You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by ma...@apache.org on 2014/06/17 16:23:49 UTC
svn commit: r1603185 - in /nutch/trunk: CHANGES.txt
src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
Author: markus
Date: Tue Jun 17 14:23:49 2014
New Revision: 1603185
URL: http://svn.apache.org/r1603185
Log:
NUTCH-1794 IndexingFilterChecker to optionally dumpText
Modified:
nutch/trunk/CHANGES.txt
nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
Modified: nutch/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1603185&r1=1603184&r2=1603185&view=diff
==============================================================================
--- nutch/trunk/CHANGES.txt (original)
+++ nutch/trunk/CHANGES.txt Tue Jun 17 14:23:49 2014
@@ -2,6 +2,8 @@ Nutch Change Log
Nutch Current Development
+* NUTCH-1794 IndexingFilterChecker to optionally dumpText (markus)
+
* NUTCH-1590 [SECURITY] Frame injection vulnerability in published Javadoc (jnioche)
* NUTCH-1793 HttpRobotRulesParser not configured properly (jnioche)
Modified: nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java?rev=1603185&r1=1603184&r2=1603185&view=diff
==============================================================================
--- nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java (original)
+++ nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java Tue Jun 17 14:23:49 2014
@@ -63,15 +63,25 @@ public class IndexingFiltersChecker exte
public int run(String[] args) throws Exception {
String contentType = null;
String url = null;
+ boolean dumpText = false;
- String usage = "Usage: IndexingFiltersChecker <url>";
+ String usage = "Usage: IndexingFiltersChecker [-dumpText] <url>";
- if (args.length != 1) {
+ if (args.length == 0) {
System.err.println(usage);
return -1;
}
- url = URLUtil.toASCII(args[0]);
+ for (int i = 0; i < args.length; i++) {
+ if (args[i].equals("-dumpText")) {
+ dumpText = true;
+ } else if (i != args.length - 1) {
+ System.err.println(usage);
+ System.exit(-1);
+ } else {
+ url = URLUtil.toASCII(args[i]);
+ }
+ }
if (LOG.isInfoEnabled()) {
LOG.info("fetching: " + url);
@@ -148,7 +158,7 @@ public class IndexingFiltersChecker exte
if (values != null) {
for (Object value : values) {
String str = value.toString();
- int minText = Math.min(100, str.length());
+ int minText = dumpText ? str.length() : Math.min(100, str.length());
System.out.println(fname + " :\t" + str.substring(0, minText));
}
}