BibTeX journal name abbreviator - automatically converts full journal names to standard IEEE/ACM abbreviations to fix bibliography overflow issues in LaTeX documents.

bibliography_abbreviator.py

#!/usr/bin/env python3
"""
BibTeX Journal Abbreviator

This script reads a .bib file and replaces full journal names with their
standard abbreviations based on IEEE, ACM, and other common abbreviations.
"""

import re
import sys
import argparse
from pathlib import Path

# Comprehensive journal abbreviation dictionary
JOURNAL_ABBREVIATIONS = {
    # IEEE Journals
    "IEEE Transactions on Pattern Analysis and Machine Intelligence": "IEEE Trans. Pattern Anal. Mach. Intell.",
    "IEEE Transactions on Neural Networks": "IEEE Trans. Neural Netw.",
    "IEEE Transactions on Neural Networks and Learning Systems": "IEEE Trans. Neural Netw. Learn. Syst.",
    "IEEE Transactions on Knowledge and Data Engineering": "IEEE Trans. Knowl. Data Eng.",
    "IEEE Transactions on Software Engineering": "IEEE Trans. Softw. Eng.",
    "IEEE Transactions on Computers": "IEEE Trans. Comput.",
    "IEEE Transactions on Information Theory": "IEEE Trans. Inf. Theory",
    "IEEE Transactions on Signal Processing": "IEEE Trans. Signal Process.",
    "IEEE Transactions on Image Processing": "IEEE Trans. Image Process.",
    "IEEE Transactions on Multimedia": "IEEE Trans. Multimedia",
    "IEEE Transactions on Visualization and Computer Graphics": "IEEE Trans. Vis. Comput. Graph.",
    "IEEE Computer Graphics and Applications": "IEEE Comput. Graph. Appl.",
    "IEEE Internet Computing": "IEEE Internet Comput.",
    "IEEE Software": "IEEE Softw.",
    "IEEE Computer": "IEEE Computer",
    "Proceedings of the IEEE": "Proc. IEEE",
    # IEEE Conferences
    "2019 IEEE Winter Conference on Applications of Computer Vision (WACV)": "WACV",
    "2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE)": "ASE",
    "ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)": "ICASSP",
    "IEEE Games Entertainment Media Conference": "IEEE GEM",
    # Nature/Science
    "Nature": "Nature",
    "Nature Machine Intelligence": "Nat. Mach. Intell.",
    "Nature Communications": "Nat. Commun.",
    "Nature Methods": "Nat. Methods",
    "Science": "Science",
    "Science Advances": "Sci. Adv.",
    # ACM Journals
    "ACM Transactions on Graphics": "ACM Trans. Graph.",
    "ACM Transactions on Computer Systems": "ACM Trans. Comput. Syst.",
    "ACM Transactions on Database Systems": "ACM Trans. Database Syst.",
    "ACM Transactions on Information Systems": "ACM Trans. Inf. Syst.",
    "ACM Computing Surveys": "ACM Comput. Surv.",
    "Communications of the ACM": "Commun. ACM",
    "Annual International ACM SIGIR Conference on Research and Development in Information Retrieval": "SIGIR",
    # Machine Learning Journals
    "Journal of Machine Learning Research": "J. Mach. Learn. Res.",
    "J. Mach. Learn. Res.": "J. Mach. Learn. Res.",  # Already abbreviated
    "Machine Learning": "Mach. Learn.",
    "Neural Networks": "Neural Netw.",
    "Neural Computation": "Neural Comput.",
    "Artificial Intelligence": "Artif. Intell.",
    "Journal of Artificial Intelligence Research": "J. Artif. Intell. Res.",
    "Found. Trends Mach. Learn.": "Found. Trends Mach. Learn.",  # Already abbreviated
    # Computer Vision
    "International Journal of Computer Vision": "Int. J. Comput. Vis.",
    "Computer Vision and Image Understanding": "Comput. Vis. Image Underst.",
