Author: jnioche
Date: Mon May 23 10:34:32 2011
New Revision: 1126421
URL: http://svn.apache.org/viewvc?rev=1126421&view=rev
Log:
NUTCH-999 Normalise String representation for Dates in IndexingFilters
Modified:
nutch/trunk/CHANGES.txt
nutch/trunk/conf/schema.xml
nutch/trunk/src/plugin/feed/src/java/org/apache/nutch/indexer/feed/FeedIndexingFilter.java
nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java
Modified: nutch/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1126421&r1=1126420&r2=1126421&view=diff
==============================================================================
--- nutch/trunk/CHANGES.txt (original)
+++ nutch/trunk/CHANGES.txt Mon May 23 10:34:32 2011
@@ -2,6 +2,8 @@ Nutch Change Log
Release 2.0 - Current Development
+* NUTCH-999 Normalise String representation for Dates in IndexingFilters
(jnioche)
+
* NUTCH-996 Indexer adds solr.commit.size+1 docs (markus)
* NUTCH-983 Upgrade SolrJ to 3.1 (markus, jnioche)
Modified: nutch/trunk/conf/schema.xml
URL:
http://svn.apache.org/viewvc/nutch/trunk/conf/schema.xml?rev=1126421&r1=1126420&r2=1126421&view=diff
==============================================================================
--- nutch/trunk/conf/schema.xml (original)
+++ nutch/trunk/conf/schema.xml Mon May 23 10:34:32 2011
@@ -84,9 +84,9 @@
multiValued="true"/>
<field name="contentLength" type="long" stored="true"
indexed="false"/>
- <field name="lastModified" type="long" stored="true"
+ <field name="lastModified" type="date" stored="true"
indexed="false"/>
- <field name="date" type="string" stored="true" indexed="true"/>
+ <field name="date" type="date" stored="true" indexed="true"/>
<!-- fields for languageidentifier plugin -->
<field name="lang" type="string" stored="true" indexed="true"/>
@@ -99,9 +99,9 @@
<field name="author" type="string" stored="true" indexed="true"/>
<field name="tag" type="string" stored="true" indexed="true"/>
<field name="feed" type="string" stored="true" indexed="true"/>
- <field name="publishedDate" type="string" stored="true"
+ <field name="publishedDate" type="date" stored="true"
indexed="true"/>
- <field name="updatedDate" type="string" stored="true"
+ <field name="updatedDate" type="date" stored="true"
indexed="true"/>
</fields>
<uniqueKey>id</uniqueKey>
Modified:
nutch/trunk/src/plugin/feed/src/java/org/apache/nutch/indexer/feed/FeedIndexingFilter.java
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/plugin/feed/src/java/org/apache/nutch/indexer/feed/FeedIndexingFilter.java?rev=1126421&r1=1126420&r2=1126421&view=diff
==============================================================================
---
nutch/trunk/src/plugin/feed/src/java/org/apache/nutch/indexer/feed/FeedIndexingFilter.java
(original)
+++
nutch/trunk/src/plugin/feed/src/java/org/apache/nutch/indexer/feed/FeedIndexingFilter.java
Mon May 23 10:34:32 2011
@@ -34,6 +34,7 @@ import org.apache.nutch.metadata.Feed;
import org.apache.nutch.metadata.Metadata;
import org.apache.nutch.parse.Parse;
import org.apache.nutch.parse.ParseData;
+import org.apache.solr.common.util.DateUtil;
/**
* @author dogacan
@@ -96,17 +97,15 @@ public class FeedIndexingFilter implemen
if (feed != null)
doc.add(Feed.FEED, feed);
- SimpleDateFormat sdf = new SimpleDateFormat(dateFormatStr);
- sdf.setTimeZone(TimeZone.getTimeZone("GMT"));
if (published != null) {
Date date = new Date(Long.parseLong(published));
- String dateString = sdf.format(date);
+ String dateString = DateUtil.getThreadLocalDateFormat().format(date);
doc.add(PUBLISHED_DATE, dateString);
}
if (updated != null) {
Date date = new Date(Long.parseLong(updated));
- String dateString = sdf.format(date);
+ String dateString = DateUtil.getThreadLocalDateFormat().format(date);
doc.add(UPDATED_DATE, dateString);
}
Modified:
nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java?rev=1126421&r1=1126420&r2=1126421&view=diff
==============================================================================
---
nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java
(original)
+++
nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java
Mon May 23 10:34:32 2011
@@ -43,6 +43,7 @@ import org.apache.oro.text.regex.Perl5Co
import org.apache.oro.text.regex.Perl5Matcher;
import org.apache.oro.text.regex.Perl5Pattern;
import org.apache.tika.mime.MimeType;
+import org.apache.solr.common.util.DateUtil;
/**
* Add (or reset) a few metaData properties as respective fields (if they are
@@ -88,8 +89,9 @@ public class MoreIndexingFilter implemen
// String lastModified = data.getMeta(Metadata.LAST_MODIFIED);
if (lastModified != null) { // try parse last-modified
time = getTime(lastModified.toString(), url); // use as time
+ String formlastModified = DateUtil.getThreadLocalDateFormat().format(new
Date(time));
// store as string
- doc.add("lastModified", Long.toString(time));
+ doc.add("lastModified", formlastModified);
}
if (time == -1) { // if no last-modified
@@ -97,11 +99,7 @@ public class MoreIndexingFilter implemen
time = page.getFetchTime(); // use fetch time
}
- // add support for query syntax date:
- // query filter is implemented in DateQueryFilter.java
- SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
- sdf.setTimeZone(TimeZone.getTimeZone("GMT"));
- String dateString = sdf.format(new Date(time));
+ String dateString = DateUtil.getThreadLocalDateFormat().format(new
Date(time));
// un-stored, indexed and un-tokenized
doc.add("date", dateString);