[ 
https://issues.apache.org/jira/browse/NUTCH-2533?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16435128#comment-16435128
 ] 

ASF GitHub Bot commented on NUTCH-2533:
---------------------------------------

sebastian-nagel closed pull request #312: NUTCH-2533 Injector: 
NullPointerException if seed URL dir contains non-file entries
URL: https://github.com/apache/nutch/pull/312
 
 
   

This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:

As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):

diff --git a/src/java/org/apache/nutch/crawl/InjectorJob.java 
b/src/java/org/apache/nutch/crawl/InjectorJob.java
index 1f9747f63..0b9d81220 100644
--- a/src/java/org/apache/nutch/crawl/InjectorJob.java
+++ b/src/java/org/apache/nutch/crawl/InjectorJob.java
@@ -21,6 +21,7 @@
 import org.apache.gora.persistency.Persistent;
 import org.apache.gora.store.DataStore;
 import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileStatus;
 import org.apache.hadoop.fs.Path;
 import org.apache.hadoop.io.LongWritable;
 import org.apache.hadoop.io.Text;
@@ -227,7 +228,22 @@ public InjectorJob(Configuration conf) {
     numJobs = 1;
     currentJobNum = 0;
     currentJob = NutchJob.getInstance(getConf(), "inject " + input);
-    FileInputFormat.addInputPath(currentJob, input);
+    FileStatus[] seedFiles = input.getFileSystem(getConf()).listStatus(input);
+    int numSeedFiles = 0;
+    for (FileStatus seedFile : seedFiles) {
+      if (seedFile.isFile()) {
+        FileInputFormat.addInputPath(currentJob, seedFile.getPath());
+        numSeedFiles++;
+        LOG.info("Injecting seed URL file {}", seedFile.getPath());
+      } else {
+        LOG.warn("Skipped non-file input in {}: {}", input,
+            seedFile.getPath());
+      }
+    }
+    if (numSeedFiles == 0) {
+      LOG.error("No seed files to inject found in {}", input);
+      return results;
+    }
     currentJob.setMapperClass(UrlMapper.class);
     currentJob.setMapOutputKeyClass(String.class);
     currentJob.setMapOutputValueClass(WebPage.class);


 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


> Injector: NullPointerException if seed URL dir contains non-file entries
> ------------------------------------------------------------------------
>
>                 Key: NUTCH-2533
>                 URL: https://issues.apache.org/jira/browse/NUTCH-2533
>             Project: Nutch
>          Issue Type: Bug
>          Components: injector
>    Affects Versions: 2.3.1, 1.14
>            Reporter: Krzysztof Madejski
>            Assignee: Sebastian Nagel
>            Priority: Minor
>             Fix For: 2.4, 1.15
>
>
> I'm following https://wiki.apache.org/nutch/Nutch2Tutorial
>  
> I've run `./nutch inject /` and I've got the following error:
> {noformat}
> InjectorJob: starting at 2018-03-12 11:59:05
> InjectorJob: Injecting urlDir: /
> InjectorJob: Using class org.apache.gora.hbase.store.HBaseStore as the Gora 
> storage class.
> InjectorJob: java.lang.NullPointerException
> at 
> org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getBlockIndex(FileInputFormat.java:442)
> at 
> org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:411)
> at 
> org.apache.hadoop.mapreduce.JobSubmitter.writeNewSplits(JobSubmitter.java:493)
> at org.apache.hadoop.mapreduce.JobSubmitter.writeSplits(JobSubmitter.java:510)
> at 
> org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:394)
> at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1285)
> at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1282)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at 
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1614)
> at org.apache.hadoop.mapreduce.Job.submit(Job.java:1282)
> at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1303)
> at org.apache.nutch.util.NutchJob.waitForCompletion(NutchJob.java:115)
> at org.apache.nutch.crawl.InjectorJob.run(InjectorJob.java:231)
> at org.apache.nutch.crawl.InjectorJob.inject(InjectorJob.java:252)
> at org.apache.nutch.crawl.InjectorJob.run(InjectorJob.java:275)
> at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:70){noformat}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Reply via email to