    "Pattern Recognition": "Pattern Recognit.",
    "Pattern Recognition Letters": "Pattern Recognit. Lett.",
    "CVPR 2011": "CVPR",
    # NLP/Computational Linguistics
    "Computational Linguistics": "Comput. Linguist.",
    "Natural Language Engineering": "Nat. Lang. Eng.",
    "Language Resources and Evaluation": "Lang. Resour. Eval.",
    "Annual Meeting of the Association for Computational Linguistics": "ACL",
    "Conference of the European Chapter of the Association for Computational Linguistics": "EACL",
    "North American Chapter of the Association for Computational Linguistics": "NAACL",
    "NAACL-HLT": "NAACL-HLT",
    "Transactions of the Association for Computational Linguistics": "Trans. ACL",
    "International Conference on Computational Linguistics": "COLING",
    "International Conference on Language Resources and Evaluation": "LREC",
    "Findings": "Findings",  # Keep as is (usually "Findings of ACL/EMNLP")
    # Conferences (often kept as proceedings)
    "International Conference on Machine Learning": "ICML",
    "Conference on Neural Information Processing Systems": "NeurIPS",
    "Neural Information Processing Systems": "NeurIPS",
    "International Conference on Learning Representations": "ICLR",
    "Association for Computational Linguistics": "ACL",
    "Conference on Empirical Methods in Natural Language Processing": "EMNLP",
    "Conference on Computer Vision and Pattern Recognition": "CVPR",
    "International Conference on Computer Vision": "ICCV",
    "European Conference on Computer Vision": "ECCV",
    "AAAI Conference on Artificial Intelligence": "AAAI",
    "AAAI/IAAI, Vol. 2": "AAAI",
    "International Joint Conference on Artificial Intelligence": "IJCAI",
    "ACM SIGMOD International Conference on Management of Data": "SIGMOD",
    "ACM SIGKDD International Conference on Knowledge Discovery and Data Mining": "KDD",
    "International World Wide Web Conference": "WWW",
    "ACM Conference on Human Factors in Computing Systems": "CHI",
    "International Conference on Artificial Intelligence and Statistics": "AISTATS",
    "International Conference on Algorithmic Learning Theory": "ALT",
    "Conference on Uncertainty in Artificial Intelligence": "UAI",
    "The International FLAIRS Conference Proceedings": "FLAIRS",
    # Workshops and Special Venues
    "International Workshop on Similarity-Based Pattern Recognition": "S+SSPR",
    "Machine Learning Challenges Workshop": "ML Challenges Workshop",
    "Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)": "SUKI Workshop",
    "Workshop on Document-grounded Dialogue and Conversational Question Answering": "Doc2Dial Workshop",
    # arXiv and preprints
    "arXiv preprint": "arXiv",
    "ArXiv": "arXiv",
    "arXiv: Computation and Language": "arXiv",
    # Other Journals
    "Complex.": "Complex.",  # Already abbreviated (Complexity journal)
    "Mathematical Programming": "Math. Program.",
    "Semantic Web": "Semant. Web",
    "The Scientific World Journal": "Sci. World J.",
    "Frontiers Robotics AI": "Front. Robot. AI",
    # Other common journals
    "Journal of the American Statistical Association": "J. Am. Stat. Assoc.",
    "Bioinformatics": "Bioinformatics",
    "PLOS ONE": "PLOS ONE",
    "Scientific Reports": "Sci. Rep.",
    "Applied Mathematics and Computation": "Appl. Math. Comput.",
    "Information Sciences": "Inf. Sci.",
    "Knowledge-Based Systems": "Knowl.-Based Syst.",
    "Expert Systems with Applications": "Expert Syst. Appl.",
}


