// 2026-04-25 | test_pdf_garbled_chars.dart | PDF乱码字符诊断脚本
// 2026-04-25 | 创建: 验证 _cleanPdfText 对各种Unicode字符的过滤效果

void main() {
  print('╔══════════════════════════════════════════════════════════════╗');
  print('║           PDF 乱码字符诊断工具 v1.0                          ║');
  print('║           测试 _cleanPdfText 过滤效果                        ║');
  print('╚══════════════════════════════════════════════════════════════╝\n');

  // ========== 测试用例 ==========
  final testCases = <_TestCase>[
    // 基础测试 - 正常文本应该保留
    _TestCase(name: '✅ 正常中文', input: '这道菜很好吃，营养丰富', expected: '保留'),
    _TestCase(name: '✅ 中英文混合', input: 'Hello世界，美味佳肴123', expected: '保留'),
    _TestCase(name: '✅ 纯英文', input: 'Delicious food recipe', expected: '保留'),

    // 乱码测试 - 应该被过滤
    _TestCase(name: '❌ 菱形方块 (U+25FF)', input: '▯▯▯▯▯▯▯▯▯▯▯▯', expected: '过滤'),
    _TestCase(name: '❌ 交叉形状 (U+2716)', input: '✖✖✖✖✖✖✖✖✖', expected: '过滤'),
    _TestCase(
      name: '❌ 私用区字符 (U+E000-U+F8FF)',
      input: '\uE000\uE001\uE002\uE003\uE004\uE005',
      expected: '过滤',
    ),
    _TestCase(
      name: '❌ 变体选择器 (U+FE00-U+FE0F)',
      input: 'A\uFE00B\uFE01C\uFE02',
      expected: '过滤或部分保留',
    ),
    _TestCase(
      name: '❌ 控制字符 (U+00-U+1F)',
      input: '\x00\x01\x02\x03\x04\x05',
      expected: '过滤',
    ),
    _TestCase(name: '❌ Unicode替换字符 (U+FFFD)', input: '�����', expected: '过滤'),

    // 边界情况
    _TestCase(name: '⚠️ 混合内容 (正常+乱码)', input: '很好吃▯▯▯营养▯▯丰富', expected: '部分保留'),
    _TestCase(
      name: '⚠️ 高比例乱码 (>40%)',
      input: '好吃▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯▯',
      expected: '过滤（>40%阈值）',
    ),
    _TestCase(
      name: '⚠️ 低比例乱码 (<40%)',
      input: '这道菜真的很好吃，营养丰富味道鲜美▯▯',
      expected: '保留（<40%阈值）',
    ),

    // 特殊Unicode区块
    _TestCase(
      name: '🔣 制表符/边框 (U+2500-U+257F)',
      input: '┌┐└┘├┤┬┴┼─│',
      expected: '过滤',
    ),
    _TestCase(
      name: '🔣 方块元素 (U+25A0-U+25FF)',
      input: '■□▢▣▤▥▦▧▨▩',
      expected: '过滤',
    ),
    _TestCase(
      name: '🔣 几何形状 (U+25A0-U+25FF)',
      input: '▲▼◆◇○●◐◑◒◓',
      expected: '过滤',
    ),
    _TestCase(
      name: '🔣 箭头符号 (U+2190-U+21FF)',
      input: '→←↑↓↔⇒⇐⇑⇓',
      expected: '过滤',
    ),
    _TestCase(
      name: '🔣 数学运算符 (U+2200-U+22FF)',
      input: '±×÷≈≠≤≥∞√',
      expected: '过滤',
    ),
    _TestCase(
      name: '🔣 装饰符号 (U+2700-U+27BF)',
      input: '✓✔✗✘★☆♠♣♥♦',
      expected: '过滤',
    ),
    _TestCase(
      name: '🔣 Dingbats (U+2700-U+27BF)',
      input: '❤❥❦❧❝❞❟❰❱',
      expected: '过滤',
    ),

    // 实际场景模拟
    _TestCase(
      name: '🎯 场景1: displayIntro含PUA',
      input: '美味家常菜\uE000\uE001\uE002\uE003',
      expected: '保留"美味家常菜"',
    ),
    _TestCase(
      name: '🎯 场景2: 全是乱码',
      input: '\uE000\uE001\uE002\uE003\uE004\uE005\uE006\uE007\uE008\uE009',
      expected: '空字符串',
    ),
    _TestCase(
      name: '🎯 场景3: 含控制字符',
      input: '好吃的菜\x01\x02\x03\x04\x05',
      expected: '保留"好吃的菜"',
    ),
    _TestCase(
      name: '🎯 场景4: CJK扩展区汉字',
      input: '\u3400\u3401\u3402\u4E00\u4E01', // CJK扩展A + 统一汉字
      expected: '保留（CJK扩展区）',
    ),
  ];

  // ========== 执行测试 ==========
  int passed = 0;
  int failed = 0;

  for (var i = 0; i < testCases.length; i++) {
    final tc = testCases[i];
    print('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
    print("测试 ${i + 1}/${testCases.length}: ${tc.name}");
    print('输入: "${tc.input}"');

