This is an automated email from the ASF dual-hosted git repository. snagel pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/nutch.git
commit bcf64cec92340d7a74cfb02f7ce36de5228034ce Merge: 7cb7abd 133c8dd Author: Sebastian Nagel <[email protected]> AuthorDate: Tue Mar 27 16:40:44 2018 +0200 Merge pull request #303 from sju/NUTCH-2543 fix for NUTCH-2543 contributed by Jurian Broertjes src/java/org/apache/nutch/crawl/CrawlDbReader.java | 43 +++++++++++--- src/java/org/apache/nutch/crawl/LinkDbReader.java | 65 ++++++++++++++-------- .../org/apache/nutch/util/AbstractChecker.java | 48 +++++++++------- 3 files changed, 107 insertions(+), 49 deletions(-) diff --cc src/java/org/apache/nutch/crawl/LinkDbReader.java index bf537b7,f5daf4d..8efaf0a --- a/src/java/org/apache/nutch/crawl/LinkDbReader.java +++ b/src/java/org/apache/nutch/crawl/LinkDbReader.java @@@ -43,11 -40,10 +43,12 @@@ import org.apache.hadoop.mapreduce.lib. import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.mapreduce.Partitioner; import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner; -import org.apache.hadoop.util.*; +import org.apache.hadoop.util.StringUtils; +import org.apache.hadoop.util.Tool; +import org.apache.hadoop.util.ToolRunner; import org.apache.hadoop.conf.Configuration; + import org.apache.nutch.util.AbstractChecker; import org.apache.nutch.util.NutchConfiguration; import org.apache.nutch.util.NutchJob; import org.apache.nutch.util.TimingUtil; @@@ -172,10 -168,25 +173,25 @@@ public class LinkDbReader extends Abstr } long end = System.currentTimeMillis(); - LOG.info("LinkDb dump: finished at " + sdf.format(end) + ", elapsed: " - + TimingUtil.elapsedTime(start, end)); + LOG.info("LinkDb dump: finished at {}, elapsed: {}", + sdf.format(end), TimingUtil.elapsedTime(start, end)); } + protected int process(String line, StringBuilder output) throws Exception { + + Inlinks links = getInlinks(new Text(line)); + if (links == null) { + output.append(" - no link information."); + } else { + Iterator<Inlink> it = links.iterator(); + while (it.hasNext()) { + output.append(it.next().toString()); + } + } + output.append("\n"); + return 0; + } + public static void main(String[] args) throws Exception { int res = ToolRunner.run(NutchConfiguration.create(), new LinkDbReader(), args); -- To stop receiving notification emails like this one, please contact [email protected].
