academic-refchecker 1.2.38__py3-none-any.whl → 1.2.39__py3-none-any.whl

__version__.py

@@ -1,3 +1,3 @@
 """Version information for RefChecker."""
 
-__version__ = "1.2.38"
+__version__ = "1.2.39"

{academic_refchecker-1.2.38.dist-info → academic_refchecker-1.2.39.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academic-refchecker
-Version: 1.2.38
+Version: 1.2.39
 Summary: A comprehensive tool for validating reference accuracy in academic papers
 Author-email: Mark Russinovich <markrussinovich@hotmail.com>
 License-Expression: MIT

{academic_refchecker-1.2.38.dist-info → academic_refchecker-1.2.39.dist-info}/RECORD

@@ -1,5 +1,5 @@
-__version__.py,sha256=9ez-UBx1mkgUvDMk-z63_XpqOh2QnPCeTrDEuricP1w,65
-academic_refchecker-1.2.38.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
+__version__.py,sha256=63hU3Q1fGBiJ1GUnUQ-V6-S8pbWZ7bug_ZVu4V6eo9g,65
+academic_refchecker-1.2.39.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
 checkers/__init__.py,sha256=T0PAHTFt6UiGvn-WGoJU8CdhXNmf6zaHmcGVoWHhmJQ,533
 checkers/crossref.py,sha256=Hzq4dlf1CSn0aZWU8CMOnLxIvaSivTabLoepIOkgkmY,20585
 checkers/enhanced_hybrid_checker.py,sha256=6yf5tV4jLSVzjX1xR_kQq0NOgQIst-z_WmkiqqMc8hQ,23469
@@ -28,7 +28,7 @@ services/pdf_processor.py,sha256=vu_JnhFGZY6jFVbDbPvG-mlQojvB-3Dzc8_946KVV2E,942
 utils/__init__.py,sha256=1RrGoIIn1_gVzxd56b6a7HeAS-wu7uDP-nxLbR3fJ-8,1199
 utils/arxiv_utils.py,sha256=Y8sDJgDwHxp1L33BkQoDumIl0Pkp-BuYZb1PwWYsmak,18251
 utils/author_utils.py,sha256=DLTo1xsxef2wxoe4s_MWrh36maj4fgnvFlsDLpDE-qQ,5507
-utils/biblatex_parser.py,sha256=Vznt-BfNtQQb4XQ6iPab2CgFcV2JIjva1OU33NzQ51g,20253
+utils/biblatex_parser.py,sha256=JiO_tznsemhmGFs-pDM2qGuDlvT1ArIyc6bmsdwDOPQ,20452
 utils/bibliography_utils.py,sha256=mpmdAklzAs1CT3gqrOcjujGhouL95OuliCx0LE9Pg90,11705
 utils/bibtex_parser.py,sha256=jsQ87lkzmBmJO3VEN3itw22CJ1Hesei4IvM2sfsaFKI,12867
 utils/config_validator.py,sha256=rxf7K3DYmJ-BNPsmtaCNipY2BTVT-pJZ7wN-M9Y3GC8,11167
@@ -36,11 +36,11 @@ utils/db_utils.py,sha256=_wSupfBlm0ILFvntQTvoj7tLDCbrYPRQrp9NDvphF_E,6281
 utils/doi_utils.py,sha256=8f3iE4RdSNkzeqa9wJfoKcVEiBVse3_uf643biLudmw,4134
 utils/error_utils.py,sha256=2qdRM3Bv4GvE3mlXgXp9jiQBfvB08qeg8vTgNVivcgk,5706
 utils/mock_objects.py,sha256=QxU-UXyHSY27IZYN8Sb8ei0JtNkpGSdMXoErrRLHXvE,6437
-utils/text_utils.py,sha256=KjNx_UJvVhz-oowu4CCdryEuN0hYLu4X8yVkjdYP8fM,189261
+utils/text_utils.py,sha256=8luQsOBfcEBv3O16d3LlQmCuoEB0dEF0aQWGey-s3us,190502
 utils/unicode_utils.py,sha256=-WBKarXO756p7fd7gCeNsMag4ztDNURwFX5IVniOtwY,10366
 utils/url_utils.py,sha256=n0m5rXKV0-UrE8lI85VEx23KmfGwky57sI6gFPuu78I,7358
-academic_refchecker-1.2.38.dist-info/METADATA,sha256=7V0yEKZy9zao6s3_TBHPOg7Gi86h4lG2m_rhyhStq5w,22298
-academic_refchecker-1.2.38.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-academic_refchecker-1.2.38.dist-info/entry_points.txt,sha256=WdI89tYkIfz-M628PiboOfOLzTBWZAqvlF29qCVCkek,61
-academic_refchecker-1.2.38.dist-info/top_level.txt,sha256=6RlcQEA0kHb7-ndbKMFMZnYnJQVohgsU6BBkbEvJvEs,69
-academic_refchecker-1.2.38.dist-info/RECORD,,
+academic_refchecker-1.2.39.dist-info/METADATA,sha256=Uz4a9D0tfull6uDAZTafQJOem7p8IqPA6bjl_pYUf48,22298
+academic_refchecker-1.2.39.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+academic_refchecker-1.2.39.dist-info/entry_points.txt,sha256=WdI89tYkIfz-M628PiboOfOLzTBWZAqvlF29qCVCkek,61
+academic_refchecker-1.2.39.dist-info/top_level.txt,sha256=6RlcQEA0kHb7-ndbKMFMZnYnJQVohgsU6BBkbEvJvEs,69
+academic_refchecker-1.2.39.dist-info/RECORD,,

