feat: Release v0.10 - Modular Architecture & External Config
- Refactor codebase into src/ (preprocessing, translation, assembly) - Add pipeline/ scripts for individual stages - Externalize configuration to config/config.yaml - Fix Cover Image preservation - Update documentation and manuals
This commit is contained in:
谭凯
@@ -0,0 +1,96 @@
|
||||
from pathlib import Path
|
||||
from typing import List, Dict, Optional
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
from src.data_model import BookStructure, ManifestEntry
|
||||
from src.format_restorer import FormatRestorer
|
||||
from src.utils import setup_logger
|
||||
|
||||
logger = setup_logger("backfill_engine")
|
||||
|
||||
class BackfillEngine:
|
||||
"""
|
||||
Applies translations back to the BookStructure.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self.restorer = FormatRestorer()
|
||||
|
||||
def backfill(self, structure: BookStructure, manifest_entries: List[ManifestEntry], mode: str = "bilingual") -> BookStructure:
|
||||
"""
|
||||
Modifies the BookStructure in-place with translations.
|
||||
|
||||
Args:
|
||||
structure: The BookStructure (from book_structure.json).
|
||||
manifest_entries: List of translations.
|
||||
mode: 'bilingual' or 'target_only'.
|
||||
"""
|
||||
logger.info(f"Backfilling with mode: {mode}")
|
||||
|
||||
# Index manifest by file and element ID for faster lookup
|
||||
# Map: file_path -> element_id -> ManifestEntry
|
||||
manifest_map: Dict[str, Dict[str, ManifestEntry]] = {}
|
||||
for entry in manifest_entries:
|
||||
if not entry.translated_text:
|
||||
continue # Skip untranslated entries
|
||||
|
||||
if entry.file_path not in manifest_map:
|
||||
manifest_map[entry.file_path] = {}
|
||||
manifest_map[entry.file_path][entry.element_id] = entry
|
||||
|
||||
# Iterate resources in structure
|
||||
for item_id, resource in structure.resources.items():
|
||||
if resource.media_type != "application/xhtml+xml" or resource.href not in manifest_map:
|
||||
continue
|
||||
|
||||
file_entries = manifest_map[resource.href]
|
||||
if not file_entries:
|
||||
continue
|
||||
|
||||
logger.debug(f"Processing {resource.href} with {len(file_entries)} translations")
|
||||
|
||||
soup = BeautifulSoup(resource.content, 'html.parser')
|
||||
modified = False
|
||||
|
||||
for element_id, entry in file_entries.items():
|
||||
element = soup.find(id=element_id)
|
||||
if not element:
|
||||
logger.warning(f"Element {element_id} not found in {resource.href}")
|
||||
continue
|
||||
|
||||
# Restore formatting
|
||||
restored_html, _ = self.restorer.restore(entry.translated_text, entry.placeholders)
|
||||
|
||||
# Create translated tag
|
||||
new_tag = soup.new_tag(element.name)
|
||||
# Parse restored HTML to get content nodes
|
||||
inner_soup = BeautifulSoup(restored_html, 'html.parser')
|
||||
if inner_soup.body:
|
||||
for child in list(inner_soup.body.children):
|
||||
new_tag.append(child)
|
||||
else:
|
||||
for child in list(inner_soup.children):
|
||||
new_tag.append(child)
|
||||
|
||||
# Copy classes and add 'translation'
|
||||
classes = element.get('class', [])
|
||||
if isinstance(classes, str):
|
||||
classes = classes.split()
|
||||
new_tag['class'] = classes + ['translation']
|
||||
|
||||
# Copy style
|
||||
style = element.get('style')
|
||||
if style:
|
||||
new_tag['style'] = style
|
||||
|
||||
if mode == "bilingual":
|
||||
element.insert_after(new_tag)
|
||||
else:
|
||||
element.replace_with(new_tag)
|
||||
|
||||
modified = True
|
||||
|
||||
if modified:
|
||||
resource.content = str(soup)
|
||||
|
||||
return structure
|
||||
@@ -0,0 +1,252 @@
|
||||
import shutil
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from ebooklib import epub
|
||||
from src.data_model import BookStructure
|
||||
from src.utils import setup_logger, ensure_directory
|
||||
|
||||
logger = setup_logger("bilingual_builder")
|
||||
|
||||
class BilingualBuilder:
|
||||
"""
|
||||
Assembles the final EPUB from BookStructure.
|
||||
|
||||
Preserves the original TOC structure by reading it from the original EPUB.
|
||||
"""
|
||||
|
||||
def __init__(self, work_dir: Path, original_epub_path: Path = None):
|
||||
self.work_dir = work_dir
|
||||
self.assets_dir = work_dir / "assets"
|
||||
self.original_epub_path = original_epub_path
|
||||
self._original_book = None
|
||||
|
||||
def _load_original_book(self):
|
||||
"""Lazy load original book for TOC extraction."""
|
||||
if self._original_book is None and self.original_epub_path and self.original_epub_path.exists():
|
||||
try:
|
||||
self._original_book = epub.read_epub(str(self.original_epub_path))
|
||||
logger.debug(f"Loaded original EPUB for TOC: {self.original_epub_path}")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to load original EPUB: {e}")
|
||||
return self._original_book
|
||||
|
||||
def _sanitize_toc(self, toc):
|
||||
"""
|
||||
Ensure all TOC nodes have IDs (for ebooklib compatibility).
|
||||
From v0.08 bilingual_builder.py
|
||||
"""
|
||||
result = []
|
||||
for item in toc:
|
||||
if isinstance(item, (epub.Link, epub.Section)):
|
||||
if not getattr(item, 'uid', None):
|
||||
item.uid = f"navPoint-{uuid.uuid4().hex[:8]}"
|
||||
result.append(item)
|
||||
elif isinstance(item, tuple) and len(item) == 2:
|
||||
# Handle (Section, [children]) structure
|
||||
section, children = item
|
||||
if isinstance(section, (epub.Link, epub.Section)):
|
||||
if not getattr(section, 'uid', None):
|
||||
section.uid = f"navPoint-{uuid.uuid4().hex[:8]}"
|
||||
sanitized_children = self._sanitize_toc(children)
|
||||
result.append((section, sanitized_children))
|
||||
else:
|
||||
result.append(item)
|
||||
return result
|
||||
|
||||
def _validate_and_fix_toc(self, toc, book_items):
|
||||
"""
|
||||
Recursively validate and fix TOC links.
|
||||
Removes nodes with broken links that cannot be fixed.
|
||||
"""
|
||||
fixed_toc = []
|
||||
for item in toc:
|
||||
if isinstance(item, (epub.Link, epub.Section)):
|
||||
# Check href
|
||||
href = getattr(item, 'href', '')
|
||||
if href:
|
||||
# Remove anchor for check
|
||||
clean_href = href.split('#')[0]
|
||||
# Check if item exists in book (by file_name)
|
||||
found = False
|
||||
for existing_item in book_items.values():
|
||||
if existing_item.file_name == clean_href:
|
||||
found = True
|
||||
break
|
||||
if clean_href.endswith(existing_item.file_name) or existing_item.file_name.endswith(clean_href):
|
||||
item.href = existing_item.file_name
|
||||
found = True
|
||||
break
|
||||
|
||||
if not found:
|
||||
if 'c0.xhtml' in clean_href:
|
||||
for existing_item in book_items.values():
|
||||
if 'titlepage' in existing_item.file_name or 'cover' in existing_item.file_name.lower():
|
||||
if existing_item.media_type == "application/xhtml+xml":
|
||||
logger.info(f"Fixed TOC link: {href} -> {existing_item.file_name}")
|
||||
item.href = existing_item.file_name
|
||||
found = True
|
||||
break
|
||||
|
||||
if not found:
|
||||
logger.warning(f"Removing broken TOC link: {href}")
|
||||
continue
|
||||
|
||||
if isinstance(item, tuple) and len(item) == 2:
|
||||
section, children = item
|
||||
fixed_children = self._validate_and_fix_toc(children, book_items)
|
||||
fixed_toc.append((section, fixed_children))
|
||||
else:
|
||||
fixed_toc.append(item)
|
||||
|
||||
return fixed_toc
|
||||
|
||||
def build(self, structure: BookStructure, output_path: Path) -> Path:
|
||||
"""
|
||||
Builds the EPUB file.
|
||||
Returns the path to the generated EPUB.
