[Java]Java 常用类整理一(字符串处理类)

import java.io.*;
import java.text.DecimalFormat;
import org.apache.oro.text.regex.PatternCompiler;
import org.apache.oro.text.regex.PatternMatcher;
import org.apache.oro.text.regex.Perl5Matcher;
import org.apache.oro.text.regex.Pattern;
import org.apache.oro.text.regex.Perl5Compiler;

import org.apache.commons.logging.Log;
/**
 * <p>Title: StringUtils</p>
 * <p>Description: 字符串工具类; 配合JakartaCommons工具类使用;</p>
 * <p>Copyright: Copyright (c) 2003</p>
 * <p>Company: pubinfo</p>
 * @author chineseren
 * @version 1.0
 */
public class StringUtils {
    /**
     * debug log
     */
    private static Log log = Debuger.getDebuger(StringUtils.class);
  /**
   * String charSet 转化
   * @param str String
   * @return String
   */
  public static String toChinese(String str) {
    if(str == null || str.length() == 0) {
      return "";
    }
    try {
      return new String(str.getBytes("ISO8859_1"), "GBK");
    } catch(UnsupportedEncodingException ex) {
      return str;
    }
  }

  /**
   * 判断字符串是否null或者""
   * @param src String
   * @return boolean
   */
  public static boolean isBlank(String src) {
    if(null == src || "".equals(src.trim())) {
      return true;
    }
    return false;
  }

  /**
   * @param string - 待判断的字符串是否为null或者空字符串
   * @return boolean
   * @roseuid 3FBE26DE0326
   */
  public static boolean isNullOrEmpty(String string) {
    if(string == null || string.trim().equals("")) {
      return true;
    } else {
      return false;
    }
  }

  /**
   * 把没有实例化的串转化为空串
   * @param p_in String
   * @return String
   */
  public static String convertNull(String str) {
    if(str == null) {
      return "";
    } else {
      return str;
    }
  }

  /**
   * 控制页面显示长度,dataStr为控制长度的字符串，length为字节的长度；
   * 字符串的字节长度小于显示长度，则原样输出，否则以XXX...的形式输出。
   * @param dataStr String
   * @param length int
   * @return String
   */
  public static String controlLength(String dataStr, int length) {
    if(dataStr == null) {
      return "";
    }
    //转化成格式化的Html
    dataStr = StringUtils.escape(dataStr);

    StringBuffer sb = new StringBuffer();
    char datach;
    int lengthi = 0; //字符串的字节长度
    int strj = 0; //字符串的实际长度
    int lengthi3 = 0; //字节长度-4
    //得到字符串的字节长度
    while(strj < dataStr.length()) {
      datach = dataStr.charAt(strj++);
      if(((datach <= 'z') && (datach >= 'a'))
          || ((datach <= 'Z') && (datach >= 'A'))
          || ((datach <= '9') && (datach >= '0'))) {
        lengthi++;
      } else {
        lengthi = lengthi + 2;
      }
    }
    strj = 0;
    //得到字符串的字节长度-4
    while((lengthi3 < length - 4) && (strj < dataStr.length())) {
      datach = dataStr.charAt(strj++);
      sb.append(datach);
      if(((datach <= 'z') && (datach >= 'a'))
          || ((datach <= 'Z') && (datach >= 'A'))
          || ((datach <= '9') && (datach >= '0'))) {
        lengthi3++;
      } else {
        lengthi3 = lengthi3 + 2;
      }
    }
    if(lengthi <= length) {
      return dataStr;
    } else {
      sb.append("...");
    }
    return sb.toString();
  }

  /**
   * 把字符串转化成HTML字符串
   * @param  str      --需要转换的字符串
   * @return String   --返回把特殊字符转换了的字符串
   */
  public static String escape(String str) {
    if(str == null) {
      return "";
    }
    byte[] data = str.getBytes();
    int len = data.length;
    StringBuffer result = new StringBuffer(len * 2);

    int begin = 0, count = 0, tt = 0;
    for(int i = 0; i < len; i++) {
      switch((char)data[i]) {
        case '&':
          result.append(new String(data, begin, count));
          result.append("&amp;");
          begin = i + 1;
          count = 0;
          break;
        case '\"':
          result.append(new String(data, begin, count));
          result.append("&quot;");
          begin = i + 1;
          count = 0;
          break;
        case '<':
          result.append(new String(data, begin, count));
          result.append("&lt;");
          begin = i + 1;
          count = 0;
          break;
        case '>':
          result.append(new String(data, begin, count));
          result.append("&gt;");
          begin = i + 1;
          count = 0;
          break;
        case '\n':
          result.append(new String(data, begin, count));
          result.append("<br>");
          begin = i + 1;
          count = 0;
          break;
        case '$':
          result.append(new String(data, begin, count));
          result.append("$$");
          begin = i + 1;
          count = 0;
          break;
        case ' ':
          result.append(new String(data, begin, count));
          result.append("&nbsp;");
          begin = i + 1;
          count = 0;
          break;
        default:
          count++;
          break;
      }
    }
    if(count > 0) {
      result.append(new String(data, begin, count));
    }
    return result.toString();
  }
  
