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

LUCENE-3907: Remove deprecated options (trnk only). 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1479914 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Adrien Grand 2013-05-07 14:03:26 +00:00
parent 582d0f103b
commit cc12d7e659
8 changed files with 48 additions and 395 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramFilterFactory.java
View File

@ -27,21 +27,19 @@ import org.apache.lucene.analysis.util.TokenFilterFactory;
* <fieldType name="text_edgngrm" class="solr.TextField" positionIncrementGap="100">
* <analyzer>
* <tokenizer class="solr.WhitespaceTokenizerFactory"/>
* <filter class="solr.EdgeNGramFilterFactory" side="front" minGramSize="1" maxGramSize="1"/>
* <filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="1"/>
* </analyzer>
* &lt;/fieldType&gt;</pre>
*/
public class EdgeNGramFilterFactory extends TokenFilterFactory {
private final int maxGramSize;
private final int minGramSize;
private final String side;
/** Creates a new EdgeNGramFilterFactory */
public EdgeNGramFilterFactory(Map<String, String> args) {
super(args);
minGramSize = getInt(args, "minGramSize", EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE);
maxGramSize = getInt(args, "maxGramSize", EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);
side = get(args, "side", EdgeNGramTokenFilter.Side.FRONT.getLabel());
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
}
@ -49,6 +47,6 @@ public class EdgeNGramFilterFactory extends TokenFilterFactory {
@Override
public EdgeNGramTokenFilter create(TokenStream input) {
return new EdgeNGramTokenFilter(luceneMatchVersion, input, side, minGramSize, maxGramSize);
return new EdgeNGramTokenFilter(luceneMatchVersion, input, minGramSize, maxGramSize);
}
}