    // 打印每个字符的详细信息
    print('字符分析:');
    for (var j = 0; j < tc.input.length; j++) {
      final cp = tc.input.codeUnitAt(j);
      final char = tc.input[j];
      final cpHex = 'U+${cp.toRadixString(16).toUpperCase().padLeft(4, '0')}';

      String category;
      if (_isCjk(cp)) {
        category = 'CJK汉字';
      } else if (_isAsciiLetter(cp)) {
        category = 'ASCII字母';
      } else if (_isDigit(cp)) {
        category = '数字';
      } else if (_isSpace(cp)) {
        category = '空白';
      } else if (_isPunctuation(cp)) {
        category = '标点';
      } else if (_shouldFilterChar(cp, char)) {
        category = '❌ 将被过滤';
      } else {
        category = '⚠️ 未分类';
      }

      print('  [$j] "$char" $cpHex → $category');
    }

    // 执行清理
    final result = _cleanPdfText(tc.input);
    print('输出: "${result ?? "null"}"');
    print('长度: ${result?.length ?? 0}');

    // 判断是否通过
    bool testPassed = false;
    if (tc.expected.contains('保留') && result != null && result.isNotEmpty) {
      testPassed = true;
    } else if (tc.expected.contains('过滤') &&
        (result == null || result.isEmpty)) {
      testPassed = true;
    } else if (tc.expected.contains('空字符串') &&
        (result == null || result.isEmpty)) {
      testPassed = true;
    }

    if (testPassed) {
      print('结果: ✅ 通过 (预期: ${tc.expected})');
      passed++;
    } else {
      print('结果: ❌ 失败 (预期: ${tc.expected})');
      failed++;
    }
    print('');
  }

  // ========== 汇总 ==========
  print('╔══════════════════════════════════════════════════════════════╗');
  print('║                      测试汇总                                ║');
  print('╠══════════════════════════════════════════════════════════════╣');
  print(
    '║  总测试数: ${testCases.length.toString().padLeft(3)}                                              ║',
  );
  print(
    '║  ✅ 通过:  ${passed.toString().padLeft(3)}                                              ║',
  );
  print(
    '║  ❌ 失败:  ${failed.toString().padLeft(3)}                                              ║',
  );
  print(
    '║  通过率:  ${(passed / testCases.length * 100).toStringAsFixed(1).padLeft(5)}%                                            ║',
  );
  print('╚══════════════════════════════════════════════════════════════╝');

  if (failed > 0) {
    print('\n⚠️ 有 $failed 个测试失败，请检查过滤逻辑！');
  } else {
    print('\n🎉 所有测试通过！_cleanPdfText 工作正常。');
  }
}

// ========== 核心方法 (从 recipe_export_button.dart 复制) ==========

String _cleanPdfText(String text) {
  if (text.isEmpty) return '';
  var cleaned = StringBuffer();
  for (var i = 0; i < text.length; i++) {
    final codeUnit = text.codeUnitAt(i);
    final char = text[i];
    if (_shouldFilterChar(codeUnit, char)) continue;
    cleaned.write(char);
  }
  var result = cleaned.toString().trim();
  if (result.isEmpty) return '';
  if (_isGarbledText(result)) return '';
  return result;
}

bool _shouldFilterChar(int codeUnit, String char) {
  if (codeUnit < 0x20 &&
      codeUnit != 0x09 &&
      codeUnit != 0x0A &&
      codeUnit != 0x0D) {
    return true;
  }
  if (codeUnit == 0x7F) return true;
  if (codeUnit >= 0x80 && codeUnit <= 0x9F) return true;
  if ((codeUnit & 0xFFFE) == 0xFFFE || (codeUnit & 0xFFFE) == 0xFFFF)
    return true;
  if (codeUnit == 0xFFFD) return true;
  if (codeUnit >= 0xFDD0 && codeUnit <= 0xFDEF) return true;
  if (codeUnit >= 0xE000 && codeUnit <= 0xF8FF) return true;
  if (codeUnit >= 0xFFF0 && codeUnit <= 0xFFFB) return true;
  if (codeUnit >= 0xFE00 && codeUnit <= 0xFE0F) return true;
  if (_isSpecialSymbol(char)) return true;
  return false;
}

