Solr 4 没有结果,索引已设置、运行和填充

问题描述 投票:0回答:1

以下正常工作:找到 1079 条记录

http://solr.winedatabase.org/solr/grape/select?q=*%3A*&fl=*&wt=json&indent=true&debugQuery=true

尝试定义查询总是产生 0 个结果...我尝试了许多不同的格式..例如...

http://solr.winedatabase.org/solr/grape/select?q=title%3AAb&fl=*&wt=json&indent=true&debugQuery=true

这是我认为您可能需要的所有数据:

schema.xml

    <?xml version="1.0" encoding="UTF-8" ?>

<schema name="grape" version="1.5">
    <uniqueKey>id</uniqueKey>
    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
    <field name="title" type="text_general" indexed="true" stored="true" required="true" multiValued="false" />
    <field name="common" type="boolean" indexed="true" stored="true" required="true" multiValued="false" />
    <field name="_version_" type="long" indexed="true" stored="true"/>

    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
    <fieldType name="int" class="solr.TrieIntField" 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" 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="binary" class="solr.BinaryField"/>


    <!-- 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.
         Example:
    <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>

    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <!-- 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.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </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" multiValued="true" class="solr.StrField" />
    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
</schema>

solrconfig.xml

<?xml version="1.0" encoding="UTF-8" ?>

<config>
  <luceneMatchVersion>5.2.1</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:15000}</maxTime>
       <openSearcher>false</openSearcher>
     </autoCommit>

    <!-- softAutoCommit is like autoCommit except it causes a
         'soft' commit which only ensures that changes are visible
         but does not ensure that data is synced to disk.  This is
         faster and more near-realtime friendly than a hard commit.
      -->
     <autoSoftCommit>
       <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
     </autoSoftCommit>

  </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="512"
                 initialSize="512"
                 autowarmCount="0"/>

    <!-- Query Result Cache

        Caches results of searches - ordered lists of document ids
        (DocList) based on a query, a sort, and the range of documents requested.
        Additional supported parameter by LRUCache:
           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
                      to occupy
     -->
    <queryResultCache class="solr.LRUCache"
                     size="512"
                     initialSize="512"
                     autowarmCount="0"/>

    <!-- Document Cache

         Caches Lucene Document objects (the stored fields for each
         document).  Since Lucene internal document ids are transient,
         this cache will not be autowarmed.
      -->
    <documentCache class="solr.LRUCache"
                   size="512"
                   initialSize="512"
                   autowarmCount="0"/>

    <!-- custom cache currently used by block join -->
    <cache name="perSegFilter"
      class="solr.search.LRUCache"
      size="10"
      initialSize="0"
      autowarmCount="10"
      regenerator="solr.NoOpRegenerator" />

    <!-- 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>20</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">json</str>
       <str name="indent">true</str>
       <str name="df">text</str>
     </lst>
  </requestHandler>


<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
  <lst name="defaults">
   <str name="config">db-data-config.xml</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">text</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>

查询的调试输出

没什么有趣的,在这里查看:http://pastebin.com/raw.php?i=NUbSca5E

solr
1个回答
1
投票

两种方式:

  1. (最接近
    LIKE 'cab%'
    )使用 Lucene 通配符查询语法 运行查询。 (但是这条路线禁止前导通配符,因此对于您的特定示例无效 - 假设 ab 应该匹配 cabernet
  2. 使用NGramFilterFactory 来分析你想要在其中匹配子字符串的字段。 (更多关于如何在 Khai 的 Solr Q+A 帖子“N-gram 分析一般如何工作?”中一般如何使用 N-Grams 的信息)

使用 N-Grams(例如,最大克数 = 3,最小克数 = 2),“cabernet”被索引为

ca cab ab abe be ber er ern rn rne ne net et
使其能够与
"ab"

的查询匹配

希望对您有所帮助!

(对于剥离重音,请考虑使用 ASCIIFoldingFilterFactory 或 ICU 折叠过滤器工厂。)

© www.soinside.com 2019 - 2024. All rights reserved.