@agentscope-ai/i18n 0.1.9-rc.1 → 0.1.9-rc.2

package/lib/core/translator.js

@@ -10,8 +10,21 @@ const {
   translateAndUpdateFiles,
   singleTranslateAndUpdateFiles,
 } = require('./file-processor');
-const { extractI18nKey } = require('../utils/ast-utils');
+const {
+  extractI18nKey,
+  chnRegExp,
+  onlyContainsChinesePunctuation,
+  onlyContainsEmoji,
+  isI18nCall,
+  isInConsoleCall,
+} = require('../utils/ast-utils');
 const { askQuestion } = require('../utils/cli-utils');
+const {
+  shouldIgnoreLineByComment,
+  shouldIgnoreBlockByComment,
+  shouldIgnoreByComment,
+  shouldIgnoreFile,
+} = require('../utils/file-utils');
 const { generateMedusaExcel } = require('../utils/excel-utils');
 // inquirer需要动态导入，因为它是ES模块
 const t = require('@babel/types');
@@ -310,6 +323,113 @@ const scanFilesAndCollectKeys = (files) => {
   return { usedKeys, usedKeysData };
 };
 
+// 扫描未翻译的中文文案（未被 $i18n.get 包裹的中文字符串）
+const scanUntranslatedTexts = (files, doNotTranslateFiles) => {
+  const untranslatedTexts = [];
+
+  const filteredFiles = files.filter((file) => {
+    if (shouldIgnoreFile(file, doNotTranslateFiles || [])) return false;
+    if (shouldIgnoreByComment(file)) return false;
+    return true;
+  });
+
+  filteredFiles.forEach((file) => {
+    try {
+      const code = fs.readFileSync(file, 'utf8');
+      const ast = parseAST(code);
+
+      const shouldIgnoreNode = (nodePath) => {
+        if (!nodePath.node.loc) return false;
+        const lineNumber = nodePath.node.loc.start.line;
+        return (
+          shouldIgnoreLineByComment(file, lineNumber) ||
+          shouldIgnoreBlockByComment(file, lineNumber)
+        );
+      };
+
+      traverse(ast, {
+        StringLiteral(astPath) {
+          const { value } = astPath.node;
+          if (
+            chnRegExp.test(value) &&
+            !isI18nCall(astPath.parent) &&
+            !astPath.findParent((p) => isI18nCall(p.node)) &&
+            !isInConsoleCall(astPath) &&
+            !shouldIgnoreNode(astPath) &&
+            !onlyContainsChinesePunctuation(value) &&
+            !onlyContainsEmoji(value)
+          ) {
+            untranslatedTexts.push({
+              file,
+              line: astPath.node.loc?.start.line,
+              column: astPath.node.loc?.start.column,
+              type: 'StringLiteral',
+              text: value,
+            });
+          }
+        },
+        TemplateLiteral(astPath) {
+          if (
+            !isI18nCall(astPath.parent) &&
+            !astPath.findParent((p) => isI18nCall(p.node)) &&
+            !isInConsoleCall(astPath) &&
+            !shouldIgnoreNode(astPath)
+          ) {
+            const staticParts = astPath.node.quasis.map((q) => q.value.raw).join('');
+            if (
+              chnRegExp.test(staticParts) &&
+              !onlyContainsChinesePunctuation(staticParts) &&
+              !onlyContainsEmoji(staticParts)
+            ) {
+              const fullText = astPath.node.quasis
+                .map((q, i) => {
+                  const expr = astPath.node.expressions[i];
+                  const exprStr = expr ? `\${${generate(expr, { compact: true }).code}}` : '';
+                  return q.value.raw + exprStr;
+                })
+                .join('');
+              untranslatedTexts.push({
+                file,
+                line: astPath.node.loc?.start.line,
+                column: astPath.node.loc?.start.column,
+                type: 'TemplateLiteral',
+                text: fullText,
+              });
+            }
+          }
+        },
+        JSXText(astPath) {
+          const { value } = astPath.node;
+          if (
+            chnRegExp.test(value) &&
+            !isI18nCall(astPath.parent) &&
+            !astPath.findParent((p) => isI18nCall(p.node)) &&
+            !isInConsoleCall(astPath) &&
+            !shouldIgnoreNode(astPath) &&
+            !onlyContainsChinesePunctuation(value) &&
+            !onlyContainsEmoji(value)
+          ) {
+            const trimmedValue = value.replace(/^\s+|\s+$/g, '');
+            if (trimmedValue) {
+              untranslatedTexts.push({
+                file,
+                line: astPath.node.loc?.start.line,
+                column: astPath.node.loc?.start.column,
+                type: 'JSXText',
+                text: trimmedValue,
+              });
+            }
+          }
+        },
+      });
+    } catch (error) {
+      console.error(`    # 扫描未翻译文案失败: ${file}`, error.message);
+    }
+  });
+
+  return untranslatedTexts;
+};
+
 // 读取翻译文件
 const readTranslationFiles = (localesFilePath, dashScope, checkLanguages) => {
   // 读取中文翻译文件
@@ -376,7 +496,7 @@ const analyzeMissingAndUnusedKeys = (usedKeys, zhCN, languageFiles) => {
 };
 