106
lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java
View File

@ -17,69 +17,31 @@ package org.apache.lucene.analysis.ngram;
* limitations under the License.
*/
import java.io.IOException;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.reverse.ReverseStringFilter;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.util.Version;
import java.io.IOException;
/**
* Tokenizes the given token into n-grams of given size(s).
* <p>
* This {@link TokenFilter} create n-grams from the beginning edge or ending edge of a input token.
* <p><a name="version"/>As of Lucene 4.4, this filter does not support
* {@link Side#BACK} (you can use {@link ReverseStringFilter} up-front and
* afterward to get the same behavior) and does not update offsets anymore.
* This {@link TokenFilter} create n-grams from the beginning edge of a input token.
*/
public final class EdgeNGramTokenFilter extends TokenFilter {
public static final Side DEFAULT_SIDE = Side.FRONT;
public static final int DEFAULT_MAX_GRAM_SIZE = 1;
public static final int DEFAULT_MIN_GRAM_SIZE = 1;
/** Specifies which side of the input the n-gram should be generated from */
public static enum Side {
/** Get the n-gram from the front of the input */
FRONT {
@Override
public String getLabel() { return "front"; }
},
/** Get the n-gram from the end of the input */
@Deprecated
BACK {
@Override
public String getLabel() { return "back"; }
};
public abstract String getLabel();
// Get the appropriate Side from a string
public static Side getSide(String sideName) {
if (FRONT.getLabel().equals(sideName)) {
return FRONT;
}
if (BACK.getLabel().equals(sideName)) {
return BACK;
}
return null;
}
}
private final Version version;
private final int minGram;
private final int maxGram;
private Side side;
private char[] curTermBuffer;
private int curTermLength;
private int curGramSize;
private int tokStart;
private int tokEnd; // only used if the length changed before this filter
private boolean updateOffsets; // never if the length changed before this filter
private int savePosIncr;
private boolean isFirstToken = true;
@ -90,28 +52,18 @@ public final class EdgeNGramTokenFilter extends TokenFilter {
/**
* Creates EdgeNGramTokenFilter that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param version the Lucene match version
* @param input {@link TokenStream} holding the input to be tokenized
* @param side the {@link Side} from which to chop off an n-gram
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenFilter(Version version, TokenStream input, Side side, int minGram, int maxGram) {
public EdgeNGramTokenFilter(Version version, TokenStream input, int minGram, int maxGram) {
super(input);
if (version == null) {
throw new IllegalArgumentException("version must not be null");
}
if (version.onOrAfter(Version.LUCENE_44) && side == Side.BACK) {
throw new IllegalArgumentException("Side.BACK is not supported anymore as of Lucene 4.4, use ReverseStringFilter up-front and afterward");
}
if (side == null) {
throw new IllegalArgumentException("sideLabel must be either front or back");
}
if (minGram < 1) {
throw new IllegalArgumentException("minGram must be greater than zero");
}
@ -120,36 +72,8 @@ public final class EdgeNGramTokenFilter extends TokenFilter {
throw new IllegalArgumentException("minGram must not be greater than maxGram");
}
this.version = version;
this.minGram = minGram;
this.maxGram = maxGram;
this.side = side;
}
/**
* Creates EdgeNGramTokenFilter that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param input {@link TokenStream} holding the input to be tokenized
* @param sideLabel the name of the {@link Side} from which to chop off an n-gram
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenFilter(Version version, TokenStream input, String sideLabel, int minGram, int maxGram) {
this(version, input, Side.getSide(sideLabel), minGram, maxGram);
}
/**
* Creates EdgeNGramTokenFilter that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param input {@link TokenStream} holding the input to be tokenized
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
public EdgeNGramTokenFilter(Version version, TokenStream input, int minGram, int maxGram) {
this(version, input, Side.FRONT, minGram, maxGram);
}
@Override
@ -164,28 +88,14 @@ public final class EdgeNGramTokenFilter extends TokenFilter {
curGramSize = minGram;
tokStart = offsetAtt.startOffset();
tokEnd = offsetAtt.endOffset();
if (version.onOrAfter(Version.LUCENE_44)) {
// Never update offsets
updateOffsets = false;
} else {
// if length by start + end offsets doesn't match the term text then assume
// this is a synonym and don't adjust the offsets.
updateOffsets = (tokStart + curTermLength) == tokEnd;
}
savePosIncr = posIncrAtt.getPositionIncrement();
}
}
if (curGramSize <= maxGram) { // if we have hit the end of our n-gram size range, quit
if (curGramSize <= curTermLength) { // if the remaining input is too short, we can't generate any n-grams
// grab gramSize chars from front or back
int start = side == Side.FRONT ? 0 : curTermLength - curGramSize;
int end = start + curGramSize;
clearAttributes();
if (updateOffsets) {
offsetAtt.setOffset(tokStart + start, tokStart + end);
} else {
offsetAtt.setOffset(tokStart, tokEnd);
}
offsetAtt.setOffset(tokStart, tokEnd);
// first ngram gets increment, others don't
if (curGramSize == minGram) {
// Leave the first token position increment at the cleared-attribute value of 1
@ -195,7 +105,7 @@ public final class EdgeNGramTokenFilter extends TokenFilter {
} else {
posIncrAtt.setPositionIncrement(0);
}
termAtt.copyBuffer(curTermBuffer, start, curGramSize);
termAtt.copyBuffer(curTermBuffer, 0, curGramSize);
curGramSize++;
isFirstToken = false;
return true;

