/**
* 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.handler;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.AttributeSource;
import org.apache.solr.client.solrj.request.FieldAnalysisRequest;
import org.apache.solr.common.params.AnalysisParams;
import org.apache.solr.common.params.CommonParams;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.util.SimpleOrderedMap;
import org.apache.solr.common.util.ContentStream;
import org.apache.solr.request.SolrQueryRequest;
import org.apache.solr.schema.FieldType;
import org.apache.solr.schema.IndexSchema;
import org.apache.commons.io.IOUtils;
import java.util.*;
import java.io.Reader;
import java.io.IOException;
/**
* 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. Expected parameters:
* <table border="1">
* <tr>
* <th align="left">Name</th>
* <th align="left">Type</th>
* <th align="left">required</th>
* <th align="left">Description</th>
* <th align="left">Multi-valued</th>
* </tr>
* <tr>
* <td>analysis.fieldname</td>
* <td>string</td>
* <td>no</td>
* <td>When present, the text will be analyzed based on the type of this field name.</td>
* <td>Yes, this parameter may hold a comma-separated list of values and the analysis will be performed for each of the specified fields</td>
* </tr>
* <tr>
* <td>analysis.fieldtype</td>
* <td>string</td>
* <td>no</td>
* <td>When present, the text will be analyzed based on the specified type</td>
* <td>Yes, this parameter may hold a comma-separated list of values and the analysis will be performed for each of the specified field types</td>
* </tr>
* <tr>
* <td>analysis.fieldvalue</td>
* <td>string</td>
* <td>yes</td>
* <td>The text that will be analyzed. The analysis will mimic the index-time analysis.</td>
* <td>No</td>
* </tr>
* <tr>
* <td>{@code analysis.query} OR {@code q}</td>
* <td>string</td>
* <td>no</td>
* <td>When present, the text that will be analyzed. The analysis will mimic the query-time analysis. Note that the
* {@code analysis.query} parameter as precedes the {@code q} parameters.</td>
* <td>No</td>
* </tr>
* <tr>
* <td>analysis.showmatch</td>
* <td>boolean</td>
* <td>no</td>
* <td>When set to {@code 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</td>
* <td>No</td>
* </tr>
* </table>
* <p>Note that if neither analysis.fieldname and analysis.fieldtype is specified, then the default search field's
* analyzer is used.</p>
*
* @version $Id: FieldAnalysisRequestHandler.java 1065312 2011-01-30 16:08:25Z rmuir $
* @since solr 1.4
*/
public class FieldAnalysisRequestHandler extends AnalysisRequestHandlerBase {
/**
* {@inheritDoc}
*/
@Override
protected NamedList doAnalysis(SolrQueryRequest req) throws Exception {
FieldAnalysisRequest analysisRequest = resolveAnalysisRequest(req);
IndexSchema indexSchema = req.getCore().getSchema();
return handleAnalysisRequest(analysisRequest, indexSchema);
}
@Override
public String getDescription() {
return "Provide a breakdown of the analysis process of field/query text";
}
@Override
public String getVersion() {
return "$Revision: 1065312 $";
}
@Override
public String getSourceId() {
return "$Id: FieldAnalysisRequestHandler.java 1065312 2011-01-30 16:08:25Z rmuir $";
}
@Override
public String getSource() {
return "$URL: https://svn.apache.org/repos/asf/lucene/dev/branches/lucene_solr_3_5/solr/core/src/java/org/apache/solr/handler/FieldAnalysisRequestHandler.java $";
}
// ================================================= Helper methods ================================================
/**
* Resolves the AnalysisRequest based on the parameters in the given SolrParams.
*
* @param req the request
*
* @return AnalysisRequest containing all the information about what needs to be analyzed, and using what
* fields/types
*/
FieldAnalysisRequest resolveAnalysisRequest(SolrQueryRequest req) {
SolrParams solrParams = req.getParams();
FieldAnalysisRequest analysisRequest = new FieldAnalysisRequest();
boolean useDefaultSearchField = true;
if (solrParams.get(AnalysisParams.FIELD_TYPE) != null) {
analysisRequest.setFieldTypes(Arrays.asList(solrParams.get(AnalysisParams.FIELD_TYPE).split(",")));
useDefaultSearchField = false;
}
if (solrParams.get(AnalysisParams.FIELD_NAME) != null) {
analysisRequest.setFieldNames(Arrays.asList(solrParams.get(AnalysisParams.FIELD_NAME).split(",")));
useDefaultSearchField = false;
}
if (useDefaultSearchField) {
analysisRequest.addFieldName(req.getSchema().getDefaultSearchFieldName());
}
analysisRequest.setQuery(solrParams.get(AnalysisParams.QUERY, solrParams.get(CommonParams.Q)));
String value = solrParams.get(AnalysisParams.FIELD_VALUE);
Iterable<ContentStream> streams = req.getContentStreams();
if (streams != null) {
// NOTE: Only the first content stream is currently processed
for (ContentStream stream : streams) {
Reader reader = null;
try {
reader = stream.getReader();
value = IOUtils.toString(reader);
} catch (IOException e) {
// do nothing, leave value set to the request parameter
}
finally {
IOUtils.closeQuietly(reader);
}
break;
}
}
analysisRequest.setFieldValue(value);
analysisRequest.setShowMatch(solrParams.getBool(AnalysisParams.SHOW_MATCH, false));
return analysisRequest;
}
/**
* Handles the resolved analysis request and returns the analysis breakdown response as a named list.
*
* @param request The request to handle.
* @param schema The index schema.
*
* @return The analysis breakdown as a named list.
*/
protected NamedList<NamedList> handleAnalysisRequest(FieldAnalysisRequest request, IndexSchema schema) {
NamedList<NamedList> analysisResults = new SimpleOrderedMap<NamedList>();
NamedList<NamedList> fieldTypeAnalysisResults = new SimpleOrderedMap<NamedList>();
if (request.getFieldTypes() != null) {
for (String fieldTypeName : request.getFieldTypes()) {
FieldType fieldType = schema.getFieldTypes().get(fieldTypeName);
fieldTypeAnalysisResults.add(fieldTypeName, analyzeValues(request, fieldType, null));
}
}
NamedList<NamedList> fieldNameAnalysisResults = new SimpleOrderedMap<NamedList>();
if (request.getFieldNames() != null) {
for (String fieldName : request.getFieldNames()) {
FieldType fieldType = schema.getFieldType(fieldName);
fieldNameAnalysisResults.add(fieldName, analyzeValues(request, fieldType, fieldName));
}
}
analysisResults.add("field_types", fieldTypeAnalysisResults);
analysisResults.add("field_names", fieldNameAnalysisResults);
return analysisResults;
}
/**
* Analyzes the index value (if it exists) and the query value (if it exists) in the given AnalysisRequest, using
* the Analyzers of the given field type.
*
* @param analysisRequest AnalysisRequest from where the index and query values will be taken
* @param fieldType Type of field whose analyzers will be used
* @param fieldName Name of the field to be analyzed. Can be {@code null}
*
* @return NamedList containing the tokens produced by the analyzers of the given field, separated into an index and
* a query group
*/
private NamedList<NamedList> analyzeValues(FieldAnalysisRequest analysisRequest, FieldType fieldType, String fieldName) {
final String queryValue = analysisRequest.getQuery();
final Set<String> termsToMatch = (queryValue != null && analysisRequest.isShowMatch())
? getQueryTokenSet(queryValue, fieldType.getQueryAnalyzer())
: Collections.<String>emptySet();
NamedList<NamedList> analyzeResults = new SimpleOrderedMap<NamedList>();
if (analysisRequest.getFieldValue() != null) {
AnalysisContext context = new AnalysisContext(fieldName, fieldType, fieldType.getAnalyzer(), termsToMatch);
NamedList analyzedTokens = analyzeValue(analysisRequest.getFieldValue(), context);
analyzeResults.add("index", analyzedTokens);
}
if (analysisRequest.getQuery() != null) {
AnalysisContext context = new AnalysisContext(fieldName, fieldType, fieldType.getQueryAnalyzer());
NamedList analyzedTokens = analyzeValue(analysisRequest.getQuery(), context);
analyzeResults.add("query", analyzedTokens);
}
return analyzeResults;
}
}