 // 生成检查结果输出
-const generateCheckOutput = (missingKeys, unusedKeys) => {
+const generateCheckOutput = (missingKeys, unusedKeys, untranslatedTexts) => {
   const outputLines = [];
   outputLines.push('=== 检查结果 ===');
   outputLines.push('');
@@ -392,7 +512,7 @@ const generateCheckOutput = (missingKeys, unusedKeys) => {
   }
 
   for (const [language, missing] of Object.entries(missingKeys)) {
-    if (language === 'zhCN') continue; // 跳过中文，已经处理过了
+    if (language === 'zhCN') continue;
 
     if (missing.length > 0) {
       outputLines.push('');
@@ -417,7 +537,7 @@ const generateCheckOutput = (missingKeys, unusedKeys) => {
   }
 
   for (const [language, unused] of Object.entries(unusedKeys)) {
-    if (language === 'zhCN') continue; // 跳过中文，已经处理过了
+    if (language === 'zhCN') continue;
 
     if (unused.length > 0) {
       outputLines.push('');
@@ -429,6 +549,20 @@ const generateCheckOutput = (missingKeys, unusedKeys) => {
     }
   }
 
+  outputLines.push('');
+  outputLines.push('3. 未翻译的中文文案:');
+
+  if (untranslatedTexts.length > 0) {
+    outputLines.push('');
+    outputLines.push(`共发现 ${untranslatedTexts.length} 条未翻译的中文文案:`);
+    untranslatedTexts.forEach((item) => {
+      outputLines.push(`    ${item.file}:${item.line}:${item.column}  "${item.text}"`);
+    });
+  } else {
+    outputLines.push('');
+    outputLines.push('没有发现未翻译的中文文案');
+  }
+
   outputLines.push('');
   outputLines.push('=== 检查完成 ===');
 
@@ -436,7 +570,13 @@ const generateCheckOutput = (missingKeys, unusedKeys) => {
 };
 
 // 处理输出和JSON文件生成
-const handleOutputAndJsonGeneration = (outputLines, missingKeys, unusedKeys, autoDeleteUnused) => {
+const handleOutputAndJsonGeneration = (
+  outputLines,
+  missingKeys,
+  unusedKeys,
+  untranslatedTexts,
+  autoDeleteUnused,
+) => {
   // 判断是否需要生成JSON文件（自动删除模式下不生成日志文件）
   if (outputLines.length > 100 && !autoDeleteUnused) {
     // 生成JSON文件
@@ -448,10 +588,12 @@ const handleOutputAndJsonGeneration = (outputLines, missingKeys, unusedKeys, aut
       summary: {
         totalMissingKeys: Object.values(missingKeys).reduce((sum, keys) => sum + keys.length, 0),
         totalUnusedKeys: Object.values(unusedKeys).reduce((sum, keys) => sum + keys.length, 0),
+        totalUntranslatedTexts: untranslatedTexts.length,
         totalOutputLines: outputLines.length,
       },
       missingKeys,
       unusedKeys,
+      untranslatedTexts,
     };
 