150
lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java
View File

@ -30,160 +30,56 @@ import org.apache.lucene.util.Version;
/**
* Tokenizes the input from an edge into n-grams of given size(s).
* <p>
* This {@link Tokenizer} create n-grams from the beginning edge or ending edge of a input token.
* <p><a name="version" /> As of Lucene 4.4, this tokenizer<ul>
* <li>can handle <code>maxGram</code> larger than 1024 chars, but beware that this will result in increased memory usage
* <li>doesn't trim the input,
* <li>sets position increments equal to 1 instead of 1 for the first token and 0 for all other ones
* <li>doesn't support {@link Side#BACK} anymore.
* </ul>
* This {@link Tokenizer} create n-grams from the beginning edge of a input token.
*/
public final class EdgeNGramTokenizer extends Tokenizer {
public static final Side DEFAULT_SIDE = Side.FRONT;
public static final int DEFAULT_MAX_GRAM_SIZE = 1;
public static final int DEFAULT_MIN_GRAM_SIZE = 1;
private Version version;
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
/** Specifies which side of the input the n-gram should be generated from */
public static enum Side {
/** Get the n-gram from the front of the input */
FRONT {
@Override
public String getLabel() { return "front"; }
},
/** Get the n-gram from the end of the input */
@Deprecated
BACK {
@Override
public String getLabel() { return "back"; }
};
public abstract String getLabel();
// Get the appropriate Side from a string
public static Side getSide(String sideName) {
if (FRONT.getLabel().equals(sideName)) {
return FRONT;
}
if (BACK.getLabel().equals(sideName)) {
return BACK;
}
return null;
}
}
private int minGram;
private int maxGram;
private int gramSize;
private Side side;
private boolean started;
private int inLen; // length of the input AFTER trim()
private int charsRead; // length of the input
private String inStr;
/**
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param input {@link Reader} holding the input to be tokenized
* @param side the {@link Side} from which to chop off an n-gram
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenizer(Version version, Reader input, Side side, int minGram, int maxGram) {
super(input);
init(version, side, minGram, maxGram);
}
/**
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param factory {@link org.apache.lucene.util.AttributeSource.AttributeFactory} to use
* @param input {@link Reader} holding the input to be tokenized
* @param side the {@link Side} from which to chop off an n-gram
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenizer(Version version, AttributeFactory factory, Reader input, Side side, int minGram, int maxGram) {
super(factory, input);
init(version, side, minGram, maxGram);
}
/**
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param input {@link Reader} holding the input to be tokenized
* @param sideLabel the name of the {@link Side} from which to chop off an n-gram
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenizer(Version version, Reader input, String sideLabel, int minGram, int maxGram) {
this(version, input, Side.getSide(sideLabel), minGram, maxGram);
}
/**
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param factory {@link org.apache.lucene.util.AttributeSource.AttributeFactory} to use
* @param input {@link Reader} holding the input to be tokenized
* @param sideLabel the name of the {@link Side} from which to chop off an n-gram
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenizer(Version version, AttributeFactory factory, Reader input, String sideLabel, int minGram, int maxGram) {
this(version, factory, input, Side.getSide(sideLabel), minGram, maxGram);
}
/**
