Author: siren
Date: Sat Mar 10 09:30:04 2007
New Revision: 516754
URL: http://svn.apache.org/viewvc?view=rev&rev=516754
Log:
Change OutlinkExtractor to use Regular Expressions from JRE, get rid of ORO
dependency
Removed:
lucene/nutch/trunk/lib/jakarta-oro-2.0.7.jar
Modified:
lucene/nutch/trunk/CHANGES.txt
lucene/nutch/trunk/src/java/org/apache/nutch/parse/OutlinkExtractor.java
Modified: lucene/nutch/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/lucene/nutch/trunk/CHANGES.txt?view=diff&rev=516754&r1=516753&r2=516754
==============================================================================
--- lucene/nutch/trunk/CHANGES.txt (original)
+++ lucene/nutch/trunk/CHANGES.txt Sat Mar 10 09:30:04 2007
@@ -158,6 +158,9 @@
53. NUTCH-384 - Protocol-file plugin does not allow the parse plugins
framework to operate properly (Heiko Dietze via mattmann)
+54. Change OutlinkExtractor to use Regular Expressions from JRE, get rid
+ of ORO dependency (siren)
+
Release 0.8 - 2006-07-25
Modified:
lucene/nutch/trunk/src/java/org/apache/nutch/parse/OutlinkExtractor.java
URL:
http://svn.apache.org/viewvc/lucene/nutch/trunk/src/java/org/apache/nutch/parse/OutlinkExtractor.java?view=diff&rev=516754&r1=516753&r2=516754
==============================================================================
--- lucene/nutch/trunk/src/java/org/apache/nutch/parse/OutlinkExtractor.java
(original)
+++ lucene/nutch/trunk/src/java/org/apache/nutch/parse/OutlinkExtractor.java
Sat Mar 10 09:30:04 2007
@@ -1,4 +1,4 @@
-/**
+/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
@@ -14,28 +14,21 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-
package org.apache.nutch.parse;
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.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
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 [EMAIL PROTECTED] org.apache.nutch.parse.Outlink}s
- * / URLs from plain text using Regular Expressions.
+ * Extractor to extract [EMAIL PROTECTED] org.apache.nutch.parse.Outlink}s /
URLs from
+ * plain text using Regular Expressions.
*
* @see <a
*
href="http://wiki.java.net/bin/view/Javapedia/RegularExpressions";>Comparison
@@ -44,12 +37,14 @@
* </a>
*
* @author Stephan Strittmatter - http://www.sybit.de
- * @version 1.0
+ *
* @since 0.7
*/
public class OutlinkExtractor {
private static final Log LOG = LogFactory.getLog(OutlinkExtractor.class);
+ private static final Outlink[] NO_LINKS = new Outlink[0];
+
/**
* Regex pattern to get URLs within a plain text.
*
@@ -57,190 +52,63 @@
*
href="http://www.truerwords.net/articles/ut/urlactivation.html";>http://www.truerwords.net/articles/ut/urlactivation.html
* </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 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}))?)";
+
+ static final Pattern urlPattern = Pattern.compile(URL_PATTERN);
/**
- * Extracts <code>Outlink</code> from given plain text.
- * Applying this method to non-plain-text can result in extremely lengthy
- * runtimes for parasitic cases (postscript is a known example).
- * @param plainText the plain text from wich URLs should be extracted.
+ * Extracts outlinks from a plain text.
+ * </p>
+ * @param plainText
*
- * @return Array of <code>Outlink</code>s within found in plainText
+ * @return Array of <code>Outlink</code> s within found in plainText
*/
- public static Outlink[] getOutlinks(final String plainText, Configuration
conf) {
- return OutlinkExtractor.getOutlinks(plainText, "", conf);
+ public static Outlink[] getOutlinks(final String plainText, Configuration
conf){
+ return getOutlinks(plainText, null, conf);
}
+
/**
- * 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
+ * Extracts outlinks from a plain text.