     try {
@@ -463,6 +605,7 @@ const handleOutputAndJsonGeneration = (outputLines, missingKeys, unusedKeys, aut
       console.log('\n📊 概要信息:');
       console.log(`   • 缺失的翻译key总数: ${jsonResult.summary.totalMissingKeys}`);
       console.log(`   • 未使用的翻译key总数: ${jsonResult.summary.totalUnusedKeys}`);
+      console.log(`   • 未翻译的中文文案总数: ${jsonResult.summary.totalUntranslatedTexts}`);
 
       // 显示各语言的统计
       console.log('\n📋 各语言统计:');
@@ -478,10 +621,13 @@ const handleOutputAndJsonGeneration = (outputLines, missingKeys, unusedKeys, aut
         console.log(`     ${displayLang}.json: ${unused.length}个`);
       }
 
+      if (untranslatedTexts.length > 0) {
+        console.log(`   未翻译的中文文案: ${untranslatedTexts.length}条`);
+      }
+
       console.log('\n=== 检查完成 ===\n');
     } catch (error) {
       console.error(`\n❌ 生成JSON文件失败: ${error.message}`);
-      // 如果JSON文件生成失败，仍然输出完整结果（自动删除模式下不输出）
       if (!autoDeleteUnused) {
         outputLines.forEach((line) => console.log(line));
       }
@@ -710,6 +856,7 @@ const check = async function (sourcePath, params) {
     medusa,
     autoDeleteUnused,
     summaryOnly,
+    doNotTranslateFiles,
     check: checkConfig,
   } = params;
 
@@ -730,6 +877,15 @@ const check = async function (sourcePath, params) {
   // 分析缺失和未使用的key
   const { missingKeys, unusedKeys } = analyzeMissingAndUnusedKeys(usedKeys, zhCN, languageFiles);
 
+  // 扫描未翻译的中文文案
+  console.log(`    # 扫描未翻译的中文文案...`);
+  const untranslatedTexts = scanUntranslatedTexts(files, doNotTranslateFiles);
+  if (untranslatedTexts.length > 0) {
+    console.log(`    # 发现 ${untranslatedTexts.length} 条未翻译的中文文案`);
+  } else {
+    console.log(`    # 未发现未翻译的中文文案`);
+  }
+
   // summaryOnly 模式：只输出各语言缺失的key数量，不做删除/生成等操作
   if (summaryOnly) {
     console.log('');
@@ -755,19 +911,34 @@ const check = async function (sourcePath, params) {
     }
 
     console.log('');
-    if (allGood) {
-      console.log('✅ 所有语言翻译完整');
+    if (untranslatedTexts.length > 0) {
+      console.log(`    未翻译的中文文案: ${untranslatedTexts.length} 条`);
+    } else {
+      console.log(`    未翻译的中文文案: ✓ 无`);
+    }
+
+    console.log('');
+    if (allGood && untranslatedTexts.length === 0) {
+      console.log('✅ 所有语言翻译完整，无未翻译文案');
+    } else if (allGood) {
+      console.log('❌ 存在未翻译的中文文案，请运行 npx i18n check 查看详情');
     } else {
       console.log('❌ 存在翻译缺失，请运行 npx i18n check 查看详情');
     }
 
-    return { missingKeys, unusedKeys, usedKeysData };
+    return { missingKeys, unusedKeys, usedKeysData, untranslatedTexts };
   }
 
   // 完整模式：输出详情、删除未使用key、生成Excel等
-  const outputLines = generateCheckOutput(missingKeys, unusedKeys);
+  const outputLines = generateCheckOutput(missingKeys, unusedKeys, untranslatedTexts);
 
