okky_job_sample

PUT okky_job_sample
{
  "settings": {
    "index": {
      "analysis": {
        "analyzer": {
          "korean_nori_analyzer": {
            "type": "custom",
            "char_filter" : ["html_strip"],
            "tokenizer": "korean_nori_tokenizer",
            "filter" : [
                "korean_nori_part_of_speech",
                "lowercase",
                "stemmer_filter",
                "word_length_filter",
                "puntucation_replace_filter"
              ]
          },
        "pattern_analyzer" :{
            "type": "custom",
            "char_filter" : ["html_strip"],
            "tokenizer": "pattern_tokenizer",
            "filter" : [
                "lowercase",
                "stemmer_filter",
                "josa_replace_filter",
                "word_length_filter",
                "puntucation_replace_filter"
              ]        
          }
        },
        "tokenizer": {
          "pattern_tokenizer": {                    
              "pattern": "[ ]",
              "type": "pattern"
                },          
          "korean_nori_tokenizer": {
            "type": "nori_tokenizer",
            "decompound_mode": "mixed"
          }
        },
        "filter":{
           "korean_nori_part_of_speech": {
              "type": "nori_part_of_speech",
              "stoptags": [
                            "E",
                            "J",
                            "MAG",
                            "MAJ",
                            "MM",
                            "SP",
                            "SSC",
                            "SSO",
                            "SC",
                            "SE",
                            "SF",
                            "XSA",
                            "XSN",
                            "XSV",
                            "UNA",
                            "NA",
                            "VSV",
                            "VCP",
                            "VCN"
                         ]           
           },                
           "word_length_filter": {
              "type": "length",
              "min": 2
                },
           "stemmer_filter": {
              "type": "stemmer",
              "name": "porter2"
          },
          "josa_replace_filter": {
              "type": "pattern_replace",
              "pattern": "[은는을를의에이가할된]",
              "replacement": ""
          },
          "puntucation_replace_filter": {
              "type": "pattern_replace",
              "pattern": "[\\.?!]{1,}$",
              "replacement": ""
          }
          }
        }
      }
    }
  }

GET okky_job_sample/_analyze
{
  "analyzer": "korean_nori_analyzer",
  "text": "서울시 강남구"
}

{
  "tokens" : [
    {
      "token" : "서울시",
      "start_offset" : 0,
      "end_offset" : 3,
      "type" : "word",
      "position" : 0,
      "positionLength" : 2
    },
    {
      "token" : "서울",
      "start_offset" : 0,
      "end_offset" : 2,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "강남구",
      "start_offset" : 4,
      "end_offset" : 7,
      "type" : "word",
      "position" : 2,
      "positionLength" : 2
    },
    {
      "token" : "강남",
      "start_offset" : 4,
      "end_offset" : 6,
      "type" : "word",
      "position" : 2
    }
  ]
}


GET okky_job_sample/_analyze
{
  "analyzer": "pattern_analyzer",
  "text": "c++"
}


GET okky_job_sample/_analyze
{
  "analyzer": "korean_nori_analyzer",
  "text": "하늘을"
}