bool _isSpecialSymbol(String char) {
  const rawSymbols =
      '▯□■◯○●◇◆▪▫◻◼◽◾▱░▒▓█▄▌▐▀▸▂▁▃▅▆▇▉▊▋▎▏▕▖▗▘▙▚▛▜▝▞▟╭╮╯╰╱╲╳╴╵╶╷╸╹╺╻╼╽╾╿┌┐└┘├┤┬┴┼─│┈┉┊┋━┃┅┆┇┍┎┏┐┑▒┓└┕┖┗┘┙┚┛├┝┞┟┠┡┢┣┤┥┦┧┨┩┪┫┬┭┮┯┰┱┲┳┴┵┶┷┸┹┺┻┼┽┾┿╀╁╂╃╄╅╆╇╈╉╊╋☐☑☒✓✔✗✘→←↑↓↔⇒⇐⇑⇓⇔⇕⇖⇗⇘⇙♠♣♥♦★☆▲▼◐◑◒◓◔◕◖◗❤❥❦❧❝❞❟❰❱❲❳❴❵❶❷❸❹❺❻❼❽❾❿➔➘➙➚➛➜➝➞➟➠➡➢➣➤➥➦➧➨➩➪➫➬➭➮➯➱➲➳➴➵➶➷➸➹➺➻➼➽➾➿⟦⟧⟨⟩⟪⟫⟬⟭⟮⟯⬅⬆⬇⬈⬉⬊⬋⬌⬍⬎⬏⬐⬑⬒⬓⬘⬙⬚⬛⬜⬝⬞⬟⬠⬡⭢⭣⭤⭥⭦⭧⭨⭩⭪⭫⭬⭭⭮⭯⭐⭕⭘⭙⭚⭛⭜⭝⭞⭟⭠⭡⭢⭣⭤⭥';
  return rawSymbols.contains(char);
}

bool _isGarbledText(String text) {
  if (text.length < 2) return false;
  int specialCount = 0;
  for (int i = 0; i < text.length; i++) {
    final cp = text.codeUnitAt(i);
    final isCjk =
        (cp >= 0x4E00 && cp <= 0x9FFF) ||
        (cp >= 0x3400 && cp <= 0x4DBF) ||
        (cp >= 0x20000 && cp <= 0x2A6DF) ||
        (cp >= 0x2A700 && cp <= 0x2B73F) ||
        (cp >= 0x2B740 && cp <= 0x2B81F) ||
        (cp >= 0x2B820 && cp <= 0x2CEAF) ||
        (cp >= 0xF900 && cp <= 0xFAFF) ||
        (cp >= 0x2F800 && cp <= 0x2FA1F);
    final isAsciiLetter =
        (cp >= 0x41 && cp <= 0x5A) || (cp >= 0x61 && cp <= 0x7A);
    final isDigit = cp >= 0x30 && cp <= 0x39;
    final isSpace = cp == 0x20 || cp == 0x09 || cp == 0x0A || cp == 0x0D;
    final isPunctuation =
        (cp >= 0x2000 && cp <= 0x206F) ||
        (cp >= 0x3000 && cp <= 0x303F) ||
        (cp >= 0xFF00 && cp <= 0xFFEF) ||
        cp == 0x2E ||
        cp == 0x2C ||
        cp == 0x3B ||
        cp == 0x3A ||
        cp == 0x21 ||
        cp == 0x3F ||
        cp == 0x28 ||
        cp == 0x29 ||
        cp == 0x5B ||
        cp == 0x5D ||
        cp == 0x7B ||
        cp == 0x7D ||
        cp == 0x201C ||
        cp == 0x201D ||
        cp == 0x2018 ||
        cp == 0x2019;
    if (!isCjk && !isAsciiLetter && !isDigit && !isSpace && !isPunctuation) {
      specialCount++;
    }
  }
  final ratio = specialCount / text.length;
  return ratio > 0.4;
}

// ========== 辅助判断方法 ==========

bool _isCjk(int cp) {
  return (cp >= 0x4E00 && cp <= 0x9FFF) ||
      (cp >= 0x3400 && cp <= 0x4DBF) ||
      (cp >= 0x20000 && cp <= 0x2A6DF) ||
      (cp >= 0x2A700 && cp <= 0x2B73F) ||
      (cp >= 0x2B740 && cp <= 0x2B81F) ||
      (cp >= 0x2B820 && cp <= 0x2CEAF) ||
      (cp >= 0xF900 && cp <= 0xFAFF) ||
      (cp >= 0x2F800 && cp <= 0x2FA1F);
}

bool _isAsciiLetter(int cp) {
  return (cp >= 0x41 && cp <= 0x5A) || (cp >= 0x61 && cp <= 0x7A);
}

bool _isDigit(int cp) {
  return cp >= 0x30 && cp <= 0x39;
}

bool _isSpace(int cp) {
  return cp == 0x20 || cp == 0x09 || cp == 0x0A || cp == 0x0D;
}

bool _isPunctuation(int cp) {
  return (cp >= 0x2000 && cp <= 0x206F) ||
      (cp >= 0x3000 && cp <= 0x303F) ||
      (cp >= 0xFF00 && cp <= 0xFFEF) ||
      cp == 0x2E ||
      cp == 0x2C ||
      cp == 0x3B ||
      cp == 0x3A ||
      cp == 0x21 ||
      cp == 0x3F ||
      cp == 0x28 ||
      cp == 0x29 ||
      cp == 0x5B ||
      cp == 0x5D ||
      cp == 0x7B ||
      cp == 0x7D ||
      cp == 0x201C ||
      cp == 0x201D ||
      cp == 0x2018 ||
      cp == 0x2019;
}

// ========== 测试用例数据类 ==========

class _TestCase {
  final String name;
  final String input;
  final String expected;

  _TestCase({required this.name, required this.input, required this.expected});
}