LUCENE-4766: Added a PatternCaptureGroupTokenFilter that uses Java regexes to emit multiple tokens one for each capture group in one or more patterns

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1471347 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Simon Willnauer 2013-04-24 10:21:04 +00:00
parent ffbaa58de0
commit 72721860fd
8 changed files with 891 additions and 4 deletions

View File

@ -55,6 +55,13 @@ Optimizations
a common divisor. In particular, this improves the compression ratio of dates
without time when they are encoded as milliseconds since Epoch. Also support
TABLE compressed numerics in the Disk codec. (Robert Muir, Adrien Grand)
New Features
* LUCENE-4766: Added a PatternCaptureGroupTokenFilter that uses Java regexes to
emit multiple tokens one for each capture group in one or more patterns.
(Simon Willnauer, Clinton Gormley)
======================= Lucene 4.3.0 =======================

View File

@ -0,0 +1,51 @@
package org.apache.lucene.analysis.pattern;
/*
* 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.
*/
import java.util.Map;
import java.util.regex.Pattern;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.TokenFilterFactory;
/**
* Factory for {@link PatternCaptureGroupTokenFilter}.
* <pre class="prettyprint" >
* &lt;fieldType name="text_ptncapturegroup" class="solr.TextField" positionIncrementGap="100"&gt;
* &lt;analyzer&gt;
* &lt;tokenizer class="solr.KeywordTokenizerFactory"/&gt;
* &lt;filter class="solr.PatternCaptureGroupTokenFilter" pattern="([^a-z])" preserve_original="true"/&gt;
* &lt;/analyzer&gt;
* &lt;/fieldType&gt;</pre>
*
* @see PatternCaptureGroupTokenFilter
*/
public class PatternCaptureGroupFilterFactory extends TokenFilterFactory {
private Pattern pattern;
private boolean preserveOriginal = true;
public PatternCaptureGroupFilterFactory(Map<String,String> args) {
super(args);
pattern = getPattern(args, "pattern");
preserveOriginal = args.containsKey("preserve_original") ? Boolean.parseBoolean(args.get("preserve_original")) : true;
}
@Override
public PatternCaptureGroupTokenFilter create(TokenStream input) {
return new PatternCaptureGroupTokenFilter(input, preserveOriginal, pattern);
}
}

