academic-refchecker 2.0.21__py3-none-any.whl → 2.0.22__py3-none-any.whl

{academic_refchecker-2.0.21.dist-info → academic_refchecker-2.0.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academic-refchecker
-Version: 2.0.21
+Version: 2.0.22
 Summary: A comprehensive tool for validating reference accuracy in academic papers
 Author-email: Mark Russinovich <markrussinovich@hotmail.com>
 License-Expression: MIT

{academic_refchecker-2.0.21.dist-info → academic_refchecker-2.0.22.dist-info}/RECORD

@@ -1,4 +1,4 @@
-academic_refchecker-2.0.21.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
+academic_refchecker-2.0.22.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
 backend/__init__.py,sha256=TFVkOx5tSp3abty15RzUbaSwQ9ZD0kfUn7PDh63xkYY,521
 backend/__main__.py,sha256=74V7yUMsRSZaaRyXYm-rZVc3TVUcUgwsoTQTUbV5EqM,211
 backend/cli.py,sha256=xV3l9M5OdNQQYOcrzj2d_7RmCgj7CXP_1oi0TPe6zNo,1672
@@ -19,7 +19,7 @@ backend/static/assets/index-DMZJNrR0.js,sha256=UhK5CQ8IufZmx6FTvXUCtkRxTqpGK7czS
 backend/static/assets/index-hk21nqxR.js,sha256=z2agP8ZFYw4AfYi-GJ5E_8_k-lPF-frXOJtPk-I0hDs,369533
 refchecker/__init__.py,sha256=Pg5MrtLxDBRcNYcI02N-bv3tzURVd1S3nQ8IyF7Zw7E,322
 refchecker/__main__.py,sha256=agBbT9iKN0g2xXtRNCoh29Nr7z2n5vU-r0MCVJKi4tI,232
-refchecker/__version__.py,sha256=XyBLo7S1kdSvGrt9yRtdTYCZwfWFfzPLcvw8uZes7kM,66
+refchecker/__version__.py,sha256=X_6kKif5oE_F5mSm6cC1kZmg0Jh44PqY0vD3imYvOKY,66
 refchecker/checkers/__init__.py,sha256=-dR7HX0bfPq9YMXrnODoYbfNWFLqu706xoVsUdWHYRI,611
 refchecker/checkers/arxiv_citation.py,sha256=j_waQmQSP3iuZdVuBE92ghtiOdGFTCx09s6f4mHik6o,27777
 refchecker/checkers/crossref.py,sha256=88moAyTudBqf9SKqTQkNAq1yyuRe95f8r4EpmJznupQ,20937
@@ -59,11 +59,11 @@ refchecker/utils/db_utils.py,sha256=_wSupfBlm0ILFvntQTvoj7tLDCbrYPRQrp9NDvphF_E,
 refchecker/utils/doi_utils.py,sha256=_7YvQ0DTOQBMIujUE0SdJicjPiAR3VETLU668GIji24,6094
 refchecker/utils/error_utils.py,sha256=8TcfRUD6phZ7viPJrezQ4jKf_vE65lqEXZq5707eU6s,15425
 refchecker/utils/mock_objects.py,sha256=QxU-UXyHSY27IZYN8Sb8ei0JtNkpGSdMXoErrRLHXvE,6437
-refchecker/utils/text_utils.py,sha256=4sT6YKYqINLGCrRwKOkzrZ2t2cJorHgAXT5Gd3_hKCM,235856
+refchecker/utils/text_utils.py,sha256=n6Ng1rWtQXNnE5G8MJSge0VrregKD6vcOMMqMTpiTew,237214
 refchecker/utils/unicode_utils.py,sha256=-WBKarXO756p7fd7gCeNsMag4ztDNURwFX5IVniOtwY,10366
 refchecker/utils/url_utils.py,sha256=7b0rWCQJSajzqOvD7ghsBZPejiq6mUIz6SGhvU_WGDs,9441
-academic_refchecker-2.0.21.dist-info/METADATA,sha256=D2y73gwXBF9-kvb2OHeE0bMNpcxx-Y1VksqkkUcrpyI,12443
-academic_refchecker-2.0.21.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-academic_refchecker-2.0.21.dist-info/entry_points.txt,sha256=9cREsaKwlp05Ql0CBIjKrNHk5IG2cHY5LvJPsV2-SxA,108
-academic_refchecker-2.0.21.dist-info/top_level.txt,sha256=FfNvrvpj25gfpUBjW0epvz7Qrdejhups5Za_DBiSRu4,19
-academic_refchecker-2.0.21.dist-info/RECORD,,
+academic_refchecker-2.0.22.dist-info/METADATA,sha256=ob1p0ikneyJv3z1_nLTk_ckZYdIa8YMBu7tpX8a7NqU,12443
+academic_refchecker-2.0.22.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+academic_refchecker-2.0.22.dist-info/entry_points.txt,sha256=9cREsaKwlp05Ql0CBIjKrNHk5IG2cHY5LvJPsV2-SxA,108
+academic_refchecker-2.0.22.dist-info/top_level.txt,sha256=FfNvrvpj25gfpUBjW0epvz7Qrdejhups5Za_DBiSRu4,19
+academic_refchecker-2.0.22.dist-info/RECORD,,

refchecker/__version__.py

@@ -1,3 +1,3 @@
 """Version information for RefChecker."""
 
