Elasticsearch\uc758 \uc560\ub110\ub77c\uc774\uc800\ub294,
\n0 ~ 3 \uac1c\uc758 Character Filter,
\n1\uac1c\uc758 Tokenizer,
\n\uadf8\ub9ac\uace0 0 ~ n \uac1c\uc758 Token Filter \ub85c \uc774\ub8e8\uc5b4\uc9d1\ub2c8\ub2e4.<\/p>\n
Data type text \uac00 \uc785\ub825\ub418\uba74 \uac00\uc7a5 \uba3c\uc800 0 ~ 3 \uac1c\uc758 Character Filter \uac00 \uc801\uc6a9\ub429\ub2c8\ub2e4.<\/p>\n
\uc774 \ub2e8\uacc4\uc5d0\uc11c\ub294 text \uc5d0\uc11c \ud2b9\uc815 \ubb38\uc790\ub97c replace \ub610\ub294 \uc81c\uac70\ud558\uac8c \ub429\ub2c8\ub2e4.<\/p>\n
HTML Strip Character Filter<\/p>\n
html \uc744 \uc81c\uac70\ud569\ub2c8\ub2e4.<\/p>\n
GET \/_analyze<\/p>\n
{\n "tokenizer": "keyword",\n "char_filter": [\n "html_strip"\n ],\n "text": "<p>I'm so <b>happy<\/b>!<\/p>"\n}<\/code><\/pre>\nresponse<\/p>\n
{\n "tokens": [\n {\n "token": " I'm so happy! ",\n "start_offset": 0,\n "end_offset": 32,\n "type": "word",\n "position": 0\n }\n ]\n}<\/code><\/pre>\n<\/li>\n- \n
Mapping Character Filter<\/p>\n
\ubb38\uc790 \ub610\ub294 \ubb38\uc790\uc5f4\uc744 \ub2e4\ub978 \ubb38\uc790 \ub610\ub294 \ubb38\uc790\uc5f4\ub85c \ubcc0\ud658\ud574 \uc90d\ub2c8\ub2e4.<\/p>\n
\nmappings<\/code> : \ubc30\uc5f4\uc744 \ub370\uc774\ud0c0\ub85c \ud569\ub2c8\ub2e4.<\/li>\nmappings_path<\/code> : \ud30c\uc77c\uc5d0 \ub9e4\ud551\uc815\ubcf4\ub97c \uc800\uc7a5\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\nGET \/_analyze<\/p>\n
{\n "tokenizer": "keyword",\n "char_filter": [\n {\n "type": "mapping",\n "mappings": [\n "c++ => c_plus_plus"\n ]\n }\n ],\n "text": "c++"\n}<\/code><\/pre>\nresponse<\/p>\n
{\n "tokens": [\n {\n "token": "c_plus_plus",\n "start_offset": 0,\n "end_offset": 3,\n "type": "word",\n "position": 0\n }\n ]\n}<\/code><\/pre>\n<\/li>\n- \n
Pattern Replace Character Filter<\/p>\n
Java \uc815\uaddc\uc2dd\uc744 \uc774\uc6a9\ud55c \ubcc0\ud658\uc744 \ud569\ub2c8\ub2e4.<\/p>\n<\/li>\n<\/ul>\n
Tokenizer<\/h2>\n
Character Filter \ub97c \ud1b5\uacfc\ud55c text \ub294 1\uac1c\uc758 Tokenizer \uc5d0 \uc758\ud574,
\nN \uac1c\uc758 \ub2e8\uc5b4\ub85c \ubd84\ub9ac\ub429\ub2c8\ub2e4.<\/p>\n
\uc608\ub97c \ub4e4\uc5b4, whitespace Tokenizer \ub294 \uacf5\ubc31\ubb38\uc790\ub97c \uae30\uc900\uc73c\ub85c \ub2e8\uc5b4\ub97c \ucd94\ucd9c\ud574 \ub0c5\ub2c8\ub2e4.<\/p>\n
Tokenizer \uc885\ub958<\/h3>\n\ub2e8\uc5b4 \uae30\ubc18<\/h4>\n\n- \n
Standard Tokenizer<\/p>\n
whitespace Tokenizer \uc640 \uc720\uc0ac\ud558\uc9c0\ub9cc, \ub9c8\uce68\ud45c \ubb3c\uc74c\ud45c, \ub9c8\uc774\ub108\uc2a4 \ub4f1\uc744 \uc81c\uac70\ud569\ub2c8\ub2e4.<\/p>\n
POST _analyze<\/p>\n
{\n "tokenizer": "standard",\n "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."\n}<\/code><\/pre>\n<\/li>\n- \n
Whitespace Tokenizer<\/p>\n
\uacf5\ubc31\ubb38\uc790\ub97c \uae30\uc900\uc73c\ub85c \ub2e8\uc5b4\ub97c \ucd94\ucd9c\ud569\ub2c8\ub2e4.
\n\ub9c8\uce68\ud45c \ubb3c\uc74c\ud45c \ub4f1\uc744 \uc81c\uac70\ud558\uc9c0 \uc54a\uc2b5\ub2c8\ub2e4.<\/p>\n<\/li>\n
- \n
Classic Tokenizer<\/p>\n
\uc601\uc5b4\uc5d0 \ud2b9\ud654\ub41c Tokenizer \uc785\ub2c8\ub2e4.
\n\uc774\uba54\uc77c\uc8fc\uc18c, \ub3c4\uba54\uc778, \uc804\ud654\ubc88\ud638 \ub4f1\uc744 \uc778\uc2dd\ud569\ub2c8\ub2e4.<\/p>\n<\/li>\n<\/ul>\n
\ub2e8\uc5b4 \uc870\uac01\ud654<\/h4>\n\n- \n
N-Gram Tokenizer<\/p>\n
sliding window \ubc29\uc2dd\uc73c\ub85c \ub2e8\uc5b4\ub97c \uc870\uac01\ud654 \ud569\ub2c8\ub2e4.
\nsliding window \ub780 \uc624\ub978\ucabd\uc73c\ub85c \uc774\ub3d9\ud558\uba74\uc11c,
\n\uc77c\uc815\ud55c \uae38\uc774\ub9cc\ud07c \ub2e8\uc5b4\ub97c \uc870\uac01\ub0b4\ub294 \ubc29\uc2dd\uc785\ub2c8\ub2e4.<\/p>\n
\ub744\uc5b4\uc4f0\uae30 \uc548\ub41c \ud55c\uae00\uc744 \ud1a0\ud06c\ub098\uc774\uc9d5 \ud558\uae30\uc5d0 \uc801\ud569\ud569\ub2c8\ub2e4.<\/p>\n
quick \u2192 [qu, ui, ic, ck]<\/code><\/p>\ntoken_chars<\/code> \uc5d0\ub294 letter<\/code>, digit<\/code>, whitespace<\/code>, punctuation<\/code>, symbol<\/code>, custom<\/code> \uc774 \ud3ec\ud568\ub420 \uc218 \uc788\uc2b5\ub2c8\ub2e4.
\ncustom<\/code> \uc744 \uc4f0\uae30 \uc704\ud574\uc11c\ub294 custom_token_chars<\/code> \uac00 \uc138\ud305\ub418\uc5b4 \uc788\uc5b4\uc57c \ud569\ub2c8\ub2e4.<\/p>\nPUT my_index<\/p>\n
{\n "settings": {\n "max_ngram_diff": 20,\n "analysis": {\n "analyzer": {\n "my_analyzer": {\n "tokenizer": "my_tokenizer"\n }\n },\n "tokenizer": {\n "my_tokenizer": {\n "type": "ngram",\n "custom_token_chars": "+-_'",\n "min_gram": 1,\n "max_gram": 20,\n "token_chars": [\n "letter",\n "digit",\n "custom"\n ]\n }\n }\n }\n }\n}<\/code><\/pre>\nPOST my_index\/_analyze<\/p>\n
{\n "analyzer": "my_analyzer",\n "text": "1800\uc0ac\ubb34\uc6a9\ucc45\uc0c1"\n}<\/code><\/pre>\n<\/li>\n- \n
Edge N-Gram Tokenizer<\/p>\n
\uccab\uae00\uc790\ub97c \uc2dc\uc791\uc810\uc73c\ub85c \uae00\uc790\uc218\ub97c \ub298\ub824\uac00\uba74\uc11c \ub2e8\uc5b4\ub97c \uc870\uac01\ub0c5\ub2c8\ub2e4.<\/p>\n
quick \u2192 [q, qu, qui, quic, quick]<\/code><\/p>\n<\/li>\n<\/ul>\n\uad6c\uc870\ud654\ub41c \ub2e8\uc5b4<\/h4>\n
……<\/p>\n
Token Filter<\/h2>\n
Tokenizer \ub97c \uac70\uce5c \ub2e8\uc5b4\ub4e4\uc740 Token Filter \uc5d0 \uc758\ud574 \uc815\uc81c\ub429\ub2c8\ub2e4.<\/p>\n
\uc608\ub97c \ub4e4\uc5b4, lowercase \ub294 \ubaa8\ub4e0 \ub2e8\uc5b4\ub97c \uc18c\ubb38\uc790\ub85c \ubcc0\uacbd\ud569\ub2c8\ub2e4.<\/p>\n
Token Filter \uc885\ub958<\/h3>\n
\ucc38\uc870<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"Elasticsearch – Text Analysis 3\ub2e8\uacc4 Elasticsearch\uc758 \uc560\ub110\ub77c\uc774\uc800\ub294, 0 ~ 3 \uac1c\uc758 Character Filter, 1\uac1c\uc758 Tokenizer, \uadf8\ub9ac\uace0 0 ~ n \uac1c\uc758 Token Filter \ub85c \uc774\ub8e8\uc5b4\uc9d1\ub2c8\ub2e4. Character Filter Data type text \uac00 \uc785\ub825\ub418\uba74 \uac00\uc7a5 \uba3c\uc800 0 ~ 3 \uac1c\uc758 Character Filter \uac00 \uc801\uc6a9\ub429\ub2c8\ub2e4. \uc774 \ub2e8\uacc4\uc5d0\uc11c\ub294 text \uc5d0\uc11c \ud2b9\uc815 \ubb38\uc790\ub97c replace \ub610\ub294 \uc81c\uac70\ud558\uac8c \ub429\ub2c8\ub2e4. Character Filter \uc885\ub958 HTML\u2026 Read More »<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-6025","post","type-post","status-publish","format-standard","hentry","category-elasticsearch"],"_links":{"self":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6025","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6025"}],"version-history":[{"count":14,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6025\/revisions"}],"predecessor-version":[{"id":6051,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6025\/revisions\/6051"}],"wp:attachment":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6025"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6025"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6025"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}