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

add missing eol-style 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@930161 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2010-04-02 04:36:13 +00:00
parent 868b997211
commit 88fc2e2f56
44 changed files with 3903 additions and 3903 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
solr/client/javascript/README.txt
View File

@ -1,5 +1,5 @@
For a Solr JavaScript Client, see:
http://evolvingweb.github.com/ajax-solr/
For information on (now deprecated) SorlJS, see:
For a Solr JavaScript Client, see:
http://evolvingweb.github.com/ajax-solr/
For information on (now deprecated) SorlJS, see:
http://wiki.apache.org/solr/SolrJS

268
solr/client/ruby/flare/vendor/plugins/engines/lib/engines/deprecated_config_support.rb vendored
View File

@ -1,135 +1,135 @@
# This file contains support for the now-deprecated +config+ method that the engines
# plugin provided before version 1.2. Instead of using this, plugin authors are
# now encouraged to create their own Module configuration mechanisms; the
# +mattr_accessor+ mechanism provided by ActiveSupport is ideal for this:
#
# module MyPlugin
# mattr_accessor :config_value
# self.config_value = "default"
# end
#
# == Using the deprecated config method
#
# If you require the config method to be present, change your <tt>environment.rb</tt>
# file such that the very top of the file looks like this:
#
# require File.join(File.dirname(__FILE__), 'boot')
# require File.join(RAILS_ROOT, "vendor", "plugins", "engines",
# "lib", "engines", "deprecated_config_support")
#
# Adds the +config+ and +default_constant+ methods to Module.
#
# *IMPORTANT NOTE* - these methods are deprecated. Only use them when you have no
# other choice. See link:files/lib/engines/deprecated_config_support_rb.html for more
# information.
class Module
# Defines a constant within a module/class ONLY if that constant does
# not already exist.
#
# This can be used to implement defaults in plugins/engines/libraries, e.g.
# if a plugin module exists:
# module MyPlugin
# default_constant :MyDefault, "the_default_value"
# end
#
# then developers can override this default by defining that constant at
# some point *before* the module/plugin gets loaded (such as environment.rb)
def default_constant(name, value)
if !(name.is_a?(String) or name.is_a?(Symbol))
raise "Cannot use a #{name.class.name} ['#{name}'] object as a constant name"
end
if !self.const_defined?(name)
self.class_eval("#{name} = #{value.inspect}")
end
end
# A mechanism for defining configuration of Modules. With this
# mechanism, default values for configuration can be provided within shareable
# code, and the end user can customise the configuration without having to
# provide all values.
#
# Example:
#
# module MyModule
# config :param_one, "some value"
# config :param_two, 12345
# end
#
# Those values can now be accessed by the following method
#
# MyModule.config :param_one
# => "some value"
# MyModule.config :param_two
# => 12345
#
# ... or, if you have overrriden the method 'config'
#
# MyModule::CONFIG[:param_one]
# => "some value"
# MyModule::CONFIG[:param_two]
# => 12345
#
# Once a value is stored in the configuration, it will not be altered
# by subsequent assignments, unless a special flag is given:
#
# (later on in your code, most likely in another file)
# module MyModule
# config :param_one, "another value"
# config :param_two, 98765, :force
# end
#
# The configuration is now:
#
# MyModule.config :param_one
# => "some value" # not changed
# MyModule.config :param_two
# => 98765
#
# Configuration values can also be given as a Hash:
#
# MyModule.config :param1 => 'value1', :param2 => 'value2'
#
# Setting of these values can also be forced:
#
# MyModule.config :param1 => 'value3', :param2 => 'value4', :force => true
#
# A value of anything other than false or nil given for the :force key will
# result in the new values *always* being set.
def config(*args)
raise "config expects at least one argument" if args.empty?
# extract the arguments
if args[0].is_a?(Hash)
override = args[0][:force]
args[0].delete(:force)
args[0].each { |key, value| _handle_config(key, value, override)}
else
_handle_config(*args)
end
end
private
# Actually set the config values
def _handle_config(name, value=nil, override=false)
if !self.const_defined?("CONFIG")
self.class_eval("CONFIG = {}")
end
if value != nil
if override or self::CONFIG[name] == nil
self::CONFIG[name] = value
end
else
# if we pass an array of config keys to config(),
# get the array of values back
if name.is_a? Array
name.map { |c| self::CONFIG[c] }
else
self::CONFIG[name]
end
end
end
# This file contains support for the now-deprecated +config+ method that the engines
# plugin provided before version 1.2. Instead of using this, plugin authors are
# now encouraged to create their own Module configuration mechanisms; the
# +mattr_accessor+ mechanism provided by ActiveSupport is ideal for this:
#
# module MyPlugin
# mattr_accessor :config_value
# self.config_value = "default"
# end
#
# == Using the deprecated config method
#
# If you require the config method to be present, change your <tt>environment.rb</tt>
# file such that the very top of the file looks like this:
#
# require File.join(File.dirname(__FILE__), 'boot')
# require File.join(RAILS_ROOT, "vendor", "plugins", "engines",
# "lib", "engines", "deprecated_config_support")
#
# Adds the +config+ and +default_constant+ methods to Module.
#
# *IMPORTANT NOTE* - these methods are deprecated. Only use them when you have no
# other choice. See link:files/lib/engines/deprecated_config_support_rb.html for more
# information.
class Module
# Defines a constant within a module/class ONLY if that constant does
# not already exist.
#
# This can be used to implement defaults in plugins/engines/libraries, e.g.
# if a plugin module exists:
# module MyPlugin
# default_constant :MyDefault, "the_default_value"
# end
#
# then developers can override this default by defining that constant at
# some point *before* the module/plugin gets loaded (such as environment.rb)
def default_constant(name, value)
if !(name.is_a?(String) or name.is_a?(Symbol))
raise "Cannot use a #{name.class.name} ['#{name}'] object as a constant name"
end
if !self.const_defined?(name)
self.class_eval("#{name} = #{value.inspect}")
end
end
# A mechanism for defining configuration of Modules. With this
# mechanism, default values for configuration can be provided within shareable
# code, and the end user can customise the configuration without having to
# provide all values.
#
# Example:
#
# module MyModule
# config :param_one, "some value"
# config :param_two, 12345
# end
#
# Those values can now be accessed by the following method
#
# MyModule.config :param_one
# => "some value"
# MyModule.config :param_two
# => 12345
#
# ... or, if you have overrriden the method 'config'
#
# MyModule::CONFIG[:param_one]
# => "some value"
# MyModule::CONFIG[:param_two]
# => 12345
#
# Once a value is stored in the configuration, it will not be altered
# by subsequent assignments, unless a special flag is given:
#
# (later on in your code, most likely in another file)
# module MyModule
# config :param_one, "another value"
# config :param_two, 98765, :force
# end
#
# The configuration is now:
#
# MyModule.config :param_one
# => "some value" # not changed
# MyModule.config :param_two
# => 98765
#
# Configuration values can also be given as a Hash:
#
# MyModule.config :param1 => 'value1', :param2 => 'value2'
#
# Setting of these values can also be forced:
#
# MyModule.config :param1 => 'value3', :param2 => 'value4', :force => true
#
# A value of anything other than false or nil given for the :force key will
# result in the new values *always* being set.
def config(*args)
raise "config expects at least one argument" if args.empty?
# extract the arguments
if args[0].is_a?(Hash)
override = args[0][:force]
args[0].delete(:force)
args[0].each { |key, value| _handle_config(key, value, override)}
else
_handle_config(*args)
end
end
private
# Actually set the config values
def _handle_config(name, value=nil, override=false)
if !self.const_defined?("CONFIG")
self.class_eval("CONFIG = {}")
end
if value != nil
if override or self::CONFIG[name] == nil
self::CONFIG[name] = value
end
else
# if we pass an array of config keys to config(),
# get the array of values back
if name.is_a? Array
name.map { |c| self::CONFIG[c] }
else
self::CONFIG[name]
end
end
end
end

48
solr/client/ruby/solr-ruby/solr/conf/scripts.conf
View File

@ -1,24 +1,24 @@
# 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.
user=
solr_hostname=localhost
solr_port=8983
rsyncd_port=18983
data_dir=
webapp_name=solr
master_host=
master_data_dir=
master_status_dir=
# 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.
user=
solr_hostname=localhost
solr_port=8983
rsyncd_port=18983
data_dir=
webapp_name=solr
master_host=
master_data_dir=
master_status_dir=

48
solr/client/ruby/solr-ruby/test/conf/scripts.conf
View File

@ -1,24 +1,24 @@
# 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.
user=
solr_hostname=localhost
solr_port=8983
rsyncd_port=18983
data_dir=
webapp_name=solr
master_host=
master_data_dir=
master_status_dir=
# 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.
user=
solr_hostname=localhost
solr_port=8983
rsyncd_port=18983
data_dir=
webapp_name=solr
master_host=
master_data_dir=
master_status_dir=

386
solr/contrib/dataimporthandler/src/extras/main/java/org/apache/solr/handler/dataimport/TikaEntityProcessor.java
View File

@ -1,193 +1,193 @@
/**
* 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.dataimport;
import org.apache.commons.io.IOUtils;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.wrapAndThrow;
import static org.apache.solr.handler.dataimport.DataImporter.COLUMN;
import static org.apache.solr.handler.dataimport.XPathEntityProcessor.URL;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ContentHandlerDecorator;
import org.apache.tika.sax.XHTMLContentHandler;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.sax.SAXTransformerFactory;
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamResult;
import java.io.File;
import java.io.InputStream;
import java.io.StringWriter;
import java.io.Writer;
import java.util.HashMap;
import java.util.Map;
/**
* <p>An implementation of EntityProcessor which reads data from rich docs using Tika
*
* @version $Id$
* @since solr 1.5
*/
public class TikaEntityProcessor extends EntityProcessorBase {
private TikaConfig tikaConfig;
private static final Logger LOG = LoggerFactory.getLogger(TikaEntityProcessor.class);
private String format = "text";
private boolean done = false;
private String parser;
static final String AUTO_PARSER = "org.apache.tika.parser.AutoDetectParser";
@Override
protected void firstInit(Context context) {
String tikaConfigFile = context.getResolvedEntityAttribute("tikaConfig");
if (tikaConfigFile == null) {
tikaConfig = TikaConfig.getDefaultConfig();
} else {
File configFile = new File(tikaConfigFile);
if (!configFile.isAbsolute()) {
configFile = new File(context.getSolrCore().getResourceLoader().getConfigDir(), tikaConfigFile);
}
try {
tikaConfig = new TikaConfig(configFile);
} catch (Exception e) {
wrapAndThrow (SEVERE, e,"Unable to load Tika Config");
}
}
format = context.getResolvedEntityAttribute("format");
if(format == null)
format = "text";
if (!"html".equals(format) && !"xml".equals(format) && !"text".equals(format)&& !"none".equals(format) )
throw new DataImportHandlerException(SEVERE, "'format' can be one of text|html|xml|none");
parser = context.getResolvedEntityAttribute("parser");
if(parser == null) {
parser = AUTO_PARSER;
}
done = false;
}
public Map<String, Object> nextRow() {
if(done) return null;
Map<String, Object> row = new HashMap<String, Object>();
DataSource<InputStream> dataSource = context.getDataSource();
InputStream is = dataSource.getData(context.getResolvedEntityAttribute(URL));
ContentHandler contentHandler = null;
Metadata metadata = new Metadata();
StringWriter sw = new StringWriter();
try {
if ("html".equals(format)) {
contentHandler = getHtmlHandler(sw);
} else if ("xml".equals(format)) {
contentHandler = getXmlContentHandler(sw);
} else if ("text".equals(format)) {
contentHandler = getTextContentHandler(sw);
} else if("none".equals(format)){
contentHandler = new DefaultHandler();
}
} catch (TransformerConfigurationException e) {
wrapAndThrow(SEVERE, e, "Unable to create content handler");
}
Parser tikaParser = null;
if(parser.equals(AUTO_PARSER)){
AutoDetectParser parser = new AutoDetectParser();
parser.setConfig(tikaConfig);
tikaParser = parser;
} else {
tikaParser = (Parser) context.getSolrCore().getResourceLoader().newInstance(parser);
}
try {
tikaParser.parse(is, contentHandler, metadata , new ParseContext());
} catch (Exception e) {
wrapAndThrow(SEVERE, e, "Unable to read content");
}
IOUtils.closeQuietly(is);
for (Map<String, String> field : context.getAllEntityFields()) {
if (!"true".equals(field.get("meta"))) continue;
String col = field.get(COLUMN);
String s = metadata.get(col);
if (s != null) row.put(col, s);
}
if(!"none".equals(format) ) row.put("text", sw.toString());
done = true;
return row;
}
private static ContentHandler getHtmlHandler(Writer writer)
throws TransformerConfigurationException {
SAXTransformerFactory factory = (SAXTransformerFactory)
SAXTransformerFactory.newInstance();
TransformerHandler handler = factory.newTransformerHandler();
handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
handler.setResult(new StreamResult(writer));
return new ContentHandlerDecorator(handler) {
@Override
public void startElement(
String uri, String localName, String name, Attributes atts)
throws SAXException {
if (XHTMLContentHandler.XHTML.equals(uri)) {
uri = null;
}
if (!"head".equals(localName)) {
super.startElement(uri, localName, name, atts);
}
}
@Override
public void endElement(String uri, String localName, String name)
throws SAXException {
if (XHTMLContentHandler.XHTML.equals(uri)) {
uri = null;
}
if (!"head".equals(localName)) {
super.endElement(uri, localName, name);
}
}
@Override
public void startPrefixMapping(String prefix, String uri) {/*no op*/ }
@Override
public void endPrefixMapping(String prefix) {/*no op*/ }
};
}
private static ContentHandler getTextContentHandler(Writer writer) {
return new BodyContentHandler(writer);
}
private static ContentHandler getXmlContentHandler(Writer writer)
throws TransformerConfigurationException {
SAXTransformerFactory factory = (SAXTransformerFactory)
SAXTransformerFactory.newInstance();
TransformerHandler handler = factory.newTransformerHandler();
handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml");
handler.setResult(new StreamResult(writer));
return handler;
}
}
/**
* 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.dataimport;
import org.apache.commons.io.IOUtils;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.wrapAndThrow;
import static org.apache.solr.handler.dataimport.DataImporter.COLUMN;
import static org.apache.solr.handler.dataimport.XPathEntityProcessor.URL;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;
import org.apache.tika.sax.ContentHandlerDecorator;
import org.apache.tika.sax.XHTMLContentHandler;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.sax.SAXTransformerFactory;
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamResult;
import java.io.File;
import java.io.InputStream;
import java.io.StringWriter;
import java.io.Writer;
import java.util.HashMap;
import java.util.Map;
/**
* <p>An implementation of EntityProcessor which reads data from rich docs using Tika
*
* @version $Id$
* @since solr 1.5
*/
public class TikaEntityProcessor extends EntityProcessorBase {
private TikaConfig tikaConfig;
private static final Logger LOG = LoggerFactory.getLogger(TikaEntityProcessor.class);
private String format = "text";
private boolean done = false;
private String parser;
static final String AUTO_PARSER = "org.apache.tika.parser.AutoDetectParser";
@Override
protected void firstInit(Context context) {
String tikaConfigFile = context.getResolvedEntityAttribute("tikaConfig");
if (tikaConfigFile == null) {
tikaConfig = TikaConfig.getDefaultConfig();
} else {
File configFile = new File(tikaConfigFile);
if (!configFile.isAbsolute()) {
configFile = new File(context.getSolrCore().getResourceLoader().getConfigDir(), tikaConfigFile);
}
try {
tikaConfig = new TikaConfig(configFile);
} catch (Exception e) {
wrapAndThrow (SEVERE, e,"Unable to load Tika Config");
}
}
format = context.getResolvedEntityAttribute("format");
if(format == null)
format = "text";
if (!"html".equals(format) && !"xml".equals(format) && !"text".equals(format)&& !"none".equals(format) )
throw new DataImportHandlerException(SEVERE, "'format' can be one of text|html|xml|none");
parser = context.getResolvedEntityAttribute("parser");
if(parser == null) {
parser = AUTO_PARSER;
}
done = false;
}
public Map<String, Object> nextRow() {
if(done) return null;
Map<String, Object> row = new HashMap<String, Object>();
DataSource<InputStream> dataSource = context.getDataSource();
InputStream is = dataSource.getData(context.getResolvedEntityAttribute(URL));
ContentHandler contentHandler = null;
Metadata metadata = new Metadata();
StringWriter sw = new StringWriter();
try {
if ("html".equals(format)) {
contentHandler = getHtmlHandler(sw);
} else if ("xml".equals(format)) {
contentHandler = getXmlContentHandler(sw);
} else if ("text".equals(format)) {
contentHandler = getTextContentHandler(sw);
} else if("none".equals(format)){
contentHandler = new DefaultHandler();
}
} catch (TransformerConfigurationException e) {
wrapAndThrow(SEVERE, e, "Unable to create content handler");
}
Parser tikaParser = null;
if(parser.equals(AUTO_PARSER)){
AutoDetectParser parser = new AutoDetectParser();
parser.setConfig(tikaConfig);
tikaParser = parser;
} else {
tikaParser = (Parser) context.getSolrCore().getResourceLoader().newInstance(parser);
}
try {
tikaParser.parse(is, contentHandler, metadata , new ParseContext());
} catch (Exception e) {
wrapAndThrow(SEVERE, e, "Unable to read content");
}
IOUtils.closeQuietly(is);
for (Map<String, String> field : context.getAllEntityFields()) {
if (!"true".equals(field.get("meta"))) continue;
String col = field.get(COLUMN);
String s = metadata.get(col);
if (s != null) row.put(col, s);
}
if(!"none".equals(format) ) row.put("text", sw.toString());
done = true;
return row;
}
private static ContentHandler getHtmlHandler(Writer writer)
throws TransformerConfigurationException {
SAXTransformerFactory factory = (SAXTransformerFactory)
SAXTransformerFactory.newInstance();
TransformerHandler handler = factory.newTransformerHandler();
handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
handler.setResult(new StreamResult(writer));
return new ContentHandlerDecorator(handler) {
@Override
public void startElement(
String uri, String localName, String name, Attributes atts)
throws SAXException {
if (XHTMLContentHandler.XHTML.equals(uri)) {
uri = null;
}
if (!"head".equals(localName)) {
super.startElement(uri, localName, name, atts);
}
}
@Override
public void endElement(String uri, String localName, String name)
throws SAXException {
if (XHTMLContentHandler.XHTML.equals(uri)) {
uri = null;
}
if (!"head".equals(localName)) {
super.endElement(uri, localName, name);
}
}
@Override
public void startPrefixMapping(String prefix, String uri) {/*no op*/ }
@Override
public void endPrefixMapping(String prefix) {/*no op*/ }
};
}
private static ContentHandler getTextContentHandler(Writer writer) {
return new BodyContentHandler(writer);
}
private static ContentHandler getXmlContentHandler(Writer writer)
throws TransformerConfigurationException {
SAXTransformerFactory factory = (SAXTransformerFactory)
SAXTransformerFactory.newInstance();
TransformerHandler handler = factory.newTransformerHandler();
handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml");
handler.setResult(new StreamResult(writer));
return handler;
}
}

122
solr/contrib/dataimporthandler/src/extras/test/java/org/apache/solr/handler/dataimport/TestTikaEntityProcessor.java
View File

@ -1,61 +1,61 @@
/**
* 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.dataimport;
import org.junit.After;
import org.junit.Before;
/**Testcase for TikaEntityProcessor
* @version $Id$
* @since solr 1.5
*/
public class TestTikaEntityProcessor extends AbstractDataImportHandlerTest {
@Before
public void setUp() throws Exception {
super.setUp();
}
@After
public void tearDown() throws Exception {
super.tearDown();
}
public String getSchemaFile() {
return "dataimport-schema-no-unique-key.xml";
}
public String getSolrConfigFile() {
return "dataimport-solrconfig.xml";
}
public void testIndexingWithTikaEntityProcessor() throws Exception {
String conf =
"<dataConfig>" +
" <dataSource type=\"BinFileDataSource\"/>" +
" <document>" +
" <entity processor=\"TikaEntityProcessor\" url=\"../../../../../extraction/src/test/resources/solr-word.pdf\" >" +
" <field column=\"Author\" meta=\"true\" name=\"author\"/>" +
" <field column=\"title\" meta=\"true\" name=\"docTitle\"/>" +
" <field column=\"text\"/>" +
" </entity>" +
" </document>" +
"</dataConfig>";
super.runFullImport(conf);
assertQ(req("*:*"), "//*[@numFound='1']");
}
}
/**
* 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.dataimport;
import org.junit.After;
import org.junit.Before;
/**Testcase for TikaEntityProcessor
* @version $Id$
* @since solr 1.5
*/
public class TestTikaEntityProcessor extends AbstractDataImportHandlerTest {
@Before
public void setUp() throws Exception {
super.setUp();
}
@After
public void tearDown() throws Exception {
super.tearDown();
}
public String getSchemaFile() {
return "dataimport-schema-no-unique-key.xml";
}
public String getSolrConfigFile() {
return "dataimport-solrconfig.xml";
}
public void testIndexingWithTikaEntityProcessor() throws Exception {
String conf =
"<dataConfig>" +
" <dataSource type=\"BinFileDataSource\"/>" +
" <document>" +
" <entity processor=\"TikaEntityProcessor\" url=\"../../../../../extraction/src/test/resources/solr-word.pdf\" >" +
" <field column=\"Author\" meta=\"true\" name=\"author\"/>" +
" <field column=\"title\" meta=\"true\" name=\"docTitle\"/>" +
" <field column=\"text\"/>" +
" </entity>" +
" </document>" +
"</dataConfig>";
super.runFullImport(conf);
assertQ(req("*:*"), "//*[@numFound='1']");
}
}

410
solr/contrib/dataimporthandler/src/extras/test/resources/solr/conf/dataimport-schema-no-unique-key.xml
View File

@ -1,205 +1,205 @@
<?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.
-->
<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
-->
<schema name="test" version="1.2">
<!-- attribute "name" is the name of this schema and is only used for display purposes.
Applications should change this to reflect the nature of the search collection.
version="1.1" is Solr's version number for the schema syntax and semantics. It should
not normally be changed by applications.
1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default -->
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldType.
Class names starting with "solr" refer to java classes in the
org.apache.solr.analysis package.
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
- StrField and TextField support an optional compressThreshold which
limits compression (if enabled in the derived fields) to values which
exceed a certain size (in characters).
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as strings.
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!-- numeric field types that store and index the text
value verbatim (and hence don't support range queries, since the
lexicographic ordering isn't equal to the numeric ordering) -->
<fieldType name="integer" class="solr.IntField" omitNorms="true"/>
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
<!-- Numeric field types that manipulate the value into
a string value that isn't human-readable in its internal form,
but with a lexicographic ordering the same as the numeric ordering,
so that range queries work correctly. -->
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
-->
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate psuedo-random orderings of your docs for sorting
purposes. The ordering is generated based on the field name
and the version of the index, As long as the index version
remains unchanged, and the same field name is reused,
the ordering of the docs will be consistent.
If you want differend psuedo-random orderings of documents,
for the same version of the index, use a dynamicField and
change the name
-->
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
WordDelim parts) are removed.
-->
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed, any data added to
them will be ignored outright
-->
<fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
</types>
<fields>
<field name="title" type="string" indexed="true" stored="true"/>
<field name="author" type="string" indexed="true" stored="true" />
<field name="text" type="text" indexed="true" stored="true" />
</fields>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
</schema>
<?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.
-->
<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
-->
<schema name="test" version="1.2">
<!-- attribute "name" is the name of this schema and is only used for display purposes.
Applications should change this to reflect the nature of the search collection.
version="1.1" is Solr's version number for the schema syntax and semantics. It should
not normally be changed by applications.
1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default -->
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldType.
Class names starting with "solr" refer to java classes in the
org.apache.solr.analysis package.
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
- StrField and TextField support an optional compressThreshold which
limits compression (if enabled in the derived fields) to values which
exceed a certain size (in characters).
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as strings.
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!-- numeric field types that store and index the text
value verbatim (and hence don't support range queries, since the
lexicographic ordering isn't equal to the numeric ordering) -->
<fieldType name="integer" class="solr.IntField" omitNorms="true"/>
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
<!-- Numeric field types that manipulate the value into
a string value that isn't human-readable in its internal form,
but with a lexicographic ordering the same as the numeric ordering,
so that range queries work correctly. -->
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
-->
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate psuedo-random orderings of your docs for sorting
purposes. The ordering is generated based on the field name
and the version of the index, As long as the index version
remains unchanged, and the same field name is reused,
the ordering of the docs will be consistent.
If you want differend psuedo-random orderings of documents,
for the same version of the index, use a dynamicField and
change the name
-->
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
WordDelim parts) are removed.
-->
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed, any data added to
them will be ignored outright
-->
<fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
</types>
<fields>
<field name="title" type="string" indexed="true" stored="true"/>
<field name="author" type="string" indexed="true" stored="true" />
<field name="text" type="text" indexed="true" stored="true" />
</fields>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
</schema>

136
solr/contrib/dataimporthandler/src/main/java/org/apache/solr/handler/dataimport/BinContentStreamDataSource.java
View File

@ -1,68 +1,68 @@
/**
* 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.dataimport;
import org.apache.solr.common.util.ContentStream;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
import java.io.InputStream;
import java.io.IOException;
import java.util.Properties;
/**
* <p> A data source implementation which can be used to read binary stream from content streams. </p> <p/> <p> Refer to <a
* href="http://wiki.apache.org/solr/DataImportHandler">http://wiki.apache.org/solr/DataImportHandler</a> for more
* details. </p>
* <p/>
* <b>This API is experimental and may change in the future.</b>
*
* @version $Id$
* @since solr 1.5
*/
public class BinContentStreamDataSource extends DataSource<InputStream> {
private ContextImpl context;
private ContentStream contentStream;
private InputStream in;
public void init(Context context, Properties initProps) {
this.context = (ContextImpl) context;
}
public InputStream getData(String query) {
contentStream = context.getDocBuilder().requestParameters.contentStream;
if (contentStream == null)
throw new DataImportHandlerException(SEVERE, "No stream available. The request has no body");
try {
return in = contentStream.getStream();
} catch (IOException e) {
DataImportHandlerException.wrapAndThrow(SEVERE, e);
return null;
}
}
public void close() {
if (contentStream != null) {
try {
if (in == null) in = contentStream.getStream();
in.close();
} catch (IOException e) {
/*no op*/
}
}
}
}
/**
* 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.dataimport;
import org.apache.solr.common.util.ContentStream;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
import java.io.InputStream;
import java.io.IOException;
import java.util.Properties;
/**
* <p> A data source implementation which can be used to read binary stream from content streams. </p> <p/> <p> Refer to <a
* href="http://wiki.apache.org/solr/DataImportHandler">http://wiki.apache.org/solr/DataImportHandler</a> for more
* details. </p>
* <p/>
* <b>This API is experimental and may change in the future.</b>
*
* @version $Id$
* @since solr 1.5
*/
public class BinContentStreamDataSource extends DataSource<InputStream> {
private ContextImpl context;
private ContentStream contentStream;
private InputStream in;
public void init(Context context, Properties initProps) {
this.context = (ContextImpl) context;
}
public InputStream getData(String query) {
contentStream = context.getDocBuilder().requestParameters.contentStream;
if (contentStream == null)
throw new DataImportHandlerException(SEVERE, "No stream available. The request has no body");
try {
return in = contentStream.getStream();
} catch (IOException e) {
DataImportHandlerException.wrapAndThrow(SEVERE, e);
return null;
}
}
public void close() {
if (contentStream != null) {
try {
if (in == null) in = contentStream.getStream();
in.close();
} catch (IOException e) {
/*no op*/
}
}
}
}

126
solr/contrib/dataimporthandler/src/main/java/org/apache/solr/handler/dataimport/BinFileDataSource.java
View File

@ -1,63 +1,63 @@
/**
* 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.dataimport;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.wrapAndThrow;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
import java.io.InputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.util.Properties;
/**
* <p>
* A DataSource which reads from local files
* </p>
* <p/>
* <p>
* Refer to <a
* href="http://wiki.apache.org/solr/DataImportHandler">http://wiki.apache.org/solr/DataImportHandler</a>
* for more details.
* </p>
* <p/>
* <b>This API is experimental and may change in the future.</b>
*
* @version $Id$
* @since solr 1.5
*/
public class BinFileDataSource extends DataSource<InputStream>{
protected String basePath;
public void init(Context context, Properties initProps) {
basePath = initProps.getProperty(FileDataSource.BASE_PATH);
}
public InputStream getData(String query) {
File f = FileDataSource.getFile(basePath,query);
try {
return new FileInputStream(f);
} catch (FileNotFoundException e) {
wrapAndThrow(SEVERE,e,"Unable to open file "+f.getAbsolutePath());
return null;
}
}
public void close() {
}
}
/**
* 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.dataimport;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.wrapAndThrow;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
import java.io.InputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.util.Properties;
/**
* <p>
* A DataSource which reads from local files
* </p>
* <p/>
* <p>
* Refer to <a
* href="http://wiki.apache.org/solr/DataImportHandler">http://wiki.apache.org/solr/DataImportHandler</a>
* for more details.
* </p>
* <p/>
* <b>This API is experimental and may change in the future.</b>
*
* @version $Id$
* @since solr 1.5
*/
public class BinFileDataSource extends DataSource<InputStream>{
protected String basePath;
public void init(Context context, Properties initProps) {
basePath = initProps.getProperty(FileDataSource.BASE_PATH);
}
public InputStream getData(String query) {
File f = FileDataSource.getFile(basePath,query);
try {
return new FileInputStream(f);
} catch (FileNotFoundException e) {
wrapAndThrow(SEVERE,e,"Unable to open file "+f.getAbsolutePath());
return null;
}
}
public void close() {
}
}

202
solr/contrib/dataimporthandler/src/main/java/org/apache/solr/handler/dataimport/BinURLDataSource.java
View File

@ -1,101 +1,101 @@
/**
* 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.dataimport;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.*;
import static org.apache.solr.handler.dataimport.URLDataSource.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.Properties;
/**
* <p> A data source implementation which can be used to read binary streams using HTTP. </p> <p/> <p> Refer to <a
* href="http://wiki.apache.org/solr/DataImportHandler">http://wiki.apache.org/solr/DataImportHandler</a> for more
* details. </p>
* <p/>
* <b>This API is experimental and may change in the future.</b>
*
* @version $Id$
* @since solr 1.5
*/
public class BinURLDataSource extends DataSource<InputStream>{
private static final Logger LOG = LoggerFactory.getLogger(BinURLDataSource.class);
private String baseUrl;
private int connectionTimeout = CONNECTION_TIMEOUT;
private int readTimeout = READ_TIMEOUT;
private Context context;
private Properties initProps;
public BinURLDataSource() { }
public void init(Context context, Properties initProps) {
this.context = context;
this.initProps = initProps;
baseUrl = getInitPropWithReplacements(BASE_URL);
String cTimeout = getInitPropWithReplacements(CONNECTION_TIMEOUT_FIELD_NAME);
String rTimeout = getInitPropWithReplacements(READ_TIMEOUT_FIELD_NAME);
if (cTimeout != null) {
try {
connectionTimeout = Integer.parseInt(cTimeout);
} catch (NumberFormatException e) {
LOG.warn("Invalid connection timeout: " + cTimeout);
}
}
if (rTimeout != null) {
try {
readTimeout = Integer.parseInt(rTimeout);
} catch (NumberFormatException e) {
LOG.warn("Invalid read timeout: " + rTimeout);
}
}
}
public InputStream getData(String query) {
URL url = null;
try {
if (URIMETHOD.matcher(query).find()) url = new URL(query);
else url = new URL(baseUrl + query);
LOG.debug("Accessing URL: " + url.toString());
URLConnection conn = url.openConnection();
conn.setConnectTimeout(connectionTimeout);
conn.setReadTimeout(readTimeout);
return conn.getInputStream();
} catch (Exception e) {
LOG.error("Exception thrown while getting data", e);
wrapAndThrow (SEVERE, e, "Exception in invoking url " + url);
return null;//unreachable
}
}
public void close() { }
private String getInitPropWithReplacements(String propertyName) {
final String expr = initProps.getProperty(propertyName);
if (expr == null) {
return null;
}
return context.replaceTokens(expr);
}
}
/**
* 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.dataimport;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.*;
import static org.apache.solr.handler.dataimport.URLDataSource.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.Properties;
/**
* <p> A data source implementation which can be used to read binary streams using HTTP. </p> <p/> <p> Refer to <a
* href="http://wiki.apache.org/solr/DataImportHandler">http://wiki.apache.org/solr/DataImportHandler</a> for more
* details. </p>
* <p/>
* <b>This API is experimental and may change in the future.</b>
*
* @version $Id$
* @since solr 1.5
*/
public class BinURLDataSource extends DataSource<InputStream>{
private static final Logger LOG = LoggerFactory.getLogger(BinURLDataSource.class);
private String baseUrl;
private int connectionTimeout = CONNECTION_TIMEOUT;
private int readTimeout = READ_TIMEOUT;
private Context context;
private Properties initProps;
public BinURLDataSource() { }
public void init(Context context, Properties initProps) {
this.context = context;
this.initProps = initProps;
baseUrl = getInitPropWithReplacements(BASE_URL);
String cTimeout = getInitPropWithReplacements(CONNECTION_TIMEOUT_FIELD_NAME);
String rTimeout = getInitPropWithReplacements(READ_TIMEOUT_FIELD_NAME);
if (cTimeout != null) {
try {
connectionTimeout = Integer.parseInt(cTimeout);
} catch (NumberFormatException e) {
LOG.warn("Invalid connection timeout: " + cTimeout);
}
}
if (rTimeout != null) {
try {
readTimeout = Integer.parseInt(rTimeout);
} catch (NumberFormatException e) {
LOG.warn("Invalid read timeout: " + rTimeout);
}
}
}
public InputStream getData(String query) {
URL url = null;
try {
if (URIMETHOD.matcher(query).find()) url = new URL(query);
else url = new URL(baseUrl + query);
LOG.debug("Accessing URL: " + url.toString());
URLConnection conn = url.openConnection();
conn.setConnectTimeout(connectionTimeout);
conn.setReadTimeout(readTimeout);
return conn.getInputStream();
} catch (Exception e) {
LOG.error("Exception thrown while getting data", e);
wrapAndThrow (SEVERE, e, "Exception in invoking url " + url);
return null;//unreachable
}
}
public void close() { }
private String getInitPropWithReplacements(String propertyName) {
final String expr = initProps.getProperty(propertyName);
if (expr == null) {
return null;
}
return context.replaceTokens(expr);
}
}

190
solr/contrib/dataimporthandler/src/main/java/org/apache/solr/handler/dataimport/FieldStreamDataSource.java
View File

@ -1,95 +1,95 @@
/**
* 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.dataimport;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.lang.reflect.Method;
import java.lang.reflect.Modifier;
import java.sql.Blob;
import java.util.Properties;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
/**
* This can be useful for users who have a DB field containing BLOBs which may be Rich documents
* <p/>
* The datasouce may be configured as follows
* <p/>
* <datasource name="f1" type="FieldStreamDataSource" />
* <p/>
* The enity which uses this datasource must keep and attribute dataField
* <p/>
* The fieldname must be resolvable from VariableResolver
* <p/>
* This may be used with any EntityProcessor which uses a DataSource<InputStream> eg:TikaEntityProcessor
* <p/>
*
* @version $Id$
* @since 1.5
*/
public class FieldStreamDataSource extends DataSource<InputStream> {
private static final Logger LOG = LoggerFactory.getLogger(FieldReaderDataSource.class);
protected VariableResolver vr;
protected String dataField;
private EntityProcessorWrapper wrapper;
public void init(Context context, Properties initProps) {
dataField = context.getEntityAttribute("dataField");
wrapper = (EntityProcessorWrapper) context.getEntityProcessor();
/*no op*/
}
public InputStream getData(String query) {
Object o = wrapper.getVariableResolver().resolve(dataField);
if (o == null) {
throw new DataImportHandlerException(SEVERE, "No field available for name : " + dataField);
}
if (o instanceof Blob) {
Blob blob = (Blob) o;
try {
//Most of the JDBC drivers have getBinaryStream defined as public
// so let us just check it
Method m = blob.getClass().getDeclaredMethod("getBinaryStream");
if (Modifier.isPublic(m.getModifiers())) {
return (InputStream) m.invoke(blob);
} else {
// force invoke
m.setAccessible(true);
return (InputStream) m.invoke(blob);
}
} catch (Exception e) {
LOG.info("Unable to get data from BLOB");
return null;
}
} else if (o instanceof byte[]) {
byte[] bytes = (byte[]) o;
return new ByteArrayInputStream(bytes);
} else {
throw new RuntimeException("unsupported type : " + o.getClass());
}
}
public void close() {
}
}
/**
* 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.dataimport;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.lang.reflect.Method;
import java.lang.reflect.Modifier;
import java.sql.Blob;
import java.util.Properties;
import static org.apache.solr.handler.dataimport.DataImportHandlerException.SEVERE;
/**
* This can be useful for users who have a DB field containing BLOBs which may be Rich documents
* <p/>
* The datasouce may be configured as follows
* <p/>
* <datasource name="f1" type="FieldStreamDataSource" />
* <p/>
* The enity which uses this datasource must keep and attribute dataField
* <p/>
* The fieldname must be resolvable from VariableResolver
* <p/>
* This may be used with any EntityProcessor which uses a DataSource<InputStream> eg:TikaEntityProcessor
* <p/>
*
* @version $Id$
* @since 1.5
*/
public class FieldStreamDataSource extends DataSource<InputStream> {
private static final Logger LOG = LoggerFactory.getLogger(FieldReaderDataSource.class);
protected VariableResolver vr;
protected String dataField;
private EntityProcessorWrapper wrapper;
public void init(Context context, Properties initProps) {
dataField = context.getEntityAttribute("dataField");
wrapper = (EntityProcessorWrapper) context.getEntityProcessor();
/*no op*/
}
public InputStream getData(String query) {
Object o = wrapper.getVariableResolver().resolve(dataField);
if (o == null) {
throw new DataImportHandlerException(SEVERE, "No field available for name : " + dataField);
}
if (o instanceof Blob) {
Blob blob = (Blob) o;
try {
//Most of the JDBC drivers have getBinaryStream defined as public
// so let us just check it
Method m = blob.getClass().getDeclaredMethod("getBinaryStream");
if (Modifier.isPublic(m.getModifiers())) {
return (InputStream) m.invoke(blob);
} else {
// force invoke
m.setAccessible(true);
return (InputStream) m.invoke(blob);
}
} catch (Exception e) {
LOG.info("Unable to get data from BLOB");
return null;
}
} else if (o instanceof byte[]) {
byte[] bytes = (byte[]) o;
return new ByteArrayInputStream(bytes);
} else {
throw new RuntimeException("unsupported type : " + o.getClass());
}
}
public void close() {
}
}

410
solr/example/example-DIH/solr/tika/conf/schema.xml
View File

@ -1,205 +1,205 @@
<?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.
-->
<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
-->
<schema name="test" version="1.2">
<!-- attribute "name" is the name of this schema and is only used for display purposes.
Applications should change this to reflect the nature of the search collection.
version="1.1" is Solr's version number for the schema syntax and semantics. It should
not normally be changed by applications.
1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default -->
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldType.
Class names starting with "solr" refer to java classes in the
org.apache.solr.analysis package.
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
- StrField and TextField support an optional compressThreshold which
limits compression (if enabled in the derived fields) to values which
exceed a certain size (in characters).
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as strings.
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!-- numeric field types that store and index the text
value verbatim (and hence don't support range queries, since the
lexicographic ordering isn't equal to the numeric ordering) -->
<fieldType name="integer" class="solr.IntField" omitNorms="true"/>
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
<!-- Numeric field types that manipulate the value into
a string value that isn't human-readable in its internal form,
but with a lexicographic ordering the same as the numeric ordering,
so that range queries work correctly. -->
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
-->
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate psuedo-random orderings of your docs for sorting
purposes. The ordering is generated based on the field name
and the version of the index, As long as the index version
remains unchanged, and the same field name is reused,
the ordering of the docs will be consistent.
If you want differend psuedo-random orderings of documents,
for the same version of the index, use a dynamicField and
change the name
-->
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
WordDelim parts) are removed.
-->
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed, any data added to
them will be ignored outright
-->
<fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
</types>
<fields>
<field name="title" type="string" indexed="true" stored="true"/>
<field name="author" type="string" indexed="true" stored="true" />
<field name="text" type="text" indexed="true" stored="true" />
</fields>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
</schema>
<?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.
-->
<!--
This is the Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
-->
<schema name="test" version="1.2">
<!-- attribute "name" is the name of this schema and is only used for display purposes.
Applications should change this to reflect the nature of the search collection.
version="1.1" is Solr's version number for the schema syntax and semantics. It should
not normally be changed by applications.
1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default -->
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldType.
Class names starting with "solr" refer to java classes in the
org.apache.solr.analysis package.
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
- StrField and TextField support an optional compressThreshold which
limits compression (if enabled in the derived fields) to values which
exceed a certain size (in characters).
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as strings.
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!-- numeric field types that store and index the text
value verbatim (and hence don't support range queries, since the
lexicographic ordering isn't equal to the numeric ordering) -->
<fieldType name="integer" class="solr.IntField" omitNorms="true"/>
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
<!-- Numeric field types that manipulate the value into
a string value that isn't human-readable in its internal form,
but with a lexicographic ordering the same as the numeric ordering,
so that range queries work correctly. -->
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
-->
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate psuedo-random orderings of your docs for sorting
purposes. The ordering is generated based on the field name
and the version of the index, As long as the index version
remains unchanged, and the same field name is reused,
the ordering of the docs will be consistent.
If you want differend psuedo-random orderings of documents,
for the same version of the index, use a dynamicField and
change the name
-->
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
WordDelim parts) are removed.
-->
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed, any data added to
them will be ignored outright
-->
<fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
</types>
<fields>
<field name="title" type="string" indexed="true" stored="true"/>
<field name="author" type="string" indexed="true" stored="true" />
<field name="text" type="text" indexed="true" stored="true" />
</fields>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
</schema>

820
solr/example/example-DIH/solr/tika/conf/solrconfig.xml
View File

@ -1,410 +1,410 @@
<?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.
-->
<config>
<!-- Set this to 'false' if you want solr to continue working after it has
encountered an severe configuration error. In a production environment,
you may want solr to keep working even if one handler is mis-configured.
You may also set this to false using by setting the system property:
-Dsolr.abortOnConfigurationError=false
-->
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
<lib dir="../../../../contrib/extraction/lib" />
<lib dir="../../../../dist/" regex="apache-solr-dataimporthandler-extras-\d.*\.jar" />
<!-- Used to specify an alternate directory to hold all index data
other than the default ./data under the Solr home.
If replication is in use, this should match the replication configuration. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<indexDefaults>
<!-- Values here affect all index writers and act as a default unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!--
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<!-- Tell Lucene when to flush documents to disk.
Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!--
Expert: Turn on Lucene's auto commit capability.
TODO: Add recommendations on why you would want to do this.
NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
-->
<!--<luceneAutoCommit>false</luceneAutoCommit>-->
<!--
Expert:
The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
versions used LogDocMergePolicy.
LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when
to merge based on number of documents
Other implementations of MergePolicy must have a no-argument constructor
-->
<!--<mergePolicy>org.apache.lucene.index.LogByteSizeMergePolicy</mergePolicy>-->
<!--
Expert:
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>org.apache.lucene.index.ConcurrentMergeScheduler</mergeScheduler>-->
<!--
As long as Solr is the only process modifying your index, it is
safe to use Lucene's in process locking mechanism. But you may
specify one of the other Lucene LockFactory implementations in
the event that you have a custom situation.
none = NoLockFactory (typically only used with read only indexes)
single = SingleInstanceLockFactory (suggested)
native = NativeFSLockFactory
simple = SimpleFSLockFactory
('simple' is the default for backwards compatibility with Solr 1.2)
-->
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<!-- options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<ramBufferSizeMB>32</ramBufferSizeMB>
<mergeFactor>10</mergeFactor>
<!-- Deprecated -->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<!-- If true, unlock any held write or commit locks on startup.
This defeats the locking mechanism that allows multiple
processes to safely access a lucene index, and should be
used with care.
This is not needed if lock type is 'none' or 'single'
-->
<unlockOnStartup>false</unlockOnStartup>
</mainIndex>
<!-- the default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
<!-- 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)
-->
<!-- Limit the number of deletions Solr will buffer during doc updating.
Setting this lower can help bound memory use during indexing.
-->
<maxPendingDeletes>100000</maxPendingDeletes>
</updateHandler>
<query>
<!-- Maximum number of clauses in a boolean query... can affect
range or prefix queries that expand to big boolean
queries. An exception is thrown if exceeded. -->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- 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 (currently only LRUCache)
size - the maximum number of entries in the cache
initialSize - the initial capacity (number of entries) of
the cache. (seel java.util.HashMap)
autowarmCount - the number of entries to prepopulate from
and old cache.
-->
<filterCache
class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<!-- queryResultCache caches results of searches - ordered lists of
document ids (DocList) based on a query, a sort, and the range
of documents requested. -->
<queryResultCache
class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<!-- documentCache 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"/>
<!-- 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>
<!-- 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.search.CacheRegenerator if autowarming is desired. -->
<!--
<cache name="myUserCache"
class="solr.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="org.mycompany.mypackage.MyRegenerator"
/>
-->
<!-- An 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.
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<!-- 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>50</queryResultWindowSize>
<!-- Maximum number of documents to cache for any entry in the
queryResultCache. -->
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
<!-- This entry enables an int hash representation for filters (DocSets)
when the number of items in the set is less than maxSize. For smaller
sets, this representation is more memory efficient, more efficient to
iterate over, and faster to take intersections. -->
<HashDocSet maxSize="3000" loadFactor="0.75"/>
<!-- a newSearcher event is fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka registered). -->
<!-- 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="start">0</str> <str name="rows">10</str> </lst>
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
<lst><str name="q">static newSearcher warming query from solrconfig.xml</str></lst>
</arr>
</listener>
<!-- a firstSearcher event is fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain autowarming data from. -->
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
</arr>
</listener>
<!-- 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>
<!-- Maximum number of searchers that may be warming in the background
concurrently. An error is returned if this limit is exceeded. Recommend
1-2 for read-only slaves, higher for masters w/o cache warming. -->
<maxWarmingSearchers>4</maxWarmingSearchers>
</query>
<!--
Let the dispatch filter handler /select?qt=XXX
handleSelect=true will use consistent error handling for /select and /update
handleSelect=false will use solr1.1 style error formatting
-->
<requestDispatcher handleSelect="true" >
<!--Make sure your system has some authentication before enabling remote streaming! -->
<requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
<!-- Set HTTP caching related parameters (for proxy caches and clients).
To get the behaviour of Solr 1.2 (ie: no caching related headers)
use the never304="true" option and do not specify a value for
<cacheControl>
-->
<httpCaching never304="true">
<!--httpCaching lastModifiedFrom="openTime"
etagSeed="Solr"-->
<!-- lastModFrom="openTime" is the default, 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 corrispond 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
differnet 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.
-->
<!-- 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"
-->
<!-- <cacheControl>max-age=30, public</cacheControl> -->
</httpCaching>
</requestDispatcher>
<!-- requestHandler plugins... incoming queries will be dispatched to the
correct handler based on the path or the qt (query type) param.
Names starting with a '/' are accessed with the a path equal to the
registered name. Names without a leading '/' are accessed with:
http://host/app/select?qt=name
If no qt is defined, the requestHandler that declares default="true"
will be used.
-->
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true">
<!-- default values for query parameters -->
<lst name="defaults">
<str name="echoParams">explicit</str>
<!--
<int name="rows">10</int>
<str name="fl">*</str>
<str name="version">2.1</str>
-->
</lst>
</requestHandler>
<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
<lst name="defaults">
<str name="config">tika-data-config.xml</str>
</lst>
</requestHandler>
<!--
Search components are registered to SolrCore and used by Search Handlers
By default, the following components are avaliable:
<searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" />
<searchComponent name="facet" class="org.apache.solr.handler.component.FacetComponent" />
<searchComponent name="mlt" class="org.apache.solr.handler.component.MoreLikeThisComponent" />
<searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" />
<searchComponent name="debug" class="org.apache.solr.handler.component.DebugComponent" />
If you register a searchComponent to one of the standard names, that will be used instead.
-->
<requestHandler name="/search" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
</lst>
<!--
By default, this will register the following components:
<arr name="components">
<str>query</str>
<str>facet</str>
<str>mlt</str>
<str>highlight</str>
<str>debug</str>
</arr>
To insert handlers before or after the 'standard' components, use:
<arr name="first-components">
<str>first</str>
</arr>
<arr name="last-components">
<str>last</str>
</arr>
-->
</requestHandler>
<!-- Update request handler.
Note: Since solr1.1 requestHandlers requires a valid content type header if posted in
the body. For example, curl now requires: -H 'Content-type:text/xml; charset=utf-8'
The response format differs from solr1.1 formatting and returns a standard error code.
To enable solr1.1 behavior, remove the /update handler or change its path
"update.processor.class" is the class name for the UpdateRequestProcessor. It is initalized
only once. This can not be changed for each request.
-->
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" >
<!--
<str name="update.processor.class">org.apache.solr.handler.UpdateRequestProcessor</str>
-->
</requestHandler>
<!-- config for the admin interface -->
<admin>
<defaultQuery>*:*</defaultQuery>
<!-- configure a healthcheck file for servers behind a loadbalancer
<healthcheck type="file">server-enabled</healthcheck>
-->
</admin>
</config>
<?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.
-->
<config>
<!-- Set this to 'false' if you want solr to continue working after it has
encountered an severe configuration error. In a production environment,
you may want solr to keep working even if one handler is mis-configured.
You may also set this to false using by setting the system property:
-Dsolr.abortOnConfigurationError=false
-->
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
<lib dir="../../../../contrib/extraction/lib" />
<lib dir="../../../../dist/" regex="apache-solr-dataimporthandler-extras-\d.*\.jar" />
<!-- Used to specify an alternate directory to hold all index data
other than the default ./data under the Solr home.
If replication is in use, this should match the replication configuration. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<indexDefaults>
<!-- Values here affect all index writers and act as a default unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!--
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<!-- Tell Lucene when to flush documents to disk.
Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!--
Expert: Turn on Lucene's auto commit capability.
TODO: Add recommendations on why you would want to do this.
NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
-->
<!--<luceneAutoCommit>false</luceneAutoCommit>-->
<!--
Expert:
The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
versions used LogDocMergePolicy.
LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when
to merge based on number of documents
Other implementations of MergePolicy must have a no-argument constructor
-->
<!--<mergePolicy>org.apache.lucene.index.LogByteSizeMergePolicy</mergePolicy>-->
<!--
Expert:
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>org.apache.lucene.index.ConcurrentMergeScheduler</mergeScheduler>-->
<!--
As long as Solr is the only process modifying your index, it is
safe to use Lucene's in process locking mechanism. But you may
specify one of the other Lucene LockFactory implementations in
the event that you have a custom situation.
none = NoLockFactory (typically only used with read only indexes)
single = SingleInstanceLockFactory (suggested)
native = NativeFSLockFactory
simple = SimpleFSLockFactory
('simple' is the default for backwards compatibility with Solr 1.2)
-->
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<!-- options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<ramBufferSizeMB>32</ramBufferSizeMB>
<mergeFactor>10</mergeFactor>
<!-- Deprecated -->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<!-- If true, unlock any held write or commit locks on startup.
This defeats the locking mechanism that allows multiple
processes to safely access a lucene index, and should be
used with care.
This is not needed if lock type is 'none' or 'single'
-->
<unlockOnStartup>false</unlockOnStartup>
</mainIndex>
<!-- the default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
<!-- 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)
-->
<!-- Limit the number of deletions Solr will buffer during doc updating.
Setting this lower can help bound memory use during indexing.
-->
<maxPendingDeletes>100000</maxPendingDeletes>
</updateHandler>
<query>
<!-- Maximum number of clauses in a boolean query... can affect
range or prefix queries that expand to big boolean
queries. An exception is thrown if exceeded. -->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- 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 (currently only LRUCache)
size - the maximum number of entries in the cache
initialSize - the initial capacity (number of entries) of
the cache. (seel java.util.HashMap)
autowarmCount - the number of entries to prepopulate from
and old cache.
-->
<filterCache
class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<!-- queryResultCache caches results of searches - ordered lists of
document ids (DocList) based on a query, a sort, and the range
of documents requested. -->
<queryResultCache
class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<!-- documentCache 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"/>
<!-- 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>
<!-- 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.search.CacheRegenerator if autowarming is desired. -->
<!--
<cache name="myUserCache"
class="solr.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="org.mycompany.mypackage.MyRegenerator"
/>
-->
<!-- An 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.
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<!-- 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>50</queryResultWindowSize>
<!-- Maximum number of documents to cache for any entry in the
queryResultCache. -->
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
<!-- This entry enables an int hash representation for filters (DocSets)
when the number of items in the set is less than maxSize. For smaller
sets, this representation is more memory efficient, more efficient to
iterate over, and faster to take intersections. -->
<HashDocSet maxSize="3000" loadFactor="0.75"/>
<!-- a newSearcher event is fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka registered). -->
<!-- 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="start">0</str> <str name="rows">10</str> </lst>
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
<lst><str name="q">static newSearcher warming query from solrconfig.xml</str></lst>
</arr>
</listener>
<!-- a firstSearcher event is fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain autowarming data from. -->
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
</arr>
</listener>
<!-- 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>
<!-- Maximum number of searchers that may be warming in the background
concurrently. An error is returned if this limit is exceeded. Recommend
1-2 for read-only slaves, higher for masters w/o cache warming. -->
<maxWarmingSearchers>4</maxWarmingSearchers>
</query>
<!--
Let the dispatch filter handler /select?qt=XXX
handleSelect=true will use consistent error handling for /select and /update
handleSelect=false will use solr1.1 style error formatting
-->
<requestDispatcher handleSelect="true" >
<!--Make sure your system has some authentication before enabling remote streaming! -->
<requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
<!-- Set HTTP caching related parameters (for proxy caches and clients).
To get the behaviour of Solr 1.2 (ie: no caching related headers)
use the never304="true" option and do not specify a value for
<cacheControl>
-->
<httpCaching never304="true">
<!--httpCaching lastModifiedFrom="openTime"
etagSeed="Solr"-->
<!-- lastModFrom="openTime" is the default, 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 corrispond 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
differnet 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.
-->
<!-- 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"
-->
<!-- <cacheControl>max-age=30, public</cacheControl> -->
</httpCaching>
</requestDispatcher>
<!-- requestHandler plugins... incoming queries will be dispatched to the
correct handler based on the path or the qt (query type) param.
Names starting with a '/' are accessed with the a path equal to the
registered name. Names without a leading '/' are accessed with:
http://host/app/select?qt=name
If no qt is defined, the requestHandler that declares default="true"
will be used.
-->
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true">
<!-- default values for query parameters -->
<lst name="defaults">
<str name="echoParams">explicit</str>
<!--
<int name="rows">10</int>
<str name="fl">*</str>
<str name="version">2.1</str>
-->
</lst>
</requestHandler>
<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
<lst name="defaults">
<str name="config">tika-data-config.xml</str>
</lst>
</requestHandler>
<!--
Search components are registered to SolrCore and used by Search Handlers
By default, the following components are avaliable:
<searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" />
<searchComponent name="facet" class="org.apache.solr.handler.component.FacetComponent" />
<searchComponent name="mlt" class="org.apache.solr.handler.component.MoreLikeThisComponent" />
<searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" />
<searchComponent name="debug" class="org.apache.solr.handler.component.DebugComponent" />
If you register a searchComponent to one of the standard names, that will be used instead.
-->
<requestHandler name="/search" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
</lst>
<!--
By default, this will register the following components:
<arr name="components">
<str>query</str>
<str>facet</str>
<str>mlt</str>
<str>highlight</str>
<str>debug</str>
</arr>
To insert handlers before or after the 'standard' components, use:
<arr name="first-components">
<str>first</str>
</arr>
<arr name="last-components">
<str>last</str>
</arr>
-->
</requestHandler>
<!-- Update request handler.
Note: Since solr1.1 requestHandlers requires a valid content type header if posted in
the body. For example, curl now requires: -H 'Content-type:text/xml; charset=utf-8'
The response format differs from solr1.1 formatting and returns a standard error code.
To enable solr1.1 behavior, remove the /update handler or change its path
"update.processor.class" is the class name for the UpdateRequestProcessor. It is initalized
only once. This can not be changed for each request.
-->
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" >
<!--
<str name="update.processor.class">org.apache.solr.handler.UpdateRequestProcessor</str>
-->
</requestHandler>
<!-- config for the admin interface -->
<admin>
<defaultQuery>*:*</defaultQuery>
<!-- configure a healthcheck file for servers behind a loadbalancer
<healthcheck type="file">server-enabled</healthcheck>
-->
</admin>
</config>

20
solr/example/example-DIH/solr/tika/conf/tika-data-config.xml
View File

@ -1,10 +1,10 @@
<dataConfig>
<dataSource type="BinFileDataSource" />
<document>
<entity name="tika-test" processor="TikaEntityProcessor" url="../contrib/extraction/src/test/resources/solr-word.pdf" format="text">
<field column="Author" name="author" meta="true"/>
<field column="title" name="title" meta="true"/>
<field column="text" name="text"/>
</entity>
</document>
</dataConfig>
<dataConfig>
<dataSource type="BinFileDataSource" />
<document>
<entity name="tika-test" processor="TikaEntityProcessor" url="../contrib/extraction/src/test/resources/solr-word.pdf" format="text">
<field column="Author" name="author" meta="true"/>
<field column="title" name="title" meta="true"/>
<field column="text" name="text"/>
</entity>
</document>
</dataConfig>

68
solr/example/solr/solr.xml
View File

@ -1,34 +1,34 @@
<?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.
-->
<!--
All (relative) paths are relative to the installation path
persistent: Save changes made via the API to this file
sharedLib: path to a lib directory that will be shared across all cores
-->
<solr persistent="false">
<!--
adminPath: RequestHandler path to manage cores.
If 'null' (or absent), cores will not be manageable via request handler
-->
<cores adminPath="/admin/cores" defaultCoreName="collection1">
<core name="collection1" instanceDir="." />
</cores>
</solr>
<?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.
-->
<!--
All (relative) paths are relative to the installation path
persistent: Save changes made via the API to this file
sharedLib: path to a lib directory that will be shared across all cores
-->
<solr persistent="false">
<!--
adminPath: RequestHandler path to manage cores.
If 'null' (or absent), cores will not be manageable via request handler
-->
<cores adminPath="/admin/cores" defaultCoreName="collection1">
<core name="collection1" instanceDir="." />
</cores>
</solr>

108
solr/src/java/org/apache/solr/analysis/EdgeNGramFilterFactory.java
View File

@ -1,54 +1,54 @@
package org.apache.solr.analysis;
/**
* 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.
*/
import java.util.Map;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
/**
* Creates new instances of {@link EdgeNGramTokenFilter}.
*/
public class EdgeNGramFilterFactory extends BaseTokenFilterFactory {
private int maxGramSize = 0;
private int minGramSize = 0;
private String side;
@Override
public void init(Map<String, String> args) {
super.init(args);
String maxArg = args.get("maxGramSize");
maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
: EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);
String minArg = args.get("minGramSize");
minGramSize = (minArg != null ? Integer.parseInt(minArg)
: EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE);
side = args.get("side");
if (side == null) {
side = EdgeNGramTokenFilter.Side.FRONT.getLabel();
}
}
public EdgeNGramTokenFilter create(TokenStream input) {
return new EdgeNGramTokenFilter(input, side, minGramSize, maxGramSize);
}
}
package org.apache.solr.analysis;
/**
* 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.
*/
import java.util.Map;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
/**
* Creates new instances of {@link EdgeNGramTokenFilter}.
*/
public class EdgeNGramFilterFactory extends BaseTokenFilterFactory {
private int maxGramSize = 0;
private int minGramSize = 0;
private String side;
@Override
public void init(Map<String, String> args) {
super.init(args);
String maxArg = args.get("maxGramSize");
maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
: EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);
String minArg = args.get("minGramSize");
minGramSize = (minArg != null ? Integer.parseInt(minArg)
: EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE);
side = args.get("side");
if (side == null) {
side = EdgeNGramTokenFilter.Side.FRONT.getLabel();
}
}
public EdgeNGramTokenFilter create(TokenStream input) {
return new EdgeNGramTokenFilter(input, side, minGramSize, maxGramSize);
}
}

96
solr/src/java/org/apache/solr/analysis/NGramFilterFactory.java
View File

@ -1,48 +1,48 @@
package org.apache.solr.analysis;
/**
* 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.
*/
import java.util.Map;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ngram.NGramTokenFilter;
/**
* Creates new instances of {@link NGramTokenFilter}.
*/
public class NGramFilterFactory extends BaseTokenFilterFactory {
private int maxGramSize = 0;
private int minGramSize = 0;
/** Initialize the n-gram min and max sizes and the side from which one should start tokenizing. */
@Override
public void init(Map<String, String> args) {
super.init(args);
String maxArg = args.get("maxGramSize");
maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
: NGramTokenFilter.DEFAULT_MAX_NGRAM_SIZE);
String minArg = args.get("minGramSize");
minGramSize = (minArg != null ? Integer.parseInt(minArg)
: NGramTokenFilter.DEFAULT_MIN_NGRAM_SIZE);
}
public NGramTokenFilter create(TokenStream input) {
return new NGramTokenFilter(input, minGramSize, maxGramSize);
}
}
package org.apache.solr.analysis;
/**
* 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.
*/
import java.util.Map;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.ngram.NGramTokenFilter;
/**
* Creates new instances of {@link NGramTokenFilter}.
*/
public class NGramFilterFactory extends BaseTokenFilterFactory {
private int maxGramSize = 0;
private int minGramSize = 0;
/** Initialize the n-gram min and max sizes and the side from which one should start tokenizing. */
@Override
public void init(Map<String, String> args) {
super.init(args);
String maxArg = args.get("maxGramSize");
maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
: NGramTokenFilter.DEFAULT_MAX_NGRAM_SIZE);
String minArg = args.get("minGramSize");
minGramSize = (minArg != null ? Integer.parseInt(minArg)
: NGramTokenFilter.DEFAULT_MIN_NGRAM_SIZE);
}
public NGramTokenFilter create(TokenStream input) {
return new NGramTokenFilter(input, minGramSize, maxGramSize);
}
}

52
solr/src/java/org/apache/solr/request/BinaryQueryResponseWriter.java
View File

@ -1,26 +1,26 @@
package org.apache.solr.request;
/**
* 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.
*/
/**
* @deprecated use org.apache.solr.response.BinaryQueryResponseWriter
*/
public interface BinaryQueryResponseWriter extends org.apache.solr.response.BinaryQueryResponseWriter
{
}
package org.apache.solr.request;
/**
* 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.
*/
/**
* @deprecated use org.apache.solr.response.BinaryQueryResponseWriter
*/
public interface BinaryQueryResponseWriter extends org.apache.solr.response.BinaryQueryResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/BinaryResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.BinaryResponseWriter
*/
public class BinaryResponseWriter extends org.apache.solr.response.BinaryResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.BinaryResponseWriter
*/
public class BinaryResponseWriter extends org.apache.solr.response.BinaryResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/JSONResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.JSONResponseWriter
*/
public class JSONResponseWriter extends org.apache.solr.response.JSONResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.JSONResponseWriter
*/
public class JSONResponseWriter extends org.apache.solr.response.JSONResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/PHPResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.PHPResponseWriter
*/
public class PHPResponseWriter extends org.apache.solr.response.PHPResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.PHPResponseWriter
*/
public class PHPResponseWriter extends org.apache.solr.response.PHPResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/PHPSerializedResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.PHPSerializedResponseWriter
*/
public class PHPSerializedResponseWriter extends org.apache.solr.response.PHPSerializedResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.PHPSerializedResponseWriter
*/
public class PHPSerializedResponseWriter extends org.apache.solr.response.PHPSerializedResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/PythonResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.PythonResponseWriter
*/
public class PythonResponseWriter extends org.apache.solr.response.PythonResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.PythonResponseWriter
*/
public class PythonResponseWriter extends org.apache.solr.response.PythonResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/QueryResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.QueryResponseWriter
*/
public interface QueryResponseWriter extends org.apache.solr.response.QueryResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.QueryResponseWriter
*/
public interface QueryResponseWriter extends org.apache.solr.response.QueryResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/RawResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.RawResponseWriter
*/
public class RawResponseWriter extends org.apache.solr.response.RawResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.RawResponseWriter
*/
public class RawResponseWriter extends org.apache.solr.response.RawResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/RubyResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.RubyResponseWriter
*/
public class RubyResponseWriter extends org.apache.solr.response.RubyResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.RubyResponseWriter
*/
public class RubyResponseWriter extends org.apache.solr.response.RubyResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/SolrQueryResponse.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.SolrQueryResponse
*/
public class SolrQueryResponse extends org.apache.solr.response.SolrQueryResponse
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.SolrQueryResponse
*/
public class SolrQueryResponse extends org.apache.solr.response.SolrQueryResponse
{
}

64
solr/src/java/org/apache/solr/request/TextResponseWriter.java
View File

@ -1,32 +1,32 @@
/**
* 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.request;
import java.io.Writer;
import org.apache.solr.response.SolrQueryResponse;
/**
* @deprecated use org.apache.solr.response.TextResponseWriter
*/
public abstract class TextResponseWriter extends org.apache.solr.response.TextResponseWriter
{
public TextResponseWriter(Writer writer, SolrQueryRequest req, SolrQueryResponse rsp) {
super(writer, req, rsp);
}
}
/**
* 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.request;
import java.io.Writer;
import org.apache.solr.response.SolrQueryResponse;
/**
* @deprecated use org.apache.solr.response.TextResponseWriter
*/
public abstract class TextResponseWriter extends org.apache.solr.response.TextResponseWriter
{
public TextResponseWriter(Writer writer, SolrQueryRequest req, SolrQueryResponse rsp) {
super(writer, req, rsp);
}
}

52
solr/src/java/org/apache/solr/request/XMLResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.XMLResponseWriter
*/
public class XMLResponseWriter extends org.apache.solr.response.XMLResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.XMLResponseWriter
*/
public class XMLResponseWriter extends org.apache.solr.response.XMLResponseWriter
{
}

52
solr/src/java/org/apache/solr/request/XSLTResponseWriter.java
View File

@ -1,26 +1,26 @@
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.XSLTResponseWriter
*/
public class XSLTResponseWriter extends org.apache.solr.response.XSLTResponseWriter
{
}
/**
* 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.request;
/**
* @deprecated use org.apache.solr.response.XSLTResponseWriter
*/
public class XSLTResponseWriter extends org.apache.solr.response.XSLTResponseWriter
{
}

660
solr/src/java/org/apache/solr/response/BaseResponseWriter.java
View File

@ -1,330 +1,330 @@
/**
* 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.response;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrDocument;
import org.apache.solr.common.SolrInputDocument;
import org.apache.solr.common.params.CommonParams;
import org.apache.solr.request.SolrQueryRequest;
import org.apache.solr.search.DocList;
import org.apache.solr.search.SolrIndexSearcher;
import org.apache.solr.search.DocIterator;
import org.apache.solr.schema.FieldType;
import org.apache.solr.schema.IndexSchema;
import org.apache.solr.schema.SchemaField;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Fieldable;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
import java.util.List;
import java.util.Set;
import java.util.ArrayList;
/**
*
*
* This class serves as a basis from which {@link QueryResponseWriter}s can be
* developed. The class provides a single method
* {@link #write(SingleResponseWriter, SolrQueryRequest, SolrQueryResponse)}
* that allows users to implement a {@link SingleResponseWriter} sub-class which
* defines how to output {@link SolrInputDocument}s or a
* {@link SolrDocumentList}.
*
* @version $Id$
* @since 1.5
*
*/
public abstract class BaseResponseWriter {
private static final Logger LOG = LoggerFactory
.getLogger(BaseResponseWriter.class);
private static final String SCORE_FIELD = "score";
/**
*
* The main method that allows users to write {@link SingleResponseWriter}s
* and provide them as the initial parameter <code>responseWriter</code> to
* this method which defines how output should be generated.
*
* @param responseWriter
* The user-provided {@link SingleResponseWriter} implementation.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
* @throws IOException
* If any error occurs.
*/
public void write(SingleResponseWriter responseWriter,
SolrQueryRequest request, SolrQueryResponse response) throws IOException {
responseWriter.start();
NamedList nl = response.getValues();
for (int i = 0; i < nl.size(); i++) {
String name = nl.getName(i);
Object val = nl.getVal(i);
if ("responseHeader".equals(name)) {
Boolean omitHeader = request.getParams().getBool(CommonParams.OMIT_HEADER);
if (omitHeader == null || !omitHeader) responseWriter.writeResponseHeader((NamedList) val);
} else if (val instanceof SolrDocumentList) {
SolrDocumentList list = (SolrDocumentList) val;
DocListInfo info = new DocListInfo((int)list.getNumFound(), list.size(), (int)list.getStart(), list.getMaxScore());
if (responseWriter.isStreamingDocs()) {
responseWriter.startDocumentList(name,info);
for (SolrDocument solrDocument : list)
responseWriter.writeDoc(solrDocument);
responseWriter.endDocumentList();
} else {
responseWriter.writeAllDocs(info, list);
}
} else if (val instanceof DocList) {
DocList docList = (DocList) val;
int sz = docList.size();
IdxInfo idxInfo = new IdxInfo(request.getSchema(), request
.getSearcher(), response.getReturnFields());
DocListInfo info = new DocListInfo(docList.matches(), docList.size(),docList.offset(),
docList.maxScore());
DocIterator iterator = docList.iterator();
if (responseWriter.isStreamingDocs()) {
responseWriter.startDocumentList(name,info);
for (int j = 0; j < sz; j++) {
SolrDocument sdoc = getDoc(iterator.nextDoc(), idxInfo);
if (idxInfo.includeScore && docList.hasScores()) {
sdoc.addField(SCORE_FIELD, iterator.score());
}
responseWriter.writeDoc(sdoc);
}
responseWriter.end();
} else {
ArrayList<SolrDocument> list = new ArrayList<SolrDocument>(docList
.size());
for (int j = 0; j < sz; j++) {
SolrDocument sdoc = getDoc(iterator.nextDoc(), idxInfo);
if (idxInfo.includeScore && docList.hasScores()) {
sdoc.addField(SCORE_FIELD, iterator.score());
}
}
responseWriter.writeAllDocs(info, list);
}
} else {
responseWriter.writeOther(name, val);
}
}
responseWriter.end();
}
/**No ops implementation so that the implementing classes do not have to do it
*/
public void init(NamedList args){}
private static class IdxInfo {
IndexSchema schema;
SolrIndexSearcher searcher;
Set<String> returnFields;
boolean includeScore;
private IdxInfo(IndexSchema schema, SolrIndexSearcher searcher,
Set<String> returnFields) {
this.schema = schema;
this.searcher = searcher;
this.includeScore = returnFields != null
&& returnFields.contains(SCORE_FIELD);
if (returnFields != null) {
if (returnFields.size() == 0 || (returnFields.size() == 1 && includeScore) || returnFields.contains("*")) {
returnFields = null; // null means return all stored fields
}
}
this.returnFields = returnFields;
}
}
private static SolrDocument getDoc(int id, IdxInfo info) throws IOException {
Document doc = info.searcher.doc(id);
SolrDocument solrDoc = new SolrDocument();
for (Fieldable f : (List<Fieldable>) doc.getFields()) {
String fieldName = f.name();
if (info.returnFields != null && !info.returnFields.contains(fieldName))
continue;
SchemaField sf = info.schema.getFieldOrNull(fieldName);
FieldType ft = null;
if (sf != null) ft = sf.getType();
Object val = null;
if (ft == null) { // handle fields not in the schema
if (f.isBinary())
val = f.getBinaryValue();
else
val = f.stringValue();
} else {
try {
if (BinaryResponseWriter.KNOWN_TYPES.contains(ft.getClass())) {
val = ft.toObject(f);
} else {
val = ft.toExternal(f);
}
} catch (Exception e) {
// There is a chance of the underlying field not really matching the
// actual field type . So ,it can throw exception
LOG.warn("Error reading a field from document : " + solrDoc, e);
// if it happens log it and continue
continue;
}
}
if (sf != null && sf.multiValued() && !solrDoc.containsKey(fieldName)) {
ArrayList l = new ArrayList();
l.add(val);
solrDoc.addField(fieldName, l);
} else {
solrDoc.addField(fieldName, val);
}
}
return solrDoc;
}
public static class DocListInfo {
public final int numFound;
public final int start ;
public Float maxScore = null;
public final int size;
public DocListInfo(int numFound, int sz,int start, Float maxScore) {
this.numFound = numFound;
size = sz;
this.start = start;
this.maxScore = maxScore;
}
}
/**
*
* Users wanting to define custom {@link QueryResponseWriter}s that deal with
* {@link SolrInputDocument}s and {@link SolrDocumentList} should override the
* methods for this class. All the methods are w/o body because the user is left
* to choose which all methods are required for his purpose
*/
public static abstract class SingleResponseWriter {
/**
* This method is called at the start of the {@link QueryResponseWriter}
* output. Override this method if you want to provide a header for your
* output, e.g., XML headers, etc.
*
* @throws IOException
* if any error occurs.
*/
public void start() throws IOException { }
/**
* This method is called at the start of processing a
* {@link SolrDocumentList}. Those that override this method are provided
* with {@link DocListInfo} object to use to inspect the output
* {@link SolrDocumentList}.
*
* @param info Information about the {@link SolrDocumentList} to output.
*/
public void startDocumentList(String name, DocListInfo info) throws IOException { }
/**
* This method writes out a {@link SolrDocument}, on a doc-by-doc basis.
* This method is only called when {@link #isStreamingDocs()} returns true.
*
* @param solrDocument
* The doc-by-doc {@link SolrDocument} to transform into output as
* part of this {@link QueryResponseWriter}.
*/
public void writeDoc(SolrDocument solrDocument) throws IOException { }
/**
* This method is called at the end of outputting a {@link SolrDocumentList}
* or on a doc-by-doc {@link SolrDocument} basis.
*/
public void endDocumentList() throws IOException { }
/**
* This method defines how to output the {@link SolrQueryResponse} header
* which is provided as a {@link NamedList} parameter.
*
* @param responseHeader
* The response header to output.
*/
public void writeResponseHeader(NamedList responseHeader) throws IOException { }
/**
* This method is called at the end of the {@link QueryResponseWriter}
* lifecycle. Implement this method to add a footer to your output, e.g., in
* the case of XML, the outer tag for your tag set, etc.
*
* @throws IOException
* If any error occurs.
*/
public void end() throws IOException { }
/**
* Define this method to control how output is written by this
* {@link QueryResponseWriter} if the output is not a
* {@link SolrInputDocument} or a {@link SolrDocumentList}.
*
* @param name
* The name of the object to output.
* @param other
* The object to output.
* @throws IOException
* If any error occurs.
*/
public void writeOther(String name, Object other) throws IOException { }
/**
* Overriding this method to return false forces all
* {@link SolrInputDocument}s to be spit out as a {@link SolrDocumentList}
* so they can be processed as a whole, rather than on a doc-by-doc basis.
* If set to false, this method calls
* {@link #writeAllDocs(DocListInfo, List)}, else if set to true, then this
* method forces calling {@link #writeDoc(SolrDocument)} on a doc-by-doc
* basis. one
*
* @return True to force {@link #writeDoc(SolrDocument)} to be called, False
* to force {@link #writeAllDocs(DocListInfo, List)} to be called.
*/
public boolean isStreamingDocs() { return true; }
/**
* Writes out all {@link SolrInputDocument}s . This is invoked only if
* {@link #isStreamingDocs()} returns false.
*
* @param info
* Information about the {@link List} of {@link SolrDocument}s to
* output.
* @param allDocs
* A {@link List} of {@link SolrDocument}s to output.
* @throws IOException
* If any error occurs.
*/
public void writeAllDocs(DocListInfo info, List<SolrDocument> allDocs) throws IOException { }
}
}
/**
* 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.response;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrDocument;
import org.apache.solr.common.SolrInputDocument;
import org.apache.solr.common.params.CommonParams;
import org.apache.solr.request.SolrQueryRequest;
import org.apache.solr.search.DocList;
import org.apache.solr.search.SolrIndexSearcher;
import org.apache.solr.search.DocIterator;
import org.apache.solr.schema.FieldType;
import org.apache.solr.schema.IndexSchema;
import org.apache.solr.schema.SchemaField;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Fieldable;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
import java.util.List;
import java.util.Set;
import java.util.ArrayList;
/**
*
*
* This class serves as a basis from which {@link QueryResponseWriter}s can be
* developed. The class provides a single method
* {@link #write(SingleResponseWriter, SolrQueryRequest, SolrQueryResponse)}
* that allows users to implement a {@link SingleResponseWriter} sub-class which
* defines how to output {@link SolrInputDocument}s or a
* {@link SolrDocumentList}.
*
* @version $Id$
* @since 1.5
*
*/
public abstract class BaseResponseWriter {
private static final Logger LOG = LoggerFactory
.getLogger(BaseResponseWriter.class);
private static final String SCORE_FIELD = "score";
/**
*
* The main method that allows users to write {@link SingleResponseWriter}s
* and provide them as the initial parameter <code>responseWriter</code> to
* this method which defines how output should be generated.
*
* @param responseWriter
* The user-provided {@link SingleResponseWriter} implementation.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
* @throws IOException
* If any error occurs.
*/
public void write(SingleResponseWriter responseWriter,
SolrQueryRequest request, SolrQueryResponse response) throws IOException {
responseWriter.start();
NamedList nl = response.getValues();
for (int i = 0; i < nl.size(); i++) {
String name = nl.getName(i);
Object val = nl.getVal(i);
if ("responseHeader".equals(name)) {
Boolean omitHeader = request.getParams().getBool(CommonParams.OMIT_HEADER);
if (omitHeader == null || !omitHeader) responseWriter.writeResponseHeader((NamedList) val);
} else if (val instanceof SolrDocumentList) {
SolrDocumentList list = (SolrDocumentList) val;
DocListInfo info = new DocListInfo((int)list.getNumFound(), list.size(), (int)list.getStart(), list.getMaxScore());
if (responseWriter.isStreamingDocs()) {
responseWriter.startDocumentList(name,info);
for (SolrDocument solrDocument : list)
responseWriter.writeDoc(solrDocument);
responseWriter.endDocumentList();
} else {
responseWriter.writeAllDocs(info, list);
}
} else if (val instanceof DocList) {
DocList docList = (DocList) val;
int sz = docList.size();
IdxInfo idxInfo = new IdxInfo(request.getSchema(), request
.getSearcher(), response.getReturnFields());
DocListInfo info = new DocListInfo(docList.matches(), docList.size(),docList.offset(),
docList.maxScore());
DocIterator iterator = docList.iterator();
if (responseWriter.isStreamingDocs()) {
responseWriter.startDocumentList(name,info);
for (int j = 0; j < sz; j++) {
SolrDocument sdoc = getDoc(iterator.nextDoc(), idxInfo);
if (idxInfo.includeScore && docList.hasScores()) {
sdoc.addField(SCORE_FIELD, iterator.score());
}
responseWriter.writeDoc(sdoc);
}
responseWriter.end();
} else {
ArrayList<SolrDocument> list = new ArrayList<SolrDocument>(docList
.size());
for (int j = 0; j < sz; j++) {
SolrDocument sdoc = getDoc(iterator.nextDoc(), idxInfo);
if (idxInfo.includeScore && docList.hasScores()) {
sdoc.addField(SCORE_FIELD, iterator.score());
}
}
responseWriter.writeAllDocs(info, list);
}
} else {
responseWriter.writeOther(name, val);
}
}
responseWriter.end();
}
/**No ops implementation so that the implementing classes do not have to do it
*/
public void init(NamedList args){}
private static class IdxInfo {
IndexSchema schema;
SolrIndexSearcher searcher;
Set<String> returnFields;
boolean includeScore;
private IdxInfo(IndexSchema schema, SolrIndexSearcher searcher,
Set<String> returnFields) {
this.schema = schema;
this.searcher = searcher;
this.includeScore = returnFields != null
&& returnFields.contains(SCORE_FIELD);
if (returnFields != null) {
if (returnFields.size() == 0 || (returnFields.size() == 1 && includeScore) || returnFields.contains("*")) {
returnFields = null; // null means return all stored fields
}
}
this.returnFields = returnFields;
}
}
private static SolrDocument getDoc(int id, IdxInfo info) throws IOException {
Document doc = info.searcher.doc(id);
SolrDocument solrDoc = new SolrDocument();
for (Fieldable f : (List<Fieldable>) doc.getFields()) {
String fieldName = f.name();
if (info.returnFields != null && !info.returnFields.contains(fieldName))
continue;
SchemaField sf = info.schema.getFieldOrNull(fieldName);
FieldType ft = null;
if (sf != null) ft = sf.getType();
Object val = null;
if (ft == null) { // handle fields not in the schema
if (f.isBinary())
val = f.getBinaryValue();
else
val = f.stringValue();
} else {
try {
if (BinaryResponseWriter.KNOWN_TYPES.contains(ft.getClass())) {
val = ft.toObject(f);
} else {
val = ft.toExternal(f);
}
} catch (Exception e) {
// There is a chance of the underlying field not really matching the
// actual field type . So ,it can throw exception
LOG.warn("Error reading a field from document : " + solrDoc, e);
// if it happens log it and continue
continue;
}
}
if (sf != null && sf.multiValued() && !solrDoc.containsKey(fieldName)) {
ArrayList l = new ArrayList();
l.add(val);
solrDoc.addField(fieldName, l);
} else {
solrDoc.addField(fieldName, val);
}
}
return solrDoc;
}
public static class DocListInfo {
public final int numFound;
public final int start ;
public Float maxScore = null;
public final int size;
public DocListInfo(int numFound, int sz,int start, Float maxScore) {
this.numFound = numFound;
size = sz;
this.start = start;
this.maxScore = maxScore;
}
}
/**
*
* Users wanting to define custom {@link QueryResponseWriter}s that deal with
* {@link SolrInputDocument}s and {@link SolrDocumentList} should override the
* methods for this class. All the methods are w/o body because the user is left
* to choose which all methods are required for his purpose
*/
public static abstract class SingleResponseWriter {
/**
* This method is called at the start of the {@link QueryResponseWriter}
* output. Override this method if you want to provide a header for your
* output, e.g., XML headers, etc.
*
* @throws IOException
* if any error occurs.
*/
public void start() throws IOException { }
/**
* This method is called at the start of processing a
* {@link SolrDocumentList}. Those that override this method are provided
* with {@link DocListInfo} object to use to inspect the output
* {@link SolrDocumentList}.
*
* @param info Information about the {@link SolrDocumentList} to output.
*/
public void startDocumentList(String name, DocListInfo info) throws IOException { }
/**
* This method writes out a {@link SolrDocument}, on a doc-by-doc basis.
* This method is only called when {@link #isStreamingDocs()} returns true.
*
* @param solrDocument
* The doc-by-doc {@link SolrDocument} to transform into output as
* part of this {@link QueryResponseWriter}.
*/
public void writeDoc(SolrDocument solrDocument) throws IOException { }
/**
* This method is called at the end of outputting a {@link SolrDocumentList}
* or on a doc-by-doc {@link SolrDocument} basis.
*/
public void endDocumentList() throws IOException { }
/**
* This method defines how to output the {@link SolrQueryResponse} header
* which is provided as a {@link NamedList} parameter.
*
* @param responseHeader
* The response header to output.
*/
public void writeResponseHeader(NamedList responseHeader) throws IOException { }
/**
* This method is called at the end of the {@link QueryResponseWriter}
* lifecycle. Implement this method to add a footer to your output, e.g., in
* the case of XML, the outer tag for your tag set, etc.
*
* @throws IOException
* If any error occurs.
*/
public void end() throws IOException { }
/**
* Define this method to control how output is written by this
* {@link QueryResponseWriter} if the output is not a
* {@link SolrInputDocument} or a {@link SolrDocumentList}.
*
* @param name
* The name of the object to output.
* @param other
* The object to output.
* @throws IOException
* If any error occurs.
*/
public void writeOther(String name, Object other) throws IOException { }
/**
* Overriding this method to return false forces all
* {@link SolrInputDocument}s to be spit out as a {@link SolrDocumentList}
* so they can be processed as a whole, rather than on a doc-by-doc basis.
* If set to false, this method calls
* {@link #writeAllDocs(DocListInfo, List)}, else if set to true, then this
* method forces calling {@link #writeDoc(SolrDocument)} on a doc-by-doc
* basis. one
*
* @return True to force {@link #writeDoc(SolrDocument)} to be called, False
* to force {@link #writeAllDocs(DocListInfo, List)} to be called.
*/
public boolean isStreamingDocs() { return true; }
/**
* Writes out all {@link SolrInputDocument}s . This is invoked only if
* {@link #isStreamingDocs()} returns false.
*
* @param info
* Information about the {@link List} of {@link SolrDocument}s to
* output.
* @param allDocs
* A {@link List} of {@link SolrDocument}s to output.
* @throws IOException
* If any error occurs.
*/
public void writeAllDocs(DocListInfo info, List<SolrDocument> allDocs) throws IOException { }
}
}

172
solr/src/java/org/apache/solr/response/GenericBinaryResponseWriter.java
View File

@ -1,86 +1,86 @@
/**
* 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.response;
import java.io.OutputStream;
import java.io.IOException;
import java.io.Writer;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrInputDocument;
import org.apache.solr.request.SolrQueryRequest;
/**
*
*
* A generic {@link QueryResponseWriter} implementation that requires a user to
* implement the
* {@link #getSingleResponseWriter(OutputStream, SolrQueryRequest, SolrQueryResponse)}
* that defines a {@link SingleResponseWriter} to handle the binary output.
*
* @since 1.5
* @version $Id$
*
*/
public abstract class GenericBinaryResponseWriter extends BaseResponseWriter
implements BinaryQueryResponseWriter {
/**
*
* Writes the binary output data using the {@link SingleResponseWriter}
* provided by a call to
* {@link #getSingleResponseWriter(OutputStream, SolrQueryRequest, SolrQueryResponse)}
* .
*
* @param out
* The {@link OutputStream} to write the binary data to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
*/
public void write(OutputStream out, SolrQueryRequest request,
SolrQueryResponse response) throws IOException {
super.write(getSingleResponseWriter(out, request, response), request,
response);
}
/**
* Users of this class should implement this method to define a
* {@link SingleResponseWriter} responsible for writing the binary output
* given a {@link SolrDocumentList} or doc-by-doc, given a
* {@link SolrInputDocument}.
*
* @param out
* The {@link OutputStream} to write the binary data response to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
* @return A {@link SingleResponseWriter} that will be used to generate the
* response output from this {@link QueryResponseWriter}.
*/
public abstract SingleResponseWriter getSingleResponseWriter(
OutputStream out, SolrQueryRequest request, SolrQueryResponse response);
/**Just to throw Exception So that the eimplementing classes do not have to do the same
*/
public void write(Writer writer, SolrQueryRequest request, SolrQueryResponse response) throws IOException {
throw new RuntimeException("This is a binary writer , Cannot write to a characterstream");
}
}
/**
* 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.response;
import java.io.OutputStream;
import java.io.IOException;
import java.io.Writer;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrInputDocument;
import org.apache.solr.request.SolrQueryRequest;
/**
*
*
* A generic {@link QueryResponseWriter} implementation that requires a user to
* implement the
* {@link #getSingleResponseWriter(OutputStream, SolrQueryRequest, SolrQueryResponse)}
* that defines a {@link SingleResponseWriter} to handle the binary output.
*
* @since 1.5
* @version $Id$
*
*/
public abstract class GenericBinaryResponseWriter extends BaseResponseWriter
implements BinaryQueryResponseWriter {
/**
*
* Writes the binary output data using the {@link SingleResponseWriter}
* provided by a call to
* {@link #getSingleResponseWriter(OutputStream, SolrQueryRequest, SolrQueryResponse)}
* .
*
* @param out
* The {@link OutputStream} to write the binary data to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
*/
public void write(OutputStream out, SolrQueryRequest request,
SolrQueryResponse response) throws IOException {
super.write(getSingleResponseWriter(out, request, response), request,
response);
}
/**
* Users of this class should implement this method to define a
* {@link SingleResponseWriter} responsible for writing the binary output
* given a {@link SolrDocumentList} or doc-by-doc, given a
* {@link SolrInputDocument}.
*
* @param out
* The {@link OutputStream} to write the binary data response to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
* @return A {@link SingleResponseWriter} that will be used to generate the
* response output from this {@link QueryResponseWriter}.
*/
public abstract SingleResponseWriter getSingleResponseWriter(
OutputStream out, SolrQueryRequest request, SolrQueryResponse response);
/**Just to throw Exception So that the eimplementing classes do not have to do the same
*/
public void write(Writer writer, SolrQueryRequest request, SolrQueryResponse response) throws IOException {
throw new RuntimeException("This is a binary writer , Cannot write to a characterstream");
}
}

