我需要在Solr索引中存储特殊字符。 我将尝试索引包含Solr特殊字符的mysql数据库,但是当我在生成的索引中搜索时,特殊字符的存储方式如下:�。
配置文件包括:
数据-config.xml中
<dataConfig>
<dataSource type="JdbcDataSource"
encoding="UTF-8"
URIEncoding="UTF-8"
driver="com.mysql.jdbc.Driver"
url="jdbc:mysql://localhost:3306/db_name"
user="***"
password="***" />
<document name="content">
<entity name="id" query="SELECT * FROM organization"
deltaImportQuery="SELECT * FROM organization" deltaQuery="SELECT * FROM organization">
<field column="organization_id" name="organization_id" />
<field column="name" name="name" />
<field column="cb_url" name="cb_url" />
<field column="cb_image_url" name="cb_image_url" />
<field column="fb_url" name="fb_url" />
<field column="tw_url" name="tw_url" />
<field column="ln_url" name="ln_url" />
<field column="city" name="city" />
<field column="region" name="region" />
<field column="state" name="state" />
<field column="cb_description" name="cb_description" />
<field column="last_change_date" name="last_change_date" />
<field column="al_id" name="al_id" />
<field column="al_url" name="al_url" />
<field column="al_followers" name="al_followers" />
<field column="al_pre_money_valuation" name="al_pre_money_valuation" />
<field column="al_raising_amount" name="al_raising_amount" />
<field column="al_blog_url" name="al_blog_url" />
<field column="fb_name" name="fb_name" />
<field column="fb_id" name="fb_id" />
<field column="fb_about" name="fb_about" />
<field column="fb_companyoverview" name="fb_companyoverview" />
<field column="fb_checkins" name="fb_checkins" />
<field column="fb_founded" name="fb_founded" />
<field column="fb_likes" name="fb_likes" />
<field column="fb_latitude" name="fb_latitude" />
<field column="fb_longitude" name="fb_longitude" />
<field column="fb_street" name="fb_street" />
<field column="fb_talkingabout" name="fb_talkingabout" />
<field column="ln_name" name="ln_name" />
<field column="ln_id" name="ln_id" />
<field column="ln_companytype" name="ln_companytype" />
<field column="ln_industries" name="ln_industries" />
<field column="ln_status" name="ln_status" />
<field column="ln_blogrssurl" name="ln_blogrssurl" />
<field column="ln_employeecountrange" name="ln_employeecountrange" />
<field column="ln_specialties" name="ln_specialties" />
<field column="ln_description" name="ln_description" />
<field column="ln_endyear" name="ln_endyear" />
<field column="ln_numfollowers" name="ln_numfollowers" />
<field column="tw_name" name="tw_name" />
<field column="tw_id" name="tw_id" />
<field column="tw_followers" name="tw_followers" />
<field column="tw_friendscount" name="tw_friendscount" />
<field column="tw_favouritescount" name="tw_favouritescount" />
<field column="tw_statusescount" name="tw_statusescount" />
</entity>
</document>
</dataConfig>
schema.xml中
<schema>
<fieldType name="text_split" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory" />
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<field name="organization_id" type="string" indexed="true"
stored="true" required="true" />
<field name="name" type="text_general" indexed="true" stored="true" />
<field name="cb_description" type="text_split" indexed="true"
stored="true" />
<field name="fb_about" type="text_split" indexed="true" stored="true" />
<field name="fb_companyoverview" type="text_split" indexed="true"
stored="true" />
<field name="ln_description" type="text_split" indexed="true"
stored="true" />
<field name="cb_url" type="text_split" indexed="true" stored="true" />
<field name="cb_image_url" type="text_split" indexed="true"
stored="true" />
<field name="fb_url" type="text_split" indexed="true" stored="true" />
<field name="tw_url" type="text_split" indexed="true" stored="true" />
<field name="ln_url" type="text_split" indexed="true" stored="true" />
<field name="city" type="text_split" indexed="true" stored="true" />
<field name="region" type="text_split" indexed="true" stored="true" />
<field name="state" type="text_split" indexed="true" stored="true" />
<field name="last_change_date" type="text_split" indexed="true"
stored="true" />
<field name="al_id" type="text_split" indexed="true" stored="true" />
<field name="al_url" type="text_split" indexed="true" stored="true" />
<field name="al_followers" type="text_split" indexed="true"
stored="true" />
<field name="al_pre_money_valuation" type="text_split" indexed="true"
stored="true" />
<field name="al_raising_amount" type="text_split" indexed="true"
stored="true" />
<field name="al_blog_url" type="text_split" indexed="true"
stored="true" />
<field name="fb_name" type="text_split" indexed="true" stored="true" />
<field name="fb_id" type="text_split" indexed="true" stored="true" />
<field name="fb_checkins" type="text_split" indexed="true"
stored="true" />
<field name="fb_founded" type="text_split" indexed="true" stored="true" />
<field name="fb_likes" type="text_split" indexed="true" stored="true" />
<field name="fb_latitude" type="text_split" indexed="true"
stored="true" />
<field name="fb_longitude" type="text_split" indexed="true"
stored="true" />
<field name="fb_street" type="text_split" indexed="true" stored="true" />
<field name="fb_talkingabout" type="text_split" indexed="true"
stored="true" />
<field name="ln_name" type="text_split" indexed="true" stored="true" />
<field name="ln_id" type="text_split" indexed="true" stored="true" />
<field name="ln_companytype" type="text_split" indexed="true"
stored="true" />
<field name="ln_industries" type="text_split" indexed="true"
stored="true" />
<field name="ln_status" type="text_split" indexed="true" stored="true" />
<field name="ln_blogrssurl" type="text_split" indexed="true"
stored="true" />
<field name="ln_employeecountrange" type="text_split" indexed="true"
stored="true" />
<field name="ln_specialties" type="text_split" indexed="true"
stored="true" />
<field name="ln_endyear" type="text_split" indexed="true" stored="true" />
<field name="ln_numfollowers" type="text_split" indexed="true"
stored="true" />
<field name="tw_name" type="text_split" indexed="true" stored="true" />
<field name="tw_id" type="text_split" indexed="true" stored="true" />
<field name="tw_followers" type="text_split" indexed="true"
stored="true" />
<field name="tw_friendscount" type="text_split" indexed="true"
stored="true" />
<field name="tw_favouritescount" type="text_split" indexed="true"
stored="true" />
<field name="tw_statusescount" type="text_split" indexed="true"
stored="true" />
</schema>