Initial release prep

This commit is contained in:
Justin Visser 2026-02-27 10:46:05 +01:00
parent c9b9d892f4
commit 92395b2b4b
100 changed files with 405 additions and 401 deletions

View file

@ -7,14 +7,14 @@ import unicodedata
from typing import Any
from urllib.parse import urljoin
from app.services.domains.ingestion.constants import (
from app.services.ingestion.constants import (
HTML_TAG_RE,
INITIAL_PAGE_FINGERPRINT_MAX_PUBLICATIONS,
SPACE_RE,
TITLE_ALNUM_RE,
WORD_RE,
)
from app.services.domains.scholar.parser import ParsedProfilePage, ParseState, PublicationCandidate
from app.services.scholar.parser import ParsedProfilePage, ParseState, PublicationCandidate
# Scholar-specific noise patterns stripped before canonical comparison.
# Applied in order; each targets a different Scholar metadata injection style.