Revision: 16583
http://sourceforge.net/p/gate/code/16583
Author: valyt
Date: 2013-03-12 13:07:53 +0000 (Tue, 12 Mar 2013)
Log Message:
-----------
Removed no-op class AbstractTermsQuery.
More default stop-words: single digits and letters.
Added support for multiple strategies when combining counts from multiple
sub-queries.
Modified Paths:
--------------
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractCompoundTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractDocumentsBasedTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractIndexTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AndTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AnnotationTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/LimitTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/OrTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/SortedTermsQuery.java
mimir/trunk/mimir-core/src/gate/mimir/search/terms/TermTypeTermsQuery.java
Removed Paths:
-------------
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractTermsQuery.java
Modified:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractCompoundTermsQuery.java
===================================================================
---
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractCompoundTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractCompoundTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -23,10 +23,46 @@
* Abstract base class for {@link TermQuery} implementations that wrap a group
* of {@link TermQuery} sub-queries.
*/
-public abstract class AbstractCompoundTermsQuery extends AbstractTermsQuery
- implements CompoundTermsQuery{
+public abstract class AbstractCompoundTermsQuery implements CompoundTermsQuery{
/**
+ * Enum describing different ways term counts can be calculated for a
compound
+ * terms query.
+ *
+ * A compound terms query produces its result set by combining the result
sets
+ * from a set of constituent sub-queries. When each of the sub-queries
+ * supplies potentially different counts for the same term, different
+ * strategies can be employed for deriving the output term count for the
+ * compound query.
+ */
+ public static enum CompoundCountsStrategy {
+
+ /**
+ * The output count is the count from the first sub-query found to supply
a
+ * count for each output term.
+ */
+ FIRST,
+
+ /**
+ * The output count is the maximum count from all of the sub-queries for
+ * each output term.
+ */
+ MAX,
+
+ /**
+ * The output count is the minimum count from all of the sub-queries for
+ * each output term.
+ */
+ MIN,
+
+ /**
+ * The output count is the sum of the counts from all of the sub-queries
for
+ * each output term.
+ */
+ SUM
+ }
+
+ /**
* The wrapped wrappedQuery
*/
protected TermsQuery[] subQueries;
@@ -62,4 +98,66 @@
}
return combine(resSets);
}
+
+ protected AbstractCompoundTermsQuery.CompoundCountsStrategy countsStrategy;
+
+ /**
+ * Gets the current counts strategy. See
+ * {@link #setCountsStrategy(CompoundCountsStrategy)} for more details.
+ * @return the countsStrategy
+ */
+ public AbstractCompoundTermsQuery.CompoundCountsStrategy getCountsStrategy()
{
+ return countsStrategy;
+ }
+
+ /**
+ * A compound terms query produces its result set by combining the result
sets
+ * from a set of constituent sub-queries. When each of the sub-queries
+ * supplies potentially different counts for the same term, different
+ * strategies can be employed for deriving the output term count for the
+ * compound query. This method can be used to set what strategy should be
used
+ * when generating output counts.
+ *
+ * @param countsStrategy the countsStrategy to set
+ */
+ public void
setCountsStrategy(AbstractCompoundTermsQuery.CompoundCountsStrategy
countsStrategy) {
+ this.countsStrategy = countsStrategy;
+ }
+
+ /**
+ * Given an array of counts, compute the output count taking into account the
+ * provided {@link #countsStrategy}.
+ * @param counts an array of count values. Zero and negative values are
+ * ignored (interpreted as count not available).
+ * @param countsStrategy the chosen counts strategy.
+ * @return the computed output count.
+ */
+ protected static int computeCompoundCount(final int[] counts,
+ final CompoundCountsStrategy countsStrategy) {
+ int count = 0;
+ counts:for(int aCount : counts) {
+ if(aCount > 0) {
+ switch(countsStrategy){
+ case FIRST:
+ if(count <= 0) count = aCount;
+ break counts;
+ case MAX:
+ if(aCount > count) count = aCount;
+ break;
+ case MIN:
+ if(aCount < count) count = aCount;
+ break;
+ case SUM:
+ count += aCount;
+ break;
+ default:
+ throw new IllegalArgumentException("Unknown count strategy " +
+ countsStrategy.toString());
+ }
+ }
+ }
+ return count;
+ }
+
+
}
Modified:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractDocumentsBasedTermsQuery.java
===================================================================
---
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractDocumentsBasedTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractDocumentsBasedTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -20,7 +20,7 @@
* search.
*/
public abstract class AbstractDocumentsBasedTermsQuery
- extends AbstractTermsQuery implements DocumentsBasedTermsQuery {
+ implements DocumentsBasedTermsQuery {
/**
* Serialization ID.
Modified:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractIndexTermsQuery.java
===================================================================
---
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractIndexTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractIndexTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -41,7 +41,9 @@
*/
private static final long serialVersionUID = 8382919427152317859L;
- private static final Logger logger =
Logger.getLogger(AbstractIndexTermsQuery.class);
+ private static final Logger logger = Logger
+ .getLogger(AbstractIndexTermsQuery.class);
+
/**
* The name of the subindex in which the terms are sought. Each Mímir index
* includes multiple sub-indexes (some storing tokens, other storing
@@ -111,47 +113,50 @@
*/
public static final String[] DEFAULT_STOP_WORDS = new String[]{",", ".", "?",
"!", ":", ";", "#", "~", "^", "@", "%", "&", "(", ")", "[", "]", "{", "}",
- "|", "\\", "<", ">", "-", "+", "*", "/", "=", "a", "about", "above",
- "above", "across", "after", "afterwards", "again", "against", "all",
- "almost", "alone", "along", "already", "also", "although", "always", "am",
- "among", "amongst", "amoungst", "amount", "an", "and", "another", "any",
- "anyhow", "anyone", "anything", "anyway", "anywhere", "are", "around",
- "as", "at", "back", "be", "became", "because", "become", "becomes",
- "becoming", "been", "before", "beforehand", "behind", "being", "below",
- "beside", "besides", "between", "beyond", "bill", "both", "bottom", "but",
- "by", "call", "can", "cannot", "cant", "co", "con", "could", "couldnt",
- "cry", "de", "describe", "detail", "do", "done", "down", "due", "during",
- "each", "eg", "eight", "either", "eleven", "else", "elsewhere", "empty",
- "enough", "etc", "even", "ever", "every", "everyone", "everything",
- "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire",
- "first", "five", "for", "former", "formerly", "forty", "found", "four",
- "from", "front", "full", "further", "get", "give", "go", "had", "has",
- "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby",
- "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how",
- "however", "hundred", "ie", "if", "in", "inc", "indeed", "interest",
- "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly",
- "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might",
- "mill", "mine", "more", "moreover", "most", "mostly", "move", "much",
- "must", "my", "myself", "name", "namely", "neither", "never",
- "nevertheless", "next", "nine", "no", "nobody", "none", "noone", "nor",
- "not", "nothing", "now", "nowhere", "of", "off", "often", "on", "once",
- "one", "only", "onto", "or", "other", "others", "otherwise", "our", "ours",
- "ourselves", "out", "over", "own", "part", "per", "perhaps", "please",
- "put", "rather", "re", "same", "see", "seem", "seemed", "seeming", "seems",
- "serious", "several", "she", "should", "show", "side", "since", "sincere",
- "six", "sixty", "so", "some", "somehow", "someone", "something",
- "sometime", "sometimes", "somewhere", "still", "such", "system", "take",
- "ten", "than", "that", "the", "their", "them", "themselves", "then",
- "thence", "there", "thereafter", "thereby", "therefore", "therein",
+ "|", "\\", "<", ">", "-", "+", "*", "/", "=", "'", "\"", "'s", "1", "2",
+ "3", "4", "5", "6", "7", "8", "9", "0", "a", "about", "above", "above",
+ "across", "after", "afterwards", "again", "against", "all", "almost",
+ "alone", "along", "already", "also", "although", "always", "am", "among",
+ "amongst", "amoungst", "amount", "an", "and", "another", "any", "anyhow",
+ "anyone", "anything", "anyway", "anywhere", "are", "around", "as", "at",
+ "b", "back", "be", "became", "because", "become", "becomes", "becoming",
+ "been", "before", "beforehand", "behind", "being", "below", "beside",
+ "besides", "between", "beyond", "bill", "both", "bottom", "but", "by", "c",
+ "call", "can", "cannot", "cant", "co", "con", "could", "couldnt", "cry",
+ "d", "de", "describe", "detail", "do", "done", "down", "due", "during",
+ "e", "each", "eg", "eight", "either", "eleven", "else", "elsewhere",
+ "empty", "enough", "etc", "even", "ever", "every", "everyone",
+ "everything", "everywhere", "except", "f", "few", "fifteen", "fify",
+ "fill", "find", "fire", "first", "five", "for", "former", "formerly",
+ "forty", "found", "four", "from", "front", "full", "further", "g", "get",
+ "give", "go", "h", "had", "has", "hasnt", "have", "he", "hence", "her",
+ "here", "hereafter", "hereby", "herein", "hereupon", "hers", "herself",
+ "him", "himself", "his", "how", "however", "hundred", "i", "ie", "if",
+ "in", "inc", "indeed", "interest", "into", "is", "it", "its", "itself",
+ "j", "k", "keep", "l", "last", "latter", "latterly", "least", "less",
+ "ltd", "m", "made", "many", "may", "me", "meanwhile", "might", "mill",
+ "mine", "more", "moreover", "most", "mostly", "move", "much", "must", "my",
+ "myself", "n", "name", "namely", "neither", "never", "nevertheless",
+ "next", "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing",
+ "now", "nowhere", "o", "of", "off", "often", "on", "once", "one", "only",
+ "onto", "or", "other", "others", "otherwise", "our", "ours", "ourselves",
+ "out", "over", "own", "p", "part", "per", "perhaps", "please", "put", "q",
+ "r", "rather", "re", "s", "same", "see", "seem", "seemed", "seeming",
+ "seems", "serious", "several", "she", "should", "show", "side", "since",
+ "sincere", "six", "sixty", "so", "some", "somehow", "someone", "something",
+ "sometime", "sometimes", "somewhere", "still", "such", "system", "t",
+ "take", "ten", "than", "that", "the", "their", "them", "themselves",
+ "then", "thence", "there", "thereafter", "thereby", "therefore", "therein",
"thereupon", "these", "they", "thickv", "thin", "third", "this", "those",
"though", "three", "through", "throughout", "thru", "thus", "to",
"together", "too", "top", "toward", "towards", "twelve", "twenty", "two",
- "un", "under", "until", "up", "upon", "us", "very", "via", "was", "we",
- "well", "were", "what", "whatever", "when", "whence", "whenever", "where",
- "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever",
- "whether", "which", "while", "whither", "who", "whoever", "whole", "whom",
- "whose", "why", "will", "with", "within", "without", "would", "yet", "you",
- "your", "yours", "yourself", "yourselves"};
+ "u", "un", "under", "until", "up", "upon", "us", "v", "very", "via", "w",
+ "was", "we", "well", "were", "what", "whatever", "when", "whence",
+ "whenever", "where", "whereafter", "whereas", "whereby", "wherein",
+ "whereupon", "wherever", "whether", "which", "while", "whither", "who",
+ "whoever", "whole", "whom", "whose", "why", "will", "with", "within",
+ "without", "would", "x", "y", "yet", "you", "your", "yours", "yourself",
+ "yourselves", "z"};
/**
* @param indexName
@@ -170,7 +175,7 @@
* URIs whose format depends on the actual implementation of the
* index. These strings make little sense outside of the index. If
* this is set to <code>true</code>, then term descriptions are also
- * included in the results set. See
+ * included in the results set. See
* {@link TermsResultSet#termDescriptions} and
* {@link SemanticAnnotationHelper#describeMention(String)}. Setting
* this to <code>true</code> has no effect if the index being
@@ -184,8 +189,8 @@
this.indexName = indexName;
this.indexType = indexType;
this.countsEnabled = countsEnabled;
- this.describeAnnotations = describeAnnotations &&
- (indexType == IndexType.ANNOTATIONS);
+ this.describeAnnotations =
+ describeAnnotations && (indexType == IndexType.ANNOTATIONS);
}
/**
@@ -226,8 +231,8 @@
throws IOException {
// prepare local data
ObjectArrayList<String> termStrings = new ObjectArrayList<String>();
- ObjectArrayList<String> termDescriptions = describeAnnotations ?
- new ObjectArrayList<String>() : null;
+ ObjectArrayList<String> termDescriptions =
+ describeAnnotations ? new ObjectArrayList<String>() : null;
IntArrayList termCounts = countsEnabled ? new IntArrayList() : null;
TermCollectionVisitor termCollectionVisitor = null;
CounterSetupVisitor counterSetupVisitor = null;
@@ -258,10 +263,11 @@
}
String termString = null;
// get the term string
- try{
+ try {
termString = indirectIndexPool.getTerm(termId);
- } catch (Exception e) {
- System.err.println("Error reading indirect index term with ID " +
termId);
+ } catch(Exception e) {
+ System.err.println("Error reading indirect index term with ID " +
+ termId);
e.printStackTrace();
termId = documentIterator.nextDocument();
continue terms;
@@ -278,10 +284,9 @@
continue terms;
}
if(describeAnnotations) {
- termDescriptions.add(annotationHelper.describeMention(termString));
+ termDescriptions.add(annotationHelper.describeMention(termString));
}
}
-
termStrings.add(termString);
if(countsEnabled) {
termCounts.add(termCount);
@@ -289,12 +294,12 @@
termId = documentIterator.nextDocument();
}
// construct the result
- TermsResultSet res = new TermsResultSet(
- termStrings.toArray(new String[termStrings.size()]),
- null,
- countsEnabled ? termCounts.toIntArray() : null,
- describeAnnotations ?
- termDescriptions.toArray(new String[termDescriptions.size()]) : null);
+ TermsResultSet res =
+ new TermsResultSet(termStrings.toArray(new String[termStrings.size()]),
+ null, countsEnabled ? termCounts.toIntArray() : null,
+ describeAnnotations
+ ? termDescriptions.toArray(new String[termDescriptions.size()])
+ : null);
if(describeAnnotations) res = TermsResultSet.groupByDescription(res);
return res;
}
@@ -350,5 +355,4 @@
for(String sw : stopWords)
this.stopWords.add(sw);
}
-
}
Deleted:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractTermsQuery.java
===================================================================
--- mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++ mimir/trunk/mimir-core/src/gate/mimir/search/terms/AbstractTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -1,42 +0,0 @@
-/*
- * AbstractTermsQuery.java
- *
- * Copyright (c) 2007-2011, The University of Sheffield.
- *
- * This file is part of GATE Mímir (see http://gate.ac.uk/family/mimir.html),
- * and is free software, licenced under the GNU Lesser General Public License,
- * Version 3, June 2007 (also included with this distribution as file
- * LICENCE-LGPL3.html).
- *
- * Valentin Tablan, 13 Jul 2012
- *
- * $Id$
- */
-package gate.mimir.search.terms;
-
-import java.io.IOException;
-
-import gate.mimir.search.QueryEngine;
-
-
-/**
- * Base class for term queries.
- */
-public abstract class AbstractTermsQuery implements TermsQuery{
-
- /**
- * Serialization ID.
- */
- private static final long serialVersionUID = -8448110711378800097L;
-
- public AbstractTermsQuery() {
- }
-
-
-
- @Override
- public TermsResultSet execute(QueryEngine engine) throws IOException {
- // TODO Auto-generated method stub
- return null;
- }
-}
Modified: mimir/trunk/mimir-core/src/gate/mimir/search/terms/AndTermsQuery.java
===================================================================
--- mimir/trunk/mimir-core/src/gate/mimir/search/terms/AndTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++ mimir/trunk/mimir-core/src/gate/mimir/search/terms/AndTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -14,6 +14,7 @@
*/
package gate.mimir.search.terms;
+import
gate.mimir.search.terms.AbstractCompoundTermsQuery.CompoundCountsStrategy;
import it.unimi.dsi.fastutil.Arrays;
import it.unimi.dsi.fastutil.Swapper;
import it.unimi.dsi.fastutil.ints.IntArrayList;
@@ -22,6 +23,8 @@
/**
* Performs Boolean AND between multiple {@link TermsQuery} instances.
+ * The default count strategy used is
+ * {@link AbstractCompoundTermsQuery.CompoundCountsStrategy#FIRST}.
*/
public class AndTermsQuery extends AbstractCompoundTermsQuery {
@@ -42,6 +45,7 @@
*/
public AndTermsQuery(TermsQuery... subQueries) {
super(subQueries);
+ setCountsStrategy(AbstractCompoundTermsQuery.CompoundCountsStrategy.FIRST);
}
/* (non-Javadoc)
@@ -49,10 +53,12 @@
*/
@Override
public TermsResultSet combine(TermsResultSet... resSets) {
- return andResultSets(resSets);
+ return andResultSets(resSets, countsStrategy);
}
- public static TermsResultSet andResultSets(final TermsResultSet[] resSets) {
+ public static TermsResultSet andResultSets(final TermsResultSet[] resSets,
+ AbstractCompoundTermsQuery.CompoundCountsStrategy countsStrategy) {
+ if(countsStrategy == null) countsStrategy =
AbstractCompoundTermsQuery.CompoundCountsStrategy.FIRST;
boolean lengthsAvailable = false;
boolean countsAvailable = true;
boolean descriptionsAvaialble = false;
@@ -71,25 +77,28 @@
// all sub-queries must provide counts, for us to be able to
if(resSets[i].termCounts == null) countsAvailable = false;
}
- // optimisation: sort sub-runners by increasing sizes
- Arrays.quickSort(0, resSets.length, new IntComparator() {
- @Override
- public int compare(Integer o1, Integer o2) {
- return compare(o1.intValue(), o2.intValue());
- }
- @Override
- public int compare(int k1, int k2) {
- return resSets[k1].termStrings.length -
resSets[k2].termStrings.length;
- }
- }, new Swapper() {
- @Override
- public void swap(int a, int b) {
- TermsResultSet trs = resSets[a];
- resSets[a] = resSets[b];
- resSets[b] = trs;
- }
- });
-
+ if(!countsAvailable || countsStrategy !=
AbstractCompoundTermsQuery.CompoundCountsStrategy.FIRST) {
+ // the sorting of sub-queries is irrelevant
+ // optimisation: sort sub-runners by increasing sizes
+ Arrays.quickSort(0, resSets.length, new IntComparator() {
+ @Override
+ public int compare(Integer o1, Integer o2) {
+ return compare(o1.intValue(), o2.intValue());
+ }
+ @Override
+ public int compare(int k1, int k2) {
+ return resSets[k1].termStrings.length -
resSets[k2].termStrings.length;
+ }
+ }, new Swapper() {
+ @Override
+ public void swap(int a, int b) {
+ TermsResultSet trs = resSets[a];
+ resSets[a] = resSets[b];
+ resSets[b] = trs;
+ }
+ });
+ }
+
// prepare local data
ObjectArrayList<String> termStrings = new ObjectArrayList<String>();
ObjectArrayList<String> termDescriptions = descriptionsAvaialble ?
@@ -114,13 +123,12 @@
termStrings.add(termString);
// calculate the term count
if(countsAvailable) {
- int count = 0;
+ int[] counts = new int[resSets.length];
for(int i = 0; i < resSets.length; i++) {
- if(resSets[i].termCounts != null) {
- count += resSets[i].termCounts[indexes[i]];
- }
+ counts[i] = (resSets[i].termCounts != null) ?
+ (resSets[i].termCounts[indexes[i]]): -1;
}
- termCounts.add(count);
+
termCounts.add(AbstractCompoundTermsQuery.computeCompoundCount(counts,
countsStrategy));
}
// calculate the term length
if(lengthsAvailable) {
Modified:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AnnotationTermsQuery.java
===================================================================
---
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AnnotationTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++
mimir/trunk/mimir-core/src/gate/mimir/search/terms/AnnotationTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -32,7 +32,7 @@
* Given an {@link AnnotationQuery}, this finds the set of terms that satisfy
* it.
*/
-public class AnnotationTermsQuery extends AbstractTermsQuery {
+public class AnnotationTermsQuery implements TermsQuery {
/**
* Serialization ID.
Modified:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/LimitTermsQuery.java
===================================================================
--- mimir/trunk/mimir-core/src/gate/mimir/search/terms/LimitTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++ mimir/trunk/mimir-core/src/gate/mimir/search/terms/LimitTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -84,4 +84,13 @@
return trs;
}
}
+
+
+ /**
+ * This method has no effect, as the number of sub-queries is always 1.
+ */
+ @Override
+ public void
setCountsStrategy(AbstractCompoundTermsQuery.CompoundCountsStrategy
countsStrategy) {
+ super.setCountsStrategy(countsStrategy);
+ }
}
Modified: mimir/trunk/mimir-core/src/gate/mimir/search/terms/OrTermsQuery.java
===================================================================
--- mimir/trunk/mimir-core/src/gate/mimir/search/terms/OrTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++ mimir/trunk/mimir-core/src/gate/mimir/search/terms/OrTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -20,6 +20,8 @@
/**
* Boolean OR operator for term queries.
+ * The default count strategy used is
+ * {@link AbstractCompoundTermsQuery.CompoundCountsStrategy#FIRST}.
*/
public class OrTermsQuery extends AbstractCompoundTermsQuery {
@@ -40,6 +42,7 @@
*/
public OrTermsQuery(TermsQuery... subQueries) {
super(subQueries);
+ setCountsStrategy(AbstractCompoundTermsQuery.CompoundCountsStrategy.FIRST);
}
/* (non-Javadoc)
@@ -47,7 +50,7 @@
*/
@Override
public TermsResultSet combine(TermsResultSet... resSets) {
- return orResultsSets(resSets);
+ return orResultsSets(resSets, countsStrategy);
}
/**
@@ -57,7 +60,9 @@
* @param resSets
* @return
*/
- public static TermsResultSet orResultsSets(TermsResultSet... resSets) {
+ public static TermsResultSet orResultsSets(TermsResultSet[] resSets,
+ AbstractCompoundTermsQuery.CompoundCountsStrategy countsStrategy) {
+ if(countsStrategy == null) countsStrategy =
AbstractCompoundTermsQuery.CompoundCountsStrategy.FIRST;
String[] currentTerm = new String[resSets.length];
ObjectHeapSemiIndirectPriorityQueue<String> queue =
new ObjectHeapSemiIndirectPriorityQueue<String>(currentTerm);
@@ -109,12 +114,12 @@
if(countsAvailable) {
// sum all counts
int frontSize = queue.front(front);
- int count = 0;
+ int[] counts = new int[frontSize];
for(int i = 0; i < frontSize; i++) {
int subRunnerId = front[i];
- count += resSets[subRunnerId].termCounts[termIndex[subRunnerId]];
+ counts[i]= resSets[subRunnerId].termCounts[termIndex[subRunnerId]];
}
- termCounts.add(count);
+ termCounts.add(AbstractCompoundTermsQuery.computeCompoundCount(counts,
countsStrategy));
}
// consume all equal terms
while(resSets[first].termStrings[termIndex[first]].equals(termString)) {
Modified:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/SortedTermsQuery.java
===================================================================
--- mimir/trunk/mimir-core/src/gate/mimir/search/terms/SortedTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++ mimir/trunk/mimir-core/src/gate/mimir/search/terms/SortedTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -14,6 +14,7 @@
*/
package gate.mimir.search.terms;
+import
gate.mimir.search.terms.AbstractCompoundTermsQuery.CompoundCountsStrategy;
import it.unimi.dsi.fastutil.Arrays;
import it.unimi.dsi.fastutil.ints.IntComparator;
@@ -148,4 +149,12 @@
}, new TermsResultSet.Swapper(trs));
return trs;
}
+
+ /**
+ * This method has no effect, as the number of sub-queries is always 1.
+ */
+ @Override
+ public void
setCountsStrategy(AbstractCompoundTermsQuery.CompoundCountsStrategy
countsStrategy) {
+ super.setCountsStrategy(countsStrategy);
+ }
}
Modified:
mimir/trunk/mimir-core/src/gate/mimir/search/terms/TermTypeTermsQuery.java
===================================================================
--- mimir/trunk/mimir-core/src/gate/mimir/search/terms/TermTypeTermsQuery.java
2013-03-12 12:58:32 UTC (rev 16582)
+++ mimir/trunk/mimir-core/src/gate/mimir/search/terms/TermTypeTermsQuery.java
2013-03-12 13:07:53 UTC (rev 16583)
@@ -32,7 +32,7 @@
* A {@link TermsQuery} that enumerates all terms of a given type. The type of
* a term is the name of a token feature, or an annotation type.
*/
-public class TermTypeTermsQuery extends AbstractTermsQuery {
+public class TermTypeTermsQuery implements TermsQuery {
/**
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
Symantec Endpoint Protection 12 positioned as A LEADER in The Forrester
Wave(TM): Endpoint Security, Q1 2013 and "remains a good choice" in the
endpoint security space. For insight on selecting the right partner to
tackle endpoint security challenges, access the full report.
http://p.sf.net/sfu/symantec-dev2dev
_______________________________________________
GATE-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gate-cvs