|
||||
"""
|
||||
logger.info(f"Building final EPUB: {output_path}")
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
book = epub.EpubBook()
|
||||
|
||||
# 1. Metadata
|
||||
book.set_identifier(structure.metadata.identifier or f"uuid-{uuid.uuid4().hex[:12]}")
|
||||
book.set_title(structure.metadata.title)
|
||||
book.set_language(structure.metadata.language)
|
||||
book.add_author(structure.metadata.author)
|
||||
|
||||
# 2. Copy TOC from original EPUB if available
|
||||
original_book = self._load_original_book()
|
||||
if original_book and hasattr(original_book, 'toc') and original_book.toc:
|
||||
book.toc = self._sanitize_toc(original_book.toc)
|
||||
logger.info("Copied TOC structure from original EPUB")
|
||||
|
||||
|
||||
|
||||
# 3. Add Resources - First pass: Collect CSS items
|
||||
items_map = {} # id -> epub_item
|
||||
css_items = [] # List of CSS EpubItem for linking
|
||||
html_items = [] # List of (item_id, EpubHtml) tuples
|
||||
|
||||
for item_id, resource in structure.resources.items():
|
||||
# Skip NCX - we'll handle it separately
|
||||
if resource.media_type == "application/x-dtbncx+xml":
|
||||
continue
|
||||
|
||||
if resource.media_type == "application/xhtml+xml":
|
||||
# HTML Item - create but don't add yet (need to add CSS links)
|
||||
item = epub.EpubHtml(
|
||||
uid=item_id,
|
||||
file_name=resource.href,
|
||||
media_type=resource.media_type,
|
||||
content=resource.content.encode('utf-8')
|
||||
)
|
||||
html_items.append((item_id, item))
|
||||
elif resource.file_path:
|
||||
# Binary/Asset Item
|
||||
asset_full_path = self.work_dir / resource.file_path
|
||||
|
||||
if not asset_full_path.exists():
|
||||
logger.warning(f"Asset missing: {asset_full_path}")
|
||||
continue
|
||||
|
||||
with open(asset_full_path, 'rb') as f:
|
||||
content = f.read()
|
||||
|
||||
if "image" in resource.media_type:
|
||||
item = epub.EpubImage(
|
||||
uid=item_id,
|
||||
file_name=resource.href,
|
||||
media_type=resource.media_type,
|
||||
content=content
|
||||
)
|
||||
else:
|
||||
item = epub.EpubItem(
|
||||
uid=item_id,
|
||||
file_name=resource.href,
|
||||
media_type=resource.media_type,
|
||||
content=content
|
||||
)
|
||||
# Track CSS items
|
||||
if resource.media_type == "text/css":
|
||||
css_items.append(item)
|
||||
|
||||
book.add_item(item)
|
||||
items_map[item_id] = item
|
||||
else:
|
||||
logger.warning(f"Skipping resource {item_id}: No content or file path.")
|
||||
continue
|
||||
|
||||
# 4. Add HTML items with CSS links
|
||||
for item_id, item in html_items:
|
||||
html_dir = Path(item.file_name).parent
|
||||
for css_item in css_items:
|
||||
css_path = Path(css_item.file_name)
|
||||
# Calculate relative path from HTML directory to CSS file
|
||||
try:
|
||||
relative_css_path = Path(css_path).relative_to(html_dir)
|
||||
except ValueError:
|
||||
# Not a subpath, calculate full relative
|
||||
# Go up from html_dir, then down to css_path
|
||||
up_count = len(html_dir.parts)
|
||||
relative_css_path = Path("/".join([".."] * up_count)) / css_path
|
||||
|
||||
item.add_link(href=str(relative_css_path), rel='stylesheet', type='text/css')
|
||||
book.add_item(item)
|
||||
items_map[item_id] = item
|
||||
|
||||
# 5. Copy missing items from original EPUB (cover, etc.)
|
||||
# This ensures TOC links don't break
|
||||
if original_book:
|
||||
added_hrefs = {item.file_name for item in items_map.values() if hasattr(item, 'file_name')}
|
||||
|
||||
for orig_item in original_book.get_items():
|
||||
orig_name = orig_item.get_name()
|
||||
if orig_name not in added_hrefs:
|
||||
# Skip NCX and NAV - we generate these
|
||||
if 'ncx' in orig_name.lower() or orig_name.endswith('nav.xhtml'):
|
||||
continue
|
||||
|
||||
# Copy the item directly
|
||||
try:
|
||||
book.add_item(orig_item)
|
||||
items_map[orig_item.id] = orig_item
|
||||
logger.debug(f"Copied missing item from original: {orig_name}")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to copy item {orig_name}: {e}")
|
||||
|
||||
# 6. Spine
|
||||
book.spine = []
|
||||
for item_id in structure.spine:
|
||||
if item_id in items_map:
|
||||
book.spine.append(items_map[item_id])
|
||||
else:
|
||||
logger.warning(f"Spine item {item_id} not found in resources.")
|
||||
|
||||
# Add missing spine items from original
|
||||
if original_book:
|
||||
for spine_id, _ in original_book.spine:
|
||||
if spine_id not in [i.id for i in book.spine]:
|
||||
orig_item = original_book.get_item_with_id(spine_id)
|
||||
if orig_item and orig_item.id in items_map:
|
||||
book.spine.append(items_map[orig_item.id])
|
||||
|
||||
# Validate and fix TOC
|
||||
if original_book and hasattr(book, 'toc') and book.toc:
|
||||
try:
|
||||
book.toc = self._validate_and_fix_toc(book.toc, items_map)
|
||||
logger.info("Validated and fixed TOC links")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to validate TOC: {e}")
|
||||
|
||||
# 7. Navigation - NCX and Nav
|
||||
book.add_item(epub.EpubNcx())
|
||||
book.add_item(epub.EpubNav())
|
||||
|
||||
# 7. Write
|
||||
epub.write_epub(str(output_path), book)
|
||||
logger.info(f"EPUB created successfully at {output_path}")
|
||||
|
||||
return output_path
|
||||
|
||||
@@ -0,0 +1,76 @@
|
||||
import json
|
||||
import random
|
||||
from typing import Dict, List
|
||||
from loguru import logger
|
||||
from src.llm_client import LLMClient
|
||||
from src.manifest_manager import ManifestManager
|
||||
from src.data_model import BookProfile
|
||||
|
||||
class BookProfiler:
|
||||
def __init__(self, llm_client: LLMClient):
|
||||
self.llm_client = llm_client
|
||||
|
||||
def extract_sample_text(self, entries: List[object], char_limit: int = 3000) -> str:
|
||||
"""Extract sample text from manifest entries."""
|
||||
if not entries: return ""
|
||||
|
||||
# Simple sampling strategy: First few + random middle
|
||||
intro_text = []
|
||||
for entry in entries[:50]:
|
||||
if len(entry.original_text) > 50:
|
||||
intro_text.append(entry.original_text)
|
||||
|
||||
body_text = []
|
||||
candidates = [e for e in entries[50:] if len(e.original_text) > 80]
|
||||
if candidates:
|
||||
samples = random.sample(candidates, min(5, len(candidates)))
|
||||
body_text = [e.original_text for e in samples]
|
||||
|
||||
full_text = "\n\n".join(intro_text[:5] + body_text)
|
||||
return full_text[:char_limit]
|
||||
|
||||
async def analyze(self, entries: List[object]) -> BookProfile:
|
||||
"""Generate Book Profile."""
|
||||
sample = self.extract_sample_text(entries)
|
||||
if not sample:
|
||||
return BookProfile(title="Unknown", author="Unknown")
|
||||
|
||||
logger.info("Generating Book Profile from sample text...")
|
||||
|
||||
system_prompt = "You are a senior publishing editor. Analyze the text and output JSON."
|
||||
user_prompt = f"""
|
||||
Please analyze the following book excerpt.
|
||||
Output JSON format:
|
||||
{{
|
||||
"title": "Book Title",
|
||||
"author": "Author Name",
|
||||
"genre": "Genre",
|
||||
"style": "Style description",
|
||||
"keywords": ["keyword1", "keyword2"],
|
||||
"style_guide": "Specific instruction for translator"
|
||||
}}
|
||||
|
||||
Excerpt:
|
||||
{sample}
|
||||
"""
|
||||
try:
|
||||
response = await self.llm_client.raw_chat_completion(system_prompt, user_prompt)
|
||||
json_str = response.strip()
|
||||
# Basic cleanup
|
||||
if "```json" in json_str:
|
||||
json_str = json_str.split("```json")[1].split("```")[0].strip()
|
||||
elif "```" in json_str:
|
||||
json_str = json_str.split("```")[1].split("```")[0].strip()
|
||||
|
||||
data = json.loads(json_str)
|
||||
|
||||
return BookProfile(
|
||||
title=data.get("title", "Unknown"),
|
||||
author=data.get("author", "Unknown"),
|
||||
genre=data.get("genre", "General"),
|
||||
keywords=data.get("keywords", []),
|
||||
style_guide=data.get("style_guide", "")
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"Profile generation failed: {e}")
|
||||
return BookProfile(title="Unknown", author="Unknown")
|
||||
@@ -0,0 +1,51 @@
|
||||
from pathlib import Path
|
||||
from typing import List, Optional, Dict, Any
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
class ManifestEntry(BaseModel):
|
||||
"""Represents a single translatable unit."""
|
||||
entry_id: str = Field(..., description="Global unique ID (e.g. file.html#paragraph_id)")
|
||||
file_path: str = Field(..., description="Internal path in EPUB")
|
||||
element_id: str = Field(..., description="HTML ID (e.g. uuid-1234)")
|
||||
original_text: str
|
||||
placeholders: Dict[str, str] = Field(default_factory=dict)
|
||||
translated_text: Optional[str] = None
|
||||
context: Optional[str] = None
|
||||
|
||||
class BookMetaData(BaseModel):
|
||||
title: str = "Unknown Title"
|
||||
author: str = "Unknown Author"
|
||||
language: str = "en"
|
||||
identifier: str = ""
|
||||
|
||||
class ResourceItem(BaseModel):
|
||||
href: str
|
||||
media_type: str
|
||||
content: Optional[str] = None # For text/html
|
||||
file_path: Optional[str] = None # For binary/assets (relative to assets dir)
|
||||
properties: Optional[str] = None
|
||||
|
||||
class BookStructure(BaseModel):
|
||||
metadata: BookMetaData
|
||||
spine: List[str] = Field(default_factory=list, description="Ordered list of item IDs in spine")
|
||||
resources: Dict[str, ResourceItem] = Field(default_factory=dict, description="Map of item_id to ResourceItem")
|
||||
|
||||
@classmethod
|
||||
def load(cls, path: Path) -> "BookStructure":
|
||||
"""Load BookStructure from JSON file."""
|
||||
with open(path, 'r', encoding='utf-8') as f:
|
||||
return cls.model_validate_json(f.read())
|
||||
|
||||
def save(self, path: Path):
|
||||
"""Save BookStructure to JSON file."""
|
||||
with open(path, 'w', encoding='utf-8') as f:
|
||||
f.write(self.model_dump_json(indent=2))
|
||||
|
||||
class BookProfile(BaseModel):
|
||||
"""Represents the profile of the book."""
|
||||
title: str
|
||||
author: str
|
||||
genre: str = "General"
|
||||
keywords: List[str] = Field(default_factory=list)
|
||||
style_guide: str = ""
|
||||
|
||||
@@ -0,0 +1,178 @@
|
||||
import shutil
|
||||
import uuid
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
from typing import Dict, Set
|
||||
|
||||
import ebooklib
|
||||
from bs4 import BeautifulSoup, Tag
|
||||
from ebooklib import epub
|
||||
|
||||
from src.data_model import BookStructure, BookMetaData, ResourceItem
|
||||
from src.exceptions import CleaningError
|
||||
from src.utils import setup_logger, ensure_directory
|
||||
|
||||
logger = setup_logger("epub_cleaner")
|
||||
|
||||
class EpubCleaner:
|
||||
def __init__(self, input_path: Path, work_dir: Path):
|
||||
self.input_path = input_path
|
||||
self.work_dir = work_dir
|
||||
self.assets_dir = work_dir / "assets"
|
||||
self.json_path = work_dir / "book_structure.json"
|
||||
|
||||
def clean(self) -> Path:
|
||||
"""
|
||||
Cleans the input EPUB and generates book_structure.json.
|
||||
Returns the path to the JSON file.
|
||||
"""
|
||||
logger.info(f"Starting cleanup for {self.input_path}")
|
||||
ensure_directory(self.work_dir)
|
||||
ensure_directory(self.assets_dir)
|
||||
|
||||
try:
|
||||
book = epub.read_epub(self.input_path)
|
||||
|
||||
# 1. Extract Metadata
|
||||
metadata = self._extract_metadata(book)
|
||||
|
||||
# 2. Process Resources
|
||||
resources = {}
|
||||
# Use zipfile for binary extraction to avoid ebooklib's memory overhead/decoding issues
|
||||
with zipfile.ZipFile(self.input_path, 'r') as zf:
|
||||
# Map ebooklib items to zip entries isn't straightforward directly via name
|
||||
# So we iterate ebooklib items and assume standard structure or handle content bytes
|
||||
|
||||
for item in book.get_items():
|
||||
item_id = item.get_id()
|
||||
file_name = item.get_name()
|
||||
media_type = item.get_type() # ebooklib constant
|
||||
|
||||
if media_type == ebooklib.ITEM_DOCUMENT:
|
||||
# Clean HTML
|
||||
content_str = item.get_content().decode('utf-8')
|
||||
cleaned_content = self._clean_html(content_str, file_name)
|
||||
|
||||
resources[item_id] = ResourceItem(
|
||||
href=file_name,
|
||||
media_type="application/xhtml+xml",
|
||||
content=cleaned_content
|
||||
)
|
||||
elif media_type in (ebooklib.ITEM_IMAGE, ebooklib.ITEM_STYLE, ebooklib.ITEM_FONT, ebooklib.ITEM_COVER):
|
||||
# Save asset
|
||||
# Preserve directory structure to avoid collisions
|
||||
asset_path = self.assets_dir / file_name
|
||||
ensure_directory(asset_path.parent)
|
||||
|
||||
# Ebooklib might change filenames, safer to use item.get_content()
|
||||
with open(asset_path, "wb") as f:
|
||||
f.write(item.get_content())
|
||||
|
||||
resources[item_id] = ResourceItem(
|
||||
href=file_name,
|
||||
media_type=self._get_media_type_str(item),
|
||||
file_path=str(asset_path.relative_to(self.work_dir))
|
||||
)
|
||||
elif media_type == ebooklib.ITEM_NAVIGATION:
|
||||
# NCX or NAV document - preserve for TOC
|
||||
content_bytes = item.get_content()
|
||||
asset_path = self.assets_dir / file_name
|
||||
ensure_directory(asset_path.parent)
|
||||
|
||||
with open(asset_path, "wb") as f:
|
||||
f.write(content_bytes)
|
||||
|
||||
# Determine media type
|
||||
if file_name.endswith('.ncx'):
|
||||
mt = "application/x-dtbncx+xml"
|
||||
else:
|
||||
mt = "application/xhtml+xml"
|
||||
|
||||
resources[item_id] = ResourceItem(
|
||||
href=file_name,
|
||||
media_type=mt,
|
||||
file_path=str(asset_path.relative_to(self.work_dir))
|
||||
)
|
||||
logger.debug(f"Preserved navigation: {file_name}")
|
||||
else:
|
||||
# Skip other items (scripts, etc.)
|
||||
pass
|
||||
|
||||
# 3. Extract Spine
|
||||
spine_ids = [item[0] for item in book.spine]
|
||||
|
||||
# 4. Construct Structure
|
||||
structure = BookStructure(
|
||||
metadata=metadata,
|
||||
spine=spine_ids,
|
||||
resources=resources
|
||||
)
|
||||
|
||||
# 5. Serialize
|
||||
with open(self.json_path, "w", encoding="utf-8") as f:
|
||||
f.write(structure.model_dump_json(indent=2))
|
||||
|
||||
logger.info(f"Cleanup finished. Structure saved to {self.json_path}")
|
||||
return self.json_path
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Cleaning failed: {e}")
|
||||
raise CleaningError(f"Failed to clean EPUB: {e}") from e
|
||||
|
||||
def _extract_metadata(self, book: epub.EpubBook) -> BookMetaData:
|
||||
title = book.get_metadata('DC', 'title')[0][0] if book.get_metadata('DC', 'title') else "Unknown"
|
||||
author = book.get_metadata('DC', 'creator')[0][0] if book.get_metadata('DC', 'creator') else "Unknown"
|
||||
lang = book.get_metadata('DC', 'language')[0][0] if book.get_metadata('DC', 'language') else "en"
|
||||
ident = book.get_metadata('DC', 'identifier')[0][0] if book.get_metadata('DC', 'identifier') else ""
|
||||
|
||||
return BookMetaData(
|
||||
title=str(title),
|
||||
author=str(author),
|
||||
language=str(lang),
|
||||
identifier=str(ident)
|
||||
)
|
||||
|
||||
def _get_media_type_str(self, item) -> str:
|
||||
# Helper to map ebooklib type to mime string if needed
|
||||
# ebooklib doesn't expose easy MIME string for all types directly on item object sometimes
|
||||
if hasattr(item, 'media_type'):
|
||||
return item.media_type
|
||||
return "application/octet-stream"
|
||||
|
||||
def _clean_html(self, content: str, filename: str) -> str:
|
||||
soup = BeautifulSoup(content, 'html.parser')
|
||||
|
||||
# 1. Provide IDs for structural/translatable elements
|
||||
self._ensure_element_ids(soup)
|
||||
|
||||
# 2. Flatten divs (Disable to prevent style loss)
|
||||
# self._flatten_divs(soup)
|
||||
|
||||
return str(soup)
|
||||
|
||||
def _ensure_element_ids(self, soup: BeautifulSoup):
|
||||
"""
|
||||
Injects UUIDs into p, h1-h6, li tags if they don't have an ID.
|
||||
This provides the anchor for translation backfilling.
|
||||
"""
|
||||
targets = soup.find_all(['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'li'])
|
||||
for tag in targets:
|
||||
if not tag.has_attr('id'):
|
||||
tag['id'] = f"uuid-{uuid.uuid4()}"
|
||||
|
||||
def _flatten_divs(self, soup: BeautifulSoup):
|
||||
"""
|
||||
Converts generic divs containing only inline text/styles to p tags.
|
||||
Recursive strategies can be complex, sticking to simple heuristic from archive.
|
||||
"""
|
||||
inline_tags = {'span', 'em', 'strong', 'i', 'b', 'u', 'a', 'br', 'sub', 'sup', 'small'}
|
||||
|
||||
for div in list(soup.find_all('div')):
|
||||
# If div has no block children, convert to p
|
||||
has_block = any(
|
||||
isinstance(c, Tag) and c.name not in inline_tags
|
||||
for c in div.children
|
||||
)
|
||||
|
||||
if not has_block:
|
||||
div.name = 'p'
|
||||
@@ -0,0 +1,18 @@
|
||||
class EpubTranslatorError(Exception):
|
||||
"""Base exception for Epub Translator."""
|
||||
pass
|
||||
|
||||
class CleaningError(EpubTranslatorError):
|
||||
pass
|
||||
|
||||
class ExtractionError(EpubTranslatorError):
|
||||
pass
|
||||
|
||||
class TranslationError(EpubTranslatorError):
|
||||
pass
|
||||
|
||||
class RestorationError(EpubTranslatorError):
|
||||
pass
|
||||
|
||||
class BuildError(EpubTranslatorError):
|
||||
pass
|
||||
@@ -0,0 +1,132 @@
|
||||
import re
|
||||
from typing import List, Dict, Any, Optional
|
||||
from bs4 import BeautifulSoup
|
||||
from loguru import logger
|
||||
|
||||
from src.data_model import BookStructure, ManifestEntry, BookProfile
|
||||
from src.format_extractor import FormatExtractor
|
||||
from src.utils import setup_logger
|
||||
|
||||
logger = setup_logger("fine_grained_extractor")
|
||||
|
||||
class FineGrainedExtractor:
|
||||
"""
|
||||
Extracts translatable text segments from BookStructure.
