{"id":41424,"date":"2023-12-31T00:45:00","date_gmt":"2022-12-23T03:00:02","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/"},"modified":"2024-05-04T16:04:50","modified_gmt":"2024-05-04T08:04:50","slug":"%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/","title":{"rendered":"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668&#8221; Sudachi&#8221;"},"content":{"rendered":"<h2>\u592a\u957f\u4e0d\u770b\uff08\u7b80\u79f0TL;DR\uff09<\/h2>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Kuromoji\u306b\u4ee3\u308f\u308b\u65b0\u3057\u3044\u5f62\u614b\u7d20\u89e3\u6790\u5668\u300cSudachi\u300d<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u306a\u306b\u304c\u826f\u3044\u306e\uff1f<\/ul>\n<\/li>\n<\/ul>\n<p>\u6700\u65b0\u306e\u8f9e\u66f8<br \/>\n\u4f01\u696d\uff08\u30ef\u30fc\u30af\u30b9\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u30ba\uff09\u306b\u3088\u308b\u7d99\u7d9a\u7684\u306a\u66f4\u65b0<br \/>\n\u8907\u6570\u306e\u5206\u5272\u5358\u4f4d \u2192 \u691c\u7d22\u7528\u9014\u3067\u306e\u518d\u73fe\u7387\u3068\u9069\u5408\u7387\u306e\u5411\u4e0a<br \/>\n\u30d7\u30e9\u30b0\u30a4\u30f3\u306b\u3088\u308b\u62e1\u5f35<br \/>\n\u7701\u30e1\u30e2\u30ea<\/p>\n<p>Elasticsearch\u3067\u4f7f\u3044\u305f\u3044<\/p>\n<p>\u30d7\u30e9\u30b0\u30a4\u30f3: WorksApplications\/elasticsearch-sudachi<\/p>\n<p>\u4f7f\u3044\u65b9\u306f\u5f53\u8a18\u4e8b\u306e\u5f8c\u534a\u3092\u3054\u89a7\u304f\u3060\u3055\u3044<\/p>\n<p>\u8bf7\u6ce8\u610f\uff1a\u672c\u6587\u7684\u4f5c\u8005\u53c2\u4e0e\u4e86Sudachi\u7684\u5f00\u53d1\u3002<\/p>\n<h2>\u5404\u79cd\u5404\u6837\u7684\u5f62\u6001\u7d20\u5206\u6790\u5668<\/h2>\n<p>\u5f62\u614b\u7d20\u89e3\u6790\u662f\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08Natural Language Processing, NLP\uff09\u4e2d\u7684\u57fa\u7840\u6280\u672f\u3002\u4e16\u754c\u4e0a\u5b58\u5728\u7740\u5404\u79cd\u5f62\u614b\u7d20\u89e3\u6790\u5668\uff0c\u6709\u4e9b\u662f\u53ef\u4f9b\u8d2d\u4e70\u7684\uff0c\u4f46\u4e5f\u6709\u4e00\u4e9b\u662f\u516c\u5f00\u7684\u3002\u4e3e\u4f8b\u6765\u8bf4\uff0cJUMAN++\u662f\u5229\u7528JUMAN\u548cRNNLM\u5f00\u53d1\u7684\uff0c\u8fd8\u6709ChaSen\uff08\u4e5f\u53ebChampion-Segmenter\uff09\u548c\u5b83\u7684\u540e\u7ee7\u8005MeCab\uff0c\u76ee\u524d\u662f\u6700\u8457\u540d\u7684\u5f62\u614b\u7d20\u89e3\u6790\u5668\u3002\u8fd8\u6709\u53ef\u4ee5\u901a\u8fc7\u70b9\u4f30\u8ba1\u4ece\u90e8\u5206\u6ce8\u91ca\u6570\u636e\u4e2d\u8fdb\u884c\u5b66\u4e60\u7684KyTea\uff0ckuromoji\u5728Elasticsearch\u4e2d\u6709\u5b98\u65b9\u652f\u6301\uff0c\u8fd8\u6709\u4f7f\u7528\u7eafGo\/JavaScript\/Python\u5b9e\u73b0\u5e76\u5e26\u6709\u8bcd\u5178\u7684kagome\/kuromoji.js\/Janome\u7b49\u89e3\u6790\u5668\u3002\u9664\u4e86\u8f6f\u4ef6\u5f62\u5f0f\uff0c\u8fd8\u6709\u901a\u8fc7Web API\u63d0\u4f9b\u7684\u5f62\u614b\u7d20\u89e3\u6790\u5668\uff08\u4f8b\u5982Yahoo! JAPAN\u6587\u672c\u5206\u6790Web API\uff09\u3002\u56e0\u4e3a\u6709\u5404\u79cd\u4e0d\u540c\u7684\u89e3\u6790\u5668\uff0c\u6240\u4ee5\u4e5f\u6709\u4e00\u4e9b\u5e93\uff08\u5982JapaneseTokenizers\uff09\u53ef\u4ee5\u96c6\u5408\u591a\u4e2a\u89e3\u6790\u5668\u4e00\u8d77\u4f7f\u7528\u3002<\/p>\n<p>\u9664\u6b64\u4e4b\u5916\u8fd8\u6709\u5176\u4ed6\u4e00\u4e9b\u8ddf\u6240\u8c13\u7684\u5206\u8bcd\u89e3\u6790\u7684\u5b9a\u4e49\u7a0d\u6709\u51fa\u5165\u7684\u5de5\u5177\uff0c\u6bd4\u5982\u57fa\u4e8eJavaScript\u5b9e\u73b0\u7684Rakuten MA\uff08\u5206\u8bcd+\u8bcd\u6027\u6807\u6ce8\uff09\u3001\u540c\u6837\u7531JavaScript\u5f00\u53d1\u7684\u7b80\u6d01\u5206\u8bcd\u5de5\u5177TinySegmenter\uff0c\u4ee5\u53ca\u6700\u8fd1\u57fa\u4e8e\u795e\u7ecf\u7f51\u7edc\u65b9\u6cd5\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5206\u8bcd\u5de5\u5177SentencePiece\u7b49\u3002\u6b64\u5916\uff0c\u8fd8\u6709\u4e00\u4e2a\u7279\u522b\u503c\u5f97\u4e00\u63d0\u7684\u9879\u76ee\u662f\u96ea\u3060\u308b\u307e\uff0c\u5b83\u81f4\u529b\u4e8e\u6839\u672c\u6539\u8fdb\u4ee5\u5f80\u7684\u5206\u8bcd\u89e3\u6790\uff0c\u53ef\u4ee5\u8bf4\u662f\u4e00\u4e2a\u9ad8\u5ea6\u7406\u5ff5\u9a71\u52a8\u7684\u65e5\u672c\u8bed\u8a00\u89e3\u6790\u7cfb\u7edf\u9879\u76ee\u3002<\/p>\n<p>\u5927\u591a\u6570\u60c5\u51b5\u4e0b\uff0c\u5f62\u6001\u7d20\u89e3\u6790\u90fd\u9700\u8981\u4f7f\u7528\u5b57\u5178\u4ee5\u53ca\u7ecf\u8fc7\u6ce8\u91ca\u7684\u8bad\u7ec3\u6570\u636e\u6216\u5df2\u8bad\u7ec3\u7684\u6a21\u578b\u3002\u4f5c\u4e3a\u8bed\u8a00\u8d44\u6e90\uff0cUnidic\u8f9e\u5178\/BCCWJ\u8bed\u6599\u5e93\u3001IPA\u8f9e\u5178\/\u8bed\u6599\u5e93\u3001Juman\u8f9e\u5178\/\u4eac\u90fd\u8bed\u6599\u5e93\u3001NAIST JDic\u7b49\u662f\u4e3b\u8981\u7684\u8d44\u6e90\u3002\u7531\u4e8e\u8fd9\u4e9b\u8d44\u6e90\u4e0d\u7ecf\u5e38\u66f4\u65b0\uff0c\u56e0\u6b64\u8bb8\u591a\u4eba\u4e5f\u4f1a\u540c\u65f6\u4f7f\u7528\u4ece\u7f51\u7edc\u6587\u672c\u4e2d\u6536\u96c6\u548c\u8bb0\u5f55\u65b0\u8bcd\u7684NEologd\u3002<\/p>\n<p>2018\u5e743\u6708\uff0c\u5c06\u5728\u4e3e\u529e\u7b2c24\u5c4a\u5e74\u5ea6\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5b66\u4f1a(NLP2018)\u5e74\u4f1a\uff0c\u5176\u4e2d\u6709\u4e00\u4e2a\u9898\u4e3a\u201c\u5f62\u6001\u5206\u6790\u7684\u73b0\u5728\u4e0e\u672a\u6765\u201d\u7684\u7814\u8ba8\u4f1a\u5c06\u4e8e\u8fd1\u671f\u4e3e\u884c\uff0c\u9884\u8ba1\u4f1a\u6709\u70ed\u70c8\u7684\u8ba8\u8bba\u3002\u6b64\u5916\uff0c\u636e\u6089\u8fd1\u65e5\u5c06\u51fa\u7248\u4e00\u672c\u7531\u5de5\u85e4\u62d3\u5148\u751f\u64b0\u5199\u7684\u5b8c\u5168\u5173\u4e8e\u5f62