From d401f344af13a5b4dfe54f17354ebbfc634a31cf Mon Sep 17 00:00:00 2001 From: ai_member_only Date: Wed, 1 Apr 2026 23:17:01 +0800 Subject: [PATCH] auto-sync: kids-english-script-production 2026-04-01 --- kids-english-script-production/.DS_Store | Bin 0 -> 6148 bytes kids-english-script-production/SKILL.md | 50 +++++ .../assets/expression_map.yaml | 27 +++ .../assets/prompt_config.yaml | 21 ++ .../assets/sci_fi_map.yaml | 14 ++ .../assets/skill.yml | 27 +++ .../assets/stage_config.yaml | 17 ++ .../assets/validation_config.yaml | 88 ++++++++ .../assets/调优指南.md | 53 +++++ .../examples/sample_script.txt | 4 + .../references/l1_word_list.json | 1 + .../scripts/gen_script.py | 212 ++++++++++++++++++ 12 files changed, 514 insertions(+) create mode 100644 kids-english-script-production/.DS_Store create mode 100644 kids-english-script-production/SKILL.md create mode 100644 kids-english-script-production/assets/expression_map.yaml create mode 100644 kids-english-script-production/assets/prompt_config.yaml create mode 100644 kids-english-script-production/assets/sci_fi_map.yaml create mode 100644 kids-english-script-production/assets/skill.yml create mode 100644 kids-english-script-production/assets/stage_config.yaml create mode 100644 kids-english-script-production/assets/validation_config.yaml create mode 100644 kids-english-script-production/assets/调优指南.md create mode 100644 kids-english-script-production/examples/sample_script.txt create mode 100644 kids-english-script-production/references/l1_word_list.json create mode 100644 kids-english-script-production/scripts/gen_script.py diff --git a/kids-english-script-production/.DS_Store b/kids-english-script-production/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..ed0f20e575908cc3bc4cb5f7e0373c9f12bfe0ab GIT binary patch literal 6148 zcmeHK%TB{U3>-rR5nOuYxWB+3tg7}4_yHgV2`SKufW$Gk{x;(WC?)jDf!dLGHeS!J zb`Eh2Ko;-oYhVtbp(|pi!_;(LePSmOnGwbIctgML+wOj|=_c8~2b6n;JM?@W@Ppql z^ufhvY|(N4y*W?A1zs6?q$|Fl9Vh5v=iIX8;uG1Ujg_003Zw$5Kq`<59IpaV37gB~ zl^}1P3Zw!D6wvQOp)1zF!O=b)9IOQ(>TkRm=hjOQiw1}_aByUVCQcS1=4-5岁零基础
S2=5-6岁入门
S3=6-7岁进阶
S4=7-8岁提升 | +| --output | 否 | 目录路径 | 结果输出目录，指定后自动保存所有结果到该目录，不指定则直接打印到控制台 | + +## 错误处理规则 +- 输入路径不存在/无txt文件：直接报错退出，给出明确提示 +- 配置文件加载失败：报错退出，提示检查配置文件格式 +- LLM调用失败：单个剧本生成失败不影响其他批量任务，给出错误提示 +- 参数不合法：直接输出参数说明，提示正确用法 + +## 使用示例 +```bash +# 1. 直接输入文本生成，结果打印到控制台 +openclaw skill run kids-english-script-production --input "角色A: 光有水不行，得先拿上毛巾。角色B: 好的，我现在去拿" --stage S2 + +# 2. 处理单个文件，结果保存到output目录 +openclaw skill run kids-english-script-production --path ./script.txt --stage S3 --output ./result + +# 3. 批量处理目录下所有txt剧本，结果保存到output目录 +openclaw skill run kids-english-script-production --path ./scripts_dir --stage S1 --output ./batch_result +``` diff --git a/kids-english-script-production/assets/expression_map.yaml b/kids-english-script-production/assets/expression_map.yaml new file mode 100644 index 0000000..45c3e89 --- /dev/null +++ b/kids-english-script-production/assets/expression_map.yaml @@ -0,0 +1,27 @@ +# 可自定义的表达映射表，教研老师可直接修改，无需动代码 +# 情绪词映射：中文情绪表达 → 对应地道英文儿童口语表达 +emotion_map: + 天呐: Oh my + 呜呼: Woo-hoo + 太棒了: Awesome + 哇: Wow + 哦不: Oh no + 耶: Yay + 嘿: Hey + 等等: Wait + +# 同义替换表：标准表达 → 更口语化的儿童表达（同义替换，不改变原意） +synonym_replace: + it is so nice: it is beautiful + Do you?: Wanna see? + Let's get in: Here we go + Let's start: Let's go + very good: Great + I like it: I love it + very fast: So fast + very slow: So slow + +# 拆分规则：需要拆成两句的常见长句规则 +split_rules: + - 包含两个动作的句子自动拆分 + - 包含"，"的短句优先拆分为单信息句 diff --git a/kids-english-script-production/assets/prompt_config.yaml b/kids-english-script-production/assets/prompt_config.yaml new file mode 100644 index 0000000..f97dd70 --- /dev/null +++ b/kids-english-script-production/assets/prompt_config.yaml @@ -0,0 +1,21 @@ +# Prompt生成配置，教研老师可自定义调整生成效果，无需改代码 +# 生成温度：越高越灵活，越低越严格遵守规则 +temperature: + S1: 0.2 + S2: 0.3 + S3: 0.4 + S4: 0.5 + +# 自然化开关 +naturalization: + enable_emotion_word: true # 是否启用情绪词映射 + enable_synonym_replace: true # 是否启用同义口语替换 + enable_long_sentence_split: true # 是否启用长句拆分 + enable_exclamation_mark: true # 是否给情绪强烈的句子加感叹号 + allow_repeat_expression: true # 是否允许自然重复（如It is dirty. Very dirty.） + +# 剧本忠实度开关（核心规则，谨慎修改） +script_fidelity: + strictly_no_add: true # 100%禁止新增原剧本没有的内容 + strictly_no_delete: true # 100%禁止删除原剧本已有的内容 + allow_detail_optimization: true # 允许同义细节优化（不改变核心信息） diff --git a/kids-english-script-production/assets/sci_fi_map.yaml b/kids-english-script-production/assets/sci_fi_map.yaml new file mode 100644 index 0000000..8f410a1 --- /dev/null +++ b/kids-english-script-production/assets/sci_fi_map.yaml @@ -0,0 +1,14 @@ +# 科幻词汇降级映射表，可随时更新无需修改代码 +energy core: "a bright red light inside the robot" +system error: "the robot cannot work because something inside is wrong" +malfunction: "the robot stops and will not move" +space station: "a big house in space" +orbit shift: "the ship goes the wrong way in space" +radiation leak: "a bad light that can hurt people" +shield generator: "a big machine that makes us safe" +AI control room: "a smart room that tells the robots what to do" +emergency evacuation: "we all have to leave this place very fast" +life support system: "the part that gives us air and keeps us alive" +gravity failure: "there is no pull, so we all float" +communication signal lost: "we cannot talk to them anymore" +explosion: "a big boom" diff --git a/kids-english-script-production/assets/skill.yml b/kids-english-script-production/assets/skill.yml new file mode 100644 index 0000000..8ceafa9 --- /dev/null +++ b/kids-english-script-production/assets/skill.yml @@ -0,0 +1,27 @@ +name: kids-english-script-production +description: 4-8岁儿童英文台词标准化生产工具，支持纯中/纯英/中英混合输入，自动生成分级合规地道台词 +version: 1.1.0 +author: shark +entry: python3 scripts/gen_script.py +parameters: + - name: input + type: string + description: 直接输入待处理的剧本文本 + required: false + - name: path + type: string + description: 待处理的单个剧本文件路径或包含多个剧本的目录路径 + required: false + - name: stage + type: string + description: 目标难度等级 S1/S2/S3/S4 + required: true + - name: output + type: string + description: 结果输出目录，指定后自动保存结果 + required: false +tags: + - 内容生产 + - 英语课程 + - 台词生成 + - 批量处理 diff --git a/kids-english-script-production/assets/stage_config.yaml b/kids-english-script-production/assets/stage_config.yaml new file mode 100644 index 0000000..c8e4dae --- /dev/null +++ b/kids-english-script-production/assets/stage_config.yaml @@ -0,0 +1,17 @@ +# 各Stage难度配置，可随时调整无需修改代码 +S1: + age: "4-5岁" + lexile: "≤200L" + rules: "词汇90%+Starters核心词，禁止抽象词（fix/before/finish等）；仅简单句（This is/It is/I/We开头），无连词从句，仅用一般现在时；句长4-7词；无复杂结构" +S2: + age: "5-6岁" + lexile: "200L-400L" + rules: "60%Starters+40%Movers词汇，可出现简单情绪词（happy/scared/tired）、简单副词（now/slowly/fast）；可使用连词and/but/so/because，每句最多1个连词；可使用一般过去时、时间标记then/later；句长7-10词" +S3: + age: "6-7岁" + lexile: "400L-600L" + rules: "可出现轻抽象词（problem/idea/plan）、描述词（bright/noisy/broken）；可使用连词when/before/after，可表达两层动作链；可用一般过去时+现在进行时混用；句长10-15词" +S4: + age: "7-8岁" + lexile: "600L-800L" + rules: "全覆盖Flyers词汇，可加入低难度抽象词（decide/safe/dangerous/fix）；可使用连词because/so/if/when/although，可表达动机to do；可使用将来时will；句长15-20词" diff --git a/kids-english-script-production/assets/validation_config.yaml b/kids-english-script-production/assets/validation_config.yaml new file mode 100644 index 0000000..ec49607 --- /dev/null +++ b/kids-english-script-production/assets/validation_config.yaml @@ -0,0 +1,88 @@ +# 英文台词完整校验规则配置 +# 版本：2026-04-01 +--- +## 一、基础通用校验规则（强制执行） +basic_rules: + sentence_spec: + - 默认保留be going to标准表达，无特殊标注（如指定学龄前场景）禁止使用gonna等过度口语化表达 + vocabulary_control: + - 低龄学习场景禁止使用超纲词，动作指令优先选择基础词汇（如用look at替代focus） + redundancy_check: + - 禁止同一句台词连续重复出现2次及以上，此类排版错误直接标注 + confirmed_optimization: + - "Today, we must train!" 统一优化为 "Let's start training!" + +## 二、核心精校5大法则（A1级别内容强制遵循） +core_principles: + simplification: + name: 极简降维法则 + rules: + - 严格执行"一句一意"，复杂嵌套句型拆分为独立简单句，禁止复合从句 + - 时态仅允许使用一般现在时、一般过去时、基础将来时（will/be going to），禁止完成时、虚拟语气 + chunking: + name: 语块优先法则 + rules: + - 上下文/画面信息充足时可省略冗余成分，保留核心语块 + - 允许使用母语儿童常用地道祈使短句（如Game start!/Watch this!/Silly me!），禁止生造表达 + tpr_action: + name: TPR动作强绑定法则 + rules: + - 引导交互/动作的台词以基础动词原形开头（Look/Listen/Hit/Run等） + - 确保台词与画面动作/UI组件完全同步，利用视觉辅助听力解码 + target_focus: + name: 目标大纲无痕植入法则 + rules: + - 核心词汇/句型通过剧情冲突（找不到/受伤/失误等）自然重复，禁止生硬植入 + - 目标句型通过NPC提问引导输出，禁止直接生硬陈述 + emotional_resonance: + name: 情绪夸张法则 + rules: + - 允许使用低认知负荷语气词传递情绪（Phew!/Ouch!/Oops!/Aha!/Waaaaah!等） + - 情绪表达直接使用A1级形容词（sad/happy/angry等），禁止复杂心理描写 + +## 三、AR等级/词汇/难度校验规则 +ar_validation: + enable: true + S1_allow_AR2_ratio: 0.1 # S1允许AR2占比最大10% + S2_allow_AR3_ratio: 0.1 # S2允许AR3占比最大10% + S3_allow_AR4_ratio: 0.15 # S3允许AR4占比最大15% + +vocab_validation: + enable_OOV_remind: true # 是否开启超纲词提醒 + S1_allow_OOV_ratio: 0.05 # S1允许超纲词占比最大5% + S2_allow_OOV_ratio: 0.1 # S2允许超纲词占比最大10% + stop_words: # 超纲词校验时忽略的词 + - hey + - look + - oh + - wow + - wait + - oh no + - yay + - i + - you + - he + - she + - it + - we + - they + - am + - is + - are + - was + - were + - a + - an + - the + - and + - but + - so + - because + +difficulty_validation: + enable: true + allow_lexile_deviation: 50 # 允许蓝思值偏差±50L + +## 四、校验输出标准 +output_standard: + - 所有问题标注需包含：上下文引用+问题类型说明+具体优化方案，确保可直接落地修改 diff --git a/kids-english-script-production/assets/调优指南.md b/kids-english-script-production/assets/调优指南.md new file mode 100644 index 0000000..9c8ea3c --- /dev/null +++ b/kids-english-script-production/assets/调优指南.md @@ -0,0 +1,53 @@ +# 英文台词生产技能调优指南 +## 📌 核心原则 +**所有调优无需修改代码/核心Prompt，仅需修改`assets/`目录下的yaml配置文件，改完立即生效**，核心生成策略完全不变，避免人为改动导致规则混乱。 + +--- +## 📁 可修改配置文件说明 +| 文件名 | 作用 | 修改场景 | +| ---- | ---- | ---- | +| `assets/expression_map.yaml` | 表达映射配置 | 需要调整情绪词、口语同义替换、拆分规则时修改 | +| `assets/prompt_config.yaml` | 生成效果配置 | 需要调整生成灵活度、自然化开关、剧本忠实度时修改 | +| `assets/validation_config.yaml` | 校验规则配置 | 需要调整校验严格程度、超纲词阈值、AR等级允许比例时修改 | +| `assets/stage_config.yaml` | 难度等级配置 | 需要调整各Stage的词汇、句法、句长要求时修改 | +| `assets/sci_fi_map.yaml` | 科幻词映射配置 | 需要新增/修改科幻词汇降级规则时修改 | +| `references/l1_word_list.json` | L1核心词表 | 需要更新L1词汇白名单时修改 | + +--- +## 🔧 常见调优场景示例 +### 1. 想把"天呐"的默认表达从"Oh my"改成"Wow" +修改`assets/expression_map.yaml`里的`emotion_map`： +```yaml +emotion_map: + 天呐: Wow # 原来的Oh my改成Wow即可 +``` +### 2. 想关闭长句拆分，让句子更连贯 +修改`assets/prompt_config.yaml`里的`naturalization`： +```yaml +naturalization: + enable_long_sentence_split: false # 把true改成false +``` +### 3. 想提高S1阶段允许的超纲词比例到10% +修改`assets/validation_config.yaml`里的`vocab_validation`： +```yaml +vocab_validation: + S1_allow_OOV_ratio: 0.1 # 从0.05改成0.1 +``` +### 4. 想让生成的内容更灵活，不那么死板 +修改`assets/prompt_config.yaml`里的`temperature`： +```yaml +temperature: + S2: 0.4 # 从0.3改成0.4，数值越高越灵活，最高不要超过0.7 +``` +### 5. 想新增一个科幻词的降级规则 +修改`assets/sci_fi_map.yaml`，在末尾加一行： +```yaml +new_sci_word: "儿童易懂的表达" +``` + +--- +## ⚠️ 注意事项 +1. 所有yaml文件必须严格遵守yaml格式，缩进用2个空格，不要用tab，否则会加载失败 +2. 核心规则（禁止新增/删减原剧本内容）建议不要修改，避免输出不符合要求 +3. 修改配置后可以先拿样例剧本测试效果，没问题再批量使用 +4. 配置改乱了可以直接用备份的默认配置覆盖，恢复出厂设置 diff --git a/kids-english-script-production/examples/sample_script.txt b/kids-english-script-production/examples/sample_script.txt new file mode 100644 index 0000000..cf20390 --- /dev/null +++ b/kids-english-script-production/examples/sample_script.txt @@ -0,0 +1,4 @@ +用户: 光有水不行，得先拿上毛巾。 +Ben: 好的，我现在去院子里拿毛巾，顺便把水桶也拿过来。 +用户: 太棒了，我们快点把飞船擦干净，不然天黑就完不成了！ +Ben: 没问题，飞船的能量 core 出了点小问题，我们擦完再一起修。 diff --git a/kids-english-script-production/references/l1_word_list.json b/kids-english-script-production/references/l1_word_list.json new file mode 100644 index 0000000..0a35410 --- /dev/null +++ b/kids-english-script-production/references/l1_word_list.json @@ -0,0 +1 @@ +{"update_time": "2026-03-26", "total_count": 980, "words": [{"word": "red", "pos": "adj", "meaning": "红色的", "level": "LV1（上）", "unit": "S0-U0-L1", "difficulty": 1, "enabled": true}, {"word": "hat", "pos": "n", "meaning": "帽子", "level": "LV1（上）", "unit": "S0-U0-L1", "difficulty": 1, "enabled": true}, {"word": "blue", "pos": "adj", "meaning": "蓝的", "level": "LV1（上）", "unit": "S0-U0-L1", "difficulty": 1, "enabled": true}, {"word": "bag", "pos": "n", "meaning": "袋，包", "level": "LV1（上）", "unit": "S0-U0-L1", "difficulty": 1, "enabled": true}, {"word": "orange", "pos": "adj", "meaning": "橙色的", "level": "LV1（上）", "unit": "S0-U0-L3", "difficulty": 1, "enabled": true}, {"word": "green", "pos": "adj", "meaning": "绿色的", "level": "LV1（上）", "unit": "S0-U0-L2", "difficulty": 1, "enabled": true}, {"word": "dress", "pos": "n", "meaning": "连衣裙", "level": "LV1（上）", "unit": "S0-U0-L2", "difficulty": 1, "enabled": true}, {"word": "there", "pos": "adv", "meaning": "那里", "level": "LV1（上）", "unit": "S0-U0-L3", "difficulty": 1, "enabled": true}, {"word": "put", "pos": "v", "meaning": "放", "level": "LV1（上）", "unit": "S0-U0-L3", "difficulty": 1, "enabled": true}, {"word": "purple", "pos": "adj", "meaning": "紫色的", "level": "LV1（上）", "unit": "S0-U0-L5", "difficulty": 1, "enabled": true}, {"word": "give", "pos": "v", "meaning": "给", "level": "LV1（上）", "unit": "S0-U0-L3", "difficulty": 1, "enabled": true}, {"word": "water", "pos": "n", "meaning": "水", "level": "LV1（上）", "unit": "S0-U0-L4", "difficulty": 1, "enabled": true}, {"word": "here", "pos": "adv", "meaning": "在这里", "level": "LV1（上）", "unit": "S0-U0-L4", "difficulty": 1, "enabled": true}, {"word": "dirty", "pos": "adj", "meaning": "肮脏的", "level": "LV1（上）", "unit": "S0-U0-L4", "difficulty": 1, "enabled": true}, {"word": "clean", "pos": "v", "meaning": "清洁", "level": "LV1（上）", "unit": "S0-U0-L4", "difficulty": 1, "enabled": true}, {"word": "pink", "pos": "adj", "meaning": "粉红色的", "level": "LV1（上）", "unit": "S0-U0-L2", "difficulty": 1, "enabled": true}, {"word": "get", "pos": "v", "meaning": "收到", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "wall", "pos": "n", "meaning": "墙", "level": "LV1（上）", "unit": "S1-U1-L1", "difficulty": 