ElasticSearch 入门（转）

最大的特点：
1. 数据库的 database, 就是 index
2. 数据库的 table, 就是 tag
3. 不要使用browser，使用curl来进行客户端操作. 否则会出现 java heap ooxx...

curl: -X 后面跟 RESTful ： GET, POST ...
-d 后面跟数据。 (d = data to send)

1. create:

指定 ID 来建立新记录。（貌似PUT， POST都可以）
$ curl -XPOST localhost:9200/films/md/2 -d '
{ "name":"hei yi ren", "tag": "good"}'

使用自动生成的 ID 建立新纪录：
$ curl -XPOST localhost:9200/films/md -d '
{ "name":"ma da jia si jia3", "tag": "good"}'

2. 查询：
2.1 查询所有的 index, type:
$ curl localhost:9200/_search?pretty=true

2.2 查询某个index下所有的type:
$ curl localhost:9200/films/_search

2.3 查询某个index 下，某个 type下所有的记录：
$ curl localhost:9200/films/md/_search?pretty=true

2.4 带有参数的查询：
$ curl localhost:9200/films/md/_search?q=tag:good
{"took":7,"timed_out":false,"_shards":{"total":5,"successful":5,"failed":0},"hits":{"total":2,"max_score":1.0,"hits":[{"_index":"film","_type":"md","_id":"2","_score":1.0, "_source" :
{ "name":"hei yi ren", "tag": "good"}},{"_index":"film","_type":"md","_id":"1","_score":0.30685282, "_source" :
{ "name":"ma da jia si jia", "tag": "good"}}]}}

2.5 使用JSON参数的查询：（注意 query 和 term 关键字）
$ curl localhost:9200/film/_search -d '
{"query" : { "term": { "tag":"bad"}}}'

3. update
$ curl -XPUT localhost:9200/films/md/1 -d { ...(data)... }

4. 删除。删除所有的：

$ curl -XDELETE localhost:9200/films

---------------------------------------------------------------------------------------------------------

角色关系对照

elasticsearch 跟 MySQL 中定义资料格式的角色关系对照表如下

MySQL elasticsearch
database index
table type

table schema mapping
row document
field field

3.索引映射

#创建索引
$ curl -XPUT http://localhost:9200/test-index

#创建Mapping
$ curl -XPUT http://localhost:9200/test-index/test-type/_mapping -d '{
"properties" : {
"name" : { "type" : "string" }
}
}'

@route('/indexsetting/')
def indexmapping():
  """索引映射"""
conn = ES('127.0.0.1:9200')
conn.debug_dump = True
  try:
  #删除索引
conn.delete_index("test-index")
  except:
  pass
  #创建索引
conn.create_index("test-index")
mapping = {
u'id': {'store': 'yes',
  'type': u'integer'},
u'author': {'boost': 1.0,
'index': 'not_analyzed',
'store': 'yes',
'type': u'string'},
u'published': {'boost': 1.0,
  'index': 'not_analyzed',
  'store': 'yes',
  'type': u'datetime'},
u'url': {'store': 'yes',
  'type': u'string'},
u'title': {'boost': 1.0,
'index': 'analyzed',
'store': 'yes',
'type': u'string'},
u'content': {'boost': 1.0,
'index': 'analyzed',
'store': 'yes',
'type': u'string',
"term_vector" : "with_positions_offsets"}
}
  #索引映射
conn.put_mapping("test-type", {'properties':mapping}, ["test-index"])
  return "索引映射"

4.索引

#索引
$ curl -XPUT http://localhost:9200/test-index/test-type/1 -d '{
"user": "kimchy",
"post_date": "2009-11-15T13:12:00",
"message": "Trying out elasticsearch, so far so good?"
}'

#获取
$ curl -XGET http://localhost:9200/test-index/test-type/1

#删除
$ curl -XDELETE 'http://localhost:9200/test-index/test-type/1'

@route('/indextest/')
def indexTest():
  """索引测试"""
conn = ES('127.0.0.1:9200')
  for item in Data().getData():
  #添加索引
conn.index(item,"test-index", "test-type",item['id'])

#索引优化
conn.optimize(["test-index"])
#删除索引内容
conn.delete("test-index", "test-type", 2668090)
#更新索引内容
model = conn.get("test-index", "test-type", 2667371)
model["title"]="标题修改测试"
conn.update(model,"test-index", "test-type",2667371)

#刷新索引
conn.refresh(["test-index"])

q = MatchAllQuery()
results = conn.search(query = q,indices="test-index",doc_types="test-type")
# for r in results:
# print r
return template('default.tpl', list=results,count=len(results))

5.搜索

#lucene语法方式的查询
$ curl -XGET http://localhost:9200/test-index/test-type/_search?q=user:kimchy

#query DSL方式查询
$ curl -XGET http://localhost:9200/test-index/test-type/_search -d '{
"query" : {
"term" : { "user": "kimchy" }
}
}'

#query DSL方式查询
$ curl -XGET http://localhost:9200/test-index/_search?pretty=true -d '{
"query" : {
"range" : {
"post_date" : {
"from" : "2009-11-15T13:00:00",
"to" : "2009-11-15T14:30:00"
}
}
}
}'

#查找全部索引内容
$ curl -XGET http://localhost:9200/test-index/test-type/_search?pretty=true

@route('/search/')
@route('/search/<searchkey>')
def search(searchkey=u"关键算法"):
"""索引搜索"""
conn = ES('127.0.0.1:9200')

#TextQuery会对searchkey进行分词
qtitle = TextQuery("title", searchkey)
qcontent = TextQuery("content", searchkey)
#发布时间大于"2012-9-2 22:00:00"
qpublished=RangeQuery(ESRangeOp("published", "gt", datetime(2012, 9,2, 22, 0, 0)))

h = HighLighter(['<b>'], ['</b>'], fragment_size=500)
#多字段搜索(must=>and,should=>or)，高亮，结果截取（分页），排序
q = Search(BoolQuery(must=[qpublished],should=[qtitle,qcontent]),highlight=h, start=0, size=3, sort={'id': {'order': 'asc'}})
q.add_highlight("title")
q.add_highlight("content")
results = conn.search(query = q,indices="test-index",doc_types="test-type")

list=[]
  for r in results:
  if(r._meta.highlight.has_key("title")):
r['title']=r._meta.highlight[u"title"][0]
  if(r._meta.highlight.has_key("content")):
r['content']=r._meta.highlight[u"content"][0]
  list.append(r)
  return template('search.tpl', list=list,count=results.total)

6.设置

#创建索引，并设置分片和副本参数
$ curl -XPUT http://localhost:9200/elasticsearch/ -d '{
"settings" : {
"number_of_shards" : 2,
"number_of_replicas" : 3
}
}'

7.其他

#分词
curl -XGET 'http://localhost:9200/test-index/_analyze?text=中华人民共和国'