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param version the Lucene match version
* @param input {@link Reader} holding the input to be tokenized
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenizer(Version version, Reader input, int minGram, int maxGram) {
this(version, input, Side.FRONT, minGram, maxGram);
super(input);
init(version, minGram, maxGram);
}
/**
* Creates EdgeNGramTokenizer that can generate n-grams in the sizes of the given range
*
* @param version the <a href="#version">Lucene match version</a>
* @param version the Lucene match version
* @param factory {@link org.apache.lucene.util.AttributeSource.AttributeFactory} to use
* @param input {@link Reader} holding the input to be tokenized
* @param minGram the smallest n-gram to generate
* @param maxGram the largest n-gram to generate
*/
@Deprecated
public EdgeNGramTokenizer(Version version, AttributeFactory factory, Reader input, int minGram, int maxGram) {
this(version, factory, input, Side.FRONT, minGram, maxGram);
super(factory, input);
init(version, minGram, maxGram);
}
private void init(Version version, Side side, int minGram, int maxGram) {
private void init(Version version, int minGram, int maxGram) {
if (version == null) {
throw new IllegalArgumentException("version must not be null");
}
if (side == null) {
throw new IllegalArgumentException("sideLabel must be either front or back");
}
if (minGram < 1) {
throw new IllegalArgumentException("minGram must be greater than zero");
}
@ -192,18 +88,8 @@ public final class EdgeNGramTokenizer extends Tokenizer {
throw new IllegalArgumentException("minGram must not be greater than maxGram");
}
if (version.onOrAfter(Version.LUCENE_44)) {
if (side == Side.BACK) {
throw new IllegalArgumentException("Side.BACK is not supported anymore as of Lucene 4.4");
}
} else {
maxGram = Math.min(maxGram, 1024);
}
this.version = version;
this.minGram = minGram;
this.maxGram = maxGram;
this.side = side;
}
/** Returns the next token in the stream, or null at EOS. */
@ -214,27 +100,23 @@ public final class EdgeNGramTokenizer extends Tokenizer {
if (!started) {
started = true;
gramSize = minGram;
final int limit = side == Side.FRONT ? maxGram : 1024;
char[] chars = new char[Math.min(1024, limit)];
char[] chars = new char[Math.min(1024, maxGram)];
charsRead = 0;
// TODO: refactor to a shared readFully somewhere:
boolean exhausted = false;
while (charsRead < limit) {
while (charsRead < maxGram) {
final int inc = input.read(chars, charsRead, chars.length-charsRead);
if (inc == -1) {
exhausted = true;
break;
}
charsRead += inc;
if (charsRead == chars.length && charsRead < limit) {
if (charsRead == chars.length && charsRead < maxGram) {
chars = ArrayUtil.grow(chars);
}
}
inStr = new String(chars, 0, charsRead);
if (!version.onOrAfter(Version.LUCENE_44)) {
inStr = inStr.trim();
}
if (!exhausted) {
// Read extra throwaway chars so that on end() we
@ -254,10 +136,8 @@ public final class EdgeNGramTokenizer extends Tokenizer {
return false;
}
posIncrAtt.setPositionIncrement(1);
} else if (version.onOrAfter(Version.LUCENE_44)) {
posIncrAtt.setPositionIncrement(1);
} else {
posIncrAtt.setPositionIncrement(0);
posIncrAtt.setPositionIncrement(1);
}
// if the remaining input is too short, we can't generate any n-grams
@ -271,10 +151,8 @@ public final class EdgeNGramTokenizer extends Tokenizer {
}
// grab gramSize chars from front or back
int start = side == Side.FRONT ? 0 : inLen - gramSize;
int end = start + gramSize;
termAtt.setEmpty().append(inStr, start, end);
offsetAtt.setOffset(correctOffset(start), correctOffset(end));
termAtt.setEmpty().append(inStr, 0, gramSize);
offsetAtt.setOffset(correctOffset(0), correctOffset(gramSize));
gramSize++;
return true;
}