  
  /**
   * 把字符串转化成HTML字符串(除了空格)
   * @param  str      --需要转换的字符串
   * @return String   --返回把特殊字符转换了的字符串
   */
  public static String escape2(String str) {
    if(str == null) {
      return "";
    }
    byte[] data = str.getBytes();
    int len = data.length;
    StringBuffer result = new StringBuffer(len * 2);

    int begin = 0, count = 0, tt = 0;
    for(int i = 0; i < len; i++) {
      switch((char)data[i]) {
        case '&':
          result.append(new String(data, begin, count));
          result.append("&amp;");
          begin = i + 1;
          count = 0;
          break;
        case '\"':
          result.append(new String(data, begin, count));
          result.append("&quot;");
          begin = i + 1;
          count = 0;
          break;
        case '<':
          result.append(new String(data, begin, count));
          result.append("&lt;");
          begin = i + 1;
          count = 0;
          break;
        case '>':
          result.append(new String(data, begin, count));
          result.append("&gt;");
          begin = i + 1;
          count = 0;
          break;
        case '\n':
          result.append(new String(data, begin, count));
          result.append("<br>");
          begin = i + 1;
          count = 0;
          break;
        case '$':
          result.append(new String(data, begin, count));
          result.append("$$");
          begin = i + 1;
          count = 0;
          break;
        default:
          count++;
          break;
      }
    }
    if(count > 0) {
      result.append(new String(data, begin, count));
    }
    return result.toString();
  }
  
  
  /**
   * 将textarea输入的文本转化成前台html显示的格式，主要将回车（/r/n）替换成<br>," "替换成&nbsp;
   * @param text String
   * @return String
   */
  public static String textConvertToHtmlText(String text){
      if(text != null){
          return text.replaceAll("\r\n", "<br>").replaceAll(" ", "&nbsp;");
      }else{
          return null;
      }
  }
  /**
   * 全数字判断
   * @param strIn String
   * @return boolean
   */
  public static boolean isNumberString(String strIn) {
    return isNumberString(strIn, "0123456789");
  }

  /**
   * 全数字判断,参照字符串strRef可以是:"0123456789","23546"或"0123"等等。
   * @param strIn String
   * @param strRef String
   * @return boolean
   */
  public static boolean isNumberString(String strIn, String strRef) {
    if(strIn == null || strIn.length() == 0)
      return(false);
    for(int i = 0; i < strIn.length(); i++) {
      String strTmp = strIn.substring(i, i + 1);
      if(strRef.indexOf(strTmp, 0) == -1)
        return(false);
    }
    return(true);
  }

  /**
   * 字符串替换,调用了org.apache.commons.lang.StringUtils.replace()
   * @param strObj 目标字符串
   * @param str1 被替换的字符串
   * @param str2 替换成的字符串
   * @return String
   */
  public static String replace(String strObj, String str1, String str2) {
    if("".equals(str1)) {
      return strObj;
    }
    return org.apache.commons.lang.StringUtils.replace(strObj, str1, str2);
  }
  /**
   * 根据内容生成摘要
   * @param content String
   * @return String
   */
  public static String createSummary(String content){
    if(content == null)return null;
    String regexp = "<.*?>";
    //System.out.println(regexp);
    content = content.replaceAll(regexp,"");
    int len = content.length();
    if(len > 120){
      return content.substring(0, 120);
    }else{
      return content;
    }
  }

  /**
   * 字符串切割,比如"#sd#kf##dkf##Ej#"按照"#"切割之后length=8,即"#"出现的次数加一
   * @param strObj 目标字符串
   * @param str1 用于切割的字符串
   * @return String[]
   */
  public static String[] split(String strObj, String delimiter) {
    if(strObj == null) {
      return null;
    }
    if("".equals(strObj) || "".equals(delimiter)) {
      return new String[] {
          strObj};
    }

    int count = org.apache.commons.lang.StringUtils.countMatches(strObj,
        delimiter) + 1; //调用org.apache.commons
    int length = delimiter.length();
    String[] strs = new String[count];
    int posPre = 0 - length;
    int pos = 0;
    for(int i = 0; i < count - 1; i++) {
      pos = strObj.indexOf(delimiter, posPre + length);
      strs[i] = strObj.substring(posPre + length, pos);
      posPre = pos;
    }
    strs[count - 1] = strObj.substring(posPre + length);
    return strs;
  }

