使用最新 solr4.10 快速开发团购网站等垂直搜索网站
说明:
1,环境搭建,使用solr4.10 版本
从apache 官方网站下载最新的 solr 4.10.0 http://lucene.apache.org/solr/
团购数据从 hao123 的官方网站接口找到的,大家都可以获得,公开的数据。
http://www.hao123.com/redian/api.htm 美团数据下载:http://www.meituan.com/api/deals/hao123 一共
1.27G 非常大,因为是没有压缩的xml数据,(使用htttp下载,用工具可能会被封。)。
将工程修改成maven的工程,因为不是开发solr而是使用solr,在example下面有个war包,解压缩到maven工程。
2,配置solr
<urlset> <url> <loc>http://bj.meituan.com/deal/6330826.html?source=hao123</loc> <data> <display> <website>美团网</website> <siteurl>http://bj.meituan.com</siteurl> <city>北京</city> <sort>休闲娱乐</sort> <title>【2店通用】CGV星星国际影城单人电影票1张,2D/3D可兑</title> <image>http://p1.meituan.net/275.168/deal/201301/04/173144_2860489.jpg</image> <startTime>1373040000</startTime> <endTime>1377943200</endTime> <value>100</value> <price>30</price> <rebate>3折</rebate> <bought>13593</bought> <spend_start_time>1373040000</spend_start_time> <spend_close_time>1377964799</spend_close_time> <longitude>116.490591</longitude> <latitude>39.970472</latitude> <collections>0</collections> <type>2</type> <soldout>no</soldout> </display> </data> </url> .... </urlset>
在工程根目录下面 有个solr文件夹,下面是solr的配置文件,其中一个子文件夹,tuan是团购的配置文件夹。
工程是用mave搭建的,扩展性更强。
根据美团的数据,将配置solr的数据文件。
参考:
<?xml version="1.0" encoding="UTF-8" ?> <schema name="example" version="1.5"> <fields> <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> <field name="title" type="text_general" indexed="true" stored="true" /> <field name="image" type="string" indexed="false" stored="true" /> <field name="value" type="double" indexed="false" stored="true" /> <field name="price" type="double" indexed="true" stored="true" /> <field name="rebate" type="double" indexed="true" stored="true" /> <field name="bought" type="long" indexed="true" stored="true" /> <field name="city" type="string" indexed="true" stored="true" /> <field name="sort" type="string" indexed="true" stored="true" /> <field name="loc" type="string" indexed="true" stored="true" /> <field name="startTime" type="date" indexed="true" stored="true" /> <field name="endTime" type="date" indexed="true" stored="true" /> <!-- catchall field, containing all other searchable text fields (implemented via copyField further on in this schema --> <field name="text" type="text_general" indexed="true" stored="false" multiValued="true" /> <field name="_version_" type="long" indexed="true" stored="true" /> </fields> <uniqueKey>id</uniqueKey> <copyField source="title" dest="text" /> <types> <fieldType name="string" class="solr.StrField" sortMissingLast="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" /> <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0" /> <fieldtype name="binary" class="solr.BinaryField" /> <fieldType name="pint" class="solr.IntField" /> <fieldType name="plong" class="solr.LongField" /> <fieldType name="pfloat" class="solr.FloatField" /> <fieldType name="pdouble" class="solr.DoubleField" /> <fieldType name="pdate" class="solr.DateField" sortMissingLast="true" /> <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.LowerCaseFilterFactory" /> </analyzer> <analyzer type="query"> <tokenizer class="solr.StandardTokenizerFactory" /> <filter class="solr.LowerCaseFilterFactory" /> </analyzer> </fieldType> <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) --> <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100"> <analyzer> <tokenizer class="solr.StandardTokenizerFactory" /> <!-- normalize width before bigram, as e.g. half-width dakuten combine --> <filter class="solr.CJKWidthFilterFactory" /> <!-- for any non-CJK --> <filter class="solr.LowerCaseFilterFactory" /> <filter class="solr.CJKBigramFilterFactory" /> </analyzer> </fieldType> </types> </schema>
配置:solrconfig.xml
