You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by us...@apache.org on 2011/06/13 18:14:50 UTC
svn commit: r1135156 - in /lucene/dev/branches/branch_3x: ./ lucene/
lucene/backwards/ lucene/backwards/src/test-framework/
lucene/backwards/src/test/ solr/ solr/src/java/org/apache/solr/handler/
solr/src/test/org/apache/solr/handler/
Author: uschindler
Date: Mon Jun 13 16:14:49 2011
New Revision: 1135156
URL: http://svn.apache.org/viewvc?rev=1135156&view=rev
Log:
SOLR-2400: Use int[] for position history in serialization
Modified:
lucene/dev/branches/branch_3x/ (props changed)
lucene/dev/branches/branch_3x/lucene/ (props changed)
lucene/dev/branches/branch_3x/lucene/backwards/ (props changed)
lucene/dev/branches/branch_3x/lucene/backwards/src/test/ (props changed)
lucene/dev/branches/branch_3x/lucene/backwards/src/test-framework/ (props changed)
lucene/dev/branches/branch_3x/solr/ (props changed)
lucene/dev/branches/branch_3x/solr/CHANGES.txt
lucene/dev/branches/branch_3x/solr/src/java/org/apache/solr/handler/AnalysisRequestHandlerBase.java
lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/AnalysisRequestHandlerTestBase.java
lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/DocumentAnalysisRequestHandlerTest.java
lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java
Modified: lucene/dev/branches/branch_3x/solr/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/solr/CHANGES.txt?rev=1135156&r1=1135155&r2=1135156&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/solr/CHANGES.txt (original)
+++ lucene/dev/branches/branch_3x/solr/CHANGES.txt Mon Jun 13 16:14:49 2011
@@ -33,8 +33,8 @@ New Features
* SOLR-2400: Field- and DocumentAnalysisRequestHandler now provide a position
history for each token, so you can follow the token through all analysis stages.
- The output contains a separate string attribute, that is a "/"-delimited string
- containing all positions from previous Tokenizers/TokenFilters.
+ The output contains a separate int[] attribute containing all positions from
+ previous Tokenizers/TokenFilters (called "positionHistory").
(Uwe Schindler)
Optimizations
Modified: lucene/dev/branches/branch_3x/solr/src/java/org/apache/solr/handler/AnalysisRequestHandlerBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/solr/src/java/org/apache/solr/handler/AnalysisRequestHandlerBase.java?rev=1135156&r1=1135155&r2=1135156&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/solr/src/java/org/apache/solr/handler/AnalysisRequestHandlerBase.java (original)
+++ lucene/dev/branches/branch_3x/solr/src/java/org/apache/solr/handler/AnalysisRequestHandlerBase.java Mon Jun 13 16:14:49 2011
@@ -46,6 +46,7 @@ import java.io.IOException;
import java.io.StringReader;
import java.util.*;
import java.math.BigInteger;
+import org.apache.commons.lang.ArrayUtils;
/**
* A base class for all analysis request handlers.
@@ -378,26 +379,30 @@ public abstract class AnalysisRequestHan
public static final class TokenTrackingAttributeImpl extends AttributeImpl implements TokenTrackingAttribute {
private int[] basePositions = new int[0];
private int position = 0;
+ private transient int[] cachedPositions = null;
public void freezeStage() {
this.basePositions = getPositions();
this.position = 0;
+ this.cachedPositions = null;
}
public void setActPosition(int pos) {
this.position = pos;
+ this.cachedPositions = null;
}
public int[] getPositions() {
- final int[] positions = new int[basePositions.length + 1];
- System.arraycopy(basePositions, 0, positions, 0, basePositions.length);
- positions[basePositions.length] = position;
- return positions;
+ if (cachedPositions == null) {
+ cachedPositions = ArrayUtils.add(basePositions, position);
+ }
+ return cachedPositions;
}
public void reset(int[] basePositions, int position) {
this.basePositions = basePositions;
this.position = position;
+ this.cachedPositions = null;
}
@Override
@@ -407,14 +412,9 @@ public abstract class AnalysisRequestHan
@Override
public void reflectWith(AttributeReflector reflector) {
- final int[] positions = getPositions();
- final StringBuilder sb = new StringBuilder(positions.length * 2);
- for (int p : positions) {
- if (sb.length() > 0) sb.append('/');
- sb.append(p);
- }
- reflector.reflect(TokenTrackingAttribute.class, "positionHistory", sb.toString());
reflector.reflect(TokenTrackingAttribute.class, "position", position);
+ // convert to Integer[] array, as only such one can be serialized by ResponseWriters
+ reflector.reflect(TokenTrackingAttribute.class, "positionHistory", ArrayUtils.toObject(getPositions()));
}
@Override
Modified: lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/AnalysisRequestHandlerTestBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/AnalysisRequestHandlerTestBase.java?rev=1135156&r1=1135155&r2=1135156&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/AnalysisRequestHandlerTestBase.java (original)
+++ lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/AnalysisRequestHandlerTestBase.java Mon Jun 13 16:14:49 2011
@@ -19,6 +19,7 @@ package org.apache.solr.handler;
import org.apache.solr.SolrTestCaseJ4;
import org.apache.solr.common.util.NamedList;
+import org.apache.commons.lang.ArrayUtils;
/**
* A base class for all analysis request handler tests.
@@ -37,7 +38,7 @@ public abstract class AnalysisRequestHan
assertEquals(new Integer(info.getStart()), token.get("start"));
assertEquals(new Integer(info.getEnd()), token.get("end"));
assertEquals(new Integer(info.getPosition()), token.get("position"));
- assertEquals(info.getPositionHistory(), token.get("positionHistory"));
+ assertArrayEquals(info.getPositionHistory(), ArrayUtils.toPrimitive((Integer[]) token.get("positionHistory")));
if (info.isMatch()) {
assertEquals(Boolean.TRUE, token.get("match"));
}
@@ -58,7 +59,7 @@ public abstract class AnalysisRequestHan
private int end;
private String payload;
private int position;
- private String positionHistory;
+ private int[] positionHistory;
private boolean match;
public TokenInfo(
@@ -68,7 +69,7 @@ public abstract class AnalysisRequestHan
int start,
int end,
int position,
- String positionHistory,
+ int[] positionHistory,
String payload,
boolean match) {
@@ -111,7 +112,7 @@ public abstract class AnalysisRequestHan
return position;
}
- public String getPositionHistory() {
+ public int[] getPositionHistory() {
return positionHistory;
}
Modified: lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/DocumentAnalysisRequestHandlerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/DocumentAnalysisRequestHandlerTest.java?rev=1135156&r1=1135155&r2=1135156&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/DocumentAnalysisRequestHandlerTest.java (original)
+++ lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/DocumentAnalysisRequestHandlerTest.java Mon Jun 13 16:14:49 2011
@@ -235,7 +235,7 @@ public class DocumentAnalysisRequestHand
assertTrue("Only the default analyzer should be applied", name.matches("org.apache.solr.schema.FieldType\\$DefaultAnalyzer.*"));
List<NamedList> tokenList = (List<NamedList>) queryResult.getVal(0);
assertEquals("Query has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "word", 0, 7, 1, "1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "word", 0, 7, 1, new int[]{1}, null, false));
NamedList<Object> indexResult = idResult.get("index");
assertEquals("The id field has only a single value", 1, indexResult.size());
@@ -245,7 +245,7 @@ public class DocumentAnalysisRequestHand
assertTrue("Only the default analyzer should be applied", name.matches("org.apache.solr.schema.FieldType\\$DefaultAnalyzer.*"));
tokenList = valueResult.getVal(0);
assertEquals("The 'id' field value has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("1", null, "word", 0, 1, 1, "1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("1", null, "word", 0, 1, 1, new int[]{1}, null, false));
***/
// the name field
@@ -255,14 +255,14 @@ public class DocumentAnalysisRequestHand
tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.WhitespaceTokenizer");
assertNotNull("Expecting the 'WhitespaceTokenizer' to be applied on the query for the 'whitetok' field", tokenList);
assertEquals("Query has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "word", 0, 7, 1, "1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "word", 0, 7, 1, new int[]{1}, null, false));
indexResult = whitetokResult.get("index");
assertEquals("The 'whitetok' field has only a single value", 1, indexResult.size());
valueResult = (NamedList<List<NamedList>>) indexResult.get("Jumping Jack");
tokenList = valueResult.getVal(0);
assertEquals("Expecting 2 tokens to be present", 2, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("Jumping", null, "word", 0, 7, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("Jack", null, "word", 8, 12, 2, "2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("Jumping", null, "word", 0, 7, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("Jack", null, "word", 8, 12, 2, new int[]{2}, null, false));
// the text field
NamedList<NamedList<Object>> textResult = documentResult.get("text");
@@ -271,66 +271,66 @@ public class DocumentAnalysisRequestHand
tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.standard.StandardTokenizer");
assertNotNull("Expecting the 'StandardTokenizer' to be applied on the query for the 'text' field", tokenList);
assertEquals("Query has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "<ALPHANUM>", 0, 7, 1, "1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "<ALPHANUM>", 0, 7, 1, new int[]{1}, null, false));
tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.standard.StandardFilter");
assertNotNull("Expecting the 'StandardFilter' to be applied on the query for the 'text' field", tokenList);
assertEquals("Query has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "<ALPHANUM>", 0, 7, 1, "1/1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("JUMPING", null, "<ALPHANUM>", 0, 7, 1, new int[]{1,1}, null, false));
tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.LowerCaseFilter");
assertNotNull("Expecting the 'LowerCaseFilter' to be applied on the query for the 'text' field", tokenList);
assertEquals("Query has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("jumping", null, "<ALPHANUM>", 0, 7, 1, "1/1/1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("jumping", null, "<ALPHANUM>", 0, 7, 1, new int[]{1,1,1}, null, false));
tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.StopFilter");
assertNotNull("Expecting the 'StopFilter' to be applied on the query for the 'text' field", tokenList);
assertEquals("Query has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("jumping", null, "<ALPHANUM>", 0, 7, 1, "1/1/1/1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("jumping", null, "<ALPHANUM>", 0, 7, 1, new int[]{1,1,1,1}, null, false));
tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.PorterStemFilter");
assertNotNull("Expecting the 'PorterStemFilter' to be applied on the query for the 'text' field", tokenList);
assertEquals("Query has only one token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("jump", null, "<ALPHANUM>", 0, 7, 1, "1/1/1/1/1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("jump", null, "<ALPHANUM>", 0, 7, 1, new int[]{1,1,1,1,1}, null, false));
indexResult = textResult.get("index");
assertEquals("The 'text' field has only a single value", 1, indexResult.size());
valueResult = (NamedList<List<NamedList>>) indexResult.get("The Fox Jumped Over The Dogs");
tokenList = valueResult.get("org.apache.lucene.analysis.standard.StandardTokenizer");
assertNotNull("Expecting the 'StandardTokenizer' to be applied on the index for the 'text' field", tokenList);
assertEquals("Expecting 6 tokens", 6, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("The", null, "<ALPHANUM>", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("Fox", null, "<ALPHANUM>", 4, 7, 2, "2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("Jumped", null, "<ALPHANUM>", 8, 14, 3, "3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("Over", null, "<ALPHANUM>", 15, 19, 4, "4", null, false));
- assertToken(tokenList.get(4), new TokenInfo("The", null, "<ALPHANUM>", 20, 23, 5, "5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("Dogs", null, "<ALPHANUM>", 24, 28, 6, "6", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("The", null, "<ALPHANUM>", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("Fox", null, "<ALPHANUM>", 4, 7, 2, new int[]{2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("Jumped", null, "<ALPHANUM>", 8, 14, 3, new int[]{3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("Over", null, "<ALPHANUM>", 15, 19, 4, new int[]{4}, null, false));
+ assertToken(tokenList.get(4), new TokenInfo("The", null, "<ALPHANUM>", 20, 23, 5, new int[]{5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("Dogs", null, "<ALPHANUM>", 24, 28, 6, new int[]{6}, null, false));
tokenList = valueResult.get("org.apache.lucene.analysis.standard.StandardFilter");
assertNotNull("Expecting the 'StandardFilter' to be applied on the index for the 'text' field", tokenList);
assertEquals("Expecting 6 tokens", 6, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("The", null, "<ALPHANUM>", 0, 3, 1, "1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("Fox", null, "<ALPHANUM>", 4, 7, 2, "2/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("Jumped", null, "<ALPHANUM>", 8, 14, 3, "3/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("Over", null, "<ALPHANUM>", 15, 19, 4, "4/4", null, false));
- assertToken(tokenList.get(4), new TokenInfo("The", null, "<ALPHANUM>", 20, 23, 5, "5/5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("Dogs", null, "<ALPHANUM>", 24, 28, 6, "6/6", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("The", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("Fox", null, "<ALPHANUM>", 4, 7, 2, new int[]{2,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("Jumped", null, "<ALPHANUM>", 8, 14, 3, new int[]{3,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("Over", null, "<ALPHANUM>", 15, 19, 4, new int[]{4,4}, null, false));
+ assertToken(tokenList.get(4), new TokenInfo("The", null, "<ALPHANUM>", 20, 23, 5, new int[]{5,5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("Dogs", null, "<ALPHANUM>", 24, 28, 6, new int[]{6,6}, null, false));
tokenList = valueResult.get("org.apache.lucene.analysis.LowerCaseFilter");
assertNotNull("Expecting the 'LowerCaseFilter' to be applied on the index for the 'text' field", tokenList);
assertEquals("Expecting 6 tokens", 6, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, "1/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("fox", null, "<ALPHANUM>", 4, 7, 2, "2/2/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("jumped", null, "<ALPHANUM>", 8, 14, 3, "3/3/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("over", null, "<ALPHANUM>", 15, 19, 4, "4/4/4", null, false));
- assertToken(tokenList.get(4), new TokenInfo("the", null, "<ALPHANUM>", 20, 23, 5, "5/5/5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("dogs", null, "<ALPHANUM>", 24, 28, 6, "6/6/6", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("fox", null, "<ALPHANUM>", 4, 7, 2, new int[]{2,2,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("jumped", null, "<ALPHANUM>", 8, 14, 3, new int[]{3,3,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("over", null, "<ALPHANUM>", 15, 19, 4, new int[]{4,4,4}, null, false));
+ assertToken(tokenList.get(4), new TokenInfo("the", null, "<ALPHANUM>", 20, 23, 5, new int[]{5,5,5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("dogs", null, "<ALPHANUM>", 24, 28, 6, new int[]{6,6,6}, null, false));
tokenList = valueResult.get("org.apache.lucene.analysis.StopFilter");
assertNotNull("Expecting the 'StopFilter' to be applied on the index for the 'text' field", tokenList);
assertEquals("Expecting 4 tokens after stop word removal", 4, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 4, 7, 1, "2/2/2/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("jumped", null, "<ALPHANUM>", 8, 14, 2, "3/3/3/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("over", null, "<ALPHANUM>", 15, 19, 3, "4/4/4/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("dogs", null, "<ALPHANUM>", 24, 28, 4, "6/6/6/4", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 4, 7, 1, new int[]{2,2,2,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("jumped", null, "<ALPHANUM>", 8, 14, 2, new int[]{3,3,3,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("over", null, "<ALPHANUM>", 15, 19, 3, new int[]{4,4,4,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("dogs", null, "<ALPHANUM>", 24, 28, 4, new int[]{6,6,6,4}, null, false));
tokenList = valueResult.get("org.apache.lucene.analysis.PorterStemFilter");
assertNotNull("Expecting the 'PorterStemFilter' to be applied on the index for the 'text' field", tokenList);
assertEquals("Expecting 4 tokens", 4, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 4, 7, 1, "2/2/2/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("jump", null, "<ALPHANUM>", 8, 14, 2, "3/3/3/2/2", null, true));
- assertToken(tokenList.get(2), new TokenInfo("over", null, "<ALPHANUM>", 15, 19, 3, "4/4/4/3/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("dog", null, "<ALPHANUM>", 24, 28, 4, "6/6/6/4/4", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 4, 7, 1, new int[]{2,2,2,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("jump", null, "<ALPHANUM>", 8, 14, 2, new int[]{3,3,3,2,2}, null, true));
+ assertToken(tokenList.get(2), new TokenInfo("over", null, "<ALPHANUM>", 15, 19, 3, new int[]{4,4,4,3,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("dog", null, "<ALPHANUM>", 24, 28, 4, new int[]{6,6,6,4,4}, null, false));
}
}
Modified: lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java?rev=1135156&r1=1135155&r2=1135156&view=diff
==============================================================================
--- lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java (original)
+++ lucene/dev/branches/branch_3x/solr/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java Mon Jun 13 16:14:49 2011
@@ -139,64 +139,64 @@ public class FieldAnalysisRequestHandler
List<NamedList> tokenList = indexPart.get("org.apache.lucene.analysis.standard.StandardTokenizer");
assertNotNull("Expcting StandardTokenizer analysis breakdown", tokenList);
assertEquals(tokenList.size(), 10);
- assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 2, "2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 3, "3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 4, "4", null, true));
- assertToken(tokenList.get(4), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 5, "5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 6, "6", null, false));
- assertToken(tokenList.get(6), new TokenInfo("the", null, "<ALPHANUM>", 30, 33, 7, "7", null, false));
- assertToken(tokenList.get(7), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 8, "8", null, false));
- assertToken(tokenList.get(8), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 9, "9", null, true));
- assertToken(tokenList.get(9), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 10, "10", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 2, new int[]{2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 3, new int[]{3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 4, new int[]{4}, null, true));
+ assertToken(tokenList.get(4), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 5, new int[]{5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 6, new int[]{6}, null, false));
+ assertToken(tokenList.get(6), new TokenInfo("the", null, "<ALPHANUM>", 30, 33, 7, new int[]{7}, null, false));
+ assertToken(tokenList.get(7), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 8, new int[]{8}, null, false));
+ assertToken(tokenList.get(8), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 9, new int[]{9}, null, true));
+ assertToken(tokenList.get(9), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 10, new int[]{10}, null, false));
tokenList = indexPart.get("org.apache.lucene.analysis.standard.StandardFilter");
assertNotNull("Expcting StandardFilter analysis breakdown", tokenList);
assertEquals(tokenList.size(), 10);
- assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, "1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 2, "2/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 3, "3/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 4, "4/4", null, true));
- assertToken(tokenList.get(4), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 5, "5/5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 6, "6/6", null, false));