-  handleOutputAndJsonGeneration(outputLines, missingKeys, unusedKeys, autoDeleteUnused);
+  handleOutputAndJsonGeneration(
+    outputLines,
+    missingKeys,
+    unusedKeys,
+    untranslatedTexts,
+    autoDeleteUnused,
+  );
 
   await handleUnusedKeysDeletion(
     unusedKeys,
@@ -783,6 +954,7 @@ const check = async function (sourcePath, params) {
     missingKeys,
     unusedKeys,
     usedKeysData,
+    untranslatedTexts,
   };
 
   return result;

package/lib/parse-jsx.js

@@ -4,87 +4,13 @@ const generate = require('@babel/generator').default;
 const t = require('@babel/types');
 const fs = require('fs-extra');
 const { shouldIgnoreLineByComment, shouldIgnoreBlockByComment } = require('./utils/file-utils');
-
-// 中文识别正则表达式
-const chnRegExp = new RegExp(/[^\x00-\xff]/);
-
-// 检查是否只包含中文标点符号
-const onlyContainsChinesePunctuation = (text) => {
-  // 中文标点符号正则，包括全角标点符号和常见符号
-  const chinesePunctuationRegex =
-    /[，。！？；：""''（）【】《》｜、…—·~～@#$%^&*()_+\-={}\[\]|\\:;"'<>,.?\/]/g;
-  // 移除所有中文标点符号
-  const textWithoutPunctuation = text.replace(chinesePunctuationRegex, '');
-  // 如果移除标点后为空，说明只包含标点符号
-  return textWithoutPunctuation.trim() === '';
-};
-
-const onlyContainsEmoji = (text) => {
-  // Emoji 正则表达式，包含常见的emoji Unicode范围
-  const emojiRegex =
-    /[\u{1F600}-\u{1F64F}]|[\u{1F300}-\u{1F5FF}]|[\u{1F680}-\u{1F6FF}]|[\u{1F1E0}-\u{1F1FF}]|[\u{2600}-\u{26FF}]|[\u{2700}-\u{27BF}]|[\u{1F900}-\u{1F9FF}]|[\u{1F018}-\u{1F270}]|[\u{238C}-\u{2454}]|[\u{20D0}-\u{20FF}]|[\u{FE00}-\u{FE0F}]|[\u{1F200}-\u{1F2FF}]|[\u{1F700}-\u{1F77F}]|[\u{1F780}-\u{1F7FF}]|[\u{1F800}-\u{1F8FF}]|[\u{2300}-\u{23FF}]|[\u{2B00}-\u{2BFF}]|[\u{3030}]|[\u{303D}]|[\u{3297}]|[\u{3299}]/gu;
-
-  // 移除所有空白字符
-  const trimmedText = text.trim();
-
-  // 如果文本为空，返回false
-  if (!trimmedText) {
-    return false;
-  }
-
-  // 移除所有emoji字符
-  const textWithoutEmoji = trimmedText.replace(emojiRegex, '');
-
-  // 如果移除emoji后为空，说明只包含emoji
-  return textWithoutEmoji === '';
-};
-
-// 检查节点是否是i18n调用
-function isI18nCall(node) {
-  return (
-    node &&
-    node.type === 'CallExpression' &&
-    node.callee &&
-    node.callee.type === 'MemberExpression' &&
-    node.callee.object &&
-    node.callee.object.name === '$i18n' &&
-    node.callee.property &&
-    node.callee.property.name === 'get'
-  );
-}
-
-// 检测是否在 console 方法中
-function isInConsoleCall(path) {
-  const consoleMethods = [
-    'log',
-    'warn',
-    'error',
-    'info',
-    'debug',
-    'trace',
-    'group',
-    'groupEnd',
-    'groupCollapsed',
-    'assert',
-    'table',
-    'time',
-    'timeEnd',
-    'count',
-    'countReset',
-  ];
-
-  return path.findParent((p) => {
-    return (
-      p.isCallExpression() &&
-      p.node.callee &&
-      p.node.callee.type === 'MemberExpression' &&
-      p.node.callee.object &&
-      p.node.callee.object.name === 'console' &&
-      p.node.callee.property &&
-      consoleMethods.includes(p.node.callee.property.name)
-    );
-  });
-}
+const {
+  chnRegExp,
+  onlyContainsChinesePunctuation,
+  onlyContainsEmoji,
+  isI18nCall,
+  isInConsoleCall,
+} = require('./utils/ast-utils');
 