6
lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerFactory.java
View File

@ -28,21 +28,19 @@ import java.util.Map;
* <pre class="prettyprint">
* &lt;fieldType name="text_edgngrm" class="solr.TextField" positionIncrementGap="100"&gt;
* &lt;analyzer&gt;
* &lt;tokenizer class="solr.EdgeNGramTokenizerFactory" side="front" minGramSize="1" maxGramSize="1"/&gt;
* &lt;tokenizer class="solr.EdgeNGramTokenizerFactory" minGramSize="1" maxGramSize="1"/&gt;
* &lt;/analyzer&gt;
* &lt;/fieldType&gt;</pre>
*/
public class EdgeNGramTokenizerFactory extends TokenizerFactory {
private final int maxGramSize;
private final int minGramSize;
private final String side;
/** Creates a new EdgeNGramTokenizerFactory */
public EdgeNGramTokenizerFactory(Map<String, String> args) {
super(args);
minGramSize = getInt(args, "minGramSize", EdgeNGramTokenizer.DEFAULT_MIN_GRAM_SIZE);
maxGramSize = getInt(args, "maxGramSize", EdgeNGramTokenizer.DEFAULT_MAX_GRAM_SIZE);
side = get(args, "side", EdgeNGramTokenFilter.Side.FRONT.getLabel());
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
}
@ -50,6 +48,6 @@ public class EdgeNGramTokenizerFactory extends TokenizerFactory {
@Override
public EdgeNGramTokenizer create(AttributeFactory factory, Reader input) {
return new EdgeNGramTokenizer(luceneMatchVersion, factory, input, side, minGramSize, maxGramSize);
return new EdgeNGramTokenizer(luceneMatchVersion, factory, input, minGramSize, maxGramSize);
}
}

14
lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
View File

@ -431,20 +431,6 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
}
}
});
put(EdgeNGramTokenizer.Side.class, new ArgProducer() {
@Override public Object create(Random random) {
return random.nextBoolean()
? EdgeNGramTokenizer.Side.FRONT
: EdgeNGramTokenizer.Side.BACK;
}
});
put(EdgeNGramTokenFilter.Side.class, new ArgProducer() {
@Override public Object create(Random random) {
return random.nextBoolean()
? EdgeNGramTokenFilter.Side.FRONT
: EdgeNGramTokenFilter.Side.BACK;
}
});
put(HyphenationTree.class, new ArgProducer() {
@Override public Object create(Random random) {
// TODO: make nastier

85
lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java
View File

@ -19,15 +19,12 @@ package org.apache.lucene.analysis.ngram;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter;
import org.apache.lucene.analysis.position.PositionFilter;
import org.apache.lucene.util.Version;
import java.io.Reader;
import java.io.StringReader;
@ -48,7 +45,7 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
public void testInvalidInput() throws Exception {
boolean gotException = false;
try {
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 0, 0);
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, 0, 0);
} catch (IllegalArgumentException e) {
gotException = true;
}
@ -58,7 +55,7 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
public void testInvalidInput2() throws Exception {
boolean gotException = false;
try {
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 2, 1);
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, 2, 1);
} catch (IllegalArgumentException e) {
gotException = true;
}
@ -68,7 +65,7 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
public void testInvalidInput3() throws Exception {
boolean gotException = false;
try {
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, -1, 2);
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, -1, 2);
} catch (IllegalArgumentException e) {
gotException = true;
}
@ -76,41 +73,23 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
}
public void testFrontUnigram() throws Exception {
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 1, 1);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, 1, 1);
assertTokenStreamContents(tokenizer, new String[]{"a"}, new int[]{0}, new int[]{5});
}
public void testBackUnigram() throws Exception {
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(Version.LUCENE_43, input, EdgeNGramTokenFilter.Side.BACK, 1, 1);
assertTokenStreamContents(tokenizer, new String[]{"e"}, new int[]{4}, new int[]{5});
}
public void testOversizedNgrams() throws Exception {
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 6, 6);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, 6, 6);
assertTokenStreamContents(tokenizer, new String[0], new int[0], new int[0]);
}
public void testFrontRangeOfNgrams() throws Exception {
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 1, 3);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, 1, 3);
assertTokenStreamContents(tokenizer, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{5,5,5});
}
public void testBackRangeOfNgrams() throws Exception {
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(Version.LUCENE_43, input, EdgeNGramTokenFilter.Side.BACK, 1, 3);
assertTokenStreamContents(tokenizer,
new String[]{"e","de","cde"},
new int[]{4,3,2},
new int[]{5,5,5},
null,
null,
null,
null,
false);
}
public void testFilterPositions() throws Exception {
TokenStream ts = new MockTokenizer(new StringReader("abcde vwxyz"), MockTokenizer.WHITESPACE, false);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, ts, EdgeNGramTokenFilter.Side.FRONT, 1, 3);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, ts, 1, 3);
assertTokenStreamContents(tokenizer,
new String[]{"a","ab","abc","v","vw","vwx"},
new int[]{0,0,0,6,6,6},
@ -125,7 +104,7 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
public void testFirstTokenPositionIncrement() throws Exception {
TokenStream ts = new MockTokenizer(new StringReader("a abc"), MockTokenizer.WHITESPACE, false);
ts = new PositionFilter(ts, 0); // All but first token will get 0 position increment
EdgeNGramTokenFilter filter = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, ts, EdgeNGramTokenFilter.Side.FRONT, 2, 3);
EdgeNGramTokenFilter filter = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, ts, 2, 3);
// The first token "a" will not be output, since it's smaller than the mingram size of 2.
// The second token on input to EdgeNGramTokenFilter will have position increment of 0,
// which should be increased to 1, since this is the first output token in the stream.
@ -139,38 +118,18 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
public void testSmallTokenInStream() throws Exception {
input = new MockTokenizer(new StringReader("abc de fgh"), MockTokenizer.WHITESPACE, false);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, EdgeNGramTokenFilter.Side.FRONT, 3, 3);
EdgeNGramTokenFilter tokenizer = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, input, 3, 3);
assertTokenStreamContents(tokenizer, 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"));
EdgeNGramTokenFilter filter = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, EdgeNGramTokenFilter.Side.FRONT, 1, 3);
EdgeNGramTokenFilter filter = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, 1, 3);
assertTokenStreamContents(filter, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{5,5,5});
tokenizer.setReader(new StringReader("abcde"));
assertTokenStreamContents(filter, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{5,5,5});
}
// 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 Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
TokenFilter filters = new ASCIIFoldingFilter(tokenizer);
filters = new EdgeNGramTokenFilter(Version.LUCENE_43, filters, EdgeNGramTokenFilter.Side.FRONT, 2, 15);
return new TokenStreamComponents(tokenizer, filters);
}
};
assertAnalyzesTo(analyzer, "mosfellsbær",
new String[] { "mo", "mos", "mosf", "mosfe", "mosfel", "mosfell", "mosfells", "mosfellsb", "mosfellsba", "mosfellsbae", "mosfellsbaer" },
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 Analyzer() {
@ -178,20 +137,10 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
return new TokenStreamComponents(tokenizer,
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, EdgeNGramTokenFilter.Side.FRONT, 2, 4));
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, 2, 4));
}
};
checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER);
Analyzer b = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
return new TokenStreamComponents(tokenizer,
new EdgeNGramTokenFilter(Version.LUCENE_43, tokenizer, EdgeNGramTokenFilter.Side.BACK, 2, 4));
}
};
checkRandomData(random(), b, 1000*RANDOM_MULTIPLIER, 20, false, false);
}
public void testEmptyTerm() throws Exception {
@ -201,19 +150,9 @@ public class EdgeNGramTokenFilterTest extends BaseTokenStreamTestCase {
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new KeywordTokenizer(reader);
return new TokenStreamComponents(tokenizer,
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, EdgeNGramTokenFilter.Side.FRONT, 2, 15));
new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, 2, 15));
}
};
checkAnalysisConsistency(random, a, random.nextBoolean(), "");
Analyzer b = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new KeywordTokenizer(reader);
return new TokenStreamComponents(tokenizer,
new EdgeNGramTokenFilter(Version.LUCENE_43, tokenizer, EdgeNGramTokenFilter.Side.BACK, 2, 15));
}
};
checkAnalysisConsistency(random, b, random.nextBoolean(), "");
}
}

52
lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java
View File

@ -28,7 +28,6 @@ import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.util.Version;
import org.apache.lucene.util._TestUtil;
/**
@ -46,7 +45,7 @@ public class EdgeNGramTokenizerTest extends BaseTokenStreamTestCase {
public void testInvalidInput() throws Exception {
boolean gotException = false;
try {
new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, EdgeNGramTokenizer.Side.FRONT, 0, 0);
new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, 0, 0);
} catch (IllegalArgumentException e) {
gotException = true;
}
@ -56,7 +55,7 @@ public class EdgeNGramTokenizerTest extends BaseTokenStreamTestCase {
public void testInvalidInput2() throws Exception {
boolean gotException = false;
try {
new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, EdgeNGramTokenizer.Side.FRONT, 2, 1);
new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, 2, 1);
} catch (IllegalArgumentException e) {
gotException = true;
}
@ -66,7 +65,7 @@ public class EdgeNGramTokenizerTest extends BaseTokenStreamTestCase {
public void testInvalidInput3() throws Exception {
boolean gotException = false;
try {
new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, EdgeNGramTokenizer.Side.FRONT, -1, 2);
new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, -1, 2);
} catch (IllegalArgumentException e) {
gotException = true;
}
@ -74,32 +73,22 @@ public class EdgeNGramTokenizerTest extends BaseTokenStreamTestCase {
}
public void testFrontUnigram() throws Exception {
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, EdgeNGramTokenizer.Side.FRONT, 1, 1);
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, 1, 1);
assertTokenStreamContents(tokenizer, new String[]{"a"}, new int[]{0}, new int[]{1}, 5 /* abcde */);
}
public void testBackUnigram() throws Exception {
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(Version.LUCENE_43, input, EdgeNGramTokenizer.Side.BACK, 1, 1);
assertTokenStreamContents(tokenizer, new String[]{"e"}, new int[]{4}, new int[]{5}, 5 /* abcde */);
}
public void testOversizedNgrams() throws Exception {
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, EdgeNGramTokenizer.Side.FRONT, 6, 6);
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, 6, 6);
assertTokenStreamContents(tokenizer, new String[0], new int[0], new int[0], 5 /* abcde */);
}
public void testFrontRangeOfNgrams() throws Exception {
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, EdgeNGramTokenizer.Side.FRONT, 1, 3);
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, 1, 3);
assertTokenStreamContents(tokenizer, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{1,2,3}, 5 /* abcde */);
}
public void testBackRangeOfNgrams() throws Exception {
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(Version.LUCENE_43, input, EdgeNGramTokenizer.Side.BACK, 1, 3);
assertTokenStreamContents(tokenizer, new String[]{"e","de","cde"}, new int[]{4,3,2}, new int[]{5,5,5}, null, null, null, 5 /* abcde */, false);
}
public void testReset() throws Exception {
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, EdgeNGramTokenizer.Side.FRONT, 1, 3);
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, input, 1, 3);
assertTokenStreamContents(tokenizer, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{1,2,3}, 5 /* abcde */);
tokenizer.setReader(new StringReader("abcde"));
assertTokenStreamContents(tokenizer, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{1,2,3}, 5 /* abcde */);
@ -110,37 +99,16 @@ public class EdgeNGramTokenizerTest extends BaseTokenStreamTestCase {
Analyzer a = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, reader, EdgeNGramTokenizer.Side.FRONT, 2, 4);
Tokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, reader, 2, 4);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER, 20, false, false);
checkRandomData(random(), a, 100*RANDOM_MULTIPLIER, 8192, false, false);
Analyzer b = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new EdgeNGramTokenizer(Version.LUCENE_43, reader, EdgeNGramTokenizer.Side.BACK, 2, 4);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
checkRandomData(random(), b, 1000*RANDOM_MULTIPLIER, 20, false, false);
checkRandomData(random(), b, 100*RANDOM_MULTIPLIER, 8192, false, false);
}
public void testTokenizerPositions() throws Exception {
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(Version.LUCENE_43, new StringReader("abcde"), EdgeNGramTokenizer.Side.FRONT, 1, 3);
assertTokenStreamContents(tokenizer,
new String[]{"a","ab","abc"},
new int[]{0,0,0},
new int[]{1,2,3},
null,
new int[] {1,0,0},
null,
null,
false);
tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, new StringReader("abcde"), EdgeNGramTokenizer.Side.FRONT, 1, 3);
EdgeNGramTokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, new StringReader("abcde"), 1, 3);
assertTokenStreamContents(tokenizer,
new String[]{"a","ab","abc"},
new int[]{0,0,0},
@ -156,7 +124,7 @@ public class EdgeNGramTokenizerTest extends BaseTokenStreamTestCase {
final String input = _TestUtil.randomSimpleString(random(), 1024 * 5);
final int minGram = _TestUtil.nextInt(random(), 1, 1024);
final int maxGram = _TestUtil.nextInt(random(), minGram, 5 * 1024);
EdgeNGramTokenizer tk = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, new StringReader(input), EdgeNGramTokenizer.Side.FRONT, minGram, maxGram);
EdgeNGramTokenizer tk = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, new StringReader(input), minGram, maxGram);
final CharTermAttribute charTermAtt = tk.addAttribute(CharTermAttribute.class);
final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
final PositionIncrementAttribute posIncAtt = tk.addAttribute(PositionIncrementAttribute.class);

24
lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/TestNGramFilters.java
View File

@ -23,7 +23,6 @@ import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
import org.apache.lucene.util.Version;
/**
* Simple tests to ensure the NGram filter factories are working.
@ -97,17 +96,6 @@ public class TestNGramFilters extends BaseTokenStreamFactoryTestCase {
new String[] { "t", "te" });
}
/**
* Test EdgeNGramTokenizerFactory with side option
*/
public void testEdgeNGramTokenizer3() throws Exception {
Reader reader = new StringReader("ready");
TokenStream stream = tokenizerFactory("EdgeNGram", Version.LUCENE_43,
"side", "back").create(reader);
assertTokenStreamContents(stream,
new String[] { "y" });
}
/**
* Test EdgeNGramFilterFactory
*/
@ -131,18 +119,6 @@ public class TestNGramFilters extends BaseTokenStreamFactoryTestCase {
assertTokenStreamContents(stream,
new String[] { "t", "te" });
}
/**
* Test EdgeNGramFilterFactory with side option
*/
public void testEdgeNGramFilter3() throws Exception {
Reader reader = new StringReader("ready");
TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
stream = tokenFilterFactory("EdgeNGram", Version.LUCENE_43,
"side", "back").create(stream);
assertTokenStreamContents(stream,
new String[] { "y" });
}
/** Test that bogus arguments result in exception */
public void testBogusArguments() throws Exception {