查询 - 学习性查询 - 《不积跬步无以至千里(技术)》


http://my.oschina.net/u/730537/blog/288703
这是初始化创建index和mapping的代码：
$elasticaClient = new \Elastica\Client(array('host'=>'localhost','port'=>9200));
   // Load index
   $elasticaIndex = $elasticaClient->getIndex('links');
   // Create the index new
   // 创建index的参数自行参见官网，就不一一解释了
   $elasticaIndex->create(
       array(
           'number_of_shards' => 4,
           'number_of_replicas' => 1,
           'analysis' => array(
               'analyzer' => array(
                   'indexAnalyzer' => array(
                       'type' => 'custom',
                       'tokenizer' => 'standard',
                       'filter' => array('lowercase', 'mySnowball')
                   ),
                   'searchAnalyzer' => array(
                       'type' => 'custom',
                       'tokenizer' => 'standard',
                       'filter' => array('standard', 'lowercase', 'mySnowball')
                   )
               ),
               'filter' => array(
                   'mySnowball' => array(
                       'type' => 'snowball',
                       'language' => 'German'
                   )
               )
           )
       ),
       true
   );
   //创建media的mapping,作为父级
   $mediaType = $elasticaIndex->getType('media');
   // Define mapping
   $mapping = new \Elastica\Type\Mapping();
   $mapping->setType($mediaType);
   $mapping->setParam('index_analyzer', 'indexAnalyzer');
   $mapping->setParam('search_analyzer', 'searchAnalyzer');
   // Define boost field
   $mapping->setParam('_boost', array('name' => '_boost', 'null_value' => 1.0));
   // Set mapping
   // 定义media的字段和属性
   $mapping->setProperties(array(
       'id'      => array('type' => 'string', 'include_in_all' => FALSE),
       'media_name'     => array('type' => 'string', 'include_in_all' => TRUE),
       'tstamp'  => array('type' => 'date', 'include_in_all' => FALSE),
       'language' => array('type' => 'integer', 'include_in_all' => FALSE),
       '_boost'  => array('type' => 'float', 'include_in_all' => FALSE)
   ));
   // Send mapping to type
   // 保存media的mapping
   $mapping->send();
   //创建question的mapping,父级为media
   $questionType = $elasticaIndex->getType('question');
   // Define mapping
   $mapping = new \Elastica\Type\Mapping();
   $mapping->setType($questionType);
   $mapping->setParam('index_analyzer', 'indexAnalyzer');
   $mapping->setParam('search_analyzer', 'searchAnalyzer');
   // Define boost field
   $mapping->setParam('_boost', array('name' => '_boost', 'null_value' => 1.0));
   // Set mapping
   // question的字段和属性
   $mapping->setProperties(array(
       'id'      => array('type' => 'string', 'include_in_all' => FALSE),
       'level_one'      => array('type' => 'integer', 'include_in_all' => FALSE),
       'level_two'      => array('type' => 'integer', 'include_in_all' => FALSE),
       'level_thr'      => array('type' => 'integer', 'include_in_all' => FALSE),
       'top_level'      => array('type' => 'string', 'include_in_all' => FALSE),
       'cat_id'      => array('type' => 'integer', 'include_in_all' => FALSE),
       'quest_hash'      => array('type' => 'string', 'include_in_all' => TRUE),
       'content'     => array('type' => 'string', 'include_in_all' => TRUE),
       'view_num'      => array('type' => 'integer', 'include_in_all' => FALSE),
       'like_num'      => array('type' => 'integer', 'include_in_all' => FALSE),
       '_boost'  => array('type' => 'float', 'include_in_all' => FALSE)