|
||||
Uses FormatExtractor for detailed content analysis.
|
||||
"""
|
||||
|
||||
SKIP_TRANSLATION_PATTERNS = [
|
||||
r'index\.x?html',
|
||||
r'bibliography\.x?html',
|
||||
r'endnotes?\.x?html',
|
||||
r'footnotes?\.x?html',
|
||||
r'copyright\.x?html',
|
||||
]
|
||||
|
||||
TOC_PATTERNS = [
|
||||
r'nav\.x?html',
|
||||
r'toc\.x?html',
|
||||
]
|
||||
|
||||
def __init__(self, translate_toc: bool = False):
|
||||
self.translate_toc = translate_toc
|
||||
self.format_extractor = FormatExtractor()
|
||||
|
||||
def extract(self, structure: BookStructure, profile: Optional[BookProfile] = None) -> List[ManifestEntry]:
|
||||
"""
|
||||
Extracts translatable segments from the BookStructure.
|
||||
Iteration follows the spine order.
|
||||
"""
|
||||
logger.info("Starting extraction from BookStructure...")
|
||||
manifest_entries = []
|
||||
|
||||
# Iterate over spine to maintain order
|
||||
for item_id in structure.spine:
|
||||
if item_id not in structure.resources:
|
||||
logger.warning(f"Item ID {item_id} in spine but not in resources.")
|
||||
continue
|
||||
|
||||
resource = structure.resources[item_id]
|
||||
|
||||
# Only process HTML/XHTML
|
||||
if resource.media_type != "application/xhtml+xml" or not resource.content:
|
||||
continue
|
||||
|
||||
file_path = resource.href
|
||||
doc_type = self._classify_document(file_path)
|
||||
|
||||
# Parse HTML
|
||||
soup = BeautifulSoup(resource.content, 'html.parser')
|
||||
target_tags = ['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'li']
|
||||
|
||||
for element in soup.find_all(target_tags):
|
||||
# Ensure element has ID (should have been done by Cleaner)
|
||||
element_id = element.get('id')
|
||||
if not element_id:
|
||||
logger.warning(f"Element in {file_path} missing ID, skipping: {element.name}")
|
||||
continue
|
||||
|
||||
# Check translation eligibility
|
||||
raw_text = element.get_text(separator=' ', strip=True)
|
||||
if not raw_text.strip():
|
||||
continue
|
||||
|
||||
is_decorative = self._is_decorative(raw_text)
|
||||
should_translate = self._should_translate(doc_type, is_decorative, raw_text)
|
||||
|
||||
if should_translate:
|
||||
# Extract detailed format
|
||||
outer_html = str(element)
|
||||
clean_text, text_with_ph, ph_map, p_type, _ = self.format_extractor.extract(outer_html)
|
||||
|
||||
if clean_text.strip() and text_with_ph.strip():
|
||||
entry = ManifestEntry(
|
||||
entry_id=f"{file_path}#{element_id}",
|
||||
file_path=file_path,
|
||||
element_id=element_id,
|
||||
original_text=text_with_ph,
|
||||
placeholders=ph_map,
|
||||
context=p_type
|
||||
)
|
||||
manifest_entries.append(entry)
|
||||
|
||||
logger.info(f"Extracted {len(manifest_entries)} entries in total.")
|
||||
return manifest_entries
|
||||
|
||||
def _classify_document(self, file_name: str) -> str:
|
||||
if not file_name: return 'core'
|
||||
fname = file_name.lower()
|
||||
if any(re.search(p, fname) for p in self.SKIP_TRANSLATION_PATTERNS): return 'skip'
|
||||
if any(re.search(p, fname) for p in self.TOC_PATTERNS): return 'toc'
|
||||
return 'core'
|
||||
|
||||
def _should_translate(self, doc_type: str, is_decorative: bool, text: str = "") -> bool:
|
||||
if is_decorative: return False
|
||||
if self._is_roman_numeral(text): return False
|
||||
if doc_type == 'core': return True
|
||||
if doc_type == 'toc': return self.translate_toc
|
||||
return False
|
||||
|
||||
def _is_roman_numeral(self, text: str) -> bool:
|
||||
text = text.strip().upper()
|
||||
if not text: return False
|
||||
pattern = re.compile(r"^M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})$")
|
||||
return bool(pattern.match(text))
|
||||
|
||||
def _is_decorative(self, text: str) -> bool:
|
||||
s = text.strip()
|
||||
if not s: return False
|
||||
if not any(c.isalnum() for c in s): return True
|
||||
if len(s) > 20: return False
|
||||
|
||||
patterns = [
|
||||
r'^[*\-_~•◆◇■□▪▫●○◉◎⦿⦾]+$',
|
||||
r'^[*\-_~•◆◇■□▪▫●○◉◎⦿⦾\s]+$',
|
||||
]
|
||||
for p in patterns:
|
||||
if re.match(p, s): return True
|
||||
|
||||
unique = set(s.replace(' ', ''))
|
||||
if len(unique) <= 3 and (unique & set('*-_~•◆◇■□▪▫●○◉◎⦿⦾')):
|
||||
return True
|
||||
return False
|
||||
@@ -0,0 +1,372 @@
|
||||
import re
|
||||
from bs4 import BeautifulSoup, Tag
|
||||
from typing import Tuple, Dict, List
|
||||
|
||||
class HeadingDetector:
|
||||
"""Detects heading types and paragraph roles."""
|
||||
|
||||
CHAPTER_PATTERNS = [
|
||||
r'^(chapter|chap\.?|part)\s+([0-9]+|[ivxlc]+|[a-z])',
|
||||
r'^(第\s*[0-9一二三四五六七八九十百]+\s*[章节部篇])',
|
||||
r'^(\d+|[IVXLC]+|[A-Z])\.$'
|
||||
]
|
||||
|
||||
EPIGRAPH_CLASSES = {
|
||||
'epigraph', 'quote', 'blockquote', 'motto',
|
||||
'dedication', 'verse', 'poetry', 'poem'
|
||||
}
|
||||
|
||||
def detect(self, element: Tag, text: str) -> str:
|
||||
if self._is_epigraph(element):
|
||||
return "epigraph"
|
||||
tag_name = element.name.lower()
|
||||
if tag_name in ['h1', 'h2']:
|
||||
return "chapter" if self._matches_chapter_pattern(text) else "section"
|
||||
if tag_name == 'h3':
|
||||
return "section"
|
||||
if tag_name in ['h4', 'h5', 'h6']:
|
||||
return "subsection"
|
||||
if self._is_pseudo_heading(element, text):
|
||||
return "subsection"
|
||||
return "body"
|
||||
|
||||
def _is_epigraph(self, element: Tag) -> bool:
|
||||
if element.name == 'blockquote':
|
||||
return True
|
||||
current = element
|
||||
for _ in range(3):
|
||||
if not current: break
|
||||
classes = current.get('class', [])
|
||||
if isinstance(classes, list):
|
||||
classes = ' '.join(classes)
|
||||
if any(k in classes.lower() for k in self.EPIGRAPH_CLASSES):
|
||||
return True
|
||||
current = current.parent
|
||||
return False
|
||||
|
||||
def _matches_chapter_pattern(self, text: str) -> bool:
|
||||
text = text.strip().lower()
|
||||
for pattern in self.CHAPTER_PATTERNS:
|
||||
if re.match(pattern, text, re.IGNORECASE):
|
||||
return True
|
||||
return False
|
||||
|
||||
def _is_pseudo_heading(self, element: Tag, text: str) -> bool:
|
||||
if element.name != 'p':
|
||||
return False
|
||||
text = text.strip()
|
||||
if not text or len(text) > 80:
|
||||
return False
|
||||
children = list(element.children)
|
||||
if len(children) == 1 and isinstance(children[0], Tag):
|
||||
if children[0].name in ['strong', 'b']:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
class FormatExtractor:
|
||||
"""
|
||||
HTML Format Extractor (Ported from v0.09 v3)
|
||||
Handles inline styles, formulas, and drop caps.
|
||||
"""
|
||||
|
||||
FORMULA_CHARS = re.compile(
|
||||
r'^[\d\s\+\-\×\÷\=\(\)\[\]\{\}\<\>\^\*\/\.\,\;\:\'\"\`\~\@\#\$\%\&\|\\'
|
||||
r'αβγδεζηθικλμνξοπρστυφχψωΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩ'
|
||||
r'a-zA-Z]+$'
|
||||
)
|
||||
|
||||
def __init__(self):
|
||||
self.detector = HeadingDetector()
|
||||
|
||||
def extract(self, element_html: str) -> Tuple[str, str, Dict[str, str], str, List[str]]:
|
||||
"""
|
||||
Extracts format information.