View File

@ -0,0 +1,200 @@
package org.apache.lucene.analysis.pattern;
/*
* 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.
*/
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.util.CharsRef;
/**
* CaptureGroup uses Java regexes to emit multiple tokens - one for each capture
* group in one or more patterns.
*
* <p>
* For example, a pattern like:
* </p>
*
* <p>
* <code>"(https?://([a-zA-Z\-_0-9.]+))"</code>
* </p>
*
* <p>
* when matched against the string "http://www.foo.com/index" would return the
* tokens "https://www.foo.com" and "www.foo.com".
* </p>
*
* <p>
* If none of the patterns match, or if preserveOriginal is true, the original
* token will be preserved.
* </p>
* <p>
* Each pattern is matched as often as it can be, so the pattern
* <code> "(...)"</code>, when matched against <code>"abcdefghi"</code> would
* produce <code>["abc","def","ghi"]</code>
* </p>
* <p>
* A camelCaseFilter could be written as:
* </p>
* <p>
* <code>
* "([A-Z]{2,})", <br />
* "(?&lt;![A-Z])([A-Z][a-z]+)", <br />
* "(?:^|\\b|(?&lt;=[0-9_])|(?&lt;=[A-Z]{2}))([a-z]+)", <br />
* "([0-9]+)"
* </code>
* </p>
* <p>
* plus if {@link #preserveOriginal} is true, it would also return
* <code>"camelCaseFilter</code>
* </p>
*/
public final class PatternCaptureGroupTokenFilter extends TokenFilter {
private final CharTermAttribute charTermAttr = addAttribute(CharTermAttribute.class);
private final PositionIncrementAttribute posAttr = addAttribute(PositionIncrementAttribute.class);
private State state;
private final Matcher[] matchers;
private final CharsRef spare = new CharsRef();
private final int[] groupCounts;
private final boolean preserveOriginal;
private int[] currentGroup;
private int currentMatcher;
/**
* @param input
* the input {@link TokenStream}
* @param preserveOriginal
* set to true to return the original token even if one of the
* patterns matches
* @param patterns
* an array of {@link Pattern} objects to match against each token
*/
public PatternCaptureGroupTokenFilter(TokenStream input,
boolean preserveOriginal, Pattern... patterns) {
super(input);
this.preserveOriginal = preserveOriginal;
this.matchers = new Matcher[patterns.length];
this.groupCounts = new int[patterns.length];
this.currentGroup = new int[patterns.length];
for (int i = 0; i < patterns.length; i++) {
this.matchers[i] = patterns[i].matcher("");
this.groupCounts[i] = this.matchers[i].groupCount();
this.currentGroup[i] = -1;
}
}
private boolean nextCapture() {
int min_offset = Integer.MAX_VALUE;
currentMatcher = -1;
Matcher matcher;
for (int i = 0; i < matchers.length; i++) {
matcher = matchers[i];
if (currentGroup[i] == -1) {
currentGroup[i] = matcher.find() ? 1 : 0;
}
if (currentGroup[i] != 0) {
while (currentGroup[i] < groupCounts[i] + 1) {
final int start = matcher.start(currentGroup[i]);
final int end = matcher.end(currentGroup[i]);
if (start == end || preserveOriginal && start == 0
&& spare.length == end) {
currentGroup[i]++;
continue;
}
if (start < min_offset) {
min_offset = start;
currentMatcher = i;
}
break;
}
if (currentGroup[i] == groupCounts[i] + 1) {
currentGroup[i] = -1;
i--;
}
}
}
return currentMatcher != -1;
}
@Override
public boolean incrementToken() throws IOException {
if (currentMatcher != -1 && nextCapture()) {
assert state != null;
clearAttributes();
restoreState(state);
final int start = matchers[currentMatcher]
.start(currentGroup[currentMatcher]);
final int end = matchers[currentMatcher]
.end(currentGroup[currentMatcher]);
posAttr.setPositionIncrement(0);
charTermAttr.copyBuffer(spare.chars, start, end - start);
currentGroup[currentMatcher]++;
return true;
}
if (!input.incrementToken()) {
return false;
}
char[] buffer = charTermAttr.buffer();
int length = charTermAttr.length();
spare.copyChars(buffer, 0, length);
state = captureState();
for (int i = 0; i < matchers.length; i++) {
matchers[i].reset(spare);
currentGroup[i] = -1;
}
if (preserveOriginal) {
currentMatcher = 0;
} else if (nextCapture()) {
final int start = matchers[currentMatcher]
.start(currentGroup[currentMatcher]);
final int end = matchers[currentMatcher]
.end(currentGroup[currentMatcher]);
// if we start at 0 we can simply set the length and save the copy
if (start == 0) {
charTermAttr.setLength(end);
} else {
charTermAttr.copyBuffer(spare.chars, start, end - start);
}
currentGroup[currentMatcher]++;
}
return true;
}
@Override
public void reset() throws IOException {
super.reset();
state = null;
currentMatcher = -1;
}
}

View File

@ -38,7 +38,6 @@ import java.io.IOException;
* @see Pattern
*/
public final class PatternReplaceFilter extends TokenFilter {
private final Pattern p;
private final String replacement;
private final boolean all;
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
@ -60,7 +59,6 @@ public final class PatternReplaceFilter extends TokenFilter {
String replacement,
boolean all) {
super(in);
this.p=p;
this.replacement = (null == replacement) ? "" : replacement;
this.all=all;
this.m = p.matcher(termAtt);

View File

@ -60,7 +60,6 @@ public final class PatternTokenizer extends Tokenizer {
private final StringBuilder str = new StringBuilder();
private int index;
private final Pattern pattern;
private final int group;
private final Matcher matcher;
@ -72,7 +71,6 @@ public final class PatternTokenizer extends Tokenizer {
/** creates a new PatternTokenizer returning tokens from group (-1 for split functionality) */
public PatternTokenizer(AttributeFactory factory, Reader input, Pattern pattern, int group) {
super(factory, input);
this.pattern = pattern;
this.group = group;
// Use "" instead of str so don't consume chars

View File

@ -71,6 +71,7 @@ org.apache.lucene.analysis.ngram.NGramFilterFactory
org.apache.lucene.analysis.no.NorwegianLightStemFilterFactory
org.apache.lucene.analysis.no.NorwegianMinimalStemFilterFactory
org.apache.lucene.analysis.pattern.PatternReplaceFilterFactory
org.apache.lucene.analysis.pattern.PatternCaptureGroupFilterFactory
org.apache.lucene.analysis.payloads.DelimitedPayloadTokenFilterFactory
org.apache.lucene.analysis.payloads.NumericPayloadTokenFilterFactory
org.apache.lucene.analysis.payloads.TokenOffsetPayloadTokenFilterFactory

View File

@ -470,6 +470,12 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
return Pattern.compile("a");
}
});
put(Pattern[].class, new ArgProducer() {
@Override public Object create(Random random) {
return new Pattern[] {Pattern.compile("([a-z]+)"), Pattern.compile("([0-9]+)")};
}
});
put(PayloadEncoder.class, new ArgProducer() {
@Override public Object create(Random random) {
return new IdentityEncoder(); // the other encoders will throw exceptions if tokens arent numbers?

View File

@ -0,0 +1,626 @@
package org.apache.lucene.analysis.pattern;
/*
* 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.
*/
import java.io.Reader;
import java.io.StringReader;
import java.util.regex.Pattern;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
public class TestPatternCaptureGroupTokenFilter extends BaseTokenStreamTestCase {
public void testNoPattern() throws Exception {
testPatterns(
"foobarbaz",
new String[] {},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
true
);
testPatterns(
"foo bar baz",
new String[] {},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
true
);
}
public void testNoMatch() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"xx"},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {"xx"},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
true
);
testPatterns(
"foo bar baz",
new String[] {"xx"},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {"xx"},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
true
);
}
public void testNoCapture() throws Exception {
testPatterns(
"foobarbaz",
new String[] {".."},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {".."},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
true
);
testPatterns(
"foo bar baz",
new String[] {".."},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {".."},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
true
);
}
public void testEmptyCapture() throws Exception {
testPatterns(
"foobarbaz",
new String[] {".(y*)"},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {".(y*)"},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
true
);
testPatterns(
"foo bar baz",
new String[] {".(y*)"},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {".(y*)"},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
true
);
}
public void testCaptureAll() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"(.+)"},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {"(.+)"},
new String[] {"foobarbaz"},
new int[] {0},
new int[] {9},
new int[] {1},
true
);
testPatterns(
"foo bar baz",
new String[] {"(.+)"},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {"(.+)"},
new String[] {"foo","bar","baz"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
true
);
}
public void testCaptureStart() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"^(.)"},
new String[] {"f"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {"^(.)"},
new String[] {"foobarbaz","f"},
new int[] {0,0},
new int[] {9,9},
new int[] {1,0},
true
);
testPatterns(
"foo bar baz",
new String[] {"^(.)"},
new String[] {"f","b","b"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {"^(.)"},
new String[] {"foo","f","bar","b","baz","b"},
new int[] {0,0,4,4,8,8},
new int[] {3,3,7,7,11,11},
new int[] {1,0,1,0,1,0},
true
);
}
public void testCaptureMiddle() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"^.(.)."},
new String[] {"o"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {"^.(.)."},
new String[] {"foobarbaz","o"},
new int[] {0,0},
new int[] {9,9},
new int[] {1,0},
true
);
testPatterns(
"foo bar baz",
new String[] {"^.(.)."},
new String[] {"o","a","a"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {"^.(.)."},
new String[] {"foo","o","bar","a","baz","a"},
new int[] {0,0,4,4,8,8},
new int[] {3,3,7,7,11,11},
new int[] {1,0,1,0,1,0},
true
);
}
public void testCaptureEnd() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"(.)$"},
new String[] {"z"},
new int[] {0},
new int[] {9},
new int[] {1},
false
);
testPatterns(
"foobarbaz",
new String[] {"(.)$"},
new String[] {"foobarbaz","z"},
new int[] {0,0},
new int[] {9,9},
new int[] {1,0},
true
);
testPatterns(
"foo bar baz",
new String[] {"(.)$"},
new String[] {"o","r","z"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"foo bar baz",
new String[] {"(.)$"},
new String[] {"foo","o","bar","r","baz","z"},
new int[] {0,0,4,4,8,8},
new int[] {3,3,7,7,11,11},
new int[] {1,0,1,0,1,0},
true
);
}
public void testCaptureStartMiddle() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"^(.)(.)"},
new String[] {"f","o"},
new int[] {0,0},
new int[] {9,9},
new int[] {1,0},
false
);
testPatterns(
"foobarbaz",
new String[] {"^(.)(.)"},
new String[] {"foobarbaz","f","o"},
new int[] {0,0,0},
new int[] {9,9,9},
new int[] {1,0,0},
true
);
testPatterns(
"foo bar baz",
new String[] {"^(.)(.)"},
new String[] {"f","o","b","a","b","a"},
new int[] {0,0,4,4,8,8},
new int[] {3,3,7,7,11,11},
new int[] {1,0,1,0,1,0},
false
);
testPatterns(
"foo bar baz",
new String[] {"^(.)(.)"},
new String[] {"foo","f","o","bar","b","a","baz","b","a"},
new int[] {0,0,0,4,4,4,8,8,8},
new int[] {3,3,3,7,7,7,11,11,11},
new int[] {1,0,0,1,0,0,1,0,0},
true
);
}
public void testCaptureStartEnd() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"^(.).+(.)$"},
new String[] {"f","z"},
new int[] {0,0},
new int[] {9,9},
new int[] {1,0},
false
);
testPatterns(
"foobarbaz",
new String[] {"^(.).+(.)$"},
new String[] {"foobarbaz","f","z"},
new int[] {0,0,0},
new int[] {9,9,9},
new int[] {1,0,0},
true
);
testPatterns(
"foo bar baz",
new String[] {"^(.).+(.)$"},
new String[] {"f","o","b","r","b","z"},
new int[] {0,0,4,4,8,8},
new int[] {3,3,7,7,11,11},
new int[] {1,0,1,0,1,0},
false
);
testPatterns(
"foo bar baz",
new String[] {"^(.).+(.)$"},
new String[] {"foo","f","o","bar","b","r","baz","b","z"},
new int[] {0,0,0,4,4,4,8,8,8},
new int[] {3,3,3,7,7,7,11,11,11},
new int[] {1,0,0,1,0,0,1,0,0},
true
);
}
public void testCaptureMiddleEnd() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"(.)(.)$"},
new String[] {"a","z"},
new int[] {0,0},
new int[] {9,9},
new int[] {1,0},
false
);
testPatterns(
"foobarbaz",
new String[] {"(.)(.)$"},
new String[] {"foobarbaz","a","z"},
new int[] {0,0,0},
new int[] {9,9,9},
new int[] {1,0,0},
true
);
testPatterns(
"foo bar baz",
new String[] {"(.)(.)$"},
new String[] {"o","o","a","r","a","z"},
new int[] {0,0,4,4,8,8},
new int[] {3,3,7,7,11,11},
new int[] {1,0,1,0,1,0},
false
);
testPatterns(
"foo bar baz",
