academic-refchecker 1.2.43__tar.gz → 1.2.44__tar.gz

{academic_refchecker-1.2.43/src/academic_refchecker.egg-info → academic_refchecker-1.2.44}/PKG-INFO

@@ -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 → academic_refchecker-1.2.44}/src/__version__.py

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

{academic_refchecker-1.2.43 → academic_refchecker-1.2.44/src/academic_refchecker.egg-info}/PKG-INFO

@@ -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 → academic_refchecker-1.2.44}/src/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

{academic_refchecker-1.2.43 → academic_refchecker-1.2.44}/src/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+',

{academic_refchecker-1.2.43 → academic_refchecker-1.2.44}/src/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('.,;!?)')