|
||||
|
||||
Returns:
|
||||
clean_text: Pure text
|
||||
text_with_placeholders: Text with inline placeholders
|
||||
placeholder_map: Map of placeholders
|
||||
paragraph_type: Detected type
|
||||
endnote_anchors: List of detected endnote IDs
|
||||
"""
|
||||
soup = BeautifulSoup(element_html, 'html.parser')
|
||||
root = list(soup.children)[0] if list(soup.children) else soup
|
||||
|
||||
clean_text = root.get_text().strip()
|
||||
clean_text = re.sub(r'\s+', ' ', clean_text)
|
||||
p_type = self.detector.detect(root, clean_text) if isinstance(root, Tag) else "body"
|
||||
|
||||
inner_html = root.decode_contents() if isinstance(root, Tag) else str(root)
|
||||
|
||||
text_with_ph, local_map = self._smart_extract_v3(inner_html)
|
||||
|
||||
if text_with_ph:
|
||||
text_with_ph = re.sub(r'\s+', ' ', text_with_ph).strip()
|
||||
|
||||
# Verify integrity
|
||||
stripped_text = self._strip_placeholders(text_with_ph)
|
||||
stripped_text = re.sub(r'\s+', ' ', stripped_text).strip()
|
||||
|
||||
if not self._verify_content_integrity(clean_text, stripped_text):
|
||||
# Fallback
|
||||
text_with_ph, local_map = self._fallback_extract(inner_html, clean_text)
|
||||
|
||||
endnote_anchors = []
|
||||
for pid, html in local_map.items():
|
||||
if pid.startswith("_"):
|
||||
continue
|
||||
if re.match(r'<(span|a)\s+id="[a-zA-Z][a-zA-Z0-9]{2,5}"\s*>\s*</\1>', html):
|
||||
endnote_anchors.append(pid)
|
||||
|
||||
return clean_text, text_with_ph, local_map, p_type, endnote_anchors
|
||||
|
||||
def _strip_placeholders(self, text: str) -> str:
|
||||
return re.sub(r'φ/?[0-9]+φ', '', text)
|
||||
|
||||
def _verify_content_integrity(self, clean_text: str, stripped_text: str) -> bool:
|
||||
def normalize(s):
|
||||
s = re.sub(r'\s+', '', s)
|
||||
s = s.lower()
|
||||
return s
|
||||
|
||||
norm_clean = normalize(clean_text)
|
||||
norm_stripped = normalize(stripped_text)
|
||||
|
||||
if norm_clean == norm_stripped:
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def _fallback_extract(self, inner_html: str, clean_text: str) -> Tuple[str, Dict[str, str]]:
|
||||
return clean_text, {"_prefix": "", "_suffix": ""}
|
||||
|
||||
def _smart_extract_v3(self, inner_html: str) -> Tuple[str, Dict[str, str]]:
|
||||
parts = re.split(r'(<[^>]+>)', inner_html)
|
||||
parts = [p for p in parts if p]
|
||||
|
||||
if not parts:
|
||||
return "", {"_prefix": "", "_suffix": ""}
|
||||
|
||||
part_types = []
|
||||
for part in parts:
|
||||
if part.startswith('<'):
|
||||
part_types.append('tag')
|
||||
elif not part.strip():
|
||||
part_types.append('whitespace')
|
||||
elif self._is_translatable_text(part):
|
||||
part_types.append('translatable')
|
||||
else:
|
||||
part_types.append('formula')
|
||||
|
||||
first_trans_idx = None
|
||||
last_trans_idx = None
|
||||
for i, t in enumerate(part_types):
|
||||
if t == 'translatable':
|
||||
if first_trans_idx is None:
|
||||
first_trans_idx = i
|
||||
last_trans_idx = i
|
||||
|
||||
if first_trans_idx is None:
|
||||
return "", {"_prefix": inner_html, "_suffix": ""}
|
||||
|
||||
# Prefix Separation
|
||||
safe_prefix_end = 0
|
||||
for i in range(first_trans_idx):
|
||||
if part_types[i] == 'tag':
|
||||
tag = parts[i]
|
||||
is_self_closing = tag.endswith('/>') or re.match(r'<(br|hr|img|meta|link)\b', tag, re.I)
|
||||
is_closing = tag.startswith('</')
|
||||
if is_self_closing or is_closing:
|
||||
safe_prefix_end = i + 1
|
||||
else:
|
||||
break
|
||||
elif part_types[i] == 'whitespace':
|
||||
safe_prefix_end = i + 1
|
||||
else:
|
||||
break
|
||||
|
||||
# Suffix Separation
|
||||
safe_suffix_start = len(parts)
|
||||
for i in range(len(parts) - 1, last_trans_idx, -1):
|
||||
if part_types[i] == 'tag':
|
||||
tag = parts[i]
|
||||
is_closing = tag.startswith('</')
|
||||
is_self_closing = tag.endswith('/>') or re.match(r'<(br|hr|img|meta|link)\b', tag, re.I)
|
||||
if is_closing or is_self_closing:
|
||||
safe_suffix_start = i
|
||||
else:
|
||||
break
|
||||
elif part_types[i] == 'whitespace':
|
||||
safe_suffix_start = i
|
||||
else:
|
||||
break
|
||||
|
||||
prefix_parts = parts[:safe_prefix_end]
|
||||
middle_parts = parts[safe_prefix_end:safe_suffix_start]
|
||||
middle_types = part_types[safe_prefix_end:safe_suffix_start]
|
||||
suffix_parts = parts[safe_suffix_start:]
|
||||
|
||||
# Drop Cap Check
|
||||
if prefix_parts and middle_parts:
|
||||
prefix_parts, middle_parts, middle_types = self._handle_drop_cap(
|
||||
prefix_parts, middle_parts, middle_types
|
||||
)
|
||||
|
||||
local_map = {}
|
||||
if prefix_parts:
|
||||
local_map["_prefix"] = "".join(prefix_parts)
|
||||
if suffix_parts:
|
||||
local_map["_suffix"] = "".join(suffix_parts)
|
||||
|
||||
# Middle processing
|
||||
placeholder_counter = 1
|
||||
result_parts = []
|
||||
tag_stack = []
|
||||
|
||||
i = 0
|
||||
while i < len(middle_parts):
|
||||
part = middle_parts[i]
|
||||
ptype = middle_types[i]
|
||||
|
||||
if ptype == 'translatable':
|
||||
result_parts.append(part)
|
||||
i += 1
|
||||
|
||||
elif ptype == 'tag':
|
||||
is_closing = part.startswith('</')
|
||||
if is_closing:
|
||||
if tag_stack:
|
||||
open_id, open_tag = tag_stack.pop()
|
||||
local_map[f"/{open_id}"] = part
|
||||
result_parts.append(f"φ/{open_id}φ")
|
||||
else:
|
||||
pid = str(placeholder_counter)
|
||||
placeholder_counter += 1
|
||||
local_map[pid] = part
|
||||
result_parts.append(f"φ{pid}φ")
|
||||
i += 1
|
||||
else:
|
||||
has_translatable_after = False
|
||||
for j in range(i + 1, len(middle_parts)):
|
||||
if middle_types[j] == 'translatable':
|
||||
has_translatable_after = True
|
||||
break
|
||||
elif middle_types[j] == 'tag' and middle_parts[j].startswith('</'):
|
||||
break
|
||||
|
||||
if has_translatable_after:
|
||||
pid = str(placeholder_counter)
|
||||
placeholder_counter += 1
|
||||
local_map[pid] = part
|
||||
result_parts.append(f"φ{pid}φ")
|
||||
tag_stack.append((pid, part))
|
||||
i += 1
|
||||
else:
|
||||
block_parts = []
|
||||
while i < len(middle_parts) and middle_types[i] != 'translatable':
|
||||
block_parts.append(middle_parts[i])
|
||||
i += 1
|
||||
if block_parts:
|
||||
block_html = "".join(block_parts)
|
||||
pid = str(placeholder_counter)
|
||||
placeholder_counter += 1
|
||||
local_map[pid] = block_html
|
||||
result_parts.append(f"φ{pid}φ")
|
||||
else:
|
||||
result_parts.append(part)
|
||||
i += 1
|
||||
|
||||
text_with_ph = "".join(result_parts)
|
||||
text_with_ph = re.sub(r'\s+', ' ', text_with_ph).strip()
|
||||
|
||||
# Merge consecutive placeholders
|
||||
def merge_match(m):
|
||||
full_match = m.group(0)
|
||||
pids = re.findall(r'φ(/?\d+)φ', full_match)
|
||||
if len(pids) <= 1:
|
||||
return full_match
|
||||
|
||||
merged_html = ""
|
||||
for pid in pids:
|
||||
if pid in local_map:
|
||||
merged_html += local_map[pid]
|
||||
del local_map[pid]
|
||||
|
||||
new_pid = pids[0] if pids[0].isdigit() else pids[0][1:]
|
||||
local_map[new_pid] = merged_html
|
||||
return f"φ{new_pid}φ"
|
||||
|
||||
text_with_ph = re.sub(r'(φ/?\d+φ)(φ/?\d+φ)+', merge_match, text_with_ph)
|
||||
|
||||
return text_with_ph, local_map
|
||||
|
||||
def _handle_drop_cap(self, prefix_parts: List[str], middle_parts: List[str], middle_types: List[str]):
|
||||
if not prefix_parts or not middle_parts:
|
||||
return prefix_parts, middle_parts, middle_types
|
||||
|
||||
prefix_text = ""
|
||||
for part in prefix_parts:
|
||||
if not part.startswith('<'):
|
||||
prefix_text = part.strip()
|
||||
|
||||
if not prefix_text or len(prefix_text) != 1 or not prefix_text.isupper():
|
||||
return prefix_parts, middle_parts, middle_types
|
||||
|
||||
first_middle_text = ""
|
||||
first_middle_idx = -1
|
||||
for i, (part, ptype) in enumerate(zip(middle_parts, middle_types)):
|
||||
if ptype == 'translatable':
|
||||
first_middle_text = part.strip()
|
||||
first_middle_idx = i
|
||||
break
|
||||
|
||||
if not first_middle_text:
|
||||
return prefix_parts, middle_parts, middle_types
|
||||
|
||||
is_drop_cap = False
|
||||
first_char = first_middle_text[0] if first_middle_text else ''
|
||||
if first_char.islower() or first_char.isupper():
|
||||
is_drop_cap = True
|
||||
|
||||
combined = prefix_text + first_middle_text.split()[0] if first_middle_text else ""
|
||||
if not (len(combined) >= 2 and combined.isalpha()):
|
||||
return prefix_parts, middle_parts, middle_types
|
||||
|
||||
new_prefix = []
|
||||
skip_until_close = False
|
||||
found_letter = False
|
||||
|
||||
for part in prefix_parts:
|
||||
if part.startswith('<') and not part.startswith('</'):
|
||||
skip_until_close = True
|
||||
elif part.startswith('</'):
|
||||
if skip_until_close:
|
||||
skip_until_close = False
|
||||
continue
|
||||
new_prefix.append(part)
|
||||
elif part.strip() == prefix_text:
|
||||
found_letter = True
|
||||
continue
|
||||
else:
|
||||
if not skip_until_close:
|
||||
new_prefix.append(part)
|
||||
|
||||
if found_letter:
|
||||
middle_parts = middle_parts.copy()
|
||||
middle_parts[first_middle_idx] = prefix_text + middle_parts[first_middle_idx]
|
||||
prefix_parts = new_prefix
|
||||
|
||||
return prefix_parts, middle_parts, middle_types
|
||||
|
||||
def _is_translatable_text(self, text: str) -> bool:
|
||||
text = text.strip()
|
||||
if not text:
|
||||
return False
|
||||
if re.search(r'[a-zA-Z]{3,}', text):
|
||||
return True
|
||||
if ' ' in text and re.search(r'[a-zA-Z]', text):
|
||||
return True
|
||||
if re.search(r'\d', text):
|
||||
return True
|
||||
return False
|
||||
@@ -0,0 +1,70 @@
|
||||
import re
|
||||
from typing import Dict, Tuple, List, Optional
|
||||
from loguru import logger
|
||||
from src.utils import setup_logger
|
||||
|
||||
logger = setup_logger("format_restorer")
|
||||
|
||||
class FormatRestorer:
|
||||
"""
|
||||
Restores HTML formatting from placeholders.