1, "enabled": true}, {"word": "table", "pos": "n", "meaning": "桌子", "level": "LV1（上）", "unit": "S1-U1-L1", "difficulty": 1, "enabled": true}, {"word": "floor", "pos": "n", "meaning": "地板", "level": "LV1（上）", "unit": "S1-U1-L1", "difficulty": 1, "enabled": true}, {"word": "hand", "pos": "n", "meaning": "手", "level": "LV1（上）", "unit": "S1-U1-L2", "difficulty": 1, "enabled": true}, {"word": "foot", "pos": "n", "meaning": "脚", "level": "LV1（上）", "unit": "S1-U1-L2", "difficulty": 1, "enabled": true}, {"word": "black", "pos": "adj", "meaning": "黑的", "level": "LV1（上）", "unit": "S1-U1-L2", "difficulty": 1, "enabled": true}, {"word": "tomato", "pos": "n", "meaning": "西红柿", "level": "LV1（上）", "unit": "S1-U1-L3", "difficulty": 1, "enabled": true}, {"word": "fish", "pos": "n", "meaning": "鱼", "level": "LV1（上）", "unit": "S1-U1-L3", "difficulty": 1, "enabled": true}, {"word": "chicken", "pos": "n", "meaning": "鸡肉", "level": "LV1（上）", "unit": "S1-U1-L3", "difficulty": 1, "enabled": true}, {"word": "nose", "pos": "n", "meaning": "鼻子", "level": "LV1（上）", "unit": "S1-U1-L4", "difficulty": 1, "enabled": true}, {"word": "eye", "pos": "n", "meaning": "眼睛", "level": "LV1（上）", "unit": "S1-U1-L4", "difficulty": 1, "enabled": true}, {"word": "brown", "pos": "adj", "meaning": "棕色的", "level": "LV1（上）", "unit": "S1-U1-L4", "difficulty": 1, "enabled": true}, {"word": "yellow", "pos": "adj", "meaning": "黄色的", "level": "LV1（上）", "unit": "S1-U1-L5", "difficulty": 1, "enabled": true}, {"word": "white", "pos": "adj", "meaning": "白色的", "level": "LV1（上）", "unit": "S1-U1-L5", "difficulty": 1, "enabled": true}, {"word": "go", "pos": "v", "meaning": "去，走", "level": "LV1（上）", "unit": "S1-U2-L1", "difficulty": 1, "enabled": true}, {"word": "dog", "pos": "n", "meaning": "狗", "level": "LV1（上）", "unit": "S1-U2-L1", "difficulty": 1, "enabled": true}, {"word": "come", "pos": "v", "meaning": "来", "level": "LV1（上）", "unit": "S1-U2-L1", "difficulty": 1, "enabled": true}, {"word": "cat", "pos": "n", "meaning": "猫", "level": "LV1（上）", "unit": "S1-U2-L1", "difficulty": 1, "enabled": true}, {"word": "pie", "pos": "n", "meaning": "馅饼", "level": "LV1（上）", "unit": "S1-U2-L2", "difficulty": 1, "enabled": true}, {"word": "can", "pos": "v", "meaning": "能，会", "level": "LV1（上）", "unit": "S1-U2-L4", "difficulty": 1, "enabled": true}, {"word": "open", "pos": "v", "meaning": "打开", "level": "LV1（上）", "unit": "S1-U2-L5", "difficulty": 1, "enabled": true}, {"word": "happy", "pos": "adj", "meaning": "快乐的", "level": "LV1（上）", "unit": "S1-U2-L5", "difficulty": 1, "enabled": true}, {"word": "see", "pos": "v", "meaning": "看见", "level": "LV1（上）", "unit": "S1-U3-L1", "difficulty": 1, "enabled": true}, {"word": "1", "pos": "num", "meaning": "1", "level": "LV1（上）", "unit": "S1-U3-L1", "difficulty": 1, "enabled": true}, {"word": "paper", "pos": "n", "meaning": "纸", "level": "LV1（上）", "unit": "S1-U3-L2", "difficulty": 1, "enabled": true}, {"word": "book", "pos": "n", "meaning": "书", "level": "LV1（上）", "unit": "S1-U3-L2", "difficulty": 1, "enabled": true}, {"word": "3", "pos": "num", "meaning": "3", "level": "LV1（上）", "unit": "S1-U3-L2", "difficulty": 1, "enabled": true}, {"word": "2", "pos": "num", "meaning": "2", "level": "LV1（上）", "unit": "S1-U3-L2", "difficulty": 1, "enabled": true}, {"word": "pen", "pos": "n", "meaning": "钢笔", "level": "LV1（上）", "unit": "S1-U3-L3", "difficulty": 1, "enabled": true}, {"word": "box", "pos": "n", "meaning": "盒子", "level": "LV1（上）", "unit": "S1-U3-L3", "difficulty": 1, "enabled": true}, {"word": "4", "pos": "num", "meaning": "4", "level": "LV1（上）", "unit": "S1-U3-L3", "difficulty": 1, "enabled": true}, {"word": "6", "pos": "num", "meaning": "6", "level": "LV1（上）", "unit": "S1-U3-L4", "difficulty": 1, "enabled": true}, {"word": "5", "pos": "num", "meaning": "5", "level": "LV1（上）", "unit": "S1-U3-L4", "difficulty": 1, "enabled": true}, {"word": "sing", "pos": "v", "meaning": "唱", "level": "LV1（上）", "unit": "S1-U4-L1", "difficulty": 1, "enabled": true}, {"word": "eat", "pos": "v", "meaning": "吃", "level": "LV1（上）", "unit": "S1-U4-L2", "difficulty": 1, "enabled": true}, {"word": "7", "pos": "num", "meaning": "7", "level": "LV1（上）", "unit": "S1-U4-L2", "difficulty": 1, "enabled": true}, {"word": "rug", "pos": "n", "meaning": "小地毯", "level": "LV1（上）", "unit": "S1-U4-L3", "difficulty": 1, "enabled": true}, {"word": "door", "pos": "n", "meaning": " 门", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "bed", "pos": "n", "meaning": "床", "level": "LV1（上）", "unit": "S1-U4-L3", "difficulty": 