-__version__ = "2.0.21"
+__version__ = "2.0.22"

refchecker/utils/text_utils.py

@@ -6,7 +6,6 @@ Text processing utilities for ArXiv Reference Checker
 import re
 import logging
 import unicodedata
-import html
 from typing import List
 
 logger = logging.getLogger(__name__)
@@ -1373,6 +1372,15 @@ def is_name_match(name1: str, name2: str) -> bool:
                         first_initial == first_name[0] and
                         middle_initial == middle_name[0]):
                         return True
+                else:
+                    # Simple last name case: "W. R. Weimer" vs "Westley Weimer"
+                    # The cited name has an extra middle initial that the actual name doesn't have
+                    # Allow match if first initial and last name match (tolerate extra middle initial)
+                    # BUT: Exclude cases where first_name is just concatenated initials (like "gv")
+                    # which should require exact initial matching, not tolerance
+                    is_real_first_name = len(first_name) > 2  # "Westley" yes, "gv" no
+                    if is_real_first_name and last_name == compound_last and first_initial == first_name[0]:
+                        return True
         
         elif len(init_parts) == 3 and len(name_parts) == 3:
             # Check for "Last, First Middle" vs "First Middle Last" format
@@ -4290,6 +4298,7 @@ def are_venues_substantially_different(venue1: str, venue2: str) -> bool:
                 # Handle specific multi-word patterns and well-known acronyms
                 'proc. natl. acad. sci.': 'proceedings of the national academy of sciences',
                 'pnas': 'proceedings of the national academy of sciences',
+                'cacm': 'communications of the acm',
                 # Special cases that don't follow standard acronym patterns
                 'neurips': 'neural information processing systems',  # Special case
                 'nips': 'neural information processing systems',     # old name for neurips
@@ -4426,6 +4435,8 @@ def are_venues_substantially_different(venue1: str, venue2: str) -> bool:
             'neurips': 'neural information processing systems',  # Special case: doesn't follow standard acronym rules
             'nips': 'neural information processing systems',     # old name for neurips
             'nsdi': 'networked systems design and implementation',  # USENIX NSDI
+            'cacm': 'communications of the acm',
+            'communications of the': 'communications of the acm',
         }
         
         # Apply abbreviation expansion - handle multi-word phrases first
@@ -5089,8 +5100,18 @@ def normalize_venue_for_display(venue: str) -> str:
         
         return text_lower
     
-    # Decode any HTML entities (e.g., "&" -> "&") before further cleaning
-    venue_text = html.unescape(venue).strip()
+    venue_text = venue.strip()
+
+    # Fix common truncated venues that lose their organization suffix during PDF extraction
+    truncated_aliases = {
+        "communications of the": "Communications of the ACM",
+    }
+
+    # Allow trailing punctuation/whitespace while matching truncated forms
+    normalized_candidate = re.sub(r"[\s.,;:]+$", "", venue_text, flags=re.IGNORECASE)
+    alias = truncated_aliases.get(normalized_candidate.lower())
+    if alias:
+        return alias
     
     # Strip leading editor name lists like "..., editors, Venue ..." or "..., eds., Venue ..."
     # This prevents author/editor lists from being treated as venue
@@ -5152,7 +5173,8 @@ def normalize_venue_for_display(venue: str) -> str:
     if not re.match(r'ieee\s+transactions', venue_text, re.IGNORECASE):
         venue_text = re.sub(r'^(ieee|acm|aaai|usenix|sigcomm|sigkdd|sigmod|vldb|osdi|sosp|eurosys)\s+', '', venue_text, flags=re.IGNORECASE)  # Remove org prefixes
     venue_text = re.sub(r'^ieee/\w+\s+', '', venue_text, flags=re.IGNORECASE)  # Remove "IEEE/RSJ " etc
-    venue_text = re.sub(r'\s+(ieee|acm|aaai|usenix)\s*$', '', venue_text, flags=re.IGNORECASE)  # Remove org suffixes
+    # Remove org suffixes, but NOT when preceded by "of the" (e.g., "Communications of the ACM", "Journal of the ACM")
+    venue_text = re.sub(r'(?<!of the)\s+(ieee|acm|aaai|usenix)\s*$', '', venue_text, flags=re.IGNORECASE)  # Remove org suffixes
     venue_text = re.sub(r'/\w+\s+', ' ', venue_text)  # Remove "/ACM " style org separators
     
     # IMPORTANT: Don't remove "Conference on" or "International" - they're needed for display