   ));
   $mapping->setParent("media");//指定question的父类
   // Send mapping to type
   // 保存question的mapping
   $mapping->send();
上面虽然是PHP代码，但是最终生成的也是一个url请求。
下面说搜索，搜索的话ES是通过query、filter等来处理的，query里面有很多不同的方式，参见：http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/query-dsl-queries.html，filter也是，参见http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/query-dsl-filters.html
这里搜索是这样的，根据media的media_name做query_string搜索，然后对media进行has_child的filter搜索，has_child搜索内使用boolAnd的filter来筛选。
下面是搜索的代码：
$query = new \Elastica\Query();
if (!empty($input['key'])) {
   //针对media的media_name字段设置QueryString查询
   $elasticaQueryString  = new \Elastica\Query\QueryString();
   $elasticaQueryString->setFields(array("media.media_name"));
   $elasticaQueryString->setQuery($input['key']);
   //
   $query->setQuery($elasticaQueryString);
}else {
   $query->setQuery(new MatchAll()); //命中全部纪录
}
$language_bool = false;
$elasticaFilterAnd = new \Elastica\Filter\BoolAnd();
//language也是针对media，设置BoolAnd查询
if (isset($input['language']) && !empty($input['language'])) {
   $filterl1 = new \Elastica\Filter\Term();
   $filterl1->setTerm('language', intval($input['language']));
   $elasticaFilterAnd->addFilter($filterl1);
   $language_bool = true;
}
//
//对子集进行筛选查询，使用has_child
$subFilterAnd = new \Elastica\Filter\BoolAnd();
$bool = false;
// 一级分类条件
if (isset($input['level_one']) && !empty($input['level_one'])) {
   $filterl1 = new \Elastica\Filter\Term();
   $filterl1->setTerm('level_one', intval($input['level_one']));
   $subFilterAnd->addFilter($filterl1);
   $bool = true;
}
// 二级分类条件
if (isset($input['level_two']) && !empty($input['level_two'])) {
   $filterl1 = new \Elastica\Filter\Term();
   $filterl1->setTerm('level_two', intval($input['level_two']));
   $subFilterAnd->addFilter($filterl1);
   $bool = true;
}
// 三级分类条件
if (isset($input['level_thr']) && !empty($input['level_thr'])) {
   $filterl1 = new \Elastica\Filter\Term();
   $filterl1->setTerm('level_thr', intval($input['level_thr']));
   $subFilterAnd->addFilter($filterl1);
   $bool = true;
}
// 直接指定分类ID查询
if (isset($input['cat_id']) && !empty($input['cat_id'])) {
   $filterl1 = new \Elastica\Filter\Term();
   $filterl1->setTerm('cat_id', intval($input['cat_id']));
   $subFilterAnd->addFilter($filterl1);
   $bool = true;
}
// 分类属性查询
if (isset($input['top_level']) && !empty($input['top_level'])) {
   $filterl1 = new \Elastica\Filter\Term();
   $filterl1->setTerm('top_level', $input['top_level']);
   $subFilterAnd->addFilter($filterl1);
   $bool = true;
}
if($bool){
   // 声明一个查询，用于放入子查询
   $subQuery = new \Elastica\Query();
   // 使用filteredquery，融合query和filter
   $filteredQuery = new \Elastica\Query\Filtered(new MatchAll(),$subFilterAnd);
   // 添加filterquery到子查询
   $subQuery->setQuery($filteredQuery);
   // 声明hasChildFilter，声明的时候就指定子查询的内容，指定查询的子表（也就是TYPE）为question
   $filterHasChild = new \Elastica\Filter\HasChild($subQuery,"question");
   // 将拥有子类查询增加到父级查询的filter中
   $elasticaFilterAnd->addFilter($filterHasChild);
}
if($bool || $language_bool){
   // 将filter增加到父查询汇中
   $query->setFilter($elasticaFilterAnd);
}
//
//        
$query->setFrom($start);    // Where to start?
$query->setLimit($limit);   // How many?
//
//Search on the index.
$elasticaResultSet = $elasticaIndex->search($query);
在处理过程中，感谢之前的哥们留下的代码，至少不是摸瞎。感谢同事搞的谷歌搜索，一般人我不告诉他，大家可以去试试 另客网，首页的搜索框里面，选择谷歌。
http://www.links123.com/
部分借鉴来自于这里：http://www.spacevatican.org/2012/6/3/fun-with-elasticsearch-s-children-and-nested-documents/