You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2012/01/24 11:10:57 UTC
svn commit: r1235193 - in /lucene/dev/branches/branch_3x: ./ lucene/
lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/
lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/
lucene/src/java/org/apache/lucene...
Author: rmuir
Date: Tue Jan 24 10:10:56 2012
New Revision: 1235193
URL: http://svn.apache.org/viewvc?rev=1235193&view=rev
Log:
LUCENE-3717: fix broken offsets in ngramtokenizers, and check return value of Reader.read
Modified:
lucene/dev/branches/branch_3x/ (props changed)
lucene/dev/branches/branch_3x/lucene/ (props changed)
lucene/dev/branches/branch_3x/lucene/CHANGES.txt
lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java
lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java
lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java
lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java
lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java
lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java
lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/ReusableAnalyzerBase.java
Modified: lucene/dev/branches/branch_3x/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/CHANGES.txt?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/CHANGES.txt (original)
+++ lucene/dev/branches/branch_3x/lucene/CHANGES.txt Tue Jan 24 10:10:56 2012
@@ -126,7 +126,7 @@ Bug fixes
* LUCENE-3641: Fixed MultiReader to correctly propagate readerFinishedListeners
to clones/reopened readers. (Uwe Schindler)
-* LUCENE-3642, SOLR-2891, LUCENE-3717: Fixed bugs in CharTokenizer, n-gram filters,
+* LUCENE-3642, SOLR-2891, LUCENE-3717: Fixed bugs in CharTokenizer, n-gram tokenizers/filters,
compound token filters, thai word filter, icutokenizer, pattern analyzer,
wikipediatokenizer, and smart chinese where they would create invalid offsets in
some situations, leading to problems in highlighting.
Modified: lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java Tue Jan 24 10:10:56 2012
@@ -74,7 +74,8 @@ public final class EdgeNGramTokenizer ex
private int gramSize;
private Side side;
private boolean started = false;
- private int inLen;
+ private int inLen; // length of the input AFTER trim()
+ private int charsRead; // length of the input
private String inStr;
@@ -183,7 +184,11 @@ public final class EdgeNGramTokenizer ex
if (!started) {
started = true;
char[] chars = new char[1024];
- int charsRead = input.read(chars);
+ charsRead = input.read(chars);
+ if (charsRead < 0) {
+ charsRead = inLen = 0;
+ return false;
+ }
inStr = new String(chars, 0, charsRead).trim(); // remove any leading or trailing spaces
inLen = inStr.length();
gramSize = minGram;
@@ -211,7 +216,7 @@ public final class EdgeNGramTokenizer ex
@Override
public final void end() {
// set final offset
- final int finalOffset = inLen;
+ final int finalOffset = correctOffset(charsRead);
this.offsetAtt.setOffset(finalOffset, finalOffset);
}
@@ -225,5 +230,6 @@ public final class EdgeNGramTokenizer ex
public void reset() throws IOException {
super.reset();
started = false;
+ charsRead = 0;
}
}
Modified: lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java Tue Jan 24 10:10:56 2012
@@ -35,7 +35,8 @@ public final class NGramTokenizer extend
private int minGram, maxGram;
private int gramSize;
private int pos = 0;
- private int inLen;
+ private int inLen; // length of the input AFTER trim()
+ private int charsRead; // length of the input
private String inStr;
private boolean started = false;
@@ -104,7 +105,11 @@ public final class NGramTokenizer extend
started = true;
gramSize = minGram;
char[] chars = new char[1024];
- input.read(chars);
+ charsRead = input.read(chars);
+ if (charsRead < 0) {
+ charsRead = inLen = 0;
+ return false;
+ }
inStr = new String(chars).trim(); // remove any trailing empty strings
inLen = inStr.length();
}
@@ -128,7 +133,7 @@ public final class NGramTokenizer extend
@Override
public final void end() {
// set final offset
- final int finalOffset = inLen;
+ final int finalOffset = correctOffset(charsRead);
this.offsetAtt.setOffset(finalOffset, finalOffset);
}
@@ -143,5 +148,6 @@ public final class NGramTokenizer extend
super.reset();
started = false;
pos = 0;
+ charsRead = 0;
}
}
Modified: lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java Tue Jan 24 10:10:56 2012
@@ -130,4 +130,27 @@ public class EdgeNGramTokenFilterTest ex
new int[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
new int[] { 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11 });
}
+
+ /** blast some random strings through the analyzer */
+ public void testRandomStrings() throws Exception {
+ Analyzer a = new ReusableAnalyzerBase() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ return new TokenStreamComponents(tokenizer,
+ new EdgeNGramTokenFilter(tokenizer, EdgeNGramTokenFilter.Side.FRONT, 2, 15));
+ }
+ };
+ checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+
+ Analyzer b = new ReusableAnalyzerBase() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ return new TokenStreamComponents(tokenizer,
+ new EdgeNGramTokenFilter(tokenizer, EdgeNGramTokenFilter.Side.BACK, 2, 15));
+ }
+ };
+ checkRandomData(random, b, 10000*RANDOM_MULTIPLIER);
+ }
}
Modified: lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java Tue Jan 24 10:10:56 2012
@@ -18,9 +18,13 @@ package org.apache.lucene.analysis.ngram
*/
+import java.io.Reader;
import java.io.StringReader;
+import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.ReusableAnalyzerBase;
+import org.apache.lucene.analysis.Tokenizer;
/**
* Tests {@link EdgeNGramTokenizer} for correctness.
@@ -95,4 +99,25 @@ public class EdgeNGramTokenizerTest exte
tokenizer.reset(new StringReader("abcde"));
assertTokenStreamContents(tokenizer, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{1,2,3}, 5 /* abcde */);
}
+
+ /** blast some random strings through the analyzer */
+ public void testRandomStrings() throws Exception {
+ Analyzer a = new ReusableAnalyzerBase() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new EdgeNGramTokenizer(reader, EdgeNGramTokenizer.Side.FRONT, 2, 15);
+ return new TokenStreamComponents(tokenizer, tokenizer);
+ }
+ };
+ checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+
+ Analyzer b = new ReusableAnalyzerBase() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new EdgeNGramTokenizer(reader, EdgeNGramTokenizer.Side.BACK, 2, 15);
+ return new TokenStreamComponents(tokenizer, tokenizer);
+ }
+ };
+ checkRandomData(random, b, 10000*RANDOM_MULTIPLIER);
+ }
}
Modified: lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java Tue Jan 24 10:10:56 2012
@@ -34,89 +34,102 @@ import java.io.StringReader;
* Tests {@link NGramTokenFilter} for correctness.
*/
public class NGramTokenFilterTest extends BaseTokenStreamTestCase {
- private TokenStream input;
-
- @Override
- public void setUp() throws Exception {
- super.setUp();
- input = new MockTokenizer(new StringReader("abcde"), MockTokenizer.WHITESPACE, false);
- }
-
- public void testInvalidInput() throws Exception {
- boolean gotException = false;
- try {
- new NGramTokenFilter(input, 2, 1);
- } catch (IllegalArgumentException e) {
- gotException = true;
- }
- assertTrue(gotException);
- }
-
- public void testInvalidInput2() throws Exception {
- boolean gotException = false;
- try {
- new NGramTokenFilter(input, 0, 1);
- } catch (IllegalArgumentException e) {
- gotException = true;
- }
- assertTrue(gotException);
- }
-
- public void testUnigrams() throws Exception {
- NGramTokenFilter filter = new NGramTokenFilter(input, 1, 1);
- assertTokenStreamContents(filter, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5});
- }
-
- public void testBigrams() throws Exception {