- assertToken(tokenList.get(6), new TokenInfo("the", null, "<ALPHANUM>", 30, 33, 7, "7/7", null, false));
- assertToken(tokenList.get(7), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 8, "8/8", null, false));
- assertToken(tokenList.get(8), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 9, "9/9", null, true));
- assertToken(tokenList.get(9), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 10, "10/10", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 2, new int[]{2,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 3, new int[]{3,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 4, new int[]{4,4}, null, true));
+ assertToken(tokenList.get(4), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 5, new int[]{5,5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 6, new int[]{6,6}, null, false));
+ assertToken(tokenList.get(6), new TokenInfo("the", null, "<ALPHANUM>", 30, 33, 7, new int[]{7,7}, null, false));
+ assertToken(tokenList.get(7), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 8, new int[]{8,8}, null, false));
+ assertToken(tokenList.get(8), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 9, new int[]{9,9}, null, true));
+ assertToken(tokenList.get(9), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 10, new int[]{10,10}, null, false));
tokenList = indexPart.get("org.apache.lucene.analysis.LowerCaseFilter");
assertNotNull("Expcting LowerCaseFilter analysis breakdown", tokenList);
assertEquals(tokenList.size(), 10);
- assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, "1/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 2, "2/2/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 3, "3/3/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 4, "4/4/4", null, true));
- assertToken(tokenList.get(4), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 5, "5/5/5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 6, "6/6/6", null, false));
- assertToken(tokenList.get(6), new TokenInfo("the", null, "<ALPHANUM>", 30, 33, 7, "7/7/7", null, false));
- assertToken(tokenList.get(7), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 8, "8/8/8", null, false));
- assertToken(tokenList.get(8), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 9, "9/9/9", null, true));
- assertToken(tokenList.get(9), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 10, "10/10/10", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("the", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 2, new int[]{2,2,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 3, new int[]{3,3,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 4, new int[]{4,4,4}, null, true));
+ assertToken(tokenList.get(4), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 5, new int[]{5,5,5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 6, new int[]{6,6,6}, null, false));
+ assertToken(tokenList.get(6), new TokenInfo("the", null, "<ALPHANUM>", 30, 33, 7, new int[]{7,7,7}, null, false));
+ assertToken(tokenList.get(7), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 8, new int[]{8,8,8}, null, false));
+ assertToken(tokenList.get(8), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 9, new int[]{9,9,9}, null, true));
+ assertToken(tokenList.get(9), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 10, new int[]{10,10,10}, null, false));
tokenList = indexPart.get("org.apache.lucene.analysis.StopFilter");
assertNotNull("Expcting StopFilter analysis breakdown", tokenList);
assertEquals(tokenList.size(), 8);
- assertToken(tokenList.get(0), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 1, "2/2/2/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 2, "3/3/3/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 3, "4/4/4/3", null, true));
- assertToken(tokenList.get(3), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 4, "5/5/5/4", null, false));
- assertToken(tokenList.get(4), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 5, "6/6/6/5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 6, "8/8/8/6", null, false));
- assertToken(tokenList.get(6), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 7, "9/9/9/7", null, true));
- assertToken(tokenList.get(7), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 8, "10/10/10/8", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 1, new int[]{2,2,2,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 2, new int[]{3,3,3,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 3, new int[]{4,4,4,3}, null, true));
+ assertToken(tokenList.get(3), new TokenInfo("jumped", null, "<ALPHANUM>", 18, 24, 4, new int[]{5,5,5,4}, null, false));
+ assertToken(tokenList.get(4), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 5, new int[]{6,6,6,5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 6, new int[]{8,8,8,6}, null, false));
+ assertToken(tokenList.get(6), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 7, new int[]{9,9,9,7}, null, true));
+ assertToken(tokenList.get(7), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 8, new int[]{10,10,10,8}, null, false));
tokenList = indexPart.get("org.apache.lucene.analysis.PorterStemFilter");
assertNotNull("Expcting PorterStemFilter analysis breakdown", tokenList);
assertEquals(tokenList.size(), 8);
- assertToken(tokenList.get(0), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 1, "2/2/2/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 2, "3/3/3/2/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 3, "4/4/4/3/3", null, true));
- assertToken(tokenList.get(3), new TokenInfo("jump", null, "<ALPHANUM>", 18, 24, 4, "5/5/5/4/4", null, false));
- assertToken(tokenList.get(4), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 5, "6/6/6/5/5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("lazi", null, "<ALPHANUM>", 34, 38, 6, "8/8/8/6/6", null, false));
- assertToken(tokenList.get(6), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 7, "9/9/9/7/7", null, true));
- assertToken(tokenList.get(7), new TokenInfo("dog", null, "<ALPHANUM>", 45, 49, 8, "10/10/10/8/8", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 1, new int[]{2,2,2,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 2, new int[]{3,3,3,2,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("fox", null, "<ALPHANUM>", 14, 17, 3, new int[]{4,4,4,3,3}, null, true));
+ assertToken(tokenList.get(3), new TokenInfo("jump", null, "<ALPHANUM>", 18, 24, 4, new int[]{5,5,5,4,4}, null, false));
+ assertToken(tokenList.get(4), new TokenInfo("over", null, "<ALPHANUM>", 25, 29, 5, new int[]{6,6,6,5,5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("lazi", null, "<ALPHANUM>", 34, 38, 6, new int[]{8,8,8,6,6}, null, false));
+ assertToken(tokenList.get(6), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 7, new int[]{9,9,9,7,7}, null, true));
+ assertToken(tokenList.get(7), new TokenInfo("dog", null, "<ALPHANUM>", 45, 49, 8, new int[]{10,10,10,8,8}, null, false));
NamedList<List<NamedList>> queryPart = textType.get("query");
assertNotNull("expecting a query token analysis for field type 'text'", queryPart);
@@ -204,28 +204,28 @@ public class FieldAnalysisRequestHandler
tokenList = queryPart.get("org.apache.lucene.analysis.standard.StandardTokenizer");
assertNotNull("Expecting StandardTokenizer analysis breakdown", tokenList);
assertEquals("Expecting StandardTokenizer to produce 2 tokens from '" + request.getQuery() + "'", 2, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, "2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, new int[]{2}, null, false));
tokenList = queryPart.get("org.apache.lucene.analysis.standard.StandardFilter");
assertNotNull("Expcting StandardFilter analysis breakdown", tokenList);
assertEquals(2, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, "1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, "2/2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, new int[]{2,2}, null, false));
tokenList = queryPart.get("org.apache.lucene.analysis.LowerCaseFilter");
assertNotNull("Expcting LowerCaseFilter analysis breakdown", tokenList);
assertEquals(2, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, "1/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, "2/2/2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, new int[]{2,2,2}, null, false));
tokenList = queryPart.get("org.apache.lucene.analysis.StopFilter");
assertNotNull("Expcting StopFilter analysis breakdown", tokenList);
assertEquals(2, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, "1/1/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, "2/2/2/2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, new int[]{2,2,2,2}, null, false));
tokenList = queryPart.get("org.apache.lucene.analysis.PorterStemFilter");
assertNotNull("Expcting PorterStemFilter analysis breakdown", tokenList);
assertEquals(2, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, "1/1/1/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, "2/2/2/2/2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, new int[]{1,1,1,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, new int[]{2,2,2,2,2}, null, false));
NamedList<NamedList> nameTextType = fieldTypes.get("nametext");
assertNotNull("expecting result for field type 'nametext'", nameTextType);
@@ -236,22 +236,22 @@ public class FieldAnalysisRequestHandler
tokenList = indexPart.get("org.apache.lucene.analysis.WhitespaceTokenizer");
assertNotNull("Expcting WhitespaceTokenizer analysis breakdown", tokenList);
assertEquals(10, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("the", null, "word", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("quick", null, "word", 4, 9, 2, "2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("red", null, "word", 10, 13, 3, "3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("fox", null, "word", 14, 17, 4, "4", null, true));
- assertToken(tokenList.get(4), new TokenInfo("jumped", null, "word", 18, 24, 5, "5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("over", null, "word", 25, 29, 6, "6", null, false));
- assertToken(tokenList.get(6), new TokenInfo("the", null, "word", 30, 33, 7, "7", null, false));
- assertToken(tokenList.get(7), new TokenInfo("lazy", null, "word", 34, 38, 8, "8", null, false));
- assertToken(tokenList.get(8), new TokenInfo("brown", null, "word", 39, 44, 9, "9", null, true));
- assertToken(tokenList.get(9), new TokenInfo("dogs", null, "word", 45, 49, 10, "10", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("the", null, "word", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("quick", null, "word", 4, 9, 2, new int[]{2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("red", null, "word", 10, 13, 3, new int[]{3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("fox", null, "word", 14, 17, 4, new int[]{4}, null, true));
+ assertToken(tokenList.get(4), new TokenInfo("jumped", null, "word", 18, 24, 5, new int[]{5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("over", null, "word", 25, 29, 6, new int[]{6}, null, false));
+ assertToken(tokenList.get(6), new TokenInfo("the", null, "word", 30, 33, 7, new int[]{7}, null, false));
+ assertToken(tokenList.get(7), new TokenInfo("lazy", null, "word", 34, 38, 8, new int[]{8}, null, false));
+ assertToken(tokenList.get(8), new TokenInfo("brown", null, "word", 39, 44, 9, new int[]{9}, null, true));
+ assertToken(tokenList.get(9), new TokenInfo("dogs", null, "word", 45, 49, 10, new int[]{10}, null, false));
queryPart = nameTextType.get("query");
assertNotNull("expecting a query token analysis for field type 'nametext'", queryPart);
tokenList = queryPart.get(WhitespaceTokenizer.class.getName());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "word", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("brown", null, "word", 4, 9, 2, "2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "word", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("brown", null, "word", 4, 9, 2, new int[]{2}, null, false));
NamedList<NamedList> fieldNames = result.get("field_names");
assertNotNull("field_nameds should never be null", fieldNames);
@@ -265,16 +265,16 @@ public class FieldAnalysisRequestHandler
tokenList = indexPart.get(WhitespaceTokenizer.class.getName());
assertNotNull("expecting only WhitespaceTokenizer to be applied", tokenList);
assertEquals("expecting WhitespaceTokenizer to produce 10 tokens", 10, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("the", null, "word", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("quick", null, "word", 4, 9, 2, "2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("red", null, "word", 10, 13, 3, "3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("fox", null, "word", 14, 17, 4, "4", null, true));
- assertToken(tokenList.get(4), new TokenInfo("jumped", null, "word", 18, 24, 5, "5", null, false));
- assertToken(tokenList.get(5), new TokenInfo("over", null, "word", 25, 29, 6, "6", null, false));
- assertToken(tokenList.get(6), new TokenInfo("the", null, "word", 30, 33, 7, "7", null, false));
- assertToken(tokenList.get(7), new TokenInfo("lazy", null, "word", 34, 38, 8, "8", null, false));
- assertToken(tokenList.get(8), new TokenInfo("brown", null, "word", 39, 44, 9, "9", null, true));
- assertToken(tokenList.get(9), new TokenInfo("dogs", null, "word", 45, 49, 10, "10", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("the", null, "word", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("quick", null, "word", 4, 9, 2, new int[]{2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("red", null, "word", 10, 13, 3, new int[]{3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("fox", null, "word", 14, 17, 4, new int[]{4}, null, true));
+ assertToken(tokenList.get(4), new TokenInfo("jumped", null, "word", 18, 24, 5, new int[]{5}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("over", null, "word", 25, 29, 6, new int[]{6}, null, false));
+ assertToken(tokenList.get(6), new TokenInfo("the", null, "word", 30, 33, 7, new int[]{7}, null, false));
+ assertToken(tokenList.get(7), new TokenInfo("lazy", null, "word", 34, 38, 8, new int[]{8}, null, false));
+ assertToken(tokenList.get(8), new TokenInfo("brown", null, "word", 39, 44, 9, new int[]{9}, null, true));
+ assertToken(tokenList.get(9), new TokenInfo("dogs", null, "word", 45, 49, 10, new int[]{10}, null, false));
queryPart = whitetok.get("query");
assertNotNull("expecting a query token analysis for field 'whitetok'", queryPart);
@@ -282,8 +282,8 @@ public class FieldAnalysisRequestHandler
tokenList = queryPart.get(WhitespaceTokenizer.class.getName());
assertNotNull("expecting only WhitespaceTokenizer to be applied", tokenList);
assertEquals("expecting WhitespaceTokenizer to produce 2 tokens", 2, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox", null, "word", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("brown", null, "word", 4, 9, 2, "2", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox", null, "word", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("brown", null, "word", 4, 9, 2, new int[]{2}, null, false));
NamedList<NamedList> keywordtok = fieldNames.get("keywordtok");
assertNotNull("expecting result for field 'keywordtok'", keywordtok);
@@ -294,7 +294,7 @@ public class FieldAnalysisRequestHandler
tokenList = indexPart.get(KeywordTokenizer.class.getName());
assertNotNull("expecting only KeywordTokenizer to be applied", tokenList);
assertEquals("expecting KeywordTokenizer to produce 1 token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("the quick red fox jumped over the lazy brown dogs", null, "word", 0, 49, 1, "1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("the quick red fox jumped over the lazy brown dogs", null, "word", 0, 49, 1, new int[]{1}, null, false));
queryPart = keywordtok.get("query");
assertNotNull("expecting a query token analysis for field 'keywordtok'", queryPart);
@@ -302,7 +302,7 @@ public class FieldAnalysisRequestHandler
tokenList = queryPart.get(KeywordTokenizer.class.getName());
assertNotNull("expecting only KeywordTokenizer to be applied", tokenList);
assertEquals("expecting KeywordTokenizer to produce 1 token", 1, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("fox brown", null, "word", 0, 9, 1, "1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("fox brown", null, "word", 0, 9, 1, new int[]{1}, null, false));
}
@@ -331,7 +331,7 @@ public class FieldAnalysisRequestHandler
List<NamedList> tokenList = (List<NamedList>)indexPart.get("org.apache.lucene.analysis.WhitespaceTokenizer");
assertNotNull("Expecting WhitespaceTokenizer analysis breakdown", tokenList);
assertEquals(tokenList.size(), 1);
- assertToken(tokenList.get(0), new TokenInfo("whatever", null, "word", 12, 20, 1, "1", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("whatever", null, "word", 12, 20, 1, new int[]{1}, null, false));
}
@Test
@@ -356,28 +356,28 @@ public class FieldAnalysisRequestHandler
List<NamedList> tokenList = indexPart.get("org.apache.lucene.analysis.WhitespaceTokenizer");
assertNotNull("Expcting WhitespaceTokenizer analysis breakdown", tokenList);
assertEquals(4, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("hi,", null, "word", 0, 3, 1, "1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("3456-12", null, "word", 4, 11, 2, "2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("a", null, "word", 12, 13, 3, "3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("Test", null, "word", 14, 18, 4, "4", null, false));
- tokenList = indexPart.get("org.apache.solr.analysis.WordDelimiterFilter");
+ assertToken(tokenList.get(0), new TokenInfo("hi,", null, "word", 0, 3, 1, new int[]{1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("3456-12", null, "word", 4, 11, 2, new int[]{2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("a", null, "word", 12, 13, 3, new int[]{3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("Test", null, "word", 14, 18, 4, new int[]{4}, null, false));
+ tokenList = indexPart.get("org.apache.solr.analysis.WordDelimiterFilter");
assertNotNull("Expcting WordDelimiterFilter analysis breakdown", tokenList);
assertEquals(6, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("hi", null, "word", 0, 2, 1, "1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("3456", null, "word", 4, 8, 2, "2/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("12", null, "word", 9, 11, 3, "2/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("345612", null, "word", 4, 11, 3, "2/3", null, false));
- assertToken(tokenList.get(4), new TokenInfo("a", null, "word", 12, 13, 4, "3/4", null, false));
- assertToken(tokenList.get(5), new TokenInfo("Test", null, "word", 14, 18, 5, "4/5", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("hi", null, "word", 0, 2, 1, new int[]{1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("3456", null, "word", 4, 8, 2, new int[]{2,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("12", null, "word", 9, 11, 3, new int[]{2,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("345612", null, "word", 4, 11, 3, new int[]{2,3}, null, false));
+ assertToken(tokenList.get(4), new TokenInfo("a", null, "word", 12, 13, 4, new int[]{3,4}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("Test", null, "word", 14, 18, 5, new int[]{4,5}, null, false));
tokenList = indexPart.get("org.apache.lucene.analysis.LowerCaseFilter");
assertNotNull("Expcting LowerCaseFilter analysis breakdown", tokenList);
assertEquals(6, tokenList.size());
- assertToken(tokenList.get(0), new TokenInfo("hi", null, "word", 0, 2, 1, "1/1/1", null, false));
- assertToken(tokenList.get(1), new TokenInfo("3456", null, "word", 4, 8, 2, "2/2/2", null, false));
- assertToken(tokenList.get(2), new TokenInfo("12", null, "word", 9, 11, 3, "2/3/3", null, false));
- assertToken(tokenList.get(3), new TokenInfo("345612", null, "word", 4, 11, 3, "2/3/3", null, false));
- assertToken(tokenList.get(4), new TokenInfo("a", null, "word", 12, 13, 4, "3/4/4", null, false));
- assertToken(tokenList.get(5), new TokenInfo("test", null, "word", 14, 18, 5, "4/5/5", null, false));
+ assertToken(tokenList.get(0), new TokenInfo("hi", null, "word", 0, 2, 1, new int[]{1,1,1}, null, false));
+ assertToken(tokenList.get(1), new TokenInfo("3456", null, "word", 4, 8, 2, new int[]{2,2,2}, null, false));
+ assertToken(tokenList.get(2), new TokenInfo("12", null, "word", 9, 11, 3, new int[]{2,3,3}, null, false));
+ assertToken(tokenList.get(3), new TokenInfo("345612", null, "word", 4, 11, 3, new int[]{2,3,3}, null, false));
+ assertToken(tokenList.get(4), new TokenInfo("a", null, "word", 12, 13, 4, new int[]{3,4,4}, null, false));
+ assertToken(tokenList.get(5), new TokenInfo("test", null, "word", 14, 18, 5, new int[]{4,5,5}, null, false));
}
}