Java Code Examples for org.apache.oro.text.regex.PatternMatcher#contains()

/** 
 * 字符串下标 regx在src中首次出现的位置 
 * @param src     src
 * @param regx    regx
 * @param begin   有效开始位置 
 * @return return
 */ 
public static int indexOf(String src, String regx, int begin){ 
	int idx = -1; 
	try{ 
		PatternCompiler patternCompiler = new Perl5Compiler(); 
		Pattern pattern = patternCompiler.compile(regx, Perl5Compiler.CASE_INSENSITIVE_MASK); 
		PatternMatcher matcher = new Perl5Matcher(); 
		PatternMatcherInput input = new PatternMatcherInput(src); 
		 
		while(matcher.contains(input, pattern)){ 
			MatchResult matchResult = matcher.getMatch(); 
			int tmp = matchResult.beginOffset(0); 
			if(tmp >= begin){//匹配位置从begin开始 
				idx = tmp; 
				break; 
			} 
		} 
	}catch(Exception e){
		log.error("[提取异常][src:{}][regx:{}]", src, regx); 
		e.printStackTrace();
	} 
	return idx; 
}
 

/** 
 * 提取子串 
 * @param src	输入字符串  src	输入字符串
 * @param regx	表达式  regx	表达式
 * @return return
 */ 
public List<List<String>> fetchs(String src, String regx){ 
	List<List<String>> list = new ArrayList<List<String>>(); 
	try{ 
		Pattern pattern = patternCompiler.compile(regx, Perl5Compiler.CASE_INSENSITIVE_MASK); 
		PatternMatcher matcher = new Perl5Matcher(); 
		PatternMatcherInput input = new PatternMatcherInput(src); 
		while(matcher.contains(input, pattern)){ 
			MatchResult matchResult = matcher.getMatch(); 
			int groups = matchResult.groups(); 
			List<String> item = new ArrayList<String>(); 
			for(int i=0; i<groups; i++){ 
				item.add(matchResult.group(i)); 
			} 
			list.add(item); 
		} 
	}catch(Exception e){ 
		log.error("[提取异常][src:{}][reg:{}]", src, regx);
		if(ConfigTable.isDebug() && log.isWarnEnabled()){
			e.printStackTrace();
		} 
	} 
	return list; 
}
 

/** 
 * 提取子串 
 * @param src		输入字符串  src		输入字符串
 * @param regx		表达式  regx		表达式
 * @param idx		指定提取位置  idx		指定提取位置
 * @return return
 */ 
public List<String> fetch(String src, String regx, int idx) throws Exception{ 
	List<String> list = new ArrayList<String>(); 
	 
	try{ 
		Pattern pattern = patternCompiler.compile(regx, Perl5Compiler.CASE_INSENSITIVE_MASK); 
		PatternMatcher matcher = new Perl5Matcher(); 
		PatternMatcherInput input = new PatternMatcherInput(src); 
		 
		while(matcher.contains(input, pattern)){ 
			MatchResult matchResult = matcher.getMatch(); 
			list.add(matchResult.group(idx)); 
		} 
	}catch(Exception e){
		log.error("[提取异常][src:{}][reg:{}]", src, regx);
		if(ConfigTable.isDebug() && log.isWarnEnabled()){
			e.printStackTrace();
		} 
		throw e; 
	} 
	return list; 
}
 

/** 
 * 提取子串 
 * @param src	输入字符串  src	输入字符串
 * @param regx	表达式  regx	表达式
 * @return return
 */ 
public List<List<String>> fetchs(String src, String regx){ 
	List<List<String>> list = new ArrayList<List<String>>(); 
	try{ 
		Pattern pattern = patternCompiler.compile(regx, Perl5Compiler.CASE_INSENSITIVE_MASK); 
		PatternMatcher matcher = new Perl5Matcher(); 
		PatternMatcherInput input = new PatternMatcherInput(src); 
		while(matcher.contains(input, pattern)){ 
			MatchResult matchResult = matcher.getMatch(); 
			int groups = matchResult.groups(); 
			List<String> item = new ArrayList<String>(); 
			for(int i=0; i<groups; i++){ 
				item.add(matchResult.group(i)); 
			} 
			list.add(item); 
		} 
	}catch(Exception e){
		log.error("[提取异常][src:{}][reg:{}]", src, regx);
		e.printStackTrace(); 
	} 
	return list; 
}
 

/** 
 * 提取子串 
 * @param src		输入字符串  src		输入字符串
 * @param regx		表达式  regx		表达式
 * @param idx		指定提取位置  idx		指定提取位置
 * @return return
 */ 
public List<String> fetch(String src, String regx, int idx) throws Exception{ 
	List<String> list = new ArrayList<String>(); 
	 
	try{ 
		Pattern pattern = patternCompiler.compile(regx, Perl5Compiler.CASE_INSENSITIVE_MASK); 
		PatternMatcher matcher = new Perl5Matcher(); 
		PatternMatcherInput input = new PatternMatcherInput(src); 
		 
		while(matcher.contains(input, pattern)){ 
			MatchResult matchResult = matcher.getMatch(); 
			list.add(matchResult.group(idx)); 
		} 
	}catch(Exception e){ 
		log.error("[提取异常][src:{}][reg:{}]", src, regx);
		e.printStackTrace(); 
		throw e; 
	} 
	return list; 
}
 

/** 
 * 配置状态 
 * @param src  src
 * @param regx  regx
 * @return return
 */ 
public boolean match(String src, String regx){ 
	boolean result = false; 
	try{ 
		Pattern pattern = patternCompiler.compile(regx, Perl5Compiler.CASE_INSENSITIVE_MASK); 
		PatternMatcher matcher = new Perl5Matcher(); 
		result = matcher.contains(src, pattern); 
	}catch(Exception e){ 
		result = false;
		if(ConfigTable.isDebug() && log.isWarnEnabled()){
			e.printStackTrace();
		} 
	} 
	return result; 
}
 

/** 
 * 匹配状态 
 * @param src  src
 * @param regx 表达式
 * @return return
 */ 
public boolean match(String src, String regx){ 
	boolean result = false; 
	try{ 
		Pattern pattern = patternCompiler.compile(regx, Perl5Compiler.CASE_INSENSITIVE_MASK); 
		PatternMatcher matcher = new Perl5Matcher(); 
		result = matcher.contains(src, pattern); 
	}catch(Exception e){ 
		result = false; 
	} 
	return result; 
}
 

/**
 * checks, if the current request comes from a searchbot
 *
 * @param request
 * @return whether the request is from a web searchbot
 */
public static boolean checkURLforSpiders(HttpServletRequest request) {
    boolean result = false;

    String spiderRequest = (String) request.getAttribute("_REQUEST_FROM_SPIDER_");
    if (UtilValidate.isNotEmpty(spiderRequest)) {
        if ("Y".equals(spiderRequest)) {
            return true;
        }
        return false;
    }
    String initialUserAgent = request.getHeader("User-Agent") != null ? request.getHeader("User-Agent") : "";
    List<String> spiderList = StringUtil.split(UtilProperties.getPropertyValue("url", "link.remove_lsessionid.user_agent_list"), ",");

    if (UtilValidate.isNotEmpty(spiderList)) {
        for (String spiderNameElement : spiderList) {
            Pattern pattern = null;
            try {
                pattern = PatternFactory.createOrGetPerl5CompiledPattern(spiderNameElement, false);
            } catch (MalformedPatternException e) {
                Debug.logError(e, module);
            }
            PatternMatcher matcher = new Perl5Matcher();
            if (matcher.contains(initialUserAgent, pattern)) {
                request.setAttribute("_REQUEST_FROM_SPIDER_", "Y");
                result = true;
                break;
            }
        }
    }

    if (!result) {
        request.setAttribute("_REQUEST_FROM_SPIDER_", "N");
    }

    return result;
}
 

public String findFirst(String originalStr, String regex) {
    if (StringUtils.isBlank(originalStr) || StringUtils.isBlank(regex)) {
        return StringUtils.EMPTY;
    }

    PatternMatcher matcher = new Perl5Matcher();
    if (matcher.contains(originalStr, patterns.get(regex))) {
        return StringUtils.trimToEmpty(matcher.getMatch().group(0));
    }
    return StringUtils.EMPTY;
}
 

public void run(int loop) {
    PatternMatcher matcher = new Perl5Matcher();

    for (int i = 0; i < loop; i++) {
        for (Pattern pattern : patterns) {
            for (String value : data) {
                matcher.contains(value, pattern);
            }
        }
    }
}
 

public void warmUp() {
    PatternMatcher matcher = new Perl5Matcher();
    int matchedCount = 0;

    for (Pattern pattern : patterns) {
        for (String value : data) {
            if (matcher.contains(value, pattern)) {
                matchedCount++;
            }
        }
    }

    assertEquals(RegexpStressTest.this.matchedCount, matchedCount);
}
 

/**
 * Extracts <code>Outlink</code> from given plain text and adds anchor
 * to the extracted <code>Outlink</code>s
 * 
 * @param plainText the plain text from wich URLs should be extracted.
 * @param anchor    the anchor of the url
 * 
 * @return Array of <code>Outlink</code>s within found in plainText
 */
public static Outlink[] getOutlinks(final String plainText, String anchor, Configuration conf) {
  long start = System.currentTimeMillis();
  final List<Outlink> outlinks = new ArrayList<Outlink>();

  try {
    final PatternCompiler cp = new Perl5Compiler();
    final Pattern pattern = cp.compile(URL_PATTERN,
        Perl5Compiler.CASE_INSENSITIVE_MASK | Perl5Compiler.READ_ONLY_MASK
            | Perl5Compiler.MULTILINE_MASK);
    final PatternMatcher matcher = new Perl5Matcher();

    final PatternMatcherInput input = new PatternMatcherInput(plainText);

    MatchResult result;
    String url;