- NGramTokenFilter filter = new NGramTokenFilter(input, 2, 2);
- assertTokenStreamContents(filter, new String[]{"ab","bc","cd","de"}, new int[]{0,1,2,3}, new int[]{2,3,4,5});
- }
-
- public void testNgrams() throws Exception {
- NGramTokenFilter filter = new NGramTokenFilter(input, 1, 3);
- assertTokenStreamContents(filter,
+ private TokenStream input;
+
+ @Override
+ public void setUp() throws Exception {
+ super.setUp();
+ input = new MockTokenizer(new StringReader("abcde"), MockTokenizer.WHITESPACE, false);
+ }
+
+ public void testInvalidInput() throws Exception {
+ boolean gotException = false;
+ try {
+ new NGramTokenFilter(input, 2, 1);
+ } catch (IllegalArgumentException e) {
+ gotException = true;
+ }
+ assertTrue(gotException);
+ }
+
+ public void testInvalidInput2() throws Exception {
+ boolean gotException = false;
+ try {
+ new NGramTokenFilter(input, 0, 1);
+ } catch (IllegalArgumentException e) {
+ gotException = true;
+ }
+ assertTrue(gotException);
+ }
+
+ public void testUnigrams() throws Exception {
+ NGramTokenFilter filter = new NGramTokenFilter(input, 1, 1);
+ assertTokenStreamContents(filter, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5});
+ }
+
+ public void testBigrams() throws Exception {
+ NGramTokenFilter filter = new NGramTokenFilter(input, 2, 2);
+ assertTokenStreamContents(filter, new String[]{"ab","bc","cd","de"}, new int[]{0,1,2,3}, new int[]{2,3,4,5});
+ }
+
+ public void testNgrams() throws Exception {
+ NGramTokenFilter filter = new NGramTokenFilter(input, 1, 3);
+ assertTokenStreamContents(filter,
new String[]{"a","b","c","d","e", "ab","bc","cd","de", "abc","bcd","cde"},
new int[]{0,1,2,3,4, 0,1,2,3, 0,1,2},
new int[]{1,2,3,4,5, 2,3,4,5, 3,4,5}
);
}
-
- public void testOversizedNgrams() throws Exception {
- NGramTokenFilter filter = new NGramTokenFilter(input, 6, 7);
- assertTokenStreamContents(filter, new String[0], new int[0], new int[0]);
- }
-
- public void testSmallTokenInStream() throws Exception {
- input = new MockTokenizer(new StringReader("abc de fgh"), MockTokenizer.WHITESPACE, false);
- NGramTokenFilter filter = new NGramTokenFilter(input, 3, 3);
- assertTokenStreamContents(filter, new String[]{"abc","fgh"}, new int[]{0,7}, new int[]{3,10});
- }
- public void testReset() throws Exception {
- WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("abcde"));
- NGramTokenFilter filter = new NGramTokenFilter(tokenizer, 1, 1);
- assertTokenStreamContents(filter, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5});
- tokenizer.reset(new StringReader("abcde"));
- assertTokenStreamContents(filter, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5});
- }
-
- // LUCENE-3642
- // EdgeNgram blindly adds term length to offset, but this can take things out of bounds
- // wrt original text if a previous filter increases the length of the word (in this case æ -> ae)
- // so in this case we behave like WDF, and preserve any modified offsets
- public void testInvalidOffsets() throws Exception {
- Analyzer analyzer = new ReusableAnalyzerBase() {
- @Override
- protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- TokenFilter filters = new ASCIIFoldingFilter(tokenizer);
- filters = new NGramTokenFilter(filters, 2, 2);
- return new TokenStreamComponents(tokenizer, filters);
- }
- };
- assertAnalyzesTo(analyzer, "mosfellsbær",
- new String[] { "mo", "os", "sf", "fe", "el", "ll", "ls", "sb", "ba", "ae", "er" },
- new int[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
- new int[] { 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11 });
- }
+ public void testOversizedNgrams() throws Exception {
+ NGramTokenFilter filter = new NGramTokenFilter(input, 6, 7);
+ assertTokenStreamContents(filter, new String[0], new int[0], new int[0]);
+ }
+
+ public void testSmallTokenInStream() throws Exception {
+ input = new MockTokenizer(new StringReader("abc de fgh"), MockTokenizer.WHITESPACE, false);
+ NGramTokenFilter filter = new NGramTokenFilter(input, 3, 3);
+ assertTokenStreamContents(filter, new String[]{"abc","fgh"}, new int[]{0,7}, new int[]{3,10});
+ }
+
+ public void testReset() throws Exception {
+ WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("abcde"));
+ NGramTokenFilter filter = new NGramTokenFilter(tokenizer, 1, 1);
+ assertTokenStreamContents(filter, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5});
+ tokenizer.reset(new StringReader("abcde"));
+ assertTokenStreamContents(filter, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5});
+ }
+
+ // LUCENE-3642
+ // EdgeNgram blindly adds term length to offset, but this can take things out of bounds
+ // wrt original text if a previous filter increases the length of the word (in this case æ -> ae)
+ // so in this case we behave like WDF, and preserve any modified offsets
+ public void testInvalidOffsets() throws Exception {
+ Analyzer analyzer = new ReusableAnalyzerBase() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ TokenFilter filters = new ASCIIFoldingFilter(tokenizer);
+ filters = new NGramTokenFilter(filters, 2, 2);
+ return new TokenStreamComponents(tokenizer, filters);
+ }
+ };
+ assertAnalyzesTo(analyzer, "mosfellsbær",
+ new String[] { "mo", "os", "sf", "fe", "el", "ll", "ls", "sb", "ba", "ae", "er" },
+ new int[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 },
+ new int[] { 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11 });
+ }
+
+ /** blast some random strings through the analyzer */
+ public void testRandomStrings() throws Exception {
+ Analyzer a = new ReusableAnalyzerBase() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ return new TokenStreamComponents(tokenizer,
+ new NGramTokenFilter(tokenizer, 2, 15));
+ }
+ };
+ checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+ }
}
Modified: lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java (original)
+++ lucene/dev/branches/branch_3x/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java Tue Jan 24 10:10:56 2012
@@ -18,71 +18,87 @@ package org.apache.lucene.analysis.ngram
*/
+import java.io.Reader;
import java.io.StringReader;
+import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.ReusableAnalyzerBase;
+import org.apache.lucene.analysis.Tokenizer;
/**
* Tests {@link NGramTokenizer} for correctness.
*/
public class NGramTokenizerTest extends BaseTokenStreamTestCase {
- private StringReader input;
-
- @Override
- public void setUp() throws Exception {
- super.setUp();
- input = new StringReader("abcde");
- }
-
- public void testInvalidInput() throws Exception {
- boolean gotException = false;
- try {
- new NGramTokenizer(input, 2, 1);
- } catch (IllegalArgumentException e) {
- gotException = true;
- }
- assertTrue(gotException);
- }
-
- public void testInvalidInput2() throws Exception {
- boolean gotException = false;
- try {
- new NGramTokenizer(input, 0, 1);
- } catch (IllegalArgumentException e) {
- gotException = true;
- }
- assertTrue(gotException);
- }
-
- public void testUnigrams() throws Exception {
- NGramTokenizer tokenizer = new NGramTokenizer(input, 1, 1);
- assertTokenStreamContents(tokenizer, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5}, 5 /* abcde */);
- }
-
- public void testBigrams() throws Exception {
- NGramTokenizer tokenizer = new NGramTokenizer(input, 2, 2);
- assertTokenStreamContents(tokenizer, new String[]{"ab","bc","cd","de"}, new int[]{0,1,2,3}, new int[]{2,3,4,5}, 5 /* abcde */);
- }
-
- public void testNgrams() throws Exception {
- NGramTokenizer tokenizer = new NGramTokenizer(input, 1, 3);
- assertTokenStreamContents(tokenizer,
- new String[]{"a","b","c","d","e", "ab","bc","cd","de", "abc","bcd","cde"},
- new int[]{0,1,2,3,4, 0,1,2,3, 0,1,2},
- new int[]{1,2,3,4,5, 2,3,4,5, 3,4,5},
- 5 /* abcde */
+ private StringReader input;
+
+ @Override
+ public void setUp() throws Exception {
+ super.setUp();
+ input = new StringReader("abcde");
+ }
+
+ public void testInvalidInput() throws Exception {
+ boolean gotException = false;
+ try {
+ new NGramTokenizer(input, 2, 1);
+ } catch (IllegalArgumentException e) {
+ gotException = true;
+ }
+ assertTrue(gotException);
+ }
+
+ public void testInvalidInput2() throws Exception {
+ boolean gotException = false;
+ try {
+ new NGramTokenizer(input, 0, 1);
+ } catch (IllegalArgumentException e) {
+ gotException = true;
+ }
+ assertTrue(gotException);
+ }
+
+ public void testUnigrams() throws Exception {
+ NGramTokenizer tokenizer = new NGramTokenizer(input, 1, 1);
+ assertTokenStreamContents(tokenizer, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5}, 5 /* abcde */);
+ }
+
+ public void testBigrams() throws Exception {
+ NGramTokenizer tokenizer = new NGramTokenizer(input, 2, 2);
+ assertTokenStreamContents(tokenizer, new String[]{"ab","bc","cd","de"}, new int[]{0,1,2,3}, new int[]{2,3,4,5}, 5 /* abcde */);
+ }
+
+ public void testNgrams() throws Exception {
+ NGramTokenizer tokenizer = new NGramTokenizer(input, 1, 3);
+ assertTokenStreamContents(tokenizer,
+ new String[]{"a","b","c","d","e", "ab","bc","cd","de", "abc","bcd","cde"},
+ new int[]{0,1,2,3,4, 0,1,2,3, 0,1,2},
+ new int[]{1,2,3,4,5, 2,3,4,5, 3,4,5},
+ 5 /* abcde */
);
- }
-
- public void testOversizedNgrams() throws Exception {
- NGramTokenizer tokenizer = new NGramTokenizer(input, 6, 7);
- assertTokenStreamContents(tokenizer, new String[0], new int[0], new int[0], 5 /* abcde */);
- }
-
- public void testReset() throws Exception {
- NGramTokenizer tokenizer = new NGramTokenizer(input, 1, 1);
- assertTokenStreamContents(tokenizer, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5}, 5 /* abcde */);
- tokenizer.reset(new StringReader("abcde"));
- assertTokenStreamContents(tokenizer, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5}, 5 /* abcde */);
- }
+ }
+
+ public void testOversizedNgrams() throws Exception {
+ NGramTokenizer tokenizer = new NGramTokenizer(input, 6, 7);
+ assertTokenStreamContents(tokenizer, new String[0], new int[0], new int[0], 5 /* abcde */);
+ }
+
+ public void testReset() throws Exception {
+ NGramTokenizer tokenizer = new NGramTokenizer(input, 1, 1);
+ assertTokenStreamContents(tokenizer, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5}, 5 /* abcde */);
+ tokenizer.reset(new StringReader("abcde"));
+ assertTokenStreamContents(tokenizer, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5}, 5 /* abcde */);
+ }
+
+ /** blast some random strings through the analyzer */
+ public void testRandomStrings() throws Exception {
+ Analyzer a = new ReusableAnalyzerBase() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new NGramTokenizer(reader, 2, 15);
+ return new TokenStreamComponents(tokenizer, tokenizer);
+ }
+ };
+ checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+ }
}
Modified: lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/ReusableAnalyzerBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/ReusableAnalyzerBase.java?rev=1235193&r1=1235192&r2=1235193&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/ReusableAnalyzerBase.java (original)
+++ lucene/dev/branches/branch_3x/lucene/src/java/org/apache/lucene/analysis/ReusableAnalyzerBase.java Tue Jan 24 10:10:56 2012
@@ -44,12 +44,12 @@ public abstract class ReusableAnalyzerBa
* @param fieldName
* the name of the fields content passed to the
* {@link TokenStreamComponents} sink as a reader
- * @param aReader
+ * @param reader
* the reader passed to the {@link Tokenizer} constructor
* @return the {@link TokenStreamComponents} for this analyzer.
*/
protected abstract TokenStreamComponents createComponents(String fieldName,
- Reader aReader);
+ Reader reader);
/**
* This method uses {@link #createComponents(String, Reader)} to obtain an