def parse_bib_file(file_path):
    """Parse a BibTeX file and return entries."""
    with open(file_path, "r", encoding="utf-8") as f:
        content = f.read()

    # Split into entries
    entries = re.split(r"@\w+\s*\{", content)
    parsed_entries = []

    for i, entry in enumerate(entries):
        if i == 0:  # Skip the part before first entry
            continue

        # Find the entry type from the previous split
        entry_match = re.search(r"@(\w+)\s*\{", content)
        if entry_match:
            entry_type = entry_match.group(1)

        # Extract the entry key and fields
        lines = entry.split("\n")
        if lines:
            key_line = lines[0].strip()
            key = key_line.split(",")[0] if "," in key_line else key_line.rstrip("}")

            parsed_entries.append(
                {
                    "type": entry_type if "entry_type" in locals() else "article",
                    "key": key,
                    "content": entry,
                }
            )

    return parsed_entries


def extract_journal_field(entry_content):
    """Extract journal field from BibTeX entry."""
    # Look for journal field (case insensitive)
    journal_match = re.search(
        r"journal\s*=\s*\{([^}]+)\}", entry_content, re.IGNORECASE
    )
    if journal_match:
        return journal_match.group(1)

    # Also check for booktitle field (for conference proceedings)
    booktitle_match = re.search(
        r"booktitle\s*=\s*\{([^}]+)\}", entry_content, re.IGNORECASE
    )
    if booktitle_match:
        return booktitle_match.group(1)

    return None


def find_abbreviation(journal_name):
    """Find abbreviation for a journal name."""
    # Direct match
    if journal_name in JOURNAL_ABBREVIATIONS:
        return JOURNAL_ABBREVIATIONS[journal_name]

    # Case-insensitive match
    for full_name, abbrev in JOURNAL_ABBREVIATIONS.items():
        if journal_name.lower() == full_name.lower():
            return abbrev

    # Partial match (for slight variations)
    for full_name, abbrev in JOURNAL_ABBREVIATIONS.items():
        if (
            journal_name.lower() in full_name.lower()
            or full_name.lower() in journal_name.lower()
        ):
            # Only return if it's a significant match (>70% overlap)
            if (
                len(set(journal_name.lower().split()) & set(full_name.lower().split()))
                / max(len(journal_name.split()), len(full_name.split()))
                > 0.7
            ):
                return abbrev

    return None


def abbreviate_bib_file(input_file, output_file=None, dry_run=False):
    """Process BibTeX file and abbreviate journal names."""
    if output_file is None:
        output_file = input_file.replace(".bib", "_abbreviated.bib")

    with open(input_file, "r", encoding="utf-8") as f:
        content = f.read()

    changes_made = []
    modified_content = content

    # Find all journal and booktitle fields
    journal_pattern = r"(journal\s*=\s*\{)([^}]+)(\})"
    booktitle_pattern = r"(booktitle\s*=\s*\{)([^}]+)(\})"

    def replace_journal(match):
        prefix, journal_name, suffix = match.groups()
        abbrev = find_abbreviation(journal_name)
        if abbrev and abbrev != journal_name:
            changes_made.append(f"'{journal_name}' -> '{abbrev}'")
            return prefix + abbrev + suffix
        return match.group(0)

    # Replace journal fields
    modified_content = re.sub(
        journal_pattern, replace_journal, modified_content, flags=re.IGNORECASE
    )

    # Replace booktitle fields
    modified_content = re.sub(
        booktitle_pattern, replace_journal, modified_content, flags=re.IGNORECASE
    )

    if dry_run:
        print("DRY RUN - Changes that would be made:")
        if changes_made:
            for change in changes_made:
                print(f"  {change}")
        else:
            print("  No abbreviations found")
        return

    # Write the modified content
    with open(output_file, "w", encoding="utf-8") as f:
        f.write(modified_content)

    print(f"Processed {input_file} -> {output_file}")
    if changes_made:
        print(f"Made {len(changes_made)} abbreviations:")
        for change in changes_made:
            print(f"  {change}")
    else:
        print("No journal names were abbreviated (none found in dictionary)")


def list_unrecognized_journals(input_file):
    """List journal names that don't have abbreviations."""
    with open(input_file, "r", encoding="utf-8") as f:
        content = f.read()

    unrecognized = set()

    # Find all journal and booktitle fields
    journal_matches = re.findall(r"journal\s*=\s*\{([^}]+)\}", content, re.IGNORECASE)
    booktitle_matches = re.findall(
        r"booktitle\s*=\s*\{([^}]+)\}", content, re.IGNORECASE
    )

    all_journals = journal_matches + booktitle_matches

    for journal in all_journals:
        if not find_abbreviation(journal):
            unrecognized.add(journal)

    if unrecognized:
        print("Unrecognized journal names:")
        for journal in sorted(unrecognized):
            print(f"  '{journal}'")
    else:
        print("All journal names have abbreviations available")


def main():
    parser = argparse.ArgumentParser(
        description="Abbreviate journal names in BibTeX files"
    )
    parser.add_argument("input_file", help="Input .bib file")
    parser.add_argument(
        "-o", "--output", help="Output .bib file (default: input_abbreviated.bib)"
    )
    parser.add_argument(
        "--dry-run",
        action="store_true",
        help="Show what would be changed without making changes",
    )
    parser.add_argument(
        "--list-unrecognized",
        action="store_true",
        help="List journal names without abbreviations",
    )

    args = parser.parse_args()

    if not Path(args.input_file).exists():
        print(f"Error: File '{args.input_file}' not found")
        sys.exit(1)

    if args.list_unrecognized:
        list_unrecognized_journals(args.input_file)
    else:
        abbreviate_bib_file(args.input_file, args.output, args.dry_run)


if __name__ == "__main__":
    main()