utils/biblatex_parser.py

@@ -261,11 +261,13 @@ def parse_biblatex_entry_content(entry_num: str, content: str) -> Dict[str, Any]
     else:
         # If no quoted title, look for title after author names
         # Pattern: "FirstAuthor et al. Title Goes Here. Year." or "Author. Title. Year."
+        # Order matters: more specific patterns first
         title_patterns = [
-            r'[A-Z][a-z]+(?:\s+et\s+al)?\.?\s+([A-Z][^.]*?)\.\s+\d{4}',  # "Author et al. Title. Year"
-            r'[A-Z][^.]+\.\s*([A-Z][^.]*?)\.\s*(?:https?://|arXiv:|\d{4})',  # "Authors. Title. URL/arXiv/Year" (flexible spacing)
-            r'(?:[A-Z][a-z]+,?\s+)+([A-Z][^.]*?)\.\s+\d{4}',  # "Name, Name. Title. Year"
+            r'[A-Z][^.]+\.\s*([A-Z][^.]*?)\.\s*(?:https?://|arXiv:|\d{4})',  # "Authors. Title. URL/arXiv/Year" (flexible spacing) - MOST SPECIFIC
             r'\.([A-Z][A-Za-z\s]+(?:\?|!)?)\.?\s+\d{4}',  # ".Title. Year" - for cases where authors end without space
+            r'[A-Z][a-z]+\.([A-Z][A-Za-z\s\-&]+?)\.\s+\d{4}',  # "Name.Title. Year" - missing space after period
+            r'[A-Z][a-z]+(?:\s+et\s+al)?\.?\s+([A-Z][^.]*?)\.\s+\d{4}',  # "Author et al. Title. Year" - LESS SPECIFIC
+            r'(?:[A-Z][a-z]+,?\s+)+([A-Z][^.]*?)\.\s+\d{4}',  # "Name, Name. Title. Year"
             r'\b([A-Z][A-Za-z\s\-0-9]+)\s+\.\s+https',  # "Title . https" - handle space before period
         ]
         

utils/text_utils.py

@@ -11,6 +11,31 @@ from typing import List
 logger = logging.getLogger(__name__)
 
 
+def normalize_apostrophes(text):
+    """
+    Normalize all apostrophe variants to standard ASCII apostrophe
+    """
+    if not text:
+        return text
+    
+    # All known apostrophe variants
+    apostrophe_variants = [
+        "'",      # U+0027 ASCII apostrophe
+        "'",      # U+2019 Right single quotation mark (most common)
+        "'",      # U+2018 Left single quotation mark  
+        "ʼ",      # U+02BC Modifier letter apostrophe
+        "ˈ",      # U+02C8 Modifier letter vertical line (primary stress)
+        "`",      # U+0060 Grave accent (sometimes used as apostrophe)
+        "´",      # U+00B4 Acute accent (sometimes used as apostrophe)
+    ]
+    
+    # Replace all variants with standard ASCII apostrophe
+    for variant in apostrophe_variants:
+        text = text.replace(variant, "'")
+    
+    return text
+
+
 def normalize_text(text):
     """
     Normalize text by removing diacritical marks and special characters
@@ -18,6 +43,9 @@ def normalize_text(text):
     if not text:
         return ""
         
