Script for acl-org/acl-anthology to dump all paper–author assignments into a file

print_author_assignments.py

# -*- coding: utf-8 -*-
#
# Copyright 2026 Marcel Bollmann <marcel@bollmann.me>
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Writes paper–author assignments to a file, for debugging purposes.

Usage:
  print_author_assignments.py [OUTFILE]

Arguments:
  OUTFILE             The file to write the assignments to.  If not given,
                      defaults to `paperid-authorid-{git rev-parse --short HEAD}.tsv`
"""

from docopt import docopt
from pathlib import Path
import git
import itertools as it
import logging as log

from acl_anthology import Anthology
from acl_anthology.utils.logging import setup_rich_logging


if __name__ == "__main__":
    args = docopt(__doc__)
    tracker = setup_rich_logging(level=log.INFO)

    repo = git.Repo(__file__, search_parent_directories=True)
    anthology = Anthology(datadir=Path(repo.working_dir) / "data")
    anthology.load_all()  # since we need to resolve authors

    if not (outfile := args["OUTFILE"]):
        ref = repo.rev_parse("HEAD").name_rev[:8]
        outfile = f"paperid-authorid-{ref}.tsv"

    output = []
    for paper in anthology.papers():
        for namespec in it.chain(paper.authors, paper.editors):
            person = anthology.resolve(namespec)
            output.append((paper.full_id_tuple, paper.full_id, person.id))

    if tracker.highest >= log.ERROR:
        exit(1)

    output.sort(key=lambda x: (x[0], x[1]))
    with open(outfile, "w") as f:
        for ids in output:
            print("\t".join(ids[1:]), file=f)