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

remove deprecated HtmlStrip*Tokenizer, which only overrides reset() with the charfilter for a tokenizer 

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/branches/solr@923497 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2010-03-15 23:11:14 +00:00
parent 3cb43deb0e
commit 78b5767746
8 changed files with 40 additions and 152 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
contrib/extraction/src/test/resources/solr/conf/schema.xml
View File

@ -158,10 +158,16 @@
<analyzer><tokenizer class="solr.WhitespaceTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="HTMLstandardtok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripStandardTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="HTMLwhitetok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="standardtokfilt" class="solr.TextField">
<analyzer>

58
src/java/org/apache/solr/analysis/HTMLStripReader.java
View File

@ -1,58 +0,0 @@
/**
* 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 org.apache.solr.analysis;
import java.io.Reader;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.Set;
import org.apache.lucene.analysis.CharReader;
/**
* A Reader that wraps another reader and attempts to strip out HTML constructs.
*
*
* @version $Id$
* @deprecated Use {@link HTMLStripCharFilter}
*/
@Deprecated
public class HTMLStripReader extends HTMLStripCharFilter {
public static void main(String[] args) throws IOException {
Reader in = new HTMLStripReader(
new InputStreamReader(System.in));
int ch;
while ( (ch=in.read()) != -1 ) System.out.print((char)ch);
}
public HTMLStripReader(Reader source){
super(CharReader.get(source.markSupported() ? source : new BufferedReader(source)));
}
public HTMLStripReader(Reader source, Set<String> escapedTags){
super(CharReader.get(source),escapedTags);
}
public HTMLStripReader(Reader source, Set<String> escapedTags,int readAheadLimit){
super(CharReader.get(source),escapedTags,readAheadLimit);
}
}

43
src/java/org/apache/solr/analysis/HTMLStripStandardTokenizerFactory.java
View File

@ -1,43 +0,0 @@
/**
* 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 org.apache.solr.analysis;
import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.util.Version;
/**
* @version $Id$
* @deprecated Use {@link HTMLStripCharFilterFactory} and {@link StandardTokenizerFactory}
*/
@Deprecated
public class HTMLStripStandardTokenizerFactory extends BaseTokenizerFactory {
public Tokenizer create(Reader input) {
assureMatchVersion();
return new StandardTokenizer(luceneMatchVersion, new HTMLStripReader(input));
// nocommit: what to do about this?
// new HTMLStripReader(input)) {
// @Override
// public void reset(Reader reader) throws IOException {
// super.reset(new HTMLStripReader(reader));
// }
// };
}
}

41
src/java/org/apache/solr/analysis/HTMLStripWhitespaceTokenizerFactory.java
View File

@ -1,41 +0,0 @@
/**
* 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 org.apache.solr.analysis;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.WhitespaceTokenizer;
import java.io.Reader;
import java.io.IOException;
/**
* @version $Id$
* @deprecated Use {@link HTMLStripCharFilterFactory} and {@link WhitespaceTokenizerFactory}
*/
@Deprecated
public class HTMLStripWhitespaceTokenizerFactory extends BaseTokenizerFactory {
public Tokenizer create(Reader input) {
return new WhitespaceTokenizer(new HTMLStripReader(input)) {
@Override
public void reset(Reader input) throws IOException {
super.reset(new HTMLStripReader(input));
}
};
}
}

10
src/test/test-files/solr/conf/schema-copyfield-test.xml
View File

@ -150,10 +150,16 @@
<analyzer><tokenizer class="solr.WhitespaceTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="HTMLstandardtok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripStandardTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="HTMLwhitetok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="standardtokfilt" class="solr.TextField">
<analyzer>

10
src/test/test-files/solr/conf/schema-required-fields.xml
View File

@ -141,10 +141,16 @@
<analyzer><tokenizer class="solr.WhitespaceTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="HTMLstandardtok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripStandardTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="HTMLwhitetok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="standardtokfilt" class="solr.TextField">
<analyzer>

10
src/test/test-files/solr/conf/schema.xml
View File

@ -171,10 +171,16 @@
<analyzer><tokenizer class="solr.WhitespaceTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="HTMLstandardtok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripStandardTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="HTMLwhitetok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="standardtokfilt" class="solr.TextField">
<analyzer>

10
src/test/test-files/solr/conf/schema12.xml
View File

@ -172,10 +172,16 @@
<analyzer><tokenizer class="solr.WhitespaceTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="HTMLstandardtok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripStandardTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="HTMLwhitetok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/></analyzer>
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="standardtokfilt" class="solr.TextField">
<analyzer>