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

revert position increment change due to conflict with PhraseQuery 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@150152 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Erik Hatcher 2003-12-05 14:30:12 +00:00
parent 7298a4a49e
commit d83ae1586c
2 changed files with 4 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
CHANGES.txt
View File

@ -7,12 +7,6 @@ $Id$
1. Added catch of BooleanQuery$TooManyClauses in QueryParser to
throw ParseException instead. (Erik Hatcher)
2. Modified StopFilter to increment positions to account for
stop words removed. This prevents exact phrase queries from
matching erroneously (use slop factor to account for missing
stop words). StopFilter is used by StopAnalyzer, StandardAnalyzer
and some others. (Erik Hatcher)
1.3 RC3
1. Added minMergeDocs in IndexWriter. This can be raised to speed

19
src/java/org/apache/lucene/analysis/StopFilter.java
View File

@ -57,12 +57,8 @@ package org.apache.lucene.analysis;
import java.io.IOException;
import java.util.Hashtable;
/**
* Removes stop words from a token stream. Position increments
* on tokens emitted are adjusted to account for words
* removed. Exact phrase queries will not match across holes left
* by stop word removal, but sloppy phrase queries may match.
*/
/** Removes stop words from a token stream. */
public final class StopFilter extends TokenFilter {
private Hashtable table;
@ -93,17 +89,10 @@ public final class StopFilter extends TokenFilter {
/** Returns the next input Token whose termText() is not a stop word. */
public final Token next() throws IOException {
int position = 1;
// return the first non-stop word found
for (Token token = input.next(); token != null; token = input.next()) {
if (table.get(token.termText) == null) {
token.setPositionIncrement(position);
for (Token token = input.next(); token != null; token = input.next())
if (table.get(token.termText) == null)
return token;
}
position++;
}
// reached EOS -- return null
return null;
}