断词机制详解 (hyphenateWord)

// 第242-244行
const hyphenateWord = (word: string) => {
  const lower = word.toLowerCase().replace(/[.,;:!?"'""''—–-]/g, "");
  // 移除标点符号后转小写，用于匹配词典和词缀
  
  if (lower.length < 5) return [word];
  // 长度小于5的单词不拆分，避免过度断裂

// 第245-255行
const exc = HYPHEN_EXCEPTIONS[lower as keyof typeof HYPHEN_EXCEPTIONS];
if (exc) {
  const parts: string[] = [];
  let pos = 0;
  // 逐片段累加位置指针
  for (const part of exc) {
    parts.push(word.slice(pos, pos + part.length));
    // 按词典定义的长度切分，保持原词大小写
    pos += part.length;
  }
  if (pos < word.length) 
    parts[parts.length - 1] += word.slice(pos);
    // 处理边界情况：词典未完整覆盖（如末尾有多余字符）
  return parts.filter((p) => p.length > 0);
}

// 示例：relationship 的词典定义
relationship: ["re", "la", "tion", "ship"]
//         re  +  la  +  tion  +  ship
//         2 + 2 + 4 + 4 = 12 ✓

// 第256-260行
for (const prefix of PREFIXES) {
  if (lower.startsWith(prefix) && lower.length - prefix.length >= 3) {
    // 必须匹配前缀，且剩余部分 ≥ 3 个字符
    return [word.slice(0, prefix.length), word.slice(prefix.length)];
    // 前缀保持原样，后缀也保持原样（不断开）
  }
}

// 第261-266行
for (const suffix of SUFFIXES) {
  if (lower.endsWith(suffix) && lower.length - suffix.length >= 3) {
    const cut = word.length - suffix.length;
    return [word.slice(0, cut), word.slice(cut)];
    // 前半部分 + 后缀（后半部分）
  }
}

const PREFIXES = [
  "anti", "auto", "be", "bi", "co", "com", "con", 
  "contra", "counter", "de", "dis", "en", "em", 
  "ex", "extra", "fore", "hyper", "il", "im", "in",
  "inter", "intra", "ir", "macro", "mal", "micro", 
  // ... 共55个
];

const SUFFIXES = [
  "able", "ible", "tion", "sion", "ment", "ness",
  "ous", "ious", "eous", "ful", "less", "ive",
  "ative", "itive", "al", "ial", "ical", "ing",
  // ... 共37个
];

// 第428-434行（renderCanvas 中）
const hyphenated = tokens
  .map((t) => {
    if (/^\s+$/.test(t)) return t;  // 空格保留
    const parts = hyphenateWord(t);
    return parts.length <= 1 ? t : parts.join("­");
    // 拆分后用软连字符 U+00AD 连接
  })
  .join("");

import Hypher from 'hypher';
import english from 'hyphenation.en-us';

const hypher = new Hypher(english);
const parts = hypher.hyphenate('extensively');
// → ['ex', 'ten', 'sive', 'ly']

const hyphenate = (word: string, lang: string) => {
  switch(lang) {
    case 'en': return hyphenateEnglish(word);
    case 'de': return hyphenateGerman(word);  // 德语规则不同
    case 'fr': return hyphenateFrench(word);
    default: return [word];
  }
};