1, "enabled": true}, {"word": "9", "pos": "num", "meaning": "9", "level": "LV1（上）", "unit": "S1-U4-L4", "difficulty": 1, "enabled": true}, {"word": "8", "pos": "num", "meaning": "8", "level": "LV1（上）", "unit": "S1-U4-L4", "difficulty": 1, "enabled": true}, {"word": "10", "pos": "num", "meaning": "10", "level": "LV1（上）", "unit": "S1-U4-L5", "difficulty": 1, "enabled": true}, {"word": "zoo", "pos": "n", "meaning": "动物园", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "zebra", "pos": "n", "meaning": "斑马", "level": "LV1（上）", "unit": "S1-U7-L2", "difficulty": 1, "enabled": true}, {"word": "young", "pos": "adj", "meaning": "年轻的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "year", "pos": "n", "meaning": "年", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "write", "pos": "v", "meaning": "写", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "woman", "pos": "n", "meaning": "女人", "level": "LV1（上）", "unit": "S1-U5-L1", "difficulty": 1, "enabled": true}, {"word": "window", "pos": "n", "meaning": "窗户", "level": "LV1（上）", "unit": "S1-U12-L4", "difficulty": 1, "enabled": true}, {"word": "warm", "pos": "adj", "meaning": "温暖的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "want", "pos": "v", "meaning": "想要", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "walk", "pos": "v", "meaning": "走", "level": "LV1（上）", "unit": "S1-U7-L2", "difficulty": 1, "enabled": true}, {"word": "very", "pos": "adv", "meaning": "非常", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "under", "pos": "prep", "meaning": "在...下面", "level": "LV1（上）", "unit": "S2-U14-L5", "difficulty": 1, "enabled": true}, {"word": "try", "pos": "n", "meaning": "尝试", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "try", "pos": "v", "meaning": "尝试", "level": "LV1（上）", "unit": "S1-U12-L5", "difficulty": 1, "enabled": true}, {"word": "tree", "pos": "n", "meaning": "树", "level": "LV1（上）", "unit": "S1-U7-L1", "difficulty": 1, "enabled": true}, {"word": "train", "pos": "n", "meaning": "火车", "level": "LV1（上）", "unit": "S1-U8-L1", "difficulty": 1, "enabled": true}, {"word": "too", "pos": "adv", "meaning": "也", "level": "LV1（上）", "unit": "S1-U12-L2", "difficulty": 1, "enabled": true}, {"word": "tomorrow", "pos": "adv", "meaning": "明天", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "tomorrow", "pos": "n", "meaning": "明天", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "today", "pos": "adv", "meaning": "今天", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "today", "pos": "n", "meaning": "今天", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "tiger", "pos": "n", "meaning": "老虎", "level": "LV1（上）", "unit": "S1-U5-L3", "difficulty": 1, "enabled": true}, {"word": "those", "pos": "det", "meaning": "那些", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "those", "pos": "pron", "meaning": "那些", "level": "LV1（上）", "unit": "S1-U12-L1", "difficulty": 1, "enabled": true}, {"word": "this", "pos": "det", "meaning": "这个", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "this", "pos": "pron", "meaning": "这个", "level": "LV1（上）", "unit": "S1-U12-L1", "difficulty": 1, "enabled": true}, {"word": "these", "pos": "det", "meaning": "这些", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "these", "pos": "pron", "meaning": "这些", "level": "LV1（上）", "unit": "S1-U12-L1", "difficulty": 1, "enabled": true}, {"word": "that", "pos": "det", "meaning": "那个", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "that", "pos": "pron", "meaning": "那个", "level": "LV1（上）", "unit": "S1-U12-L1", "difficulty": 1, "enabled": true}, {"word": "tell", "pos": "v", "meaning": "告诉", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "teacher", "pos": "n", "meaning": "老师", "level": "LV1（上）", "unit": "S2-U14-L2", "difficulty": 1, "enabled": true}, {"word": "talk", "pos": "v", "meaning": "说话", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "swim", "pos": "v", "meaning": "游泳", "level": "LV1（上）", "unit": "S1-U11-L5", "difficulty": 1, "enabled": true}, {"word": "sun", "pos": "n", "meaning": "太阳", "level": "LV1（上）", "unit": "S1-U8-L2", "difficulty": 1, "enabled": true}, {"word": "study", "pos": "v", "meaning": "学习", "level": "LV1（上）", "unit": "S2-U14-L1", "difficulty": 1, "enabled": true}, {"word": "student", "pos": "n", "meaning": "学生", "level": "LV1（上）", "unit": "S2-U14-L1", "difficulty": 1, "enabled": true}, {"word": "speak", "pos": "v", "meaning": "说", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "some", "pos": "det", "meaning": "一些", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "sofa", "pos": "n", "meaning": "沙发", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "sock", "pos": "n", "meaning": "袜子", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "small", "pos": "adj", "meaning": "小的", "level": "LV1（上）", "unit": "S1-U9-L1", "difficulty": 