Emoticon analyzer

emoticon list

e_smiley        :-) :) :o) :] :3 :c) :> =] 8) =) :} :^) :っ) :-)) :-))) :-)))) :)) :))) :))))
e_laugh         :-D :D 8-D 8D x-D xD X-D XD =-D =D =-3 =3 B^D
e_sad           >:[ :-( :(  :-c :c :-<  :っC :< :-[ :[ :{
e_wink_frown    ;(
e_angry         :-|| :@ >:(
e_cry           :'-( :'(
e_happy_tears   :'-) :')
e_disgust       D:< D: D8 D; D= DX v.v D-':
e_surprise      >:O :-O :O :-o :o 8-0 O_O o-o O_o o_O o_o O-O
e_kiss          :* :^*  '}{'
e_wink          ;-) ;) *-) *) ;-] ;] ;D ;^) :-,
e_tongue        >:P :-P :P X-P x-p xp XP :-p :p =p :-Þ :Þ :þ :-þ :-b :b d:
e_skeptical     >:\ >:/ :-/ :-. :/ :\ =/ =\ :L =L :S >.<
e_neutral       :| :-|
e_embarrassed   :$ :S
e_silent        :-X :X :-# :#
e_halo          O:-) 0:-3 0:3 0:-) 0:) 0;^)
e_evil          >:) >;) >:-)
e_devil         }:-) }:) 3:-) 3:)
e_highfive      o/\o ^5 >_>^ ^<_<
e_disapprove    ಠ_ಠ
e_cheer         \o/
e_heart         <3
e_broken_heart  </3

