Index: src/java/org/apache/nutch/parse/OutlinkExtractor.java
===================================================================
--- src/java/org/apache/nutch/parse/OutlinkExtractor.java	(revision 1721613)
+++ src/java/org/apache/nutch/parse/OutlinkExtractor.java	(working copy)
@@ -20,19 +20,14 @@
 import java.net.MalformedURLException;
 import java.util.ArrayList;
 import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 
+import org.apache.hadoop.conf.Configuration;
+
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
-import org.apache.hadoop.conf.Configuration;
-import org.apache.oro.text.regex.MatchResult;
-import org.apache.oro.text.regex.Pattern;
-import org.apache.oro.text.regex.PatternCompiler;
-import org.apache.oro.text.regex.PatternMatcher;
-import org.apache.oro.text.regex.PatternMatcherInput;
-import org.apache.oro.text.regex.Perl5Compiler;
-import org.apache.oro.text.regex.Perl5Matcher;
-
 /**
  * Extractor to extract {@link org.apache.nutch.parse.Outlink}s / URLs from
  * plain text using Regular Expressions.
@@ -59,7 +54,7 @@
 
    *      </a>
    */
-  private static final String URL_PATTERN = "([A-Za-z][A-Za-z0-9+.-]{1,120}:[A-Za-z0-9/](([A-Za-z0-9$_.+!*,;/?:@&~=-])|%[A-Fa-f0-9]{2}){1,333}(#([a-zA-Z0-9][a-zA-Z0-9$_.+!*,;/?:@&~=%-]{0,1000}))?)";
+  private static final Pattern URL_PATTERN = Pattern.compile("([A-Za-z][A-Za-z0-9+.-]{1,120}:[A-Za-z0-9/](([A-Za-z0-9$_.+!*,;/?:@&~=-])|%[A-Fa-f0-9]{2}){1,333}(#([a-zA-Z0-9][a-zA-Z0-9$_.+!*,;/?:@&~=%-]{0,1000}))?)");
 
   /**
    * Extracts <code>Outlink</code> from given plain text. Applying this method
@@ -92,19 +87,12 @@
     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;
+      Matcher matcher = URL_PATTERN.matcher(plainText);
+      int pos = 0;
       String url;
 
-      // loop the matches
-      while (matcher.contains(input, pattern)) {
+      // Check for stuff!
+      while (matcher.find(pos)) {
         // 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.)
@@ -114,8 +102,11 @@
           }
           break;
         }
-        result = matcher.getMatch();
-        url = result.group(0);
+        
+        pos = matcher.start();
+        url = matcher.group().trim();
+        pos++;
+        
         try {
           outlinks.add(new Outlink(url, anchor));
         } catch (MalformedURLException mue) {
Index: src/plugin/parse-js/src/java/org/apache/nutch/parse/js/JSParseFilter.java
===================================================================
--- src/plugin/parse-js/src/java/org/apache/nutch/parse/js/JSParseFilter.java	(revision 1721613)
+++ src/plugin/parse-js/src/java/org/apache/nutch/parse/js/JSParseFilter.java	(working copy)
@@ -25,10 +25,9 @@
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
-
 import org.apache.nutch.parse.HTMLMetaTags;
 import org.apache.nutch.parse.HtmlParseFilter;
 import org.apache.nutch.parse.Outlink;
@@ -42,13 +41,6 @@
 import org.apache.nutch.protocol.Content;
 import org.apache.nutch.util.NutchConfiguration;
 import org.apache.hadoop.conf.Configuration;
-import org.apache.oro.text.regex.MatchResult;
-import org.apache.oro.text.regex.Pattern;
-import org.apache.oro.text.regex.PatternCompiler;
-import org.apache.oro.text.regex.PatternMatcher;
-import org.apache.oro.text.regex.PatternMatcherInput;
-import org.apache.oro.text.regex.Perl5Compiler;
-import org.apache.oro.text.regex.Perl5Matcher;
 import org.w3c.dom.DocumentFragment;
 import org.w3c.dom.Element;
 import org.w3c.dom.NamedNodeMap;
@@ -55,6 +47,9 @@
 import org.w3c.dom.Node;
 import org.w3c.dom.NodeList;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 /**
  * This class is a heuristic link extractor for JavaScript files and code
  * snippets. The general idea of a two-pass regex matching comes from Heritrix.
@@ -179,9 +174,9 @@
     return ParseResult.createParseResult(c.getUrl(), new ParseImpl(script, pd));
   }
 
-  private static final String STRING_PATTERN = "(\\\\*(?:\"|\'))([^\\s\"\']+?)(?:\\1)";
+  private static final Pattern STRING_PATTERN = Pattern.compile("(\\\\*(?:\"|\'))([^\\s\"\']+?)(?:\\1)");
   // A simple pattern. This allows also invalid URL characters.
-  private static final String URI_PATTERN = "(^|\\s*?)/?\\S+?[/\\.]\\S+($|\\s*)";
+  private static final Pattern URI_PATTERN = Pattern.compile("(^|\\s*?)/?\\S+?[/\\.]\\S+($|\\s*)");
 
   // Alternative pattern, which limits valid url characters.
   // private static final String URI_PATTERN =