apache的Jakarta-ORO库 的正则表达式的使用

1/5/2008来源:Java教程人气:9672


  apache的Jakarta-ORO库 的正则表达式的使用
  ---附件是代码和相关文件
  package regulareXPRessiontest.Jakarta_ORO;
  
  /**
  * <p>Title: </p>
  * <p>Description: </p>
  * <p>Copyright: Copyright (c) 2003</p>
  * <p>Company: </p>
  * @author wdz : [email protected]
  * @version 1.0
  */
  
  import org.apache.oro.io.*;
  import org.apache.oro.text.regex.*;
  
  public class Jakarta_OROTest1 {
  public Jakarta_OROTest1() {
  System.out.println("aaa121-0hhksjds找出第一个数字串");
  containMatch("aaa121-0hhksjds", "\\d+");
  
  System.out.println("从 3$xaaa121-0hhksjds 找出第一个[a-z]{4}[0-9]{3}");
  containMatch("3$xaaa121-0hhksjds", "[a-z]{4}[0-9]{3}");
  
  System.out.println("从 Catlog catherone cat cat1 catlog catherone 找出第一个cat[a-z]*\\s+");
  preMatch("Catlog catherone cat cat1 catlog catherone", "cat[a-z]*\\s+");
  
  ////找出第一个t*n
  System.out.println("ten tig找出第一个t*n");
  containMatch("ten tig", "[a-z]{1}.[a-z]{1}");
  
  System.out.println("获得年月日");
  getDateString();
  
  // 找出所有 car*的单词,单词分割符号是空格符号或者逗号
  System.out.println("找出所有 car*的单词,单词分割符号是空格符号或者逗号");
  cycleMatch("Catlog catherone cat cat1 catlog catlog2 catherone", "((cat\\w*))\\s+",0);
  
  //找出所有的 扩号内的内容
  //使用 (( 和))配对使用可以进行分组,
  System.out.println("找出所有的 扩号内的内容");
  cycleMatch("Cuid=100(guest) gid=100(others) groups=10(users),11(floppy)", "[(]{1}((\\w*))[)]{1}",1);
  
  //找出所有的日期字符串得月份
  //使用 (( 和))配对使用可以进行分组,
  System.out.println("找出所有的日期字符串的月份");
  cycleMatch("July 11, 2003 bbb 423434dfg*fg October 22, 2004", "(([a-z]{1,10}))\\s[0-9]{1,2},[\\s]?[0-9]{4}",1);
  
  
  //找出所有的 t*n
  System.out.println("找出所有的 [aeion]{1,2}n");
  cycleMatch("tan ten tin tonn toon","t[aeion]{1,2}n",0);
  
  //找出所有的 t*n
  // .用于站位,想当于文件查找得?符号
  System.out.println("找出所有的 t*n");
  cycleMatch("tan ten tin,tonn toon","((t.n))[\\s,]?",1);
  
  //123-12-1234和123121234形式的社会安全号码
  System.out.println("123-12-1234和123121234形式的社会安全号码");
  cycleMatch("t199-12-1234n toon 122-80-7875 434338899","\\d{3}\\-?\\d{2}\\-?\\d{4}",0);
  //电话号码
  System.out.println("电话号码");
  cycleMatch("t023-67890221n toon023-88890221 4312906677","\\d{3}\\-?\\d{8}",0);
  
  //ip列表
  System.out.prin猀??獡????у耈ф?慰档????扩牥慮整?传??????????????????????????????????????????佄???偁??????????????侰?????????偁????????????楈敢湲瑡???????????????????佄??????????????????楈敢湲瑡?????????????????俄????扩牥慮整?????????????????????佄?溜????????????????楈敢湲瑡??????????????????????楈敢湲瑡??????????????????????????????????????????????????????????????????扩牥慮整?????????????楈敢湲瑡???????????????????????????????????????????????????????癡湩??????????????扩牥慮整????????楈敢湲瑡???????????????????扩牥慮整????????????????????????????????????????????扩牥慮整??????????????????????????????????????????????????????????溜??????????????楈敢湲瑡??????????????????扩牥慮整?????????六???????????????楈敢湲瑡???????????????????????????????????????????扩牥慮整???????????????????????????????????????????????????????????????扩牥慮整??????瑨灴?栯扩牥慮整昮湡慫?潣???????扩牥慮整???????????a??? tln("ip list --192.168.200.10,192.168.201.11获得ip列表");
  cycleMatch("ip list --192.168.200.10,192.168.211.51","\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}",0);
  
