版本分别支持到最新的 es v2.4.1和 es v5.0.0-rc1 新增若干特性，支持多种选项配置，支持 pinyin 的切分，比之前需要结合 ngram 的方式更加准确， 如：liudehuaalibaba13zhuanghan->liu,de,hua,a,li,ba,ba,13,zhuang,han， 具体配置参加文档： https://github.com/medcl/elast ... inyin   下载： https://github.com/medcl/elast ... eases   欢迎测试：

curl -XPUT http://localhost:9200/medcl/ -d'
{
    "index" : {
        "analysis" : {
            "analyzer" : {
                "pinyin_analyzer" : {
                    "tokenizer" : "my_pinyin"
                    }
            },
            "tokenizer" : {
                "my_pinyin" : {
                    "type" : "pinyin",
                    "keep_separate_first_letter" : false,
                    "keep_full_pinyin" : true,
                    "keep_original" : false,
                    "limit_first_letter_length" : 16,
                    "lowercase" : true
                }
            }
        }
    }
}'

curl http://localhost:9200/medcl/_a ... lyzer
{
  "tokens" : [ {
    "token" : "liu",
    "start_offset" : 0,
    "end_offset" : 1,
    "type" : "word",
    "position" : 0
  }, {
    "token" : "de",
    "start_offset" : 1,
    "end_offset" : 2,
    "type" : "word",
    "position" : 1
  }, {
    "token" : "hua",
    "start_offset" : 2,
    "end_offset" : 3,
    "type" : "word",
    "position" : 2
  }, {
    "token" : "a",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 3
  }, {
    "token" : "b",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 4
  }, {
    "token" : "c",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 5
  }, {
    "token" : "d",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 6
  }, {
    "token" : "liu",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 7
  }, {
    "token" : "de",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 8
  }, {
    "token" : "hua",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 9
  }, {
    "token" : "wo",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 10
  }, {
    "token" : "bu",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 11
  }, {
    "token" : "zhi",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 12
  }, {
    "token" : "dao",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 13
  }, {
    "token" : "shi",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 14
  }, {
    "token" : "shui",
    "start_offset" : 2,
    "end_offset" : 31,
    "type" : "word",
    "position" : 15
  }, {
    "token" : "ldhabcdliudehuaw",
    "start_offset" : 0,
    "end_offset" : 16,
    "type" : "word",
    "position" : 16
  } ]
}