Author: jnioche
Date: Fri Aug 23 08:52:38 2013
New Revision: 1516752
URL: http://svn.apache.org/r1516752
Log:
NUTCH-1629 Injector skips empty lines
Modified:
nutch/branches/2.x/CHANGES.txt
nutch/branches/2.x/src/java/org/apache/nutch/crawl/InjectorJob.java
Modified: nutch/branches/2.x/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/branches/2.x/CHANGES.txt?rev=1516752&r1=1516751&r2=1516752&view=diff
==============================================================================
--- nutch/branches/2.x/CHANGES.txt (original)
+++ nutch/branches/2.x/CHANGES.txt Fri Aug 23 08:52:38 2013
@@ -2,6 +2,8 @@ Nutch Change Log
Current Development
+* NUTCH-1629 Injector skips empty lines in seed files (kaveh minooie via
jnioche)
+
* NUTCH-1624 Typo in WebTableReader line 486 (kaveh minooie via lewismc)
* NUTCH-1294 IndexClean job with solr implementation. (Dan Rosher, lewismc,
Claudiu Chis via feng)
Modified: nutch/branches/2.x/src/java/org/apache/nutch/crawl/InjectorJob.java
URL:
http://svn.apache.org/viewvc/nutch/branches/2.x/src/java/org/apache/nutch/crawl/InjectorJob.java?rev=1516752&r1=1516751&r2=1516752&view=diff
==============================================================================
--- nutch/branches/2.x/src/java/org/apache/nutch/crawl/InjectorJob.java
(original)
+++ nutch/branches/2.x/src/java/org/apache/nutch/crawl/InjectorJob.java Fri Aug
23 08:52:38 2013
@@ -110,9 +110,9 @@ public class InjectorJob extends NutchTo
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
- String url = value.toString(); // value is line of text
+ String url = value.toString().trim(); // value is line of text
- if (url != null && url.trim().startsWith("#")) {
+ if (url != null && ( url.length() == 0 || url.startsWith("#") ) ) {
/* Ignore line that start with # */
return;
}