+ * </p>
+ * @param plainText text to extract urls from
*
- * @return Array of <code>Outlink</code>s within found in plainText
+ * @return Array of <code>Outlink</code> s found in plainText
*/
- public static Outlink[] getOutlinks(final String plainText, String anchor,
Configuration conf) {
- long start = System.currentTimeMillis();
- final List outlinks = new ArrayList();
-
- 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 {
- Outlink outlink = new Outlink(url, anchor, conf);
- outlinks.add(new Outlink(url, anchor, conf));
- } catch (MalformedURLException mue) {
- LOG.warn("Invalid url: '" + url + "', skipping.");
+ public static Outlink[] getOutlinks(final String plainText, String anchor,
+ Configuration conf) {
+
+ if(plainText == null){
+ return NO_LINKS;
+ }
+
+ final ArrayList<Outlink> outlinks = new ArrayList<Outlink>();
+ Outlink[] retval;
+ Outlink link;
+
+ Matcher m = urlPattern.matcher(plainText);
+ while (m.find()) {
+
+ try {
+ link = new Outlink(m.toMatchResult().group(), anchor, conf);
+ outlinks.add(link);
+ } catch (MalformedURLException ex) {
+ // if it is a malformed URL we just throw it away and continue with
+ // extraction.
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("extracted malformed url:" + m.toMatchResult().group(),
ex);
}
}
- } 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 = (Outlink[]) outlinks.toArray(new Outlink[0]);
+ if (outlinks.size() > 0) {
+ retval = outlinks.toArray(new Outlink[outlinks.size()]);
} else {
- retval = new Outlink[0];
+ retval = NO_LINKS;
}
return retval;
}
-
- /**
- * Extracts outlinks from a plain text. <br />
- * This Method takes the Jakarta Regexp API.
- *
- * @param plainText
- *
- * @return Array of <code>Outlink</code> s within found in plainText
- * @deprecated only for tests
- */
- private Outlink[] getOutlinksJakartaRegexpImpl(final String plainText) {
-
- throw new UnsupportedOperationException(
- "Implementation commented out. Please uncomment to use it.");
-
- // final List outlinks = new ArrayList();
- // String url;
- // Outlink link;
- //
- // RE re = new RE(URL_PATTERN);
- //
- // int pos = 0;
- //
- // while (re.match(plainText, pos)) {
- //
- // url = re.getParen(0);
- //
- // if (LOG.isTraceEnabled()) {
- // LOG.trace("Extracted url: " + url);
- // }
- //
- // try {
- //
- // link = new Outlink(url, null);
- // outlinks.add(link);
- //
- // } catch (MalformedURLException ex) {
- // // if it is a malformed URL we just throw it away and continue with
- // // extraction.
- // if (LOG.isErrorEnabled()) { LOG.error("getOutlinks", ex); }
- // }
- //
- // pos = re.getParenEnd(0);
- // }
- //
- // final Outlink[] retval;
- //
- // if (pos > 0) {
- // retval = (Outlink[]) outlinks.toArray(new Outlink[0]);
- // } else {
- // retval = new Outlink[0];
- // }
- //
- // return retval;
-
- }
-
- /**
- * Extracts outlinks from a plain text.
- * </p>
- * This Method takes the JDK5 Regexp API.
- *
- * @param plainText
- *
- * @return Array of <code>Outlink</code> s within found in plainText
- * @deprecated only for tests
- */
- private Outlink[] getOutlinksJDK5Impl(final String plainText) {
-
- throw new UnsupportedOperationException(
- "Implementation commented out. Please uncomment to use it.");
-
- // final List outlinks = new ArrayList();
- // String url;
- // Outlink link;
- //
- // final Pattern urlPattern = Pattern.compile(URL_PATTERN);
- // final RE re = new RE(urlPattern);
- //
- // int pos = 0;
- //
- // while (re.match(plainText, pos)) {
- //
- // url = re.getParen(0);
- //
- // try {
- //
- // link = new Outlink(url, null);
- // outlinks.add(link);
- // } catch (MalformedURLException ex) {
- // // if it is a malformed URL we just throw it away and continue with
- // // extraction.
- // if (LOG.isErrorEnabled()) { LOG.error("getOutlinks", ex); }
- // }
- //
- // pos = re.getParenEnd(0);
- // }
- //
- // final Outlink[] retval;
- //
- // if (pos > 0) {
- // retval = (Outlink[]) outlinks.toArray(new Outlink[0]);
- // } else {
- // retval = new Outlink[0];
- // }
- //
- // return retval;
- }
-
}
-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys-and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
Nutch-cvs mailing list
Nutch-cvs@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nutch-cvs
