academic-refchecker 1.2.43__py3-none-any.whl → 1.2.44__py3-none-any.whl

__version__.py

@@ -1,3 +1,3 @@
 """Version information for RefChecker."""
 
-__version__ = "1.2.43"
+__version__ = "1.2.44"

{academic_refchecker-1.2.43.dist-info → academic_refchecker-1.2.44.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academic-refchecker
-Version: 1.2.43
+Version: 1.2.44
 Summary: A comprehensive tool for validating reference accuracy in academic papers
 Author-email: Mark Russinovich <markrussinovich@hotmail.com>
 License-Expression: MIT

{academic_refchecker-1.2.43.dist-info → academic_refchecker-1.2.44.dist-info}/RECORD

@@ -1,5 +1,5 @@
-__version__.py,sha256=JbybFux4Juuafz1jN0cgsedPmzBO8U9DJ874tJu2saA,65
-academic_refchecker-1.2.43.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
+__version__.py,sha256=k3lYUlcZL-yL2e_2u3UPBtgwqMqZJ11x7KVMZOotlE8,65
+academic_refchecker-1.2.44.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
@@ -15,7 +15,7 @@ config/settings.py,sha256=-vODFoXbWbGPUElpmchE5zbCj_n4Vtxr8HU1hQDFp_c,6164
 core/__init__.py,sha256=1T2MSQyDk0u_PupbHvm4CvNNN--dxsw78fqKUrqoYrM,157
 core/db_connection_pool.py,sha256=XRiOdehikkSz3obH4WKgf8woa3694if50Q15rBT-4XQ,4697
 core/parallel_processor.py,sha256=5V2iJDBFwwryMCnCNU_oRt2u5he1wpy-_9qapC_6f00,17043
-core/refchecker.py,sha256=sVRg3PUzrs2vLFlEBoi4bxUy-TpO5iQHCkokGas-ygQ,273616
+core/refchecker.py,sha256=w3KNWyyaZZVL3ghFhEfro8SPs4xXEUjmCJERfZ7Du6A,273648
 database/__init__.py,sha256=mEuVHlEBuS44t_2ZT_JnvQQrlRCjo1SJq1NmaJ6r8OY,125
 database/download_semantic_scholar_db.py,sha256=waN4I97KC_36YMiPbiBDUUmgfzu1nub5yeKdAsIR2aw,75276
 llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -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=JqnRg4z-O9GcJ1eJGeTMzmOQwPWbWo2Lf6Duwj-ymHQ,6258
 utils/mock_objects.py,sha256=QxU-UXyHSY27IZYN8Sb8ei0JtNkpGSdMXoErrRLHXvE,6437
-utils/text_utils.py,sha256=jPgCOBTVboLRJyypoOtL-dg1wBDQrKBux2ImvC6wL58,206296
+utils/text_utils.py,sha256=uEwKasw3aTVgIDHbDJDSOcTUbPwfiivIdhKwmxQJy0U,206378
 utils/unicode_utils.py,sha256=-WBKarXO756p7fd7gCeNsMag4ztDNURwFX5IVniOtwY,10366
-utils/url_utils.py,sha256=aq1hSYEA888bOKuBOGWRclgTFIjw32rpFdsBO_Ja8ZM,8402
-academic_refchecker-1.2.43.dist-info/METADATA,sha256=ZsJhIw1n7Yjoug6mpV4zpAPf-eSW5xSMdd3Dl_WTOlI,22298
-academic_refchecker-1.2.43.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-academic_refchecker-1.2.43.dist-info/entry_points.txt,sha256=WdI89tYkIfz-M628PiboOfOLzTBWZAqvlF29qCVCkek,61
-academic_refchecker-1.2.43.dist-info/top_level.txt,sha256=6RlcQEA0kHb7-ndbKMFMZnYnJQVohgsU6BBkbEvJvEs,69
-academic_refchecker-1.2.43.dist-info/RECORD,,
+utils/url_utils.py,sha256=HdxIO8QvciP6Jp8Wd4sTSrS8JQrOMwgM7pxdUC8RJb4,9176
+academic_refchecker-1.2.44.dist-info/METADATA,sha256=ueA0mwKqmiqhR9WBLyPy2W40wfJc4JRiWSTbrQHKU14,22298
+academic_refchecker-1.2.44.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+academic_refchecker-1.2.44.dist-info/entry_points.txt,sha256=WdI89tYkIfz-M628PiboOfOLzTBWZAqvlF29qCVCkek,61
+academic_refchecker-1.2.44.dist-info/top_level.txt,sha256=6RlcQEA0kHb7-ndbKMFMZnYnJQVohgsU6BBkbEvJvEs,69
+academic_refchecker-1.2.44.dist-info/RECORD,,

