Как сделать поиск по нескольким словам в SOLRJQuery
В настоящее время я работаю с SolrJ API для нашего веб-приложения. Нам нужно иметь поиск нескольких слов в приложении. Но я не знаю, как это сделать.
Вот код, который мы разработали до сих пор, выполняя поиск в Интернете.
HttpSolrClient solr = new HttpSolrClient("http://localhost:8983/solr/Test");
SolrQuery query = new SolrQuery();
query.setQuery("product_name:Dell laptop*");
query.setFields("product_name");
query.setStart(0);
query.setRows(1000);
QueryResponse response = solr.query(query);
SolrDocumentList results = response.getResults();
for (int i = 0; i < results.size(); ++i) {
System.out.println(results.get(i));
}
Но я не получаю никакого результата. Наш Solr имеет встроенную в него монго БД с помощью административной консоли apache Solr, работающей на порту 8983.
Пожалуйста помоги. Я новичок в Apache SOLR.
Обновление: вот schema.xml, который мы создали
<?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" multiValued="false" />
<field name="product_name" type="string" indexed="true" stored="true" required="true" multiValued="true"/>
<field name="product_url" type="string" indexed="true" stored="true" required="true" multiValued="true"/>
<field name="product_img" type="string" indexed="true" stored="true" required="true" multiValued="true"/>
<field name="product_price" type="double" indexed="true" stored="true" required="true" multiValued="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"/>
<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"/>
<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" />
<uniqueKey>id</uniqueKey>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
<fieldType name="binary" class="solr.BinaryField"/>
<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="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>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.TrimFilterFactory" />
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
<fieldType name="bbox" class="solr.BBoxField"
geo="true" distanceUnits="kilometers" 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>
А вот и данные-config.xml
<?xml version="1.0" encoding="UTF-8" ?>
<dataConfig>
<dataSource name="client_XXXX" type="MongoDataSource" database="client_XXXX" host="192.168.11.XXX" port="27017"/>
<document name="Titles">
<entity name="TitleEntity"
processor="MongoEntityProcessor"
query=""
collection="XXXX_data"
datasource="client_XXXX"
transformer="MongoMapperTransformer" >
<field column="product_name" name="product_name"/>
<field column="product_url" name="product_url"/>
<field column="product_img" name="product_img"/>
<field column="product_price" name="product_price"/>
<field column="_id" name="id"/>
</entity>
</document>
</dataConfig>
2 ответа
Решение
Мы создали новый schema.xml, удалив ненужные ссылки. Вот схема, которую мы использовали.
<schema name="example" version="1.5">
<field name="_version_" type="long" indexed="true" stored="true"/>
<field name="_root_" type="string" indexed="true" stored="false"/>
<fields>
<field name="id" type="long" indexed="true" stored="true" required="true" multiValued="false" />
<field name="product_name" type="string" indexed="true" stored="true" required="true" />
<field name="product_price" type="" indexed="true" stored="true" required="true" />
</fields>
<uniqueKey>id</uniqueKey>
<types>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0" />
<fieldType name="text_wslc" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
</types>
<defaultSearchField>product_name</defaultSearchField>
<!-- we don't want too many results in this usecase -->
<solrQueryParser defaultOperator="AND"/>
</schema>
То, с чем вы сталкиваетесь, упоминается в JavaDoc от Lucene. Почему Lucene? Синтаксис запроса Solr является расширенным набором Lucene. Как уже упоминалось
Примечание. Поле действительно только для термина, которому оно предшествует, поэтому запрос
title: Сделай это правильно
Найти только "До" в поле заголовка. Он найдет "это" и "право" в поле по умолчанию (в данном случае текстовое поле).
В вашем случае только Dell направляется в поле product_name, остальное - в поле поиска по умолчанию, определенное в вашей конфигурации.
То, что вы хотите использовать, чтобы обойти это, называется группировкой полей. Поэтому вам нужно заключить слова, которые должны идти в одно поле, в круглые скобки, например так:
SolrQuery query = new SolrQuery();
query.setQuery("product_name:(Dell laptop*)"); // surround the words with ( ... )
query.setFields("product_name");
query.setStart(0);
query.setRows(1000);