中英文混排的字串拆分

1 UTF-8編碼

/**  * 把字串以UTF-8編碼按照佔用指定的位元組數進行拆分，支援中英文混排  *   * @param wideStr  *            要拆分的字串  * @param maxByteLen  *            字串佔用的最大位元組數  * @return 如果不需要拆分，返回null。否著返回拆分好的字串列表。  */ public List<String> splitUTF8Words(String wideStr, int maxByteLen) {     if (maxByteLen < 3 || wideStr.length() < (maxByteLen / 3)) {         return null;     } else {         try {             byte[] bytes = wideStr.getBytes("utf-8");             int bytesLen = bytes.length;             if (bytesLen < maxByteLen) {                 return null;             }             List<String> result = new ArrayList<String>(3);             int i = 0; // 指向原數組的標記。             int count = 0; // 該組的計數器             int currSplitStrStartIndex = 0; // 當前拆分的字元起始位置             int currSplitStrIndex = -1; // 當前拆分時，計算的字元             int lastIndex = -1; // 為了回退             while (i < bytesLen) {                 byte b = bytes[i]; // 起始字元                 lastIndex = i;                 if ((b & 0x80) == 0) {                     i++;                     count++;                 } else if ((b & 0xe0) != 0) {                     // 3個位元組的漢字                     i = i + 3;                     count = count + 3;                 } else {                     // 2個位元組                     i = i + 2;                     count = count + 2;                 }                 currSplitStrIndex++;                 if (count == maxByteLen) {                     result.add(wideStr.substring(currSplitStrStartIndex,                             currSplitStrIndex + 1));                     // 清零                     count = 0;                     currSplitStrStartIndex = currSplitStrIndex + 1;                 } else if (count > maxByteLen) {                     // 如果大於需要回退                     i = lastIndex;                     currSplitStrIndex--;                     result.add(wideStr.substring(currSplitStrStartIndex,                             currSplitStrIndex + 1));                     // 清零                     count = 0;                     currSplitStrStartIndex = currSplitStrIndex + 1;                 }             }             if (currSplitStrIndex >= currSplitStrStartIndex) {                 result.add(wideStr.substring(currSplitStrStartIndex,                         currSplitStrIndex + 1));             }             return result;         } catch (Exception e) {             e.printStackTrace();             return null;         }     } }

 

2 GBK編碼，原理差不多

 

/**  * 把字串以GBK編碼按照佔用指定的位元組數進行拆分，支援中英文混排  *   * @param wideStr  *            要拆分的字串  * @param maxByteLen  *            字串佔用的最大位元組數  * @return 如果不需要拆分，返回null。否著返回拆分好的字串列表。  */ public List<String> splitGBKWords(String wideStr, int maxByteLen) {     if (maxByteLen < 2 || wideStr.length() < (maxByteLen / 2)) {         return null;     } else {         try {             byte[] bytes = wideStr.getBytes("gbk");             int bytesLen = bytes.length;             if (bytesLen < maxByteLen) {                 return null;             }             List<String> result = new ArrayList<String>(3);             int i = 0; // 指向原數組的標記。             int count = 0; // 該組的計數器             int currSplitStrStartIndex = 0; // 當前拆分的字元起始位置             int currSplitStrIndex = -1; // 當前拆分時，計算的字元             int lastIndex = -1; // 為了回退             while (i < bytesLen) {                 byte b = bytes[i]; // 起始字元                 lastIndex = i;                 if ((b & 0x80) == 0) {                     // 首位為0說明是英文                     i++;                     count++;                 } else {                     // 漢字                     i = i + 2;                     count = count + 2;                 }                 currSplitStrIndex++;                 if (count == maxByteLen) {                     result.add(wideStr.substring(currSplitStrStartIndex,                             currSplitStrIndex + 1));                     // 清零                     count = 0;                     currSplitStrStartIndex = currSplitStrIndex + 1;                 } else if (count > maxByteLen) {                     // 如果大於需要回退                     i = lastIndex;                     currSplitStrIndex--;                     result.add(wideStr.substring(currSplitStrStartIndex,                             currSplitStrIndex + 1));                     // 清零                     count = 0;                     currSplitStrStartIndex = currSplitStrIndex + 1;                 }             }             if (currSplitStrIndex >= currSplitStrStartIndex) {                 result.add(wideStr.substring(currSplitStrStartIndex,                         currSplitStrIndex + 1));             }             return result;         } catch (Exception e) {             e.printStackTrace();             return null;         }     } }