new String[] {"(.)(.)$"},
new String[] {"foo","o","o","bar","a","r","baz","a","z"},
new int[] {0,0,0,4,4,4,8,8,8},
new int[] {3,3,3,7,7,7,11,11,11},
new int[] {1,0,0,1,0,0,1,0,0},
true
);
}
public void testMultiCaptureOverlap() throws Exception {
testPatterns(
"foobarbaz",
new String[] {"(.(.(.)))"},
new String[] {"foo","oo","o","bar","ar","r","baz","az","z"},
new int[] {0,0,0,0,0,0,0,0,0},
new int[] {9,9,9,9,9,9,9,9,9},
new int[] {1,0,0,0,0,0,0,0,0},
false
);
testPatterns(
"foobarbaz",
new String[] {"(.(.(.)))"},
new String[] {"foobarbaz","foo","oo","o","bar","ar","r","baz","az","z"},
new int[] {0,0,0,0,0,0,0,0,0,0},
new int[] {9,9,9,9,9,9,9,9,9,9},
new int[] {1,0,0,0,0,0,0,0,0,0},
true
);
testPatterns(
"foo bar baz",
new String[] {"(.(.(.)))"},
new String[] {"foo","oo","o","bar","ar","r","baz","az","z"},
new int[] {0,0,0,4,4,4,8,8,8},
new int[] {3,3,3,7,7,7,11,11,11},
new int[] {1,0,0,1,0,0,1,0,0},
false
);
testPatterns(
"foo bar baz",
new String[] {"(.(.(.)))"},
new String[] {"foo","oo","o","bar","ar","r","baz","az","z"},
new int[] {0,0,0,4,4,4,8,8,8},
new int[] {3,3,3,7,7,7,11,11,11},
new int[] {1,0,0,1,0,0,1,0,0},
true
);
}
public void testMultiPattern() throws Exception {
testPatterns(
"aaabbbaaa",
new String[] {"(aaa)","(bbb)","(ccc)"},
new String[] {"aaa","bbb","aaa"},
new int[] {0,0,0},
new int[] {9,9,9},
new int[] {1,0,0},
false
);
testPatterns(
"aaabbbaaa",
new String[] {"(aaa)","(bbb)","(ccc)"},
new String[] {"aaabbbaaa","aaa","bbb","aaa"},
new int[] {0,0,0,0},
new int[] {9,9,9,9},
new int[] {1,0,0,0},
true
);
testPatterns(
"aaa bbb aaa",
new String[] {"(aaa)","(bbb)","(ccc)"},
new String[] {"aaa","bbb","aaa"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
false
);
testPatterns(
"aaa bbb aaa",
new String[] {"(aaa)","(bbb)","(ccc)"},
new String[] {"aaa","bbb","aaa"},
new int[] {0,4,8},
new int[] {3,7,11},
new int[] {1,1,1},
true
);
}
public void testCamelCase() throws Exception {
testPatterns(
"letsPartyLIKEits1999_dude",
new String[] {
"([A-Z]{2,})",
"(?<![A-Z])([A-Z][a-z]+)",
"(?:^|\\b|(?<=[0-9_])|(?<=[A-Z]{2}))([a-z]+)",
"([0-9]+)"
},
new String[] {"lets","Party","LIKE","its","1999","dude"},
new int[] {0,0,0,0,0,0},
new int[] {25,25,25,25,25,25},
new int[] {1,0,0,0,0,0,0},
false
);
testPatterns(
"letsPartyLIKEits1999_dude",
new String[] {
"([A-Z]{2,})",
"(?<![A-Z])([A-Z][a-z]+)",
"(?:^|\\b|(?<=[0-9_])|(?<=[A-Z]{2}))([a-z]+)",
"([0-9]+)"
},
new String[] {"letsPartyLIKEits1999_dude","lets","Party","LIKE","its","1999","dude"},
new int[] {0,0,0,0,0,0,0},
new int[] {25,25,25,25,25,25,25},
new int[] {1,0,0,0,0,0,0,0},
true
);
}
public void testRandomString() throws Exception {
Analyzer a = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader,
MockTokenizer.WHITESPACE, false);
return new TokenStreamComponents(tokenizer,
new PatternCaptureGroupTokenFilter(tokenizer, false,
Pattern.compile("((..)(..))")));
}
};
checkRandomData(random(), a, 1000 * RANDOM_MULTIPLIER);
}
private void testPatterns(String input, String[] regexes, String[] tokens,
int[] startOffsets, int[] endOffsets, int[] positions,
boolean preserveOriginal) throws Exception {
Pattern[] patterns = new Pattern[regexes.length];
for (int i = 0; i < regexes.length; i++) {
patterns[i] = Pattern.compile(regexes[i]);
}
TokenStream ts = new PatternCaptureGroupTokenFilter(new MockTokenizer(
new StringReader(input), MockTokenizer.WHITESPACE, false),
preserveOriginal, patterns);
assertTokenStreamContents(ts, tokens, startOffsets, endOffsets, positions);
}
}