  /**
   * 用于转义单斜杠特殊字符
   * @param str String
   * @return String
   */
  public static final String appendStr(String str) {
    char c = ' ';
    StringBuffer sb = new StringBuffer();
    for(int i = 0; i < str.length(); i++) {
      c = str.charAt(i);
      if(c == '\\') {
        sb.append("\\\\");
      } else {
        sb.append(c);
      }
    }
    return sb.toString();
  }

  /**
   * 将reader流中的数据变成String
   * @param is reader流
   * @return String
   * @throws IOException
   */
  public static String readerToString(Reader is) throws IOException {
    StringBuffer sb = new StringBuffer();
    char[] b = new char[8192];
    int n;
    while((n = is.read(b)) > 0) {
      sb.append(b, 0, n);
    }
    return sb.toString();
  }

  /**
   * 将input流中的数据变成String
   * @param is InputStream流
   * @throws IOException
   * @return String
   */
  public static String inputStreamToString(InputStream is) throws IOException {
    return readerToString(new InputStreamReader(is));
  }

  /**
   * 返回字符串的前len个字符.例如:输入"abcdefg",3 返回 "abc".
   * @param value String
   * @param len int
   * @return String
   */
  public static String getLmtStr(String value, int len) {
    if(value == null || value.length() <= len)
      return value;
    return value.substring(0, len);
  }
  /**
   * 返回字符串的前len个字符.例如:输入"abcdefg",3 返回 "abc...".
   * @param value String
   * @param len int
   * @return String
   */
  public static String getLmtString(String value, int len) {
    if(value == null || value.length() <= len)
      return value;
    return value.substring(0, len) + "...";
  }
  /**
   * 输入带html标签的字符串,返回干净的字符串,其中将(&nbsp;->" "),(<br>->\r\n),(<p>->\r\n\r\n)
   * @param body String
   * @return String
   */
  public static String getCleanString(String body) {
    //替换&nbsp;->" ",<br>->\r\n <p>->\r\n\r\n
    body = body.replaceAll("&[nN][bB][sS][pP];"," ");
    body = body.replaceAll("<[bB][rR]\\s*>","\r\n");
    body = body.replaceAll("<[pP]\\s*>","\r\n\r\n");
    //删除所有标签

    body = body.replaceAll("<.+?>","");
    return body;
//    String htmlStr = body; //含html标签的字符串
//    String textStr = "";
//
//
//    try {
//        //定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script> }
//        String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>";
//        //定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style> }
//        String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>";
//        //定义HTML标签的正则表达式
//        String regEx_html = "<[^>]+>";
//        //过滤script标签
//        java.util.regex.Pattern p_script = java.util.regex.Pattern.compile(regEx_script, java.util.regex.Pattern.CASE_INSENSITIVE);
//        java.util.regex.Matcher m_script = p_script.matcher(htmlStr);
//        htmlStr = m_script.replaceAll("");
//        //过滤style标签
//        java.util.regex.Pattern p_style = java.util.regex.Pattern.compile(regEx_style, java.util.regex.Pattern.CASE_INSENSITIVE);
//        java.util.regex.Matcher m_style = p_style.matcher(htmlStr);
//        htmlStr = m_style.replaceAll("");
//        //过滤html标签
//        java.util.regex.Pattern p_html = java.util.regex.Pattern.compile(regEx_html, java.util.regex.Pattern.CASE_INSENSITIVE);
//        java.util.regex.Matcher m_html = p_html.matcher(htmlStr);
//        htmlStr = m_html.replaceAll("");
//
//        textStr = htmlStr;
//
//    } catch (Exception e) {
//
//    }
//
//    return textStr; //返回文本字符串

  }

  /**
   * 返回字符串的len个字符.取前后，去掉中间 例如:输入"abcdefg",3 返回 "ab ... g".
   * @param value String
   * @param len int
   * @return String
   */
  public static String getLmtStrx(String value, int len) {
    if(value == null || value.length() <= len)
      return value;
    value = value.substring(0,len/2) + ".." + value.substring(value.length()-len/2);
    return value;
  }

