solr7.7.0 对pdf.doc文件做索引（六）

其他 2020-01-10 16:01:15 阅读次数: 0

1 接上文整合讲，

2本利与上文关系不大。  这里我没配置数据库，自行增加

2.1首先我们需要把/usr/local/solr/solr-7.7.0/contrib/extraction/lib  所有的jar  放到tomcat下的solr的web_info下的lib里

/usr/local/solr/apache-tomcat-8.5.31/webapps/solr7/WEB-INF/lib

2.2 以及还要把

把dataimport插件（/usr/local/solr/solr-7.7.0/dist  下）的依赖的jar包添加到/usr/local/solr/solrhome/contrib/dataimporthandler/lib下，lib目录没有就创建一个

3jar都放好后，需要对new_core 进行配置

3.1打开  /usr/local/solr/solrhome/new_core/conf      下的solrconfig.xml 

添加以下：

<lib dir="${solr.install.dir:..}/contrib/dataimporthandler/lib" regex=".*\.jar" />
<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
<lst name="defaults">
<str name="config">data-config.xml</str>
</lst>
</requestHandler>

3.2 以及在该目录下 创建   data-config.xml。

我自己的solr服务器用   /usr/file  存放pdf.doc等文件

<?xml version="1.0" encoding="UTF-8" ?>
<dataConfig>
    <dataSource type="BinFileDataSource"/>
    <document>
        <entity name="file" processor="FileListEntityProcessor" dataSource="null"
                baseDir="/usr/file" fileName=".(doc)|(pdf)|(docx)|(txt)|(csv)|(json)|(xml)|(pptx)|(pptx)|(ppt)|(xls)|(xlsx)"
                rootEntity="false">

            <field column="file" name="id"/>
            <field column="fileSize" name="fileSize"/>
            <field column="fileLastModified" name="fileLastModified"/>
            <field column="fileLastModified" name="fileLastModified"/>
            <field column="fileAbsolutePath" name="fileAbsolutePath"/>
            <entity name="pdf" processor="TikaEntityProcessor"
                    url="${file.fileAbsolutePath}" format="text">

                <field column="Author" name="author" meta="true"/>
                <!-- in the original PDF, the Author meta-field name is upper-cased,
                  but in Solr schema it is lower-cased
                 -->

<!---   这里的分词需要在managed-schemea   设置自己的分词规则-->

                <field column="title" name="title" meta="true"/>
                <field column="text" name="text"/>

            </entity>
        </entity>
    </document>


</dataConfig>

managed-schemea：
<?xml version="1.0" encoding="UTF-8"?>
<!-- Solr managed schema - automatically generated - DO NOT EDIT -->
<schema name="default-config" version="1.6">
  <uniqueKey>id</uniqueKey>
  <fieldType name="ancestor_path" class="solr.TextField">
    <analyzer type="index">
      <tokenizer class="solr.KeywordTokenizerFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
    </analyzer>
  </fieldType>
  <fieldType name="binary" class="solr.BinaryField"/>
  <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
  <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
  <fieldType name="delimited_payloads_float" class="solr.TextField" indexed="true" stored="false">
    <analyzer>
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
    </analyzer>
  </fieldType>
  <fieldType name="delimited_payloads_int" class="solr.TextField" indexed="true" stored="false">
    <analyzer>
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
    </analyzer>
  </fieldType>
  <fieldType name="delimited_payloads_string" class="solr.TextField" indexed="true" stored="false">
    <analyzer>
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
    </analyzer>
  </fieldType>
  <fieldType name="descendent_path" class="solr.TextField">
    <analyzer type="index">
      <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.KeywordTokenizerFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
  <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" maxDistErr="0.001" distErrPct="0.025" distanceUnits="kilometers"/>
  <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.KeywordTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
  <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
  <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
  <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
  <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
  <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
  <fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
    </analyzer>
  </fieldType>
  <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
  <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
  <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
  <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
  <fieldType name="point" class="solr.PointType" subFieldSuffix="_d" dimension="2"/>
  <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
  <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true"/>
  <fieldType name="strings" class="solr.StrField" sortMissingLast="true" docValues="true" multiValued="true"/>
  <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_ar.txt" ignoreCase="true"/>
      <filter class="solr.ArabicNormalizationFilterFactory"/>
      <filter class="solr.ArabicStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_bg.txt" ignoreCase="true"/>
      <filter class="solr.BulgarianStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.ElisionFilterFactory" articles="lang/contractions_ca.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_ca.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.CJKWidthFilterFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.CJKBigramFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_cz.txt" ignoreCase="true"/>
      <filter class="solr.CzechStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_da.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_de.txt" ignoreCase="true"/>
      <filter class="solr.GermanNormalizationFilterFactory"/>
      <filter class="solr.GermanLightStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.GreekLowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_el.txt" ignoreCase="false"/>
      <filter class="solr.GreekStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
    <analyzer type="index">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.EnglishPossessiveFilterFactory"/>
      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      <filter class="solr.PorterStemFilterFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.EnglishPossessiveFilterFactory"/>
      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      <filter class="solr.PorterStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
    <analyzer type="index">
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      <filter class="solr.PorterStemFilterFactory"/>
      <filter class="solr.FlattenGraphFilterFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      <filter class="solr.PorterStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
    <analyzer type="index">
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      <filter class="solr.EnglishMinimalStemFilterFactory"/>
      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      <filter class="solr.FlattenGraphFilterFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
      <filter class="solr.EnglishMinimalStemFilterFactory"/>
      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_es.txt" ignoreCase="true"/>
      <filter class="solr.SpanishLightStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_eu.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <charFilter class="solr.PersianCharFilterFactory"/>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.ArabicNormalizationFilterFactory"/>
      <filter class="solr.PersianNormalizationFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_fa.txt" ignoreCase="true"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fi.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.ElisionFilterFactory" articles="lang/contractions_fr.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fr.txt" ignoreCase="true"/>
      <filter class="solr.FrenchLightStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.ElisionFilterFactory" articles="lang/contractions_ga.txt" ignoreCase="true"/>
      <filter class="solr.StopFilterFactory" words="lang/hyphenations_ga.txt" ignoreCase="true"/>
      <filter class="solr.IrishLowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_ga.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
    <analyzer type="index">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
    <analyzer type="index">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
    <analyzer type="index">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.ReversedWildcardFilterFactory" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_gl.txt" ignoreCase="true"/>
      <filter class="solr.GalicianStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.IndicNormalizationFilterFactory"/>
      <filter class="solr.HindiNormalizationFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_hi.txt" ignoreCase="true"/>
      <filter class="solr.HindiStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_hu.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_hy.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_id.txt" ignoreCase="true"/>
      <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ik" class="solr.TextField">
    <analyzer class="org.wltea.analyzer.lucene.IKAnalyzer"/>
  </fieldType>
  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_it.txt" ignoreCase="true"/>
      <filter class="solr.ItalianLightStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ja" class="solr.TextField" autoGeneratePhraseQueries="false" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
      <filter class="solr.JapaneseBaseFormFilterFactory"/>
      <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt"/>
      <filter class="solr.CJKWidthFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_ja.txt" ignoreCase="true"/>
      <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.KoreanTokenizerFactory" outputUnknownUnigrams="false" decompoundMode="discard"/>
      <filter class="solr.KoreanPartOfSpeechStopFilterFactory"/>
      <filter class="solr.KoreanReadingFormFilterFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_lv.txt" ignoreCase="true"/>
      <filter class="solr.LatvianStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_nl.txt" ignoreCase="true"/>
      <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_no.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_pt.txt" ignoreCase="true"/>
      <filter class="solr.PortugueseLightStemFilterFactory"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_ro.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_ru.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_sv.txt" ignoreCase="true"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.ThaiTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_th.txt" ignoreCase="true"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.TurkishLowerCaseFilterFactory"/>
      <filter class="solr.StopFilterFactory" words="lang/stopwords_tr.txt" ignoreCase="false"/>
      <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
    </analyzer>
  </fieldType>
  <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
    <analyzer>
      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    </analyzer>
  </fieldType>
  <field name="_root_" type="string" docValues="false" indexed="true" stored="false"/>
  <field name="_text_" type="text_general" multiValued="true" indexed="true" stored="false"/>
  <field name="_version_" type="plong" indexed="false" stored="false"/>
  <field name="content_ik" type="text_ik" indexed="true" stored="true"/>
  <field name="id" type="string" multiValued="false" indexed="true" required="true" stored="true"/>
  <field name="name" type="text_general"/>
  <field name="title_ik" type="text_ik" indexed="true" stored="true"/>
   <field name="title" type="text_ik" indexed="true" stored="true"/>
  <field name="text" type="text_ik" indexed="true" stored="true" omitNorms ="true"/>
  <field name="author" type="string" indexed="true" stored="true"/>
  <field name="fileSize" type="plong" indexed="true" stored="true"/>
  <field name="fileLastModified" type="pdate" indexed="true" stored="true"/>
  <field name="fileAbsolutePath" type="string" indexed="true" stored="true"/>
  
  
  
  <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
  <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
  <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
  <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
  <dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
  <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
  <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
  <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
  <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
  <dynamicField name="random_*" type="random"/>
  <dynamicField name="*_t_sort" type="text_gen_sort" multiValued="false" indexed="true" stored="true"/>
  <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
  <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
  <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
  <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
  <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
  <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
  <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
  <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
  <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
  <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
  <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
  <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
  <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
  <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
  <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
  <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
  <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
  <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
  <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
  <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
  <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
  <dynamicField name="*_txt_ko" type="text_ko" indexed="true" stored="true"/>
  <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
  <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
  <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
  <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
  <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
  <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
  <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
  <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
  <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
  <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
  <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
  <dynamicField name="attr_*" type="text_general" multiValued="true" indexed="true" stored="true"/>
  <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
  <dynamicField name="*_str" type="strings" docValues="true" indexed="false" stored="false" useDocValuesAsStored="false"/>
  <dynamicField name="*_dts" type="pdate" multiValued="true" indexed="true" stored="true"/>
  <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
  <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
  <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
  <dynamicField name="*_is" type="pints" indexed="true" stored="true"/>
  <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
  <dynamicField name="*_ls" type="plongs" indexed="true" stored="true"/>
  <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
  <dynamicField name="*_fs" type="pfloats" indexed="true" stored="true"/>
  <dynamicField name="*_ds" type="pdoubles" indexed="true" stored="true"/>
  <dynamicField name="*_dt" type="pdate" indexed="true" stored="true"/>
  <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
  <dynamicField name="*_i" type="pint" indexed="true" stored="true"/>
  <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
  <dynamicField name="*_l" type="plong" indexed="true" stored="true"/>
  <dynamicField name="*_t" type="text_general" multiValued="false" indexed="true" stored="true"/>
  <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
  <dynamicField name="*_f" type="pfloat" indexed="true" stored="true"/>
  <dynamicField name="*_d" type="pdouble" indexed="true" stored="true"/>
  <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
  <copyField source="name" dest="name_str" maxChars="256"/>
</schema>

在solr页面操作

在验证下：

  END:  在后面的篇章里，笔者会结合业务系统，做更多分析。

猜你喜欢

转载自www.cnblogs.com/woshuaile/p/12176462.html
今日推荐
面壁智能发布 Eurux-8x22B 开源大模型 —— 堪称「理科状元」
开源日报 | 谷歌扶持鸿蒙上位；开源Rabbit R1；Docker加持的安卓手机；微软的焦虑和野心；海尔电器把开放平台关了
中国码农的“35岁魔咒”
蘭雅 CorelDRAW 插件 2024.5.1 国际劳动节版，免费下载
Arc Browser for Windows 1.0 正式 GA
90后程序员开发视频搬运软件、不到一年获利超 700 万，结局很刑！
周排行
【转】spring中对控制反转和依赖注入的理解
tms webcore 安装和使用
java程序员进阶相关书籍
SpringMVC接受请求参数、
如何保存训练好的机器学习模型
MyEclipse、Eclipse设置项目JDK的三个地方
商超行业微信小程序开发定制一般多少钱 （行业技术人员解读）
Markdown编辑器语言——30分钟入门到到精通
Linux系统下MongoDB的简单安装与基本操作
Power Strings
每日归档
更多
2024-05-07(14)
2024-05-06(40)
2024-05-05(0)
2024-05-04(7)
2024-05-03(19)
2024-05-02(0)
2024-05-01(4)
2024-04-30(1)
2024-04-29(40)
2024-04-28(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022