You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by cp...@apache.org on 2016/12/19 17:18:44 UTC
[1/3] lucene-solr:branch_6x: SOLR-8542: techproducts example now
includes (disabled) learning-to-rank support (enable via
-Dsolr.ltr.enabled=true)
Repository: lucene-solr
Updated Branches:
refs/heads/branch_6x b1de7364b -> 8c81deb88
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/LinearModel.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/LinearModel.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/LinearModel.java
index 57fc5ad..ee065c3 100644
--- a/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/LinearModel.java
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/LinearModel.java
@@ -47,6 +47,16 @@ import org.apache.solr.ltr.norm.Normalizer;
}
}</pre>
* <p>
+ * Training libraries:
+ * <ul>
+ * <li> <a href="https://www.csie.ntu.edu.tw/~cjlin/liblinear/">
+ * LIBLINEAR -- A Library for Large Linear Classification</a>
+ * </ul>
+ * <ul>
+ * <li> <a href="https://www.csie.ntu.edu.tw/~cjlin/libsvm/">
+ * LIBSVM -- A Library for Support Vector Machines</a>
+ * </ul>
+ * <p>
* Background reading:
* <ul>
* <li> <a href="http://www.cs.cornell.edu/people/tj/publications/joachims_02c.pdf">
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/MultipleAdditiveTreesModel.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/MultipleAdditiveTreesModel.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/MultipleAdditiveTreesModel.java
index 4fa595e..926fab4 100644
--- a/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/MultipleAdditiveTreesModel.java
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/model/MultipleAdditiveTreesModel.java
@@ -71,6 +71,11 @@ import org.apache.solr.util.SolrPluginUtils;
}
}</pre>
* <p>
+ * Training libraries:
+ * <ul>
+ * <li> <a href="http://sourceforge.net/p/lemur/wiki/RankLib/">RankLib</a>
+ * </ul>
+ * <p>
* Background reading:
* <ul>
* <li> <a href="http://research.microsoft.com/pubs/132652/MSR-TR-2010-82.pdf">
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/response/transform/LTRFeatureLoggerTransformerFactory.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/response/transform/LTRFeatureLoggerTransformerFactory.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/response/transform/LTRFeatureLoggerTransformerFactory.java
index f19db3b..608f317 100644
--- a/solr/contrib/ltr/src/java/org/apache/solr/ltr/response/transform/LTRFeatureLoggerTransformerFactory.java
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/response/transform/LTRFeatureLoggerTransformerFactory.java
@@ -17,6 +17,7 @@
package org.apache.solr.ltr.response.transform;
import java.io.IOException;
+import java.lang.invoke.MethodHandles;
import java.util.Collections;
import java.util.List;
import java.util.Map;
@@ -27,6 +28,7 @@ import org.apache.solr.common.SolrDocument;
import org.apache.solr.common.SolrException;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
+import org.apache.solr.ltr.CSVFeatureLogger;
import org.apache.solr.ltr.FeatureLogger;
import org.apache.solr.ltr.LTRRescorer;
import org.apache.solr.ltr.LTRScoringQuery;
@@ -44,17 +46,25 @@ import org.apache.solr.response.transform.DocTransformer;
import org.apache.solr.response.transform.TransformerFactory;
import org.apache.solr.search.SolrIndexSearcher;
import org.apache.solr.util.SolrPluginUtils;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
/**
* This transformer will take care to generate and append in the response the
- * features declared in the feature store of the current model. The class is
- * useful if you are not interested in the reranking (e.g., bootstrapping a
- * machine learning framework).
- */
+ * features declared in the feature store of the current reranking model,
+ * or a specified feature store. Ex. <code>fl=id,[features store=myStore efi.user_text="ibm"]</code>
+ *
+ * <h3>Parameters</h3>
+ * <code>store</code> - The feature store to extract features from. If not provided it
+ * will default to the features used by your reranking model.<br>
+ * <code>efi.*</code> - External feature information variables required by the features
+ * you are extracting.<br>
+ * <code>format</code> - The format you want the features to be returned in. Supports (dense|sparse). Defaults to sparse.<br>
+*/
+
public class LTRFeatureLoggerTransformerFactory extends TransformerFactory {
- // used inside fl to specify the output format (csv/json) of the extracted features
- private static final String FV_RESPONSE_WRITER = "fvwt";
+ private static final Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());
// used inside fl to specify the format (dense|sparse) of the extracted features
private static final String FV_FORMAT = "format";
@@ -64,27 +74,43 @@ public class LTRFeatureLoggerTransformerFactory extends TransformerFactory {
private static String DEFAULT_LOGGING_MODEL_NAME = "logging-model";
+ private String fvCacheName;
private String loggingModelName = DEFAULT_LOGGING_MODEL_NAME;
- private String defaultFvStore;
- private String defaultFvwt;
- private String defaultFvFormat;
+ private String defaultStore;
+ private String defaultFormat;
+ private char csvKeyValueDelimiter = CSVFeatureLogger.DEFAULT_KEY_VALUE_SEPARATOR;
+ private char csvFeatureSeparator = CSVFeatureLogger.DEFAULT_FEATURE_SEPARATOR;
private LTRThreadModule threadManager = null;
+ public void setFvCacheName(String fvCacheName) {
+ this.fvCacheName = fvCacheName;
+ }
+
public void setLoggingModelName(String loggingModelName) {
this.loggingModelName = loggingModelName;
}
- public void setStore(String defaultFvStore) {
- this.defaultFvStore = defaultFvStore;
+ public void setDefaultStore(String defaultStore) {
+ this.defaultStore = defaultStore;
}
- public void setFvwt(String defaultFvwt) {
- this.defaultFvwt = defaultFvwt;
+ public void setDefaultFormat(String defaultFormat) {
+ this.defaultFormat = defaultFormat;
+ }
+
+ public void setCsvKeyValueDelimiter(String csvKeyValueDelimiter) {
+ if (csvKeyValueDelimiter.length() != 1) {
+ throw new IllegalArgumentException("csvKeyValueDelimiter must be exactly 1 character");
+ }
+ this.csvKeyValueDelimiter = csvKeyValueDelimiter.charAt(0);
}
- public void setFormat(String defaultFvFormat) {
- this.defaultFvFormat = defaultFvFormat;
+ public void setCsvFeatureSeparator(String csvFeatureSeparator) {
+ if (csvFeatureSeparator.length() != 1) {
+ throw new IllegalArgumentException("csvFeatureSeparator must be exactly 1 character");
+ }
+ this.csvFeatureSeparator = csvFeatureSeparator.charAt(0);
}
@Override
@@ -95,35 +121,62 @@ public class LTRFeatureLoggerTransformerFactory extends TransformerFactory {
}
@Override
- public DocTransformer create(String name, SolrParams params,
+ public DocTransformer create(String name, SolrParams localparams,
SolrQueryRequest req) {
// Hint to enable feature vector cache since we are requesting features
SolrQueryRequestContextUtils.setIsExtractingFeatures(req);
// Communicate which feature store we are requesting features for
- SolrQueryRequestContextUtils.setFvStoreName(req, params.get(FV_STORE, defaultFvStore));
+ SolrQueryRequestContextUtils.setFvStoreName(req, localparams.get(FV_STORE, defaultStore));
// Create and supply the feature logger to be used
SolrQueryRequestContextUtils.setFeatureLogger(req,
- FeatureLogger.createFeatureLogger(
- params.get(FV_RESPONSE_WRITER, defaultFvwt),
- params.get(FV_FORMAT, defaultFvFormat)));
+ createFeatureLogger(
+ localparams.get(FV_FORMAT, defaultFormat)));
+
+ return new FeatureTransformer(name, localparams, req);
+ }
- return new FeatureTransformer(name, params, req);
+ /**
+ * returns a FeatureLogger that logs the features
+ * 'featureFormat' param: 'dense' will write features in dense format,
+ * 'sparse' will write the features in sparse format, null or empty will
+ * default to 'sparse'
+ *
+ *
+ * @return a feature logger for the format specified.
+ */
+ private FeatureLogger createFeatureLogger(String featureFormat) {
+ final FeatureLogger.FeatureFormat f;
+ if (featureFormat == null || featureFormat.isEmpty() ||
+ featureFormat.equals("sparse")) {
+ f = FeatureLogger.FeatureFormat.SPARSE;
+ }
+ else if (featureFormat.equals("dense")) {
+ f = FeatureLogger.FeatureFormat.DENSE;
+ }
+ else {
+ f = FeatureLogger.FeatureFormat.SPARSE;
+ log.warn("unknown feature logger feature format {}", featureFormat);
+ }
+ if (fvCacheName == null) {
+ throw new IllegalArgumentException("a fvCacheName must be configured");
+ }
+ return new CSVFeatureLogger(fvCacheName, f, csvKeyValueDelimiter, csvFeatureSeparator);
}
class FeatureTransformer extends DocTransformer {
final private String name;
- final private SolrParams params;
+ final private SolrParams localparams;
final private SolrQueryRequest req;
private List<LeafReaderContext> leafContexts;
private SolrIndexSearcher searcher;
private LTRScoringQuery scoringQuery;
private LTRScoringQuery.ModelWeight modelWeight;
- private FeatureLogger<?> featureLogger;
+ private FeatureLogger featureLogger;
private boolean docsWereNotReranked;
/**
@@ -131,10 +184,10 @@ public class LTRFeatureLoggerTransformerFactory extends TransformerFactory {
* Name of the field to be added in a document representing the
* feature vectors
*/
- public FeatureTransformer(String name, SolrParams params,
+ public FeatureTransformer(String name, SolrParams localparams,
SolrQueryRequest req) {
this.name = name;
- this.params = params;
+ this.localparams = localparams;
this.req = req;
}
@@ -178,7 +231,7 @@ public class LTRFeatureLoggerTransformerFactory extends TransformerFactory {
featureStoreName, store.getFeatures());
scoringQuery = new LTRScoringQuery(lm,
- LTRQParserPlugin.extractEFIParams(params),
+ LTRQParserPlugin.extractEFIParams(localparams),
true,
threadManager); // request feature weights to be created for all features
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/overview.html
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/overview.html b/solr/contrib/ltr/src/java/overview.html
index d1a22f0..b0802d2 100644
--- a/solr/contrib/ltr/src/java/overview.html
+++ b/solr/contrib/ltr/src/java/overview.html
@@ -28,7 +28,7 @@ that sophisticated models can make more nuanced ranking decisions than standard
functions like TF-IDF or BM25.
</p>
<p>
-This module allows to plug a reranking component directly into Solr, enabling users
+This module allows to plug a reranking model directly into Solr, enabling users
to easily build their own learning to rank systems and access the rich
matching features readily available in Solr. It also provides tools to perform
feature engineering and feature extraction.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr.xml b/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr.xml
index d6f8d8e..1e1a618 100644
--- a/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr.xml
+++ b/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr.xml
@@ -35,8 +35,9 @@
in the response. The name of the field we will be the the name of the transformer
enclosed between brackets (in this case [fv]). In order to get the feature
vector you will have to specify that you want the field (e.g., fl="*,[fv]) -->
- <transformer name="fv"
- class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory" />
+ <transformer name="fv" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory">
+ <str name="fvCacheName">QUERY_DOC_FV</str>
+ </transformer>
<updateHandler class="solr.DirectUpdateHandler2">
<autoCommit>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr_Th10_10.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr_Th10_10.xml b/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr_Th10_10.xml
index 51971f7..b41bce1 100644
--- a/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr_Th10_10.xml
+++ b/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-ltr_Th10_10.xml
@@ -39,8 +39,9 @@
in the response. The name of the field we will be the the name of the transformer
enclosed between brackets (in this case [fv]). In order to get the feature
vector you will have to specify that you want the field (e.g., fl="*,[fv]) -->
- <transformer name="fv"
- class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory" />
+ <transformer name="fv" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory">
+ <str name="fvCacheName">QUERY_DOC_FV</str>
+ </transformer>
<updateHandler class="solr.DirectUpdateHandler2">
<autoCommit>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-multiseg.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-multiseg.xml b/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-multiseg.xml
index 5abff6f..b34be8f 100644
--- a/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-multiseg.xml
+++ b/solr/contrib/ltr/src/test-files/solr/collection1/conf/solrconfig-multiseg.xml
@@ -22,6 +22,13 @@
<!-- Query parser used to rerank top docs with a provided model -->
<queryParser name="ltr" class="org.apache.solr.ltr.search.LTRQParserPlugin" />
+ <query>
+ <filterCache class="solr.FastLRUCache" size="4096"
+ initialSize="2048" autowarmCount="0" />
+ <cache name="QUERY_DOC_FV" class="solr.search.LRUCache" size="4096"
+ initialSize="2048" autowarmCount="4096" regenerator="solr.search.NoOpRegenerator" />
+ </query>
+
<maxBufferedDocs>1</maxBufferedDocs>
<mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
<int name="maxMergeAtOnce">10</int>
@@ -32,8 +39,9 @@
in the response. The name of the field we will be the the name of the transformer
enclosed between brackets (in this case [fv]). In order to get the feature
vector you will have to specify that you want the field (e.g., fl="*,[fv]) -->
- <transformer name="features"
- class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory" />
+ <transformer name="features" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory">
+ <str name="fvCacheName">QUERY_DOC_FV</str>
+ </transformer>
<updateHandler class="solr.DirectUpdateHandler2">
<autoCommit>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/FeatureLoggerTestUtils.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/FeatureLoggerTestUtils.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/FeatureLoggerTestUtils.java
new file mode 100644
index 0000000..f2afd9c
--- /dev/null
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/FeatureLoggerTestUtils.java
@@ -0,0 +1,44 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.solr.ltr;
+
+public class FeatureLoggerTestUtils {
+
+ public static String toFeatureVector(String ... keysAndValues) {
+ return toFeatureVector(
+ CSVFeatureLogger.DEFAULT_KEY_VALUE_SEPARATOR,
+ CSVFeatureLogger.DEFAULT_FEATURE_SEPARATOR,
+ keysAndValues);
+ }
+
+ public static String toFeatureVector(char keyValueSeparator, char featureSeparator,
+ String ... keysAndValues) {
+ StringBuilder sb = new StringBuilder(keysAndValues.length/2 * 3);
+ for (int ii = 0; ii+1 < keysAndValues.length; ii += 2) {
+ sb.append(keysAndValues[ii])
+ .append(keyValueSeparator)
+ .append(keysAndValues[ii+1])
+ .append(featureSeparator);
+ }
+
+ final String features = (sb.length() > 0 ?
+ sb.substring(0, sb.length() - 1) : "");
+
+ return features;
+ }
+
+}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestLTROnSolrCloud.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestLTROnSolrCloud.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestLTROnSolrCloud.java
index 2e01a64..2bef197 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestLTROnSolrCloud.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestLTROnSolrCloud.java
@@ -92,6 +92,15 @@ public class TestLTROnSolrCloud extends TestRerankBase {
assertEquals("3", queryResponse.getResults().get(2).get("id").toString());
assertEquals("4", queryResponse.getResults().get(3).get("id").toString());
+ final String result0_features= FeatureLoggerTestUtils.toFeatureVector(
+ "powpularityS","64.0", "c3","2.0");
+ final String result1_features= FeatureLoggerTestUtils.toFeatureVector(
+ "powpularityS","49.0", "c3","2.0");
+ final String result2_features= FeatureLoggerTestUtils.toFeatureVector(
+ "powpularityS","36.0", "c3","2.0");
+ final String result3_features= FeatureLoggerTestUtils.toFeatureVector(
+ "powpularityS","25.0", "c3","2.0");
+
// Test re-rank and feature vectors returned
query.setFields("*,score,features:[fv]");
query.add("rq", "{!ltr model=powpularityS-model reRankDocs=8}");
@@ -99,16 +108,16 @@ public class TestLTROnSolrCloud extends TestRerankBase {
solrCluster.getSolrClient().query(COLLECTION,query);
assertEquals(8, queryResponse.getResults().getNumFound());
assertEquals("8", queryResponse.getResults().get(0).get("id").toString());
- assertEquals("powpularityS:64.0;c3:2.0",
+ assertEquals(result0_features,
queryResponse.getResults().get(0).get("features").toString());
assertEquals("7", queryResponse.getResults().get(1).get("id").toString());
- assertEquals("powpularityS:49.0;c3:2.0",
+ assertEquals(result1_features,
queryResponse.getResults().get(1).get("features").toString());
assertEquals("6", queryResponse.getResults().get(2).get("id").toString());
- assertEquals("powpularityS:36.0;c3:2.0",
+ assertEquals(result2_features,
queryResponse.getResults().get(2).get("features").toString());
assertEquals("5", queryResponse.getResults().get(3).get("id").toString());
- assertEquals("powpularityS:25.0;c3:2.0",
+ assertEquals(result3_features,
queryResponse.getResults().get(3).get("features").toString());
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestSelectiveWeightCreation.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestSelectiveWeightCreation.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestSelectiveWeightCreation.java
index 68961d2..b9b3d63 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestSelectiveWeightCreation.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/TestSelectiveWeightCreation.java
@@ -215,6 +215,11 @@ public class TestSelectiveWeightCreation extends TestRerankBase {
@Test
public void testSelectiveWeightsRequestFeaturesFromDifferentStore() throws Exception {
+ final String docs0fv = FeatureLoggerTestUtils.toFeatureVector(
+ "matchedTitle","1.0", "titlePhraseMatch","0.40254828");
+ final String docs0fv_fstore4= FeatureLoggerTestUtils.toFeatureVector(
+ "popularity","3.0", "originalScore","1.0");
+
final SolrQuery query = new SolrQuery();
query.setQuery("*:*");
query.add("fl", "*,score");
@@ -225,7 +230,7 @@ public class TestSelectiveWeightCreation extends TestRerankBase {
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/id=='1'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/id=='3'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[2]/id=='4'");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='matchedTitle:1.0;titlePhraseMatch:0.40254828'"); // extract all features in default store
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='"+docs0fv+"'"); // extract all features in default store
query.remove("fl");
query.remove("rq");
@@ -235,7 +240,7 @@ public class TestSelectiveWeightCreation extends TestRerankBase {
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/id=='1'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/score==0.999");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='popularity:3.0;originalScore:1.0'"); // extract all features from fstore4
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='"+docs0fv_fstore4+"'"); // extract all features from fstore4
query.remove("fl");
@@ -245,7 +250,7 @@ public class TestSelectiveWeightCreation extends TestRerankBase {
query.add("fl", "fv:[fv store=fstore4 efi.myPop=3]");
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/id=='1'"); // score using fstore2 used by externalmodelstore
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/score==0.7992");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='popularity:3.0;originalScore:1.0'"); // extract all features from fstore4
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='"+docs0fv_fstore4+"'"); // extract all features from fstore4
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalFeatures.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalFeatures.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalFeatures.java
index 8c00758..15b7633 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalFeatures.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalFeatures.java
@@ -17,6 +17,7 @@
package org.apache.solr.ltr.feature;
import org.apache.solr.client.solrj.SolrQuery;
+import org.apache.solr.ltr.FeatureLoggerTestUtils;
import org.apache.solr.ltr.TestRerankBase;
import org.junit.AfterClass;
import org.junit.BeforeClass;
@@ -103,6 +104,9 @@ public class TestExternalFeatures extends TestRerankBase {
query.setQuery("*:*");
query.add("rows", "1");
+ final String docs0fv_sparse_csv = FeatureLoggerTestUtils.toFeatureVector(
+ "confidence","2.3", "originalScore","1.0");
+
// Features we're extracting depend on external feature info not passed in
query.add("fl", "[fv]");
assertJQ("/query" + query.toQueryString(), "/error/msg=='Exception from createWeight for SolrFeature [name=matchedTitle, params={q={!terms f=title}${user_query}}] SolrFeatureWeight requires efi parameter that was not passed in request.'");
@@ -110,13 +114,13 @@ public class TestExternalFeatures extends TestRerankBase {
// Adding efi in features section should make it work
query.remove("fl");
query.add("fl", "score,fvalias:[fv store=fstore2 efi.myconf=2.3]");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='confidence:2.3;originalScore:1.0'");
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='"+docs0fv_sparse_csv+"'");
// Adding efi in transformer + rq should still use the transformer's params for feature extraction
query.remove("fl");
query.add("fl", "score,fvalias:[fv store=fstore2 efi.myconf=2.3]");
query.add("rq", "{!ltr reRankDocs=3 model=externalmodel efi.user_query=w3}");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='confidence:2.3;originalScore:1.0'");
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='"+docs0fv_sparse_csv+"'");
}
@Test
@@ -128,7 +132,7 @@ public class TestExternalFeatures extends TestRerankBase {
// Efi is explicitly not required, so we do not score the feature
query.remove("fl");
query.add("fl", "fvalias:[fv store=fstore2]");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='originalScore:0.0'");
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='"+FeatureLoggerTestUtils.toFeatureVector("originalScore","0.0")+"'");
}
@Test
@@ -140,7 +144,7 @@ public class TestExternalFeatures extends TestRerankBase {
// Efi is explicitly not required, so we do not score the feature
query.remove("fl");
query.add("fl", "fvalias:[fv store=fstore3]");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='originalScore:0.0'");
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fvalias=='"+FeatureLoggerTestUtils.toFeatureVector("originalScore","0.0")+"'");
}
@Test
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalValueFeatures.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalValueFeatures.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalValueFeatures.java
index bc073cb..fc0ade2 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalValueFeatures.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestExternalValueFeatures.java
@@ -17,6 +17,7 @@
package org.apache.solr.ltr.feature;
import org.apache.solr.client.solrj.SolrQuery;
+import org.apache.solr.ltr.FeatureLoggerTestUtils;
import org.apache.solr.ltr.TestRerankBase;
import org.junit.AfterClass;
import org.junit.BeforeClass;
@@ -55,12 +56,11 @@ public class TestExternalValueFeatures extends TestRerankBase {
query.setQuery("*:*");
query.add("fl", "*,score,features:[fv]");
query.add("rows", "3");
- query.add("fl", "[fv]");
query.add("rq", "{!ltr reRankDocs=3 model=external_model_binary_feature efi.user_device_tablet=1}");
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/id=='1'");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/features=='user_device_tablet:1.0'");
+ "/response/docs/[0]/features=='"+FeatureLoggerTestUtils.toFeatureVector("user_device_tablet","1.0")+"'");
assertJQ("/query" + query.toQueryString(),
"/response/docs/[0]/score==65.0");
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFeatureLogging.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFeatureLogging.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFeatureLogging.java
index 14e2903..f18c6bf 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFeatureLogging.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFeatureLogging.java
@@ -17,6 +17,7 @@
package org.apache.solr.ltr.feature;
import org.apache.solr.client.solrj.SolrQuery;
+import org.apache.solr.ltr.FeatureLoggerTestUtils;
import org.apache.solr.ltr.TestRerankBase;
import org.apache.solr.ltr.model.LinearModel;
import org.apache.solr.ltr.store.FeatureStore;
@@ -55,6 +56,13 @@ public class TestFeatureLogging extends TestRerankBase {
"c1", "c2", "c3"}, "test1",
"{\"weights\":{\"c1\":1.0,\"c2\":1.0,\"c3\":1.0}}");
+ final String docs0fv_sparse_csv = FeatureLoggerTestUtils.toFeatureVector(
+ "c1","1.0",
+ "c2","2.0",
+ "c3","3.0",
+ "pop","2.0",
+ "yesmatch","1.0");
+
final SolrQuery query = new SolrQuery();
query.setQuery("title:bloomberg");
query.add("fl", "title,description,id,popularity,[fv]");
@@ -65,7 +73,7 @@ public class TestFeatureLogging extends TestRerankBase {
restTestHarness.query("/query" + query.toQueryString());
assertJQ(
"/query" + query.toQueryString(),
- "/response/docs/[0]/=={'title':'bloomberg bloomberg ', 'description':'bloomberg','id':'7', 'popularity':2, '[fv]':'c1:1.0;c2:2.0;c3:3.0;pop:2.0;yesmatch:1.0'}");
+ "/response/docs/[0]/=={'title':'bloomberg bloomberg ', 'description':'bloomberg','id':'7', 'popularity':2, '[fv]':'"+docs0fv_sparse_csv+"'}");
query.remove("fl");
query.add("fl", "[fv]");
@@ -74,15 +82,7 @@ public class TestFeatureLogging extends TestRerankBase {
restTestHarness.query("/query" + query.toQueryString());
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'c1:1.0;c2:2.0;c3:3.0;pop:2.0;yesmatch:1.0'}");
- query.remove("rq");
-
- // set logging at false but still asking for feature, and it should work anyway
- query.add("rq", "{!ltr reRankDocs=3 model=sum1}");
- assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'c1:1.0;c2:2.0;c3:3.0;pop:2.0;yesmatch:1.0'}");
-
-
+ "/response/docs/[0]/=={'[fv]':'"+docs0fv_sparse_csv+"'}");
}
@Test
@@ -108,24 +108,24 @@ public class TestFeatureLogging extends TestRerankBase {
// No store specified, use default store for extraction
query.add("fl", "fv:[fv]");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'fv':'defaultf1:1.0'}");
+ "/response/docs/[0]/=={'fv':'"+FeatureLoggerTestUtils.toFeatureVector("defaultf1","1.0")+"'}");
// Store specified, use store for extraction
query.remove("fl");
query.add("fl", "fv:[fv store=store8]");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'fv':'store8f1:2.0'}");
+ "/response/docs/[0]/=={'fv':'"+FeatureLoggerTestUtils.toFeatureVector("store8f1","2.0")+"'}");
// Store specified + model specified, use store for extraction
query.add("rq", "{!ltr reRankDocs=3 model=store9m1}");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'fv':'store8f1:2.0'}");
+ "/response/docs/[0]/=={'fv':'"+FeatureLoggerTestUtils.toFeatureVector("store8f1","2.0")+"'}");
// No store specified + model specified, use model store for extraction
query.remove("fl");
query.add("fl", "fv:[fv]");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'fv':'store9f1:3.0'}");
+ "/response/docs/[0]/=={'fv':'"+FeatureLoggerTestUtils.toFeatureVector("store9f1","3.0")+"'}");
}
@@ -157,23 +157,16 @@ public class TestFeatureLogging extends TestRerankBase {
query.add("rq", "{!ltr reRankDocs=3 model=sumgroup}");
- restTestHarness.query("/query" + query.toQueryString());
- assertJQ(
- "/query" + query.toQueryString(),
- "/grouped/title/groups/[0]/doclist/docs/[0]/=={'fv':'c1:1.0;c2:2.0;c3:3.0;pop:5.0'}");
+ final String docs0fv_sparse_csv = FeatureLoggerTestUtils.toFeatureVector(
+ "c1","1.0",
+ "c2","2.0",
+ "c3","3.0",
+ "pop","5.0");
- query.remove("fl");
- query.add("fl", "fv:[fv fvwt=json]");
restTestHarness.query("/query" + query.toQueryString());
assertJQ(
"/query" + query.toQueryString(),
- "/grouped/title/groups/[0]/doclist/docs/[0]/fv/=={'c1':1.0,'c2':2.0,'c3':3.0,'pop':5.0}");
- query.remove("fl");
- query.add("fl", "fv:[fv fvwt=json]");
-
- assertJQ(
- "/query" + query.toQueryString(),
- "/grouped/title/groups/[0]/doclist/docs/[0]/fv/=={'c1':1.0,'c2':2.0,'c3':3.0,'pop':5.0}");
+ "/grouped/title/groups/[0]/doclist/docs/[0]/=={'fv':'"+docs0fv_sparse_csv+"'}");
}
@Test
@@ -187,68 +180,46 @@ public class TestFeatureLogging extends TestRerankBase {
"match"}, "test4",
"{\"weights\":{\"match\":1.0}}");
- //json - no feature format check (default to sparse)
+ final String docs0fv_sparse_csv = FeatureLoggerTestUtils.toFeatureVector("match", "1.0", "c4", "1.0");
+ final String docs1fv_sparse_csv = FeatureLoggerTestUtils.toFeatureVector("c4", "1.0");
+
+ final String docs0fv_dense_csv = FeatureLoggerTestUtils.toFeatureVector("match", "1.0", "c4", "1.0");
+ final String docs1fv_dense_csv = FeatureLoggerTestUtils.toFeatureVector("match", "0.0", "c4", "1.0");
+
final SolrQuery query = new SolrQuery();
query.setQuery("title:bloomberg");
query.add("rows", "10");
- query.add("fl", "*,score,fv:[fv store=test4 fvwt=json]");
query.add("rq", "{!ltr reRankDocs=10 model=sum4}");
- assertJQ(
- "/query" + query.toQueryString(),
- "/response/docs/[0]/fv/=={'match':1.0,'c4':1.0}");
- assertJQ(
- "/query" + query.toQueryString(),
- "/response/docs/[1]/fv/=={'c4':1.0}");
-
- //json - sparse feature format check
- query.remove("fl");
- query.add("fl", "*,score,fv:[fv store=test4 format=sparse fvwt=json]");
- assertJQ(
- "/query" + query.toQueryString(),
- "/response/docs/[0]/fv/=={'match':1.0,'c4':1.0}");
- assertJQ(
- "/query" + query.toQueryString(),
- "/response/docs/[1]/fv/=={'c4':1.0}");
-
- //json - dense feature format check
- query.remove("fl");
- query.add("fl", "*,score,fv:[fv store=test4 format=dense fvwt=json]");
- assertJQ(
- "/query" + query.toQueryString(),
- "/response/docs/[0]/fv/=={'match':1.0,'c4':1.0}");
- assertJQ(
- "/query" + query.toQueryString(),
- "/response/docs/[1]/fv/=={'match':0.0,'c4':1.0}");
//csv - no feature format check (default to sparse)
query.remove("fl");
- query.add("fl", "*,score,fv:[fv store=test4 fvwt=csv]");
+ query.add("fl", "*,score,fv:[fv store=test4]");
assertJQ(
"/query" + query.toQueryString(),
- "/response/docs/[0]/fv/=='match:1.0;c4:1.0'");
+ "/response/docs/[0]/fv/=='"+docs0fv_sparse_csv+"'");
assertJQ(
"/query" + query.toQueryString(),
- "/response/docs/[1]/fv/=='c4:1.0'");
+ "/response/docs/[1]/fv/=='"+docs1fv_sparse_csv+"'");
//csv - sparse feature format check
query.remove("fl");
- query.add("fl", "*,score,fv:[fv store=test4 format=sparse fvwt=csv]");
+ query.add("fl", "*,score,fv:[fv store=test4 format=sparse]");
assertJQ(
"/query" + query.toQueryString(),
- "/response/docs/[0]/fv/=='match:1.0;c4:1.0'");
+ "/response/docs/[0]/fv/=='"+docs0fv_sparse_csv+"'");
assertJQ(
"/query" + query.toQueryString(),
- "/response/docs/[1]/fv/=='c4:1.0'");
+ "/response/docs/[1]/fv/=='"+docs1fv_sparse_csv+"'");
//csv - dense feature format check
query.remove("fl");
- query.add("fl", "*,score,fv:[fv store=test4 format=dense fvwt=csv]");
+ query.add("fl", "*,score,fv:[fv store=test4 format=dense]");
assertJQ(
"/query" + query.toQueryString(),
- "/response/docs/[0]/fv/=='match:1.0;c4:1.0'");
+ "/response/docs/[0]/fv/=='"+docs0fv_dense_csv+"'");
assertJQ(
"/query" + query.toQueryString(),
- "/response/docs/[1]/fv/=='match:0.0;c4:1.0'");
+ "/response/docs/[1]/fv/=='"+docs1fv_dense_csv+"'");
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFieldValueFeature.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFieldValueFeature.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFieldValueFeature.java
index 9574273..8295403 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFieldValueFeature.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFieldValueFeature.java
@@ -17,6 +17,7 @@
package org.apache.solr.ltr.feature;
import org.apache.solr.client.solrj.SolrQuery;
+import org.apache.solr.ltr.FeatureLoggerTestUtils;
import org.apache.solr.ltr.TestRerankBase;
import org.apache.solr.ltr.model.LinearModel;
import org.junit.AfterClass;
@@ -116,7 +117,7 @@ public class TestFieldValueFeature extends TestRerankBase {
query.add("fl", "[fv]");
assertJQ("/query" + query.toQueryString(), "/response/numFound/==1");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'popularity:"+FIELD_VALUE_FEATURE_DEFAULT_VAL+"'}");
+ "/response/docs/[0]/=={'[fv]':'"+FeatureLoggerTestUtils.toFeatureVector("popularity",Float.toString(FIELD_VALUE_FEATURE_DEFAULT_VAL))+"'}");
}
@@ -145,7 +146,7 @@ public class TestFieldValueFeature extends TestRerankBase {
query.add("fl", "[fv]");
assertJQ("/query" + query.toQueryString(), "/response/numFound/==1");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'popularity42:42.0'}");
+ "/response/docs/[0]/=={'[fv]':'"+FeatureLoggerTestUtils.toFeatureVector("popularity42","42.0")+"'}");
}
@@ -165,7 +166,7 @@ public class TestFieldValueFeature extends TestRerankBase {
query.add("fl", "[fv]");
assertJQ("/query" + query.toQueryString(), "/response/numFound/==1");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'not-existing-field:"+FIELD_VALUE_FEATURE_DEFAULT_VAL+"'}");
+ "/response/docs/[0]/=={'[fv]':'"+FeatureLoggerTestUtils.toFeatureVector("not-existing-field",Float.toString(FIELD_VALUE_FEATURE_DEFAULT_VAL))+"'}");
}
@@ -183,7 +184,7 @@ public class TestFieldValueFeature extends TestRerankBase {
query.add("rq", "{!ltr model=trendy-model reRankDocs=4}");
query.add("fl", "[fv]");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'trendy:0.0'}");
+ "/response/docs/[0]/=={'[fv]':'"+FeatureLoggerTestUtils.toFeatureVector("trendy","0.0")+"'}");
query = new SolrQuery();
@@ -191,7 +192,7 @@ public class TestFieldValueFeature extends TestRerankBase {
query.add("rq", "{!ltr model=trendy-model reRankDocs=4}");
query.add("fl", "[fv]");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'trendy:1.0'}");
+ "/response/docs/[0]/=={'[fv]':'"+FeatureLoggerTestUtils.toFeatureVector("trendy","1.0")+"'}");
// check default value is false
query = new SolrQuery();
@@ -199,7 +200,7 @@ public class TestFieldValueFeature extends TestRerankBase {
query.add("rq", "{!ltr model=trendy-model reRankDocs=4}");
query.add("fl", "[fv]");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/=={'[fv]':'trendy:0.0'}");
+ "/response/docs/[0]/=={'[fv]':'"+FeatureLoggerTestUtils.toFeatureVector("trendy","0.0")+"'}");
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFilterSolrFeature.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFilterSolrFeature.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFilterSolrFeature.java
index 14baefa..a6a80bd 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFilterSolrFeature.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestFilterSolrFeature.java
@@ -17,6 +17,7 @@
package org.apache.solr.ltr.feature;
import org.apache.solr.client.solrj.SolrQuery;
+import org.apache.solr.ltr.FeatureLoggerTestUtils;
import org.apache.solr.ltr.TestRerankBase;
import org.apache.solr.ltr.model.LinearModel;
import org.apache.solr.ltr.store.rest.ManagedFeatureStore;
@@ -96,10 +97,13 @@ public class TestFilterSolrFeature extends TestRerankBase {
query.add("rq", "{!ltr reRankDocs=4 model=fqmodel efi.user_query=w2}");
query.add("fl", "fv:[fv]");
+ final String docs0fv_sparse_csv= FeatureLoggerTestUtils.toFeatureVector(
+ "matchedTitle","1.0", "popularity","3.0");
+
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/id=='2'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/id=='1'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[2]/id=='3'");
- assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='matchedTitle:1.0;popularity:3.0'");
+ assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/fv=='"+docs0fv_sparse_csv+"'");
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestNoMatchSolrFeature.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestNoMatchSolrFeature.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestNoMatchSolrFeature.java
index 5712687..004e314 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestNoMatchSolrFeature.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestNoMatchSolrFeature.java
@@ -20,6 +20,7 @@ import java.util.ArrayList;
import java.util.Map;
import org.apache.solr.client.solrj.SolrQuery;
+import org.apache.solr.ltr.FeatureLoggerTestUtils;
import org.apache.solr.ltr.TestRerankBase;
import org.apache.solr.ltr.model.LinearModel;
import org.apache.solr.ltr.model.MultipleAdditiveTreesModel;
@@ -104,12 +105,11 @@ public class TestNoMatchSolrFeature extends TestRerankBase {
final Double doc0Score = (Double) ((Map<String,Object>) ((ArrayList<Object>) ((Map<String,Object>) jsonParse
.get("response")).get("docs")).get(0)).get("score");
-
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/id=='1'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/score=="
+ (doc0Score * 1.1));
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/fv=='yesmatchfeature:" + doc0Score + "'");
+ "/response/docs/[0]/fv=='"+FeatureLoggerTestUtils.toFeatureVector("yesmatchfeature", doc0Score.toString())+"'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/id=='2'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/score==0.0");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/fv==''");
@@ -144,7 +144,7 @@ public class TestNoMatchSolrFeature extends TestRerankBase {
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/score==0.0");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/fv=='yesmatchfeature:" + doc0Score + "'");
+ "/response/docs/[0]/fv=='"+FeatureLoggerTestUtils.toFeatureVector("yesmatchfeature", doc0Score.toString())+"'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/score==0.0");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/fv==''");
assertJQ("/query" + query.toQueryString(), "/response/docs/[2]/score==0.0");
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestOriginalScoreFeature.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestOriginalScoreFeature.java b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestOriginalScoreFeature.java
index e525891..48662e6 100644
--- a/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestOriginalScoreFeature.java
+++ b/solr/contrib/ltr/src/test/org/apache/solr/ltr/feature/TestOriginalScoreFeature.java
@@ -20,6 +20,7 @@ import java.util.ArrayList;
import java.util.Map;
import org.apache.solr.client.solrj.SolrQuery;
+import org.apache.solr.ltr.FeatureLoggerTestUtils;
import org.apache.solr.ltr.TestRerankBase;
import org.apache.solr.ltr.model.LinearModel;
import org.junit.AfterClass;
@@ -132,17 +133,17 @@ public class TestOriginalScoreFeature extends TestRerankBase {
assertJQ("/query" + query.toQueryString(), "/response/numFound/==4");
assertJQ("/query" + query.toQueryString(), "/response/docs/[0]/id=='1'");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[0]/fv=='origScore:" + doc0Score + ";c2:2.0'");
+ "/response/docs/[0]/fv=='" + FeatureLoggerTestUtils.toFeatureVector("origScore", doc0Score, "c2", "2.0")+"'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[1]/id=='8'");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[1]/fv=='origScore:" + doc1Score + ";c2:2.0'");
+ "/response/docs/[1]/fv=='" + FeatureLoggerTestUtils.toFeatureVector("origScore", doc1Score, "c2", "2.0")+"'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[2]/id=='6'");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[2]/fv=='origScore:" + doc2Score + ";c2:2.0'");
+ "/response/docs/[2]/fv=='" + FeatureLoggerTestUtils.toFeatureVector("origScore", doc2Score, "c2", "2.0")+"'");
assertJQ("/query" + query.toQueryString(), "/response/docs/[3]/id=='7'");
assertJQ("/query" + query.toQueryString(),
- "/response/docs/[3]/fv=='origScore:" + doc3Score + ";c2:2.0'");
+ "/response/docs/[3]/fv=='" + FeatureLoggerTestUtils.toFeatureVector("origScore", doc3Score, "c2", "2.0")+"'");
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml b/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
index c0e37b8..6ca9876 100644
--- a/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
+++ b/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
@@ -81,6 +81,9 @@
<lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/contrib/ltr/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-ltr-\d.*\.jar" />
+
<lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
@@ -504,6 +507,23 @@
showItems="32" />
-->
+ <!-- Feature Values Cache
+
+ Cache used by the Learning To Rank (LTR) contrib module.
+
+ You will need to set the solr.ltr.enabled system property
+ when running solr to run with ltr enabled:
+ -Dsolr.ltr.enabled=true
+
+ https://cwiki.apache.org/confluence/display/solr/Result+Reranking
+ -->
+ <cache enable="${solr.ltr.enabled:false}" name="QUERY_DOC_FV"
+ class="solr.search.LRUCache"
+ size="4096"
+ initialSize="2048"
+ autowarmCount="4096"
+ regenerator="solr.search.NoOpRegenerator" />
+
<!-- Custom Cache
Example of a generic cache. These caches may be accessed by
@@ -1586,8 +1606,19 @@
<valueSourceParser name="myfunc"
class="com.mycompany.MyValueSourceParser" />
-->
-
-
+
+ <!-- LTR query parser
+
+ You will need to set the solr.ltr.enabled system property
+ when running solr to run with ltr enabled:
+ -Dsolr.ltr.enabled=true
+
+ https://cwiki.apache.org/confluence/display/solr/Result+Reranking
+
+ Query parser is used to rerank top docs with a provided model
+ -->
+ <queryParser enable="${solr.ltr.enabled:false}" name="ltr" class="org.apache.solr.ltr.search.LTRQParserPlugin"/>
+
<!-- Document Transformers
http://wiki.apache.org/solr/DocTransformers
-->
@@ -1611,5 +1642,22 @@
EditorialMarkerFactory will do exactly that:
<transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
-->
-
+
+ <!--
+ LTR Transformer will encode the document features in the response. For each document the transformer
+ will add the features as an extra field in the response. The name of the field will be the
+ name of the transformer enclosed between brackets (in this case [features]).
+ In order to get the feature vector you will have to specify that you
+ want the field (e.g., fl="*,[features])
+
+ You will need to set the solr.ltr.enabled system property
+ when running solr to run with ltr enabled:
+ -Dsolr.ltr.enabled=true
+
+ https://cwiki.apache.org/confluence/display/solr/Result+Reranking
+ -->
+ <transformer enable="${solr.ltr.enabled:false}" name="features" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory">
+ <str name="fvCacheName">QUERY_DOC_FV</str>
+ </transformer>
+
</config>
[2/3] lucene-solr:branch_6x: SOLR-8542: techproducts example now
includes (disabled) learning-to-rank support (enable via
-Dsolr.ltr.enabled=true)
Posted by cp...@apache.org.
SOLR-8542: techproducts example now includes (disabled) learning-to-rank support (enable via -Dsolr.ltr.enabled=true)
additional changes as follows:
* LTRFeatureLoggerTransformerFactory:
** feature values cache name configurable (instead of hard-coded value that needs to match solrconfig.xml configuration)
** javadocs (example and parameters)
* CSV FeatureLogger:
** removed delimiter and separator assumptions in tests
** changed delimiter and separator (from "key:val;key:val" to "key=val,key=val")
** configurable (key value) delimiter and (features) separator
* JSON FeatureLogger:
** defer support for this (removing MapFeatureLogger class)
* adds 'training libraries' to (Linear|MultipleAdditiveTrees)Model javadocs
(Diego Ceccarelli, Michael Nilsson, Christine Poerschke)
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/4852851d
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/4852851d
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/4852851d
Branch: refs/heads/branch_6x
Commit: 4852851d85fc874e3d6fb48faac98d0552873b80
Parents: b1de736
Author: Christine Poerschke <cp...@apache.org>
Authored: Mon Dec 19 16:22:50 2016 +0000
Committer: Christine Poerschke <cp...@apache.org>
Committed: Mon Dec 19 16:50:33 2016 +0000
----------------------------------------------------------------------
solr/contrib/ltr/README.md | 36 +-
solr/contrib/ltr/example/solrconfig.xml | 1711 ------------------
.../org/apache/solr/ltr/CSVFeatureLogger.java | 62 +
.../java/org/apache/solr/ltr/FeatureLogger.java | 134 +-
.../java/org/apache/solr/ltr/LTRRescorer.java | 2 +-
.../org/apache/solr/ltr/LTRScoringQuery.java | 2 +-
.../solr/ltr/SolrQueryRequestContextUtils.java | 6 +-
.../org/apache/solr/ltr/model/LinearModel.java | 10 +
.../ltr/model/MultipleAdditiveTreesModel.java | 5 +
.../LTRFeatureLoggerTransformerFactory.java | 105 +-
solr/contrib/ltr/src/java/overview.html | 2 +-
.../solr/collection1/conf/solrconfig-ltr.xml | 5 +-
.../collection1/conf/solrconfig-ltr_Th10_10.xml | 5 +-
.../collection1/conf/solrconfig-multiseg.xml | 12 +-
.../apache/solr/ltr/FeatureLoggerTestUtils.java | 44 +
.../org/apache/solr/ltr/TestLTROnSolrCloud.java | 17 +-
.../solr/ltr/TestSelectiveWeightCreation.java | 11 +-
.../solr/ltr/feature/TestExternalFeatures.java | 12 +-
.../ltr/feature/TestExternalValueFeatures.java | 4 +-
.../solr/ltr/feature/TestFeatureLogging.java | 99 +-
.../solr/ltr/feature/TestFieldValueFeature.java | 13 +-
.../solr/ltr/feature/TestFilterSolrFeature.java | 6 +-
.../ltr/feature/TestNoMatchSolrFeature.java | 6 +-
.../ltr/feature/TestOriginalScoreFeature.java | 9 +-
.../conf/solrconfig.xml | 54 +-
25 files changed, 379 insertions(+), 1993 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/README.md
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/README.md b/solr/contrib/ltr/README.md
index 2033ffc..5c95056 100644
--- a/solr/contrib/ltr/README.md
+++ b/solr/contrib/ltr/README.md
@@ -13,6 +13,8 @@ deploy that model to Solr and use it to rerank your top X search results.
Solr provides some simple example of indices. In order to test the plugin with
the techproducts example please follow these steps.
+If you want to install the plugin on your instance of Solr, please refer
+to the [Solr Ref Guide](https://cwiki.apache.org/confluence/display/solr/Result+Reranking).
1. Compile solr and the examples
@@ -20,38 +22,17 @@ the techproducts example please follow these steps.
`ant dist`
`ant server`
-2. Run the example to setup the index
+2. Run the example to setup the index, enabling the ltr plugin
- `./bin/solr -e techproducts`
+ `./bin/solr -e techproducts -Dsolr.ltr.enabled=true`
-3. Stop solr and install the plugin:
- 1. Stop solr
-
- `./bin/solr stop`
- 2. Create the lib folder
-
- `mkdir example/techproducts/solr/techproducts/lib`
- 3. Install the plugin in the lib folder
-
- `cp build/contrib/ltr/solr-ltr-7.0.0-SNAPSHOT.jar example/techproducts/solr/techproducts/lib/`
- 4. Replace the original solrconfig with one importing all the ltr components
-
- `cp contrib/ltr/example/solrconfig.xml example/techproducts/solr/techproducts/conf/`
-
-4. Run the example again
-
- `./bin/solr -e techproducts`
-
- Note you could also have just restarted your collection using the admin page.
- You can find more detailed instructions [here](https://wiki.apache.org/solr/SolrPlugins).
-
-5. Deploy features and a model
+3. Deploy features and a model
`curl -XPUT 'http://localhost:8983/solr/techproducts/schema/feature-store' --data-binary "@./contrib/ltr/example/techproducts-features.json" -H 'Content-type:application/json'`
`curl -XPUT 'http://localhost:8983/solr/techproducts/schema/model-store' --data-binary "@./contrib/ltr/example/techproducts-model.json" -H 'Content-type:application/json'`
-6. Have fun !
+4. Have fun !
* Access to the default feature store
@@ -99,7 +80,9 @@ BONUS: Train an actual machine learning model
In order to get the feature vector you will have to
specify that you want the field (e.g., fl="*,[features]) -->
- <transformer name="features" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory" />
+ <transformer name="features" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory">
+ <str name="fvCacheName">QUERY_DOC_FV</str>
+ </transformer>
<query>
...
@@ -395,6 +378,7 @@ About half the time for ranking is spent in the creation of weights for each fea
<!-- Transformer for extracting features -->
<transformer name="features" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory">
+ <str name="fvCacheName">QUERY_DOC_FV</str>
<int name="threadModule.totalPoolThreads">10</int> <!-- Maximum threads to share for all requests -->
<int name="threadModule.numThreadsPerRequest">5</int> <!-- Maximum threads to use for a single request -->
</transformer>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/example/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/example/solrconfig.xml b/solr/contrib/ltr/example/solrconfig.xml
deleted file mode 100644
index 1c66c49..0000000
--- a/solr/contrib/ltr/example/solrconfig.xml
+++ /dev/null
@@ -1,1711 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>6.0.0</luceneMatchVersion>
-
- <!-- <lib/> directives can be used to instruct Solr to load any Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- Please note that <lib/> directives are processed in the order
- that they appear in your solrconfig.xml file, and are "stacked"
- on top of each other when building a ClassLoader - so if you have
- plugin jars with dependencies on other jars, the "lower level"
- dependency jars should be loaded first.
-
- If a "./lib" directory exists in your instanceDir, all files
- found in it are included as if you had used the following
- syntax...
- -->
- <lib dir="./lib" />
-
-
- <!-- A 'dir' option by itself adds any files found in the directory
- to the classpath, this is useful for including all jars in a
- directory.
-
- When a 'regex' is specified in addition to a 'dir', only the
- files in that directory which completely match the regex
- (anchored on both ends) will be included.
-
- If a 'dir' option (with or without a regex) is used and nothing
- is found that matches, a warning will be logged.
-
- The examples below can be used to load some solr-contribs along
- with their external dependencies.
- -->
- <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
-
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific jar file. This will cause a serious error to be logged
- if it can't be loaded.
- -->
- <!--
- <lib path="../a-jar-that-does-not-exist.jar" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:}</dataDir>
-
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory,
- solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
-
- <!-- The CodecFactory for defining the format of the inverted index.
- The default implementation is SchemaCodecFactory, which is the official Lucene
- index format, but hooks into the schema to provide per-field customization of
- the postings lists and per-document values in the fieldType element
- (postingsFormat/docValuesFormat). Note that most of the alternative implementations
- are experimental, so if you choose to customize the index format, it's a good
- idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
- before upgrading to a newer version to avoid unnecessary reindexing.
- A "compressionMode" string element can be added to <codecFactory> to choose
- between the existing compression modes in the default codec: "BEST_SPEED" (default)
- or "BEST_COMPRESSION".
- -->
- <codecFactory class="solr.SchemaCodecFactory"/>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <!-- <writeLockTimeout>1000</writeLockTimeout> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
- Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>false</useCompoundFile> -->
-
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
- indexing for buffering added documents and deletions before they are
- flushed to the Directory.
- maxBufferedDocs sets a limit on the number of documents buffered
- before flushing.
- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first.
- The default is 100 MB. -->
- <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <!-- Expert: Merge Policy
- -->
- <!--
- <mergePolicyFactory class="...">
- ...
- </mergePolicyFactory>
- -->
-
- <!-- Expert: Merge Scheduler
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- can perform merges in the background using separate threads.
- The SerialMergeScheduler (Lucene 2.2 default) does not.
- -->
- <!--
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
- This option specifies which Lucene LockFactory implementation
- to use.
-
- single = SingleInstanceLockFactory - suggested for a
- read-only index or when there is no possibility of
- another process trying to modify the index.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>${solr.lock.type:native}</lockType>
-
- <!-- Commit Deletion Policy
- Custom deletion policies can be specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- The default Solr IndexDeletionPolicy implementation supports
- deleting index commit points on number of commits, age of
- commit point and optimized status.
-
- The latest commit point should always be preserved regardless
- of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <str name="maxCommitAge">30MINUTES</str>
- <str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
-
- <!-- Lucene Infostream
-
- To aid in advanced debugging, Lucene provides an "InfoStream"
- of detailed information when indexing.
-
- Setting the value to true will instruct the underlying Lucene
- IndexWriter to write its info stream to solr's log. By default,
- this is enabled here, and controlled through log4j.properties.
- -->
- <infoStream>true</infoStream>
- </indexConfig>
-
-
- <!-- JMX
-
- This example enables JMX if and only if an existing MBeanServer
- is found, use this if you want to configure JMX through JVM
- parameters. Remove this to disable exposing Solr configuration
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- Enables a transaction log, used for real-time get, durability, and
- and solr cloud replica recovery. The log can grow as big as
- uncommitted changes to the index, so use of a hard autoCommit
- is recommended (see below).
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory.
- "numVersionBuckets" - sets the number of buckets used to keep
- track of max version values when checking for re-ordered
- updates; increase this value to reduce the cost of
- synchronizing access to version buckets during high-volume
- indexing, this requires 8 bytes (long) * numVersionBuckets
- of heap space per Solr core.
- -->
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
- </updateLog>
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
-
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
- </autoSoftCommit>
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
- hook such as postCommit or postOptimize.
-
- exe - the name of the executable to run
- dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Slow Query Threshold (in millis)
-
- At high request rates, logging all requests can become a bottleneck
- and therefore INFO logging is often turned off. However, it is still
- useful to be able to set a latency threshold above which a request
- is considered "slow" and log that request at WARN level so we can
- easily identify slow queries.
- -->
- <slowQueryThresholdMillis>-1</slowQueryThresholdMillis>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Query Result Cache
-
- Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- Additional supported parameter by LRUCache:
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy
- -->
- <queryResultCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Document Cache
-
- Caches Lucene Document objects (the stored fields for each
- document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
- -->
- <documentCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- custom cache currently used by block join -->
- <cache name="perSegFilter"
- class="solr.search.LRUCache"
- size="10"
- initialSize="0"
- autowarmCount="10"
- regenerator="solr.NoOpRegenerator" />
-
- <!-- Field Value Cache
-
- Cache used to hold field values that are quickly accessible
- by document id. The fieldValueCache is created by default
- even if not configured here.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- name through SolrIndexSearcher.getCache(),cacheLookup(), and
- cacheInsert(). The purpose is to enable easy caching of
- user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
- -->
- <!-- Cache for storing and fetching feature vectors -->
- <cache name="QUERY_DOC_FV"
- class="solr.search.LRUCache"
- size="4096"
- initialSize="2048"
- autowarmCount="4096"
- regenerator="solr.search.NoOpRegenerator" />
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <useColdSearcher>false</useColdSearcher>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect is a legacy option that affects the behavior of requests
- such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and dispatch the query to a handler specified by the
- "qt" param, assuming "/select" isn't already registered.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests, resulting in a 404 unless a handler
- is explicitly registered with the name "/select"
-
- handleSelect="true" is not recommended for new users, but is the default
- for backwards compatibility
- -->
- <requestDispatcher handleSelect="false" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- multipartUploadLimitInKB - specifies the max size (in KiB) of
- Multipart File Uploads that Solr will allow in a Request.
-
- formdataUploadLimitInKB - specifies the max size (in KiB) of
- form data (application/x-www-form-urlencoded) sent via
- POST. You can use POST to pass request parameters not
- fitting into the URL.
-
- addHttpRequestToContext - if set to true, it will instruct
- the requestParsers to include the original HttpServletRequest
- object in the context map of the SolrQueryRequest under the
- key "httpRequest". It will not be used by any of the existing
- Solr components, but may be useful when developing custom
- plugins.
-
- *** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
- addHttpRequestToContext="false"/>
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- If you include a <cacheControl> directive, it will be used to
- generate a Cache-Control header (as well as an Expires header
- if the value contains "max-age=")
-
- By default, no Cache-Control header is generated.
-
- You can use the <cacheControl> option even if you have set
- never304="true"
- -->
- <!--
- <httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- <!-- To enable Solr to respond with automatically generated HTTP
- Caching headers, and to response to Cache Validation requests
- correctly, set the value of never304="false"
-
- This will cause Solr to generate Last-Modified and ETag
- headers based on the properties of the Index.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- Incoming queries will be dispatched to a specific handler by name
- based on the path specified in the request.
-
- Legacy behavior: If the request path uses "/select" but no Request
- Handler has that name, and if handleSelect="true" has been specified in
- the requestDispatcher, then the Request Handler is dispatched based on
- the qt parameter. Handlers without a leading '/' are accessed this way
- like so: http://host/app/[core/]select?qt=name If no qt is
- given, then the requestHandler that declares default="true" will be
- used or the one named "standard".
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="/select" class="solr.SearchHandler">
- <!-- default values for query parameters can be specified, these
- will be overridden by parameters in the request
- -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <!-- Controls the distribution of a query to shards other than itself.
- Consider making 'preferLocalShards' true when:
- 1) maxShardsPerNode > 1
- 2) Number of shards > 1
- 3) CloudSolrClient or LbHttpSolrServer is used by clients.
- Without this option, every core broadcasts the distributed query to
- a replica of each shard where the replicas are chosen randomly.
- This option directs the cores to prefer cores hosted locally, thus
- preventing network delays between machines.
- This behavior also immunizes a bad/slow machine from slowing down all
- the good machines (if those good machines were querying this bad one).
-
- Specify this option=false for clients connecting through HttpSolrServer
- -->
- <bool name="preferLocalShards">false</bool>
- </lst>
- <!-- In addition to defaults, "appends" params can be specified
- to identify values which should be appended to the list of
- multi-val params from the query (or the existing "defaults").
- -->
- <!-- In this example, the param "fq=instock:true" would be appended to
- any query time fq params the user may specify, as a mechanism for
- partitioning the index, independent of any user selected filtering
- that may also be desired (perhaps as a result of faceted searching).
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "appends" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="appends">
- <str name="fq">inStock:true</str>
- </lst>
- -->
- <!-- "invariants" are a way of letting the Solr maintainer lock down
- the options available to Solr clients. Any params values
- specified here are used regardless of what values may be specified
- in either the query, the "defaults", or the "appends" params.
-
- In this example, the facet.field and facet.query params would
- be fixed, limiting the facets clients can use. Faceting is
- not turned on by default - but if the client does specify
- facet=true in the request, these are the only facets they
- will be able to see counts for; regardless of what other
- facet.field or facet.query params they may specify.
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "invariants" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="invariants">
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">price:[* TO 500]</str>
- <str name="facet.query">price:[500 TO *]</str>
- </lst>
- -->
- <!-- If the default list of SearchComponents is not desired, that
- list can either be overridden completely, or components can be
- prepended or appended to the default list. (see below)
- -->
- <!--
- <arr name="components">
- <str>nameOfCustomComponent1</str>
- <str>nameOfCustomComponent2</str>
- </arr>
- -->
- </requestHandler>
-
- <!-- Query parser used to rerank top docs with a provided model -->
- <queryParser name="ltr" class="org.apache.solr.ltr.search.LTRQParserPlugin" >
- <int name="threadModule.totalPoolThreads">10</int> <!-- Maximum threads to use for all queries -->
- <int name="threadModule.numThreadsPerRequest">10</int> <!-- Maximum threads to use for a single query-->
- </queryParser>
-
- <!-- Transformer that will encode the document features in the response. For each document the transformer
- will add the features as an extra field in the response. The name of the field we will be the the name of the
- transformer enclosed between brackets (in this case [features]). In order to get the feature vector you will have to
- specify that you want the field (e.g., fl="*,[features]) -->
- <transformer name="features" class="org.apache.solr.ltr.response.transform.LTRFeatureLoggerTransformerFactory" />
-
-
- <!-- A request handler that returns indented JSON by default -->
- <requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- <str name="df">text</str>
- </lst>
- </requestHandler>
-
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
- <str name="title">Solritas</str>
-
- <!-- Query settings -->
- <str name="defType">edismax</str>
- <str name="qf">
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
- title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
- </str>
- <str name="mm">100%</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
-
- <str name="mlt.qf">
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
- title^10.0 description^5.0 keywords^5.0 author^2.0 resourcename^1.0
- </str>
- <str name="mlt.fl">text,features,name,sku,id,manu,cat,title,description,keywords,author,resourcename</str>
- <int name="mlt.count">3</int>
-
- <!-- Faceting defaults -->
- <str name="facet">on</str>
- <str name="facet.missing">true</str>
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.field">content_type</str>
- <str name="facet.field">author_s</str>
- <str name="facet.query">ipod</str>
- <str name="facet.query">GB</str>
- <str name="facet.mincount">1</str>
- <str name="facet.pivot">cat,inStock</str>
- <str name="facet.range.other">after</str>
- <str name="facet.range">price</str>
- <int name="f.price.facet.range.start">0</int>
- <int name="f.price.facet.range.end">600</int>
- <int name="f.price.facet.range.gap">50</int>
- <str name="facet.range">popularity</str>
- <int name="f.popularity.facet.range.start">0</int>
- <int name="f.popularity.facet.range.end">10</int>
- <int name="f.popularity.facet.range.gap">3</int>
- <str name="facet.range">manufacturedate_dt</str>
- <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
- <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
- <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
- <str name="f.manufacturedate_dt.facet.range.other">before</str>
- <str name="f.manufacturedate_dt.facet.range.other">after</str>
-
- <!-- Highlighting defaults -->
- <str name="hl">on</str>
- <str name="hl.fl">content features title name</str>
- <str name="hl.preserveMulti">true</str>
- <str name="hl.encoder">html</str>
- <str name="hl.simple.pre"><b></str>
- <str name="hl.simple.post"></b></str>
- <str name="f.title.hl.fragsize">0</str>
- <str name="f.title.hl.alternateField">title</str>
- <str name="f.name.hl.fragsize">0</str>
- <str name="f.name.hl.alternateField">name</str>
- <str name="f.content.hl.snippets">3</str>
- <str name="f.content.hl.fragsize">200</str>
- <str name="f.content.hl.alternateField">content</str>
- <str name="f.content.hl.maxAlternateFieldLength">750</str>
-
- <!-- Spell checking defaults -->
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">false</str>
- <str name="spellcheck.count">5</str>
- <str name="spellcheck.alternativeTermCount">2</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">5</str>
- <str name="spellcheck.maxCollations">3</str>
- </lst>
-
- <!-- append spellchecking to our list of components -->
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
-
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
- <lst name="defaults">
- <str name="df">text</str>
- </lst>
- </initParams>
-
- <initParams path="/update/json/docs">
- <lst name="defaults">
- <!--this ensures that the entire json doc will be stored verbatim into one field-->
- <str name="srcField">_src_</str>
- <!--This means a the uniqueKeyField will be extracted from the fields and
- all fields go into the 'df' field. In this config df is already configured to be 'text'
- -->
- <str name="mapUniqueKeyOnly">true</str>
- </lst>
-
- </initParams>
-
- <!-- The following are implicitly added
- <requestHandler name="/update/json" class="solr.UpdateRequestHandler">
- <lst name="defaults">
- <str name="stream.contentType">application/json</str>
- </lst>
- </requestHandler>
- <requestHandler name="/update/csv" class="solr.UpdateRequestHandler">
- <lst name="defaults">
- <str name="stream.contentType">application/csv</str>
- </lst>
- </requestHandler>
- -->
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <str name="lowernames">true</str>
- <str name="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</str>
- </lst>
- </requestHandler>
-
-
- <!-- Field Analysis Request Handler
-
- RequestHandler that provides much the same functionality as
- analysis.jsp. Provides the ability to specify multiple field
- types and field names in the same request and outputs
- index-time and query-time analysis for each of them.
-
- Request parameters are:
- analysis.fieldname - field name whose analyzers are to be used
-
- analysis.fieldtype - field type whose analyzers are to be used
- analysis.fieldvalue - text for index-time analysis
- q (or analysis.q) - text for query time analysis
- analysis.showmatch (true|false) - When set to true and when
- query analysis is performed, the produced tokens of the
- field value analysis will be marked as "matched" for every
- token that is produces by the query analysis
- -->
- <requestHandler name="/analysis/field"
- startup="lazy"
- class="solr.FieldAnalysisRequestHandler" />
-
-
- <!-- Document Analysis Handler
-
- http://wiki.apache.org/solr/AnalysisRequestHandler
-
- An analysis handler that provides a breakdown of the analysis
- process of provided documents. This handler expects a (single)
- content stream with the following format:
-
- <docs>
- <doc>
- <field name="id">1</field>
- <field name="name">The Name</field>
- <field name="text">The Text Value</field>
- </doc>
- <doc>...</doc>
- <doc>...</doc>
- ...
- </docs>
-
- Note: Each document must contain a field which serves as the
- unique key. This key is used in the returned response to associate
- an analysis breakdown to the analyzed document.
-
- Like the FieldAnalysisRequestHandler, this handler also supports
- query analysis by sending either an "analysis.query" or "q"
- request parameter that holds the query text to be analyzed. It
- also supports the "analysis.showmatch" parameter which when set to
- true, all field tokens that match the query tokens will be marked
- as a "match".
- -->
- <requestHandler name="/analysis/document"
- class="solr.DocumentAnalysisRequestHandler"
- startup="lazy" />
-
- <!-- Echo the request contents back to the client -->
- <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="echoHandler">true</str>
- </lst>
- </requestHandler>
-
- <!-- Search Components
-
- Search components are registered to SolrCore and used by
- instances of SearchHandler (which can access them by name)
-
- By default, the following components are available:
-
- <searchComponent name="query" class="solr.QueryComponent" />
- <searchComponent name="facet" class="solr.FacetComponent" />
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="solr.HighlightComponent" />
- <searchComponent name="stats" class="solr.StatsComponent" />
- <searchComponent name="debug" class="solr.DebugComponent" />
-
- Default configuration in a requestHandler would look like:
-
- <arr name="components">
- <str>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- If you register a searchComponent to one of the standard names,
- that will be used instead of the default.
-
- To insert components before or after the 'standard' components, use:
-
- <arr name="first-components">
- <str>myFirstComponentName</str>
- </arr>
-
- <arr name="last-components">
- <str>myLastComponentName</str>
- </arr>
-
- NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text_general</str>
-
- <!-- Multiple "Spell Checkers" can be declared and used by this
- component
- -->
-
- <!-- a spellchecker built from a field of the main index -->
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">text</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
- <str name="distanceMeasure">internal</str>
- <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
- <float name="accuracy">0.5</float>
- <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
- <int name="maxEdits">2</int>
- <!-- the minimum shared prefix when enumerating terms -->
- <int name="minPrefix">1</int>
- <!-- maximum number of inspections per result. -->
- <int name="maxInspections">5</int>
- <!-- minimum length of a query term to be considered for correction -->
- <int name="minQueryLength">4</int>
- <!-- maximum threshold of documents a query term can appear to be considered for correction -->
- <float name="maxQueryFrequency">0.01</float>
- <!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
- <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
- <lst name="spellchecker">
- <str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
- <str name="field">name</str>
- <str name="combineWords">true</str>
- <str name="breakWords">true</str>
- <int name="maxChanges">10</int>
- </lst>
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="comparatorClass">freq</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
- </searchComponent>
-
- <!-- A request handler for demonstrating the spellcheck component.
-
- NOTE: This is purely as an example. The whole purpose of the
- SpellCheckComponent is to hook it into the request handler that
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
- See http://wiki.apache.org/solr/SpellCheckComponent for details
- on the request parameters.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <!-- Solr will use suggestions from both the 'default' spellchecker
- and from the 'wordbreak' spellchecker and combine them.
- collations (re-written queries) can include a combination of
- corrections from both spellcheckers -->
- <str name="spellcheck.dictionary">default</str>
- <str name="spellcheck.dictionary">wordbreak</str>
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
- <str name="spellcheck.count">10</str>
- <str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- The SuggestComponent in Solr provides users with automatic suggestions for query terms.
- You can use this to implement a powerful auto-suggest feature in your search application.
- As with the rest of this solrconfig.xml file, the configuration of this component is purely
- an example that applies specifically to this configset and example documents.
-
- More information about this component and other configuration options are described in the
- "Suggester" section of the reference guide available at
- http://archive.apache.org/dist/lucene/solr/ref-guide
- -->
- <searchComponent name="suggest" class="solr.SuggestComponent">
- <lst name="suggester">
- <str name="name">mySuggester</str>
- <str name="lookupImpl">FuzzyLookupFactory</str>
- <str name="dictionaryImpl">DocumentDictionaryFactory</str>
- <str name="field">cat</str>
- <str name="weightField">price</str>
- <str name="suggestAnalyzerFieldType">string</str>
- <str name="buildOnStartup">false</str>
- </lst>
- </searchComponent>
-
- <requestHandler name="/suggest" class="solr.SearchHandler"
- startup="lazy" >
- <lst name="defaults">
- <str name="suggest">true</str>
- <str name="suggest.count">10</str>
- </lst>
- <arr name="components">
- <str>suggest</str>
- </arr>
- </requestHandler>
-
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component
-
- You'll need to set the solr.clustering.enabled system property
- when running solr to run with clustering enabled:
- -Dsolr.clustering.enabled=true
-
- https://cwiki.apache.org/confluence/display/solr/Result+Clustering
- -->
- <searchComponent name="clustering"
- enable="${solr.clustering.enabled:false}"
- class="solr.clustering.ClusteringComponent" >
- <!--
- Declaration of "engines" (clustering algorithms).
-
- The open source algorithms from Carrot2.org project:
- * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
- * org.carrot2.clustering.stc.STCClusteringAlgorithm
- * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
- See http://project.carrot2.org/algorithms.html for more information.
-
- Commercial algorithm Lingo3G (needs to be installed separately):
- * com.carrotsearch.lingo3g.Lingo3GClusteringAlgorithm
- -->
-
- <lst name="engine">
- <str name="name">lingo3g</str>
- <bool name="optional">true</bool>
- <str name="carrot.algorithm">com.carrotsearch.lingo3g.Lingo3GClusteringAlgorithm</str>
- <str name="carrot.resourcesDir">clustering/carrot2</str>
- </lst>
-
- <lst name="engine">
- <str name="name">lingo</str>
- <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
- <str name="carrot.resourcesDir">clustering/carrot2</str>
- </lst>
-
- <lst name="engine">
- <str name="name">stc</str>
- <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
- <str name="carrot.resourcesDir">clustering/carrot2</str>
- </lst>
-
- <lst name="engine">
- <str name="name">kmeans</str>
- <str name="carrot.algorithm">org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm</str>
- <str name="carrot.resourcesDir">clustering/carrot2</str>
- </lst>
- </searchComponent>
-
- <!-- A request handler for demonstrating the clustering component.
- This is meant as an example.
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/clustering"
- startup="lazy"
- enable="${solr.clustering.enabled:false}"
- class="solr.SearchHandler">
- <lst name="defaults">
- <bool name="clustering">true</bool>
- <bool name="clustering.results">true</bool>
- <!-- Field name with the logical "title" of a each document (optional) -->
- <str name="carrot.title">name</str>
- <!-- Field name with the logical "URL" of a each document (optional) -->
- <str name="carrot.url">id</str>
- <!-- Field name with the logical "content" of a each document (optional) -->
- <str name="carrot.snippet">features</str>
- <!-- Apply highlighter to the title/ content and use this for clustering. -->
- <bool name="carrot.produceSummary">true</bool>
- <!-- the maximum number of labels per cluster -->
- <!--<int name="carrot.numDescriptions">5</int>-->
- <!-- produce sub clusters -->
- <bool name="carrot.outputSubClusters">false</bool>
-
- <!-- Configure the remaining request handler parameters. -->
- <str name="defType">edismax</str>
- <str name="qf">
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
- </str>
- <str name="q.alt">*:*</str>
- <str name="rows">100</str>
- <str name="fl">*,score</str>
- </lst>
- <arr name="last-components">
- <str>clustering</str>
- </arr>
- </requestHandler>
-
- <!-- Terms Component
-
- http://wiki.apache.org/solr/TermsComponent
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- <bool name="distrib">false</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
- default="true"
- class="solr.highlight.WeightedFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
- default="true"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
- <lst name="defaults">
- <str name="hl.multiValuedSeparatorChar">/</str>
- </lst>
- -->
- </fragmentsBuilder>
-
- <!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
-
- <boundaryScanner name="default"
- default="true"
- class="solr.highlight.SimpleBoundaryScanner">
- <lst name="defaults">
- <str name="hl.bs.maxScan">10</str>
- <str name="hl.bs.chars">.,!? 	 </str>
- </lst>
- </boundaryScanner>
-
- <boundaryScanner name="breakIterator"
- class="solr.highlight.BreakIteratorBoundaryScanner">
- <lst name="defaults">
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
- <str name="hl.bs.type">WORD</str>
- <!-- language and country are used when constructing Locale object. -->
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
- <str name="hl.bs.language">en</str>
- <str name="hl.bs.country">US</str>
- </lst>
- </boundaryScanner>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- http://wiki.apache.org/solr/UpdateRequestProcessor
-
- -->
- <!-- Deduplication
-
- An example dedup update processor that creates the "id" field
- on the fly based on the hash code of some other fields. This
- example has overwriteDupes set to false since we are using the
- id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Language identification
-
- This example update chain identifies the language of the incoming
- documents using the langid contrib. The detected language is
- written to field language_s. No field name mapping is done.
- The fields used for detection are text, title, subject and description,
- making this example suitable for detecting languages form full-text
- rich documents injected via ExtractingRequestHandler.
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
- -->
- <!--
- <updateRequestProcessorChain name="langid">
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
- <str name="langid.fl">text,title,subject,description</str>
- <str name="langid.langField">language_s</str>
- <str name="langid.fallback">en</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Script update processor
-
- This example hooks in an update processor implemented using JavaScript.
-
- See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
- -->
- <!--
- <updateRequestProcessorChain name="script">
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <lst name="params">
- <str name="config_param">example config parameter</str>
- </lst>
- </processor>
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
- -->
-
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
- <str name="template.base.dir">${velocity.template.base.dir:}</str>
- </queryResponseWriter>
-
-
- <!-- XSLT response writer transforms the XML output by any xslt file found
- in Solr's conf/xslt directory. Changes to xslt files are checked for
- every xsltCacheLifetimeSeconds.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- http://wiki.apache.org/solr/SolrQuerySyntax
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
-
- <!-- Document Transformers
- http://wiki.apache.org/solr/DocTransformers
- -->
- <!--
- Could be something like:
- <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
- <int name="connection">jdbc://....</int>
- </transformer>
-
- To add a constant value to all docs, use:
- <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <int name="value">5</int>
- </transformer>
-
- If you want the user to still be able to change it with _value:something_ use this:
- <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <double name="defaultValue">5</double>
- </transformer>
-
- If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
- EditorialMarkerFactory will do exactly that:
- <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
- -->
-
-
- <!-- Legacy config for the admin interface -->
- <admin>
- <defaultQuery>*:*</defaultQuery>
- </admin>
-
-</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/CSVFeatureLogger.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/CSVFeatureLogger.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/CSVFeatureLogger.java
new file mode 100644
index 0000000..2da754e
--- /dev/null
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/CSVFeatureLogger.java
@@ -0,0 +1,62 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.solr.ltr;
+
+/**
+ * A feature logger that logs in csv format.
+ */
+public class CSVFeatureLogger extends FeatureLogger {
+ public static final char DEFAULT_KEY_VALUE_SEPARATOR = '=';
+ public static final char DEFAULT_FEATURE_SEPARATOR = ',';
+ private final char keyValueSep;
+ private final char featureSep;
+
+ public CSVFeatureLogger(String fvCacheName, FeatureFormat f) {
+ super(fvCacheName, f);
+ this.keyValueSep = DEFAULT_KEY_VALUE_SEPARATOR;
+ this.featureSep = DEFAULT_FEATURE_SEPARATOR;
+ }
+
+ public CSVFeatureLogger(String fvCacheName, FeatureFormat f, char keyValueSep, char featureSep) {
+ super(fvCacheName, f);
+ this.keyValueSep = keyValueSep;
+ this.featureSep = featureSep;
+ }
+
+ @Override
+ public String makeFeatureVector(LTRScoringQuery.FeatureInfo[] featuresInfo) {
+ // Allocate the buffer to a size based on the number of features instead of the
+ // default 16. You need space for the name, value, and two separators per feature,
+ // but not all the features are expected to fire, so this is just a naive estimate.
+ StringBuilder sb = new StringBuilder(featuresInfo.length * 3);
+ boolean isDense = featureFormat.equals(FeatureFormat.DENSE);
+ for (LTRScoringQuery.FeatureInfo featInfo:featuresInfo) {
+ if (featInfo.isUsed() || isDense){
+ sb.append(featInfo.getName())
+ .append(keyValueSep)
+ .append(featInfo.getValue())
+ .append(featureSep);
+ }
+ }
+
+ final String features = (sb.length() > 0 ?
+ sb.substring(0, sb.length() - 1) : "");
+
+ return features;
+ }
+
+}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/FeatureLogger.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/FeatureLogger.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/FeatureLogger.java
index 9c10c2c..ec14ab9 100644
--- a/solr/contrib/ltr/src/java/org/apache/solr/ltr/FeatureLogger.java
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/FeatureLogger.java
@@ -16,30 +16,22 @@
*/
package org.apache.solr.ltr;
-import java.lang.invoke.MethodHandles;
-import java.util.Collections;
-import java.util.HashMap;
-import java.util.Map;
-
import org.apache.solr.search.SolrIndexSearcher;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
/**
* FeatureLogger can be registered in a model and provide a strategy for logging
* the feature values.
*/
-public abstract class FeatureLogger<FV_TYPE> {
-
- private static final Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());
+public abstract class FeatureLogger {
/** the name of the cache using for storing the feature value **/
- private static final String QUERY_FV_CACHE_NAME = "QUERY_DOC_FV";
+ private final String fvCacheName;
- protected enum FeatureFormat {DENSE, SPARSE};
+ public enum FeatureFormat {DENSE, SPARSE};
protected final FeatureFormat featureFormat;
- protected FeatureLogger(FeatureFormat f) {
+ protected FeatureLogger(String fvCacheName, FeatureFormat f) {
+ this.fvCacheName = fvCacheName;
this.featureFormat = f;
}
@@ -58,56 +50,16 @@ public abstract class FeatureLogger<FV_TYPE> {
public boolean log(int docid, LTRScoringQuery scoringQuery,
SolrIndexSearcher searcher, LTRScoringQuery.FeatureInfo[] featuresInfo) {
- final FV_TYPE featureVector = makeFeatureVector(featuresInfo);
+ final String featureVector = makeFeatureVector(featuresInfo);
if (featureVector == null) {
return false;
}
- return searcher.cacheInsert(QUERY_FV_CACHE_NAME,
+ return searcher.cacheInsert(fvCacheName,
fvCacheKey(scoringQuery, docid), featureVector) != null;
}
- /**
- * returns a FeatureLogger that logs the features in output, using the format
- * specified in the 'stringFormat' param: 'csv' will log the features as a unique
- * string in csv format 'json' will log the features in a map in a Map of
- * featureName keys to featureValue values if format is null or empty, csv
- * format will be selected.
- * 'featureFormat' param: 'dense' will write features in dense format,
- * 'sparse' will write the features in sparse format, null or empty will
- * default to 'sparse'
- *
- *
- * @return a feature logger for the format specified.
- */
- public static FeatureLogger<?> createFeatureLogger(String stringFormat, String featureFormat) {
- final FeatureFormat f;
- if (featureFormat == null || featureFormat.isEmpty() ||
- featureFormat.equals("sparse")) {
- f = FeatureFormat.SPARSE;
- }
- else if (featureFormat.equals("dense")) {
- f = FeatureFormat.DENSE;
- }
- else {
- f = FeatureFormat.SPARSE;
- log.warn("unknown feature logger feature format {} | {}", stringFormat, featureFormat);
- }
- if ((stringFormat == null) || stringFormat.isEmpty()) {
- return new CSVFeatureLogger(f);
- }
- if (stringFormat.equals("csv")) {
- return new CSVFeatureLogger(f);
- }
- if (stringFormat.equals("json")) {
- return new MapFeatureLogger(f);
- }
- log.warn("unknown feature logger string format {} | {}", stringFormat, featureFormat);
- return null;
-
- }
-
- public abstract FV_TYPE makeFeatureVector(LTRScoringQuery.FeatureInfo[] featuresInfo);
+ public abstract String makeFeatureVector(LTRScoringQuery.FeatureInfo[] featuresInfo);
private static int fvCacheKey(LTRScoringQuery scoringQuery, int docid) {
return scoringQuery.hashCode() + (31 * docid);
@@ -121,75 +73,9 @@ public abstract class FeatureLogger<FV_TYPE> {
* @return String representation of the list of features calculated for docid
*/
- public FV_TYPE getFeatureVector(int docid, LTRScoringQuery scoringQuery,
+ public String getFeatureVector(int docid, LTRScoringQuery scoringQuery,
SolrIndexSearcher searcher) {
- return (FV_TYPE) searcher.cacheLookup(QUERY_FV_CACHE_NAME, fvCacheKey(scoringQuery, docid));
- }
-
-
- public static class MapFeatureLogger extends FeatureLogger<Map<String,Float>> {
-
- public MapFeatureLogger(FeatureFormat f) {
- super(f);
- }
-
- @Override
- public Map<String,Float> makeFeatureVector(LTRScoringQuery.FeatureInfo[] featuresInfo) {
- boolean isDense = featureFormat.equals(FeatureFormat.DENSE);
- Map<String,Float> hashmap = Collections.emptyMap();
- if (featuresInfo.length > 0) {
- hashmap = new HashMap<String,Float>(featuresInfo.length);
- for (LTRScoringQuery.FeatureInfo featInfo:featuresInfo){
- if (featInfo.isUsed() || isDense){
- hashmap.put(featInfo.getName(), featInfo.getValue());
- }
- }
- }
- return hashmap;
- }
-
- }
-
- public static class CSVFeatureLogger extends FeatureLogger<String> {
- char keyValueSep = ':';
- char featureSep = ';';
-
- public CSVFeatureLogger(FeatureFormat f) {
- super(f);
- }
-
- public CSVFeatureLogger setKeyValueSep(char keyValueSep) {
- this.keyValueSep = keyValueSep;
- return this;
- }
-
- public CSVFeatureLogger setFeatureSep(char featureSep) {
- this.featureSep = featureSep;
- return this;
- }
-
- @Override
- public String makeFeatureVector(LTRScoringQuery.FeatureInfo[] featuresInfo) {
- // Allocate the buffer to a size based on the number of features instead of the
- // default 16. You need space for the name, value, and two separators per feature,
- // but not all the features are expected to fire, so this is just a naive estimate.
- StringBuilder sb = new StringBuilder(featuresInfo.length * 3);
- boolean isDense = featureFormat.equals(FeatureFormat.DENSE);
- for (LTRScoringQuery.FeatureInfo featInfo:featuresInfo) {
- if (featInfo.isUsed() || isDense){
- sb.append(featInfo.getName())
- .append(keyValueSep)
- .append(featInfo.getValue())
- .append(featureSep);
- }
- }
-
- final String features = (sb.length() > 0 ?
- sb.substring(0, sb.length() - 1) : "");
-
- return features;
- }
-
+ return (String) searcher.cacheLookup(fvCacheName, fvCacheKey(scoringQuery, docid));
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRRescorer.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRRescorer.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRRescorer.java
index 27223b7..818d861 100644
--- a/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRRescorer.java
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRRescorer.java
@@ -148,7 +148,7 @@ public class LTRRescorer extends Rescorer {
LTRScoringQuery.ModelWeight.ModelScorer scorer = null;
int hitUpto = 0;
- final FeatureLogger<?> featureLogger = scoringQuery.getFeatureLogger();
+ final FeatureLogger featureLogger = scoringQuery.getFeatureLogger();
while (hitUpto < hits.length) {
final ScoreDoc hit = hits[hitUpto];
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRScoringQuery.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRScoringQuery.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRScoringQuery.java
index b43f955..9f227b9 100644
--- a/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRScoringQuery.java
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/LTRScoringQuery.java
@@ -63,7 +63,7 @@ public class LTRScoringQuery extends Query {
final private Semaphore querySemaphore; // limits the number of threads per query, so that multiple requests can be serviced simultaneously
// feature logger to output the features.
- private FeatureLogger<?> fl;
+ private FeatureLogger fl;
// Map of external parameters, such as query intent, that can be used by
// features
final private Map<String,String[]> efi;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4852851d/solr/contrib/ltr/src/java/org/apache/solr/ltr/SolrQueryRequestContextUtils.java
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/java/org/apache/solr/ltr/SolrQueryRequestContextUtils.java b/solr/contrib/ltr/src/java/org/apache/solr/ltr/SolrQueryRequestContextUtils.java
index 66426ea..2cff28f 100644
--- a/solr/contrib/ltr/src/java/org/apache/solr/ltr/SolrQueryRequestContextUtils.java
+++ b/solr/contrib/ltr/src/java/org/apache/solr/ltr/SolrQueryRequestContextUtils.java
@@ -37,12 +37,12 @@ public class SolrQueryRequestContextUtils {
/** feature logger accessors **/
- public static void setFeatureLogger(SolrQueryRequest req, FeatureLogger<?> featureLogger) {
+ public static void setFeatureLogger(SolrQueryRequest req, FeatureLogger featureLogger) {
req.getContext().put(FEATURE_LOGGER, featureLogger);
}
- public static FeatureLogger<?> getFeatureLogger(SolrQueryRequest req) {
- return (FeatureLogger<?>) req.getContext().get(FEATURE_LOGGER);
+ public static FeatureLogger getFeatureLogger(SolrQueryRequest req) {
+ return (FeatureLogger) req.getContext().get(FEATURE_LOGGER);
}
/** scoring query accessors **/
[3/3] lucene-solr:branch_6x: fix java warning in SolrQueryTest
Posted by cp...@apache.org.
fix java warning in SolrQueryTest
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/8c81deb8
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/8c81deb8
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/8c81deb8
Branch: refs/heads/branch_6x
Commit: 8c81deb88424c719719e379a43b1f5ef5b45f4f0
Parents: 4852851
Author: Christine Poerschke <cp...@apache.org>
Authored: Wed Dec 7 21:16:42 2016 +0000
Committer: Christine Poerschke <cp...@apache.org>
Committed: Mon Dec 19 17:08:44 2016 +0000
----------------------------------------------------------------------
.../solrj/src/test/org/apache/solr/client/solrj/SolrQueryTest.java | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/8c81deb8/solr/solrj/src/test/org/apache/solr/client/solrj/SolrQueryTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/SolrQueryTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/SolrQueryTest.java
index d27847f..1c86c93 100644
--- a/solr/solrj/src/test/org/apache/solr/client/solrj/SolrQueryTest.java
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/SolrQueryTest.java
@@ -441,7 +441,7 @@ public class SolrQueryTest extends LuceneTestCase {
solrQuery.addMoreLikeThisField("mlt3");
solrQuery.addMoreLikeThisField("mlt4");
assertEquals(4, solrQuery.getMoreLikeThisFields().length);
- solrQuery.setMoreLikeThisFields(null);
+ solrQuery.setMoreLikeThisFields((String[])null);
assertTrue(null == solrQuery.getMoreLikeThisFields());
assertFalse(solrQuery.getMoreLikeThis());