[prev in list] [next in list] [prev in thread] [next in thread]
List: nutch-cvs
Subject: [Nutch-cvs] svn commit: r240286 - in
From: cutting () apache ! org
Date: 2005-08-26 16:51:27
Message-ID: 20050826165128.46554.qmail () minotaur ! apache ! org
[Download RAW message or body]
Author: cutting
Date: Fri Aug 26 09:51:25 2005
New Revision: 240286
URL: http://svn.apache.org/viewcvs?rev=240286&view=rev
Log:
Add reporter to RecordWriter.close().
Modified:
lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/FetcherOutputFormat.java
lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/Indexer.java
lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/ParseOutputFormat.java
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/FetcherOutputFormat.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/FetcherOutputFormat.java?rev=240286&r1=240285&r2=240286&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/FetcherOutputFormat.java \
(original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/FetcherOutputFormat.java \
Fri Aug 26 09:51:25 2005 @@ -29,6 +29,7 @@
import org.apache.nutch.mapred.OutputFormat;
import org.apache.nutch.mapred.RecordWriter;
import org.apache.nutch.mapred.JobConf;
+import org.apache.nutch.mapred.Reporter;
import org.apache.nutch.protocol.Content;
@@ -79,13 +80,13 @@
}
- public void close() throws IOException {
+ public void close(Reporter reporter) throws IOException {
fetchOut.close();
if (contentOut != null) {
contentOut.close();
}
if (parseOut != null) {
- parseOut.close();
+ parseOut.close(reporter);
}
}
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/Indexer.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/Indexer.java?rev=240286&r1=240285&r2=240286&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/Indexer.java \
(original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/Indexer.java Fri Aug \
26 09:51:25 2005 @@ -89,18 +89,37 @@
writer.setSimilarity(new NutchSimilarity());
return new RecordWriter() {
+ boolean closed;
public void write(WritableComparable key, Writable value)
throws IOException { // unwrap & index doc
writer.addDocument((Document)((ObjectWritable)value).get());
}
- public void close() throws IOException {
- LOG.info("Optimizing index."); // optimize & close index
- writer.optimize();
- writer.close();
- fs.completeLocalOutput(perm, temp); // copy to ndfs
- fs.createNewFile(new File(perm, IndexSegment.DONE_NAME));
+ public void close(final Reporter reporter) throws IOException {
+ // spawn a thread to give progress heartbeats
+ Thread prog = new Thread() {
+ public void run() {
+ while (!closed) {
+ try {
+ reporter.setStatus("closing");
+ Thread.sleep(1000);
+ } catch (InterruptedException e) { continue; }
+ catch (Throwable e) { return; }
+ }
+ }
+ };
+
+ try {
+ prog.start();
+ LOG.info("Optimizing index."); // optimize & close index
+ writer.optimize();
+ writer.close();
+ fs.completeLocalOutput(perm, temp); // copy to ndfs
+ fs.createNewFile(new File(perm, IndexSegment.DONE_NAME));
+ } finally {
+ closed = true;
+ }
}
};
}
Modified: lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/ParseOutputFormat.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/ParseOutputFormat.java?rev=240286&r1=240285&r2=240286&view=diff
==============================================================================
--- lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/ParseOutputFormat.java \
(original)
+++ lucene/nutch/branches/mapred/src/java/org/apache/nutch/crawl/ParseOutputFormat.java \
Fri Aug 26 09:51:25 2005 @@ -79,7 +79,7 @@
}
}
- public void close() throws IOException {
+ public void close(Reporter reporter) throws IOException {
textOut.close();
dataOut.close();
crawlOut.close();
-------------------------------------------------------
SF.Net email is Sponsored by the Better Software Conference & EXPO
September 19-22, 2005 * San Francisco, CA * Development Lifecycle Practices
Agile & Plan-Driven Development * Managing Projects & Teams * Testing & QA
Security * Process Improvement & Measurement * http://www.sqe.com/bsce5sf
_______________________________________________
Nutch-cvs mailing list
Nutch-cvs@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nutch-cvs
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic