LUCENE-7476: JapaneseNumberFilter should not invoke incrementToken on its input after it's exhausted

This commit is contained in:
Mike McCandless 2016-10-10 11:37:23 -04:00
parent 9ada6ecb5e
commit 257ea3423f
3 changed files with 217 additions and 0 deletions

View File

@ -67,6 +67,9 @@ Bug Fixes
* LUCENE-7484: FastVectorHighlighter failed to highlight SynonymQuery
(Jim Ferenczi via Mike McCandless)
* LUCENE-7476: JapaneseNumberFilter should not invoke incrementToken
on its input after it's exhausted (Andy Hind via Mike McCandless)
Improvements
* LUCENE-7439: FuzzyQuery now matches all terms within the specified

View File

@ -105,6 +105,8 @@ public class JapaneseNumberFilter extends TokenFilter {
private int fallThroughTokens;
private boolean exhausted = false;
static {
numerals = new char[0x10000];
for (int i = 0; i < numerals.length; i++) {
@ -149,7 +151,12 @@ public class JapaneseNumberFilter extends TokenFilter {
return true;
}
if (exhausted) {
return false;
}
if (!input.incrementToken()) {
exhausted = true;
return false;
}
@ -184,6 +191,9 @@ public class JapaneseNumberFilter extends TokenFilter {
endOffset = offsetAttr.endOffset();
moreTokens = input.incrementToken();
if (moreTokens == false) {
exhausted = true;
}
if (posIncrAttr.getPositionIncrement() == 0) {
// This token is a stacked/synonym token, capture number of tokens "under" this token,
@ -227,6 +237,7 @@ public class JapaneseNumberFilter extends TokenFilter {
fallThroughTokens = 0;
numeral = new StringBuilder();
state = null;
exhausted = false;
}
/**

View File

@ -0,0 +1,203 @@
/*
* 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.lucene.analysis.ja;
import java.io.IOException;
import java.io.Reader;
import java.lang.reflect.Constructor;
import java.lang.reflect.InvocationTargetException;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.util.AbstractAnalysisFactory;
import org.apache.lucene.analysis.util.CharFilterFactory;
import org.apache.lucene.analysis.util.MultiTermAwareComponent;
import org.apache.lucene.analysis.util.ResourceLoaderAware;
import org.apache.lucene.analysis.util.TokenFilterFactory;
import org.apache.lucene.analysis.util.TokenizerFactory;
import org.apache.lucene.util.AttributeFactory;
import org.apache.lucene.util.Version;
/**
* Sanity check some things about all factories,
* we do our best to see if we can sanely initialize it with
* no parameters and smoke test it, etc.
*/
// TODO: this was copied from the analysis/common module ... find a better way to share it!
// TODO: fix this to use CustomAnalyzer instead of its own FactoryAnalyzer
public class TestFactories extends BaseTokenStreamTestCase {
public void test() throws IOException {
for (String tokenizer : TokenizerFactory.availableTokenizers()) {
doTestTokenizer(tokenizer);
}
for (String tokenFilter : TokenFilterFactory.availableTokenFilters()) {
doTestTokenFilter(tokenFilter);
}
for (String charFilter : CharFilterFactory.availableCharFilters()) {
doTestCharFilter(charFilter);
}
}
private void doTestTokenizer(String tokenizer) throws IOException {
Class<? extends TokenizerFactory> factoryClazz = TokenizerFactory.lookupClass(tokenizer);
TokenizerFactory factory = (TokenizerFactory) initialize(factoryClazz);
if (factory != null) {
// we managed to fully create an instance. check a few more things:
// if it implements MultiTermAware, sanity check its impl
if (factory instanceof MultiTermAwareComponent) {
AbstractAnalysisFactory mtc = ((MultiTermAwareComponent) factory).getMultiTermComponent();
assertNotNull(mtc);
// it's not ok to return e.g. a charfilter here: but a tokenizer could wrap a filter around it
assertFalse(mtc instanceof CharFilterFactory);
}
// beast it just a little, it shouldnt throw exceptions:
// (it should have thrown them in initialize)
Analyzer a = new FactoryAnalyzer(factory, null, null);
checkRandomData(random(), a, 20, 20, false, false);
a.close();
}
}
private void doTestTokenFilter(String tokenfilter) throws IOException {
Class<? extends TokenFilterFactory> factoryClazz = TokenFilterFactory.lookupClass(tokenfilter);
TokenFilterFactory factory = (TokenFilterFactory) initialize(factoryClazz);
if (factory != null) {
// we managed to fully create an instance. check a few more things:
// if it implements MultiTermAware, sanity check its impl
if (factory instanceof MultiTermAwareComponent) {
AbstractAnalysisFactory mtc = ((MultiTermAwareComponent) factory).getMultiTermComponent();
assertNotNull(mtc);
// it's not ok to return a charfilter or tokenizer here, this makes no sense
assertTrue(mtc instanceof TokenFilterFactory);
}
// beast it just a little, it shouldnt throw exceptions:
// (it should have thrown them in initialize)
Analyzer a = new FactoryAnalyzer(assertingTokenizer, factory, null);
checkRandomData(random(), a, 20, 20, false, false);
a.close();
}
}
private void doTestCharFilter(String charfilter) throws IOException {
Class<? extends CharFilterFactory> factoryClazz = CharFilterFactory.lookupClass(charfilter);
CharFilterFactory factory = (CharFilterFactory) initialize(factoryClazz);
if (factory != null) {
// we managed to fully create an instance. check a few more things:
// if it implements MultiTermAware, sanity check its impl
if (factory instanceof MultiTermAwareComponent) {
AbstractAnalysisFactory mtc = ((MultiTermAwareComponent) factory).getMultiTermComponent();
assertNotNull(mtc);
// it's not ok to return a tokenizer or tokenfilter here, this makes no sense
assertTrue(mtc instanceof CharFilterFactory);
}
// beast it just a little, it shouldnt throw exceptions:
// (it should have thrown them in initialize)
Analyzer a = new FactoryAnalyzer(assertingTokenizer, null, factory);
checkRandomData(random(), a, 20, 20, false, false);
a.close();
}
}
/** tries to initialize a factory with no arguments */
private AbstractAnalysisFactory initialize(Class<? extends AbstractAnalysisFactory> factoryClazz) throws IOException {
Map<String,String> args = new HashMap<>();
args.put("luceneMatchVersion", Version.LATEST.toString());
Constructor<? extends AbstractAnalysisFactory> ctor;
try {
ctor = factoryClazz.getConstructor(Map.class);
} catch (Exception e) {
throw new RuntimeException("factory '" + factoryClazz + "' does not have a proper ctor!");
}
AbstractAnalysisFactory factory = null;
try {
factory = ctor.newInstance(args);
} catch (InstantiationException | IllegalAccessException e) {
throw new RuntimeException(e);
} catch (InvocationTargetException e) {
if (e.getCause() instanceof IllegalArgumentException) {
// it's ok if we dont provide the right parameters to throw this
return null;
}
}
if (factory instanceof ResourceLoaderAware) {
try {
((ResourceLoaderAware) factory).inform(new StringMockResourceLoader(""));
} catch (IOException ignored) {
// it's ok if the right files arent available or whatever to throw this
} catch (IllegalArgumentException ignored) {
// is this ok? I guess so
}
}
return factory;
}
// some silly classes just so we can use checkRandomData
private TokenizerFactory assertingTokenizer = new TokenizerFactory(new HashMap<String,String>()) {
@Override
public MockTokenizer create(AttributeFactory factory) {
return new MockTokenizer(factory);
}
};
private static class FactoryAnalyzer extends Analyzer {
final TokenizerFactory tokenizer;
final CharFilterFactory charFilter;
final TokenFilterFactory tokenfilter;
FactoryAnalyzer(TokenizerFactory tokenizer, TokenFilterFactory tokenfilter, CharFilterFactory charFilter) {
assert tokenizer != null;
this.tokenizer = tokenizer;
this.charFilter = charFilter;
this.tokenfilter = tokenfilter;
}
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer tf = tokenizer.create(newAttributeFactory());
if (tokenfilter != null) {
return new TokenStreamComponents(tf, tokenfilter.create(tf));
} else {
return new TokenStreamComponents(tf);
}
}
@Override
protected Reader initReader(String fieldName, Reader reader) {
if (charFilter != null) {
return charFilter.create(reader);
} else {
return reader;
}
}
}
}