emoticons.json

DELETE /test

PUT /test 
{
  "settings": {
    "analysis": {
      "char_filter": {
        "e_happy_tears": {
          "pattern": "\\:\\'(?:\\-\\)|\\))",
          "type": "pattern_replace",
          "replacement": " e_happy_tears "
        },
        "e_wink_frown": {
          "pattern": "\\;\\(",
          "type": "pattern_replace",
          "replacement": " e_wink_frown "
        },
        "e_broken_heart": {
          "pattern": "\\<\\/3",
          "type": "pattern_replace",
          "replacement": " e_broken_heart "
        },
        "e_silent": {
          "pattern": "\\:(?:\\-[\\#X]|[\\#X])",
          "type": "pattern_replace",
          "replacement": " e_silent "
        },
        "e_cheer": {
          "pattern": "\\\\o\\/",
          "type": "pattern_replace",
          "replacement": " e_cheer "
        },
        "e_tongue": {
          "pattern": "(?:\\:(?:\\-[PbpÞþ]|[PbpÞþ])|\\=p|\\>\\:P|X(?:\\-P|P)|d\\:|x(?:\\-p|p))",
          "type": "pattern_replace",
          "replacement": " e_tongue "
        },
        "e_wink": {
          "pattern": "(?:\\*(?:\\-\\)|\\))|\\:\\-\\,|\\;(?:\\-[\\)\\]]|\\^\\)|[\\)D\\]]))",
          "type": "pattern_replace",
          "replacement": " e_wink "
        },
        "e_laugh": {
          "pattern": "(?:8(?:\\-D|D)|\\:(?:\\-D|D)|\\=(?:\\-[3D]|[3D])|B\\^D|X(?:\\-D|D)|x(?:\\-D|D))",
          "type": "pattern_replace",
          "replacement": " e_laugh "
        },
        "e_surprise": {
          "pattern": "(?:8\\-0|\\:(?:\\-[Oo]|[Oo])|\\>\\:O|O(?:\\-O|_[Oo])|o(?:\\-o|_[Oo]))",
          "type": "pattern_replace",
          "replacement": " e_surprise "
        },
        "e_disapprove": {
          "pattern": "ಠ_ಠ",
          "type": "pattern_replace",
          "replacement": " e_disapprove "
        },
        "e_embarrassed": {
          "pattern": "\\:[\\$S]",
          "type": "pattern_replace",
          "replacement": " e_embarrassed "
        },
        "e_kiss": {
          "pattern": "(?:\\'\\}\\{\\'|\\:(?:\\^\\*|\\*))",
          "type": "pattern_replace",
          "replacement": " e_kiss "
        },
        "e_cry": {
          "pattern": "\\:\\'(?:\\-\\(|\\()",
          "type": "pattern_replace",
          "replacement": " e_cry "
        },
        "e_devil": {
          "pattern": "(?:3\\:(?:\\-\\)|\\))|\\}\\:(?:\\-\\)|\\)))",
          "type": "pattern_replace",
          "replacement": " e_devil "
        },
        "e_angry": {
          "pattern": "(?:\\:(?:\\-\\|\\||\\@)|\\>\\:\\()",
          "type": "pattern_replace",
          "replacement": " e_angry "
        },
        "e_halo": {
          "pattern": "(?:0(?:\\:(?:\\-[\\)3]|[\\)3])|\\;\\^\\))|O\\:\\-\\))",
          "type": "pattern_replace",
          "replacement": " e_halo "
        },
        "e_disgust": {
          "pattern": "(?:D(?:\\-\\'\\:|\\:\\<?|[8\\;\\=X])|v\\.v)",
          "type": "pattern_replace",
          "replacement": " e_disgust "
        },
        "e_skeptical": {
          "pattern": "(?:\\:(?:\\-[\\.\\/]|[\\/LS\\\\])|\\=[\\/L\\\\]|\\>(?:\\.\\<|\\:[\\/\\\\]))",
          "type": "pattern_replace",
          "replacement": " e_skeptical "
        },
        "e_evil": {
          "pattern": "\\>(?:\\:(?:\\-\\)|\\))|\\;\\))",
          "type": "pattern_replace",
          "replacement": " e_evil "
        },
        "e_smiley": {
          "pattern": "(?:8\\)|\\:(?:\\)(?:\\)(?:\\)\\)?)?)?|\\-\\)(?:\\)(?:\\)\\)?)?)?|\\^\\)|c\\)|o\\)|っ\\)|[3\\>\\]\\}])|\\=[\\)\\]])",
          "type": "pattern_replace",
          "replacement": " e_smiley "
        },
        "e_highfive": {
          "pattern": "(?:\\>_\\>\\^|\\^(?:\\<_\\<|5)|o\\/\\\\o)",
          "type": "pattern_replace",
          "replacement": " e_highfive "
        },
        "e_neutral": {
          "pattern": "\\:(?:\\-\\||\\|)",
          "type": "pattern_replace",
          "replacement": " e_neutral "
        },
        "e_heart": {
          "pattern": "\\<3",
          "type": "pattern_replace",
          "replacement": " e_heart "
        },
        "e_sad": {
          "pattern": "(?:\\:(?:\\-[\\(\\<\\[c]|っC|[\\(\\<\\[c\\{])|\\>\\:\\[)",
          "type": "pattern_replace",
          "replacement": " e_sad "
        }
      },
      "analyzer": {
        "emoticons": {
          "filter": [
            "lowercase"
          ],
          "char_filter": [
            "e_smiley",
            "e_laugh",
            "e_sad",
            "e_wink_frown",
            "e_angry",
            "e_cry",
            "e_happy_tears",
            "e_disgust",
            "e_surprise",
            "e_kiss",
            "e_wink",
            "e_tongue",
            "e_skeptical",
            "e_neutral",
            "e_embarrassed",
            "e_silent",
            "e_halo",
            "e_evil",
            "e_devil",
            "e_highfive",
            "e_disapprove",
            "e_cheer",
            "e_heart",
            "e_broken_heart"
          ],
          "tokenizer": "standard"
        }
      }
    }
  }
}

# "Awesome day ;) don't you think?"
GET /test/_analyze?analyzer=emoticons&pretty=1&text=Awesome+day+%3B)+don't+you+think%3F

# {
#    "tokens" : [
#       {
#          "end_offset" : 7,
#          "position" : 1,
#          "start_offset" : 0,
#          "type" : "<ALPHANUM>",
#          "token" : "awesome"
#       },
#       {
#          "end_offset" : 11,
#          "position" : 2,
#          "start_offset" : 8,
#          "type" : "<ALPHANUM>",
#          "token" : "day"
#       },
#       {
#          "end_offset" : 13,
#          "position" : 3,
#          "start_offset" : 13,
#          "type" : "<ALPHANUM>",
#          "token" : "e_wink"
#       },
#       {
#          "end_offset" : 20,
#          "position" : 4,
#          "start_offset" : 15,
#          "type" : "<ALPHANUM>",
#          "token" : "don't"
#       },
#       {
#          "end_offset" : 24,
#          "position" : 5,
#          "start_offset" : 21,
#          "type" : "<ALPHANUM>",
#          "token" : "you"
#       },
#       {
#          "end_offset" : 30,
#          "position" : 6,
#          "start_offset" : 25,
#          "type" : "<ALPHANUM>",
#          "token" : "think"
#       }
#    ]
# }

Reading this made me remember nearly a decade old code I wrote !

http://www.mircscripts.org/showdoc.php?type=code&id=3033

Very interesting technique of doing replacements with partterns char filters by the way, would have never thought of doing that!