Constrain automatic aliases and cache terminology matchers

src/translation/glossary.py

@@ -4,13 +4,19 @@ import json
 import re
 import copy
 from pathlib import Path
+from functools import lru_cache
 from src.common.utils import setup_logger
 
 logger = setup_logger('glossary')
 COMMON_ALIASES = {'who', 'us', 'it', 'he', 'she', 'we', 'you', 'they', 'me', 'them',
                   'our', 'my', 'the', 'a', 'an', 'in', 'on', 'at', 'to', 'of', 'or',
                   'dad', 'father', 'mother', 'mom', 'son', 'brother', 'sister',
-                  'family', 'face', 'carry'}
+                  'family', 'face', 'carry', 'arm',
+                  'january', 'february', 'march', 'april', 'may', 'june', 'july',
+                  'august', 'september', 'october', 'november', 'december',
+                  'chinese', 'japanese', 'korean', 'russian', 'english', 'french',
+                  'german', 'british', 'american', 'indian', 'african', 'asian',
+                  'european', 'turkish', 'italian'}
 
 
 def sanitize_automatic_terms(terms, ambiguous_aliases):
@@ -23,6 +29,11 @@ def sanitize_automatic_terms(terms, ambiguous_aliases):
         keep = []
         for alias in term.get('aliases', []):
             unsafe = alias.casefold() in COMMON_ALIASES or re.fullmatch(r'[a-z]+', alias)
+            if re.fullmatch(r'[A-Za-z][A-Za-z.-]*', alias) and alias != term['source']:
+                acronym = bool(re.fullmatch(r'[A-Z][A-Z.-]+', alias))
+                nickname = 'nickname' in term.get('notes', '').casefold() and alias in term.get('notes', '')
+                if not acronym and not nickname:
+                    unsafe = True
             # A surname shared implicitly by another full name is ambiguous,
             # even when the model did not explicitly propose it as an alias.
             for other in terms:
@@ -48,13 +59,18 @@ def source_digest(entries):
 
 
 def matches(source, text):
+    return alias_pattern(source).search(text) is not None
+
+
+@lru_cache(maxsize=8192)
+def alias_pattern(source):
     # Word boundaries for Latin aliases prevent Son matching Sony / grandson.
     escaped = re.escape(source)
     if source and source[0].isascii() and source[0].isalnum():
         escaped = r'(?<!\w)' + escaped
     if source and source[-1].isascii() and source[-1].isalnum():
         escaped += r'(?!\w)'
-    return re.search(escaped, text, matching_flags(source)) is not None
+    return re.compile(escaped, matching_flags(source))
 
 
 def matching_flags(alias):
@@ -94,12 +110,7 @@ class BookGlossary:
             excluded = [m.span() for context in term.get('exclude_contexts', [])
                         for m in re.finditer(re.escape(context), text, re.IGNORECASE)]
             for alias in [term['source']] + term.get('aliases', []):
-                pattern = re.escape(alias)
-                if alias[0].isascii() and alias[0].isalnum():
-                    pattern = r'(?<!\w)' + pattern
-                if alias[-1].isascii() and alias[-1].isalnum():
-                    pattern += r'(?!\w)'
-                for match in re.finditer(pattern, text, matching_flags(alias)):
+                for match in alias_pattern(alias).finditer(text):
                     start, end = match.span()
                     if any(start < right and end > left for left, right in excluded):
                         continue