core/refchecker.py

@@ -5181,7 +5181,7 @@ class ArxivReferenceChecker:
             from utils.text_utils import format_authors_for_display
             authors = format_authors_for_display(reference.get('authors', []))
             year = reference.get('year', '')
-            venue = reference.get('venue', '')
+            venue = reference.get('venue', '') or reference.get('journal', '')
             url = reference.get('url', '')
             doi = reference.get('doi', '')
             # Extract actual reference number from raw text for accurate display

utils/text_utils.py

@@ -4594,7 +4594,7 @@ def normalize_venue_for_display(venue: str) -> str:
     prefixes_to_remove = [
         r'^\d{4}\s+\d+(st|nd|rd|th)\s+',  # "2012 IEEE/RSJ"
         r'^\d{4}\s+',                     # "2024 "
-        r'^proceedings\s+(of\s+)?(the\s+)?(\d+(st|nd|rd|th)\s+)?(ieee\s+)?',  # "Proceedings of the IEEE"
+        r'^proceedings\s+(of\s+)?(the\s+)?((acm|ieee|usenix|aaai|sigcomm|sigkdd|sigmod|sigops|vldb|osdi|sosp|eurosys)\s+)*(\d+(st|nd|rd|th)\s+)?',  # "Proceedings of the [ORG] [ORG] 29th"
         r'^proc\.\s+of\s+(the\s+)?(\d+(st|nd|rd|th)\s+)?(ieee\s+)?',        # "Proc. of the IEEE" (require "of")
         r'^procs\.\s+of\s+(the\s+)?(\d+(st|nd|rd|th)\s+)?(ieee\s+)?',       # "Procs. of the IEEE" (require "of")
         r'^in\s+',

utils/url_utils.py

@@ -214,6 +214,7 @@ def clean_url(url: str) -> str:
     This function handles:
     - Whitespace trimming
     - Malformed LaTeX URL wrappers like \\url{https://...}
+    - Markdown-style links like [text](url)
     - Trailing punctuation from academic references
     - DOI URL query parameter cleanup
     
@@ -237,6 +238,14 @@ def clean_url(url: str) -> str:
     if url_match:
         url = url_match.group(1)
     
+    # Handle markdown-style links like [text](url) or [url](url)
+    # e.g., "[https://example.com](https://example.com)" -> "https://example.com"
+    markdown_pattern = r'\[([^\]]*)\]\((https?://[^)]+)\)'
+    markdown_match = re.search(markdown_pattern, url)
+    if markdown_match:
+        # Use the URL from parentheses
+        url = markdown_match.group(2)
+    
     # Remove trailing punctuation that's commonly part of sentence structure
     # but preserve legitimate URL characters
     url = url.rstrip('.,;!?)')
@@ -280,6 +289,14 @@ def clean_url_punctuation(url: str) -> str:
     if url_match:
         url = url_match.group(1)
     
+    # Handle markdown-style links like [text](url) or [url](url)
+    # e.g., "[https://example.com](https://example.com)" -> "https://example.com"
+    markdown_pattern = r'\[([^\]]*)\]\((https?://[^)]+)\)'
+    markdown_match = re.search(markdown_pattern, url)
+    if markdown_match:
+        # Use the URL from parentheses
+        url = markdown_match.group(2)
+    
     # Remove trailing punctuation that's commonly part of sentence structure
     # but preserve legitimate URL characters
     url = url.rstrip('.,;!?)')