#!/usr/bin/env python3
"""Test script to verify that hardcoded values have been properly replaced with constants."""

import re
from scraper import (
    DEFAULT_PART_FILE,
    DEFAULT_OUTPUT_DIR,
    DETAIL_BASE_URL,
    DEFAULT_MATERIAL_NAME,
    DEFAULT_CHAPTER_NAME,
    DEFAULT_COURSE_TITLE,
    DEFAULT_FILENAME,
    TAG_DIMENSION_ID,
    MAX_FILENAME_LENGTH,
    MAX_DIRNAME_LENGTH,
    CHUNK_SIZE,
    REQUEST_TIMEOUT,
    DETAIL_REQUEST_TIMEOUT,
    DEFAULT_TOKEN
)

def test_constants():
    """Test that all constants have expected values."""
    print("Testing configuration constants...")
    
    # Test file paths
    assert DEFAULT_PART_FILE == "example_part_100.json", f"Expected 'example_part_100.json', got '{DEFAULT_PART_FILE}'"
    assert DEFAULT_OUTPUT_DIR == "downloaded", f"Expected 'downloaded', got '{DEFAULT_OUTPUT_DIR}'"
    
    # Test API endpoints
    assert DETAIL_BASE_URL == "https://s-file-2.ykt.cbern.com.cn/zxx/ndrv2/national_lesson/resources/details", f"URL mismatch"
    
    # Test default values
    assert DEFAULT_MATERIAL_NAME == "未知教材", f"Expected '未知教材', got '{DEFAULT_MATERIAL_NAME}'"
    assert DEFAULT_CHAPTER_NAME == "未知章节", f"Expected '未知章节', got '{DEFAULT_CHAPTER_NAME}'"
    assert DEFAULT_COURSE_TITLE == "未知课程", f"Expected '未知课程', got '{DEFAULT_COURSE_TITLE}'"
    assert DEFAULT_FILENAME == "unnamed", f"Expected 'unnamed', got '{DEFAULT_FILENAME}'"
    
    # Test tag and identifier constants
    assert TAG_DIMENSION_ID == "zxxcc", f"Expected 'zxxcc', got '{TAG_DIMENSION_ID}'"
    
    # Test file and directory constraints
    assert MAX_FILENAME_LENGTH == 100, f"Expected 100, got {MAX_FILENAME_LENGTH}"
    assert MAX_DIRNAME_LENGTH == 50, f"Expected 50, got {MAX_DIRNAME_LENGTH}"
    
    # Test network settings
    assert CHUNK_SIZE == 8192, f"Expected 8192, got {CHUNK_SIZE}"
    assert REQUEST_TIMEOUT == 30, f"Expected 30, got {REQUEST_TIMEOUT}"
    assert DETAIL_REQUEST_TIMEOUT == 20, f"Expected 20, got {DETAIL_REQUEST_TIMEOUT}"
    
    print("✓ All constants have expected values")

def test_no_hardcoded_values():
    """Test that no hardcoded values remain in the scraper.py file."""
    print("Testing for remaining hardcoded values...")
    
    with open('scraper.py', 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Remove the constant definition section to avoid false positives
    # Find where the main function starts
    lines = content.split('\n')
    main_start = None
    for i, line in enumerate(lines):
        if line.startswith('def main():'):
            main_start = i
            break
    
    if main_start is None:
        print("❌ Could not find main function")
        return False
    
    # Get only the content after constant definitions (from main function onward)
    function_content = '\n'.join(lines[main_start:])
    
    # Check for hardcoded values in function bodies only
    hardcoded_patterns = [
        r'https://s-file-2\.ykt\.cbern\.com\.cn/zxx/ndrv2/national_lesson/resources/details',
        r'"example_part_100\.json"',
        r'"downloaded"',
        r'"未知教材"',
        r'"未知章节"', 
        r'"未知课程"',
        r'"unnamed"',
        r'"zxxcc"',
        r'timeout=20',
        r'timeout=30',
        r'chunk_size=8192'
    ]
    
    found_hardcoded = []
    for pattern in hardcoded_patterns:
        matches = re.findall(pattern, function_content)
        if matches:
            found_hardcoded.extend(matches)
    
    if found_hardcoded:
        print("⚠️ Found potential hardcoded values in function bodies:")
        for value in set(found_hardcoded):
            print(f"  - {value}")
    else:
        print("✓ No hardcoded values found in function bodies")
    
    return len(found_hardcoded) == 0

if __name__ == "__main__":
    test_constants()
    all_good = test_no_hardcoded_values()
    
    if all_good:
        print("\n🎉 All tests passed! Hardcoded values have been successfully optimized.")
    else:
        print("\n❌ Some hardcoded values may still exist. Please review the code.")