Update ai_mapping.py

ai_mapping.py

@@ -31,14 +31,13 @@ def extract_key_values_with_layoutlm(page_data: list, pdf_path: str) -> Dict[str
         key_values = {}
         # Enhanced regex patterns with flexibility
         dates = re.findall(r'(Agreement\s+(?:Start|End)\s+Date(?:s)?)\s*[:\s]*(\d{1,2}[/-]\d{1,2}[/-]\d{4})', text_data, re.IGNORECASE)
-        # Capture date anywhere with context like "executed as of" or "Effective Date"
-        date_context = re.findall(r'(?:executed\s+as\s+of|Effective\s+Date)\s*[:\s]*(\d{1,2}[/-]\d{1,2}[/-]\d{4})', text_data, re.IGNORECASE)
+        # Capture date with line break tolerance for "executed as of: 7/5/25"
+        date_context = re.findall(r'(?:executed\s+as\s+of|Effective\s+Date)[\s:]*(\d{1,2}[/-]\d{1,2}[/-]\d{4})', text_data, re.IGNORECASE)
         amounts = re.findall(r'\$\d{1,3}(?:,\d{3})*(?:\.\d{2})?', text_data)
-        # Refined Agreement Name near Order Form or document start
-        name_context = re.findall(r'(?:Order\s+Form|Agreement)\s*[:\s]*([A-Za-z0-9\s-]+)(?=\s*(?:Product|Quantity|List|Net|\Z))', text_data, re.IGNORECASE)
-        # Prioritize first meaningful name, avoiding procedural text
+        # Refined Agreement Name near Order Form or document start, avoiding procedural text
+        name_context = re.findall(r'(?:Order\s+Form|Agreement)\s*[:\s]*([A-Za-z0-9\s-]+)(?=\s*(?:Product|Quantity|List|Net|\n\n|\Z))', text_data, re.IGNORECASE)
         if name_context:
-            key_values["Agreement Name"] = next((name.strip() for name in name_context if len(name.split()) > 1 and not name.lower().startswith("no")), "Unknown")
+            key_values["Agreement Name"] = next((name.strip() for name in name_context if len(name.split()) > 1 and not name.lower().startswith("no purchase")), "Unknown")
         # Update key_values with matched fields
         for key, value in dates:
             key_values[key] = value
@@ -128,7 +127,7 @@ def extract_clauses(page_data: list) -> Dict[str, str]:
     # Target exact "NO WAIVER" text only
     no_waiver_match = re.search(r'NO\s+WAIVER\s*[:\s]*(.*?)(?=\n\n|\Z)', text_data, re.IGNORECASE)
     if no_waiver_match:
-        clauses["NO WAIVER"] = no_waiver_match.group(1).strip()
+        clauses["NO WAIVER"] = no_waiver_match.group(1).strip() if no_waiver_match.group(1).strip() else "NO WAIVER"
     return clauses if clauses else {}
 
 def run_ai_mapping_with_layoutlm(key_values: Dict[str, str], object_field_names: List[str], pdf_path: str) -> Dict: