lucene-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From arafa...@apache.org
Subject [3/7] lucene-solr:branch_7x: SOLR-11694: Remove outdated UIMA module
Date Sun, 08 Jul 2018 13:56:36 GMT
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9cd7daf8/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml
deleted file mode 100644
index 776de39..0000000
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml
+++ /dev/null
@@ -1,773 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-
-  <!--
-    Licensed to the Apache Software Foundation (ASF) under one or more
-    contributor license agreements. See the NOTICE file distributed with
-    this work for additional information regarding copyright ownership.
-    The ASF licenses this file to You under the Apache License, Version
-    2.0 (the "License"); you may not use this file except in compliance
-    with the License. You may obtain a copy of the License at
-
-    http://www.apache.org/licenses/LICENSE-2.0 Unless required by
-    applicable law or agreed to in writing, software distributed under
-    the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES
-    OR CONDITIONS OF ANY KIND, either express or implied. See the
-    License for the specific language governing permissions and
-    limitations under the License.
-  -->
-  <!--
-    For more details about configurations options that may appear in
-    this file, see http://wiki.apache.org/solr/SolrConfigXml.
-
-    Specifically, the Solr Config can support XInclude, which may make
-    it easier to manage the configuration. See
-    https://issues.apache.org/jira/browse/SOLR-1167
-  -->
-<config xmlns:xi="http://www.w3.org/2001/XInclude">
-  <luceneMatchVersion>${tests.luceneMatchVersion:LATEST}</luceneMatchVersion>
-  <indexConfig>
-    <useCompoundFile>${useCompoundFile:false}</useCompoundFile>
-  </indexConfig>
-  <!--
-    lib directives can be used to instruct Solr to load any Jars
-    identified and use them to resolve any "plugins" specified in your
-    solrconfig.xml or schema.xml (ie: Analyzers, Request Handlers,
-    etc...). All directories and paths are resolved relative the
-    instanceDir. If a "./lib" directory exists in your instanceDir, all
-    files found in it are included as if you had used the following
-    syntax... <lib dir="./lib" />
-  -->
-  <!--
-    A dir option by itself adds any files found in the directory to the
-    classpath, this is useful for including all jars in a directory.
-  -->
-  <lib dir="../../contrib/extraction/lib" />
-  <!--
-    When a regex is specified in addition to a directory, only the files
-    in that directory which completely match the regex (anchored on both
-    ends) will be included.
-  -->
-  <lib dir="../../dist/" regex="solr-cell-\d.*\.jar" />
-  <!--
-    If a dir option (with or without a regex) is used and nothing is
-    found that matches, it will be ignored
-  -->
-  <lib dir="/total/crap/dir/ignored" />
-  <!--
-    an exact path can be used to specify a specific file. This will
-    cause a serious error to be logged if it can't be loaded. <lib
-    path="../a-jar-that-does-not-exist.jar" />
-  -->
-
-  <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
-  <schemaFactory class="ClassicIndexSchemaFactory"/>
-
-  <!--
-    Used to specify an alternate directory to hold all index data other
-    than the default ./data under the Solr home. If replication is in
-    use, this should match the replication configuration.
-  -->
-  <dataDir>${solr.data.dir:}</dataDir>
-
-
-  <!--
-    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.
-
-    If you want to connect to a particular server, specify the agentId
-    e.g. <jmx agentId="myAgent" /> If you want to start a new
-    MBeanServer, specify the serviceUrl e.g <jmx
-    serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/> For
-    more details see http://wiki.apache.org/solr/SolrJmx
-  -->
-  <jmx />
-
-  <!-- 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)
-    -->
-
-    <!--
-      Perform a <commit/> automatically under certain conditions:
-      maxDocs - number of updates since last commit is greater than this
-      maxTime - oldest uncommited update (in ms) is this long ago
-      Instead of enabling autoCommit, consider using "commitWithin" when
-      adding documents. http://wiki.apache.org/solr/UpdateXmlMessages
-      <autoCommit> <maxDocs>10000</maxDocs> <maxTime>1000</maxTime>
-      </autoCommit>
-    -->
-
-  </updateHandler>
-
-  <!--
-    Use the following format to specify a custom IndexReaderFactory -
-    allows for alternate IndexReader implementations. ** Experimental
-    Feature ** Please note - Using a custom IndexReaderFactory may
-    prevent certain other features from working. The API to
-    IndexReaderFactory may change without warning or may even be removed
-    from future releases if the problems cannot be resolved. ** Features
-    that may not work with custom IndexReaderFactory ** The
-    ReplicationHandler assumes a disk-resident index. Using a custom
-    IndexReader implementation may cause incompatibility with
-    ReplicationHandler and may cause replication to not work correctly.
-    See SOLR-1366 for details. <indexReaderFactory
-    name="IndexReaderFactory" class="package.class"> Parameters as
-    required by the implementation </indexReaderFactory >
-  -->
-  <!-- To set the termInfosIndexDivisor, do this: -->
-  <!--
-    <indexReaderFactory name="IndexReaderFactory"
-    class="org.apache.solr.core.StandardIndexReaderFactory"> <int
-    name="setTermIndexDivisor">12</int> </indexReaderFactory >
-  -->
-
-
-  <query>
-    <!--
-      Maximum number of clauses in a boolean query... in the past, this
-      affected range or prefix queries that expanded to big boolean
-      queries - built in Solr query parsers no longer create queries
-      with this limitation. An exception is thrown if exceeded.
-    -->
-    <maxBooleanClauses>1024</maxBooleanClauses>
-
-
-    <!--
-      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.
-    -->
-    <!--
-      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 FastLRUCache 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.FastLRUCache" size="512"
-      initialSize="512" autowarmCount="0" />
-
-    <!--
-      Cache used to hold field values that are quickly accessible by
-      document id. The fieldValueCache is created by default even if not
-      configured here. <fieldValueCache class="solr.FastLRUCache"
-      size="512" autowarmCount="128" showItems="32" />
-    -->
-
-    <!--
-      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="0" />
-
-    <!--
-      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>20</queryResultWindowSize>
-
-    <!--
-      Maximum number of documents to cache for any entry in the
-      queryResultCache.
-    -->
-    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
-    <!--
-      a newSearcher event is fired whenever a new searcher is being
-      prepared and there is a current searcher handling requests (aka
-      registered). It can be used to prime certain caches to prevent
-      long request times for certain requests.
-    -->
-    <!--
-      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">
-        <lst>
-          <str name="q">solr rocks</str>
-          <str name="start">0</str>
-          <str name="rows">10</str>
-        </lst>
-        <lst>
-          <str name="q">static firstSearcher warming query from
-            solrconfig.xml</str>
-        </lst>
-      </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>2</maxWarmingSearchers>
-
-  </query>
-
-  <requestDispatcher>
-    <!--
-      Make sure your system has some authentication before enabling
-      remote streaming!
-    -->
-    <requestParsers enableRemoteStreaming="false"
-      multipartUploadLimitInKB="-1" />
-
-    <!--
-      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 name="/select" class="solr.SearchHandler">
-    <!-- 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>
-
-  <!--
-    DisMaxRequestHandler allows easy searching across multiple fields
-    for simple user-entered phrases. Its implementation is now just the
-    standard SearchHandler with a default query parser of "dismax". see
-    http://wiki.apache.org/solr/DisMaxRequestHandler
-  -->
-  <requestHandler name="/dismax" class="solr.SearchHandler">
-    <lst name="defaults">
-      <str name="defType">dismax</str>
-      <str name="echoParams">explicit</str>
-      <float name="tie">0.01</float>
-      <str name="qf">
-        text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0
-        manu^1.1 cat^1.4
-     </str>
-      <str name="pf">
-        text^0.2 features^1.1 name^1.5 manu^1.4
-        manu_exact^1.9
-     </str>
-      <str name="bf">
-        popularity^0.5 recip(price,1,1000,1000)^0.3
-     </str>
-      <str name="fl">
-        id,name,price,score
-     </str>
-      <str name="mm">
-        2&lt;-1 5&lt;-2 6&lt;90% </str>
-      <int name="ps">100</int>
-      <str name="q.alt">*:*</str>
-      <!-- example highlighter config, enable per-query with hl=true -->
-      <str name="hl.fl">text features name</str>
-      <!-- for this field, we want no fragmenting, just highlighting -->
-      <str name="f.name.hl.fragsize">0</str>
-      <!--
-        instructs Solr to return the field itself if no query terms are
-        found
-      -->
-      <str name="f.name.hl.alternateField">name</str>
-      <str name="f.text.hl.fragmenter">regex</str> <!-- defined below -->
-    </lst>
-  </requestHandler>
-
-  <!--
-    Note how you can register the same handler multiple times with
-    different names (and different init parameters)
-  -->
-  <requestHandler name="/partitioned" class="solr.SearchHandler">
-    <lst name="defaults">
-      <str name="defType">dismax</str>
-      <str name="echoParams">explicit</str>
-      <str name="qf">text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0</str>
-      <str name="mm">2&lt;-1 5&lt;-2 6&lt;90%</str>
-      <!--
-        This is an example of using Date Math to specify a constantly
-        moving date range in a config...
-      -->
-      <str name="bq">incubationdate_dt:[* TO NOW/DAY-1MONTH]^2.2</str>
-    </lst>
-    <!--
-      In addition to defaults, "appends" params can be specified to
-      identify values which should be appended to the list of multi-val
-      params from the query (or the existing "defaults"). In this
-      example, the param "fq=instock:true" will be appended to any query
-      time fq params the user may specify, as a mechanism for
-      partitioning the index, independent of any user selected filtering
-      that may also be desired (perhaps as a result of faceted
-      searching). NOTE: there is *absolutely* nothing a client can do to
-      prevent these "appends" values from being used, so don't use this
-      mechanism unless you are sure you always want it.
-    -->
-    <lst name="appends">
-      <str name="fq">inStock:true</str>
-    </lst>
-    <!--
-      "invariants" are a way of letting the Solr maintainer lock down
-      the options available to Solr clients. Any params values specified
-      here are used regardless of what values may be specified in either
-      the query, the "defaults", or the "appends" params. In this
-      example, the facet.field and facet.query params are fixed,
-      limiting the facets clients can use. Faceting is not turned on by
-      default - but if the client does specify facet=true in the
-      request, these are the only facets they will be able to see counts
-      for; regardless of what other facet.field or facet.query params
-      they may specify. NOTE: there is *absolutely* nothing a client can
-      do to prevent these "invariants" values from being used, so don't
-      use this mechanism unless you are sure you always want it.
-    -->
-    <lst name="invariants">
-      <str name="facet.field">cat</str>
-      <str name="facet.field">manu_exact</str>
-      <str name="facet.query">price:[* TO 500]</str>
-      <str name="facet.query">price:[500 TO *]</str>
-    </lst>
-  </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="stats"
-    class="org.apache.solr.handler.component.StatsComponent" />
-    <searchComponent name="debug"
-    class="org.apache.solr.handler.component.DebugComponent" /> Default
-    configuration in a requestHandler would look like: <arr
-    name="components"> <str>query</str> <str>facet</str> <str>mlt</str>
-    <str>highlight</str> <str>stats</str> <str>debug</str> </arr> If you
-    register a searchComponent to one of the standard names, that will
-    be used instead. To insert components before or after the 'standard'
-    components, use: <arr name="first-components">
-    <str>myFirstComponentName</str> </arr> <arr name="last-components">
-    <str>myLastComponentName</str> </arr>
-  -->
-
-  <!--
-    The spell check component can return a list of alternative spelling
-    suggestions.
-  -->
-  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
-    <str name="queryAnalyzerFieldType">textSpell</str>
-
-    <lst name="spellchecker">
-      <str name="name">default</str>
-      <str name="field">name</str>
-      <str name="spellcheckIndexDir">./spellchecker</str>
-    </lst>
-
-    <!--
-      a spellchecker that uses a different distance measure <lst
-      name="spellchecker"> <str name="name">jarowinkler</str> <str
-      name="field">spell</str> <str
-      name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
-      <str name="spellcheckIndexDir">./spellchecker2</str> </lst>
-    -->
-
-    <!--
-      a file based spell checker <lst name="spellchecker"> <str
-      name="classname">solr.FileBasedSpellChecker</str> <str
-      name="name">file</str> <str
-      name="sourceLocation">spellings.txt</str> <str
-      name="characterEncoding">UTF-8</str> <str
-      name="spellcheckIndexDir">./spellcheckerFile</str> </lst>
-    -->
-  </searchComponent>
-
-  <!--
-    A request handler utilizing the spellcheck component.
-    #############################################################################
-    NOTE: This is purely as an example. The whole purpose of the
-    SpellCheckComponent is to hook it into the request handler that
-    handles (i.e. the standard or dismax SearchHandler) queries such
-    that a separate request is not needed to get suggestions. IN OTHER
-    WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS NOT WHAT YOU
-    WANT FOR YOUR PRODUCTION SYSTEM!
-    #############################################################################
-  -->
-  <requestHandler name="/spell" class="solr.SearchHandler"
-    lazy="true">
-    <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" />
-  <!--
-    A Req Handler for working with the tvComponent. This is purely as an
-    example. You will likely want to add the component to your already
-    specified request handlers.
-  -->
-  <requestHandler name="/tvrh"
-    class="org.apache.solr.handler.component.SearchHandler">
-    <lst name="defaults">
-      <bool name="tv">true</bool>
-    </lst>
-    <arr name="last-components">
-      <str>tvComponent</str>
-    </arr>
-  </requestHandler>
-
-  <!-- Solr Cell: http://wiki.apache.org/solr/ExtractingRequestHandler -->
-  <requestHandler name="/update/extract"
-    class="org.apache.solr.handler.extraction.ExtractingRequestHandler"
-    startup="lazy">
-    <lst name="defaults">
-      <!--
-        All the main content goes into "text"... if you need to return
-        the extracted text or do highlighting, use a stored field.
-      -->
-      <str name="fmap.content">text</str>
-      <str name="lowernames">true</str>
-      <str name="uprefix">ignored_</str>
-
-      <!-- capture link hrefs but ignore div attributes -->
-      <str name="captureAttr">true</str>
-      <str name="fmap.a">links</str>
-      <str name="fmap.div">ignored_</str>
-    </lst>
-  </requestHandler>
-
-
-  <!--
-    A component to return terms and document frequency of those terms.
-    This component does not yet support distributed search.
-  -->
-  <searchComponent name="termsComponent"
-    class="org.apache.solr.handler.component.TermsComponent" />
-
-  <requestHandler name="/terms"
-    class="org.apache.solr.handler.component.SearchHandler">
-    <lst name="defaults">
-      <bool name="terms">true</bool>
-    </lst>
-    <arr name="components">
-      <str>termsComponent</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
-  -->
-  <requestHandler name="/update" class="solr.UpdateRequestHandler" >
-    <lst name="defaults">
-      <str name="update.chain">uima</str>
-    </lst>
-  </requestHandler>
-  <!-- CSV update handler, loaded on demand -->
-  <requestHandler name="/update/csv" class="solr.CSVRequestHandler"
-    startup="lazy" />
-
-  <!--
-    An example dedup update processor that creates the "id" field on the
-    fly based on the hash code of some other fields. This example has
-    overwriteDupes set to false since we are using the id field as the
-    signatureField and Solr will maintain uniqueness based on that
-    anyway. You have to link the chain to an update handler above to use
-    it ie: <requestHandler name="/update
-    "class="solr.UpdateRequestHandler"> <lst name="defaults"> <str
-    name="update.chain">dedupe</str> </lst> </requestHandler>
-  -->
-
-  <updateRequestProcessorChain name="uima">
-    <processor class="org.apache.solr.uima.processor.UIMAUpdateRequestProcessorFactory">
-      <lst name="uimaConfig">
-        <lst name="runtimeParameters">
-          <int name="ngramsize">3</int>
-        </lst>
-        <str name="analysisEngine">/uima/TestAE.xml</str>
-        <lst name="analyzeFields">
-          <bool name="merge">false</bool>
-          <arr name="fields">
-            <str>text</str>
-          </arr>
-        </lst>
-        <lst name="fieldMappings">
-          <lst name="type">
-            <str name="name">org.apache.uima.SentenceAnnotation</str>
-            <lst name="mapping">
-              <str name="feature">coveredText</str>
-              <str name="field">sentence</str>
-            </lst>
-          </lst>
-          <lst name="type">
-            <str name="name">org.apache.solr.uima.ts.DummySentimentAnnotation</str>
-            <lst name="mapping">
-              <str name="feature">mood</str>
-              <str name="field">sentiment</str>
-            </lst>
-          </lst>
-          <lst name="type">
-            <str name="name">org.apache.solr.uima.ts.EntityAnnotation</str>
-            <lst name="mapping">
-              <str name="feature">entity</str>
-              <str name="fieldNameFeature">name</str>
-              <str name="dynamicField">*_sm</str>
-            </lst>
-          </lst>
-        </lst>
-      </lst>
-    </processor>
-    <processor class="solr.RunUpdateProcessorFactory" />
-  </updateRequestProcessorChain>
-
-  <updateRequestProcessorChain name="uima-multi-map">
-    <processor class="org.apache.solr.uima.processor.UIMAUpdateRequestProcessorFactory">
-      <lst name="uimaConfig">
-        <lst name="runtimeParameters">
-          <int name="ngramsize">3</int>
-        </lst>
-        <str name="analysisEngine">/uima/TestAE.xml</str>
-        <lst name="analyzeFields">
-          <bool name="merge">false</bool>
-          <arr name="fields">
-            <str>text</str>
-          </arr>
-        </lst>
-        <lst name="fieldMappings">
-          <lst name="type">
-            <str name="name">a-type-which-can-have-multiple-features</str>
-            <lst name="mapping">
-              <str name="feature">A</str>
-              <str name="field">1</str>
-            </lst>
-            <lst name="mapping">
-              <str name="feature">B</str>
-              <str name="field">2</str>
-            </lst>
-          </lst>
-        </lst>
-      </lst>
-    </processor>
-  </updateRequestProcessorChain>
-
-  <updateRequestProcessorChain name="uima-not-ignoreErrors">
-    <processor class="org.apache.solr.uima.processor.UIMAUpdateRequestProcessorFactory">
-      <lst name="uimaConfig">
-        <lst name="runtimeParameters">
-          <int name="ngramsize">3</int>
-        </lst>
-        <str name="analysisEngine">/uima/TestExceptionAE.xml</str>
-        <bool name="ignoreErrors">false</bool>
-        <lst name="analyzeFields">
-          <bool name="merge">false</bool>
-          <arr name="fields">
-            <str>text</str>
-          </arr>
-        </lst>
-        <lst name="fieldMappings"/>
-      </lst>
-    </processor>
-    <processor class="solr.RunUpdateProcessorFactory" />
-  </updateRequestProcessorChain>
-
-  <updateRequestProcessorChain name="uima-ignoreErrors">
-    <processor class="org.apache.solr.uima.processor.UIMAUpdateRequestProcessorFactory">
-      <lst name="uimaConfig">
-        <lst name="runtimeParameters">
-          <int name="ngramsize">3</int>
-        </lst>
-        <str name="analysisEngine">/uima/TestExceptionAE.xml</str>
-        <bool name="ignoreErrors">true</bool>
-        <!-- This is optional. It is used for logging when text processing fails. Usually, set uniqueKey field name -->
-        <str name="logField">id</str>
-        <lst name="analyzeFields">
-          <bool name="merge">false</bool>
-          <arr name="fields">
-            <str>text</str>
-          </arr>
-        </lst>
-        <lst name="fieldMappings"/>
-      </lst>
-    </processor>
-    <processor class="solr.RunUpdateProcessorFactory" />
-  </updateRequestProcessorChain>
-
-  <!--
-    queryResponseWriter plugins... query responses will be written using
-    the writer specified by the 'wt' request parameter matching the name
-    of a registered writer. The "default" writer is the default and will
-    be used if 'wt' is not specified in the request. XMLResponseWriter
-    will be used if nothing is specified here. The json, python, and
-    ruby writers are also available by default. <queryResponseWriter
-    name="xml" class="org.apache.solr.request.XMLResponseWriter"
-    default="true"/> <queryResponseWriter name="json"
-    class="org.apache.solr.request.JSONResponseWriter"/>
-    <queryResponseWriter name="python"
-    class="org.apache.solr.request.PythonResponseWriter"/>
-    <queryResponseWriter name="ruby"
-    class="org.apache.solr.request.RubyResponseWriter"/>
-    <queryResponseWriter name="php"
-    class="org.apache.solr.request.PHPResponseWriter"/>
-    <queryResponseWriter name="phps"
-    class="org.apache.solr.request.PHPSerializedResponseWriter"/>
-
-    <queryResponseWriter name="custom"
-    class="com.example.MyResponseWriter"/>
-  -->
-
-  <!--
-    XSLT response writer transforms the XML output by any xslt file
-    found in Solr's conf/xslt directory. Changes to xslt files are
-    checked for every xsltCacheLifetimeSeconds.
-  -->
-  <queryResponseWriter name="xslt"
-    class="org.apache.solr.response.XSLTResponseWriter">
-    <int name="xsltCacheLifetimeSeconds">5</int>
-  </queryResponseWriter>
-
-
-  <!--
-    example of registering a query parser <queryParser name="lucene"
-    class="org.apache.solr.search.LuceneQParserPlugin"/>
-  -->
-
-  <!--
-    example of registering a custom function parser <valueSourceParser
-    name="myfunc" class="com.mycompany.MyValueSourceParser" />
-  -->
-
-  <!-- config for the admin interface -->
-  <admin>
-    <defaultQuery>*</defaultQuery>
-  </admin>
-
-</config>

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9cd7daf8/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/spellings.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/spellings.txt b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/spellings.txt
deleted file mode 100644
index 162a044..0000000
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/spellings.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-pizza
-history

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9cd7daf8/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/stopwords.txt b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/stopwords.txt
deleted file mode 100644
index b5824da..0000000
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/stopwords.txt
+++ /dev/null
@@ -1,58 +0,0 @@
-# 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.
-
-#-----------------------------------------------------------------------
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-#Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-s
-such
-t
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
-

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9cd7daf8/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt
deleted file mode 100644
index 26d237a..0000000
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-# 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.
-
-#-----------------------------------------------------------------------
-#some test synonym mappings unlikely to appear in real input text
-aaa => aaaa
-bbb => bbbb1 bbbb2
-ccc => cccc1,cccc2
-a\=>a => b\=>b
-a\,a => b\,b
-fooaaa,baraaa,bazaaa
-
-# Some synonym groups specific to this example
-GB,gib,gigabyte,gigabytes
-MB,mib,megabyte,megabytes
-Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
-#after us won't split it into two words.
-
-# Synonym mappings can be used for spelling correction too
-pixima => pixma
-

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9cd7daf8/solr/contrib/uima/src/test-files/uima/stoptypes.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/stoptypes.txt b/solr/contrib/uima/src/test-files/uima/stoptypes.txt
deleted file mode 100644
index c0e0084..0000000
--- a/solr/contrib/uima/src/test-files/uima/stoptypes.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-# 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.
-vbg
-vbz
-vbd
-vbn
-vb
-bez
-cc
-cd
-at
-.
-:
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9cd7daf8/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml b/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
deleted file mode 100644
index d5d3987..0000000
--- a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
+++ /dev/null
@@ -1,613 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
-  Licensed to the Apache Software Foundation (ASF) under one or more
-  contributor license agreements. See the NOTICE file distributed with
-  this work for additional information regarding copyright ownership.
-  The ASF licenses this file to You under the Apache License, Version
-  2.0 (the "License"); you may not use this file except in compliance
-  with the License. You may obtain a copy of the License at
-
-  http://www.apache.org/licenses/LICENSE-2.0 Unless required by
-  applicable law or agreed to in writing, software distributed under
-  the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES
-  OR CONDITIONS OF ANY KIND, either express or implied. See the
-  License for the specific language governing permissions and
-  limitations under the License.
--->
-
-<!--
-  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 PERFORMANCE NOTE: this schema
-  includes many optional features and should not be used for
-  benchmarking. To improve performance one could - set stored="false"
-  for all fields possible (esp large fields) when you only need to
-  search on the field but don't need to return the original value. -
-  set indexed="false" if you don't need to search on the field, but
-  only return the field as a result of searching on other indexed
-  fields. - remove all unneeded copyField statements - for best index
-  size and searching performance, set "index" to false for all general
-  text fields, use copyField to copy them to the catchall "text"
-  field, and use that for searching. - For maximum indexing
-  performance, use the ConcurrentUpdateSolrServer java client. -
-  Remember to run the JVM in server mode, and use a higher logging
-  level that avoids logging every request
--->
-
-<schema name="sample" 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="1.2" 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 1.2: omitTermFreqAndPositions
-    attribute introduced, true by default except for text fields.
-  -->
-
-  <!--
-    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"/>
-  <!--
-    Binary data type. The data should be sent/retrieved in as Base64
-    encoded Strings
-  -->
-  <fieldType name="binary" class="solr.BinaryField"/>
-
-  <!--
-    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.
-  -->
-
-  <!--
-    Default numeric field types. For faster range queries, consider
-    the tint/tfloat/tlong/tdouble types.
-  -->
-  <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-  <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-  <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-  <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-
-  <!--
-    Numeric field types that index each value at various levels of
-    precision to accelerate range queries when the number of values
-    between the range endpoints is large. See the javadoc for
-    LegacyNumericRangeQuery for internal implementation details. Smaller
-    precisionStep values (specified in bits) will lead to more tokens
-    indexed per value, slightly larger index size, and faster range
-    queries. A precisionStep of 0 disables indexing at different
-    precision levels.
-  -->
-  <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-  <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-  <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-  <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}"
-             precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-
-  <!--
-    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 TrieDateField javadocs for more information. Note: For faster
-    range queries, consider the tdate type
-  -->
-  <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}"
-             omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
-
-  <!--
-    A Trie based date field for faster date range queries and date
-    faceting.
-  -->
-  <fieldType name="tdate" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}"
-             omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
-
-  <!--
-    The "RandomSortField" is not used to store or search any data. You
-    can declare fields of this type it in your schema to generate
-    pseudo-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 different 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.MockTokenizerFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!--
-    A text field that uses WordDelimiterGraphFilter 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.
-  -->
-  <fieldType name="text" class="solr.TextField"
-             positionIncrementGap="100">
-    <analyzer type="index">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <!--
-        in this example, we will only use synonyms at query time
-        <filter class="solr.SynonymGraphFilterFactory"
-        synonyms="index_synonyms.txt" ignoreCase="true"
-        expand="false"/>
-      -->
-      <!--
-        Case insensitive stop word removal. add
-      -->
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="1" generateNumberParts="1" catenateWords="1"
-              catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-
-      <filter class="solr.FlattenGraphFilterFactory"/>
-
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="1" generateNumberParts="1" catenateWords="0"
-              catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-
-    </analyzer>
-  </fieldType>
-
-
-  <!--
-    Less flexible matching, but less false matches. Probably not ideal
-    for product names, but may be good for SKUs. Can insert dashes in
-    the wrong place and still match.
-  -->
-  <fieldType name="textTight" class="solr.TextField"
-             positionIncrementGap="100">
-    <analyzer type="index">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="0" generateNumberParts="0" catenateWords="1"
-              catenateNumbers="1" catenateAll="0"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-
-      <!--
-        this filter can remove any duplicate tokens that appear at the
-        same position - sometimes possible with WordDelimiterGraphFilter in
-        conjuncton with stemming.
-      -->
-      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
-
-      <filter class="solr.FlattenGraphFilterFactory" />
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="0" generateNumberParts="0" catenateWords="1"
-              catenateNumbers="1" catenateAll="0"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <fieldType name="uima_sentences" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
-      <tokenizer class="solr.UIMAAnnotationsTokenizerFactory"
-                 descriptorPath="/uima/AggregateSentenceAE.xml" tokenType="org.apache.uima.SentenceAnnotation"
-                 ngramsize="2"/>
-    </analyzer>
-  </fieldType>
-
-  <fieldType name="uima_nouns" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
-      <tokenizer class="solr.UIMATypeAwareAnnotationsTokenizerFactory"
-                 descriptorPath="/uima/AggregateSentenceAE.xml" tokenType="org.apache.uima.TokenAnnotation"
-                 featurePath="posTag"/>
-      <filter class="solr.TypeTokenFilterFactory" types="uima/stoptypes.txt"/>
-    </analyzer>
-  </fieldType>
-
-
-  <!--
-    A general unstemmed text field - good if one does not know the
-    language of the field
-  -->
-  <fieldType name="textgen" class="solr.TextField"
-             positionIncrementGap="100">
-    <analyzer type="index">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="1" generateNumberParts="1" catenateWords="1"
-              catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.FlattenGraphFilterFactory"/>
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="1" generateNumberParts="1" catenateWords="0"
-              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-
-  <!--
-    A general unstemmed text field that indexes tokens normally and
-    also reversed (via ReversedWildcardFilterFactory), to enable more
-    efficient leading wildcard queries.
-  -->
-  <fieldType name="text_rev" class="solr.TextField"
-             positionIncrementGap="100">
-    <analyzer type="index">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="1" generateNumberParts="1" catenateWords="1"
-              catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.ReversedWildcardFilterFactory"
-              withOriginal="true" maxPosAsterisk="3" maxPosQuestion="2"
-              maxFractionAsterisk="0.33"/>
-      <filter class="solr.FlattenGraphFilterFactory"/>
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterGraphFilterFactory"
-              generateWordParts="1" generateNumberParts="1" catenateWords="0"
-              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- charFilter + WhitespaceTokenizer  -->
-  <!--
-    <fieldType name="textCharNorm" class="solr.TextField"
-    positionIncrementGap="100" > <analyzer> <charFilter
-    class="solr.MappingCharFilterFactory"
-    mapping="mapping-ISOLatin1Accent.txt"/> <tokenizer
-    class="solr.MockTokenizerFactory"/> </analyzer> </fieldType>
-  -->
-
-  <!--
-    This is an example of using the KeywordTokenizer along With
-    various TokenFilterFactories to produce a sortable field that does
-    not include some properties of the source text
-  -->
-  <fieldType name="alphaOnlySort" class="solr.TextField"
-             sortMissingLast="true" omitNorms="true">
-    <analyzer>
-      <!--
-        KeywordTokenizer does no actual tokenizing, so the entire
-        input string is preserved as a single token
-      -->
-      <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
-      <!--
-        The LowerCase TokenFilter does what you expect, which can be
-        when you want your sorting to be case insensitive
-      -->
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <!-- The TrimFilter removes any leading or trailing whitespace -->
-      <filter class="solr.TrimFilterFactory"/>
-      <!--
-        The PatternReplaceFilter gives you the flexibility to use Java
-        Regular expression to replace any sequence of characters
-        matching a pattern with an arbitrary replacement string, which
-        may include back references to portions of the original string
-        matched by the pattern. See the Java Regular Expression
-        documentation for more information on pattern and replacement
-        string syntax.
-
-        http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
-      -->
-      <filter class="solr.PatternReplaceFilterFactory" pattern="([^a-z])"
-              replacement="" replace="all"/>
-    </analyzer>
-  </fieldType>
-
-  <fieldType name="phonetic" stored="false" indexed="true"
-             class="solr.TextField">
-    <analyzer>
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
-    </analyzer>
-  </fieldType>
-
-  <fieldType name="payloads" stored="false" indexed="true"
-             class="solr.TextField">
-    <analyzer>
-      <tokenizer class="solr.MockTokenizerFactory"/>
-      <!--
-        The DelimitedPayloadTokenFilter can put payloads on tokens...
-        for example, a token of "foo|1.4" would be indexed as "foo"
-        with a payload of 1.4f Attributes of the
-        DelimitedPayloadTokenFilterFactory : "delimiter" - a one
-        character delimiter. Default is | (pipe) "encoder" - how to
-        encode the following value into a playload float ->
-        org.apache.lucene.analysis.payloads.FloatEncoder, integer ->
-        o.a.l.a.p.IntegerEncoder identity -> o.a.l.a.p.IdentityEncoder
-        Fully Qualified class name implementing PayloadEncoder,
-        Encoder must have a no arg constructor.
-      -->
-      <filter class="solr.DelimitedPayloadTokenFilterFactory"
-              encoder="float"/>
-    </analyzer>
-  </fieldType>
-
-  <!--
-    lowercases the entire field value, keeping it as a single token.
-  -->
-  <fieldType name="lowercase" class="solr.TextField"
-             positionIncrementGap="100">
-    <analyzer>
-      <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
-      <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"/>
-
-  <!--
-    Valid attributes for fields: name: mandatory - the name for the
-    field type: mandatory - the name of a previously defined type from
-    the <fieldType>s indexed: true if this field should be indexed
-    (searchable or sortable) stored: true if this field should be
-    retrievable multiValued: true if this field may contain multiple
-    values per document omitNorms: (expert) set to true to omit the
-    norms associated with this field (this disables length
-    normalization and index-time boosting for the field, and saves
-    some memory). Only full-text fields or fields that need an
-    index-time boost need norms. termVectors: [false] set to true to
-    store the term vector for a given field. When using MoreLikeThis,
-    fields used for similarity should be stored for best performance.
-    termPositions: Store position information with the term vector.
-    This will increase storage costs. termOffsets: Store offset
-    information with the term vector. This will increase storage
-    costs. default: a value that should be used if no value is
-    specified when adding a document.
-  -->
-  <field name="id" type="string" indexed="true" stored="true"
-         required="true"/>
-  <field name="sku" type="textTight" indexed="true" stored="true"
-         omitNorms="true"/>
-  <field name="name" type="textgen" indexed="true" stored="true"/>
-  <field name="alphaNameSort" type="alphaOnlySort" indexed="true"
-         stored="false"/>
-  <field name="manu" type="textgen" indexed="true" stored="true"
-         omitNorms="true"/>
-  <field name="cat" type="text_ws" indexed="true" stored="true"
-         multiValued="true" omitNorms="true"/>
-  <field name="features" type="text" indexed="true" stored="true"
-         multiValued="true"/>
-  <field name="includes" type="text" indexed="true" stored="true"
-         termVectors="true" termPositions="true" termOffsets="true"/>
-
-  <field name="sentences" type="uima_sentences" indexed="true" stored="true" multiValued="true"
-         termVectors="true" termPositions="true" termOffsets="true"/>
-  <field name="nouns" type="uima_nouns" indexed="true" stored="true" multiValued="true"
-         termVectors="true" termPositions="true" termOffsets="true"/>
-
-  <field name="weight" type="float" indexed="true" stored="true"/>
-  <field name="price" type="float" indexed="true" stored="true"/>
-  <field name="popularity" type="int" indexed="true" stored="true"/>
-  <field name="inStock" type="boolean" indexed="true" stored="true"/>
-
-
-  <!--
-    Common metadata fields, named specifically to match up with
-    SolrCell metadata when parsing rich documents such as Word, PDF.
-    Some fields are multiValued only because Tika currently may return
-    multiple values for them.
-  -->
-  <field name="title" type="text" indexed="true" stored="true"
-         multiValued="true"/>
-  <field name="subject" type="text" indexed="true" stored="true"/>
-  <field name="description" type="text" indexed="true" stored="true"/>
-  <field name="comments" type="text" indexed="true" stored="true"/>
-  <field name="author" type="textgen" indexed="true" stored="true"/>
-  <field name="keywords" type="textgen" indexed="true" stored="true"/>
-  <field name="category" type="textgen" indexed="true" stored="true"/>
-  <field name="content_type" type="string" indexed="true"
-         stored="true" multiValued="true"/>
-  <field name="last_modified" type="date" indexed="true" stored="true"/>
-  <field name="links" type="string" indexed="true" stored="true"
-         multiValued="true"/>
-
-
-  <!--
-    catchall field, containing all other searchable text fields
-    (implemented via copyField further on in this schema
-  -->
-  <field name="text" type="text" indexed="true" stored="false"
-         multiValued="true"/>
-
-  <!--
-    catchall text field that indexes tokens both normally and in
-    reverse for efficient leading wildcard queries.
-  -->
-  <field name="text_rev" type="text_rev" indexed="true" stored="false"
-         multiValued="true"/>
-
-  <!--
-    non-tokenized version of manufacturer to make it easier to sort or
-    group results by manufacturer. copied from "manu" via copyField
-  -->
-  <field name="manu_exact" type="string" indexed="true" stored="false"/>
-
-  <field name="payloads" type="payloads" indexed="true" stored="true"/>
-
-  <!--
-    Uncommenting the following will create a "timestamp" field using a
-    default value of "NOW" to indicate when each document was indexed.
-  -->
-  <!--
-    <field name="timestamp" type="date" indexed="true" stored="true"
-    default="NOW" multiValued="false"/>
-  -->
-
-  <field name="language" type="string" indexed="true" stored="true" required="false"/>
-  <field name="sentence" type="text" indexed="true" stored="true" multiValued="true" required="false"/>
-  <field name="sentiment" type="string" indexed="true" stored="true" multiValued="true"/>
-  <field name="entity" type="text" indexed="true" stored="true" multiValued="true"/>
-
-  <!--
-    Dynamic field definitions. If a field name is not found,
-    dynamicFields will be used if the name matches any of the
-    patterns. RESTRICTION: the glob-like pattern in the name attribute
-    must have a "*" only at the start or the end. EXAMPLE: name="*_i"
-    will match any field ending in _i (like myid_i, z_i) Longer
-    patterns will be matched first. if equal size patterns both match,
-    the first appearing in the schema will be used. <dynamicField
-    name="*_i" type="int" indexed="true" stored="true"/> <dynamicField
-    name="*_s" type="string" indexed="true" stored="true"/>
-    <dynamicField name="*_l" type="long" indexed="true"
-    stored="true"/> <dynamicField name="*_t" type="text"
-    indexed="true" stored="true"/> <dynamicField name="*_b"
-    type="boolean" indexed="true" stored="true"/> <dynamicField
-    name="*_f" type="float" indexed="true" stored="true"/>
-    <dynamicField name="*_d" type="double" indexed="true"
-    stored="true"/> <dynamicField name="*_dt" type="date"
-    indexed="true" stored="true"/> <dynamicField name="*_ti"
-    type="tint" indexed="true" stored="true"/> <dynamicField
-    name="*_tl" type="tlong" indexed="true" stored="true"/>
-    <dynamicField name="*_tf" type="tfloat" indexed="true"
-    stored="true"/> <dynamicField name="*_td" type="tdouble"
-    indexed="true" stored="true"/> <dynamicField name="*_tdt"
-    type="tdate" indexed="true" stored="true"/>
-
-    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
-    <dynamicField name="attr_*" type="textgen" indexed="true"
-    stored="true" multiValued="true"/> <dynamicField name="random_*"
-    type="random" />
-  -->
-  <dynamicField name="*_sm" type="string" indexed="true" stored="true" multiValued="true"/>
-  <!--
-    uncomment the following to ignore any fields that don't already
-    match an existing field name or dynamic field, rather than
-    reporting them as an error. alternately, change the type="ignored"
-    to some other type e.g. "text" if you want unknown fields indexed
-    and/or stored by default
-  -->
-  <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
-
-  <!--
-    Field to use to determine and enforce document uniqueness. Unless
-    this field is marked with required="false", it will be a required
-    field
-  -->
-  <uniqueKey>id</uniqueKey>
-
-  <!--
-    copyField commands copy one field to another at the time a document
-    is added to the index. It's used either to index the same field
-    differently, or to add multiple fields to the same field for
-    easier/faster searching.
-  -->
-
-  <copyField source="cat" dest="text"/>
-  <copyField source="name" dest="text"/>
-  <copyField source="manu" dest="text"/>
-  <copyField source="features" dest="text"/>
-  <copyField source="includes" dest="text"/>
-  <copyField source="text" dest="nouns"/>
-  <copyField source="text" dest="sentences"/>
-  <copyField source="manu" dest="manu_exact"/>
-
-
-  <!--copyField source="Titolo" dest="text"/-->
-
-  <!--
-    Above, multiple source fields are copied to the [text] field.
-    Another way to map multiple source fields to the same destination
-    field is to use the dynamic field syntax. copyField also supports a
-    maxChars to copy setting.
-  -->
-
-  <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
-
-  <!--
-    copy name to alphaNameSort, a field designed for sorting by name
-  -->
-  <!-- <copyField source="name" dest="alphaNameSort"/> -->
-
-
-</schema>


Mime
View raw message