Update parser_vapi_welspun.py

parser_vapi_welspun.py

@@ -1,5 +1,4 @@
 import re
-import streamlit as st
 import pdfplumber
 from io import BytesIO
 from openpyxl.styles import Alignment
@@ -16,101 +15,11 @@ def extract_all_commodities_from_text(pdf_text):
 
 def extract_vapi_welspun_items(pdf_lines, pdf_text=""):
     parsed_items = []
-    box_commodities = extract_all_commodities_from_text(pdf_text)
-    
-    cached_bytes = st.session_state.get("cached_pdf_bytes", None)
-    if cached_bytes:
-        try:
-            with pdfplumber.open(BytesIO(cached_bytes)) as pdf:
-                for page in pdf.pages:
-                    tables = page.extract_tables()
-                    for table in tables:
-                        for row in table:
-                            if row and len(row) >= 5:
-                                clean_cells = [str(cell).strip() for cell in row if cell is not None and str(cell).strip() != ""]
-                                if not clean_cells:
-                                    continue
-                                    
-                                hs_code = ""
-                                hs_index = -1
-                                for idx, cell in enumerate(clean_cells):
-                                    if re.fullmatch(r'\d{8}', cell.replace(",", "").strip()):
-                                        hs_code = cell.replace(",", "").strip()
-                                        hs_index = idx
-                                        break
-                                        
-                                if not hs_code:
-                                    continue
-                                    
-                                dbk_sr = clean_cells[hs_index - 1] if hs_index > 0 else ""
-
-                                # डायनेमिक डिस्क्रिप्शन
-                                description_text = ""
-                                if hs_index != -1 and len(clean_cells) > hs_index + 1:
-                                    desc_parts = []
-                                    for idx in range(hs_index + 1, len(clean_cells)):
-                                        cell_val = clean_cells[idx]
-                                        if re.fullmatch(r'\d+\.\d+', cell_val) or re.fullmatch(r'\d+\s*[xX]\s*\d+', cell_val):
-                                            break
-                                        if cell_val.isdigit() and int(cell_val) > 99 and len(desc_parts) > 0:
-                                            break
-                                        desc_parts.append(cell_val)
-                                    description_text = " ".join(desc_parts).strip()
-
-                                if not description_text and hs_index > 0:
-                                    desc_candidates = [clean_cells[i] for i in range(0, hs_index) if not clean_cells[i].isdigit()]
-                                    description_text = " ".join(desc_candidates).strip()
-
-                                # 🚀 फिक्स: SQMTR और Net Wt को उनके क्रम (Order) से सेट करना ताकि कभी इंटरचेंज न हों
-                                net_wt, qty, rate, amount_usd, taxable_inr, igst_per, igst_amt, sqmtr = "", "", "", "", "", "", "", ""
-                                
-                                if len(clean_cells) >= 4:
-                                    igst_amt = clean_cells[-1]
-                                    igst_per = clean_cells[-2]
-                                    taxable_inr = clean_cells[-3]
-                                    amount_usd = clean_cells[-4]
-
-                                decimal_3_values = []
-                                for cell in clean_cells:
-                                    clean_c = cell.replace(",", "").strip()
-                                    if re.fullmatch(r'\d+\.\d{3}', clean_c):
-                                        decimal_3_values.append(cell)
-                                    elif re.fullmatch(r'\d+\.\d{5}', clean_c):
-                                        if not rate:
-                                            rate = cell
-                                    elif clean_c.isdigit() and int(clean_c) > 0 and cell != hs_code and cell != dbk_sr:
-                                        if not qty:
-                                            qty = cell
-
-                                # यदि एक से ज्यादा 3-डेसिमल वैल्यू हैं (जैसे SQMTR और Net Wt दोनों)
-                                if len(decimal_3_values) >= 2:
-                                    sqmtr = decimal_3_values[0]   # पहली वैल्यू SQMTR बनेगी
-                                    net_wt = decimal_3_values[1]  # दूसरी वैल्यू हमेशा Net Wt बनेगी
-                                elif len(decimal_3_values) == 1:
-                                    net_wt = decimal_3_values[0]  # अगर सिर्फ एक है तो वह Net Wt होगी
-
-                                item_dict = {f"col_{i}": (str(row[i]).strip() if i < len(row) and row[i] else "") for i in range(len(row))}
-                                item_dict.update({
-                                    "dbk_sr": dbk_sr,
-                                    "hs_code": hs_code,
-                                    "description_text": description_text,
-                                    "net_wt": net_wt,
-                                    "qty": qty,
-                                    "rate": rate,
-                                    "amount_usd": amount_usd,
-                                    "amount_inr": taxable_inr,
-                                    "igst_per": igst_per if igst_per else "5.00",
-                                    "igst_amt": igst_amt,
-                                    "sqmtr": sqmtr,
-                                    "box_commodities": box_commodities
-                                })
-                                parsed_items.append(item_dict)
-        except Exception as e:
-            st.error(f"Pattern Parser Error: {str(e)}")
-
-    if not parsed_items:
-        parsed_items.append({"dbk_sr": "", "hs_code": "", "description_text": "", "net_wt": "", "qty": "", "rate": "", "amount_usd": "", "amount_inr": "", "igst_per": "5.00", "igst_amt": "", "sqmtr": "", "box_commodities": []})
-
+    box_commodities = []
+    if pdf_text:
+        box_commodities = extract_all_commodities_from_text(pdf_text)
+        
+    parsed_items.append({"dbk_sr": "", "hs_code": "", "description_text": "", "net_wt": "", "qty": "", "rate": "", "amount_usd": "", "amount_inr": "", "igst_per": "5.00", "igst_amt": "", "sqmtr": "", "box_commodities": box_commodities})
     return parsed_items
 
 
@@ -130,7 +39,6 @@ def map_vapi_welspun_items_to_excel_dynamic(ws, parsed_items, item_rules, inv_sr
     v_column_value = "LUT" if matched_lut else ("P" if matched_paid else "LUT")
 
     max_rows = len(parsed_items)
-
     first_item = parsed_items[0] if parsed_items else {}
     all_comms = first_item.get("box_commodities", [])
 
@@ -163,8 +71,7 @@ def map_vapi_welspun_items_to_excel_dynamic(ws, parsed_items, item_rules, inv_sr
                 continue
                 
             if "extract" in rule_type_raw.lower() or "box" in rule_type_raw.lower() or "header" in rule_type_raw.lower() or col_letter in ["BW", "BY"]:
-                cached_bytes = st.session_state.get("cached_pdf_bytes", None)
-                extracted_val = extract_header_value(pdf_lines, pdf_text, rule_val, "📦 Extract Inside Box (डब्बे के अंदर का टेक्स्ट)", "Exact Word", "", "None", field_label=field_name, pdf_bytes=cached_bytes)
+                extracted_val = extract_header_value(pdf_lines, pdf_text, rule_val, "📦 Extract Inside Box (डब्बे के अंदर का टेक्स्ट)", "Exact Word", "", "None", field_label=field_name)
                 if not extracted_val or not extracted_val.strip():
                     extracted_val = extract_header_value(pdf_lines, pdf_text, rule_val, "Right (आगे)", "Exact Word", "", "None", field_label=field_name)
                 
@@ -239,4 +146,4 @@ def map_vapi_welspun_items_to_excel_dynamic(ws, parsed_items, item_rules, inv_sr
         curr_row += 1
         overall_sr += 1
         
-    return ws, overall_sr, curr_row
+    return ws, overall_sr, curr_row