Riak SOLR通过HTTP和日期范围?

时间:2014-06-07 02:41:03

标签: solr riak riak-search riak-cs

当使用SOLR api over HTTP搜索时,有人能告诉我Riak对日期格式的期望吗?我有一些索引的数据。通配符搜索确认:

{
    "responseHeader": {
        "status": 0,
        "QTime": 13,
        "params": {
            "q": "*",
            "q.op": "or",
            "filter": "",
            "wt": "json"
        }
    },
    "response": {
        "numFound": 2,
        "start": 0,
        "maxScore": "0.00000e+0",
        "docs": [
            {
                "id": "09d1bf74-9cdc-4001-8797-fc5a4b9170b0",
                "index": "TestIndex",
                "fields": {
                    "Timestamp_dt": "2014-06-06T02:10:35.367Z"
                },
                "props": {}
            },
            {
                "id": "09d1bf74-9cdc-4001-8797-fc5a4b9170b0",
                "index": "TestIndex",
                "fields": {
                    "Timestamp_dt": "2014-06-08T02:10:35.367Z"
                },
                "props": {}
            }
        ]
    }
}

我还确认我的架构正在将_dt作为日期时间:

%% Field names ending in "_dt" are indexed as dates
        {dynamic_field, [
            {name, "*_dt"},
            {type, date},
            {analyzer_factory, {erlang, text_analyzers, noop_analyzer_factory}}
        ]},

我尝试了很多变种,包括:

/solr/TestIndex/select?wt=json&q=Timestamp_dt:[20140508000000%20TO%2020140608000000]
/solr/TestIndex/select?wt=json&q=Timestamp_dt:[20140508T000000Z TO 20140607T000000Z]
/solr/TestIndex/select?wt=json&q=Timestamp_dt:%5B2014-05-08T00%3A00%3A00.000Z%20TO%202014-06-07T00%3A00%3A00.000Z%5D

我很难过,日期范围内的文档有点缺乏..有没有人让这个工作?我是否坚持转换为纪元日期?

1 个答案:

答案 0 :(得分:1)

日期字段使用noop分析器,因此索引文本将与您存储的完全一致。但是,冒号是查询中的活动字符,因此您需要在值中转义它:

% curl localhost:8098/buckets/testbucket/keys/1 -XPUT -H "content-type: application/json" \
  -d '{"item":"1","stamp_dt":"2014-06-06T02:10:35.367Z"}'
% curl localhost:8098/buckets/testbucket/keys/2 -XPUT -H "content-type: application/json" \
  -d '{"item":"2","stamp_dt":"2014-06-07T02:10:35.367Z"}'
% curl localhost:8098/buckets/testbucket/keys/3 -XPUT -H "content-type: application/json" \
  -d '{"item":"3","stamp_dt":"2014-06-07T06:10:35.367Z"}'

% curl -g 'localhost:8098/solr/testbucket/select?q=stamp_dt:2014-06-06T02\:10\:35.367Z'
<?xml version="1.0" encoding="UTF-8"?>
<response>
  <lst name="responseHeader">
    <int name="status">0</int>
    <int name="QTime">1</int>
    <lst name="params">
      <str name="indent">on</str>
      <str name="start">0</str>
      <str name="q">stamp_dt:2014-06-06T02\:10\:35.367Z</str>
      <str name="q.op">or</str>
      <str name="filter"></str>
      <str name="df">value</str>
      <str name="wt">standard</str>
      <str name="version">1.1</str>
      <str name="rows">1</str>
    </lst>
  </lst>
  <result name="response" numFound="1" start="0" maxScore="0.353553">
    <doc>
      <str name="id">1
      </str>
      <str name="item">1
      </str>
      <date name="stamp_dt">2014-06-06T02:10:35.367Z
      </date>
    </doc>
  </result>
</response>

您选择的日期格式也非常适合范围查询(不确定为什么必须将空格明确地url编码为%20):

% curl -g 'localhost:8098/solr/testbucket/select?q=stamp_dt:[2014-06-06%20TO%202014-06-07T23\:59]'
<?xml version="1.0" encoding="UTF-8"?>
<response>
  <lst name="responseHeader">
    <int name="status">0</int>
    <int name="QTime">4</int>
    <lst name="params">
      <str name="indent">on</str>
      <str name="start">0</str>
      <str name="q">stamp_dt:[2014-06-06 TO 2014-06-07T23\:59]</str>
      <str name="q.op">or</str>
      <str name="filter"></str>
      <str name="df">value</str>
      <str name="wt">standard</str>
      <str name="version">1.1</str>
      <str name="rows">3</str>
    </lst>
  </lst>
  <result name="response" numFound="3" start="0" maxScore="0.00000e+0">
    <doc>
      <str name="id">1
      </str>
      <str name="item">1
      </str>
      <date name="stamp_dt">2014-06-06T02:10:35.367Z
      </date>
    </doc>
    <doc>
      <str name="id">2
      </str>
      <str name="item">2
      </str>
      <date name="stamp_dt">2014-06-07T02:10:35.367Z
      </date>
    </doc>
    <doc>
      <str name="id">3
      </str>
      <str name="item">3
      </str>
      <date name="stamp_dt">2014-06-07T06:10:35.367Z
      </date>
    </doc>
  </result>
</response>