-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Lianyi Han
committed
Oct 9, 2015
1 parent
29a4106
commit 834c600
Showing
1 changed file
with
69 additions
and
0 deletions.
There are no files selected for viewing
69 changes: 69 additions & 0 deletions
69
src/main/java/gov/nih/nlm/ncbi/seqr/tokenizer/TokenSizeFilter.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,69 @@ | ||
/* | ||
* Licensed to the Apache Software Foundation (ASF) under one or more | ||
* contributor license agreements. See the NOTICE file distributed with | ||
* this work for additional information regarding copyright ownership. | ||
* The ASF licenses this file to You under the Apache License, Version 2.0 | ||
* (the "License"); you may not use this file except in compliance with | ||
* the License. You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package gov.nih.nlm.ncbi.seqr.tokenizer; | ||
|
||
import org.apache.lucene.analysis.TokenFilter; | ||
import org.apache.lucene.analysis.TokenStream; | ||
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; | ||
|
||
import java.io.IOException; | ||
|
||
/** | ||
* A TokenSizeFilter that caculate the number of tokens in the token stream and save it to the first token | ||
*/ | ||
public final class TokenSizeFilter extends TokenFilter { | ||
|
||
private final CharTermAttribute termAttribute = addAttribute(CharTermAttribute.class); | ||
private int counter = 0; | ||
|
||
/** | ||
* Creates a new TokenSizeFilter | ||
* | ||
* @param in TokenStream that will be filtered | ||
*/ | ||
public TokenSizeFilter(TokenStream in) { | ||
super(in); | ||
} | ||
|
||
/** | ||
* {@inheritDoc} | ||
*/ | ||
@Override | ||
public boolean incrementToken() throws IOException { | ||
|
||
if (counter <= 0) { | ||
while (input.incrementToken()) { | ||
counter++; | ||
} | ||
termAttribute.setEmpty(); | ||
termAttribute.append(Integer.toString(counter)); | ||
return true; | ||
} | ||
return false; | ||
} | ||
|
||
/** | ||
* {@inheritDoc} | ||
*/ | ||
@Override | ||
public void reset() throws IOException { | ||
super.reset(); | ||
counter = 0; | ||
|
||
} | ||
} |