Update ai_mapping.py

ai_mapping.py

@@ -29,10 +29,17 @@ def extract_key_values_with_layoutlm(page_data: list, pdf_path: str) -> Dict[str
         # Fallback to regex using concatenated text from all pages
         text_data = " ".join([page["text"] for page in page_data])
         key_values = {}
-        dates = re.findall(r'\d{1,2}/\d{1,2}/\d{4}', text_data)
+        # Enhanced regex patterns
+        dates = re.findall(r'(Agreement Start Date|Agreement End Date):\s*(\d{1,2}/\d{1,2}/\d{4})', text_data)
         amounts = re.findall(r'\$\d{1,3}(?:,\d{3})*(?:\.\d{2})?', text_data)
-        if dates or amounts:
-            key_values.update({"Date": dates[0] if dates else "", "Amount": amounts[0] if amounts else ""})
+        names = re.findall(r'(Agreement Name):\s*([A-Za-z0-9\s-]+)', text_data)
+        # Update key_values with matched fields
+        for key, value in dates:
+            key_values[key] = value
+        if amounts:
+            key_values["Amount"] = amounts[0]
+        for key, value in names:
+            key_values[key] = value
 
         # Attempt LayoutLMv3 processing
         doc = fitz.open(pdf_path)
@@ -100,6 +107,25 @@ def extract_key_values_with_layoutlm(page_data: list, pdf_path: str) -> Dict[str
     except Exception as e:
         return {"status": "failed", "error": str(e), "key_values": {}}
 
+def extract_clauses(page_data: list) -> Dict[str, str]:
+    """
+    Extract clauses from PDF text based on keywords.
+    Args:
+        page_data (list): List of dictionaries with 'text' (str) per page.
+    Returns:
+        dict: Mapping of clause names to their text content.
+    """
+    clauses = {}
+    text_data = " ".join([page["text"] for page in page_data])
+    clause_keywords = ["Clause", "Section", "Terms", "Condition", "Provision"]
+    for keyword in clause_keywords:
+        matches = re.finditer(rf'{keyword}\s+\d+\.?\s*(.+?)(?=(?:\s*{keyword}\s+\d+\.?|\Z))', text_data, re.DOTALL)
+        for match in matches:
+            clause_text = match.group(1).strip()
+            if clause_text and len(clause_text.split()) > 5:  # Minimum length to ensure meaningful clause
+                clauses[f"{keyword} {len(clauses) + 1}"] = clause_text
+    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:
     """
     Map extracted key-values to object fields using LayoutLMv3-base (simplified).