report-detect/archive/temp_scripts/verify_crt_extraction.py

38 lines
932 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""
直接验证CRT提取 - 不使用multiprocessing
"""
from test_accuracy_batch_full import extract_institution_from_crt
import sys
test_pdfs = [
"src/test/resources/data/pdfs/YDQ23_001838.pdf",
"src/test/resources/data/pdfs/YDQ23_001850.pdf",
]
print("="*80)
print("直接验证CRT提取无multiprocessing")
print("="*80)
for pdf_path in test_pdfs:
print(f"\nTesting: {pdf_path}")
try:
# 直接调用不使用multiprocessing
result = extract_institution_from_crt(pdf_path)
print(f"Result: {result}")
if result:
print(f"SUCCESS! Found {len(result)} institution(s)")
for i, inst in enumerate(result, 1):
print(f" {i}. {inst}")
else:
print(f"FAILED! No institutions found")
except Exception as e:
print(f"ERROR: {e}")
import traceback
traceback.print_exc()
print("\n" + "="*80)