1, "enabled": true}, {"word": "sleep", "pos": "v", "meaning": "睡觉", "level": "LV1（上）", "unit": "S1-U7-L4", "difficulty": 1, "enabled": true}, {"word": "skirt", "pos": "n", "meaning": "裙子", "level": "LV1（上）", "unit": "S1-U9-L4", "difficulty": 1, "enabled": true}, {"word": "sit", "pos": "v", "meaning": "坐下", "level": "LV1（上）", "unit": "S1-U8-L1", "difficulty": 1, "enabled": true}, {"word": "sister", "pos": "n", "meaning": "姐姐、妹妹", "level": "LV1（上）", "unit": "S1-U8-L1", "difficulty": 1, "enabled": true}, {"word": "short", "pos": "adj", "meaning": "短的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "shoe", "pos": "n", "meaning": "鞋", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "shirt", "pos": "n", "meaning": "衬衫", "level": "LV1（上）", "unit": "S1-U9-L1", "difficulty": 1, "enabled": true}, {"word": "ship", "pos": "n", "meaning": "船", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "sheep", "pos": "n", "meaning": "绵羊", "level": "LV1（上）", "unit": "S1-U5-L3", "difficulty": 1, "enabled": true}, {"word": "school", "pos": "n", "meaning": "学校", "level": "LV1（上）", "unit": "S2-U14-L1", "difficulty": 1, "enabled": true}, {"word": "say", "pos": "v", "meaning": "说", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "sad", "pos": "adj", "meaning": "悲伤的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "run", "pos": "v", "meaning": "跑", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "ruler", "pos": "n", "meaning": "尺子", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "room", "pos": "n", "meaning": "房间", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "rice", "pos": "n", "meaning": "米饭", "level": "LV1（上）", "unit": "S1-U6-L4", "difficulty": 1, "enabled": true}, {"word": "read", "pos": "v", "meaning": "阅读", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "radio", "pos": "n", "meaning": "收音机", "level": "LV1（上）", "unit": "S1-U9-L2", "difficulty": 1, "enabled": true}, {"word": "potato", "pos": "n", "meaning": "土豆", "level": "LV1（上）", "unit": "S1-U7-L3", "difficulty": 1, "enabled": true}, {"word": "play", "pos": "v", "meaning": "玩", "level": "LV1（上）", "unit": "S2-U14-L1", "difficulty": 1, "enabled": true}, {"word": "plane", "pos": "n", "meaning": "飞机", "level": "LV1（上）", "unit": "S1-U8-L3", "difficulty": 1, "enabled": true}, {"word": "pig", "pos": "n", "meaning": "猪", "level": "LV1（上）", "unit": "S1-U7-L4", "difficulty": 1, "enabled": true}, {"word": "phone", "pos": "n", "meaning": "电话", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "phone", "pos": "v", "meaning": "给…...打电话", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "people", "pos": "n", "meaning": "人", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "pencil", "pos": "n", "meaning": "铅笔", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "pea", "pos": "n", "meaning": "豌豆", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "PE", "pos": "n", "meaning": "体育", "level": "LV1（上）", "unit": "S1-U10-L4", "difficulty": 1, "enabled": true}, {"word": "paper", "pos": "adj", "meaning": "纸质的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "paint", "pos": "n", "meaning": "绘画颜料", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "paint", "pos": "v", "meaning": "（用颜料）绘画", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "orange", "pos": "n", "meaning": "橙子", "level": "LV1（上）", "unit": "S1-U10-L3", "difficulty": 1, "enabled": true}, {"word": "open", "pos": "adj", "meaning": "开着的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "one", "pos": "det", "meaning": "一个", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "one", "pos": "pron", "meaning": "一个人(或物)", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "old", "pos": "adj", "meaning": "年老的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "now", "pos": "adv", "meaning": "现在", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "night", "pos": "n", "meaning": "夜晚", "level": "LV1（上）", "unit": "S1-U12-L5", "difficulty": 1, "enabled": true}, {"word": "nice", "pos": "adj", "meaning": "好的", "level": "LV1（上）", "unit": "S1-U6-L3", "difficulty": 1, "enabled": true}, {"word": "new", "pos": "adj", "meaning": "新的", "level": "LV1（上）", "unit": "S1-U9-L2", "difficulty": 1, "enabled": true}, {"word": "mum", "pos": "n", "meaning": "妈妈", "level": "LV1（上）", "unit": "S1-U8-L4", "difficulty": 