assemble.py inputs/my_book.epub
python pipeline/03_restore_format.py inputs/my_book.epub
```
**Note**: The Assembly step now includes an **LLM-based Placeholder Repair** mechanism. If `format_restorer` detects broken placeholders in the translation, it will query the LLM (using your configured credentials) to attempt an automatic fix. Ensure your `OPENAI_API_KEY` is set if you want this feature enabled.
**Optimizes and validates translations**:
1. Applies "Pangu" spacing (inserts space between Chinese and English/Numbers).
2. Restores HTML tags using placeholders.
3. Attempts **LLM Auto-Repair** if validation fails.
4. Saves result to `manifest.json` (`translated_html` field).
### Step 4: Build EPUB
```bash
# Bilingual Output (Default)
python pipeline/04_build_epub.py inputs/my_book.epub --bilingual
# Target Language Output
python pipeline/04_build_epub.py inputs/my_book.epub
```
**Pure assembly**: Injects the pre-validated `translated_html` into the EPUB structure. Fast and deterministic.
## Configuration
@@ -88,6 +97,15 @@ If you see `AuthenticationError` despite having the correct `base_url` in config
## Change Log
### [2026-02-01] Pipeline Separation & Formatting
* **Architecture**: Decoupled "Restoration" from "Assembly" into a 4-step pipeline.
* **New Step 3**: `03_restore_format.py` handles formatting, spacing, and repair. Saves to `translated_html`.
* **New Step 4**: `04_build_epub.py` handles pure EPUB generation.
* **Data Model**: Added `translated_html` to `ManifestEntry` as the "Gold Master" formatted content.
* **UX**: Added **Pangu Spacing** (Auto-spacing between CJK and ASCII) in Restoration step.
* **Optimization**: `RestorationEngine` is now idempotent (skips processing if `translated_html` exists). Added `--force-restore` flag.
* **Fix**: `main.py` updated to orchestrate the new 4-stage pipeline.
### [2026-01-31] Robustness & Repair
* **Feature**: Added **LLM-based Placeholder Repair** in Assembly stage. If placeholders mismatch, the system asks the LLM to fix the tags without changing text.
* **Fix**: Solved `FormatExtractor` "phantom placeholders" issue by correctly unescaping HTML entities during integrity checks.