|
||||
"""
|
||||
|
||||
PLACEHOLDER_REGEX = re.compile(r'φ(/?\d+)φ')
|
||||
|
||||
def restore(self, text_with_placeholders: str, placeholder_map: Dict[str, str]) -> Tuple[str, bool]:
|
||||
"""
|
||||
Restores HTML from text with placeholders.
|
||||
Returns (restored_html, success).
|
||||
"""
|
||||
if not placeholder_map:
|
||||
return text_with_placeholders or "", True
|
||||
|
||||
if not text_with_placeholders:
|
||||
prefix = placeholder_map.get("_prefix", "")
|
||||
suffix = placeholder_map.get("_suffix", "")
|
||||
return prefix + suffix, True
|
||||
|
||||
prefix = placeholder_map.get("_prefix", "")
|
||||
suffix = placeholder_map.get("_suffix", "")
|
||||
|
||||
inner_map = {k: v for k, v in placeholder_map.items() if not k.startswith("_")}
|
||||
|
||||
found_ids = set(self.PLACEHOLDER_REGEX.findall(text_with_placeholders))
|
||||
expected_ids = set(inner_map.keys())
|
||||
|
||||
success = True
|
||||
missing_ids = expected_ids - found_ids
|
||||
if missing_ids:
|
||||
logger.warning(f"Restoration warning: missing placeholders {missing_ids}")
|
||||
success = False
|
||||
|
||||
unknown_ids = found_ids - expected_ids
|
||||
if unknown_ids:
|
||||
real_unknowns = set()
|
||||
for pid in unknown_ids:
|
||||
if pid.startswith('/') and pid[1:] in expected_ids:
|
||||
continue
|
||||
real_unknowns.add(pid)
|
||||
|
||||
if real_unknowns:
|
||||
logger.warning(f"Restoration warning: unknown placeholders {real_unknowns}")
|
||||
success = False
|
||||
|
||||
def replace_match(match):
|
||||
pid = match.group(1)
|
||||
if pid in inner_map:
|
||||
return inner_map[pid]
|
||||
else:
|
||||
return ""
|
||||
|
||||
try:
|
||||
restored_inner = self.PLACEHOLDER_REGEX.sub(replace_match, text_with_placeholders)
|
||||
restored_html = prefix + restored_inner + suffix
|
||||
return restored_html, success
|
||||
except Exception as e:
|
||||
logger.error(f"Restoration failed: {e}")
|
||||
return prefix + self._strip_placeholders(text_with_placeholders) + suffix, False
|
||||
|
||||
def _strip_placeholders(self, text: str) -> str:
|
||||
return self.PLACEHOLDER_REGEX.sub("", text)
|
||||
@@ -0,0 +1,220 @@
|
||||
import asyncio
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import List, Dict, Optional
|
||||
from openai import AsyncOpenAI
|
||||
from tenacity import retry, stop_after_attempt, wait_exponential
|
||||
from loguru import logger
|
||||
|
||||
from src.data_model import ManifestEntry
|
||||
from src.utils import setup_logger, ensure_directory
|
||||
|
||||
logger = setup_logger("llm_client")
|
||||
|
||||
# Default chunk save directory (can be overridden)
|
||||
DEFAULT_CHUNK_DIR = Path("tmp/chunks")
|
||||
|
||||
|
||||
class RateLimiter:
|
||||
"""Rate limiter for concurrency and RPM."""
|
||||
def __init__(self, requests_per_minute: int, concurrent_requests: int):
|
||||
self.semaphore = asyncio.Semaphore(concurrent_requests)
|
||||
self.min_interval = 60.0 / requests_per_minute if requests_per_minute > 0 else 0
|
||||
self.last_request_time = 0
|
||||
self._lock = asyncio.Lock()
|
||||
|
||||
async def acquire(self):
|
||||
await self.semaphore.acquire()
|
||||
async with self._lock:
|
||||
current_time = time.time()
|
||||
wait_time = self.min_interval - (current_time - self.last_request_time)
|
||||
if wait_time > 0:
|
||||
await asyncio.sleep(wait_time)
|
||||
self.last_request_time = time.time()
|
||||
|
||||
def release(self):
|
||||
self.semaphore.release()
|
||||
|
||||
|
||||
class LLMClient:
|
||||
"""Generic OpenAI-compatible API Client with short ID strategy."""
|
||||
|
||||
def __init__(self, api_key: str, base_url: str, model: str = "gpt-3.5-turbo",
|
||||
requests_per_minute: int = 60, concurrent_requests: int = 5,
|
||||
extra_headers: Dict = None, chunk_dir: Path = None):
|
||||
|
||||
# Configure proxy client to avoid SOCKS issues and ensure connectivity
|
||||
import httpx
|
||||
import os
|
||||
|
||||
# Prefer HTTP proxy if available to avoid missing socksio support
|
||||
proxy_url = os.environ.get("http_proxy") or os.environ.get("https_proxy")
|
||||
http_client = httpx.AsyncClient(
|
||||
proxy=proxy_url,
|
||||
timeout=60.0,
|
||||
follow_redirects=True
|
||||
) if proxy_url else None
|
||||
|
||||
self.client = AsyncOpenAI(
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
default_headers=extra_headers,
|
||||
http_client=http_client
|
||||
)
|
||||
self.model = model
|
||||
|
||||
self.rate_limiter = RateLimiter(requests_per_minute, concurrent_requests)
|
||||
self.prompts = self._load_prompts()
|
||||
self._chunk_counter = 0
|
||||
|
||||
# Chunk directory for debug output
|
||||
self.chunk_dir = chunk_dir or DEFAULT_CHUNK_DIR
|
||||
ensure_directory(self.chunk_dir)
|
||||
|
||||
def _load_prompts(self) -> Dict:
|
||||
try:
|
||||
with open("config/prompts.json", "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to load config/prompts.json: {e}")
|
||||
return {}
|
||||
|
||||
async def translate_chunk(self, items: List[ManifestEntry], glossary: Dict = None,
|
||||
instruction: str = None, mode: str = "bilingual") -> Dict[str, str]:
|
||||
"""
|
||||
Translate a chunk of items using short ID strategy.
|
||||
Returns: Dict[entry_id, translated_text]
|
||||
"""
|
||||
if not items: return {}
|
||||
|
||||
# Build prompt with short IDs
|
||||
id_map, prompt = self._build_prompt_with_short_ids(items)
|
||||
|
||||
try:
|
||||
# Build System Prompt
|
||||
base_sys_prompt = self.prompts.get("translation", {}).get("system",
|
||||
"You are a professional English to Chinese translator.")
|
||||
|
||||
if instruction:
|
||||
base_sys_prompt += f"\n\nBook Style Guide:\n{instruction}"
|
||||
|
||||
if glossary:
|
||||
glossary_text = "\n".join([f"{k} -> {v}" for k, v in glossary.items()])
|
||||
base_sys_prompt += f"\n\nTerminology:\n{glossary_text}"
|
||||
|
||||
# Short ID format instructions
|
||||
base_sys_prompt += """
|
||||
|
||||
Output Format:
|
||||
- Each line MUST start with #N: (keep this ID exactly as given)
|
||||
- Preserve any φXφ or φ/Xφ placeholders EXACTLY as-is
|
||||
- Only output translations, no explanations
|
||||
- Match the number of output lines to input lines"""
|
||||
|
||||
# Save chunk before translation
|
||||
chunk_id = self._save_chunk("before", prompt, base_sys_prompt)
|
||||
|
||||
logger.debug(f"Sending request to LLM (Chunk: {chunk_id}, Items: {len(items)})")
|
||||
|
||||
raw_response = await self._make_request(base_sys_prompt, prompt)
|
||||
|
||||
# Save chunk after translation
|
||||
self._save_chunk("after", raw_response, base_sys_prompt, chunk_id)
|
||||
|
||||
# Parse with short ID mapping
|
||||
results = self._parse_short_id_response(raw_response, id_map)
|
||||
return results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Translation failed: {e}")
|
||||
return {item.entry_id: f"[Error - {str(e)}]" for item in items}
|
||||
|
||||
def _build_prompt_with_short_ids(self, items: List[ManifestEntry]) -> tuple:
|
||||
"""
|
||||
Build prompt with short IDs (#1, #2, ...).