    //loop the matches
    while (matcher.contains(input, pattern)) {
      // if this is taking too long, stop matching
      //   (SHOULD really check cpu time used so that heavily loaded systems
      //   do not unnecessarily hit this limit.)
      if (System.currentTimeMillis() - start >= 60000L) {
        if (LOG.isWarnEnabled()) {
          LOG.warn("Time limit exceeded for getOutLinks");
        }
        break;
      }
      result = matcher.getMatch();
      url = result.group(0);
      try {
        outlinks.add(new Outlink(url, anchor));
      } catch (MalformedURLException mue) {
        LOG.warn("Invalid url: '" + url + "', skipping.");
      }
    }
  } catch (Exception ex) {
    // if the matcher fails (perhaps a malformed URL) we just log it and move on
    if (LOG.isErrorEnabled()) { LOG.error("getOutlinks", ex); }
  }

  final Outlink[] retval;

  //create array of the Outlinks
  if (outlinks != null && outlinks.size() > 0) {
    retval = outlinks.toArray(new Outlink[0]);
  } else {
    retval = new Outlink[0];
  }

  return retval;
}
 

public cfData execute(cfSession _session, cfArgStructData argStruct ) throws cfmRunTimeException {
	String regexp = getNamedStringParam(argStruct, "regular", "");
	String strToSearch = getNamedStringParam(argStruct, "string", "");
	boolean bUnique = getNamedBooleanParam(argStruct, "unique",false);
	
	HashSet<String>	uniqueTrack = null;
	if ( bUnique ){
		uniqueTrack	= new HashSet<String>();
	}


	/* Setup the RegEx */
	PatternCompiler compiler = new Perl5Compiler();
	Pattern pattern;
	
	try {
		if (caseSensitiveMatch) {
			pattern = compiler.compile(regexp, Perl5Compiler.SINGLELINE_MASK);
		} else {
			pattern = compiler.compile(regexp, Perl5Compiler.CASE_INSENSITIVE_MASK | Perl5Compiler.SINGLELINE_MASK);
		}
	} catch (MalformedPatternException e) {
		cfCatchData catchD = new cfCatchData();
		catchD.setType("Function");
		catchD.setMessage("REMatch - invalid parameter");
		catchD.setDetail("Invalid regular expression ( " + regexp + " )");
		throw new cfmRunTimeException(catchD);
	}

	/* Perform the search */
	cfArrayData	array	= cfArrayData.createArray(1);
	PatternMatcher matcher = new Perl5Matcher();
	MatchResult result;
	PatternMatcherInput input = new PatternMatcherInput( strToSearch );
	while ( matcher.contains(input, pattern) ) {
		result = matcher.getMatch();
		
		String strResult = result.toString();
		if ( bUnique ){
			if ( !uniqueTrack.contains( strResult ) ){
				array.addElement( new cfStringData( strResult ) );
				uniqueTrack.add( strResult );
			}
		}else		
			array.addElement( new cfStringData( strResult ) );
	}
	
	return array;
}
 

/**
 * Extracts <code>Outlink</code> from given plain text and adds anchor
 * to the extracted <code>Outlink</code>s
 * 
 * @param plainText the plain text from wich URLs should be extracted.
 * @param anchor    the anchor of the url
 * 
 * @return Array of <code>Outlink</code>s within found in plainText
 */
public static Outlink[] getOutlinks(final String plainText, String anchor, Configuration conf) {
  long start = System.currentTimeMillis();
  final List<Outlink> outlinks = new ArrayList<Outlink>();

  try {
    final PatternCompiler cp = new Perl5Compiler();
    final Pattern pattern = cp.compile(URL_PATTERN,
        Perl5Compiler.CASE_INSENSITIVE_MASK | Perl5Compiler.READ_ONLY_MASK
            | Perl5Compiler.MULTILINE_MASK);
    final PatternMatcher matcher = new Perl5Matcher();

    final PatternMatcherInput input = new PatternMatcherInput(plainText);

    MatchResult result;
    String url;

    //loop the matches
    while (matcher.contains(input, pattern)) {
      // if this is taking too long, stop matching
      //   (SHOULD really check cpu time used so that heavily loaded systems
      //   do not unnecessarily hit this limit.)
      if (System.currentTimeMillis() - start >= 60000L) {
        if (LOG.isWarnEnabled()) {
          LOG.warn("Time limit exceeded for getOutLinks");
        }
        break;
      }
      result = matcher.getMatch();
      url = result.group(0);
      try {
        outlinks.add(new Outlink(url, anchor));
      } catch (MalformedURLException mue) {
        LOG.warn("Invalid url: '" + url + "', skipping.");
      }
    }
  } catch (Exception ex) {
    // if the matcher fails (perhaps a malformed URL) we just log it and move on
    if (LOG.isErrorEnabled()) { LOG.error("getOutlinks", ex); }
  }

  final Outlink[] retval;

  //create array of the Outlinks
  if (outlinks != null && outlinks.size() > 0) {
    retval = outlinks.toArray(new Outlink[0]);
  } else {
    retval = new Outlink[0];
  }

  return retval;
}