vite-gc-i18n-plugin 1.1.8 → 1.1.9

package/dist/index.cjs

@@ -924,7 +924,7 @@ function createTextSplitter(values, maxChunkSize) {
  */
 function splitByRegex(str, separatorRegex) {
   // 定义标点符号的正则表达式
-  const punctuationRegex = /[，。？！《》,.．：!?""''；'"、0-9\n\r\t\v\f]/;
+  const punctuationRegex = /[，。？！《》（）(),.．：!?""''；'"、0-9\n\r\t\v\f]/;
   // 创建一个新的正则表达式，用于分割字符串
   const splitRegex = new RegExp(`(${separatorRegex.source}|${punctuationRegex.source})`, separatorRegex.flags);
 
@@ -934,7 +934,7 @@ function splitByRegex(str, separatorRegex) {
   let currentMatch = '';
 
   // 定义连接标点符号的正则表达式
-  const connectPunctuationRegex = /[，。？！《》,.．：!?；'"、0-9]/;
+  const connectPunctuationRegex = /[，。？！《》（）(),.．：!?；'"、0-9]/;
   // 创建一个新的正则表达式，用于检测是否需要连接
   const connectRegex = new RegExp(`(${separatorRegex.source}|${connectPunctuationRegex.source})`, separatorRegex.flags);
 
@@ -981,7 +981,85 @@ function splitByRegex(str, separatorRegex) {
   if (tempStr) {
     finalResult.push(tempStr);
   }
-  return finalResult;
+  return mergeInlineTextSeparatedOriginChunks(finalResult, separatorRegex);
+}
+function mergeInlineTextSeparatedOriginChunks(strArray, separatorRegex) {
+  const result = [];
+  for (let i = 0; i < strArray.length; i++) {
+    let current = strArray[i];
+    if (!separatorRegex.test(current) && i + 1 < strArray.length && separatorRegex.test(strArray[i + 1])) {
+      const {
+        beforeInlineText,
+        inlineText
+      } = splitTrailingInlineText(current);
+      if (inlineText && /[^\s\u00a0]/.test(inlineText)) {
+        if (beforeInlineText) {
+          result.push(beforeInlineText);
+        }
+        current = `${normalizeInlineTextPrefix(inlineText)}${strArray[i + 1]}`;
+        i += 1;
+      }
+    }
+    if (!separatorRegex.test(current) && isInlineTextSeparator(current) && /[^\s\u00a0]/.test(current) && i + 1 < strArray.length && separatorRegex.test(strArray[i + 1])) {
+      current = `${normalizeInlineTextPrefix(current)}${strArray[i + 1]}`;
+      i += 1;
+    }
+    if (separatorRegex.test(current)) {
+      while (i + 2 < strArray.length && isInlineTextSeparator(strArray[i + 1]) && separatorRegex.test(strArray[i + 2])) {
+        current += `${normalizeInlineTextSeparator(strArray[i + 1])}${strArray[i + 2]}`;
+        i += 2;
+      }
+      if (i + 1 < strArray.length) {
+        const {
+          inlineText,
+          rest
+        } = splitLeadingInlineText(strArray[i + 1]);
+        if (inlineText) {
+          current += normalizeInlineTextSeparator(inlineText);
+          strArray[i + 1] = rest;
+        }
+      }
+    }
+    if (current) {
+      result.push(current);
+    }
+  }
+  return result;
+}
+function isInlineTextSeparator(value) {
+  return value !== '' && !/[<>]/.test(value);
+}
+function normalizeInlineTextSeparator(value) {
+  return /^[\s\u00a0]+$/.test(value) ? ' ' : value.replace(/[\s\u00a0]+/g, ' ');
+}
+function normalizeInlineTextPrefix(value) {
+  return value.replace(/[\s\u00a0]+/g, ' ').trimStart();
+}
+function splitLeadingInlineText(value) {
+  const tagIndex = value.search(/[<>]/);
+  if (tagIndex === -1) {
+    return {
+      inlineText: value,
+      rest: ''
+    };
+  }
+  return {
+    inlineText: value.slice(0, tagIndex),
+    rest: value.slice(tagIndex)
+  };
+}
+function splitTrailingInlineText(value) {
+  const tagEndIndex = value.lastIndexOf('>');
+  if (tagEndIndex === -1) {
+    return {
+      beforeInlineText: '',
+      inlineText: value
+    };
+  }
+  return {
+    beforeInlineText: value.slice(0, tagEndIndex + 1),
+    inlineText: value.slice(tagEndIndex + 1)
+  };
 }
 
 /**
@@ -991,7 +1069,7 @@ function splitByRegex(str, separatorRegex) {
  */
 function checkNeedSplit(str) {
   // 检查字符串中是否包含需要切割的特殊字符
-  return str.includes('\n') || str.includes('\\') || str.includes('\r') || str.includes('\t') || str.includes('\v') || str.includes('\f') || str.includes('>') || str.includes('<');
+  return str.includes('\\') || str.includes('>') || str.includes('<');
 }
 
 /**