英文单词专业记忆工具

📚 [主题] · 单词学习指南
├── 顶部 sticky 导航（标题 + 词数统计）
├── TOC 分组标签 + 📝 复习组入口
├── 单组显示（CSS :target 机制）
├── 每张卡片含：
│   ├── 编号 + 单词 🔊 + 音标（英/美）+ 📝 复习按钮
│   ├── 📖 释义（中文 + 词性）
│   ├── 🌱 词根词缀
│   └── 💬 场景对话（3 轮 A/B/A）
│       ├── 每行：角色标签 + 英文 + 「中」按钮 + 🔊
│       └── 点击行 → 显示/隐藏中文翻译
└── 复习系统（localStorage 持久化）

# 对于结构化文件，运行提取脚本
python scripts/extract_words.py <input_file> --output ./work

# -*- coding: utf-8 -*-
DIALOGUES = {
    "utensil": [
        ("A", "The new restaurant downtown is beautiful, but the tables felt a bit empty.", "市中心那家新餐厅很漂亮，但桌子感觉有点空。"),
        ("B", "That's because they bring the utensils after you order.", "那是因为他们等你点完单才上 utensils（餐具）。"),
        ("A", "Oh, that explains it. I thought the service was just slow.", "哦，原来如此。我还以为是服务慢呢。"),
    ],
    # ... 每个单词一段
}

{
  "supply_chain": [
    ["Have you reviewed the latest supplier report?", "Yes, the lead time for {} needs attention.", "Let's schedule a call with them tomorrow."],
    ["What's the status of our {} order?", "It's still pending customs clearance.", "Keep me posted. This is a priority shipment."]
  ]
}

python scripts/build_vocab.py words_normalized.csv 
  --output ./output 
  --per-section 20 
  --title "随身带生词列表 · 词汇学习指南" 
  --custom-dialogues custom_dialogues.py

python scripts/build_vocab.py words_normalized.csv 
  --output ./output 
  --per-section 30 
  --title "商务英语360 · 单词学习指南" 
  --custom-scenarios context_scenarios.json 
  --extract-sentences

# -*- coding: utf-8 -*-
CN = {
    "Have you reviewed the latest supplier report?": "你审阅过最新的供应商报告了吗？",
    "Yes, the lead time for board needs attention.": "是的，board 的交货周期需要注意。",
    # ... 全部句子
}

python scripts/build_vocab.py words_normalized.csv 
  --output ./output 
  --per-section 30 
  --title "商务英语360 · 单词学习指南" 
  --custom-scenarios context_scenarios.json 
  --translations cn_translations.py

# 1. 安装依赖（首次）
pip install edge-tts

# 2. 生成对话音频（男声 GuyNeural / 女声 JennyNeural）
python scripts/gen_dialogue_audio.py output/xxx.html --audio-dir output/audio --concurrency 8

# 3. 生成单词音频（男声 GuyNeural，慢速学习）
python scripts/gen_word_audio.py --words-list output/words_list.txt --output-dir output/audio/words --concurrency 8

# 验证音频完整性
echo "对话音频: $(ls output/audio/d_*.mp3 | wc -l) 文件"
echo "单词音频: $(ls output/audio/words/w_*.mp3 | wc -l) 文件"
echo "零字节: $(find output/audio -size 0 | wc -l) 个"
echo "总大小: $(du -sh output/audio | cut -f1)"

output/
├── 商务英语360_单词学习指南.html    # 主文件
└── audio/                           # 音频文件夹
    ├── d_0000.mp3 ... d_XXXX.mp3    # 对话音频
    └── words/
        └── w_XXXXX.mp3              # 单词音频

# -*- coding: utf-8 -*-
DIALOGUES = {
    "word": [
        ("A", "English sentence", "中文翻译（保留英文生词）"),
        ("B", "English sentence", "中文翻译（保留英文生词）"),
        ("A", "English sentence", "中文翻译（保留英文生词）"),
    ],
    # ... 每个单词一段
}

{
  "场景英文名": [
    ["A 说的话（用 {} 占位生词）", "B 说的话", "A 说的话"],
    ["第二套模板的 A 行", "B 行", "A 行"]
  ]
}