| """ |
| Booktitle normalizer: maps verbose venue names to standard abbreviations. |
| |
| Loads rules from data/abbr.tsv (regex → abbreviation). |
| """ |
| import re |
| import csv |
| from pathlib import Path |
| from typing import Optional |
|
|
|
|
| class BooktitleNormalizer: |
| """Normalizes booktitle/journal names to standard abbreviations.""" |
|
|
| def __init__(self, tsv_path: str = None): |
| if tsv_path is None: |
| tsv_path = str(Path(__file__).resolve().parent.parent / "data" / "abbr.tsv") |
| self.rules: list[tuple[re.Pattern, str]] = [] |
| self._load_rules(tsv_path) |
|
|
| def _load_rules(self, tsv_path: str): |
| """Load regex → abbreviation rules from TSV file.""" |
| path = Path(tsv_path) |
| if not path.exists(): |
| return |
|
|
| with open(path, 'r', encoding='utf-8') as f: |
| reader = csv.reader(f, delimiter='\t') |
| for row in reader: |
| if len(row) >= 2: |
| pattern_str = row[0].strip() |
| abbr = row[1].strip() |
| |
| if not pattern_str or pattern_str.startswith('#'): |
| continue |
| try: |
| self.rules.append((re.compile(pattern_str, re.IGNORECASE), abbr)) |
| except re.error: |
| pass |
|
|
| def normalize(self, booktitle: str) -> Optional[str]: |
| """ |
| Normalize a booktitle to its standard abbreviation. |
| Returns the abbreviation if matched, None if no match found. |
| """ |
| if not booktitle: |
| return None |
| for pattern, abbr in self.rules: |
| if pattern.search(booktitle): |
| return abbr |
| return None |
|
|
