java - org.apache.solr.common.SolrException : Document is missing mandatory uniqueKey field: id

Question

我已经成功运行APache solr 6.1.0。我还创建了名为“Testcore”的新核心，并在 solr\Testcore 文件夹中添加所有必需的文件 solrconfig.xml、schema.xml。

现在我已在命令提示符中运行以下命令来索引 csv 文件:

C:\>java -Durl=http://localhost:8983/solr/Testcore/update/csv -Dtype=text/csv -jar C:\solr-6.1.0\server\lib/post.jar C:\messages\TestInsert-08-16-2016-15-47-solr.csv

现在，在索引 csv 文件时，我在命令提示符中收到以下错误响应代码:

SimplePostTool version 5.0.0
Posting files to [base] url http://localhost:8983/solr/Testcore/update/csv usin
g content-type text/csv...
POSTing file TestInsert-08-16-2016-15-47-solr.csv to [base]
SimplePostTool: WARNING: Solr returned an error #400 (Bad Request) for url: http
://localhost:8983/solr/Testcore/update/csv
SimplePostTool: WARNING: Response: <?xml version="1.0" encoding="UTF-8"?>
<response>
<lst name="responseHeader"><int name="status">400</int><int name="QTime">27</int
></lst><lst name="error"><lst name="metadata"><str name="error-class">org.apache
.solr.common.SolrException</str><str name="root-error-class">org.apache.solr.common.SolrException</str></lst><str name="msg">Document is missing mandatory uniqueKey field: id</str><int name="code">400</int></lst>
</response>
SimplePostTool: WARNING: IOException while reading response: java.io.IOException
: Server returned HTTP response code: 400 for URL: http://localhost:8983/solr/Testcore/update/csv
1 files indexed.
COMMITting Solr index changes to http://localhost:8983/solr/Testcore/update/csv
...
Time spent: 0:00:00.073 

因此，在响应代码中，它返回错误消息“文档缺少强制 uniqueKey 字段:id”。由于该错误，数据也没有在 solr 站点上建立索引。

我的 schema.xml 文件:

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

<schema name="example" version="1.5">

   <field name="_version_" type="long" indexed="true" stored="true"/>


   <field name="_root_" type="string" indexed="true" stored="false"/>


   <field name="id" type="string" indexed="true" stored="true" required="true" /> 


   <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
   <field name="name" type="text_general" indexed="true" stored="true"/>
   <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
   <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
   <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
   <field name="includes" type="text_general" indexed="true" stored="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" />

   <field name="store" type="location" indexed="true" stored="true"/>


   <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
   <field name="subject" type="text_general" indexed="true" stored="true"/>
   <field name="description" type="text_general" indexed="true" stored="true"/>
   <field name="comments" type="text_general" indexed="true" stored="true"/>
   <field name="author" type="text_general" indexed="true" stored="true"/>
   <field name="keywords" type="text_general" indexed="true" stored="true"/>
   <field name="category" type="text_general" indexed="true" stored="true"/>
   <field name="resourcename" type="text_general" indexed="true" stored="true"/>
   <field name="url" type="text_general" 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"/>


  <!-- Testcore  spcific fields -->


<field name="SRNO" type="int" indexed="true" stored="true"/> 
<field name="IDENTIFIER" type="string" indexed="true" stored="true"/>
<field name="AGENTID" type="string" indexed="true" stored="true"/>
<field name="AGENTNAME" type="string" indexed="true" stored="true"/>

<field name="event_timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
<field name="MONTH" type="string" indexed="true" stored="true"/>
<field name="DAY" type="string" indexed="true" stored="true"/>
<field name="TIMESTAMP" type="string" indexed="true" stored="true"/>
<field name="TYPE" type="string" indexed="true" stored="true"/>
<field name="TASKID" type="string" indexed="true" stored="true"/>

<!-- End of Testcore fields----->

     <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/>
     <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
     <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
     <field name="manu_exact" type="string" indexed="true" stored="false"/>
   <field name="payloads" type="payloads" indexed="true" stored="true"/>

   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
   <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
   <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_en"  type="text_en"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
   <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>

   <!-- Type used to index the lat and lon components for the "location" FieldType -->
   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" />

   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>

   <!-- some trie-coded dynamic fields for faster range queries -->
   <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="*_c"   type="currency" indexed="true"  stored="true"/>

   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
   <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>

   <dynamicField name="random_*" type="random" />




 <!-- 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 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="manu" dest="manu_exact"/>

   <!-- Copy the price into a currency enabled field (default USD) -->
   <copyField source="price" dest="price_c"/>

   <!-- Text fields from SolrCell to search by default in our catch-all field -->
   <copyField source="title" dest="text"/>
   <copyField source="author" dest="text"/>
   <copyField source="description" dest="text"/>
   <copyField source="keywords" dest="text"/>
   <copyField source="content" dest="text"/>
   <copyField source="content_type" dest="text"/>
   <copyField source="resourcename" dest="text"/>
   <copyField source="url" dest="text"/>

   <!-- Create a string version of author for faceting -->
   <copyField source="author" dest="author_s"/>

     <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
    <fieldType name="uuid" class="solr.UUIDField" indexed="true" />

    <!-- boolean type: "true" or "false" -->
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>


    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>


    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>


    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>

    <!-- A Trie based date field for faster date range queries and date faceting. -->
    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>


    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
    <fieldtype name="binary" class="solr.BinaryField"/>


    <fieldType name="random" class="solr.RandomSortField" indexed="true" />



    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="managed_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.ManagedStopFilterFactory" managed="english" />
        <filter class="solr.ManagedSynonymFilterFactory" managed="english" />
      </analyzer>
    </fieldType>


    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />

        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

       <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>

    <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <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.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <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" positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>

        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.EnglishMinimalStemFilterFactory"/>

        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
           maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>


    <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.KeywordTokenizerFactory"/>
        <!-- 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" />

        <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.WhitespaceTokenizerFactory"/>

        <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.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory" />
      </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="ancestor_path" class="solr.TextField">
      <analyzer type="index">
    <tokenizer class="solr.KeywordTokenizerFactory" />
      </analyzer>
      <analyzer type="query">
    <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
      </analyzer>
    </fieldType>

    <!-- since fields of this type are by default not stored or indexed,
         any data added to them will be ignored outright.  --> 
    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />

    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>

    <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
    <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>

    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
        geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />

    <fieldType name="bbox" class="solr.BBoxField"
        geo="true" units="degrees" numberType="_bbox_coord" />
    <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" stored="false"/>


    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />


</schema>

在 csv 文件中有以下字段:SRNO、IDENTIFIER、AGENTID、AGENTNAME、event_timestamp、MONTH、DAY、TIMESTAMP、TYPE、TASKID这些字段及其数据类型添加到 schema.xml 文件中。

请帮助我解决这个问题。提前致谢。

Answer 1

您只需删除 schema.xml 文件顶部声明为 id 的 uniqueKey 字段即可。还要从 id 字段中删除 required=true 属性。使用文档具有的任何其他字段作为唯一键。