\u6001\u5206\u6790\u7684\u75af\u72c2\u4e4b\u4f5c\uff0c\u4ed6\u4e5f\u662fMeCab\u548cSentencePiece\u7684\u4f5c\u8005\u3002\u53ef\u4ee5\u8bf4\uff0c\u5f62\u6001\u5206\u6790\u5982\u4eca\u4e3a\u4f55\u5982\u6b64\u706b\u70ed\u3002<\/p>\n<h2>&#8230;\u8fd8\u6709\u4e00\u79cd\u53eb\u505a\u300cSudachi\u300d\u7684\u5f62\u6001\u7d20\u89e3\u6790\u5668\u3002<\/h2>\n<p>\u5728\u8fd9\u4e9b\u4e2d\uff0c2017\u5e74\u8bde\u751f\u4e86\u4e00\u4e2a\u540d\u4e3a&#8221;Sudachi&#8221;\u7684\u5168\u65b0\u89e3\u6790\u5668\u3002\u5728\u5df2\u7ecf\u5b58\u5728\u5404\u79cd\u5de5\u5177\u7684\u60c5\u51b5\u4e0b\uff0c\u5b83\u5ba3\u79f0\u662f\u4e00\u4e2a\u9002\u7528\u4e8e\u5546\u4e1a\u7528\u9014\u3001\u66f4\u9ad8\u54c1\u8d28\u548c\u4f7f\u7528\u4fbf\u5229\u7684\u8bcd\u6cd5\u5206\u6790\u5668\u3002<\/p>\n<p>\u958b\u767a\u6d3b\u52d5\u4e3b\u8981\u5728\u682a\u5f0f\u4f1a\u793e\u30ef\u30fc\u30af\u30b9\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u30ba\u65d7\u4e0b\u7684\u30ef\u30fc\u30af\u30b9\u5fb3\u5cf6\u4eba\u5de5\u667a\u80fdNLP\u7814\u7a76\u6240\u8fdb\u884c\u3002\u5728\u4f01\u4e1a\u7684\u652f\u6301\u4e0b\uff0c\u5c06\u4ee3\u7801\u548c\u8bed\u8a00\u8d44\u6e90\u4f5c\u4e3a\u5f00\u6e90\u8f6f\u4ef6\u5bf9\u5916\u516c\u5f00\u3002\u8bb8\u53ef\u8bc1\u4e3aApache-2.0\u3002<\/p>\n<p>\u9996\u5148\uff0cSudachi\u7684\u7279\u9ede\u4e4b\u4e00\u662f\u63d0\u4f9b\u6700\u65b0\u7684\u8a5e\u5178\u3002\u73fe\u6709\u7684\u5f62\u614b\u7d20\u89e3\u6790\u5668\u8a5e\u5178\u5df2\u7d93\u505c\u6b62\u66f4\u65b0\u8d85\u904e10\u5e74\uff0c\u65b0\u8a5e\u548c\u5c08\u6709\u540d\u8a5e\u4e5f\u4e0d\u8db3\u3002\u7136\u800c\uff0cSudachi\u5247\u662f\u57fa\u65bcUniDic\u548cNEologd\u9032\u884c\u8abf\u6574\uff0c\u63d0\u4f9b\u4e86\u7531\u5c08\u5bb6\u8abf\u6574\u7684\u9ad8\u54c1\u8cea\u4e14\u5927\u898f\u6a21\u7684\u8cc7\u6e90\uff0c\u4e26\u8a08\u5283\u5728\u672a\u4f8610\u5e74\u6301\u7e8c\u9032\u884c\u66f4\u65b0\u3002<\/p>\n<p>\u5728\u5176\u4ed6\u65b9\u9762\uff0cSudachi\u8fd8\u5177\u6709\u4ee5\u591a\u4e2a\u5206\u5272\u5355\u5143\u8f93\u51fa\u7684\u529f\u80fd\u3002\u901a\u5e38\u60c5\u51b5\u4e0b\uff0c\u5f62\u6001\u5206\u6790\u5668\u53ea\u80fd\u4ee5\u4e00\u4e2a\u5355\u5143\u8fdb\u884c\u8f93\u51fa\uff0c\u4f46\u662fSudachi\u53ef\u4ee5\u4ee5A\u3001B\u3001C\u4e09\u4e2a\u5355\u5143\u8fdb\u884c\u8f93\u51fa\u3002\u8fd9\u662f\u901a\u8fc7\u5411Sudachi\u7684\u7cfb\u7edf\u8bcd\u5178\u6dfb\u52a0\u5206\u5272\u4fe1\u606f\u6765\u5b9e\u73b0\u7684\u3002<\/p>\n<p>\u5f53\u8f93\u5165\u4e3a\u201c\u533b\u836f\u54c1\u5b89\u5168\u7ba1\u7406\u8d1f\u8d23\u4eba\u201d\u65f6\uff0c\u53ef\u80fd\u6709\u4ee5\u4e0b3\u79cd\u8f93\u51fa\u9009\u9879\u3002<\/p>\n<pre class=\"post-pre\"><code>A: \u533b\u85ac \/ \u54c1 \/ \u5b89\u5168 \/ \u7ba1\u7406 \/ \u8cac\u4efb \/ \u8005\r\nB: \u533b\u85ac\u54c1 \/ \u5b89\u5168 \/ \u7ba1\u7406 \/ \u8cac\u4efb\u8005\r\nC: \u533b\u85ac\u54c1\u5b89\u5168\u7ba1\u7406\u8cac\u4efb\u8005\r\n<\/code><\/pre>\n<p>\u5728\u4f20\u7edf\u7684\u5f62\u6001\u7d20\u5206\u6790\u5668\u4e2d\uff0c\u53ea\u80fd\u6309\u7167A\u6216B\u8fd9\u6837\u7684\u5355\u4f4d\u8fdb\u884c\u5206\u5272\uff0c\u4f46\u662fSudachi\u8fd8\u53ef\u4ee5\u5c06\u7279\u5b9a\u8868\u8fbe\u4f5c\u4e3a\u5177\u6709\u610f\u4e49\u7684\u8bed\u8a00\u5355\u4f4d\u8fdb\u884c\u5224\u522b\uff0c\u6bd4\u5982C\u3002<\/p>\n<p>\u901a\u8fc7\u540c\u65f6\u4f7f\u7528\u77ed\u5355\u4f4d\u548c\u957f\u5355\u4f4d\uff0c\u53ef\u4ee5\u63d0\u9ad8\u5728\u641c\u7d22\u7528\u9014\u4e2d\u7684\u53ec\u56de\u7387\u548c\u7cbe\u786e\u7387\uff08\u5728\u540e\u9762\u63d0\u5230\u7684Elasticseach\u63d2\u4ef6\u7684\u641c\u7d22\u6a21\u5f0f\u4e2d\uff0c\u5c06\u4f7f\u7528A\u5355\u4f4d\u548cC\u5355\u4f4d\u540c\u65f6\uff09\u3002<\/p>\n<p>\u9664\u4e86\u5206\u5272\u4fe1\u606f\u5916\uff0cSudachi\u7684\u7cfb\u7edf\u8bcd\u5178\u8fd8\u5305\u62ec\u4ee5\u4e0b\u62fc\u5199\u89c4\u8303\u5316\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u9001\u308a\u9055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>\u6253\u8fbc\u3080 \u2192 \u6253\u3061\u8fbc\u3080<\/p>\n<p>\u5b57\u7a2e<\/p>\n<p>\u304b\u3064\u4e3c \u2192 \u30ab\u30c4\u4e3c<\/p>\n<p>\u7570\u4f53\u5b57<\/p>\n<p>\u9644\u5c5e \u2192 \u4ed8\u5c5e<\/p>\n<p>\u8aa4\u7528<\/p>\n<p>\u30b7\u30e5\u30df\u30ec\u30fc\u30b7\u30e7\u30f3 \u2192 \u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3<\/p>\n<p>\u7e2e\u7d04<\/p>\n<p>\u3061\u3083\u3042 \u2192 \u3066\u306f<\/p>\n<p>\u8fd9\u662f\u4e00\u4e2a\u9ad8\u54c1\u8d28\u7684\u7cfb\u7edf\u8bcd\u5178\uff0c\u7528\u6237\u53ef\u4ee5\u81ea\u884c\u51c6\u5907\u591a\u4e2a\u7528\u6237\u8bcd\u5178\u6765\u8fdb\u884c\u6269\u5c55\u3002<\/p>\n<p>\u6b64\u5916\uff0c\u60a8\u8fd8\u53ef\u4ee5\u901a\u8fc7\u63d2\u4ef6\u8fdb\u884c\u529f\u80fd\u6269\u5c55\u3002\u60a8\u53ef\u4ee5\u5c06\u901a\u5e38\u5728\u89e3\u6790\u5668\u5916\u8fdb\u884c\u7684\u6b63\u89c4\u5316\u548c\u6821\u6b63\u7b49\u5e38\u89c1\u5904\u7406\u8fc7\u7a0b\u5305\u542b\u8fdb\u6765\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u63d2\u4ef6\u7684\u7c7b\u578b\uff0c\u5176\u4e2d\u4e00\u4e9b\u5df2\u7ecf\u4f5c\u4e3a\u7cfb\u7edf\u63d0\u4f9b\u7684\u63d2\u4ef6\u5b58\u5728\uff0c\u5e76\u4e14\u5176\u4ed6\u63d2\u4ef6\u76ee\u524d\u4e5f\u6b63\u5728\u5f00\u53d1\u4e2d\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u5165\u529b\u30c6\u30ad\u30b9\u30c8: \u7570\u4f53\u5b57\u7d71\u5236\u3001\u9577\u97f3\u8a18\u53f7\u6b63\u898f\u5316\u3001\u306a\u3069<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u672a\u77e5\u8a9e: 1\u6587\u5b57\u672a\u77e5\u8a9e\u30ce\u30fc\u30c9\u306e\u4f5c\u6210\u3001MeCab\u4e92\u63db\u51e6\u7406\u3001\u306a\u3069<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u5358\u8a9e\u306e\u9023\u63a5: \u54c1\u8a5e\u63a5\u7d9a\u7981\u5236\u3001\u30b3\u30b9\u30c8\u5024\u306e\u66f8\u304d\u63db\u3048\u3001\u306a\u3069<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u51fa\u529b\u89e3\u88dc\u6b63: \u656c\u79f0\u3084\u524d\u5f8c\u95a2\u4fc2\u304b\u3089\u4eba\u540d\u90e8\u3092\u63a8\u5b9a\u3001\u6f22\u6570\u8a5e\u3084\u4f4d\u53d6\u308a\u306e\u6b63\u898f\u5316\u3001\u306a\u3069<\/ul>\n<p>\u5f53\u7136\uff0c\u60a8\u4e5f\u53ef\u4ee5\u81ea\u5df1\u7f16\u5199\u63d2\u4ef6\u5e76\u63d2\u5165\u3002\u4f8b\u5982\uff0c\u60a8\u53ef\u4ee5\u8fdb\u884c\u81ea\u5b9a\u4e49\u7684\u672a\u77e5\u8bcd\u5904\u7406\uff0c\u6216\u6839\u636e\u76ee\u6807\u6570\u636e\u63d0\u53d6\u4ea7\u54c1\u7f16\u53f7\u548c\u578b\u53f7\u7b49\u3002<\/p>\n<p>\u6b64\u5916\uff0c\u901a\u8fc7\u4f7f\u7528\u5185\u5b58\u6620\u5c04\u6765\u5b9e\u73b0\u591a\u4e2aJVM\u4e4b\u95f4\u7684\u5b57\u5178\u5171\u4eab\uff0c\u4ece\u800c\u5b9e\u73b0\u4e86\u5185\u5b58\u7684\u8282\u7701\u3002\u6709\u5173\u5b9e\u73b0\u7ec6\u8282\uff0c\u8bf7\u53c2\u9605\u300aJJUG CCC 2017\u79cb\u5b63\u5927\u4f1a\u300b\u4e0a\u7684\u6f14\u8bb2\u3002<\/p>\n<p>\u548cMeCab\u3001Kuromoji\u76f8\u6bd4\uff0c\u53ef\u4ee5\u5f97\u51fa\u4ee5\u4e0b\u7ed3\u8bba\u3002<\/p>\n<div>\n<div class=\"post-table\">\nSudachiMeCabkuromoji\u5206\u5272\u5358\u4f4d\u306e\u4f75\u7528\u25cb\u00d7\u25b3 ^1\u6587\u5b57\u6b63\u898f\u5316\u3001\u8868\u8a18\u6b63\u898f\u5316\u25cb\u00d7\u25b3 ^2\u307e\u3068\u3081\u4e0a\u3052\u3001\u88dc\u6b63\u51e6\u7406\u25cb\u00d7\u25b3 ^2\u8907\u6570\u30e6\u30fc\u30b6\u8f9e\u66f8\u306e\u5229\u7528\u25cb\u25cb\u00d7\u7701\u30e1\u30e2\u30ea\u25ce\u25b3\u25cb\u89e3\u6790\u7cbe\u5ea6\u25cb\u25cb\u25cb\u89e3\u6790\u901f\u5ea6\u25b3\u25cb\u25b3<\/div>\n<\/div>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">^1: n-best\u89e3\u306b\u3088\u308b\u8fd1\u4f3c<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">^2: Lucene \u30d5\u30a3\u30eb\u30bf\u30fc\u4f75\u7528<\/ul>\n<p>\u5c3d\u7ba1\u53d1\u5e03\u65f6\u95f4\u8fd8\u4e0d\u4e45\uff0c\u4f46SyncThought\u5148\u751f\u5df2\u7ecf\u6709\u4e00\u4e9b\u5e94\u7528\u5b9e\u4f8b\u4e86\u3002<\/p>\n<p>\u4ece\u8fd9\u91cc\u5f00\u59cb\uff0c\u6211\u4eec\u5c06\u5728\u5404\u4e2a\u65b9\u9762\u52a0\u5f3a\u5f62\u6001\u5206\u6790\u5668\uff0c\u5305\u62ec\u521b\u5efa\u5404\u79cd\u63d2\u4ef6\u3001\u63d0\u9ad8\u901f\u5ea6\u548c\u5206\u6790\u7cbe\u5ea6\u3001\u4e0e\u540c\u4e49\u8bcd\u8bcd\u5178\u7684\u534f\u4f5c\u3001\u6269\u5c55\u5206\u5272\u4fe1\u606f\u548c\u89c4\u8303\u5316\u8868\u793a\u3001\u6539\u5584\u9605\u8bfb\u4fe1\u606f\uff0c\u63d0\u5347\u7528\u6237\u8bcd\u5178\u7684\u6613\u7528\u6027\u7b49\u7b49\u3002\u540c\u65f6\uff0c\u6211\u4eec\u8fd8\u5728\u5f00\u53d1Python\u5b9e\u73b0\uff08\u540d\u4e3aSudachiPy\uff09\uff0c\u5b83\u5c06\u7b80\u5355\u6613\u7528\uff0c\u65b9\u4fbf\u6570\u636e\u5206\u6790\u7b49\u7528\u9014\u3002\u6211\u4eec\u8ba1\u5212\u4f7f\u5176\u80fd\u591f\u8f7b\u677e\u5b89\u88c5\u548c\u4f7f\u7528\u3002<\/p>\n<p>\u8bf7\u53c2\u9605\u4ee5\u4e0b\u8d44\u6599\uff0c\u4ee5\u4e86\u89e3\u6709\u5173Sudachi\u7684\u8bf4\u660e\u3002<\/p>\n<p>\u5f62\u614b\u7d20\u89e3\u6790\u306e\u8a71 by \u9ad8\u5ca1\u4e00\u99ac @ NLP\u30a8\u30f3\u30b8\u30cb\u30a2\u306b\u3088\u308b\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306e\u5b9f\u7528\u5316\u306b\u3080\u3051\u305f\u52c9\u5f37\u4f1a, 2017\/6\/22<\/p>\n<p>Java\u3067\u3064\u304f\u308b\u672c\u683c\u5f62\u614b\u7d20\u89e3\u6790\u5668 by \u9ad8\u5ca1\u4e00\u99ac @ JJUG CCC 2017 Fall, 2017\/11\/18<\/p>\n<p>\u8bf7\u4ece\u8fd9\u91cc\u83b7\u53d6\u5404\u79cd\u6e90\u4ee3\u7801\u3002<\/p>\n<p>WorksApplications\/Sudachi &#8211; \u672c\u5bb6Java\u7248<\/p>\n<p>WorksApplications\/elasticsearch-sudachi &#8211; Elasticsearch\u7528\u30d7\u30e9\u30b0\u30a4\u30f3<\/p>\n<p>WorksApplications\/SudachiPy &#8211; Python\u7248\uff08\u958b\u767a\u4e2d\uff09<\/p>\n<h2>Elasticsearch \u7684\u5207\u5206\u5de5\u5177\uff1aSudachi<\/h2>\n<p>\u8ba9\u6211\u4eec\u5b9e\u9645\u64cd\u4f5c\u4e00\u4e0b\uff0c\u5728Elasticsearch\u4e2d\u8fd0\u884cSudachi\uff01<\/p>\n<p>\u4ee5\u4e0b\u662f\u6b64\u6b21\u9a8c\u8bc1\u73af\u5883\u7684\u7b80\u8ff0\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Elasticsearch 5.6.1<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Ubuntu 17.10<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">Java 1.8.0_151<\/ul>\n<p>\u7531\u4e8e\u73af\u5883\u548c\u4ee3\u7801\u7684\u6574\u5907\uff0c\u4ee5\u524d\u5728Qiita\u4e0a\u5199\u7684\u5173\u4e8e\u5728Elasticsearch\u4e2d\u4f7f\u7528Sudachi\u7684\u6b65\u9aa4\uff031\u5df2\u7ecf\u53d1\u751f\u4e86\u91cd\u5927\u53d8\u5316\u3002<\/p>\n<h3>\u83b7\u53d6\u548c\u6784\u5efa\u63d2\u4ef6<\/h3>\n<p>Sudachi\u63d2\u4ef6\u9002\u7528\u4e8eElasticsearch\uff0c\u53ef\u4ee5\u5728WorksApplications\/elasticsearch-sudachi\u4e2d\u627e\u5230\u3002<\/p>\n<p>\u8fd9\u4e2a\u63d2\u4ef6\u7684pom.xml\u6587\u4ef6\u4e2d\u6307\u5b9a\u4e86Elasticsearch\u7684\u7248\u672c\u4e3a5.6.1\uff0c\u672c\u6b21\u9a8c\u8bc1\u4e2d\u6211\u4eec\u4e5f\u5339\u914d\u4e86\u76f8\u540c\u7684\u7248\u672c\u3002\u5982\u679c\u662f5.6.x\u7248\u672c\uff0c\u53ea\u9700\u8981\u628a\u8fd9\u90e8\u5206\u4fee\u6539\u4e00\u81f4\u5373\u53ef\u6b63\u5e38\u8fd0\u884c\u3002\u9488\u5bf96.x\u7248\u672c\u7684\u652f\u6301\u76ee\u524d\u6b63\u5728\u8fdb\u884c\u4e2d\uff0c\u8bf7\u7a0d\u7b49\u7247\u523b\u3002<\/p>\n<p>2018-01-09 \u8865\u5145\uff1a@matsuda_vla \u5148\u751f\u5df2\u7ecf\u5199\u4e86\u57286\u7cfb\u4e0a\u8fd0\u884c\u7684\u6b65\u9aa4\u3002<br \/>\n\u5728Elasticsearch6.1.1\u4e0a\u4f7f\u7528Sudachi\u7684\u6b65\u9aa4\uff08\u975e\u5b98\u65b9\uff09- Qiita<\/p>\n<p>\u9996\u5148\uff0c\u62ff\u51fa\u6e90\u4ee3\u7801\uff0c\u8fdb\u884c\u6784\u5efa\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span>git clone https:\/\/github.com\/WorksApplications\/elasticsearch-sudachi.git\r\n<span class=\"nv\">$ <\/span><span class=\"nb\">cd <\/span>elasticsearch-sudachi\r\n<span class=\"nv\">$ <\/span>mvn package\r\n<\/code><\/pre>\n<p>\u5f53\u6784\u5efa\u6210\u529f\u540e\uff0c\u5c06\u5728elasticsearch-sudachi\/target\/releases\/\u76ee\u5f55\u4e0b\u751f\u6210\u4e00\u4e2a\u540d\u4e3aanalysis-sudachi-1.0.0-SNAPSHOT.zip\u7684\u6587\u4ef6\u3002<\/p>\n<p>\u81ea\u5df1\u6784\u5efa\u7684\u66ff\u4ee3\u65b9\u6848\u662f\u4ece\u5feb\u7167\u7248\u672c\u5e93\u4e2d\u4e0b\u8f7d\uff082017-12-19\u6ce8\uff1a\u611f\u8c22Kengo Toda\u6307\u51fa\uff09\u3002<\/p>\n<h3>\u5b89\u88c5\u63d2\u4ef6<\/h3>\n<p>\u7136\u540e\uff0c\u4f60\u9700\u8981\u5b89\u88c5\u5df2\u7ecf\u6784\u5efa\u597d\u7684\u6587\u4ef6\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528Elasticsearch\u63d0\u4f9b\u7684elasticsearch-plugin\u811a\u672c\u6765\u5b8c\u6210\u3002\u5728install\u547d\u4ee4\u4e2d\uff0c\u8bf7\u6307\u5b9a\u521a\u521a\u6784\u5efa\u7684\u6587\u4ef6\u8def\u5f84\u3002<\/p>\n<p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u5982\u679clist\u547d\u4ee4\u7684\u7ed3\u679c\u5305\u542b\u4e86analysis-sudachi\uff0c\u90a3\u5c31\u8868\u793a\u6210\u529f\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span><span class=\"nb\">sudo<\/span> \/usr\/share\/elasticsearch\/bin\/elasticsearch-plugin <span class=\"nb\">install <\/span>file:\/\/\/path\/to\/builded\/file\/analysis-sudachi-1.0.0-SNAPSHOT.zip\r\n<span class=\"nv\">$ <\/span>\/usr\/share\/elasticsearch\/bin\/elasticsearch-plugin list\r\nanalysis-sudachi\r\n<\/code><\/pre>\n<h3>\u83b7\u53d6\u548c\u5b89\u88c5\u5b57\u5178<\/h3>\n<p>\u9664\u4e86\u5b89\u88c5\u4e4b\u5916\uff0c\u8fd8\u9700\u8981\u505a\u53e6\u5916\u4e00\u9879\u51c6\u5907\u5de5\u4f5c\uff0c\u5373\u5c06\u5b57\u5178\u6587\u4ef6\u653e\u7f6e\u5728\u9002\u5f53\u7684\u4f4d\u7f6e\u3002\u60a8\u53ef\u4ee5\u4ece\u4ee5\u4e0b\u7f51\u5740\u4e0b\u8f7d\u5b57\u5178\u6587\u4ef6\u3002<\/p>\n<p>\u7d22\u5f15 \/repositories\/snapshots\/com\/worksap\/nlp\/sudachi\/0.1.1-SNAPSHOT<\/p>\n<p>\u8bf7\u4ece\u8fd9\u91cc\u83b7\u53d6\u6700\u65b0\u7248\u672c\u7684dictionary_core\u6216dictionary_full\u3002<\/p>\n<p>dictionary_core: \u5c02\u9580\u5bb6\u306b\u3088\u308b\u8a9e\u5f59\u306e\u8ffd\u52a0\u3084\u8abf\u6574\u304c\u306a\u3055\u308c\u305f\u9ad8\u54c1\u8cea\u306a\u8f9e\u66f8\u3002UniDic\u3092\u30d9\u30fc\u30b9\u306b\u3001\u4f1a\u793e\u540d\u3001\u4f4f\u6240\u3001\u99c5\u540d\u3001\u4eba\u540d\u306a\u3069\u304c\u8ffd\u52a0\u3055\u308c\u3066\u3044\u308b\u3002\u8a9e\u5f59\u6570150\u4e07\u7a0b\u5ea6<\/p>\n<p>dictionary_full: dictionary_core\u3078\u8a9e\u5f59\u3092\u3055\u3089\u306b\u8ffd\u52a0\u3057\u305f\u4e0a\u4f4d\u96c6\u5408\u3002\u8a9e\u5f59\u6570300\u4e07\u5f31\u7a0b\u5ea6<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span>wget https:\/\/oss.sonatype.org\/content\/repositories\/snapshots\/com\/worksap\/nlp\/sudachi\/0.1.1-SNAPSHOT\/sudachi-0.1.1-20171208.130044-8-dictionary-core.tar.bz2\r\n<span class=\"nv\">$ <\/span><span class=\"nb\">tar <\/span>xf sudachi-0.1.1-20171208.130044-8-dictionary-core.tar.bz2\r\n<span class=\"nv\">$ <\/span><span class=\"nb\">ls\r\n<\/span>system_core.dic\r\n<\/code><\/pre>\n<p>\u901a\u5e38\uff0c\u8bcd\u5178\u6587\u4ef6\u653e\u7f6e\u5728$ES_HOME\/sudachi\/\u76ee\u5f55\u4e0b\u3002\u60a8\u53ef\u4ee5\u901a\u8fc7\u4fee\u6539\u540e\u7eed\u7684\u914d\u7f6e\u6587\u4ef6\u6765\u5c06\u5176\u653e\u7f6e\u5728\u5176\u4ed6\u4f4d\u7f6e\uff0c\u5e76\u66f4\u6539\u6587\u4ef6\u540d\u79f0\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span><span class=\"nb\">sudo mkdir<\/span> \/etc\/elasticsearch\/sudachi\r\n<span class=\"nv\">$ <\/span><span class=\"nb\">sudo mv <\/span>system_core.dic \/etc\/elasticsearch\/sudachi\r\n<\/code><\/pre>\n<h3>\u786e\u8ba4\u63d2\u4ef6<\/h3>\n<p>\u6700\u540e\uff0c\u91cd\u65b0\u542f\u52a8Elasticsearch\uff0c\u5e76\u9a8c\u8bc1\u63d2\u4ef6\u662f\u5426\u5df2\u52a0\u8f7d\uff0c\u5982\u679c\u5728plugins\u4e2d\u5b58\u5728analysis-sudachi\uff0c\u5219\u8868\u793a\u6210\u529f\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span><span class=\"nb\">sudo<\/span> \/etc\/init.d\/elasticsearch restart\r\n<span class=\"nv\">$ <\/span>curl <span class=\"nt\">-X<\/span> GET <span class=\"s1\">'http:\/\/localhost:9200\/_nodes\/plugins?pretty'<\/span>\r\n\r\n...\r\n  <span class=\"s2\">\"plugins\"<\/span> : <span class=\"o\">[<\/span>\r\n    <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"name\"<\/span> : <span class=\"s2\">\"analysis-sudachi\"<\/span>,\r\n      <span class=\"s2\">\"version\"<\/span> : <span class=\"s2\">\"1.0.0-SNAPSHOT\"<\/span>,\r\n      <span class=\"s2\">\"description\"<\/span> : <span class=\"s2\">\"The Japanese (Sudachi) Analysis plugin integrates Lucene Sudachi analysis module into elasticsearch.\"<\/span>,\r\n      <span class=\"s2\">\"classname\"<\/span> : <span class=\"s2\">\"com.worksap.nlp.elasticsearch.sudachi.plugin.AnalysisSudachiPlugin\"<\/span>,\r\n      <span class=\"s2\">\"has_native_controller\"<\/span> : <span class=\"nb\">false<\/span>\r\n    <span class=\"o\">}<\/span>\r\n  <span class=\"o\">]<\/span>\r\n...\r\n\r\n<\/code><\/pre>\n<h3>\u8bbe\u7f6e\u7528\u4e8e\u7d22\u5f15\u7684\u914d\u7f6e<\/h3>\n<p>\u73b0\u5728\uff0c\u6211\u4eec\u5df2\u7ecf\u51c6\u5907\u597d\u5728Elasticsearch\u4e2d\u4f7f\u7528Sudachi\u4e86\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u521b\u5efa\u7d22\u5f15\u5e76\u5b9e\u9645\u67e5\u770b\u89e3\u6790\u7ed3\u679c\u3002<\/p>\n<p>\u9996\u5148\uff0c\u6211\u4eec\u51c6\u5907\u4e86\u7528\u4e8e\u521b\u5efa\u7d22\u5f15\u7684\u8bbe\u7f6e\u3002\u5728\u8fd9\u91cc\uff0c\u6211\u4eec\u5c06\u4ee5\u4e0b\u5185\u5bb9\u5199\u5165\u4e86\u4e00\u4e2a\u540d\u4e3aanalysis_sudachi_settings.json\u7684\u6587\u4ef6\u4e2d\u3002<\/p>\n<p>tokenizer<\/p>\n<p>sudachi_tokenizer \u3092\u6307\u5b9a<\/p>\n<p>mode<\/p>\n<p>normal, search, extended \u304b\u3089\u6307\u5b9a\u3002\u30c7\u30d5\u30a9\u30eb\u30c8\u306fsearch<\/p>\n<p>normal: \u901a\u5e38\u306e\u5206\u5272<\/p>\n<p>search: A\u5358\u4f4d\u3068C\u5358\u4f4d<\/p>\n<p>extended: search\u306b\u52a0\u3048\u3066\u672a\u77e5\u8a9e\u306e\u30e6\u30cb\u30b0\u30e9\u30e0<\/p>\n<p>discard_punctuation<\/p>\n<p>\u53e5\u8aad\u70b9\u3092\u9664\u304f\u304b\u3002\u30c7\u30d5\u30a9\u30eb\u30c8\u306ftrue<\/p>\n<p>settings_path: Sudachi\u306e\u8a2d\u5b9a\u30d5\u30a1\u30a4\u30eb\u306e\u30d1\u30b9<\/p>\n<p>\u6307\u5b9a\u304c\u306a\u3051\u308c\u3070\u3001Sudachi\u306b\u540c\u68b1\u3055\u308c\u3066\u3044\u308b sudachi.json \u3092\u5229\u7528<br \/>\n\u3053\u306e\u8a2d\u5b9a\u30d5\u30a1\u30a4\u30eb\u3067\u8f9e\u66f8\u30d5\u30a1\u30a4\u30eb\u540d\u306a\u3069\u3092\u6307\u5b9a<br \/>\n\u30c7\u30d5\u30a9\u30eb\u30c8\u3067\u306f\u8f9e\u66f8\u30d5\u30a1\u30a4\u30eb\u540d\uff08systemDict\uff09\u306fsystem_core.dic\u3068\u306a\u3063\u3066\u3044\u308b<\/p>\n<p>system_full.dic\u3092\u5229\u7528\u3057\u305f\u308a\u3001\u7570\u306a\u308b\u540d\u524d\u306e\u8f9e\u66f8\u30d5\u30a1\u30a4\u30eb\u3092\u5229\u7528\u3059\u308b\u969b\u306b\u306f\u3001\u4e0a\u306esudachi.json\u3092\u66f8\u304d\u63db\u3048\u305f\u3088\u3046\u306a\u8a2d\u5b9a\u30d5\u30a1\u30a4\u30eb\u3092\u7528\u610f\u3057\u3001\u3053\u306esettings_path\u3067\u6307\u5b9a<br \/>\n\u76f8\u5bfe\u30d1\u30b9\u306e\u5834\u5408\u3001\u5f8c\u8ff0\u306eresources_path\u304b\u3089\u306e\u76f8\u5bfe<br \/>\n\u57fa\u672c\u7684\u306b$ES_HOME\u4ee5\u4e0b\u3067\u306a\u3044\u3068NG<\/p>\n<p>resources_path: \u8f9e\u66f8\u30d5\u30a1\u30a4\u30eb\u306e\u3042\u308b\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306e\u30d1\u30b9<\/p>\n<p>\u6307\u5b9a\u304c\u306a\u3051\u308c\u3070\u3001$ES_HOME\/sudachi\/<\/p>\n<p>\u57fa\u672c\u7684\u306b$ES_HOME\u4ee5\u4e0b\u3067\u306a\u3044\u3068NG<\/p>\n<pre class=\"post-pre\"><code><span class=\"p\">{<\/span>\r\n  <span class=\"nl\">\"settings\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">{<\/span>\r\n    <span class=\"nl\">\"index\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">{<\/span>\r\n      <span class=\"nl\">\"analysis\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">{<\/span>\r\n        <span class=\"nl\">\"tokenizer\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">{<\/span>\r\n          <span class=\"nl\">\"sudachi_tokenizer\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">{<\/span>\r\n            <span class=\"nl\">\"type\"<\/span><span class=\"p\">:<\/span> <span class=\"s2\">\"sudachi_tokenizer\"<\/span><span class=\"p\">,<\/span>\r\n            <span class=\"nl\">\"mode\"<\/span><span class=\"p\">:<\/span> <span class=\"s2\">\"search\"<\/span><span class=\"p\">,<\/span>\r\n        <span class=\"nl\">\"discard_punctuation\"<\/span><span class=\"p\">:<\/span> <span class=\"kc\">true<\/span><span class=\"p\">,<\/span>\r\n            <span class=\"nl\">\"resources_path\"<\/span><span class=\"p\">:<\/span> <span class=\"s2\">\"\/etc\/elasticsearch\/sudachi\"<\/span><span class=\"p\">,<\/span>\r\n            <span class=\"nl\">\"settings_path\"<\/span><span class=\"p\">:<\/span> <span class=\"s2\">\"\/etc\/elasticsearch\/sudachi\/sudachi.json\"<\/span>\r\n          <span class=\"p\">}<\/span>\r\n        <span class=\"p\">},<\/span>\r\n        <span class=\"nl\">\"analyzer\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">{<\/span>\r\n          <span class=\"nl\">\"sudachi_analyzer\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">{<\/span>\r\n            <span class=\"nl\">\"filter\"<\/span><span class=\"p\">:<\/span> <span class=\"p\">[<\/span>\r\n            <span class=\"p\">],<\/span>\r\n            <span class=\"nl\">\"tokenizer\"<\/span><span class=\"p\">:<\/span> <span class=\"s2\">\"sudachi_tokenizer\"<\/span><span class=\"p\">,<\/span>\r\n            <span class=\"nl\">\"type\"<\/span><span class=\"p\">:<\/span> <span class=\"s2\">\"custom\"<\/span>\r\n          <span class=\"p\">}<\/span>\r\n        <span class=\"p\">}<\/span>\r\n      <span class=\"p\">}<\/span>\r\n    <span class=\"p\">}<\/span>\r\n  <span class=\"p\">}<\/span>\r\n<span class=\"p\">}<\/span>\r\n<\/code><\/pre>\n<h3>\u521b\u5efa\u7d22\u5f15<\/h3>\n<p>\u6211\u4eec\u5c06\u4f7f\u7528\u5199\u6709\u6b64\u8bbe\u7f6e\u7684analysis_sudachi_settings.json\u6765\u521b\u5efa\u7d22\u5f15\u3002\u8ba9\u6211\u4eec\u7528\u540d\u79f0sudachi_test\u521b\u5efa\u5b83\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span>curl <span class=\"nt\">-X<\/span> PUT <span class=\"s1\">'http:\/\/localhost:9200\/sudachi_test\/'<\/span> <span class=\"nt\">-d<\/span> @analysis_sudachi_settings.json\r\n<span class=\"o\">{<\/span><span class=\"s2\">\"acknowledged\"<\/span>:true,<span class=\"s2\">\"shards_acknowledged\"<\/span>:true,<span class=\"s2\">\"index\"<\/span>:<span class=\"s2\">\"sudachi_test\"<\/span><span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<p>\u8ba9\u6211\u4eec\u6765\u68c0\u67e5\u4e00\u4e0b\u6240\u521b\u5efa\u7684\u7d22\u5f15\u662f\u5426\u8bbe\u7f6e\u6b63\u786e\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span>curl <span class=\"nt\">-X<\/span> GET <span class=\"s1\">'http:\/\/localhost:9200\/sudachi_test\/?pretty'<\/span>\r\n<span class=\"o\">{<\/span>\r\n  <span class=\"s2\">\"sudachi_test\"<\/span> : <span class=\"o\">{<\/span>\r\n    <span class=\"s2\">\"aliases\"<\/span> : <span class=\"o\">{<\/span> <span class=\"o\">}<\/span>,\r\n    <span class=\"s2\">\"mappings\"<\/span> : <span class=\"o\">{<\/span> <span class=\"o\">}<\/span>,\r\n    <span class=\"s2\">\"settings\"<\/span> : <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"index\"<\/span> : <span class=\"o\">{<\/span>\r\n        <span class=\"s2\">\"number_of_shards\"<\/span> : <span class=\"s2\">\"5\"<\/span>,\r\n        <span class=\"s2\">\"provided_name\"<\/span> : <span class=\"s2\">\"sudachi_test\"<\/span>,\r\n        <span class=\"s2\">\"creation_date\"<\/span> : <span class=\"s2\">\"1512992783788\"<\/span>,\r\n        <span class=\"s2\">\"analysis\"<\/span> : <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"analyzer\"<\/span> : <span class=\"o\">{<\/span>\r\n            <span class=\"s2\">\"sudachi_analyzer\"<\/span> : <span class=\"o\">{<\/span>\r\n              <span class=\"s2\">\"type\"<\/span> : <span class=\"s2\">\"custom\"<\/span>,\r\n              <span class=\"s2\">\"tokenizer\"<\/span> : <span class=\"s2\">\"sudachi_tokenizer\"<\/span>\r\n            <span class=\"o\">}<\/span>\r\n          <span class=\"o\">}<\/span>,\r\n          <span class=\"s2\">\"tokenizer\"<\/span> : <span class=\"o\">{<\/span>\r\n            <span class=\"s2\">\"sudachi_tokenizer\"<\/span> : <span class=\"o\">{<\/span>\r\n              <span class=\"s2\">\"mode\"<\/span> : <span class=\"s2\">\"search\"<\/span>,\r\n              <span class=\"s2\">\"resources_path\"<\/span> : <span class=\"s2\">\"\/etc\/elasticsearch\"<\/span>,\r\n              <span class=\"s2\">\"type\"<\/span> : <span class=\"s2\">\"sudachi_tokenizer\"<\/span>,\r\n              <span class=\"s2\">\"discard_punctuation\"<\/span> : <span class=\"s2\">\"true\"<\/span>\r\n            <span class=\"o\">}<\/span>\r\n          <span class=\"o\">}<\/span>\r\n        <span class=\"o\">}<\/span>,\r\n        <span class=\"s2\">\"number_of_replicas\"<\/span> : <span class=\"s2\">\"1\"<\/span>,\r\n        <span class=\"s2\">\"uuid\"<\/span> : <span class=\"s2\">\"DBqj21t7STS8ZE2gM32MXw\"<\/span>,\r\n        <span class=\"s2\">\"version\"<\/span> : <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"created\"<\/span> : <span class=\"s2\">\"5060199\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n      <span class=\"o\">}<\/span>\r\n    <span class=\"o\">}<\/span>\r\n  <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<h3>\u4f7f\u7528Sudachi\u63d2\u4ef6\u8fdb\u884c\u5206\u6790\u3002<\/h3>\n<p>\u6211\u4eec\u5df2\u7ecf\u5b8c\u6210\u4e86Sudachi\u63d2\u4ef6\u7684\u5b89\u88c5\u3002\u8ba9\u6211\u4eec\u770b\u770b\u5b83\u5b9e\u9645\u4e0a\u662f\u5982\u4f55\u88ab\u5206\u6790\u7684\u3002<\/p>\n<p>\u5728\u4ee5\u4e0b\u7684\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f20\u5165\u4e86\u6587\u672c\u201c\u4e1c\u4eac\u90fd\u77e5\u4e8b\u9009\u4e3e\u201d\uff0c\u53ef\u4ee5\u786e\u8ba4\u8f93\u51fa\u4e86\u591a\u4e2a\u5206\u5272\u5355\u5143\uff08\u4e00\u4e2a\u662f\u201c\u4e1c\u4eac\u90fd\u77e5\u4e8b\u9009\u4e3e\u201d\u8fd9\u4e2a\u6574\u4f53\uff0c\u4e00\u4e2a\u662f\u201c\u4e1c\u4eac\/\u90fd\/\u77e5\u4e8b\/\u9009\u4e3e\u201d\u8fd9\u51e0\u4e2a\u90e8\u5206\uff09\u3002\u8fd9\u662f\u4f7f\u7528search\u6a21\u5f0f\u548csystem_full\u8bcd\u5178\u5f97\u51fa\u7684\u7ed3\u679c\u3002\u901a\u8fc7\u66f4\u6539\u5206\u5272\u6a21\u5f0f\u3001\u66f4\u6539\u8bcd\u5178\u6216\u6dfb\u52a0\u4e0b\u8ff0\u7684\u8fc7\u6ee4\u5668\uff0c\u7ed3\u679c\u4e5f\u4f1a\u6709\u6240\u4e0d\u540c\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span>curl <span class=\"nt\">-X<\/span> GET <span class=\"s1\">'http:\/\/localhost:9200\/sudachi_test\/_analyze?analyzer=sudachi_analyzer&amp;pretty'<\/span> <span class=\"nt\">-d<\/span> <span class=\"s2\">\"\u6771\u4eac\u90fd\u77e5\u4e8b\u9078\u6319\"<\/span>\r\n<span class=\"o\">{<\/span>\r\n  <span class=\"s2\">\"tokens\"<\/span> : <span class=\"o\">[<\/span>\r\n    <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"token\"<\/span> : <span class=\"s2\">\"\u6771\u4eac\u90fd\u77e5\u4e8b\u9078\u6319\"<\/span>,\r\n      <span class=\"s2\">\"start_offset\"<\/span> : 0,\r\n      <span class=\"s2\">\"end_offset\"<\/span> : 7,\r\n      <span class=\"s2\">\"type\"<\/span> : <span class=\"s2\">\"word\"<\/span>,\r\n      <span class=\"s2\">\"position\"<\/span> : 0,\r\n      <span class=\"s2\">\"positionLength\"<\/span> : 4\r\n    <span class=\"o\">}<\/span>,\r\n    <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"token\"<\/span> : <span class=\"s2\">\"\u6771\u4eac\"<\/span>,\r\n      <span class=\"s2\">\"start_offset\"<\/span> : 0,\r\n      <span class=\"s2\">\"end_offset\"<\/span> : 2,\r\n      <span class=\"s2\">\"type\"<\/span> : <span class=\"s2\">\"word\"<\/span>,\r\n      <span class=\"s2\">\"position\"<\/span> : 0\r\n    <span class=\"o\">}<\/span>,\r\n    <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"token\"<\/span> : <span class=\"s2\">\"\u90fd\"<\/span>,\r\n      <span class=\"s2\">\"start_offset\"<\/span> : 2,\r\n      <span class=\"s2\">\"end_offset\"<\/span> : 3,\r\n      <span class=\"s2\">\"type\"<\/span> : <span class=\"s2\">\"word\"<\/span>,\r\n      <span class=\"s2\">\"position\"<\/span> : 1\r\n    <span class=\"o\">}<\/span>,\r\n    <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"token\"<\/span> : <span class=\"s2\">\"\u77e5\u4e8b\"<\/span>,\r\n      <span class=\"s2\">\"start_offset\"<\/span> : 3,\r\n      <span class=\"s2\">\"end_offset\"<\/span> : 5,\r\n      <span class=\"s2\">\"type\"<\/span> : <span class=\"s2\">\"word\"<\/span>,\r\n      <span class=\"s2\">\"position\"<\/span> : 2\r\n    <span class=\"o\">}<\/span>,\r\n    <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"token\"<\/span> : <span class=\"s2\">\"\u9078\u6319\"<\/span>,\r\n      <span class=\"s2\">\"start_offset\"<\/span> : 5,\r\n      <span class=\"s2\">\"end_offset\"<\/span> : 7,\r\n      <span class=\"s2\">\"type\"<\/span> : <span class=\"s2\">\"word\"<\/span>,\r\n      <span class=\"s2\">\"position\"<\/span> : 3\r\n    <span class=\"o\">}<\/span>\r\n  <span class=\"o\">]<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<h3>\u5404\u79cd\u4e0d\u540c\u7684\u8fc7\u6ee4\u5668<\/h3>\n<p>\u9664\u4e86\u4f7f\u7528\u65b0\u9bae\u7684Sudachi\u4e0a\u8ff0\u4e4b\u5916\uff0c\u9084\u53ef\u4ee5\u6839\u64da\u4f7f\u7528\u60c5\u5883\u61c9\u7528\u5404\u7a2e\u4e0d\u540c\u7684\u6ffe\u93e1\u3002\u4ee5\u4e0b\u662f\u63d0\u4f9b\u7684\u6ffe\u93e1\u9078\u9805\u3002<\/p>\n<p>sudachi_part_of_speech<\/p>\n<p>\u8a2d\u5b9a\u306b\u66f8\u304b\u308c\u305f\u54c1\u8a5e\u306e\u30c8\u30fc\u30af\u30f3\u3092\u9664\u5916<br \/>\n\u30c7\u30d5\u30a9\u30eb\u30c8\u8a2d\u5b9a\u306f stoptags.txt<\/p>\n<p>sudachi_ja_stop<\/p>\n<p>\u65e5\u672c\u8a9e\u306e\u30b9\u30c8\u30c3\u30d7\u30ef\u30fc\u30c9\u3092\u9664\u5916<\/p>\n<p>stopwords.txt \u3067\u30b9\u30c8\u30c3\u30d7\u30ef\u30fc\u30c9\u306e\u4e00\u89a7\u3092\u78ba\u8a8d\u53ef\u80fd<\/p>\n<p>sudachi_baseform<\/p>\n<p>\u52d5\u8a5e\u3068\u5f62\u5bb9\u8a5e\u306e\u7d42\u6b62\u5f62\u5316<br \/>\n\u4f8b: \u98f2\u307f \u2192 \u98f2\u3080<\/p>\n<p>sudachi_readingform<\/p>\n<p>\u30ab\u30bf\u30ab\u30ca\u3001\u3082\u3057\u304f\u306f\u30ed\u30fc\u30de\u5b57\u306e\u8aad\u307f\u306b\u5909\u63db<br \/>\n\u4f8b1: \u5bff\u53f8 \u2192 \u30b9\u30b7<\/p>\n<p>\u4f8b2: \u5bff\u53f8 \u2192 sushi<\/p>\n<p>\u8fd9\u4e9b\u8fc7\u6ee4\u5668\u57fa\u672c\u4e0a\u662f\u4ee5\u4e0eKuromoji\u51e0\u4e4e\u517c\u5bb9\u7684\u65b9\u5f0f\u521b\u5efa\u7684\u3002\u5728\u8bb8\u591a\u60c5\u51b5\u4e0b\uff0c\u4ec5\u9700\u5c06kuromoji\u66ff\u6362\u4e3asudachi\u5373\u53ef\u6b63\u5e38\u8fd0\u884c\u3002\u6709\u5173\u66f4\u8be6\u7ec6\u7684\u8bbe\u7f6e\u65b9\u6cd5\u548c\u7528\u6cd5\u793a\u4f8b\uff0c\u8bf7\u53c2\u9605README\u4e2d\u7684\u201c\u5bf9\u5e94\u8fc7\u6ee4\u5668\u201d\u90e8\u5206\u3002<\/p>\n<h2>\u7ed3\u5c3e\u5904<\/h2>\n<p>\u6211\u4eec\u4ecb\u7ecd\u4e86\u5206\u8bcd\u5668&#8221;Sudachi&#8221;\u4ee5\u53ca\u5176\u5728Elasticsearch\u4e2d\u7684\u4f7f\u7528\u3002<\/p>\n<p>\u6211\u8ba4\u4e3aSudachi\u7684\u5404\u79cd\u7279\u70b9\uff0c\u5982\u7cbe\u5fc3\u8bbe\u8ba1\u7684\u77ed\u5355\u4f4d\u548c\u957f\u5355\u4f4d\u3001\u8bed\u4e49\u548c\u6587\u5b57\u7684\u8868\u8fbe\u63a7\u5236\uff0c\u4ee5\u53ca\u901a\u8fc7\u63d2\u4ef6\u53ef\u4ee5\u7075\u6d3b\u6269\u5c55\u7b49\uff0c\u53ef\u4ee5\u4e3aElasticsearch\u7684\u5e94\u7528\u63d0\u4f9b\u91cd\u8981\u7684\u4f18\u52bf\u3002<\/p>\n<p>\u6211\u4eec\u5c06\u8fdb\u4e00\u6b65\u52a0\u5f3aSudachi\uff0c\u4f46\u4ecd\u7136\u7f3a\u4e4f\u77e5\u8bc6\u3001\u4f7f\u7528\u4f8b\u548c\u6587\u6863\u3002\u5982\u679c\u60a8\u5728\u4f7f\u7528\u8fc7\u7a0b\u4e2d\u6709\u4efb\u4f55\u7591\u95ee\u3001\u610f\u89c1\u6216\u53ef\u7591\u884c\u4e3a\uff0c\u8bf7\u52a1\u5fc5\u63d0\u4ea4GitHub\u7684Issue\uff0c\u6211\u4eec\u5c06\u4e0d\u80dc\u611f\u6fc0\uff01<\/p>\n<p>\u987a\u4fbf\u8bf4\u4e00\u4e0b\uff0c\u6211\u660e\u5929\u4e5f\u4f1a\u4ece\u5fb7\u5c9b\u8d76\u5230\u4e1c\u4eac\u53c2\u52a0 Elastic{ON} Tokyo 2017\u3002\u6211\u4f1a\u7a7f\u7740\u5fb7\u5c9b\u53bf\u7684\u5409\u7965\u7269\u201c\u9178\u6a59\u541b\u201d\u7684\u886c\u886b\uff0c\u5e26\u7740\u540d\u4ea7\u201c\u9178\u6a59\u6d3e\u201d\uff0c\u5982\u679c\u770b\u5230\u6211\uff0c\u8bf7\u52a1\u5fc5\u548c\u6211\u6253\u58f0\u62db\u547c\uff01<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d466237434c4406ca4f13\/84-0.jpeg\" alt=\"sudachi.jpg\" \/><\/div>\n<p>\u660e\u592912\/14\u7684\u300aElastic stack Advent Calendar 2017\u300b\u662f\u7531ZooBonta\u5148\u751f\u64b0\u5199\u7684\u6709\u5173Logstash\u7684\u6587\u7ae0\uff01<\/p>\n<h2>\uff08\u8865\u5145\uff09Sudachi \u5b98\u65b9 Slack<\/h2>\n<p>\u6211\u4eec\u4e3a\u5f00\u53d1\u4eba\u5458\u548c\u7528\u6237\u51c6\u5907\u4e86\u4e00\u4e2aSlack\u5de5\u4f5c\u7a7a\u95f4\uff0c\u4ee5\u4fbf\u4ed6\u4eec\u53ef\u4ee5\u8fdb\u884c\u63d0\u95ee\u548c\u8ba8\u8bba\u3002\u8bf7\u4e0d\u8981\u72b9\u8c6b\uff0c\u5c06\u60a8\u7684\u95ee\u9898\u548c\u9700\u6c42\u53d1\u9001\u5230\u8fd9\u91cc\u6765\uff01<\/p>\n<div>\u5173\u4e8e\u6ca1\u6709\u6559\u5e08\u7684\u5f62\u6001\u7d20\u5206\u6790\u548c\u8bcd\u8bed\u5207\u5206\uff0c\u6211\u5728\u8fd9\u91cc\u4e0d\u8fdb\u884c\u8ba8\u8bba\uff0c\u4f46\u6211\u8ba4\u4e3a\u8fd9\u662f\u4e00\u4e2a\u975e\u5e38\u4ee4\u4eba\u5174\u594b\u7684\u9886\u57df\uff0c\u4e0e\u6709\u6559\u5e08\u7684\u9886\u57df\u662f\u4e0d\u540c\u7684\uff01\u5bf9\u4e8e\u611f\u5174\u8da3\u7684\u4eba\uff0c\u53ef\u4ee5\u53c2\u8003\uff08\u6301\u6865+2009\uff09\u53ca\u5176\u89e3\u91ca\u3001\u5b9e\u65bd\uff0c\uff08\u5185\u6d77+2015\uff09\u53ca\u5176\u89e3\u91ca\uff0c\uff08Fujii+2017\uff09\uff0c\u4ee5\u53ca\u6301\u6865\u8001\u5e08\u5728\u6570\u636e\u5de5\u7a0b\u673a\u5668\u4eba\u7814\u7a76\u4f1a\u7684\u8d44\u6599\uff0c\u548c\u82e5\u6797\u8001\u5e08\u5728TokyoCL\u7684\u8d44\u6599\u7b49\u3002<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u592a\u957f\u4e0d\u770b\uff08\u7b80\u79f0TL;DR\uff09 Kuromoji\u306b\u4ee3\u308f\u308b\u65b0\u3057\u3044\u5f62\u614b\u7d20\u89e3\u6790\u5668\u300cSudachi\u300d &nbsp; \u306a\u306b\u304c [&hellip;]<\/p>\n","protected":false},"author":10,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-41424","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668&quot; Sudachi&quot; - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4e3aelasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668-sudachi\u3002\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668&quot; Sudachi&quot;\" \/>\n<meta property=\"og:description\" content=\"\u592a\u957f\u4e0d\u770b\uff08\u7b80\u79f0TL;DR\uff09 Kuromoji\u306b\u4ee3\u308f\u308b\u65b0\u3057\u3044\u5f62\u614b\u7d20\u89e3\u6790\u5668\u300cSudachi\u300d &nbsp; \u306a\u306b\u304c [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4e3aelasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668-sudachi\u3002\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2022-12-23T03:00:02+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-04T08:04:50+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d466237434c4406ca4f13\/84-0.jpeg\" \/>\n<meta name=\"author\" content=\"\u5b87, \u534e\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u5b87, \u534e\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/\",\"name\":\"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668\\\" Sudachi\\\" - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2022-12-23T03:00:02+00:00\",\"dateModified\":\"2024-05-04T08:04:50+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668&#8221; Sudachi&#8221;\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458\",\"name\":\"\u5b87, \u534e\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g\",\"caption\":\"\u5b87, \u534e\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/yuhua\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668\" Sudachi\" - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u4e3aelasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668-sudachi\u3002\/","og_locale":"zh_CN","og_type":"article","og_title":"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668\" Sudachi\"","og_description":"\u592a\u957f\u4e0d\u770b\uff08\u7b80\u79f0TL;DR\uff09 Kuromoji\u306b\u4ee3\u308f\u308b\u65b0\u3057\u3044\u5f62\u614b\u7d20\u89e3\u6790\u5668\u300cSudachi\u300d &nbsp; \u306a\u306b\u304c [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u4e3aelasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668-sudachi\u3002\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2022-12-23T03:00:02+00:00","article_modified_time":"2024-05-04T08:04:50+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d466237434c4406ca4f13\/84-0.jpeg"}],"author":"\u5b87, \u534e","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u5b87, \u534e","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"3 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/","name":"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668\" Sudachi\" - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2022-12-23T03:00:02+00:00","dateModified":"2024-05-04T08:04:50+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u4e3aElasticsearch\u5f00\u53d1\u7684\u65b0\u578b\u4e2d\u6587\u5f62\u6001\u5206\u6790\u5668&#8221; Sudachi&#8221;"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458","name":"\u5b87, \u534e","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g","caption":"\u5b87, \u534e"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/yuhua\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%b8%baelasticsearch%e5%bc%80%e5%8f%91%e7%9a%84%e6%96%b0%e5%9e%8b%e4%b8%ad%e6%96%87%e5%bd%a2%e6%80%81%e5%88%86%e6%9e%90%e5%99%a8-sudachi%e3%80%82\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/41424","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=41424"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/41424\/revisions"}],"predecessor-version":[{"id":99311,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/41424\/revisions\/99311"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=41424"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=41424"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=41424"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}