|
||||
Returns: (id_map, prompt_text)
|
||||
"""
|
||||
id_map = {} # short_id -> entry_id
|
||||
lines = []
|
||||
|
||||
for i, item in enumerate(items, 1):
|
||||
short_id = f"#{i}"
|
||||
id_map[short_id] = item.entry_id
|
||||
|
||||
# Clean text (remove extra whitespace)
|
||||
text = re.sub(r'\s+', ' ', item.original_text).strip()
|
||||
lines.append(f"{short_id}: {text}")
|
||||
|
||||
return id_map, "\n".join(lines)
|
||||
|
||||
def _parse_short_id_response(self, response: str, id_map: Dict[str, str]) -> Dict[str, str]:
|
||||
"""
|
||||
Parse response with short ID format.
|
||||
Returns: Dict[entry_id, translated_text]
|
||||
"""
|
||||
results = {}
|
||||
|
||||
for line in response.split("\n"):
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
|
||||
# Match #N: pattern
|
||||
match = re.match(r'^#(\d+):\s*(.+)$', line)
|
||||
if match:
|
||||
short_id = f"#{match.group(1)}"
|
||||
translation = match.group(2).strip()
|
||||
|
||||
if short_id in id_map:
|
||||
full_id = id_map[short_id]
|
||||
results[full_id] = translation
|
||||
else:
|
||||
logger.warning(f"Unknown short ID in response: {short_id}")
|
||||
|
||||
return results
|
||||
|
||||
def _save_chunk(self, stage: str, content: str, system_prompt: str = None,
|
||||
chunk_id: str = None) -> str:
|
||||
"""Save chunk to tmp directory for debugging."""
|
||||
if chunk_id is None:
|
||||
self._chunk_counter += 1
|
||||
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
chunk_id = f"{timestamp}_{self._chunk_counter:04d}"
|
||||
|
||||
filename = self.chunk_dir / f"chunk_{chunk_id}_{stage}.txt"
|
||||
|
||||
with open(filename, "w", encoding="utf-8") as f:
|
||||
if system_prompt and stage == "before":
|
||||
f.write("=== SYSTEM PROMPT ===\n")
|
||||
f.write(system_prompt)
|
||||
f.write("\n\n=== USER PROMPT ===\n")
|
||||
f.write(content)
|
||||
|
||||
logger.debug(f"Saved chunk: {filename}")
|
||||
return chunk_id
|
||||
|
||||
async def raw_chat_completion(self, system_prompt: str, user_prompt: str) -> str:
|
||||
"""Generic chat completion."""
|
||||
return await self._make_request(system_prompt, user_prompt)
|
||||
|
||||
@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=2, max=10))
|
||||
async def _make_request(self, system_prompt: str, user_prompt: str) -> str:
|
||||
await self.rate_limiter.acquire()
|
||||
try:
|
||||
resp = await self.client.chat.completions.create(
|
||||
model=self.model,
|
||||
messages=[
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user", "content": user_prompt}
|
||||
],
|
||||
temperature=0.3,
|
||||
)
|
||||
return resp.choices[0].message.content.strip()
|
||||
finally:
|
||||
self.rate_limiter.release()
|
||||
|
||||
async def close(self):
|
||||
await self.client.close()
|
||||
@@ -0,0 +1,74 @@
|
||||
from pathlib import Path
|
||||
from typing import List, Dict, Optional
|
||||
import json
|
||||
from src.data_model import ManifestEntry
|
||||
from src.utils import setup_logger
|
||||
|
||||
logger = setup_logger("manifest_manager")
|
||||
|
||||
class ManifestManager:
|
||||
"""
|
||||
Manages the translation manifest (Source of Truth).
|
||||
Handles persistence and state updates.
|
||||
"""
|
||||
|
||||
def __init__(self, manifest_path: Path):
|
||||
self.manifest_path = manifest_path
|
||||
self.entries: List[ManifestEntry] = []
|
||||
self._entries_map: Dict[str, ManifestEntry] = {}
|
||||
|
||||
def load(self):
|
||||
"""Loads manifest from disk if it exists."""
|
||||
if not self.manifest_path.exists():
|
||||
logger.info(f"Manifest not found at {self.manifest_path}, starting empty.")
|
||||
return
|
||||
|
||||
try:
|
||||
with open(self.manifest_path, 'r', encoding='utf-8') as f:
|
||||
data = json.load(f)
|
||||
self.entries = [ManifestEntry.model_validate(item) for item in data]
|
||||
self._rebuild_map()
|
||||
logger.info(f"Loaded {len(self.entries)} entries from manifest.")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to load manifest: {e}")
|
||||
raise
|
||||
|
||||
def save(self):
|
||||
"""Saves current state to disk."""
|
||||
try:
|
||||
# Pydantic v2: model_dump(mode='json') or just list dump
|
||||
data = [entry.model_dump(mode='json') for entry in self.entries]
|
||||
with open(self.manifest_path, 'w', encoding='utf-8') as f:
|
||||
json.dump(data, f, indent=2, ensure_ascii=False)
|
||||
logger.info(f"Saved {len(self.entries)} entries to manifest.")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to save manifest: {e}")
|
||||
raise
|
||||
|
||||
def add_entries(self, new_entries: List[ManifestEntry]):
|
||||
"""
|
||||
Adds new entries to the manifest.
|
||||
If an entry with the same ID exists, it keeps the EXISTING one (to preserve translations).
|
||||
"""
|
||||
count = 0
|
||||
for entry in new_entries:
|
||||
if entry.entry_id not in self._entries_map:
|
||||
self.entries.append(entry)
|
||||
self._entries_map[entry.entry_id] = entry
|
||||
count += 1
|
||||
|
||||
if count > 0:
|
||||
logger.info(f"Added {count} new entries to manifest.")
|
||||
|
||||
def update_translation(self, entry_id: str, translation: str):
|
||||
"""Updates translation for a specific entry."""
|
||||
if entry_id in self._entries_map:
|
||||
self._entries_map[entry_id].translated_text = translation
|
||||
else:
|
||||
logger.warning(f"Attempted to update translation for unknown ID: {entry_id}")
|
||||
|
||||
def get_entry(self, entry_id: str) -> Optional[ManifestEntry]:
|
||||
return self._entries_map.get(entry_id)
|
||||
|
||||
def _rebuild_map(self):
|
||||
self._entries_map = {e.entry_id: e for e in self.entries}
|
||||
@@ -0,0 +1,285 @@
|
||||
"""
|
||||
Translator Module - Handles translation of ManifestEntry items.
|
||||
|
||||
Key features:
|
||||
- Character-based chunking (~5000 chars per chunk)
|
||||
- Chapter-aware grouping (chunks don't cross file boundaries)
|
||||
- Concurrent translation with asyncio.gather
|
||||
- Progress tracking and error handling
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from typing import List, Dict
|
||||
from collections import defaultdict
|
||||
from loguru import logger
|
||||
|
||||
from src.data_model import ManifestEntry, BookProfile
|
||||
from src.llm_client import LLMClient
|
||||
from src.format_restorer import FormatRestorer
|
||||
from src.utils import setup_logger
|
||||
|
||||
logger = setup_logger("translator")
|
||||
|
||||
# Default chunk size in characters
|
||||
DEFAULT_CHUNK_SIZE = 5000
|
||||
# Maximum concurrent translations
|
||||
MAX_CONCURRENT = 5
|
||||
|
||||
|
||||
class Translator:
|
||||
"""
|
||||
Translates ManifestEntry items using LLM with chapter-aware chunking.
|
||||
Supports both sequential and concurrent translation modes.
|
||||
"""
|
||||
|
||||
def __init__(self, llm_client: LLMClient, chunk_size: int = DEFAULT_CHUNK_SIZE,
|
||||
max_concurrent: int = MAX_CONCURRENT):
|
||||
self.llm_client = llm_client
|
||||
self.chunk_size = chunk_size
|
||||
self.max_concurrent = max_concurrent
|
||||
self.restorer = FormatRestorer()
|
||||
|
||||
async def translate(self, entries: List[ManifestEntry], profile: BookProfile,
|
||||
concurrent: bool = True) -> List[ManifestEntry]:
|
||||
"""
|
||||
Translates all untranslated entries.
|
||||
|
||||
Args:
|
||||
entries: All manifest entries
|
||||
profile: Book profile with style guide
|
||||
concurrent: Use concurrent translation (default True)
|
||||
|
||||
Returns:
|
||||
The same entries list with translated_text populated
|
||||
"""
|
||||
untranslated = [e for e in entries if not e.translated_text]
|
||||
if not untranslated:
|
||||
logger.info("No new entries to translate.")
