justinzeus/scholarr
1
0
Fork 0
Code Issues 1 Pull requests 18 Projects Releases Packages Wiki Activity Actions

Intermediate commit

Browse source
This commit is contained in:
Justin Visser 2026-02-26 16:09:57 +01:00
parent 0e9e49df16
commit 3d4cfeff1a
65 changed files with 5507 additions and 333 deletions
Download patch file Download diff file Expand all files Collapse all files

5
app/services/domains/publication_identifiers/normalize.py
View file

@ -7,6 +7,7 @@ from app.services.domains.doi.normalize import normalize_doi
from app.services.domains.publication_identifiers.types import IdentifierKind
ARXIV_ABS_RE = re.compile(r"\barxiv:\s*([a-z-]+/\d{7}|\d{4}\.\d{4,5})(v\d+)?\b", re.I)
ARXIV_RAW_RE = re.compile(r"^([a-z-]+/\d{7}|\d{4}\.\d{4,5})(v\d+)?$", re.I)
ARXIV_PATH_RE = re.compile(r"^/(?:abs|pdf|html|ps|format)/([a-z-]+/\d{7}|\d{4}\.\d{4,5})(v\d+)?(?:\.pdf)?/?$", re.I)
PMCID_RE = re.compile(r"\b(PMC\d+)\b", re.I)
PUBMED_PATH_RE = re.compile(r"^/(\d+)/?$")
@ -31,6 +32,10 @@ def normalize_arxiv_id(value: str | None) -> str | None:
parsed = urlparse(text)
if parsed.scheme in {"http", "https"} and "arxiv.org" in parsed.netloc.lower():
return _arxiv_from_path(parsed.path)
raw_match = ARXIV_RAW_RE.match(text)
if raw_match:
version = (raw_match.group(2) or "").lower()
return f"{raw_match.group(1).lower()}{version}"
match = ARXIV_ABS_RE.search(text)
if not match:
return None