1, "enabled": true}, {"word": "mouth", "pos": "n", "meaning": "嘴巴", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "mother", "pos": "n", "meaning": "母亲", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "morning", "pos": "n", "meaning": "早上", "level": "LV1（上）", "unit": "S1-U12-L5", "difficulty": 1, "enabled": true}, {"word": "month", "pos": "n", "meaning": "月", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "monkey", "pos": "n", "meaning": "猴子", "level": "LV1（上）", "unit": "S1-U7-L1", "difficulty": 1, "enabled": true}, {"word": "minute", "pos": "n", "meaning": "分钟", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "mine", "pos": "pron", "meaning": "我的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "milk", "pos": "n", "meaning": "牛奶", "level": "LV1（上）", "unit": "S1-U5-L2", "difficulty": 1, "enabled": true}, {"word": "men", "pos": "n", "meaning": "男人（man 的复数）", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "meat", "pos": "n", "meaning": "肉类", "level": "LV1（上）", "unit": "S1-U10-L3", "difficulty": 1, "enabled": true}, {"word": "me", "pos": "pron", "meaning": "我", "level": "LV1（上）", "unit": "S1-U12-L2", "difficulty": 1, "enabled": true}, {"word": "mat", "pos": "n", "meaning": "地垫", "level": "LV1（上）", "unit": "S2-U14-L4", "difficulty": 1, "enabled": true}, {"word": "many", "pos": "det", "meaning": "许多", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "man", "pos": "n", "meaning": "男人", "level": "LV1（上）", "unit": "S1-U5-L1", "difficulty": 1, "enabled": true}, {"word": "make", "pos": "v", "meaning": "制造", "level": "LV1（上）", "unit": "S1-U6-L3", "difficulty": 1, "enabled": true}, {"word": "love", "pos": "v", "meaning": "爱", "level": "LV1（上）", "unit": "S1-U12-L2", "difficulty": 1, "enabled": true}, {"word": "lots of", "pos": "det", "meaning": "大量的", "level": "LV1（上）", "unit": "", "difficulty": 1, "enabled": true}, {"word": "long", "pos": "adj", "meaning": "长的", "level": "LV1（上）", "unit": "S1-U7-L5 ", "difficulty": 1, "enabled \ No newline at end of file diff --git a/kids-english-script-production/scripts/gen_script.py b/kids-english-script-production/scripts/gen_script.py new file mode 100644 index 0000000..1543aa8 --- /dev/null +++ b/kids-english-script-production/scripts/gen_script.py @@ -0,0 +1,212 @@ +#!/usr/bin/env python3 +import argparse +import sys +import os +import yaml +from openai import OpenAI +from pathlib import Path + +# 加载配置 +BASE_DIR = Path(__file__).parent.parent +ASSETS_DIR = BASE_DIR / "assets" + +# 加载外部配置文件（所有可调优参数全部在assets目录下的yaml文件，无需改代码） +try: + # 基础配置 + with open(ASSETS_DIR / "sci_fi_map.yaml", "r", encoding="utf-8") as f: + SCI_FI_WORD_MAP = yaml.safe_load(f) + with open(ASSETS_DIR / "stage_config.yaml", "r", encoding="utf-8") as f: + STAGE_CONFIG = yaml.safe_load(f) + # 调优配置 + with open(ASSETS_DIR / "expression_map.yaml", "r", encoding="utf-8") as f: + EXPRESSION_MAP = yaml.safe_load(f) + with open(ASSETS_DIR / "prompt_config.yaml", "r", encoding="utf-8") as f: + PROMPT_CONFIG = yaml.safe_load(f) + with open(ASSETS_DIR / "validation_config.yaml", "r", encoding="utf-8") as f: + VALIDATION_CONFIG = yaml.safe_load(f) + # 词表配置 + with open(BASE_DIR / "references" / "l1_word_list.json", "r", encoding="utf-8") as f: + L1_WORD_LIST = set([word.lower() for word in yaml.safe_load(f)]) +except Exception as e: + print(f"❌ 配置文件加载失败，请检查yaml格式是否正确: {str(e)}") + sys.exit(1) + +# 初始化LLM客户端，配置从环境变量读取 +try: + client = OpenAI( + api_key=os.getenv("OPENAI_API_KEY", "your-api-key"), + base_url=os.getenv("OPENAI_BASE_URL", "https://ark.cn-beijing.volces.com/api/v3") + ) + MODEL = os.getenv("OPENAI_MODEL", "volcengine/doubao-seed-2-0-pro-260215") +except Exception as e: + print(f"❌ LLM客户端初始化失败: {str(e)}") + sys.exit(1) + +def load_input(input_path): + """加载输入内容，支持单个文件或目录批量加载""" + input_path = Path(input_path) + if not input_path.exists(): + print(f"❌ 输入路径不存在: {input_path}") + sys.exit(1) + + if input_path.is_file(): + with open(input_path, "r", encoding="utf-8") as f: + return [(input_path.name, f.read())] + elif input_path.is_dir(): + # 批量加载目录下所有txt文件 + script_files = list(input_path.glob("*.txt")) + if not script_files: + print(f"❌ 目录下没有找到txt格式的剧本文件: {input_path}") + sys.exit(1) + results = [] + for f in script_files: + with open(f, "r", encoding="utf-8") as fp: + results.append((f.name, fp.read())) + return results + else: + print(f"❌ 不支持的输入类型: {input_path}") + sys.exit(1) + +def get_prompt(input_text, stage): + """生成Prompt，所有可调规则从配置文件读取，无需改代码""" + sci_fi_map_str = "\n".join([f"{k} → {v}" for k, v in SCI_FI_WORD_MAP.items()]) + # 动态加载配置规则 + emotion_map_rule = "优先使用以下映射匹配情绪词：" + "、".join([f"{k}→{v}" for k,v in EXPRESSION_MAP['emotion_map'].items()]) if PROMPT_CONFIG['naturalization']['enable_emotion_word'] else "不使用自定义情绪词映射" + synonym_replace_rule = "可使用以下同义口语替换（不改变原意）：" + "、".join([f"{k}→{v}" for k,v in EXPRESSION_MAP['synonym_replace'].items()]) if PROMPT_CONFIG['naturalization']['enable_synonym_replace'] else "不使用同义替换" + split_rule = "包含2个及以上信息的句子拆成单信息短句" if PROMPT_CONFIG['naturalization']['enable_long_sentence_split'] else "不拆分长句" + repeat_rule = "允许自然重复（比如It is dirty. Very dirty.）" if PROMPT_CONFIG['naturalization']['allow_repeat_expression'] else "不允许重复表达" + exclamation_rule = "情绪强烈的句子可用感叹号" if PROMPT_CONFIG['naturalization']['enable_exclamation_mark'] else "统一使用句号" + fidelity_rule = "100%忠于原剧本内容：禁止新增任何原剧本没有的信息、禁止删除任何原剧本已有的信息" if PROMPT_CONFIG['script_fidelity']['strictly_no_add'] and PROMPT_CONFIG['script_fidelity']['strictly_no_delete'] else "允许适当调整细节" + + return f""" +你是专为4-8岁儿童打造的英文台词生产专家，严格遵守以下所有规则生成内容，绝对不允许违反： +### 剧本忠实度规则（最高优先级，绝对不能违反） +{fidelity_rule} + +### 第一步：输入归一 +当前输入是：{input_text} +不管输入是纯中文/纯英文/中英混合，你首先统一转成标准中文「角色: 台词」格式，完整保留所有剧情、动作、角色关系、道具、事件触发点信息，不能丢失任何核心内容。 + +### 第二步：中文AR预处理 +严格遵守4个保留机制（绝对不能改）： +1. 保留完整事件动词链 +2. 保留所有事件触发点 +3. 保留完整道具逻辑链 +4. 保留原有角色关系 +按以下7条规则拆成单信息短句，1句仅表达1个信息，不改变剧情： +1. 复杂句拆成短句 +2. 因果拆分，保留事实不保留连接词 +3. 目的拆分，不删目的信息 +4. 多步动作拆成单动作句 +5. 条件+行为全拆分，去掉假设逻辑 +6. 情绪与事实拆分，不修改情绪 +7. 去复杂推理，只留可见事实 + +### 第三步：分级英文生成 +目标Stage：{stage} +对应要求：{STAGE_CONFIG[stage]["rules"]} +蓝思值要求：{STAGE_CONFIG[stage]["lexile"]} + +自然化要求（**严格遵守剧本忠实度规则，禁止新增/删减任何原剧本没有的内容**）： +1. 情绪词映射规则：{emotion_map_rule} +2. 同义替换规则：{synonym_replace_rule} +3. 长句拆分规则：{split_rule} +4. 重复表达规则：{repeat_rule} +5. 标点规则：{exclamation_rule} +6. 绝对禁止成人化连接词（actually/in fact/however等） +7. 完全符合母语小朋友说话习惯，绝对不能有翻译腔 +8. 科幻词汇自动按以下映射替换： +{sci_fi_map_str} + +### 第四步：自动校验 +生成后自行校验以下4项： +1. AR等级合规：S1禁止AR3/AR4，S2禁止AR4 +2. 难度合规：词汇/句法/句长/蓝思值完全匹配对应Stage要求，无超纲 +3. 自然度合规：无翻译腔，符合4-8岁儿童母语表达习惯 +4. 内容合规：无敏感内容，无中式英语 + +### 输出格式（严格按照格式输出，不要其他内容） +【Stage {stage} 英文台词（适配{STAGE_CONFIG[stage]["age"]}）】 +角色A: 台词内容 +角色B: 台词内容 +... +【蓝思值】：[估算值]L +【校验结果】：通过/待优化 +【优化建议】：无/具体建议 +""" + +def generate_single_script(input_text, stage): + """生成单个剧本的台词""" + try: + prompt = get_prompt(input_text, stage) + response = client.chat.completions.create( + model=MODEL, + messages=[{"role": "user", "content": prompt}], + temperature=0.3, + max_tokens=2000, + timeout=30 + ) + result = response.choices[0].message.content + # 增加超纲词校验 + oov_words = check_out_of_vocab(result, stage) + if oov_words and stage in ["S1", "S2"]: + result += f"\n【超纲词提醒】：{', '.join(oov_words)}（请确认是否需要替换）" + return result + except Exception as e: + return f"❌ 生成失败: {str(e)}" + +def check_out_of_vocab(script_content, stage): + """检查超纲词汇，规则从配置文件读取""" + if not VALIDATION_CONFIG['vocab_validation']['enable_OOV_remind'] or stage not in ["S1", "S2"]: + return [] + # 提取所有英文单词 + import re + words = re.findall(r"[a-zA-Z']+", script_content) + words = [word.lower().strip("'") for word in words] + # 过滤配置里定义的停用词 + stop_words = set(VALIDATION_CONFIG['vocab_validation']['stop_words']) + words = [word for word in words if word not in stop_words and len(word) > 1] + # 找超纲词 + out_of_vocab = list(set([word for word in words if word not in L1_WORD_LIST])) + return out_of_vocab + +def save_result(output_dir, filename, content): + """保存结果到文件""" + output_dir = Path(output_dir) + output_dir.mkdir(parents=True, exist_ok=True) + output_file = output_dir / f"result_{filename}" + with open(output_file, "w", encoding="utf-8") as f: + f.write(content) + return output_file + +def main(): + parser = argparse.ArgumentParser(description="4-8岁儿童英文台词标准化生产工具") + group = parser.add_mutually_exclusive_group(required=True) + group.add_argument("--input", type=str, help="直接输入待处理的剧本文本") + group.add_argument("--path", type=str, help="待处理的单个剧本文件路径或包含多个剧本的目录路径") + parser.add_argument("--stage", type=str, choices=["S1", "S2", "S3", "S4"], required=True, help="目标难度等级 S1/S2/S3/S4") + parser.add_argument("--output", type=str, help="结果输出目录，不指定则直接打印到控制台") + args = parser.parse_args() + + # 处理输入 + if args.input: + input_list = [("direct_input", args.input)] + else: + input_list = load_input(args.path) + + # 批量生成 + results = [] + for filename, text in input_list: + print(f"\n🚀 正在处理: {filename}") + result = generate_single_script(text, args.stage) + results.append((filename, result)) + print(result) + # 保存结果 + if args.output: + save_path = save_result(args.output, filename, result) + print(f"💾 结果已保存到: {save_path}") + + print(f"\n✅ 全部处理完成，共处理{len(results)}个剧本") + +if __name__ == "__main__": + main()