Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

SOLR-296 -- wrapping reader.terms() in try/catch 

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@554915 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Ryan McKinley 2007-07-10 11:57:36 +00:00
parent 1829a5d781
commit 757aa1f9a0
1 changed files with 44 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

71
src/java/org/apache/solr/handler/admin/LukeRequestHandler.java
View File

@ -71,7 +71,6 @@ import org.apache.solr.search.SolrQueryParser;
* For more documentation see:
* http://wiki.apache.org/solr/LukeRequestHandler
*
* @author ryan
* @version $Id$
* @since solr 1.2
*/
@ -390,12 +389,18 @@ public class LukeRequestHandler extends RequestHandlerBase
indexInfo.add("maxDoc", reader.maxDoc());
if( countTerms ) {
TermEnum te = reader.terms();
int numTerms = 0;
while (te.next()) {
numTerms++;
TermEnum te = null;
try{
te = reader.terms();
int numTerms = 0;
while (te.next()) {
numTerms++;
}
indexInfo.add("numTerms", numTerms );
}
finally{
if( te != null ) te.close();
}
indexInfo.add("numTerms", numTerms );
}
indexInfo.add("version", reader.getVersion()); // TODO? Is this different then: IndexReader.getCurrentVersion( dir )?
@ -538,39 +543,45 @@ public class LukeRequestHandler extends RequestHandlerBase
private static Map<String,TopTermQueue> getTopTerms( IndexReader reader, Set<String> fields, int numTerms, Set<String> junkWords ) throws Exception
{
Map<String,TopTermQueue> info = new HashMap<String, TopTermQueue>();
TermEnum terms = reader.terms();
while (terms.next()) {
String field = terms.term().field();
String t = terms.term().text();
TermEnum terms = null;
try{
terms = reader.terms();
while (terms.next()) {
String field = terms.term().field();
String t = terms.term().text();
// Compute distinct terms for every field
TopTermQueue tiq = info.get( field );
if( tiq == null ) {
tiq = new TopTermQueue( numTerms );
info.put( field, tiq );
}
tiq.distinctTerms++;
tiq.histogram.add( terms.docFreq() ); // add the term to the histogram
// Compute distinct terms for every field
TopTermQueue tiq = info.get( field );
if( tiq == null ) {
tiq = new TopTermQueue( numTerms+1 );
info.put( field, tiq );
}
tiq.distinctTerms++;
tiq.histogram.add( terms.docFreq() ); // add the term to the histogram
// Only save the distinct terms for fields we worry about
if (fields != null && fields.size() > 0) {
if( !fields.contains( field ) ) {
// Only save the distinct terms for fields we worry about
if (fields != null && fields.size() > 0) {
if( !fields.contains( field ) ) {
continue;
}
}
if( junkWords != null && junkWords.contains( t ) ) {
continue;
}
}
if( junkWords != null && junkWords.contains( t ) ) {
continue;
}
if( terms.docFreq() > tiq.minFreq ) {
tiq.put(new TopTermQueue.TermInfo(terms.term(), terms.docFreq()));
if (tiq.size() >= numTerms) { // if tiq full
tiq.pop(); // remove lowest in tiq
tiq.minFreq = ((TopTermQueue.TermInfo)tiq.top()).docFreq; // reset minFreq
if( terms.docFreq() > tiq.minFreq ) {
tiq.put(new TopTermQueue.TermInfo(terms.term(), terms.docFreq()));
if (tiq.size() > numTerms) { // if tiq full
tiq.pop(); // remove lowest in tiq
tiq.minFreq = ((TopTermQueue.TermInfo)tiq.top()).docFreq; // reset minFreq
}
}
}
}
finally {
if( terms != null ) terms.close();
}
return info;
}
}