+    # First normalize apostrophes to standard form
+    text = normalize_apostrophes(text)
+        
     # Replace common special characters with their ASCII equivalents
     replacements = {
         'ä': 'a', 'ö': 'o', 'ü': 'u', 'ß': 'ss',
@@ -29,7 +57,7 @@ def normalize_text(text):
         'Ł': 'L', 'ł': 'l',
         '¨': '', '´': '', '`': '', '^': '', '~': '',
         '–': '-', '—': '-', '−': '-',
-        '„': '"', '"': '"', '"': '"', ''': "'", ''': "'",
+        '„': '"', '"': '"', '"': '"',
         '«': '"', '»': '"',
         '¡': '!', '¿': '?',
         '°': 'degrees', '©': '(c)', '®': '(r)', '™': '(tm)',
@@ -39,10 +67,6 @@ def normalize_text(text):
         '\u00A0': ' ',  # Non-breaking space
         '\u2013': '-',  # En dash
         '\u2014': '-',  # Em dash
-        '\u2018': "'",  # Left single quotation mark
-        '\u2019': "'",  # Right single quotation mark
-        '\u201C': '"',  # Left double quotation mark
-        '\u201D': '"',  # Right double quotation mark
         '\u2026': '...',  # Horizontal ellipsis
         '\u00B7': '.',  # Middle dot
         '\u2022': '.',  # Bullet
@@ -54,8 +78,8 @@ def normalize_text(text):
     # Remove any remaining diacritical marks
     text = unicodedata.normalize('NFKD', text).encode('ASCII', 'ignore').decode('ASCII')
     
-    # Remove special characters
-    text = re.sub(r'[^\w\s]', '', text)
+    # Remove special characters except apostrophes
+    text = re.sub(r"[^\w\s']", '', text)
     
     # Normalize whitespace
     text = re.sub(r'\s+', ' ', text).strip()
@@ -368,6 +392,9 @@ def clean_author_name(author):
     # Normalize Unicode characters (e.g., combining diacritics)
     author = unicodedata.normalize('NFKC', author)
     
+    # Normalize apostrophes first before other processing
+    author = normalize_apostrophes(author)
+    
     # Handle common Unicode escape sequences and LaTeX encodings
     # Note: Order matters - process longer patterns first
     unicode_replacements = [
@@ -703,8 +730,12 @@ def normalize_diacritics(text: str) -> str:
         'José' -> 'jose'
         'Łukasz' -> 'lukasz'
         'J. Gl¨ uck' -> 'J. Gluck'
+        'D'Amato' -> 'D'Amato' (apostrophes normalized)
     """
-    # First handle special characters that don't decompose properly
+    # First normalize apostrophes
+    text = normalize_apostrophes(text)
+    
+    # Then handle special characters that don't decompose properly
     # Including common transliterations
     special_chars = {
         'ł': 'l', 'Ł': 'L',
@@ -2224,7 +2255,8 @@ def format_author_for_display(author_name):
     if not author_name:
         return author_name
     
-    author_name = author_name.strip()
+    # Normalize apostrophes for consistent display
+    author_name = normalize_apostrophes(author_name.strip())
     
     # Check if it's in "Lastname, Firstname" format
     if ',' in author_name:
@@ -3743,6 +3775,7 @@ def are_venues_substantially_different(venue1: str, venue2: str) -> bool:
         for abbrev in sorted(multi_word_abbrevs.keys(), key=len, reverse=True):
             if abbrev in expanded_text:
                 expanded_text = expanded_text.replace(abbrev, multi_word_abbrevs[abbrev])
+                break  # Only apply the first (longest) matching abbreviation to avoid conflicts
         
         # Second pass: handle single word abbreviations
         words = expanded_text.split()
@@ -4137,8 +4170,9 @@ def are_venues_substantially_different(venue1: str, venue2: str) -> bool:
         return False
     
     # Order-aware fuzzy matching - words should match in sequence
-    words1_list = list(words1)
-    words2_list = list(words2)
+    # Sort to ensure deterministic order (set iteration is not guaranteed to be consistent)
+    words1_list = sorted(list(words1))
+    words2_list = sorted(list(words2))
     
     # If word counts are very different, they're likely different venues
     if len(words1) > 0 and len(words2) > 0: