report-detect/archive/temp_scripts/analyze_ydq.py

"""
Debug CMA extraction issues for specific PDFs.
"""
import os
import cv2
import numpy as np
import re

# Set environment variables
os.environ['PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK'] = 'True'

from paddleocr import PaddleOCR

# Initialize OCR
print('Initializing PaddleOCR...')
ocr = PaddleOCR(use_angle_cls=True, lang='ch')

# Read image
img = cv2.imread('debug_images/YDQ25_002294_page1.png')
h, w = img.shape[:2]
print(f'Image size: {w}x{h}')

# Extract top-right area (CMA logo usually there)
top_right = img[0:int(h*0.4), int(w*0.4):w]
cv2.imwrite('debug_images/YDQ25_002294_top_right.png', top_right)
print(f'Top-right area saved: {top_right.shape[1]}x{top_right.shape[0]}')

# OCR on top-right
print('\nRunning OCR on top-right area...')
result = ocr.ocr(top_right)

print(f'OCR result type: {type(result)}')
if result:
    print(f'OCR result length: {len(result)}')
    if len(result) > 0:
        print(f'OCR result[0] type: {type(result[0])}')
        print(f'OCR result[0]: {result[0]}')

# Find 11-digit numbers
cma_pattern = re.compile(r'\d{11}')
all_numbers = []

# Handle different result formats
if result is None:
    print('OCR returned None')
elif isinstance(result, list) and len(result) > 0:
    ocr_data = result[0]

    if ocr_data is None:
        print('OCR result[0] is None')
    elif isinstance(ocr_data, list):
        print(f'Found {len(ocr_data)} text lines')

        for i, line in enumerate(ocr_data[:20]):
            try:
                if len(line) >= 2:
                    text = line[1][0] if isinstance(line[1], (list, tuple)) else str(line[1])
                    print(f'{i+1}. {text}')

                    # Find 11-digit numbers
                    cleaned = text.replace(' ', '').replace('-', '').replace(':', '')
                    matches = cma_pattern.findall(cleaned)
                    for match in matches:
                        all_numbers.append({
                            'number': match,
                            'text': text
                        })
            except Exception as e:
                print(f'Error processing line {i}: {e}')
                continue

print(f'\nFound {len(all_numbers)} 11-digit numbers in top-right:')
for i, num_info in enumerate(all_numbers, 1):
    print(f'{i}. {num_info["number"]} - Text: "{num_info["text"]}"')

expected = '240020349096'
found = any(n['number'] == expected for n in all_numbers)
print(f'\nExpected CMA {expected}: {"FOUND" if found else "NOT FOUND"}')

# If not found, try full page OCR
if not found:
    print('\nRunning full page OCR...')
    full_result = ocr.ocr(img)

    if full_result and isinstance(full_result, list) and len(full_result) > 0:
        full_ocr_data = full_result[0]
        if isinstance(full_ocr_data, list):
            all_numbers_full = []

            for line in full_ocr_data:
                try:
                    if len(line) >= 2:
                        text = line[1][0] if isinstance(line[1], (list, tuple)) else str(line[1])
                        cleaned = text.replace(' ', '').replace('-', '').replace(':', '')
                        matches = cma_pattern.findall(cleaned)
                        for match in matches:
                            all_numbers_full.append({
                                'number': match,
                                'text': text
                            })
                except:
                    continue

            print(f'Found {len(all_numbers_full)} 11-digit numbers on full page')
            print('\nFirst 15 numbers:')
            for i, num_info in enumerate(all_numbers_full[:15], 1):
                text_preview = num_info["text"][:60] if len(num_info["text"]) > 60 else num_info["text"]
                print(f'{i}. {num_info["number"]} - Text: "{text_preview}..."')

            found_full = any(n['number'] == expected for n in all_numbers_full)
            print(f'\nExpected CMA {expected} on full page: {"FOUND" if found_full else "NOT FOUND"}')

            if not found_full:
                print('\nCONCLUSION:')
                print(f'The expected CMA code {expected} is NOT present in the OCR output.')
                print('Possible reasons:')
                print('1. CMA code is not on the first page')
                print('2. CMA code is in an image/graphic format that OCR cannot read')
                print('3. CMA code is handwritten or in a special font')
                print('4. The expected CMA code in results.json is incorrect')