debase 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.1.4"
+__version__ = "0.1.5"

debase/enzyme_lineage_extractor.py

@@ -1024,6 +1024,38 @@ IMPORTANT: Only extract variants that belong to this specific campaign.
 
 # ---- 6.3  Helper for location-based extraction -----------------------------
 
+def _is_toc_entry(text: str, position: int, pattern: str) -> bool:
+    """Check if a found pattern is likely a table of contents entry."""
+    # Find the line containing this position
+    line_start = text.rfind('\n', 0, position)
+    line_end = text.find('\n', position)
+    
+    if line_start == -1:
+        line_start = 0
+    else:
+        line_start += 1
+        
+    if line_end == -1:
+        line_end = len(text)
+        
+    line = text[line_start:line_end]
+    
+    # TOC indicators:
+    # 1. Line contains dots (...) followed by page number
+    # 2. Line ends with just a page number
+    # 3. Line has "Table S12:" or similar followed by title and page
+    if '...' in line or re.search(r'\.\s*\d+\s*$', line) or re.search(r':\s*[^:]+\s+\d+\s*$', line):
+        return True
+        
+    # Check if this is in a contents/TOC section
+    # Look backwards up to 500 chars for "Contents" or "Table of Contents"
+    context_start = max(0, position - 500)
+    context = text[context_start:position].lower()
+    if 'contents' in context or 'table of contents' in context:
+        return True
+        
+    return False
+
 def _extract_text_at_locations(text: str, locations: List[Union[str, dict]], context_chars: int = 5000, validate_sequences: bool = False) -> str:
     """Extract text around identified locations."""
     if not locations:
@@ -1082,11 +1114,25 @@ def _extract_text_at_locations(text: str, locations: List[Union[str, dict]], con
         pos = -1
         used_pattern = None
         for pattern in page_patterns:
-            temp_pos = text_lower.find(pattern.lower())
-            if temp_pos != -1:
+            search_pos = 0
+            while search_pos < len(text_lower):
+                temp_pos = text_lower.find(pattern.lower(), search_pos)
+                if temp_pos == -1:
+                    break
+                    
+                # Check if this is a TOC entry
+                if _is_toc_entry(text, temp_pos, pattern):
+                    log.debug("Skipping TOC entry for pattern '%s' at position %d", pattern, temp_pos)
+                    search_pos = temp_pos + len(pattern)
+                    continue
+                    
+                # Found non-TOC entry
                 pos = temp_pos
                 used_pattern = pattern
-                log.debug("Found pattern '%s' at position %d", pattern, pos)
+                log.debug("Found pattern '%s' at position %d (not TOC)", pattern, pos)
+                break
+                
+            if pos != -1:
                 break
         
         if pos != -1:
@@ -1275,7 +1321,9 @@ def get_lineage(
                 
             # Use text-based extraction (works for tables and text sections)
             # Extract from full text, not caption text - use only primary location
-            focused_text = _extract_text_at_locations(full_text, [primary_location])
+            # Use more context for tables since they often span multiple pages
+            context_size = 15000 if location_type == 'table' else 5000
+            focused_text = _extract_text_at_locations(full_text, [primary_location], context_chars=context_size)
             log.info("Reduced text from %d to %d chars using primary location %s for campaign %s", 
                      len(full_text), len(focused_text), 
                      primary_location.get('location', 'Unknown') if isinstance(primary_location, dict) else 'Unknown',

{debase-0.1.4.dist-info → debase-0.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.1.4
+Version: 0.1.5
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.1.4.dist-info → debase-0.1.5.dist-info}/RECORD

@@ -1,17 +1,17 @@
 debase/PIPELINE_FLOW.md,sha256=S4nQyZlX39-Bchw1gQWPK60sHiFpB1eWHqo5GR9oTY8,4741
 debase/__init__.py,sha256=YeKveGj_8fwuu5ozoK2mUU86so_FjiCwsvg1d_lYVZU,586
 debase/__main__.py,sha256=LbxYt2x9TG5Ced7LpzzX_8gkWyXeZSlVHzqHfqAiPwQ,160
-debase/_version.py,sha256=mcDHWqAxAKwMNAAyHmpWVDTK-zafQ1kQjmiwnsZbUD4,49
+debase/_version.py,sha256=Bj9n2sI-8fEKj8LGa2ZU_dV7G5OnubUV9yK63_ZmeUU,49
 debase/build_db.py,sha256=bW574GxsL1BJtDwM19urLbciPcejLzfraXZPpzm09FQ,7167
 debase/cleanup_sequence.py,sha256=QyhUqvTBVFTGM7ebAHmP3tif3Jq-8hvoLApYwAJtpH4,32702
-debase/enzyme_lineage_extractor.py,sha256=s1kPOomvJjfMSN5odxeyXNmxiaOzXyOZICr4YUWU6j8,89288
+debase/enzyme_lineage_extractor.py,sha256=kn3pfPWctiaWC-oaynEOike9MQ-63ApAK1cmoHbTPzU,91159
 debase/lineage_format.py,sha256=mACni9M1RXA_1tIyDZJpStQoutd_HLG2qQMAORTusZs,30045
 debase/reaction_info_extractor.py,sha256=6wWj4IyUNSugNjxpwMGjABSAp68yHABaz_7ZRjh9GEk,112162
 debase/substrate_scope_extractor.py,sha256=dbve8q3K7ggA3A6EwB-KK9L19BnMNgPZMZ05G937dSY,82262
 debase/wrapper.py,sha256=lTx375a57EVuXcZ_roXaj5UDj8HjRcb5ViNaSgPN4Ik,10352
-debase-0.1.4.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
-debase-0.1.4.dist-info/METADATA,sha256=fZwXCP1i1s0VNq7Ds5bd2ys3pONgaV1XCe_edUkQdRU,10789
-debase-0.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-debase-0.1.4.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
-debase-0.1.4.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
-debase-0.1.4.dist-info/RECORD,,
+debase-0.1.5.dist-info/licenses/LICENSE,sha256=5sk9_tcNmr1r2iMIUAiioBo7wo38u8BrPlO7f0seqgE,1075
+debase-0.1.5.dist-info/METADATA,sha256=1vMeMX3yGLXnnvnp9lN3mTRDCsdqFklE0puYlBemfyE,10789
+debase-0.1.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+debase-0.1.5.dist-info/entry_points.txt,sha256=hUcxA1b4xORu-HHBFTe9u2KTdbxPzt0dwz95_6JNe9M,48
+debase-0.1.5.dist-info/top_level.txt,sha256=2BUeq-4kmQr0Rhl06AnRzmmZNs8WzBRK9OcJehkcdk8,7
+debase-0.1.5.dist-info/RECORD,,