Antigravity/notes-qpid-pro
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(reader): add PDF reading support with outline chapters, CLI blocks, and noise filtering (task 7)

Browse Source
This commit is contained in:
Antigravity
2026-10-06 10:16:40 +03:00
parent c38b1dae0a
commit 6dcfd59f73
67 changed files with 49444 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/main.py
+32 -24
View File
@@ -28,7 +28,7 @@ from app.auth import (
from app.dictionary import lookup_term, USER_AGENT
from app.export import export_csv, export_json, export_anki_tsv, export_markdown
from app.srs import calculate_sm2, generate_quiz_options, build_activity_heatmap, calculate_cefr_level
from app.reader import parse_epub, parse_text, count_words
from app.reader import parse_epub, parse_text, parse_pdf, count_words
@asynccontextmanager
@@ -1088,29 +1088,37 @@ async def api_create_book(
stem = Path(filename).stem
lower_name = filename.lower()
if lower_name.endswith(".epub"):
source_type = "epub"
parsed_title, parsed_author, chapters = parse_epub(file_bytes)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
elif lower_name.endswith(".md"):
source_type = "md"
text_str = file_bytes.decode("utf-8", errors="replace")
parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
elif lower_name.endswith(".txt"):
source_type = "txt"
text_str = file_bytes.decode("utf-8", errors="replace")
parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
else:
source_type = "text"
text_str = file_bytes.decode("utf-8", errors="replace")
parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
try:
if lower_name.endswith(".epub"):
source_type = "epub"
parsed_title, parsed_author, chapters = parse_epub(file_bytes)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
elif lower_name.endswith(".pdf"):
source_type = "pdf"
parsed_title, parsed_author, chapters = parse_pdf(file_bytes, filename=filename)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
elif lower_name.endswith(".md"):
source_type = "md"
text_str = file_bytes.decode("utf-8", errors="replace")
parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
elif lower_name.endswith(".txt"):
source_type = "txt"
text_str = file_bytes.decode("utf-8", errors="replace")
parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
else:
source_type = "text"
text_str = file_bytes.decode("utf-8", errors="replace")
parsed_title, parsed_author, chapters = parse_text(text_str, title=form_title or "Untitled", author=form_author)
title = form_title or (parsed_title if parsed_title != "Untitled" else "") or stem
author = form_author or parsed_author
except ValueError as ve:
raise HTTPException(status_code=400, detail=str(ve))
else:
try: