solr入门之suggest系统架构搭建

1.系统使用 SSM 来搭建  使用maven和svn用来管理jar和版本控制

2.架构搭建--

1.maven的配置文件导入jar包依赖和文件资源管理

2.配置web.xml加载spring相关的配置文件

3.配置spring相关的配置 springmvc 数据连接 及 事务处理(solr用不到)

4.配置相关工具类
   AOP切面日志工具类---见以前的 博客
http://blog.csdn.net/sqh201030412/article/details/50916179

返回结果工具类

package cn.com.mx.gome.search.core.common;import java.io.Serializable;import com.alibaba.fastjson.annotation.JSONField;/** * 统一结果返回类 * @author songqinghu * * @param <T> */public class ResultData<T> implements Serializable {    private static final long serialVersionUID = 1L;    /**     * 处理结果     */    @JSONField(ordinal = 1)    private Boolean success = true;    /**     * 响应码：200为成功，其他：失败（六位数正整形） 默认SUCCESS     */    @JSONField(ordinal = 2)    private int code = 200;    /**     * 响应信息，默认SUCCESS_MSG     */    @JSONField(ordinal = 4)    private String message;        @JSONField(ordinal = 3)    private Long totalCount;    /**     * 返回数据, 如果没有返回数据时，可定义为String类型，赋予""空值     */    @JSONField(ordinal = 5)    private T data;    public ResultData() {    }    public ResultData(Boolean success, int code, String message, T data) {        this.success = success;        this.code = code;        this.message = message;        this.data = data;    }    public Boolean getSuccess() {        return success;    }    public void setSuccess(Boolean success) {        this.success = success;    }    public int getCode() {        return code;    }    public void setCode(int code) {        this.code = code;    }    public String getMessage() {        return message;    }    public void setMessage(String message) {        this.message = message;    }    public T getData() {        return data;    }    public void setData(T data) {        this.data = data;    }    public Long getTotalCount() {        return totalCount;    }    public void setTotalCount(Long totalCount) {        this.totalCount = totalCount;    }}

properties文件加载

package cn.com.mx.gome.search.core.util.prop;import java.io.File;import java.io.FileInputStream;import java.io.InputStream;import java.util.Iterator;import java.util.List;import java.util.concurrent.ConcurrentHashMap;import java.util.concurrent.ConcurrentMap;import org.apache.commons.configuration.PropertiesConfiguration;import org.apache.commons.configuration.reloading.FileChangedReloadingStrategy;import org.apache.log4j.Logger;public class Property {    private static final Logger logger = Logger.getLogger(Property.class);    private final byte[] lock = new byte[0];    private ConcurrentMap<String, PropertiesConfiguration> configMap = new ConcurrentHashMap<String, PropertiesConfiguration>();    private String dir;    private String filename;    private boolean isChange = true;    protected void setDir(String dir) {        this.dir = dir;    }    protected void setFilename(String filename) {        this.filename = filename;    }    protected void setChange(boolean isChange) {        this.isChange = isChange;    }    private PropertiesConfiguration loadConfig(String configFile) {        PropertiesConfiguration config = configMap.get(configFile);        if (config == null) {            synchronized (lock) {                try {                    config = new PropertiesConfiguration();                    config.setListDelimiter((char) 0);                    if (isChange) {                        // 可以自动更新                        config.load(new File(configFile));                        config.setReloadingStrategy(new FileChangedReloadingStrategy());                    } else {                        config.load(new FileInputStream(configFile));                    }                    configMap.put(configFile, config);                } catch (Exception e) {                    logger.error("load config error: " + e);                }            }        }        return config;    }    private PropertiesConfiguration loadConfig(ClassLoader classLoader, String configFile) {        PropertiesConfiguration config = configMap.get(configFile);        if (config == null) {            synchronized (lock) {                try {                    InputStream inputStream = classLoader.getResourceAsStream(configFile);                    config = new PropertiesConfiguration();                    config.setListDelimiter((char) 0);                    config.load(inputStream);                    configMap.put(configFile, config);                } catch (Exception e) {                    logger.error("load config error: " + e);                }            }        }        return config;    }    private String path(String configFile) {        return dir + configFile;    }    /**     * 默认classes下面的config.properties     *      * @param key     * @return     */    public String get(String key) {        return get(filename, key);    }    /**     * classes下面指定的configFile     *      * @param configFile 配置文件名     * @param key     * @return     */    public String get(String configFile, String key) {        PropertiesConfiguration config = loadConfig(path(configFile));        try {            return config.getString(key);        } catch (Exception e) {            return null;        }    }    /**     * 指定jar包中的configFile     *      * @param classLoader 指定jar包的类加载器     * @param configFile 配置文件名     * @param key     * @return     */    public String get(ClassLoader classLoader, String configFile, String key) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        try {            return config.getString(key);        } catch (Exception e) {            return null;        }    }    public String getString(String key, String defaultValue) {        return getString(filename, key, defaultValue);    }    public String getString(String configFile, String key, String defaultValue) {        PropertiesConfiguration config = loadConfig(path(configFile));        return config.getString(key, defaultValue);    }    public String getString(ClassLoader classLoader, String configFile, String key, String defaultValue) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        return config.getString(key, defaultValue);    }    public int getInt(String key, int defaultValue) {        return getInt(filename, key, defaultValue);    }    public int getInt(String configFile, String key, int defaultValue) {        PropertiesConfiguration config = loadConfig(path(configFile));        try {            return config.getInt(key);        } catch (Exception e) {            return defaultValue;        }    }    public int getInt(ClassLoader classLoader, String configFile, String key, int defaultValue) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        try {            return config.getInt(key);        } catch (Exception e) {            return defaultValue;        }    }    public float getFloat(String key, float defaultValue) {        return getFloat(filename, key, defaultValue);    }    public float getFloat(String configFile, String key, float defaultValue) {        PropertiesConfiguration config = loadConfig(path(configFile));        try {            return config.getFloat(key);        } catch (Exception e) {            return defaultValue;        }    }    public float getFloat(ClassLoader classLoader, String configFile, String key, float defaultValue) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        try {            return config.getFloat(key);        } catch (Exception e) {            return defaultValue;        }    }    public long getLong(String key, long defaultValue) {        return getLong(filename, key, defaultValue);    }    public long getLong(String configFile, String key, long defaultValue) {        PropertiesConfiguration config = loadConfig(path(configFile));        try {            return config.getLong(key);        } catch (Exception e) {            return defaultValue;        }    }    public long getLong(ClassLoader classLoader, String configFile, String key, long defaultValue) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        try {            return config.getLong(key);        } catch (Exception e) {            return defaultValue;        }    }    public boolean getBoolean(String key, boolean defaultValue) {        return getBoolean(filename, key, defaultValue);    }    public boolean getBoolean(String configFile, String key, boolean defaultValue) {        PropertiesConfiguration config = loadConfig(path(configFile));        try {            return config.getBoolean(key);        } catch (Exception e) {            return defaultValue;        }    }    public boolean getBoolean(ClassLoader classLoader, String configFile, String key, boolean defaultValue) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        try {            return config.getBoolean(key);        } catch (Exception e) {            return defaultValue;        }    }    public List<?> getList(String key) {        return getList(filename, key);    }    public List<?> getList(String configFile, String key) {        PropertiesConfiguration config = loadConfig(path(configFile));        try {            return config.getList(key);        } catch (Exception e) {            return null;        }    }    public List<?> getList(ClassLoader classLoader, String configFile, String key) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        try {            return config.getList(key);        } catch (Exception e) {            return null;        }    }    /**     * {@inheritDoc} This implementation returns keys that either match the     * prefix or start with the prefix followed by a dot ('.'). So the call     * {@code getKeys("db");} will find the keys {@code db}, {@code db.user}, or     * {@code db.password}, but not the key {@code dbdriver}.     */    public Iterator<String> getKeys(String prefix) {        return getKeys(filename, prefix);    }    public Iterator<String> getKeys(String configFile, String prefix) {        PropertiesConfiguration config = loadConfig(path(configFile));        try {            return config.getKeys(prefix);        } catch (Exception e) {            return null;        }    }    public Iterator<String> getKeys(ClassLoader classLoader, String configFile, String prefix) {        PropertiesConfiguration config = loadConfig(classLoader, configFile);        try {            return config.getKeys(prefix);        } catch (Exception e) {            return null;        }    }}

package cn.com.mx.gome.search.core.util.prop;import java.net.URL;import java.util.Properties;/** * properties文件处理工具类 * @author songqinghu * */public class PropUtils extends Property {    //配置文件名称    private final static String _default = "config/config.properties";        private PropUtils(){        this(true);    }    public PropUtils(boolean isChange) {                URL url = PropUtils.class.getResource("/");                if(url != null){            setDir(url.getPath());        }        setFilename(_default);        setChange(isChange);    }        /**     * 获取默认的自动加载配置文件工具类实例     */    public static PropUtils getInstance() {        return Creater.changePropUtil;    }    /**     * 获取静态的配置文件工具类实例，不自动加载     */    public static PropUtils getUnChangeInstance() {        return Creater.unchangePropUtil;    }        private static class Creater{        public static final PropUtils changePropUtil = new PropUtils();        public static final PropUtils unchangePropUtil = new PropUtils(false);    }    }

常量配置类

package cn.com.mx.gome.suggest.constant;public final class Const {    public static final String SOLR_ZK_URL = "solr.zk.url";    public static final String SOLR_COLLECTIONS = "solr.collections";    public static final String INDEX_FULL_LIMIT_GROUP = "index.full.limit.group";    public static final String INDEX_FULL_LIMIT_USER = "index.full.limit.user";    public static final String INDEX_FULL_LIMIT_TOPIC = "index.full.limit.topic";    public static final String INDEZ_FULL_THREAD_MAX = "index.full.thread.max";//线程数大小    /**     * `expert_audit_status` tinyint(1) DEFAULT '0' COMMENT '达人审核状态     * 0表示未审核，1表示审核中，2表示审核成功，3表示审核失败',     */    public static final String USER_STATUS_V = "2";}

solr客户端初始化获取类

package cn.com.mx.gome.suggest.solr.init;import java.util.Map;import java.util.concurrent.ConcurrentHashMap;import javax.annotation.PostConstruct;import org.apache.commons.lang3.StringUtils;import org.apache.solr.client.solrj.SolrClient;import org.slf4j.Logger;import org.slf4j.LoggerFactory;import org.springframework.stereotype.Component;import org.springframework.stereotype.Service;import cn.com.mx.gome.search.core.util.prop.PropUtils;import cn.com.mx.gome.suggest.constant.Const;import cn.com.mx.gome.suggest.solr.SolrServiceWrapper;import cn.com.mx.gome.suggest.solr.connect.SolrClientConnect;/** * solr连接客户端初始化类 * @author songqinghu * */@Servicepublic class SolrServiceWrapperImpl implements SolrServiceWrapper {    private final Logger logger = LoggerFactory.getLogger(SolrServiceWrapperImpl.class);        private static  Map<String,SolrClient> solrClients= new  ConcurrentHashMap<String, SolrClient>();        @PostConstruct//类初始化后执行此方法    @Override    public Map<String, SolrClient> initSolrClient() {                //获取zk地址        String zkUrl = PropUtils.getInstance().get(Const.SOLR_ZK_URL);        System.out.println(zkUrl);        //获取collection名称 ,为切割符        String[] collectionNames = PropUtils.getInstance().get(Const.SOLR_COLLECTIONS).split(",");        //循环创建solr连接客户端存入map中        for (String name : collectionNames) {            solrClients.put(name, SolrClientConnect.getCloudSolrClient(zkUrl, name));        }        logger.info(collectionNames + " init,load solr client from zk = " + zkUrl);        return solrClients;    }    //获取指定的collection连接    @Override    public SolrClient getCollection(String name) {        SolrClient client = null;        if(solrClients !=null && solrClients.size()>0){            if(StringUtils.isNotBlank(name))                client = solrClients.get(name);        }        if(client == null) //没有获取到连接             throw  new RuntimeException("the solrClient init fail");        return client;    }}

package cn.com.mx.gome.suggest.solr.connect;import org.apache.solr.client.solrj.SolrClient;import org.apache.solr.client.solrj.impl.CloudSolrClient;import org.apache.solr.client.solrj.impl.HttpSolrClient;import cn.com.mx.gome.search.core.common.ESystemDefaultHttpClient;/** * 获取solr的客户端--集群连接 或者单机连接 * @author songqinghu * */public class SolrClientConnect {    //获取集群 方式的solr连接     public static SolrClient  getCloudSolrClient(String zkUrl,String name){                ESystemDefaultHttpClient httpClient = new ESystemDefaultHttpClient(200, 2000);                CloudSolrClient cloudSolrClient = new  CloudSolrClient(zkUrl, httpClient);                cloudSolrClient.setDefaultCollection(name);                cloudSolrClient.connect();                return cloudSolrClient;    }    //获取单机版 solr连接    public static SolrClient getSolrClient(String baseUrl,String name){        ESystemDefaultHttpClient client = new ESystemDefaultHttpClient(200, 2000);        HttpSolrClient solrClient = new HttpSolrClient(baseUrl+"/"+name, client);        return solrClient;    }        }

5.编写测试controller使用maven启动项目 访问观察项目是否成功,不成功根据报错解决问题

6.solr的collection的配置文件设置

公司的solr现在使用的是solrcloud的方式  只需要配置schema.xml和solrcofig.xml文件就可以了

分析思考---本索引库主要是用于搜索建议使用的 字段不需要考虑分词的问题,主要涉及的字段有

suggestId: 唯一标识

word:原始输入词

all_py:全程拼音   多值

short_py:首字母拼音  多值

type: 索引来源类别 (商品,店铺,人名,圈子名....)

count: 词语出现次数

all_text: 原始次 拼音 短拼 复制字段  多值  默认搜索域

createTime: 创建时间

-----------------------------------

schema.xml

<?xml version="1.0" encoding="UTF-8" ?><schema name="meixin_group" version="1.5">    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" />    <fieldType name="int" class="solr.TrieIntField" sortMissingLast="true" precisionStep="0" positionIncrementGap="0" />    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0" />    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0" />    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0" />    <fieldType name="tint" class="solr.TrieIntField" sortMissingLast="true" precisionStep="8" positionIncrementGap="0" />    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0" />    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0" />    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0" />    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0" />    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0" />    <fieldType name="random" class="solr.RandomSortField" indexed="true" />    <fieldType name="mmseg_text" class="solr.TextField">        <analyzer type="index">            <tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="max-word" dicPath="/usr/local/mmseg_dic" />        </analyzer>        <analyzer type="query">            <tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="max-word" dicPath="/usr/local/mmseg_dic" />        </analyzer>    </fieldType>    <fieldtype name="ng1_1" class="solr.TextField" positionIncrementGap="100">        <analyzer>            <tokenizer class="solr.NGramTokenizerFactory" minGramSize="1" maxGramSize="1"/>            <filter class="solr.LowerCaseFilterFactory"/>        </analyzer>  </fieldtype>    <field name="suggestId" type="string" indexed="true" stored="true" required="true" />    <field name="word" type="string" indexed="true" stored="true" />    <field name="all_py" type="string" indexed="true" stored="true" />    <field name="short_py" type="string" indexed="true" stored="true" />    <field name="type" type="string" indexed="true" stored="true" />    <field name="count" type="long" indexed="true" stored="true" />    <field name="suggest" type="string" indexed="true" stored="false" />    <field name="_version_" type="long" indexed="true" stored="true" />    <copyField source="word" dest="suggest"/>     <copyField source="all_py" dest="suggest"/>      <copyField source="short_py" dest="suggest"/>     <uniqueKey>suggestId</uniqueKey>    <defaultSearchField>suggest</defaultSearchField>    <solrQueryParser defaultOperator="AND" /></schema>solrcofig.xml<?xml version="1.0" encoding="UTF-8" ?><!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements.  See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to You under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License.  You may obtain a copy of the License at     http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.--><!--      For more details about configurations options that may appear in     this file, see http://wiki.apache.org/solr/SolrConfigXml. --><config>  <!-- In all configuration below, a prefix of "solr." for class names       is an alias that causes solr to search appropriate packages,       including org.apache.solr.(search|update|request|core|analysis)       You may also specify a fully qualified Java classname if you       have your own custom plugins.    -->  <!-- Controls what version of Lucene various components of Solr       adhere to.  Generally, you want to use the latest version to       get all bug fixes and improvements. It is highly recommended       that you fully re-index after changing this setting as it can       affect both how text is indexed and queried.  -->  <luceneMatchVersion>5.3.1</luceneMatchVersion>  <!-- Data Directory       Used to specify an alternate directory to hold all index data       other than the default ./data under the Solr home.  If       replication is in use, this should match the replication       configuration.    -->  <dataDir>${solr.data.dir:}</dataDir>  <!-- The DirectoryFactory to use for indexes.       solr.StandardDirectoryFactory is filesystem       based and tries to pick the best implementation for the current       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,       wraps solr.StandardDirectoryFactory and caches small files in memory       for better NRT performance.       One can force a particular implementation via solr.MMapDirectoryFactory,       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.       solr.RAMDirectoryFactory is memory based, not       persistent, and doesn't work with replication.    -->  <directoryFactory name="DirectoryFactory"                     class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">  </directoryFactory>   <!-- The CodecFactory for defining the format of the inverted index.       The default implementation is SchemaCodecFactory, which is the official Lucene       index format, but hooks into the schema to provide per-field customization of       the postings lists and per-document values in the fieldType element       (postingsFormat/docValuesFormat). Note that most of the alternative implementations       are experimental, so if you choose to customize the index format, it's a good       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)       before upgrading to a newer version to avoid unnecessary reindexing.  -->  <codecFactory class="solr.SchemaCodecFactory"/>  <schemaFactory class="ClassicIndexSchemaFactory"/>  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~       Index Config - These settings control low-level behavior of indexing       Most example settings here show the default value, but are commented       out, to more easily see where customizations have been made.       Note: This replaces <indexDefaults> and <mainIndex> from older versions       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->  <indexConfig>    <!-- LockFactory          This option specifies which Lucene LockFactory implementation         to use.         single = SingleInstanceLockFactory - suggested for a                  read-only index or when there is no possibility of                  another process trying to modify the index.         native = NativeFSLockFactory - uses OS native file locking.                  Do not use when multiple solr webapps in the same                  JVM are attempting to share a single index.         simple = SimpleFSLockFactory  - uses a plain file for locking         Defaults: 'native' is default for Solr3.6 and later, otherwise                   'simple' is the default         More details on the nuances of each LockFactory...         http://wiki.apache.org/lucene-java/AvailableLockFactories    -->    <lockType>${solr.lock.type:native}</lockType>    <!-- Lucene Infostream         To aid in advanced debugging, Lucene provides an "InfoStream"         of detailed information when indexing.         Setting the value to true will instruct the underlying Lucene         IndexWriter to write its info stream to solr's log. By default,         this is enabled here, and controlled through log4j.properties.      -->     <infoStream>true</infoStream>  </indexConfig>  <!-- JMX       This example enables JMX if and only if an existing MBeanServer       is found, use this if you want to configure JMX through JVM       parameters. Remove this to disable exposing Solr configuration       and statistics to JMX.       For more details see http://wiki.apache.org/solr/SolrJmx    -->  <jmx />  <!-- If you want to connect to a particular server, specify the       agentId     -->  <!-- <jmx agentId="myAgent" /> -->  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>    -->  <!-- The default high-performance update handler -->  <updateHandler class="solr.DirectUpdateHandler2">    <!-- Enables a transaction log, used for real-time get, durability, and         and solr cloud replica recovery.  The log can grow as big as         uncommitted changes to the index, so use of a hard autoCommit         is recommended (see below).         "dir" - the target directory for transaction logs, defaults to the                solr data directory.         "numVersionBuckets" - sets the number of buckets used to keep                track of max version values when checking for re-ordered                updates; increase this value to reduce the cost of                synchronizing access to version buckets during high-volume                indexing, this requires 8 bytes (long) * numVersionBuckets                of heap space per Solr core.    -->    <updateLog>      <str name="dir">${solr.ulog.dir:}</str>      <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>    </updateLog>    <!-- AutoCommit         Perform a hard commit automatically under certain conditions.         Instead of enabling autoCommit, consider using "commitWithin"         when adding documents.          http://wiki.apache.org/solr/UpdateXmlMessages         maxDocs - Maximum number of documents to add since the last                   commit before automatically triggering a new commit.         maxTime - Maximum amount of time in ms that is allowed to pass                   since a document was added before automatically                   triggering a new commit.          openSearcher - if false, the commit causes recent index changes           to be flushed to stable storage, but does not cause a new           searcher to be opened to make those changes visible.         If the updateLog is enabled, then it's highly recommended to         have some sort of hard autoCommit to limit the log size.      -->     <autoCommit>        <maxTime>${solr.autoCommit.maxTime:30000}</maxTime>        <openSearcher>false</openSearcher>      </autoCommit>    <!-- softAutoCommit is like autoCommit except it causes a         'soft' commit which only ensures that changes are visible         but does not ensure that data is synced to disk.  This is         faster and more near-realtime friendly than a hard commit.      -->     <autoSoftCommit>        <maxTime>${solr.autoSoftCommit.maxTime:1000}</maxTime>      </autoSoftCommit>  </updateHandler>  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~       Query section - these settings control query time things like caches       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->  <query>    <!-- Max Boolean Clauses         Maximum number of clauses in each BooleanQuery,  an exception         is thrown if exceeded.         ** WARNING **         This option actually modifies a global Lucene property that         will affect all SolrCores.  If multiple solrconfig.xml files         disagree on this property, the value at any given moment will         be based on the last SolrCore to be initialized.      -->    <maxBooleanClauses>1024</maxBooleanClauses>    <!-- Solr Internal Query Caches         There are two implementations of cache available for Solr,         LRUCache, based on a synchronized LinkedHashMap, and         FastLRUCache, based on a ConcurrentHashMap.           FastLRUCache has faster gets and slower puts in single         threaded operation and thus is generally faster than LRUCache         when the hit ratio of the cache is high (> 75%), and may be         faster under other scenarios on multi-cpu systems.    -->    <!-- Filter Cache         Cache used by SolrIndexSearcher for filters (DocSets),         unordered sets of *all* documents that match a query.  When a         new searcher is opened, its caches may be prepopulated or         "autowarmed" using data from caches in the old searcher.         autowarmCount is the number of items to prepopulate.  For         LRUCache, the autowarmed items will be the most recently         accessed items.         