  }
  
  /***
  *
  * 获得年月日,
  * 例如 :June 26, 1951
  * */
  private void getDateString() {
  System.out.println("获得年月日 ,从dsds June 26, 1951 ksdjks 找出第一个日期");
  containMatch(" dsds June 26, 1951 ksdjks ",
  "[a-z]+\\s[0-9]{1,2},\\s[0-9]{4}");
  System.out.println("获得年月日 ,从June 16, 1959 asdsds June 11, 1911 ksdjks 找出第一个日期");
  containMatch("June 16, 1959 asdsds June 11, 1911 ksdjks ",
  "[\\s]?[a-z]+\\s[0-9]{1,2},\\s[0-9]{4}");
  }
  
  /***
  * 前缀方式的匹配
  * @param inputValue 被匹配查找得对想
  * @param reg 匹配规则
  * **/
  private void preMatch(String inputValue, String reg) {
  PatternCompiler compiler = new Perl5Compiler();
  PatternMatcher matcher = null;
  Pattern pattern = null;
  String input = inputValue;
  String regexp = reg;
  try {
  pattern = compiler.compile(regexp, Perl5Compiler.CASE_INSENSITIVE_MASK);
  matcher = new Perl5Matcher();
  if (matcher.matchesPrefix(input, pattern)) {
  MatchResult result = matcher.getMatch();
  System.out.println("result =" + result.group(0));
  //System.out.println("result ="+result.group(1));
  }
  }
  catch (MalformedPatternException e) {
  System.err.println("preMatch--Bad pattern.");
  System.err.println(e.getMessage());
  System.exit(1);
  }
  }
  
  /***
  * 包含方式的匹配
  * @param inputValue 被匹配查找得对想
  * @param reg 匹配规则
  * **/
  private void containMatch(String inputValue, String reg) {
  // System.out.println("containMatch----");
  PatternCompiler compiler = new Perl5Compiler();
  PatternMatcher matcher = null;
  Pattern pattern = null;
  String input = inputValue;
  String regexp = reg;
  try {
  pattern = compiler.compile(regexp, Perl5Compiler.CASE_INSENSITIVE_MASK);
  matcher = new Perl5Matcher();
  if (matcher.contains(input, pattern)) {
  MatchResult result = matcher.getMatch();
  System.out.println("result =" + result.group(0));
  // System.out.println("result ="+result.group(1));
  }
  }
  catch (MalformedPatternException e) {
  System.err.println("containMatch ---Bad pattern.");猀??獡????
  System.err.println(e.getMessage());
  System.exit(1);
  }
  }
  /***
  * 循环方式的匹配
  * 使用 (( 和))配对使用可以进行分组
  * @param inputValue 被匹配查找得对想
  * @param reg 匹配规则
  * **/
  private void cycleMatch(String inputValue, String reg,final int groupid){
  org.apache.oro.text.regex.PatternCompiler compile = new Perl5Compiler();
  try {
  Pattern p = compile.compile(reg,Perl5Compiler.CASE_INSENSITIVE_MASK);
  PatternMatcherInput input = new PatternMatcherInput(inputValue);
  org.apache.oro.text.regex.Perl5Matcher pm = new Perl5Matcher();
  MatchResult result =null;
  int i=0;
  while(pm.contains(input,p)){
  result = pm.getMatch();
  System.out.println("result =" + result.group(groupid));
  input.setBeginOffset(result.length());
  i++;
  }
  System.out.println("总共匹配"+i+"次");
  }
  catch (Exception ex) {
  System.err.println("循环方式的匹配发生错误"+ex.getMessage());
  }
  }
  
  public static void main(String[] args) {
  Jakarta_OROTest1 jakarta_OROTest11 = new Jakarta_OROTest1();
  }
  
  }