#!/usr/bin/env python3
"""Script to add ObjectId conversion before creating model instances"""
import re

def add_objectid_conversion(file_path, model_name):
    """Add doc['_id'] = str(doc['_id']) before Model(**doc) calls"""

    with open(file_path, 'r') as f:
        lines = f.readlines()

    modified_lines = []
    i = 0
    changes_made = 0

    while i < len(lines):
        line = lines[i]

        # Pattern 1: Single line creation like: return Keyword(**doc)
        if re.search(rf'{model_name}\(\*\*doc\)', line):
            indent = len(line) - len(line.lstrip())
            # Check if previous line already has the conversion
            if i > 0 and 'doc["_id"] = str(doc["_id"])' in lines[i-1]:
                modified_lines.append(line)
                i += 1
                continue
            # Check if this is inside a loop or conditional that already has conversion
            if i > 0 and any('doc["_id"] = str(doc["_id"])' in lines[j] for j in range(max(0, i-5), i)):
                modified_lines.append(line)
                i += 1
                continue
            # Add conversion before this line
            modified_lines.append(' ' * indent + 'doc["_id"] = str(doc["_id"])  # Convert ObjectId to string\n')
            modified_lines.append(line)
            changes_made += 1
            i += 1
            continue

        # Pattern 2: In loops like: keywords.append(Keyword(**doc))
        if re.search(rf'{model_name}\(\*\*doc\)', line) and ('append' in line or 'for' in line):
            indent = len(line) - len(line.lstrip())
            # Check if previous line already has the conversion
            if i > 0 and 'doc["_id"] = str(doc["_id"])' in lines[i-1]:
                modified_lines.append(line)
                i += 1
                continue
            # Add conversion before this line
            modified_lines.append(' ' * indent + 'doc["_id"] = str(doc["_id"])  # Convert ObjectId to string\n')
            modified_lines.append(line)
            changes_made += 1
            i += 1
            continue

        # Pattern 3: Dictionary creation like: return Keyword(**keyword_dict)
        match = re.search(rf'{model_name}\(\*\*(\w+)\)', line)
        if match and match.group(1) != 'doc':
            dict_name = match.group(1)
            indent = len(line) - len(line.lstrip())
            # Check if previous line already has the conversion
            if i > 0 and f'{dict_name}["_id"] = str({dict_name}["_id"])' in lines[i-1]:
                modified_lines.append(line)
                i += 1
                continue
            # Add conversion before this line
            modified_lines.append(' ' * indent + f'{dict_name}["_id"] = str({dict_name}["_id"])  # Convert ObjectId to string\n')
            modified_lines.append(line)
            changes_made += 1
            i += 1
            continue

        # Pattern 4: List comprehension like: [Keyword(**kw) for kw in keywords_dicts]
        if re.search(rf'\[{model_name}\(\*\*\w+\)', line):
            # This needs manual fixing as it's a list comprehension
            print(f"Line {i+1}: List comprehension found, needs manual fixing: {line.strip()}")

        modified_lines.append(line)
        i += 1

    # Write back
    with open(file_path, 'w') as f:
        f.writelines(modified_lines)

    print(f"Modified {file_path}: {changes_made} changes made")
    return changes_made

if __name__ == "__main__":
    total = 0
    total += add_objectid_conversion("app/services/keyword_service.py", "Keyword")
    total += add_objectid_conversion("app/services/pipeline_service.py", "Pipeline")
    total += add_objectid_conversion("app/services/application_service.py", "Application")
    print(f"\nTotal changes: {total}")