  /**
   * 给传入的字符串前补足'0'，以使字符串长度为len。例如：输入字符串:"23",4 返回:"0023"。
   * @param str String
   * @param len int
   * @return String
   */
  public String getZeroStr(String str, int len) {
    int strlen = str.length();
    for(int i = 0; i < len - strlen; i++) {
      str = "0" + str;
    }
    return str;
  }
  /**
   * 输入0000返回0001，输入00000001返回00000002
   * @param rank String
   * @return String
   */
  public static String createRank(String rank){
      String prefix = null;
      String suffix = null;
//       System.out.println("rank"+rank);
//       if(rank!=null&&rank.trim().endsWith("wf")){
//          rank= rank.trim().substring(0,rank.length()-2);
//       }
      if (rank.trim().length() > 4) {
          prefix = rank.substring(0, rank.length() - 4);
          suffix = rank.substring(prefix.length());
          long tmp = Long.parseLong(suffix);
          tmp++;
          int len = suffix.length();
          suffix = new Long(tmp).toString();
          len = len - suffix.length();
          for (int n = 0; n < len; n++) {
              suffix = "0" + suffix;
          }
          rank = prefix + suffix;
      } else {
          long tmp = Long.parseLong(rank);
          tmp++;
          int len = rank.length();
          rank = new Long(tmp).toString();
          len = len - rank.length();
          for (int n = 0; n < len; n++) {
              rank = "0" + rank;
          }
      }
      return rank;
  }
  /**
   * [ab][cd] - > ab;cd
   * @param array String[]
   * @return String
   */
  public static String getArrayAsString(String[] array){
    String rs = "";
    if(array != null){
      for(int i =0;i < array.length;i ++){
        rs += array[i] + ";";
      }
    }
    if(rs.endsWith(";")){
      rs = rs.substring(0,rs.length() - 1);
    }
    return rs;
  }
  /**
   * 过滤HTML标签
   * @param value String
   * @return String
   */
  public static String filterScriptHtml(String value) {
    if(value == null)
      return "";
    else {
      value = value.replaceAll("<", "&lt;");
      value = value.replaceAll(">", "&gt;");
    }
    return value;
  }

  /**
   * @param value double
   * @param format String  "0.00"
   * @return String
   */
  public static String getFormatDouble(double value, String format) {
    DecimalFormat d = new DecimalFormat(format);
    return d.format(value);
  }

  /**
   * 0.34567 -> 0.35
   * @param value double
   * @return String
   */
  public static String getFormatDouble(double value) {
    return getFormatDouble(value, "0.00");
  }

  /**
   * double数据类型取小数点位数
   * @param doubleData double
   * @param scale int
   * @return String
   */
  public static String  getDoubleByScale(double doubleData,int scale){
    String strFormator = "#." + org.apache.commons.lang.StringUtils.repeat("#",scale);
    java.text.DecimalFormat formater = new java.text.DecimalFormat(strFormator);
    String newData = formater.format(doubleData);
    return newData;
  }

  /**
   * 判断str是否在src String[]中
   * @param src 源String[]
   * @param str 要判断的String
   * @return boolean
   */
  public static boolean isContain(String[] src, String str) {
    if(null == src) {
      return false;
    }
    for(int i = 0; i < src.length; i++) {
      if(str.equalsIgnoreCase(src[i])) {
        return true;
      }
    }
    return false;
  }

  /**
   * 正则表达式判断(忽略大小写)
   * @param target String
   * @param regex String
   * @return boolean
   */
  public static boolean isMatch(String target, String regex) {
    PatternCompiler compiler = new Perl5Compiler();
    Pattern pattern = null;
    try {
      pattern = compiler.compile(regex, Perl5Compiler.CASE_INSENSITIVE_MASK);
    }
    catch (Exception e) {
      return false;
    }
    PatternMatcher patternMatcher = new Perl5Matcher();
    return patternMatcher.matches(target, pattern);
  }
  /**
    * 产生一个随机id,这个id以系统时间开头
    * @return String
    */
   public static String createId() {
       //System.out.println(System.currentTimeMillis());
       String c = "" + getCount();
       if (c.length() == 1) {
           c = "0" + c;
       }
       String id = System.currentTimeMillis() + c;
       int len = 32 - id.length();

       return id + org.apache.commons.lang.RandomStringUtils.randomAlphanumeric(len);
   }

   private static int counter = 0;

   protected static int getCount() {
       synchronized (StringUtils.class) {
           if (counter < 0) {
               counter = 0;

           }
           counter++;
           if (counter == 99) {
               counter = 0;
           }
           return counter;
       }
   }

  public static void main(String[] args){
    //String b[] = null;
    ///System.out.print(  getArrayAsString(b));
     String a = org.trundle.common.FileUtils.read("C:\\Documents and Settings\\admin\\桌面\\aa.txt");
//    String abc = " <SPAN lang=EN-US style=\"FONT-SIZE: 12pt; COLOR: #666666; FONT-FAMILY: 宋体; mso-bidi-font-size: 9.0pt\">2003年12月4日<SPAN lang=EN-US style=\"FONT-SIZE:ze:中午 9.0pt\">";
     System.out.print(getCleanString(a));
//    String you你好 = "你好";
//    System.out.println(you你好);
//    abc = "AA&bb+CC&cc";
//    String[] b = abc.split("\\+");
//    System.out.println(b[0]);

    System.out.println(getFormatDouble(4.45,"0"));
    System.out.println(createRank("00000005"));

  }
}