|
||||
return entries
|
||||
|
||||
logger.info(f"Found {len(untranslated)} entries to translate")
|
||||
|
||||
# Group by chapter (file_path)
|
||||
chapters = self._group_by_chapter(untranslated)
|
||||
logger.info(f"Grouped into {len(chapters)} chapters")
|
||||
|
||||
# Create all chunks
|
||||
all_chunks = []
|
||||
for file_path, chapter_entries in chapters.items():
|
||||
chapter_chunks = self._create_char_based_chunks(chapter_entries)
|
||||
for chunk in chapter_chunks:
|
||||
all_chunks.append((file_path, chunk))
|
||||
|
||||
total_chunks = len(all_chunks)
|
||||
logger.info(f"Created {total_chunks} chunks (avg ~{self.chunk_size} chars each)")
|
||||
|
||||
if concurrent:
|
||||
await self._translate_concurrent(all_chunks, profile)
|
||||
else:
|
||||
await self._translate_sequential(all_chunks, profile)
|
||||
|
||||
translated_count = sum(1 for e in entries if e.translated_text)
|
||||
logger.info(f"Translation complete: {translated_count}/{len(entries)} entries translated")
|
||||
return entries
|
||||
|
||||
async def _translate_concurrent(self, all_chunks: List, profile: BookProfile):
|
||||
"""Translate chunks concurrently with semaphore control."""
|
||||
semaphore = asyncio.Semaphore(self.max_concurrent)
|
||||
completed = [0] # Use list for mutable counter in closure
|
||||
total = len(all_chunks)
|
||||
success = [0]
|
||||
failed = [0]
|
||||
|
||||
async def translate_chunk_task(file_path: str, chunk: List[ManifestEntry], idx: int):
|
||||
async with semaphore:
|
||||
try:
|
||||
results = await self.llm_client.translate_chunk(
|
||||
chunk,
|
||||
instruction=profile.style_guide if profile else None,
|
||||
mode="bilingual"
|
||||
)
|
||||
|
||||
for entry in chunk:
|
||||
if entry.entry_id in results:
|
||||
entry.translated_text = results[entry.entry_id]
|
||||
success[0] += 1
|
||||
else:
|
||||
failed[0] += 1
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Chunk {idx} failed: {e}")
|
||||
failed[0] += len(chunk)
|
||||
finally:
|
||||
completed[0] += 1
|
||||
if completed[0] % 5 == 0 or completed[0] == total:
|
||||
logger.info(f"Progress: {completed[0]}/{total} chunks ({success[0]} translated)")
|
||||
|
||||
tasks = [
|
||||
translate_chunk_task(file_path, chunk, i)
|
||||
for i, (file_path, chunk) in enumerate(all_chunks)
|
||||
]
|
||||
await asyncio.gather(*tasks)
|
||||
|
||||
logger.info(f"Concurrent translation: {success[0]} success, {failed[0]} failed")
|
||||
|
||||
async def _translate_sequential(self, all_chunks: List, profile: BookProfile):
|
||||
"""Translate chunks sequentially."""
|
||||
total_chunks = len(all_chunks)
|
||||
success_count = 0
|
||||
fail_count = 0
|
||||
|
||||
for idx, (file_path, chunk) in enumerate(all_chunks):
|
||||
try:
|
||||
results = await self.llm_client.translate_chunk(
|
||||
chunk,
|
||||
instruction=profile.style_guide if profile else None,
|
||||
mode="bilingual"
|
||||
)
|
||||
|
||||
for entry in chunk:
|
||||
if entry.entry_id in results:
|
||||
entry.translated_text = results[entry.entry_id]
|
||||
success_count += 1
|
||||
else:
|
||||
fail_count += 1
|
||||
logger.warning(f"Missing translation for: {entry.entry_id[-40:]}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Chunk {idx} translation failed: {e}")
|
||||
fail_count += len(chunk)
|
||||
|
||||
if (idx + 1) % 10 == 0 or idx + 1 == total_chunks:
|
||||
logger.info(f"Progress: {idx + 1}/{total_chunks} chunks ({success_count} entries translated)")
|
||||
|
||||
logger.info(f"Sequential translation: {success_count} success, {fail_count} failed")
|
||||
|
||||
|
||||
async def translate_chapter(self, entries: List[ManifestEntry], file_path: str,
|
||||
profile: BookProfile) -> Dict[str, int]:
|
||||
"""
|
||||
Translate a single chapter.
|
||||
|
||||
Args:
|
||||
entries: All entries (will filter by file_path)
|
||||
file_path: Chapter file path to translate
|
||||
profile: Book profile
|
||||
|
||||
Returns:
|
||||
Dict with 'success' and 'failed' counts
|
||||
"""
|
||||
chapter_entries = [e for e in entries if e.file_path == file_path and not e.translated_text]
|
||||
|
||||
if not chapter_entries:
|
||||
logger.info(f"Chapter {file_path} has no untranslated entries")
|
||||
return {"success": 0, "failed": 0}
|
||||
|
||||
logger.info(f"Translating chapter: {file_path} ({len(chapter_entries)} entries)")
|
||||
|
||||
chunks = self._create_char_based_chunks(chapter_entries)
|
||||
logger.info(f"Created {len(chunks)} chunks")
|
||||
|
||||
success = 0
|
||||
failed = 0
|
||||
|
||||
for i, chunk in enumerate(chunks, 1):
|
||||
chunk_chars = sum(len(e.original_text) for e in chunk)
|
||||
logger.debug(f"Chunk {i}/{len(chunks)}: {len(chunk)} entries, {chunk_chars} chars")
|
||||
|
||||
try:
|
||||
results = await self.llm_client.translate_chunk(
|
||||
chunk,
|
||||
instruction=profile.style_guide if profile else None,
|
||||
mode="bilingual"
|
||||
)
|
||||
|
||||
for entry in chunk:
|
||||
if entry.entry_id in results:
|
||||
entry.translated_text = results[entry.entry_id]
|
||||
|
||||
# Verify placeholder preservation
|
||||
if entry.placeholders:
|
||||
_, restored_ok = self.restorer.restore(
|
||||
entry.translated_text,
|
||||
entry.placeholders
|
||||
)
|
||||
if not restored_ok:
|
||||
logger.warning(f"Placeholder issue: {entry.entry_id[-40:]}")
|
||||
|
||||
success += 1
|
||||
else:
|
||||
failed += 1
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Chunk {i} failed: {e}")
|
||||
failed += len(chunk)
|
||||
|
||||
logger.info(f"Chapter done: {success} success, {failed} failed")
|
||||
return {"success": success, "failed": failed}
|
||||
|
||||
def _group_by_chapter(self, entries: List[ManifestEntry]) -> Dict[str, List[ManifestEntry]]:
|
||||
"""Group entries by file_path (chapter)."""
|
||||
chapters = defaultdict(list)
|
||||
for entry in entries:
|
||||
chapters[entry.file_path].append(entry)
|
||||
return dict(chapters)
|
||||
|
||||
def _create_char_based_chunks(self, entries: List[ManifestEntry]) -> List[List[ManifestEntry]]:
|
||||
"""
|
||||
Create chunks based on character count.
|
||||
|
||||
Each chunk contains approximately self.chunk_size characters.
|
||||
Chunks never cross chapter boundaries (entries from same file only).
|
||||
"""
|
||||
chunks = []
|
||||
current_chunk = []
|
||||
current_size = 0
|
||||
|
||||
for entry in entries:
|
||||
text_len = len(entry.original_text)
|
||||
|
||||
# If adding this entry exceeds limit and we have content, start new chunk
|
||||
if current_size + text_len > self.chunk_size and current_chunk:
|
||||
chunks.append(current_chunk)
|
||||
current_chunk = []
|
||||
current_size = 0
|
||||
|
||||
current_chunk.append(entry)
|
||||
current_size += text_len
|
||||
|
||||
if current_chunk:
|
||||
chunks.append(current_chunk)
|
||||
|
||||
return chunks
|
||||
|
||||
def get_chapter_stats(self, entries: List[ManifestEntry]) -> List[Dict]:
|
||||
"""
|
||||
Get statistics for each chapter.
|
||||
|
||||
Returns list of dicts with: file_path, total, translated, pending, chars
|
||||
"""
|
||||
chapters = self._group_by_chapter(entries)
|
||||
stats = []
|
||||
|
||||
for file_path, chapter_entries in sorted(chapters.items()):
|
||||
total = len(chapter_entries)
|
||||
translated = sum(1 for e in chapter_entries if e.translated_text)
|
||||
total_chars = sum(len(e.original_text) for e in chapter_entries)
|
||||
|
||||
# Get first text as title preview
|
||||
first_text = ""
|
||||
for e in chapter_entries:
|
||||
if e.original_text:
|
||||
first_text = e.original_text[:40].replace('\n', ' ')
|
||||
break
|
||||
|
||||
stats.append({
|
||||
"file_path": file_path,
|
||||
"title": first_text,
|
||||
"total": total,
|
||||
"translated": translated,
|
||||
"pending": total - translated,
|
||||
"chars": total_chars
|
||||
})
|
||||
|
||||
return stats
|
||||
|
||||
@@ -0,0 +1,25 @@
|
||||
import logging
|
||||
from pathlib import Path
|
||||
|
||||
def setup_logger(name: str, log_file: Path = None, level=logging.INFO):
|
||||
"""Sets up a logger with the given name."""
|
||||
logger = logging.getLogger(name)
|
||||
logger.setLevel(level)
|
||||
|
||||
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
||||
|
||||
if log_file:
|
||||
file_handler = logging.FileHandler(log_file)
|
||||
file_handler.setFormatter(formatter)
|
||||
logger.addHandler(file_handler)
|
||||
|
||||
stream_handler = logging.StreamHandler()
|
||||
stream_handler.setFormatter(formatter)
|
||||
logger.addHandler(stream_handler)
|
||||
|
||||
return logger
|
||||
|
||||
def ensure_directory(path: Path):
|
||||
"""Ensures a directory exists."""
|
||||
if not path.exists():
|
||||
path.mkdir(parents=True, exist_ok=True)
|
||||
Reference in New Issue
Block a user