Parameters:           class - the SolrCache implementation LRUCache or               (LRUCache or FastLRUCache)           size - the maximum number of entries in the cache           initialSize - the initial capacity (number of entries) of               the cache.  (see java.util.HashMap)           autowarmCount - the number of entries to prepopulate from               and old cache.        -->    <filterCache class="solr.FastLRUCache"                 size="2048"                 initialSize="512"                 autowarmCount="1024"/>    <!-- Query Result Cache        Caches results of searches - ordered lists of document ids        (DocList) based on a query, a sort, and the range of documents requested.        Additional supported parameter by LRUCache:           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed                      to occupy     -->    <queryResultCache class="solr.LRUCache"                     size="512"                     initialSize="512"                     autowarmCount="0"/>    <!-- Document Cache         Caches Lucene Document objects (the stored fields for each         document).  Since Lucene internal document ids are transient,         this cache will not be autowarmed.        -->    <documentCache class="solr.LRUCache"                   size="512"                   initialSize="512"                   autowarmCount="0"/>    <!-- custom cache currently used by block join -->     <cache name="perSegFilter"      class="solr.search.LRUCache"      size="10"      initialSize="0"      autowarmCount="10"      regenerator="solr.NoOpRegenerator" />    <!-- Lazy Field Loading         If true, stored fields that are not requested will be loaded         lazily.  This can result in a significant speed improvement         if the usual case is to not load all stored fields,         especially if the skipped fields are large compressed text         fields.    -->    <enableLazyFieldLoading>true</enableLazyFieldLoading>   <!-- Result Window Size        An optimization for use with the queryResultCache.  When a search        is requested, a superset of the requested number of document ids        are collected.  For example, if a search for a particular query        requests matching documents 10 through 19, and queryWindowSize is 50,        then documents 0 through 49 will be collected and cached.  Any further        requests in that range can be satisfied via the cache.       -->   <queryResultWindowSize>60</queryResultWindowSize>   <!-- Maximum number of documents to cache for any entry in the        queryResultCache.      -->   <queryResultMaxDocsCached>200</queryResultMaxDocsCached>    <!-- Use Cold Searcher         If a search request comes in and there is no current         registered searcher, then immediately register the still         warming searcher and use it.  If "false" then all requests         will block until the first searcher is done warming.      -->    <useColdSearcher>false</useColdSearcher>    <!-- Max Warming Searchers         Maximum number of searchers that may be warming in the         background concurrently.  An error is returned if this limit         is exceeded.         Recommend values of 1-2 for read-only slaves, higher for         masters w/o cache warming.      -->    <maxWarmingSearchers>2</maxWarmingSearchers>  </query>  <!-- Request Dispatcher       This section contains instructions for how the SolrDispatchFilter       should behave when processing requests for this SolrCore.       handleSelect is a legacy option that affects the behavior of requests       such as /select?qt=XXX       handleSelect="true" will cause the SolrDispatchFilter to process       the request and dispatch the query to a handler specified by the        "qt" param, assuming "/select" isn't already registered.       handleSelect="false" will cause the SolrDispatchFilter to       ignore "/select" requests, resulting in a 404 unless a handler       is explicitly registered with the name "/select"       handleSelect="true" is not recommended for new users, but is the default       for backwards compatibility    -->  <requestDispatcher handleSelect="false" >    <!-- Request Parsing         These settings indicate how Solr Requests may be parsed, and         what restrictions may be placed on the ContentStreams from         those requests         enableRemoteStreaming - enables use of the stream.file         and stream.url parameters for specifying remote streams.         multipartUploadLimitInKB - specifies the max size (in KiB) of         Multipart File Uploads that Solr will allow in a Request.         formdataUploadLimitInKB - specifies the max size (in KiB) of         form data (application/x-www-form-urlencoded) sent via         POST. You can use POST to pass request parameters not         fitting into the URL.         addHttpRequestToContext - if set to true, it will instruct         the requestParsers to include the original HttpServletRequest         object in the context map of the SolrQueryRequest under the          key "httpRequest". It will not be used by any of the existing         Solr components, but may be useful when developing custom          plugins.         *** WARNING ***         The settings below authorize Solr to fetch remote files, You         should make sure your system has some authentication before         using enableRemoteStreaming="true"      -->     <requestParsers enableRemoteStreaming="true"                     multipartUploadLimitInKB="2048000"                    formdataUploadLimitInKB="2048"                    addHttpRequestToContext="false"/>    <!-- HTTP Caching         Set HTTP caching related parameters (for proxy caches and clients).         The options below instruct Solr not to output any HTTP Caching         related headers      -->    <httpCaching never304="true" />  </requestDispatcher>  <!-- Request Handlers        http://wiki.apache.org/solr/SolrRequestHandler       Incoming queries will be dispatched to a specific handler by name       based on the path specified in the request.       Legacy behavior: If the request path uses "/select" but no Request       Handler has that name, and if handleSelect="true" has been specified in       the requestDispatcher, then the Request Handler is dispatched based on       the qt parameter.  Handlers without a leading '/' are accessed this way       like so: http://host/app/[core/]select?qt=name  If no qt is       given, then the requestHandler that declares default="true" will be       used or the one named "standard".       If a Request Handler is declared with startup="lazy", then it will       not be initialized until the first request that uses it.    -->  <!-- SearchHandler       http://wiki.apache.org/solr/SearchHandler       For processing Search Queries, the primary Request Handler       provided with Solr is "SearchHandler" It delegates to a sequent       of SearchComponents (see below) and supports distributed       queries across multiple shards    -->  <requestHandler name="/select" class="solr.SearchHandler">    <!-- default values for query parameters can be specified, these         will be overridden by parameters in the request      -->     <lst name="defaults">       <str name="echoParams">explicit</str>       <int name="rows">10</int>     </lst>    </requestHandler>  <!-- A request handler that returns indented JSON by default -->  <requestHandler name="/query" class="solr.SearchHandler">     <lst name="defaults">       <str name="echoParams">explicit</str>       <str name="wt">xml</str>       <str name="indent">true</str>       <!--         <str name="df">text</str>        -->     </lst>  </requestHandler>  <!--    The export request handler is used to export full sorted result sets.    Do not change these defaults.  -->  <requestHandler name="/export" class="solr.SearchHandler">    <lst name="invariants">      <str name="rq">{!xport}</str>      <str name="wt">xsort</str>      <str name="distrib">false</str>    </lst>    <arr name="components">      <str>query</str>    </arr>  </requestHandler>  <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell">    <lst name="defaults">      <str name="df">groupName</str>    </lst>  </initParams>  <!-- Field Analysis Request Handler       RequestHandler that provides much the same functionality as       analysis.jsp. Provides the ability to specify multiple field       types and field names in the same request and outputs       index-time and query-time analysis for each of them.       Request parameters are:       analysis.fieldname - field name whose analyzers are to be used       analysis.fieldtype - field type whose analyzers are to be used       analysis.fieldvalue - text for index-time analysis       q (or analysis.q) - text for query time analysis       analysis.showmatch (true|false) - When set to true and when           query analysis is performed, the produced tokens of the           field value analysis will be marked as "matched" for every           token that is produces by the query analysis   -->  <requestHandler name="/analysis/field"                   startup="lazy"                  class="solr.FieldAnalysisRequestHandler" />  <!-- Document Analysis Handler       http://wiki.apache.org/solr/AnalysisRequestHandler       An analysis handler that provides a breakdown of the analysis       process of provided documents. This handler expects a (single)       content stream with the following format:       <docs>         <doc>           <field name="id">1</field>           <field name="name">The Name</field>           <field name="text">The Text Value</field>         </doc>         <doc>...</doc>         <doc>...</doc>         ...       </docs>    Note: Each document must contain a field which serves as the    unique key. This key is used in the returned response to associate    an analysis breakdown to the analyzed document.    Like the FieldAnalysisRequestHandler, this handler also supports    query analysis by sending either an "analysis.query" or "q"    request parameter that holds the query text to be analyzed. It    also supports the "analysis.showmatch" parameter which when set to    true, all field tokens that match the query tokens will be marked    as a "match".   -->  <requestHandler name="/analysis/document"                   class="solr.DocumentAnalysisRequestHandler"                   startup="lazy" />  <!-- Echo the request contents back to the client -->  <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >    <lst name="defaults">     <str name="echoParams">explicit</str>      <str name="echoHandler">true</str>    </lst>  </requestHandler>  <!-- Search Components       Search components are registered to SolrCore and used by        instances of SearchHandler (which can access them by name)       By default, the following components are available:       <searchComponent name="query"     class="solr.QueryComponent" />       <searchComponent name="facet"     class="solr.FacetComponent" />       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />       <searchComponent name="highlight" class="solr.HighlightComponent" />       <searchComponent name="stats"     class="solr.StatsComponent" />       <searchComponent name="debug"     class="solr.DebugComponent" />     -->  <!-- Terms Component       http://wiki.apache.org/solr/TermsComponent       A component to return terms and document frequency of those       terms    -->  <searchComponent name="terms" class="solr.TermsComponent"/>  <!-- A request handler for demonstrating the terms component -->  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">     <lst name="defaults">      <bool name="terms">true</bool>      <bool name="distrib">false</bool>    </lst>         <arr name="components">      <str>terms</str>    </arr>  </requestHandler>  <!-- Legacy config for the admin interface -->  <admin>    <defaultQuery>*:*</defaultQuery>  </admin></config>