Skip to content

Fix bare month normalization in arxiv_to_publications_correct.py #1109

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pancetta merged 1 commit into from
Jun 15, 2026
Merged

Fix bare month normalization in arxiv_to_publications_correct.py #1109

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions bin/arxiv_to_publications_correct.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,12 +2,33 @@
import requests
import argparse
import fileinput
from html import unescape

import bibtexparser
from bibtexparser.bwriter import BibTexWriter
from requests.exceptions import RequestException


def normalize_month_fields(bib):
def replace_month(match):
prefix, value = match.groups()
value = unescape(value).strip()
if value.startswith("{") and value.endswith("}"):
return match.group(0)
if value.startswith('"') and value.endswith('"'):
value = value[1:-1].strip()
value = value.strip("'\"{}")
value = re.sub(r"[^A-Za-z]", "", value)
return f"{prefix}{{{value}}},"

return re.sub(
r"(^\s*month\s*=\s*)([^,\n]+)\s*,",
replace_month,
bib,
flags=re.MULTILINE | re.IGNORECASE,
)


def fetch_doi_content(url, accept_header, description):
try:
response = requests.get(url, headers={'Accept': accept_header}, timeout=30)
Expand Down Expand Up @@ -83,6 +104,7 @@ def fetch_doi_content(url, accept_header, description):
if id != id_db:
print(f'Note: ID updated from {id_db} to {id} to reflect the publication year.')
bib = "{".join([bType] + [','.join([id]+rest2)] + rest1[1:])
bib = normalize_month_fields(bib)
bib_db = bibtexparser.loads(bib)
new_entries = bib_db.get_entry_list()
if not new_entries:
Expand Down