156
solr/src/java/org/apache/solr/response/GenericTextResponseWriter.java
View File

@ -1,78 +1,78 @@
/**
* 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.response;
import java.io.Writer;
import java.io.IOException;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrInputDocument;
import org.apache.solr.request.SolrQueryRequest;
/**
*
*
* A generic {@link QueryResponseWriter} implementation that requires a user to
* implement the
* {@link #getSingleResponseWriter(Writer, SolrQueryRequest, SolrQueryResponse)}
* that defines a {@link SingleResponseWriter} to handle plain ol' text output.
*
* @since 1.5
* @version $Id$
*
*/
public abstract class GenericTextResponseWriter extends BaseResponseWriter
implements QueryResponseWriter {
/**
*
* Writes text output using the {@link SingleResponseWriter} provided by a
* call to
* {@link #getSingleResponseWriter(Writer, SolrQueryRequest, SolrQueryResponse)}
* .
*
* @param out
* The {@link Writer} to write the text output to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
*/
public void write(Writer writer, SolrQueryRequest request,
SolrQueryResponse response) throws IOException {
super.write(getSingleResponseWriter(writer, request, response), request,
response);
}
/**
* Users of this class should implement this method to define a
* {@link SingleResponseWriter} responsible for writing text output given a
* {@link SolrDocumentList} or doc-by-doc, given a {@link SolrInputDocument}.
*
* @param writer
* The {@link Writer} to write the text data response to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
* @return A {@link SingleResponseWriter} that will be used to generate the
* response output from this {@link QueryResponseWriter}.
*/
protected abstract SingleResponseWriter getSingleResponseWriter(
Writer writer, SolrQueryRequest request, SolrQueryResponse response);
}
/**
* 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.response;
import java.io.Writer;
import java.io.IOException;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrInputDocument;
import org.apache.solr.request.SolrQueryRequest;
/**
*
*
* A generic {@link QueryResponseWriter} implementation that requires a user to
* implement the
* {@link #getSingleResponseWriter(Writer, SolrQueryRequest, SolrQueryResponse)}
* that defines a {@link SingleResponseWriter} to handle plain ol' text output.
*
* @since 1.5
* @version $Id$
*
*/
public abstract class GenericTextResponseWriter extends BaseResponseWriter
implements QueryResponseWriter {
/**
*
* Writes text output using the {@link SingleResponseWriter} provided by a
* call to
* {@link #getSingleResponseWriter(Writer, SolrQueryRequest, SolrQueryResponse)}
* .
*
* @param out
* The {@link Writer} to write the text output to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
*/
public void write(Writer writer, SolrQueryRequest request,
SolrQueryResponse response) throws IOException {
super.write(getSingleResponseWriter(writer, request, response), request,
response);
}
/**
* Users of this class should implement this method to define a
* {@link SingleResponseWriter} responsible for writing text output given a
* {@link SolrDocumentList} or doc-by-doc, given a {@link SolrInputDocument}.
*
* @param writer
* The {@link Writer} to write the text data response to.
* @param request
* The provided {@link SolrQueryRequest}.
* @param response
* The provided {@link SolrQueryResponse}.
* @return A {@link SingleResponseWriter} that will be used to generate the
* response output from this {@link QueryResponseWriter}.
*/
protected abstract SingleResponseWriter getSingleResponseWriter(
Writer writer, SolrQueryRequest request, SolrQueryResponse response);
}

124
solr/src/java/org/apache/solr/search/FieldQParserPlugin.java
View File

@ -1,62 +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.search;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.search.*;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.SolrException;
import org.apache.solr.request.SolrQueryRequest;
import org.apache.solr.schema.FieldType;
import org.apache.solr.schema.TextField;
import org.apache.solr.schema.SchemaField;
import java.io.IOException;
import java.io.StringReader;
import java.util.ArrayList;
/**
* Create a field query from the input value, applying text analysis and constructing a phrase query if appropriate.
* <br>Other parameters: <code>f</code>, the field
* <br>Example: <code>{!field f=myfield}Foo Bar</code> creates a phrase query with "foo" followed by "bar"
* if the analyzer for myfield is a text field with an analyzer that splits on whitespace and lowercases terms.
* This is generally equivalent to the Lucene query parser expression <code>myfield:"Foo Bar"</code>
*/
public class FieldQParserPlugin extends QParserPlugin {
public static String NAME = "field";
public void init(NamedList args) {
}
public QParser createParser(String qstr, SolrParams localParams, SolrParams params, SolrQueryRequest req) {
return new QParser(qstr, localParams, params, req) {
public Query parse() throws ParseException {
String field = localParams.get(QueryParsing.F);
String queryText = localParams.get(QueryParsing.V);
SchemaField sf = req.getSchema().getField(field);
FieldType ft = sf.getType();
return ft.getFieldQuery(this, sf, queryText);
}
};
}
}
/**
* 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.search;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.search.*;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.SolrException;
import org.apache.solr.request.SolrQueryRequest;
import org.apache.solr.schema.FieldType;
import org.apache.solr.schema.TextField;
import org.apache.solr.schema.SchemaField;
import java.io.IOException;
import java.io.StringReader;
import java.util.ArrayList;
/**
* Create a field query from the input value, applying text analysis and constructing a phrase query if appropriate.
* <br>Other parameters: <code>f</code>, the field
* <br>Example: <code>{!field f=myfield}Foo Bar</code> creates a phrase query with "foo" followed by "bar"
* if the analyzer for myfield is a text field with an analyzer that splits on whitespace and lowercases terms.
* This is generally equivalent to the Lucene query parser expression <code>myfield:"Foo Bar"</code>
*/
public class FieldQParserPlugin extends QParserPlugin {
public static String NAME = "field";
public void init(NamedList args) {
}
public QParser createParser(String qstr, SolrParams localParams, SolrParams params, SolrQueryRequest req) {
return new QParser(qstr, localParams, params, req) {
public Query parse() throws ParseException {
String field = localParams.get(QueryParsing.F);
String queryText = localParams.get(QueryParsing.V);
SchemaField sf = req.getSchema().getField(field);
FieldType ft = sf.getType();
return ft.getFieldQuery(this, sf, queryText);
}
};
}
}

74
solr/src/java/org/apache/solr/search/FunctionQParserPlugin.java
View File

@ -1,37 +1,37 @@
/**
* 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.search;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.request.SolrQueryRequest;
/**
* Create a function query from the input value.
* <br>Other parameters: none
* <br>Example: <code>{!func}log(foo)</code>
*/
public class FunctionQParserPlugin extends QParserPlugin {
public static String NAME = "func";
public void init(NamedList args) {
}
public QParser createParser(String qstr, SolrParams localParams, SolrParams params, SolrQueryRequest req) {
return new FunctionQParser(qstr, localParams, params, req);
}
}
/**
* 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.search;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.request.SolrQueryRequest;
/**
* Create a function query from the input value.
* <br>Other parameters: none
* <br>Example: <code>{!func}log(foo)</code>
*/
public class FunctionQParserPlugin extends QParserPlugin {
public static String NAME = "func";
public void init(NamedList args) {
}
public QParser createParser(String qstr, SolrParams localParams, SolrParams params, SolrQueryRequest req) {
return new FunctionQParser(qstr, localParams, params, req);
}
}

90
solr/src/java/org/apache/solr/search/RawQParserPlugin.java
View File

@ -1,45 +1,45 @@
/**
* 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.search;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.request.SolrQueryRequest;
/**
* Create a term query from the input value without any text analysis or transformation whatsoever.
* <br>Other parameters: <code>f</code>, the field
* <br>Example: <code>{!raw f=myfield}Foo Bar</code> creates <code>TermQuery(Term("myfield","Foo Bar"))</code>
*/
public class RawQParserPlugin extends QParserPlugin {
public static String NAME = "raw";
public void init(NamedList args) {
}
public QParser createParser(String qstr, SolrParams localParams, SolrParams params, SolrQueryRequest req) {
return new QParser(qstr, localParams, params, req) {
public Query parse() throws ParseException {
return new TermQuery(new Term(localParams.get(QueryParsing.F), localParams.get(QueryParsing.V)));
}
};
}
}
/**
* 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.search;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.request.SolrQueryRequest;
/**
* Create a term query from the input value without any text analysis or transformation whatsoever.
* <br>Other parameters: <code>f</code>, the field
* <br>Example: <code>{!raw f=myfield}Foo Bar</code> creates <code>TermQuery(Term("myfield","Foo Bar"))</code>
*/
public class RawQParserPlugin extends QParserPlugin {
public static String NAME = "raw";
public void init(NamedList args) {
}
public QParser createParser(String qstr, SolrParams localParams, SolrParams params, SolrQueryRequest req) {
return new QParser(qstr, localParams, params, req) {
public Query parse() throws ParseException {
return new TermQuery(new Term(localParams.get(QueryParsing.F), localParams.get(QueryParsing.V)));
}
};
}
}

92
solr/src/java/org/apache/solr/search/SolrFilter.java
View File

@ -1,46 +1,46 @@
/**
* 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.search;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.DocIdSet;
import org.apache.lucene.index.IndexReader;
import java.util.Map;
import java.io.IOException;
/** A SolrFilter extends the Lucene Filter and adds extra semantics such as passing on
* weight context info for function queries.
*
* Experimental and subject to change.
*/
public abstract class SolrFilter extends Filter {
/** Implementations should propagate createWeight to sub-ValueSources which can store weight info in the context.
* The context object will be passed to getDocIdSet() where this info can be retrieved. */
public abstract void createWeight(Map context, Searcher searcher) throws IOException;
public abstract DocIdSet getDocIdSet(Map context, IndexReader reader) throws IOException;
@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
return getDocIdSet(null, reader);
}
}
/**
* 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.search;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.DocIdSet;
import org.apache.lucene.index.IndexReader;
import java.util.Map;
import java.io.IOException;
/** A SolrFilter extends the Lucene Filter and adds extra semantics such as passing on
* weight context info for function queries.
*
* Experimental and subject to change.
*/
public abstract class SolrFilter extends Filter {
/** Implementations should propagate createWeight to sub-ValueSources which can store weight info in the context.
* The context object will be passed to getDocIdSet() where this info can be retrieved. */
public abstract void createWeight(Map context, Searcher searcher) throws IOException;
public abstract DocIdSet getDocIdSet(Map context, IndexReader reader) throws IOException;
@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
return getDocIdSet(null, reader);
}
}

62
solr/src/java/org/apache/solr/util/plugin/PluginInfoInitialized.java
View File

@ -1,31 +1,31 @@
/**
* 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.util.plugin;
import org.apache.solr.core.PluginInfo;
/**
* A plugin that can be initialized with a PluginInfo
*
* @version $Id$
* @since solr 1.4
*/
public interface PluginInfoInitialized {
public void init(PluginInfo info);
}
/**
* 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.util.plugin;
import org.apache.solr.core.PluginInfo;
/**
* A plugin that can be initialized with a PluginInfo
*
* @version $Id$
* @since solr 1.4
*/
public interface PluginInfoInitialized {
public void init(PluginInfo info);
}

112
solr/src/test/org/apache/solr/core/TestBadConfig.java
View File

@ -1,57 +1,57 @@
/**
* 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.core;
import org.apache.solr.SolrTestCaseJ4;
import org.apache.solr.util.AbstractSolrTestCase;
import org.apache.solr.util.TestHarness;
import org.junit.BeforeClass;
import java.io.File;
public class TestBadConfig extends AbstractSolrTestCase {
public String getSchemaFile() { return "schema.xml"; }
public String getSolrConfigFile() { return "bad_solrconfig.xml"; }
public void setUp() throws Exception {
dataDir = new File(System.getProperty("java.io.tmpdir")
+ System.getProperty("file.separator")
+ getClass().getName());
dataDir.mkdirs();
try {
SolrTestCaseJ4.ignoreException("unset.sys.property");
solrConfig = new SolrConfig(getSolrConfigFile());
h = new TestHarness( dataDir.getAbsolutePath(),
solrConfig,
getSchemaFile());
fail("Exception should have been thrown");
} catch (Exception e) {
assertTrue(e.getMessage().contains("unset.sys.property"));
SolrTestCaseJ4.resetExceptionIgnores();
}
}
public void testNothing() {
// Empty test case as the real test is that the initialization of the TestHarness fails
assertTrue(true);
}
/**
* 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.core;
import org.apache.solr.SolrTestCaseJ4;
import org.apache.solr.util.AbstractSolrTestCase;
import org.apache.solr.util.TestHarness;
import org.junit.BeforeClass;
import java.io.File;
public class TestBadConfig extends AbstractSolrTestCase {
public String getSchemaFile() { return "schema.xml"; }
public String getSolrConfigFile() { return "bad_solrconfig.xml"; }
public void setUp() throws Exception {
dataDir = new File(System.getProperty("java.io.tmpdir")
+ System.getProperty("file.separator")
+ getClass().getName());
dataDir.mkdirs();
try {
SolrTestCaseJ4.ignoreException("unset.sys.property");
solrConfig = new SolrConfig(getSolrConfigFile());
h = new TestHarness( dataDir.getAbsolutePath(),
solrConfig,
getSchemaFile());
fail("Exception should have been thrown");
} catch (Exception e) {
assertTrue(e.getMessage().contains("unset.sys.property"));
SolrTestCaseJ4.resetExceptionIgnores();
}
}
public void testNothing() {
// Empty test case as the real test is that the initialization of the TestHarness fails
assertTrue(true);
}
}

72
solr/src/test/org/apache/solr/core/TestLegacyMergeSchedulerPolicyConfig.java
View File

@ -1,36 +1,36 @@
package org.apache.solr.core;
import java.io.IOException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.LogDocMergePolicy;
import org.apache.lucene.index.SerialMergeScheduler;
import org.apache.solr.update.DirectUpdateHandler2;
import org.apache.solr.util.AbstractSolrTestCase;
public class TestLegacyMergeSchedulerPolicyConfig extends AbstractSolrTestCase {
public String getSchemaFile() {
return "schema.xml";
}
public String getSolrConfigFile() {
return "solrconfig-legacy.xml";
}
public void testLegacy() throws Exception {
IndexWriter writer = new ExposeWriterHandler().getWriter();
assertTrue(writer.getMergePolicy().getClass().getName().equals(LogDocMergePolicy.class.getName()));
assertTrue(writer.getMergeScheduler().getClass().getName().equals(SerialMergeScheduler.class.getName()));
}
class ExposeWriterHandler extends DirectUpdateHandler2 {
public ExposeWriterHandler() throws IOException {
super(h.getCore());
}
public IndexWriter getWriter() throws IOException {
forceOpenWriter();
return writer;
}
}
}
package org.apache.solr.core;
import java.io.IOException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.LogDocMergePolicy;
import org.apache.lucene.index.SerialMergeScheduler;
import org.apache.solr.update.DirectUpdateHandler2;
import org.apache.solr.util.AbstractSolrTestCase;
public class TestLegacyMergeSchedulerPolicyConfig extends AbstractSolrTestCase {
public String getSchemaFile() {
return "schema.xml";
}
public String getSolrConfigFile() {
return "solrconfig-legacy.xml";
}
public void testLegacy() throws Exception {
IndexWriter writer = new ExposeWriterHandler().getWriter();
assertTrue(writer.getMergePolicy().getClass().getName().equals(LogDocMergePolicy.class.getName()));
assertTrue(writer.getMergeScheduler().getClass().getName().equals(SerialMergeScheduler.class.getName()));
}
class ExposeWriterHandler extends DirectUpdateHandler2 {
public ExposeWriterHandler() throws IOException {
super(h.getCore());
}
public IndexWriter getWriter() throws IOException {
forceOpenWriter();
return writer;
}
}
}

130
solr/src/test/org/apache/solr/core/TestPropInject.java
View File

@ -1,65 +1,65 @@
package org.apache.solr.core;
import java.io.IOException;
import org.apache.lucene.index.ConcurrentMergeScheduler;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.LogByteSizeMergePolicy;
import org.apache.solr.update.DirectUpdateHandler2;
import org.apache.solr.util.AbstractSolrTestCase;
public class TestPropInject extends AbstractSolrTestCase {
public String getSchemaFile() {
return "schema.xml";
}
public String getSolrConfigFile() {
if ("testMergePolicyDefaults".equals(getName()) || "testPropsDefaults".equals(getName()))
return "solrconfig-propinject-indexdefault.xml";
else
return "solrconfig-propinject.xml";
}
class ExposeWriterHandler extends DirectUpdateHandler2 {
public ExposeWriterHandler() throws IOException {
super(h.getCore());
}
public IndexWriter getWriter() throws IOException {
forceOpenWriter();
return writer;
}
}
public void testMergePolicy() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
LogByteSizeMergePolicy mp = (LogByteSizeMergePolicy)writer.getMergePolicy();
assertEquals(64.0, mp.getMaxMergeMB());
uh.close();
}
public void testMergePolicyDefaults() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
LogByteSizeMergePolicy mp = (LogByteSizeMergePolicy)writer.getMergePolicy();
assertEquals(32.0, mp.getMaxMergeMB());
uh.close();
}
public void testProps() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
ConcurrentMergeScheduler cms = (ConcurrentMergeScheduler)writer.getMergeScheduler();
assertEquals(2, cms.getMaxThreadCount());
uh.close();
}
public void testPropsDefaults() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
ConcurrentMergeScheduler cms = (ConcurrentMergeScheduler)writer.getMergeScheduler();
assertEquals(4, cms.getMaxThreadCount());
uh.close();
}
}
package org.apache.solr.core;
import java.io.IOException;
import org.apache.lucene.index.ConcurrentMergeScheduler;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.LogByteSizeMergePolicy;
import org.apache.solr.update.DirectUpdateHandler2;
import org.apache.solr.util.AbstractSolrTestCase;
public class TestPropInject extends AbstractSolrTestCase {
public String getSchemaFile() {
return "schema.xml";
}
public String getSolrConfigFile() {
if ("testMergePolicyDefaults".equals(getName()) || "testPropsDefaults".equals(getName()))
return "solrconfig-propinject-indexdefault.xml";
else
return "solrconfig-propinject.xml";
}
class ExposeWriterHandler extends DirectUpdateHandler2 {
public ExposeWriterHandler() throws IOException {
super(h.getCore());
}
public IndexWriter getWriter() throws IOException {
forceOpenWriter();
return writer;
}
}
public void testMergePolicy() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
LogByteSizeMergePolicy mp = (LogByteSizeMergePolicy)writer.getMergePolicy();
assertEquals(64.0, mp.getMaxMergeMB());
uh.close();
}
public void testMergePolicyDefaults() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
LogByteSizeMergePolicy mp = (LogByteSizeMergePolicy)writer.getMergePolicy();
assertEquals(32.0, mp.getMaxMergeMB());
uh.close();
}
public void testProps() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
ConcurrentMergeScheduler cms = (ConcurrentMergeScheduler)writer.getMergeScheduler();
assertEquals(2, cms.getMaxThreadCount());
uh.close();
}
public void testPropsDefaults() throws Exception {
ExposeWriterHandler uh = new ExposeWriterHandler();
IndexWriter writer = uh.getWriter();
ConcurrentMergeScheduler cms = (ConcurrentMergeScheduler)writer.getMergeScheduler();
assertEquals(4, cms.getMaxThreadCount());
uh.close();
}
}

46
solr/src/test/test-files/solr/conf/protwords.txt
View File

@ -1,23 +1,23 @@
# 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.
#use a protected word file to avoid stemming two
#unrelated words to the same base word.
#to test, we will use words that would normally obviously be stemmed.
cats
ridding
c#
c++
.net
# 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.
#use a protected word file to avoid stemming two
#unrelated words to the same base word.
#to test, we will use words that would normally obviously be stemmed.
cats
ridding
c#
c++
.net

922
solr/src/test/test-files/solr/conf/solrconfig-legacy.xml
View File

@ -1,461 +1,461 @@
<?xml version="1.0" ?>
<!--
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.
-->
<!-- $Id: solrconfig.xml 382610 2006-03-03 01:43:03Z yonik $
$Source$
$Name$
This is a "kitchen sink" config file that tests can use.
When writting a new test, feel free to add *new* items (plugins,
config options, etc...) as long as they don't break any existing
tests. if you need to test something esoteric please add a new
"solrconfig-your-esoteric-purpose.xml" config file.
Note in particular that this test is used by MinimalSchemaTest so
Anything added to this file needs to work correctly even if there
is now uniqueKey or defaultSearch Field.
-->
<config>
<jmx />
<!-- Used to specify an alternate directory to hold all index data.
It defaults to "index" if not present, and should probably
not be changed if replication is in use. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<!-- The DirectoryFactory to use for indexes.
solr.StandardDirectoryFactory, the default, is filesystem based.
solr.RAMDirectoryFactory is memory based and not persistent. -->
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
<indexDefaults>
<!-- Values here affect all index writers and act as a default
unless overridden. -->
<!-- Values here affect all index writers and act as a default unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<!-- Tell Lucene when to flush documents to disk.
Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!--
Expert: Turn on Lucene's auto commit capability.
NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
-->
<luceneAutoCommit>false</luceneAutoCommit>
<!--
Expert:
The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
versions used LogDocMergePolicy.
LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when
to merge based on number of documents
Other implementations of MergePolicy must have a no-argument constructor
-->
<mergePolicy>org.apache.lucene.index.LogDocMergePolicy</mergePolicy>
<!--
Expert:
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>org.apache.lucene.index.SerialMergeScheduler</mergeScheduler>
<!-- these are global... can't currently override per index -->
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<!-- lucene options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- for better multi-segment testing, we are using slower
indexing properties of maxBufferedDocs=10 and LogDocMergePolicy.
-->
<maxBufferedDocs>10</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<mergePolicy>org.apache.lucene.index.LogDocMergePolicy</mergePolicy>
<mergeScheduler>org.apache.lucene.index.SerialMergeScheduler</mergeScheduler>
<unlockOnStartup>true</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2">
<!-- autocommit pending docs if certain criteria are met
<autoCommit>
<maxDocs>10000</maxDocs>
<maxTime>3600000</maxTime>
</autoCommit>
-->
<!-- represents a lower bound on the frequency that commits may
occur (in seconds). NOTE: not yet implemented
<commitIntervalLowerBound>0</commitIntervalLowerBound>
-->
<!-- The RunExecutableListener executes an external command.
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=nothing
env - environment variables to set. default=nothing
-->
<!-- A postCommit event is fired after every commit
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">/var/opt/resin3/__PORT__/scripts/solr/snapshooter</str>
<str name="dir">/var/opt/resin3/__PORT__</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>
<query>
<!-- Maximum number of clauses in a boolean query... can affect
range or wildcard queries that expand to big boolean
queries. An exception is thrown if exceeded.
-->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- Cache specification for Filters or DocSets - unordered set of *all* documents
that match a particular query.
-->
<filterCache
class="solr.search.FastLRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<queryResultCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="1024"/>
<documentCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- If true, stored fields that are not requested will be loaded lazily.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!--
<cache name="myUserCache"
class="solr.search.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="MyRegenerator"
/>
-->
<!--
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<queryResultWindowSize>10</queryResultWindowSize>
<!-- set maxSize artificially low to exercise both types of sets -->
<HashDocSet maxSize="3" loadFactor="0.75"/>
<!-- boolToFilterOptimizer converts boolean clauses with zero boost
into cached filters if the number of docs selected by the clause exceeds
the threshold (represented as a fraction of the total index)
-->
<boolTofilterOptimizer enabled="false" cacheSize="32" threshold=".05"/>
<!-- a newSearcher event is fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka registered). -->
<!-- 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="start">0</str> <str name="rows">10</str> </lst>
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
<!-- a firstSearcher event is fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain prewarming data from. -->
<!--
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
</query>
<!-- An alternate set representation that uses an integer hash to store filters (sets of docids).
If the set cardinality <= maxSize elements, then HashDocSet will be used instead of the bitset
based HashBitset. -->
<!-- requestHandler plugins... incoming queries will be dispatched to the
correct handler based on the qt (query type) param matching the
name of registered handlers.
The "standard" request handler is the default and will be used if qt
is not specified in the request.
-->
<requestHandler name="standard" class="solr.StandardRequestHandler">
<bool name="httpCaching">true</bool>
</requestHandler>
<requestHandler name="dismaxOldStyleDefaults"
class="solr.DisMaxRequestHandler" >
<!-- for historic reasons, DisMaxRequestHandler will use all of
it's init params as "defaults" if there is no "defaults" list
specified
-->
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</requestHandler>
<requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
<lst name="defaults">
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</lst>
</requestHandler>
<requestHandler name="old" class="solr.tst.OldRequestHandler" >
<int name="myparam">1000</int>
<float name="ratio">1.4142135</float>
<arr name="myarr"><int>1</int><int>2</int></arr>
<str>foo</str>
</requestHandler>
<requestHandler name="oldagain" class="solr.tst.OldRequestHandler" >
<lst name="lst1"> <str name="op">sqrt</str> <int name="val">2</int> </lst>
<lst name="lst2"> <str name="op">log</str> <float name="val">10</float> </lst>
</requestHandler>
<requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
<requestHandler name="test" class="solr.tst.TestRequestHandler" />
<!-- test query parameter defaults -->
<requestHandler name="defaults" class="solr.StandardRequestHandler">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<!-- test query parameter defaults -->
<requestHandler name="lazy" class="solr.StandardRequestHandler" startup="lazy">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
<requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy">
<bool name="httpCaching">false</bool>
</requestHandler>
<searchComponent name="spellcheck" class="org.apache.solr.handler.component.SpellCheckComponent">
<str name="queryAnalyzerFieldType">lowerfilt</str>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">lowerfilt</str>
<str name="spellcheckIndexDir">spellchecker1</str>
<str name="buildOnCommit">true</str>
</lst>
<!-- Example of using different distance measure -->
<lst name="spellchecker">
<str name="name">jarowinkler</str>
<str name="field">lowerfilt</str>
<!-- Use a different Distance Measure -->
<str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
<str name="spellcheckIndexDir">spellchecker2</str>
</lst>
<lst name="spellchecker">
<str name="classname">solr.FileBasedSpellChecker</str>
<str name="name">external</str>
<str name="sourceLocation">spellings.txt</str>
<str name="characterEncoding">UTF-8</str>
<str name="spellcheckIndexDir">spellchecker3</str>
</lst>
</searchComponent>
<searchComponent name="termsComp" class="org.apache.solr.handler.component.TermsComponent"/>
<requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
<arr name="components">
<str>termsComp</str>
</arr>
</requestHandler>
<!--
The SpellingQueryConverter to convert raw (CommonParams.Q) queries into tokens. Uses a simple regular expression
to strip off field markup, boosts, ranges, etc. but it is not guaranteed to match an exact parse from the query parser.
-->
<queryConverter name="queryConverter" class="org.apache.solr.spelling.SpellingQueryConverter"/>
<requestHandler name="spellCheckCompRH" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<!-- omp = Only More Popular -->
<str name="spellcheck.onlyMorePopular">false</str>
<!-- exr = Extended Results -->
<str name="spellcheck.extendedResults">false</str>
<!-- The number of suggestions to return -->
<str name="spellcheck.count">1</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
<requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
</lst>
<arr name="last-components">
<str>tvComponent</str>
</arr>
</requestHandler>
<searchComponent class="solr.HighlightComponent" name="highlight">
<highlighting>
<!-- Configure the standard fragmenter -->
<fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
<lst name="defaults">
<int name="hl.fragsize">70</int>
</lst>
</fragmenter>
<!-- Configure the standard formatter -->
<formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
</highlighting>
</searchComponent>
<!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
<requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
</requestDispatcher>
<admin>
<defaultQuery>solr</defaultQuery>
<gettableFiles>solrconfig.xml scheam.xml admin-extra.html</gettableFiles>
</admin>
<!-- test getting system property -->
<propTest attr1="${solr.test.sys.prop1}-$${literal}"
attr2="${non.existent.sys.prop:default-from-config}">prefix-${solr.test.sys.prop2}-suffix</propTest>
<queryParser name="foo" class="FooQParserPlugin"/>
<updateRequestProcessorChain name="dedupe">
<processor class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
<bool name="enabled">false</bool>
<bool name="overwriteDupes">true</bool>
<str name="fields">v_t,t_field</str>
<str name="signatureClass">org.apache.solr.update.processor.TextProfileSignature</str>
</processor>
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
</config>
<?xml version="1.0" ?>
<!--
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.
-->
<!-- $Id: solrconfig.xml 382610 2006-03-03 01:43:03Z yonik $
$Source$
$Name$
This is a "kitchen sink" config file that tests can use.
When writting a new test, feel free to add *new* items (plugins,
config options, etc...) as long as they don't break any existing
tests. if you need to test something esoteric please add a new
"solrconfig-your-esoteric-purpose.xml" config file.
Note in particular that this test is used by MinimalSchemaTest so
Anything added to this file needs to work correctly even if there
is now uniqueKey or defaultSearch Field.
-->
<config>
<jmx />
<!-- Used to specify an alternate directory to hold all index data.
It defaults to "index" if not present, and should probably
not be changed if replication is in use. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<!-- The DirectoryFactory to use for indexes.
solr.StandardDirectoryFactory, the default, is filesystem based.
solr.RAMDirectoryFactory is memory based and not persistent. -->
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
<indexDefaults>
<!-- Values here affect all index writers and act as a default
unless overridden. -->
<!-- Values here affect all index writers and act as a default unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<!-- Tell Lucene when to flush documents to disk.
Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!--
Expert: Turn on Lucene's auto commit capability.
NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
-->
<luceneAutoCommit>false</luceneAutoCommit>
<!--
Expert:
The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
versions used LogDocMergePolicy.
LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when
to merge based on number of documents
Other implementations of MergePolicy must have a no-argument constructor
-->
<mergePolicy>org.apache.lucene.index.LogDocMergePolicy</mergePolicy>
<!--
Expert:
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>org.apache.lucene.index.SerialMergeScheduler</mergeScheduler>
<!-- these are global... can't currently override per index -->
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<!-- lucene options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- for better multi-segment testing, we are using slower
indexing properties of maxBufferedDocs=10 and LogDocMergePolicy.
-->
<maxBufferedDocs>10</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<mergePolicy>org.apache.lucene.index.LogDocMergePolicy</mergePolicy>
<mergeScheduler>org.apache.lucene.index.SerialMergeScheduler</mergeScheduler>
<unlockOnStartup>true</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2">
<!-- autocommit pending docs if certain criteria are met
<autoCommit>
<maxDocs>10000</maxDocs>
<maxTime>3600000</maxTime>
</autoCommit>
-->
<!-- represents a lower bound on the frequency that commits may
occur (in seconds). NOTE: not yet implemented
<commitIntervalLowerBound>0</commitIntervalLowerBound>
-->
<!-- The RunExecutableListener executes an external command.
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=nothing
env - environment variables to set. default=nothing
-->
<!-- A postCommit event is fired after every commit
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">/var/opt/resin3/__PORT__/scripts/solr/snapshooter</str>
<str name="dir">/var/opt/resin3/__PORT__</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>
<query>
<!-- Maximum number of clauses in a boolean query... can affect
range or wildcard queries that expand to big boolean
queries. An exception is thrown if exceeded.
-->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- Cache specification for Filters or DocSets - unordered set of *all* documents
that match a particular query.
-->
<filterCache
class="solr.search.FastLRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<queryResultCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="1024"/>
<documentCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- If true, stored fields that are not requested will be loaded lazily.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!--
<cache name="myUserCache"
class="solr.search.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="MyRegenerator"
/>
-->
<!--
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<queryResultWindowSize>10</queryResultWindowSize>
<!-- set maxSize artificially low to exercise both types of sets -->
<HashDocSet maxSize="3" loadFactor="0.75"/>
<!-- boolToFilterOptimizer converts boolean clauses with zero boost
into cached filters if the number of docs selected by the clause exceeds
the threshold (represented as a fraction of the total index)
-->
<boolTofilterOptimizer enabled="false" cacheSize="32" threshold=".05"/>
<!-- a newSearcher event is fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka registered). -->
<!-- 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="start">0</str> <str name="rows">10</str> </lst>
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
<!-- a firstSearcher event is fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain prewarming data from. -->
<!--
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
</query>
<!-- An alternate set representation that uses an integer hash to store filters (sets of docids).
If the set cardinality <= maxSize elements, then HashDocSet will be used instead of the bitset
based HashBitset. -->
<!-- requestHandler plugins... incoming queries will be dispatched to the
correct handler based on the qt (query type) param matching the
name of registered handlers.
The "standard" request handler is the default and will be used if qt
is not specified in the request.
-->
<requestHandler name="standard" class="solr.StandardRequestHandler">
<bool name="httpCaching">true</bool>
</requestHandler>
<requestHandler name="dismaxOldStyleDefaults"
class="solr.DisMaxRequestHandler" >
<!-- for historic reasons, DisMaxRequestHandler will use all of
it's init params as "defaults" if there is no "defaults" list
specified
-->
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</requestHandler>
<requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
<lst name="defaults">
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</lst>
</requestHandler>
<requestHandler name="old" class="solr.tst.OldRequestHandler" >
<int name="myparam">1000</int>
<float name="ratio">1.4142135</float>
<arr name="myarr"><int>1</int><int>2</int></arr>
<str>foo</str>
</requestHandler>
<requestHandler name="oldagain" class="solr.tst.OldRequestHandler" >
<lst name="lst1"> <str name="op">sqrt</str> <int name="val">2</int> </lst>
<lst name="lst2"> <str name="op">log</str> <float name="val">10</float> </lst>
</requestHandler>
<requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
<requestHandler name="test" class="solr.tst.TestRequestHandler" />
<!-- test query parameter defaults -->
<requestHandler name="defaults" class="solr.StandardRequestHandler">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<!-- test query parameter defaults -->
<requestHandler name="lazy" class="solr.StandardRequestHandler" startup="lazy">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
<requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy">
<bool name="httpCaching">false</bool>
</requestHandler>
<searchComponent name="spellcheck" class="org.apache.solr.handler.component.SpellCheckComponent">
<str name="queryAnalyzerFieldType">lowerfilt</str>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">lowerfilt</str>
<str name="spellcheckIndexDir">spellchecker1</str>
<str name="buildOnCommit">true</str>
</lst>
<!-- Example of using different distance measure -->
<lst name="spellchecker">
<str name="name">jarowinkler</str>
<str name="field">lowerfilt</str>
<!-- Use a different Distance Measure -->
<str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
<str name="spellcheckIndexDir">spellchecker2</str>
</lst>
<lst name="spellchecker">
<str name="classname">solr.FileBasedSpellChecker</str>
<str name="name">external</str>
<str name="sourceLocation">spellings.txt</str>
<str name="characterEncoding">UTF-8</str>
<str name="spellcheckIndexDir">spellchecker3</str>
</lst>
</searchComponent>
<searchComponent name="termsComp" class="org.apache.solr.handler.component.TermsComponent"/>
<requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
<arr name="components">
<str>termsComp</str>
</arr>
</requestHandler>
<!--
The SpellingQueryConverter to convert raw (CommonParams.Q) queries into tokens. Uses a simple regular expression
to strip off field markup, boosts, ranges, etc. but it is not guaranteed to match an exact parse from the query parser.
-->
<queryConverter name="queryConverter" class="org.apache.solr.spelling.SpellingQueryConverter"/>
<requestHandler name="spellCheckCompRH" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<!-- omp = Only More Popular -->
<str name="spellcheck.onlyMorePopular">false</str>
<!-- exr = Extended Results -->
<str name="spellcheck.extendedResults">false</str>
<!-- The number of suggestions to return -->
<str name="spellcheck.count">1</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
<requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
</lst>
<arr name="last-components">
<str>tvComponent</str>
</arr>
</requestHandler>
<searchComponent class="solr.HighlightComponent" name="highlight">
<highlighting>
<!-- Configure the standard fragmenter -->
<fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
<lst name="defaults">
<int name="hl.fragsize">70</int>
</lst>
</fragmenter>
<!-- Configure the standard formatter -->
<formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
</highlighting>
</searchComponent>
<!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
<requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
</requestDispatcher>
<admin>
<defaultQuery>solr</defaultQuery>
<gettableFiles>solrconfig.xml scheam.xml admin-extra.html</gettableFiles>
</admin>
<!-- test getting system property -->
<propTest attr1="${solr.test.sys.prop1}-$${literal}"
attr2="${non.existent.sys.prop:default-from-config}">prefix-${solr.test.sys.prop2}-suffix</propTest>
<queryParser name="foo" class="FooQParserPlugin"/>
<updateRequestProcessorChain name="dedupe">
<processor class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
<bool name="enabled">false</bool>
<bool name="overwriteDupes">true</bool>
<str name="fields">v_t,t_field</str>
<str name="signatureClass">org.apache.solr.update.processor.TextProfileSignature</str>
</processor>
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
</config>

940
solr/src/test/test-files/solr/conf/solrconfig-propinject.xml
View File

@ -1,470 +1,470 @@
<?xml version="1.0" ?>
<!--
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.
-->
<!-- $Id: solrconfig.xml 382610 2006-03-03 01:43:03Z yonik $
$Source$
$Name$
This is a "kitchen sink" config file that tests can use.
When writting a new test, feel free to add *new* items (plugins,
config options, etc...) as long as they don't break any existing
tests. if you need to test something esoteric please add a new
"solrconfig-your-esoteric-purpose.xml" config file.
Note in particular that this test is used by MinimalSchemaTest so
Anything added to this file needs to work correctly even if there
is now uniqueKey or defaultSearch Field.
-->
<config>
<jmx />
<!-- Used to specify an alternate directory to hold all index data.
It defaults to "index" if not present, and should probably
not be changed if replication is in use. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<!-- The DirectoryFactory to use for indexes.
solr.StandardDirectoryFactory, the default, is filesystem based.
solr.RAMDirectoryFactory is memory based and not persistent. -->
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
<indexDefaults>
<!-- Values here affect all index writers and act as a default
unless overridden. -->
<!-- Values here affect all index writers and act as a default unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<!-- Tell Lucene when to flush documents to disk.
Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!--
Expert: Turn on Lucene's auto commit capability.
NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
-->
<luceneAutoCommit>false</luceneAutoCommit>
<!--
Expert:
The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
versions used LogDocMergePolicy.
LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when
to merge based on number of documents
Other implementations of MergePolicy must have a no-argument constructor
-->
<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy">
<double name="maxMergeMB">64.0</double>
</mergePolicy>
<!--
Expert:
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">
<int name="maxThreadCount">2</int>
</mergeScheduler>
<!-- these are global... can't currently override per index -->
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<!-- lucene options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- for better multi-segment testing, we are using slower
indexing properties of maxBufferedDocs=10 and LogDocMergePolicy.
-->
<maxBufferedDocs>10</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy">
<double name="maxMergeMB">64.0</double>
</mergePolicy>
<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler">
<int name="maxThreadCount">2</int>
</mergeScheduler>
<unlockOnStartup>true</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2">
<!-- autocommit pending docs if certain criteria are met
<autoCommit>
<maxDocs>10000</maxDocs>
<maxTime>3600000</maxTime>
</autoCommit>
-->
<!-- represents a lower bound on the frequency that commits may
occur (in seconds). NOTE: not yet implemented
<commitIntervalLowerBound>0</commitIntervalLowerBound>
-->
<!-- The RunExecutableListener executes an external command.
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=nothing
env - environment variables to set. default=nothing
-->
<!-- A postCommit event is fired after every commit
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">/var/opt/resin3/__PORT__/scripts/solr/snapshooter</str>
<str name="dir">/var/opt/resin3/__PORT__</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>
<query>
<!-- Maximum number of clauses in a boolean query... can affect
range or wildcard queries that expand to big boolean
queries. An exception is thrown if exceeded.
-->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- Cache specification for Filters or DocSets - unordered set of *all* documents
that match a particular query.
-->
<filterCache
class="solr.search.FastLRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<queryResultCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="1024"/>
<documentCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- If true, stored fields that are not requested will be loaded lazily.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!--
<cache name="myUserCache"
class="solr.search.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="MyRegenerator"
/>
-->
<!--
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<queryResultWindowSize>10</queryResultWindowSize>
<!-- set maxSize artificially low to exercise both types of sets -->
<HashDocSet maxSize="3" loadFactor="0.75"/>
<!-- boolToFilterOptimizer converts boolean clauses with zero boost
into cached filters if the number of docs selected by the clause exceeds
the threshold (represented as a fraction of the total index)
-->
<boolTofilterOptimizer enabled="false" cacheSize="32" threshold=".05"/>
<!-- a newSearcher event is fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka registered). -->
<!-- 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="start">0</str> <str name="rows">10</str> </lst>
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
<!-- a firstSearcher event is fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain prewarming data from. -->
<!--
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
</query>
<!-- An alternate set representation that uses an integer hash to store filters (sets of docids).
If the set cardinality <= maxSize elements, then HashDocSet will be used instead of the bitset
based HashBitset. -->
<!-- requestHandler plugins... incoming queries will be dispatched to the
correct handler based on the qt (query type) param matching the
name of registered handlers.
The "standard" request handler is the default and will be used if qt
is not specified in the request.
-->
<requestHandler name="standard" class="solr.StandardRequestHandler">
<bool name="httpCaching">true</bool>
</requestHandler>
<requestHandler name="dismaxOldStyleDefaults"
class="solr.DisMaxRequestHandler" >
<!-- for historic reasons, DisMaxRequestHandler will use all of
it's init params as "defaults" if there is no "defaults" list
specified
-->
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</requestHandler>
<requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
<lst name="defaults">
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</lst>
</requestHandler>
<requestHandler name="old" class="solr.tst.OldRequestHandler" >
<int name="myparam">1000</int>
<float name="ratio">1.4142135</float>
<arr name="myarr"><int>1</int><int>2</int></arr>
<str>foo</str>
</requestHandler>
<requestHandler name="oldagain" class="solr.tst.OldRequestHandler" >
<lst name="lst1"> <str name="op">sqrt</str> <int name="val">2</int> </lst>
<lst name="lst2"> <str name="op">log</str> <float name="val">10</float> </lst>
</requestHandler>
<requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
<requestHandler name="test" class="solr.tst.TestRequestHandler" />
<!-- test query parameter defaults -->
<requestHandler name="defaults" class="solr.StandardRequestHandler">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<!-- test query parameter defaults -->
<requestHandler name="lazy" class="solr.StandardRequestHandler" startup="lazy">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
<requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy">
<bool name="httpCaching">false</bool>
</requestHandler>
<searchComponent name="spellcheck" class="org.apache.solr.handler.component.SpellCheckComponent">
<str name="queryAnalyzerFieldType">lowerfilt</str>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">lowerfilt</str>
<str name="spellcheckIndexDir">spellchecker1</str>
<str name="buildOnCommit">true</str>
</lst>
<!-- Example of using different distance measure -->
<lst name="spellchecker">
<str name="name">jarowinkler</str>
<str name="field">lowerfilt</str>
<!-- Use a different Distance Measure -->
<str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
<str name="spellcheckIndexDir">spellchecker2</str>
</lst>
<lst name="spellchecker">
<str name="classname">solr.FileBasedSpellChecker</str>
<str name="name">external</str>
<str name="sourceLocation">spellings.txt</str>
<str name="characterEncoding">UTF-8</str>
<str name="spellcheckIndexDir">spellchecker3</str>
</lst>
</searchComponent>
<searchComponent name="termsComp" class="org.apache.solr.handler.component.TermsComponent"/>
<requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
<arr name="components">
<str>termsComp</str>
</arr>
</requestHandler>
<!--
The SpellingQueryConverter to convert raw (CommonParams.Q) queries into tokens. Uses a simple regular expression
to strip off field markup, boosts, ranges, etc. but it is not guaranteed to match an exact parse from the query parser.
-->
<queryConverter name="queryConverter" class="org.apache.solr.spelling.SpellingQueryConverter"/>
<requestHandler name="spellCheckCompRH" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<!-- omp = Only More Popular -->
<str name="spellcheck.onlyMorePopular">false</str>
<!-- exr = Extended Results -->
<str name="spellcheck.extendedResults">false</str>
<!-- The number of suggestions to return -->
<str name="spellcheck.count">1</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
<requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
</lst>
<arr name="last-components">
<str>tvComponent</str>
</arr>
</requestHandler>
<searchComponent class="solr.HighlightComponent" name="highlight">
<highlighting>
<!-- Configure the standard fragmenter -->
<fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
<lst name="defaults">
<int name="hl.fragsize">70</int>
</lst>
</fragmenter>
<!-- Configure the standard formatter -->
<formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
</highlighting>
</searchComponent>
<!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
<requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
</requestDispatcher>
<admin>
<defaultQuery>solr</defaultQuery>
<gettableFiles>solrconfig.xml scheam.xml admin-extra.html</gettableFiles>
</admin>
<!-- test getting system property -->
<propTest attr1="${solr.test.sys.prop1}-$${literal}"
attr2="${non.existent.sys.prop:default-from-config}">prefix-${solr.test.sys.prop2}-suffix</propTest>
<queryParser name="foo" class="FooQParserPlugin"/>
<updateRequestProcessorChain name="dedupe">
<processor class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
<bool name="enabled">false</bool>
<bool name="overwriteDupes">true</bool>
<str name="fields">v_t,t_field</str>
<str name="signatureClass">org.apache.solr.update.processor.TextProfileSignature</str>
</processor>
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
</config>
<?xml version="1.0" ?>
<!--
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.
-->
<!-- $Id: solrconfig.xml 382610 2006-03-03 01:43:03Z yonik $
$Source$
$Name$
This is a "kitchen sink" config file that tests can use.
When writting a new test, feel free to add *new* items (plugins,
config options, etc...) as long as they don't break any existing
tests. if you need to test something esoteric please add a new
"solrconfig-your-esoteric-purpose.xml" config file.
Note in particular that this test is used by MinimalSchemaTest so
Anything added to this file needs to work correctly even if there
is now uniqueKey or defaultSearch Field.
-->
<config>
<jmx />
<!-- Used to specify an alternate directory to hold all index data.
It defaults to "index" if not present, and should probably
not be changed if replication is in use. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<!-- The DirectoryFactory to use for indexes.
solr.StandardDirectoryFactory, the default, is filesystem based.
solr.RAMDirectoryFactory is memory based and not persistent. -->
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
<indexDefaults>
<!-- Values here affect all index writers and act as a default
unless overridden. -->
<!-- Values here affect all index writers and act as a default unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<!-- Tell Lucene when to flush documents to disk.
Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!--
Expert: Turn on Lucene's auto commit capability.
NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
-->
<luceneAutoCommit>false</luceneAutoCommit>
<!--
Expert:
The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
versions used LogDocMergePolicy.
LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when
to merge based on number of documents
Other implementations of MergePolicy must have a no-argument constructor
-->
<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy">
<double name="maxMergeMB">64.0</double>
</mergePolicy>
<!--
Expert:
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">
<int name="maxThreadCount">2</int>
</mergeScheduler>
<!-- these are global... can't currently override per index -->
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<!-- lucene options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- for better multi-segment testing, we are using slower
indexing properties of maxBufferedDocs=10 and LogDocMergePolicy.
-->
<maxBufferedDocs>10</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy">
<double name="maxMergeMB">64.0</double>
</mergePolicy>
<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler">
<int name="maxThreadCount">2</int>
</mergeScheduler>
<unlockOnStartup>true</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2">
<!-- autocommit pending docs if certain criteria are met
<autoCommit>
<maxDocs>10000</maxDocs>
<maxTime>3600000</maxTime>
</autoCommit>
-->
<!-- represents a lower bound on the frequency that commits may
occur (in seconds). NOTE: not yet implemented
<commitIntervalLowerBound>0</commitIntervalLowerBound>
-->
<!-- The RunExecutableListener executes an external command.
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=nothing
env - environment variables to set. default=nothing
-->
<!-- A postCommit event is fired after every commit
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">/var/opt/resin3/__PORT__/scripts/solr/snapshooter</str>
<str name="dir">/var/opt/resin3/__PORT__</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>
<query>
<!-- Maximum number of clauses in a boolean query... can affect
range or wildcard queries that expand to big boolean
queries. An exception is thrown if exceeded.
-->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- Cache specification for Filters or DocSets - unordered set of *all* documents
that match a particular query.
-->
<filterCache
class="solr.search.FastLRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<queryResultCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="1024"/>
<documentCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- If true, stored fields that are not requested will be loaded lazily.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!--
<cache name="myUserCache"
class="solr.search.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="MyRegenerator"
/>
-->
<!--
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<queryResultWindowSize>10</queryResultWindowSize>
<!-- set maxSize artificially low to exercise both types of sets -->
<HashDocSet maxSize="3" loadFactor="0.75"/>
<!-- boolToFilterOptimizer converts boolean clauses with zero boost
into cached filters if the number of docs selected by the clause exceeds
the threshold (represented as a fraction of the total index)
-->
<boolTofilterOptimizer enabled="false" cacheSize="32" threshold=".05"/>
<!-- a newSearcher event is fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka registered). -->
<!-- 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="start">0</str> <str name="rows">10</str> </lst>
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
<!-- a firstSearcher event is fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain prewarming data from. -->
<!--
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
</query>
<!-- An alternate set representation that uses an integer hash to store filters (sets of docids).
If the set cardinality <= maxSize elements, then HashDocSet will be used instead of the bitset
based HashBitset. -->
<!-- requestHandler plugins... incoming queries will be dispatched to the
correct handler based on the qt (query type) param matching the
name of registered handlers.
The "standard" request handler is the default and will be used if qt
is not specified in the request.
-->
<requestHandler name="standard" class="solr.StandardRequestHandler">
<bool name="httpCaching">true</bool>
</requestHandler>
<requestHandler name="dismaxOldStyleDefaults"
class="solr.DisMaxRequestHandler" >
<!-- for historic reasons, DisMaxRequestHandler will use all of
it's init params as "defaults" if there is no "defaults" list
specified
-->
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</requestHandler>
<requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
<lst name="defaults">
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</lst>
</requestHandler>
<requestHandler name="old" class="solr.tst.OldRequestHandler" >
<int name="myparam">1000</int>
<float name="ratio">1.4142135</float>
<arr name="myarr"><int>1</int><int>2</int></arr>
<str>foo</str>
</requestHandler>
<requestHandler name="oldagain" class="solr.tst.OldRequestHandler" >
<lst name="lst1"> <str name="op">sqrt</str> <int name="val">2</int> </lst>
<lst name="lst2"> <str name="op">log</str> <float name="val">10</float> </lst>
</requestHandler>
<requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
<requestHandler name="test" class="solr.tst.TestRequestHandler" />
<!-- test query parameter defaults -->
<requestHandler name="defaults" class="solr.StandardRequestHandler">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<!-- test query parameter defaults -->
<requestHandler name="lazy" class="solr.StandardRequestHandler" startup="lazy">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
<requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy">
<bool name="httpCaching">false</bool>
</requestHandler>
<searchComponent name="spellcheck" class="org.apache.solr.handler.component.SpellCheckComponent">
<str name="queryAnalyzerFieldType">lowerfilt</str>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">lowerfilt</str>
<str name="spellcheckIndexDir">spellchecker1</str>
<str name="buildOnCommit">true</str>
</lst>
<!-- Example of using different distance measure -->
<lst name="spellchecker">
<str name="name">jarowinkler</str>
<str name="field">lowerfilt</str>
<!-- Use a different Distance Measure -->
<str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
<str name="spellcheckIndexDir">spellchecker2</str>
</lst>
<lst name="spellchecker">
<str name="classname">solr.FileBasedSpellChecker</str>
<str name="name">external</str>
<str name="sourceLocation">spellings.txt</str>
<str name="characterEncoding">UTF-8</str>
<str name="spellcheckIndexDir">spellchecker3</str>
</lst>
</searchComponent>
<searchComponent name="termsComp" class="org.apache.solr.handler.component.TermsComponent"/>
<requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
<arr name="components">
<str>termsComp</str>
</arr>
</requestHandler>
<!--
The SpellingQueryConverter to convert raw (CommonParams.Q) queries into tokens. Uses a simple regular expression
to strip off field markup, boosts, ranges, etc. but it is not guaranteed to match an exact parse from the query parser.
-->
<queryConverter name="queryConverter" class="org.apache.solr.spelling.SpellingQueryConverter"/>
<requestHandler name="spellCheckCompRH" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<!-- omp = Only More Popular -->
<str name="spellcheck.onlyMorePopular">false</str>
<!-- exr = Extended Results -->
<str name="spellcheck.extendedResults">false</str>
<!-- The number of suggestions to return -->
<str name="spellcheck.count">1</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
<requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
</lst>
<arr name="last-components">
<str>tvComponent</str>
</arr>
</requestHandler>
<searchComponent class="solr.HighlightComponent" name="highlight">
<highlighting>
<!-- Configure the standard fragmenter -->
<fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
<lst name="defaults">
<int name="hl.fragsize">70</int>
</lst>
</fragmenter>
<!-- Configure the standard formatter -->
<formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
</highlighting>
</searchComponent>
<!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
<requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
</requestDispatcher>
<admin>
<defaultQuery>solr</defaultQuery>
<gettableFiles>solrconfig.xml scheam.xml admin-extra.html</gettableFiles>
</admin>
<!-- test getting system property -->
<propTest attr1="${solr.test.sys.prop1}-$${literal}"
attr2="${non.existent.sys.prop:default-from-config}">prefix-${solr.test.sys.prop2}-suffix</propTest>
<queryParser name="foo" class="FooQParserPlugin"/>
<updateRequestProcessorChain name="dedupe">
<processor class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
<bool name="enabled">false</bool>
<bool name="overwriteDupes">true</bool>
<str name="fields">v_t,t_field</str>
<str name="signatureClass">org.apache.solr.update.processor.TextProfileSignature</str>
</processor>
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
</config>