 // 生成i18n调用节点
 const createI18nCallNode = (i18nKey, defaultMessage, variables = []) => {

package/lib/utils/ast-utils.js

@@ -93,8 +93,74 @@ function checkI18nCall(node) {
   return extractI18nKey(node);
 }
 
+const chnRegExp = /[^\x00-\xff]/;
+
+const onlyContainsChinesePunctuation = (text) => {
+  const chinesePunctuationRegex =
+    /[，。！？；：""''（）【】《》｜、…—·~～@#$%^&*()_+\-={}\[\]|\\:;"'<>,.?\/]/g;
+  const textWithoutPunctuation = text.replace(chinesePunctuationRegex, '');
+  return textWithoutPunctuation.trim() === '';
+};
+
+const onlyContainsEmoji = (text) => {
+  const emojiRegex =
+    /[\u{1F600}-\u{1F64F}]|[\u{1F300}-\u{1F5FF}]|[\u{1F680}-\u{1F6FF}]|[\u{1F1E0}-\u{1F1FF}]|[\u{2600}-\u{26FF}]|[\u{2700}-\u{27BF}]|[\u{1F900}-\u{1F9FF}]|[\u{1F018}-\u{1F270}]|[\u{238C}-\u{2454}]|[\u{20D0}-\u{20FF}]|[\u{FE00}-\u{FE0F}]|[\u{1F200}-\u{1F2FF}]|[\u{1F700}-\u{1F77F}]|[\u{1F780}-\u{1F7FF}]|[\u{1F800}-\u{1F8FF}]|[\u{2300}-\u{23FF}]|[\u{2B00}-\u{2BFF}]|[\u{3030}]|[\u{303D}]|[\u{3297}]|[\u{3299}]/gu;
+  const trimmedText = text.trim();
+  if (!trimmedText) return false;
+  return trimmedText.replace(emojiRegex, '') === '';
+};
+
+function isI18nCall(node) {
+  return (
+    node &&
+    node.type === 'CallExpression' &&
+    node.callee &&
+    node.callee.type === 'MemberExpression' &&
+    node.callee.object &&
+    node.callee.object.name === '$i18n' &&
+    node.callee.property &&
+    node.callee.property.name === 'get'
+  );
+}
+
+function isInConsoleCall(path) {
+  const consoleMethods = [
+    'log',
+    'warn',
+    'error',
+    'info',
+    'debug',
+    'trace',
+    'group',
+    'groupEnd',
+    'groupCollapsed',
+    'assert',
+    'table',
+    'time',
+    'timeEnd',
+    'count',
+    'countReset',
+  ];
+  return path.findParent((p) => {
+    return (
+      p.isCallExpression() &&
+      p.node.callee &&
+      p.node.callee.type === 'MemberExpression' &&
+      p.node.callee.object &&
+      p.node.callee.object.name === 'console' &&
+      p.node.callee.property &&
+      consoleMethods.includes(p.node.callee.property.name)
+    );
+  });
+}
+
 module.exports = {
   extractStringValue,
   extractI18nKey,
   checkI18nCall,
+  chnRegExp,
+  onlyContainsChinesePunctuation,
+  onlyContainsEmoji,
+  isI18nCall,
+  isInConsoleCall,
 };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agentscope-ai/i18n",
-  "version": "0.1.9-rc.1",
+  "version": "0.1.9-rc.2",
   "description": "A tool for translating Chinese content in frontend code repositories",
   "keywords": [
     "i18n",