文本处理工具大全：从文本分析到格式转换的一站式解决方案

// 不同语言的阅读速度（词/分钟）
const readingSpeed = {
  chinese: 300,    // 中文：300字/分钟
  english: 200,    // 英文：200词/分钟
};

// 演讲速度（词/分钟）
const speakingSpeed = {
  chinese: 200,    // 中文：200字/分钟
  english: 150,    // 英文：150词/分钟
};

function calculateReadingTime(text) {
  const chineseChars = (text.match(/[\u4e00-\u9fa5]/g) || []).length;
  const englishWords = text
    .replace(/[\u4e00-\u9fa5]/g, ' ')
    .trim()
    .split(/\s+/)
    .filter(w => /[a-zA-Z]/.test(w)).length;
  
  const readingMinutes = Math.ceil(
    (chineseChars / readingSpeed.chinese) + 
    (englishWords / readingSpeed.english)
  );
  
  return readingMinutes;
}

function analyzeWordFrequency(text) {
  const wordFreq = {};
  
  // 处理英文单词
  const englishWords = text
    .toLowerCase()
    .match(/[a-zA-Z]+/g) || [];
  
  englishWords.forEach(word => {
    wordFreq[word] = (wordFreq[word] || 0) + 1;
  });
  
  // 处理中文（二元组 + 单字）
  const chineseText = text.match(/[\u4e00-\u9fa5]+/g)?.join('') || '';
  
  // 二元组统计
  for (let i = 0; i < chineseText.length - 1; i++) {
    const bigram = chineseText.substring(i, i + 2);
    wordFreq[bigram] = (wordFreq[bigram] || 0) + 1;
  }
  
  // 单字统计
  chineseText.split('').forEach(char => {
    wordFreq[char] = (wordFreq[char] || 0) + 1;
  });
  
  // 返回频率最高的词汇
  return Object.entries(wordFreq)
    .sort((a, b) => b[1] - a[1])
    .slice(0, 10);
}

function calculateKeywordDensity(text, keyword) {
  const totalWords = text.split(/\s+/).length;
  const keywordCount = (text.match(new RegExp(keyword, 'gi')) || []).length;
  
  return ((keywordCount / totalWords) * 100).toFixed(2) + '%';
}

const caseConverters = {
  // 驼峰命名：首字母小写，后续单词首字母大写
  camelCase: (text) => text
    .toLowerCase()
    .replace(/[^a-zA-Z0-9]+(.)/g, (_, chr) => chr.toUpperCase())
    .replace(/^[A-Z]/, (c) => c.toLowerCase()),
  
  // 帕斯卡命名：所有单词首字母大写
  pascalCase: (text) => text
    .toLowerCase()
    .replace(/[^a-zA-Z0-9]+(.)/g, (_, chr) => chr.toUpperCase())
    .replace(/^[a-z]/, (c) => c.toUpperCase()),
  
  // 蛇形命名：小写字母，下划线分隔
  snakeCase: (text) => text
    .replace(/([a-z])([A-Z])/g, '$1_$2')
    .replace(/[\s-]+/g, '_')
    .toLowerCase(),
  
  // 短横线命名：小写字母，短横线分隔
  kebabCase: (text) => text
    .replace(/([a-z])([A-Z])/g, '$1-$2')
    .replace(/[\s_]+/g, '-')
    .toLowerCase(),
  
  // 常量命名：大写字母，下划线分隔
  constantCase: (text) => text
    .replace(/([a-z])([A-Z])/g, '$1_$2')
    .replace(/[\s-]+/g, '_')
    .toUpperCase(),
  
  // 标题格式：每个单词首字母大写
  titleCase: (text) => text
    .replace(/\w\S*/g, (txt) =>
      txt.charAt(0).toUpperCase() + txt.substr(1).toLowerCase()
    ),
  
  // 句子格式：句首字母大写
  sentenceCase: (text) => text
    .toLowerCase()
    .replace(/(^\s*\w|[.!?]\s*\w)/g, (c) => c.toUpperCase()),
};

# 一级标题
## 二级标题
### 三级标题
#### 四级标题
##### 五级标题
###### 六级标题

**粗体文本**
*斜体文本*
~~删除线~~
`行内代码`

无序列表：
- 项目一
- 项目二
  - 子项目

有序列表：
1. 第一步
2. 第二步
3. 第三步

[链接文本](https://example.com)
![图片描述](image.png)

```javascript
function hello() {
  console.log('Hello, World!');
}
```

| 列1 | 列2 | 列3 |
|-----|-----|-----|
| A1  | B1  | C1  |
| A2  | B2  | C2  |

> 这是一段引用文本
> 可以跨越多行

import MarkdownIt from 'markdown-it';

const md = new MarkdownIt({
  html: true,        // 允许 HTML 标签
  linkify: true,     // 自动识别链接
  typographer: true, // 智能引号
  breaks: true,      // 换行转 <br>
});

const html = md.render(markdownText);

https://example.com/blog/my-first-blog-post
                        ↑
                    这就是 Slug

function generateSlug(text, options) {
  let slug = text;
  
  // 1. 去除首尾空白
  if (options.trimWhitespace) {
    slug = slug.trim();
  }
  
  // 2. 音译转换（处理特殊字符和中文）
  if (options.transliterate) {
    // 处理带重音的字符
    slug = slug.replace(/[àáâãäå]/g, 'a')
               .replace(/[èéêë]/g, 'e')
               .replace(/[ìíîï]/g, 'i')
               .replace(/[òóôõö]/g, 'o')
               .replace(/[ùúûü]/g, 'u')
               .replace(/[ñ]/g, 'n')
               .replace(/[ç]/g, 'c');
    
