taiko-web/verify_sort.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
歌曲排序功能验证脚本
运行方式: python verify_sort.py
"""

import locale
from functools import cmp_to_key

# 设置本地化以支持多语言排序
locale.setlocale(locale.LC_ALL, '')

def smart_sort(title_a, title_b):
    """
    智能排序函数（与 JavaScript 版本逻辑相同）
    """
    def get_char_type(char):
        """判断字符类型"""
        if not char:
            return 3  # 空字符串排在最后
        
        code = ord(char)
        
        # 数字 (0-9)
        if 48 <= code <= 57:
            return 0
        
        # 英文字母 (A-Z, a-z)
        if (65 <= code <= 90) or (97 <= code <= 122):
            return 1
        
        # 其他所有字符（符号、中文、日文等）
        return 2
    
    # 获取首字符类型
    type_a = get_char_type(title_a[0] if title_a else None)
    type_b = get_char_type(title_b[0] if title_b else None)
    
    # 首先按字符类型排序：数字 < 字母 < 其他符号
    if type_a != type_b:
        return type_a - type_b
    
    # 同类型字符，使用自然排序
    # Python 的 locale.strcoll 提供类似 localeCompare 的功能
    try:
        # 尝试数值比较（对于纯数字开头的字符串）
        if type_a == 0:  # 数字类型
            # 提取开头的数字部分进行比较
            num_a = ''
            num_b = ''
            
            for c in title_a:
                if c.isdigit():
                    num_a += c
                else:
                    break
            
            for c in title_b:
                if c.isdigit():
                    num_b += c
                else:
                    break
            
            if num_a and num_b:
                num_cmp = int(num_a) - int(num_b)
                if num_cmp != 0:
                    return num_cmp
        
        # 字符串比较（忽略大小写）
        return locale.strcoll(title_a.lower(), title_b.lower())
    except:
        # 如果 locale 比较失败，使用简单的字符串比较
        if title_a.lower() < title_b.lower():
            return -1
        elif title_a.lower() > title_b.lower():
            return 1
        return 0

def get_type_label(title):
    """获取字符类型标签"""
    if not title:
        return '[空]'
    
    code = ord(title[0])
    
    if 48 <= code <= 57:
        return '[数字]'
    if (65 <= code <= 90) or (97 <= code <= 122):
        return '[字母]'
    return '[其他]'

def main():
    # 测试数据
    test_songs = [
        "太鼓の達人",
        "Zyxwv Test",
        "123 Song",
        "abc melody",
        "456 rhythm",
        "*Special*",
        "10 drums",
        "あいうえお",
        "2 beats",
        "ZZZ Final",
        "1st Place",
        "100 percent",
        "ドンだー！",
        "Battle No.1",
        "~奇跡~",
        "777",
        "Angel Beats",
        "カノン",
        "Don't Stop",
        "零 -ZERO-",
        "3pieces",
        "Apple",
        "燎原ノ舞",
        "99 Balloons",
        "Brave Heart",
        "夏祭り",
        "5 Elements",
        "50音",
        "Zephyr",
        "α wave"
    ]
    
    print('\n' + '=' * 60)
    print('🥁 Taiko Web - 歌曲智能排序功能测试')
    print('=' * 60 + '\n')
    
    print(f'📋 原始歌曲列表 (共 {len(test_songs)} 首):')
    print('-' * 60)
    for i, song in enumerate(test_songs, 1):
        print(f'{i:2d}. {song}')
    
    print('\n' + '=' * 60)
    print('⚙️  执行智能排序...\n')
    
    # 排序
    sorted_songs = sorted(test_songs, key=cmp_to_key(smart_sort))
    
    print('✅ 排序后的歌曲列表:')
    print('-' * 60)
    
    current_type = None
    for i, song in enumerate(sorted_songs, 1):
        type_label = get_type_label(song)
        
        # 检测类型变化，添加分隔符
        if current_type != type_label:
            if current_type is not None:
                print()  # 空行分隔不同类型
            current_type = type_label
        
        print(f'{i:2d}. {song:25s} {type_label}')
    
    print('\n' + '=' * 60)
    print('📊 统计信息:')
    print('-' * 60)
    
    # 统计各类型数量
    number_count = sum(1 for song in sorted_songs if get_type_label(song) == '[数字]')
    letter_count = sum(1 for song in sorted_songs if get_type_label(song) == '[字母]')
    other_count = sum(1 for song in sorted_songs if get_type_label(song) == '[其他]')
    
    print(f'数字开头: {number_count} 首')
    print(f'字母开头: {letter_count} 首')
    print(f'其他开头: {other_count} 首')
    print(f'总计:     {len(sorted_songs)} 首')
    
    print('\n' + '=' * 60)
    print('✨ 排序规则验证:')
    print('-' * 60)
    
    # 验证排序是否正确
    is_valid = True
    prev_type = -1
    
    for song in sorted_songs:
        code = ord(song[0])
        
        if 48 <= code <= 57:
            current_type = 0
        elif (65 <= code <= 90) or (97 <= code <= 122):
            current_type = 1
        else:
            current_type = 2
        
        if current_type < prev_type:
            is_valid = False
            print(f'❌ 错误: "{song}" (类型 {current_type}) 出现在类型 {prev_type} 之后')
        
        prev_type = current_type
    
    if is_valid:
        print('✅ 排序规则验证通过！')
        print('   - 数字优先')
        print('   - 字母次之')
        print('   - 其他符号最后')
    else:
        print('❌ 排序规则验证失败！')
    
    print('\n' + '=' * 60)
    print('🎵 测试完成！')
    print('=' * 60 + '\n')

if __name__ == '__main__':
    main()