mrwnslz
edc9c6d4c3
Blocktext, Block-Index und Zeichenoffsets stimmen nun bei sechs echten Büchern exakt mit parseEpub des Web-Readers überein. Grundlage für einen echten Fortschrittsanteil (fraction_for_anchor) statt 0.0. Parser html5lib statt lxml, Rohinhalt statt ebooklib-get_content (formatiert um), UTF-8 wie JSZip. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
53 lines
1.9 KiB
Python
53 lines
1.9 KiB
Python
"""On-disk cache for the (FlatBook, BookLayout) pair a book open computes —
|
|
extraction + row-layout for very large books (tens of thousands of blocks)
|
|
can take several seconds each; reopening the same book at the same terminal
|
|
width should be near-instant instead of paying that cost again every time.
|
|
|
|
Not a correctness-critical cache: any miss (new book, different width, edited
|
|
file) just falls back to recomputing from scratch, so a stale/corrupt cache
|
|
entry is handled by overwriting it, never by crashing the reader.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import pickle
|
|
from pathlib import Path
|
|
|
|
from platformdirs import user_cache_dir
|
|
|
|
from .blocks import FlatBook
|
|
from .layout import BookLayout
|
|
|
|
_CACHE_VERSION = 2 # 2: blocks carry char_start/char_len
|
|
_CACHE_DIR = Path(user_cache_dir("diora-tui", "diora")) / "layout_cache"
|
|
|
|
|
|
def _cache_key(path: Path, width: int) -> str:
|
|
stat = path.stat()
|
|
raw = f"v{_CACHE_VERSION}|{path.resolve()}|{stat.st_size}|{stat.st_mtime_ns}|{width}"
|
|
return hashlib.sha256(raw.encode()).hexdigest()[:32]
|
|
|
|
|
|
def load(path: Path, width: int) -> tuple[FlatBook, BookLayout] | None:
|
|
cache_file = _CACHE_DIR / f"{_cache_key(path, width)}.pickle"
|
|
if not cache_file.exists():
|
|
return None
|
|
try:
|
|
with cache_file.open("rb") as f:
|
|
book, book_layout = pickle.load(f)
|
|
if not isinstance(book, FlatBook) or not isinstance(book_layout, BookLayout):
|
|
return None
|
|
return book, book_layout
|
|
except Exception:
|
|
return None
|
|
|
|
|
|
def save(path: Path, width: int, book: FlatBook, book_layout: BookLayout) -> None:
|
|
_CACHE_DIR.mkdir(parents=True, exist_ok=True)
|
|
cache_file = _CACHE_DIR / f"{_cache_key(path, width)}.pickle"
|
|
try:
|
|
with cache_file.open("wb") as f:
|
|
pickle.dump((book, book_layout), f, protocol=pickle.HIGHEST_PROTOCOL)
|
|
except Exception:
|
|
pass # best-effort — a failed cache write shouldn't break reading
|