    // 处理中文（转拼音）
    if (/[\u4e00-\u9fa5]/.test(slug)) {
      slug = slug.replace(/[\u4e00-\u9fa5]+/g, (match) => {
        return ' ' + pinyin(match, { toneType: 'none' }).join(' ') + ' ';
      });
    }
  }
  
  // 3. 移除数字（可选）
  if (options.removeNumbers) {
    slug = slug.replace(/[0-9]/g, '');
  }
  
  // 4. 移除特殊字符
  slug = slug.replace(/[^\w\s-]/g, '');
  
  // 5. 替换空白为分隔符
  slug = slug.replace(/[\s_]+/g, options.separator);
  
  // 6. 移除连续分隔符
  slug = slug.replace(new RegExp(`${options.separator}+`, 'g'), options.separator);
  
  // 7. 移除首尾分隔符
  slug = slug.replace(new RegExp(`^${options.separator}|${options.separator}$`, 'g'), '');
  
  // 8. 转小写
  if (options.lowercase) {
    slug = slug.toLowerCase();
  }
  
  // 9. 限制长度
  if (options.maxLength > 0 && slug.length > options.maxLength) {
    slug = slug.substring(0, options.maxLength);
    // 在单词边界截断
    const lastSep = slug.lastIndexOf(options.separator);
    if (lastSep > options.maxLength * 0.5) {
      slug = slug.substring(0, lastSep);
    }
  }
  
  return slug;
}

function removeDuplicates(text, options) {
  let lines = text.split('\n');
  
  // 去除空白
  if (options.trimWhitespace) {
    lines = lines.map(line => line.trim());
  }
  
  // 忽略空行
  if (options.ignoreEmptyLines) {
    lines = lines.filter(line => line.length > 0);
  }
  
  // 使用 Set 去重
  const seen = new Set();
  const uniqueLines = [];
  
  for (const line of lines) {
    // 根据选项决定比较键
    const key = options.ignoreCase ? line.toLowerCase() : line;
    
    if (!seen.has(key)) {
      seen.add(key);
      uniqueLines.push(line);
    }
  }
  
  // 排序（可选）
  if (options.sortOutput === 'asc') {
    uniqueLines.sort((a, b) => a.localeCompare(b));
  } else if (options.sortOutput === 'desc') {
    uniqueLines.sort((a, b) => b.localeCompare(a));
  }
  
  return uniqueLines.join('\n');
}

function findDuplicates(text, options) {
  let lines = text.split('\n');
  
  if (options.trimWhitespace) {
    lines = lines.map(line => line.trim());
  }
  
  if (options.ignoreEmptyLines) {
    lines = lines.filter(line => line.length > 0);
  }
  
  // 统计每行出现次数
  const count = {};
  for (const line of lines) {
    const key = options.ignoreCase ? line.toLowerCase() : line;
    count[key] = (count[key] || 0) + 1;
  }
  
  // 筛选出现多次的行
  const duplicates = Object.entries(count)
    .filter(([_, c]) => c > 1)
    .map(([line, c]) => `${line} (${c}x)`);
  
  return duplicates.join('\n');
}

const ones = ['', 'one', 'two', 'three', 'four', 'five', 
              'six', 'seven', 'eight', 'nine'];
const teens = ['ten', 'eleven', 'twelve', 'thirteen', 'fourteen',
               'fifteen', 'sixteen', 'seventeen', 'eighteen', 'nineteen'];
const tens = ['', '', 'twenty', 'thirty', 'forty', 
              'fifty', 'sixty', 'seventy', 'eighty', 'ninety'];
const scales = ['', 'thousand', 'million', 'billion', 'trillion'];

function numberToWords(num) {
  if (num === 0) return 'zero';
  
  const isNegative = num < 0;
  num = Math.abs(num);
  
  let words = [];
  let scaleIndex = 0;
  
  while (num > 0) {
    const chunk = num % 1000;
    
    if (chunk > 0) {
      const chunkWords = convertChunk(chunk);
      if (scales[scaleIndex]) {
        words.unshift(chunkWords + ' ' + scales[scaleIndex]);
      } else {
        words.unshift(chunkWords);
      }
    }
    
    num = Math.floor(num / 1000);
    scaleIndex++;
  }
  
  return (isNegative ? 'minus ' : '') + words.join(' ');
}

function convertChunk(num) {
  let words = [];
  
  if (num >= 100) {
    words.push(ones[Math.floor(num / 100)] + ' hundred');
    num %= 100;
  }
  
  if (num >= 20) {
    words.push(tens[Math.floor(num / 10)]);
    num %= 10;
  }
  
  if (num >= 10) {
    words.push(teens[num - 10]);
  } else if (num > 0) {
    words.push(ones[num]);
  }
  
  return words.join(' ');
}

function numberToCurrency(num, currency = 'USD') {
  const currencyConfig = {
    USD: { main: 'dollar', sub: 'cent' },
    EUR: { main: 'euro', sub: 'cent' },
    GBP: { main: 'pound', sub: 'pence' },
    CNY: { main: 'yuan', sub: 'fen' },
  };
  
  const config = currencyConfig[currency];
  const dollars = Math.floor(num);
  const cents = Math.round((num - dollars) * 100);
  
  let result = '';
  
  if (dollars > 0) {
    result = numberToWords(dollars) + ' ' + 
             config.main + (dollars !== 1 ? 's' : '');
  }
  
  if (cents > 0) {
    if (result) result += ' and ';
    result += numberToWords(cents) + ' ' + 
              config.sub + (cents !== 1 ? 's' : '');
  }
  
  return result || 'zero ' + config.main + 's';
}