LifeAdmin-AI / tools /form_filler_server.py
Maheen001's picture
Update tools/form_filler_server.py
474279e verified
raw
history blame
12.1 kB
"""
Form Filler Server - COMPLETE FIXED VERSION
Handles DOCX, XLSX, and text form templates with robust field matching
"""
from typing import Dict, Any
import json
from pathlib import Path
from docx import Document
from openpyxl import load_workbook
import re
async def fill_form(template_path: str, data: Dict[str, Any]) -> dict:
"""
Auto-fill form template with extracted data
Args:
template_path: Path to form template (DOCX or XLSX)
data: Dictionary of field values
Returns:
Dict with filled form path and fields filled
"""
try:
file_ext = Path(template_path).suffix.lower()
output_path = template_path.replace(file_ext, f'_filled{file_ext}')
if file_ext == '.docx':
return await fill_docx_form(template_path, data, output_path)
elif file_ext in ['.xlsx', '.xls']:
return await fill_excel_form(template_path, data, output_path)
else:
# Generic text replacement
return await fill_text_form(template_path, data, output_path)
except Exception as e:
import traceback
return {'error': f"{str(e)}\n\n{traceback.format_exc()}", 'success': False}
async def fill_docx_form(template_path: str, data: Dict[str, Any], output_path: str) -> dict:
"""Fill DOCX form template - COMPLETE FIXED VERSION with robust matching"""
try:
doc = Document(template_path)
fields_filled = []
debug_info = []
# Normalize data keys for comprehensive matching
normalized_data = {}
for key, value in data.items():
# Create multiple normalized versions of each key
key_variations = [
key, # Original: "First Name"
key.lower(), # Lowercase: "first name"
key.lower().replace(" ", ""), # No spaces: "firstname"
key.lower().replace(" ", "_"), # Underscores: "first_name"
key.replace(" ", ""), # No spaces original case: "FirstName"
key.replace(" ", "_"), # Underscores original case: "First_Name"
]
for variation in key_variations:
normalized_data[variation] = value
# Process all paragraphs
for para_idx, paragraph in enumerate(doc.paragraphs):
original_text = paragraph.text
modified = False
# Try to find and replace fields in paragraphs
for key, value in data.items():
# Check for various formats
patterns = [
(f"{key}:", f"{key}: {value}"), # "First Name:" -> "First Name: John"
(f"{key} :", f"{key}: {value}"), # "First Name :" -> "First Name: John"
(f"{key} _", f"{key}: {value}"), # "First Name _" -> "First Name: John"
(f"{key}__", f"{key}: {value}"), # "First Name__" -> "First Name: John"
]
for pattern, replacement in patterns:
if pattern in paragraph.text:
paragraph.text = paragraph.text.replace(pattern, replacement)
if key not in fields_filled:
fields_filled.append(key)
debug_info.append(f"Filled '{key}' in paragraph {para_idx}")
modified = True
break
if modified:
break
# Process all tables (primary method for form templates)
for table_idx, table in enumerate(doc.tables):
for row_idx, row in enumerate(table.rows):
for cell_idx, cell in enumerate(row.cells):
cell_text = cell.text.strip()
if not cell_text:
continue
# Method 1: Direct label matching with colon
for original_key, value in data.items():
# Create normalized version of cell text
cell_normalized = cell_text.lower().replace(":", "").strip()
key_normalized = original_key.lower().replace(":", "").strip()
# Check if cell contains the field label
if key_normalized == cell_normalized or cell_normalized.startswith(key_normalized):
# Check if value is already filled
if ":" in cell.text:
parts = cell.text.split(":", 1)
if len(parts) == 2 and not parts[1].strip():
# Empty after colon, fill it
cell.text = f"{parts[0]}: {value}"
if original_key not in fields_filled:
fields_filled.append(original_key)
debug_info.append(f"Filled '{original_key}' in table {table_idx}, row {row_idx}, cell {cell_idx}")
else:
# No colon, add it
cell.text = f"{cell.text}: {value}"
if original_key not in fields_filled:
fields_filled.append(original_key)
debug_info.append(f"Filled '{original_key}' in table {table_idx}, row {row_idx}, cell {cell_idx}")
# Method 2: Check next cell in same row
elif key_normalized in cell_normalized:
if cell_idx + 1 < len(row.cells):
next_cell = row.cells[cell_idx + 1]
# Only fill if next cell is empty or has placeholder
if not next_cell.text.strip() or next_cell.text.strip() in ["_", "__", "___", ""]:
next_cell.text = str(value)
if original_key not in fields_filled:
fields_filled.append(original_key)
debug_info.append(f"Filled '{original_key}' in next cell of table {table_idx}, row {row_idx}")
# Method 3: Check for placeholder patterns in cells
for key, value in normalized_data.items():
placeholders = [
f"{{{{{key}}}}}",
f"{{{key}}}",
f"[{key}]",
]
for placeholder in placeholders:
if placeholder.lower() in cell.text.lower():
cell.text = cell.text.replace(placeholder, str(value))
# Find original key
original_key = next((k for k in data.keys()
if k.lower().replace(" ", "") == key.lower().replace(" ", "")),
key)
if original_key not in fields_filled:
fields_filled.append(original_key)
debug_info.append(f"Filled placeholder '{placeholder}' in table {table_idx}")
# Ensure output directory exists
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
doc.save(output_path)
return {
'success': True,
'output_path': output_path,
'fields_filled': list(set(fields_filled)),
'total_fields': len(set(fields_filled)),
'debug_info': debug_info
}
except Exception as e:
import traceback
return {'error': f"{str(e)}\n\n{traceback.format_exc()}", 'success': False}
async def fill_excel_form(template_path: str, data: Dict[str, Any], output_path: str) -> dict:
"""Fill Excel form template"""
try:
wb = load_workbook(template_path)
ws = wb.active
fields_filled = []
# Iterate through all cells
for row in ws.iter_rows():
for cell_idx, cell in enumerate(row):
if cell.value and isinstance(cell.value, str):
cell_text = str(cell.value).strip()
# Check each field
for key, value in data.items():
key_normalized = key.lower().replace(":", "").strip()
cell_normalized = cell_text.lower().replace(":", "").strip()
# If cell contains field label
if key_normalized == cell_normalized or key_normalized in cell_normalized:
# Try to fill next cell
next_cell = row[cell_idx + 1] if cell_idx + 1 < len(row) else None
if next_cell and (not next_cell.value or str(next_cell.value).strip() == ""):
next_cell.value = str(value)
if key not in fields_filled:
fields_filled.append(key)
# Check for placeholders
placeholders = [
f"{{{{{key}}}}}",
f"{{{key}}}",
f"[{key}]",
]
for placeholder in placeholders:
if placeholder in cell_text:
cell.value = cell_text.replace(placeholder, str(value))
if key not in fields_filled:
fields_filled.append(key)
# Ensure output directory exists
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
wb.save(output_path)
return {
'success': True,
'output_path': output_path,
'fields_filled': list(set(fields_filled)),
'total_fields': len(set(fields_filled))
}
except Exception as e:
import traceback
return {'error': f"{str(e)}\n\n{traceback.format_exc()}", 'success': False}
async def fill_text_form(template_path: str, data: Dict[str, Any], output_path: str) -> dict:
"""Fill text-based form"""
try:
with open(template_path, 'r', encoding='utf-8') as f:
content = f.read()
fields_filled = []
for key, value in data.items():
placeholders = [
f"{{{{{key}}}}}",
f"{{{key}}}",
f"[{key}]",
]
for placeholder in placeholders:
if placeholder in content:
content = content.replace(placeholder, str(value))
if key not in fields_filled:
fields_filled.append(key)
# Ensure output directory exists
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
with open(output_path, 'w', encoding='utf-8') as f:
f.write(content)
return {
'success': True,
'output_path': output_path,
'fields_filled': fields_filled,
'total_fields': len(fields_filled)
}
except Exception as e:
import traceback
return {'error': f"{str(e)}\n\n{traceback.format_exc()}", 'success': False}