<!-- 增加xml 数据导入 --> <requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler"> <lst name="defaults"> <str name="config">xml-data-config.xml</str> </lst> </requestHandler> <requestHandler name="/browse" class="solr.SearchHandler"> <lst name="defaults"> <str name="echoParams">explicit</str> <!-- VelocityResponseWriter settings --> <str name="wt">velocity</str> <str name="v.properties">velocity.properties</str> <str name="v.contentType">text/html;charset=utf-8</str> <str name="v.template">browse</str> <str name="v.layout">layout</str> <str name="title">团购网站demo</str> <!-- Query settings --> <str name="defType">edismax</str> <str name="df">text</str> <str name="mm">100%</str> <str name="q.alt">*:*</str> <str name="rows">32</str> <str name="fl">*,score</str> <!-- Faceting defaults --> <str name="facet">on</str> <str name="facet.field">city</str> <str name="facet.field">sort</str> <str name="facet.range">price</str> <int name="f.price.facet.range.start">100</int> <int name="f.price.facet.range.end">1500</int> <int name="f.price.facet.range.gap">200</int> <!-- Highlighting defaults --> <str name="hl">on</str> <str name="hl.fl">title</str> <str name="hl.encoder">html</str> <str name="hl.simple.pre"><font colr='red' ></str> <str name="hl.simple.post"></font></str> <str name="f.title.hl.fragsize">0</str> <str name="f.title.hl.alternateField">title</str> <!-- Spell checking defaults --> <str name="spellcheck">on</str> <str name="spellcheck.extendedResults">false</str> <str name="spellcheck.count">5</str> <str name="spellcheck.alternativeTermCount">2</str> <str name="spellcheck.maxResultsForSuggest">5</str> <str name="spellcheck.collate">true</str> <str name="spellcheck.collateExtendedResults">true</str> <str name="spellcheck.maxCollationTries">5</str> <str name="spellcheck.maxCollations">3</str> </lst> <!-- append spellchecking to our list of components --> <arr name="last-components"> <str>spellcheck</str> </arr> </requestHandler>
<dataConfig> <script><![CDATA[ function ReplaceLocAddId(row) { var loc_1 = row.get('loc').split('/deal/'); var loc_2 = loc_1[1].split('.html'); var id = loc_2[0]; row.put('id', id); //格式化时间. var sdf = new java.text.SimpleDateFormat('yyyy-MM-dd HH:mm:ss'); //开始时间. row.put('startTime', com.demo.tuan.DateUtils.format(row.get('startTime'))); //结束时间. row.put('endTime', com.demo.tuan.DateUtils.format(row.get('endTime'))); //去掉折扣汉字. row.put('rebate', row.get('rebate').replace('折','')); return row; } ]]></script> <dataSource type="FileDataSource" encoding="utf-8" /> <document> <entity name="tuan" pk="loc" url="/data/workspace.freewebsys/solr4_demo/doc/meituan_hao123.xml" processor="XPathEntityProcessor" forEach="/urlset/url" transformer="script:ReplaceLocAddId,DateFormatTransformer"> <field column="loc" xpath="/urlset/url/loc" commonField="true" /> <field column="city" xpath="/urlset/url/data/display/city" commonField="true" /> <field column="sort" xpath="/urlset/url/data/display/sort" commonField="true" /> <field column="title" xpath="/urlset/url/data/display/title" commonField="true" /> <field column="image" xpath="/urlset/url/data/display/image" commonField="true" /> <field column="value" xpath="/urlset/url/data/display/value" commonField="true" /> <field column="price" xpath="/urlset/url/data/display/price" commonField="true" /> <field column="rebate" xpath="/urlset/url/data/display/rebate" commonField="true" /> <field column="bought" xpath="/urlset/url/data/display/bought" commonField="true" /> <field column="startTime" xpath="/urlset/url/data/display/startTime" dateTimeFormat="yyyy-MM-dd HH:mm:ss" commonField="true" /> <field column="endTime" xpath="/urlset/url/data/display/endTime" dateTimeFormat="yyyy-MM-dd HH:mm:ss" commonField="true" /> </entity> </document> </dataConfig>
配置好了,开始导入数据:管理后台,使用超级方便。界面也非常漂亮。
3,修改页面显示
4,代码提交:
郑重声明:本站内容如果来自互联网及其他传播媒体,其版权均属原媒体及文章作者所有。转载目的在于传递更多信息及用于网络分享,并不代表本站赞同其观点和对其真实性负责,也不构成任何其他建议。