From a202abf5c0c5eb90bf118b812f8ae74b1083217b Mon Sep 17 00:00:00 2001
From: Iyeoluwa Akinrinola <iyeoluwa@connou.app>
Date: Thu, 3 Jul 2025 00:44:01 +0100
Subject: [PATCH] Fix date parsing for image import to handle various date
 formats

---
 document_processor.py | 48 ++++++++++++++++++++++++++++++++++++++++++-
 main.py               | 11 +++++++---
 2 files changed, 55 insertions(+), 4 deletions(-)

diff --git a/document_processor.py b/document_processor.py
index 87337c2..4a36c50 100644
--- a/document_processor.py
+++ b/document_processor.py
@@ -328,4 +328,50 @@ class DocumentProcessor:
                 "extraction_success": False,
                 "error": f"JSON parsing error: {str(e)}",
                 "transactions": []
-            } 
\ No newline at end of file
+            }
+
+    def _parse_date_to_iso(self, date_str: str) -> str:
+        """Parse various date formats and convert to YYYY-MM-DD"""
+        try:
+            import re
+            from datetime import datetime
+            
+            date_str = date_str.strip().upper()
+            
+            # Handle formats like "MAY 22", "JUN 01", "MAY 22, 2024"
+            month_pattern = r'(JAN|FEB|MAR|APR|MAY|JUN|JUL|AUG|SEP|OCT|NOV|DEC)\s+(\d{1,2})(?:,\s*(\d{4}))?'
+            match = re.match(month_pattern, date_str)
+            
+            if match:
+                month_abbr, day, year = match.groups()
+                month_map = {
+                    'JAN': 1, 'FEB': 2, 'MAR': 3, 'APR': 4, 'MAY': 5, 'JUN': 6,
+                    'JUL': 7, 'AUG': 8, 'SEP': 9, 'OCT': 10, 'NOV': 11, 'DEC': 12
+                }
+                
+                month = month_map[month_abbr]
+                day = int(day)
+                year = int(year) if year else datetime.now().year
+                
+                # Handle 2-digit years
+                if year < 100:
+                    year += 2000
+                
+                return f"{year:04d}-{month:02d}-{day:02d}"
+            
+            # Handle YYYY-MM-DD format
+            if re.match(r'\d{4}-\d{2}-\d{2}', date_str):
+                return date_str
+            
+            # Handle MM/DD/YYYY format
+            if re.match(r'\d{1,2}/\d{1,2}/\d{4}', date_str):
+                return datetime.strptime(date_str, '%m/%d/%Y').strftime('%Y-%m-%d')
+            
+            # Handle MM/DD/YY format
+            if re.match(r'\d{1,2}/\d{1,2}/\d{2}', date_str):
+                return datetime.strptime(date_str, '%m/%d/%y').strftime('%Y-%m-%d')
+            
+            return None
+            
+        except Exception:
+            return None 
\ No newline at end of file
diff --git a/main.py b/main.py
index ef12860..ba2c258 100644
--- a/main.py
+++ b/main.py
@@ -200,11 +200,16 @@ async def import_transactions_from_image(file: UploadFile = File(...)):
                 # Generate unique ID
                 txn_id = f"img_{file.filename}_{idx+1}"
                 
-                # Parse date
-                txn_date = txn.get("date", "")
-                if not txn_date:
+                # Parse date - handle various formats
+                txn_date_raw = txn.get("date", "")
+                if not txn_date_raw:
                     raise ValueError("No date found in transaction")
                 
+                # Convert date to YYYY-MM-DD format
+                txn_date = document_processor._parse_date_to_iso(txn_date_raw)
+                if not txn_date:
+                    raise ValueError(f"Could not parse date: {txn_date_raw}")
+                
                 # Parse amount
                 amount_str = str(txn.get("amount", "0"))
                 amount = float(amount_str.replace('$', '').replace(',', '').strip())