{"id":16434,"date":"2023-12-05T10:26:52","date_gmt":"2023-12-05T02:26:52","guid":{"rendered":"https:\/\/wx.kaifamiao.info\/?p=16434"},"modified":"2023-12-16T11:11:05","modified_gmt":"2023-12-16T03:11:05","slug":"elasticsearch-de-tokenizer-ru-he-shi-yong","status":"publish","type":"post","link":"http:\/\/wx.kaifamiao.info\/index.php\/2023\/12\/05\/elasticsearch-de-tokenizer-ru-he-shi-yong\/","title":{"rendered":"ElasticSearch \u7684 Tokenizer \u5982\u4f55\u4f7f\u7528\uff1f"},"content":{"rendered":"<p>\u5728Elasticsearch\u4e2d\uff0c\u5206\u8bcd\u5668\uff08Tokenizer\uff09\u662f\u7528\u4e8e\u5c06\u6587\u672c\u5206\u5272\u6210\u8bcd\u6761\u7684\u7ec4\u4ef6\uff0c\u5b83\u901a\u5e38\u662f\u5206\u6790\u8fc7\u7a0b\u4e2d\u7684\u7b2c\u4e00\u6b65\u3002\u5206\u8bcd\u5668\u5c06\u6587\u672c\u6309\u7167\u4e00\u5b9a\u89c4\u5219\u5212\u5206\u6210\u4e00\u4e2a\u4e2a\u6709\u610f\u4e49\u7684\u5355\u8bcd\u6216\u8bcd\u6761\uff0c\u4ee5\u5efa\u7acb\u5012\u6392\u7d22\u5f15\uff0c\u652f\u6301\u5168\u6587\u68c0\u7d22\u548c\u5176\u4ed6\u5206\u6790\u64cd\u4f5c\u3002\u5728\u5206\u8bcd\u5668\u7684\u5b9a\u4e49\u4e2d\uff0c\u4e00\u4e2a\u5173\u952e\u7684\u7ec4\u4ef6\u662f Tokenizer\u3002<\/p>\n<p>\u4ee5\u4e0b\u662f\u5982\u4f55\u5728Elasticsearch\u4e2d\u4f7f\u7528 Tokenizer \u7684\u57fa\u672c\u65b9\u6cd5\uff1a<\/p>\n<h3><a id=\"1%E9%BB%98%E8%AE%A4%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%9A\" class=\"anchor\" aria-hidden=\"true\"><span class=\"octicon octicon-link\"><\/span><\/a>1. <strong>\u9ed8\u8ba4\u5206\u8bcd\u5668\uff1a<\/strong><\/h3>\n<p>Elasticsearch\u63d0\u4f9b\u4e86\u4e00\u4e9b\u5185\u7f6e\u7684\u5206\u8bcd\u5668\uff0c\u5176\u4e2d\u7684 <code>standard<\/code> \u5206\u8bcd\u5668\u662f\u9ed8\u8ba4\u7684\u5206\u8bcd\u5668\uff0c\u5b83\u4f1a\u6309\u7167\u4e00\u5b9a\u89c4\u5219\u5c06\u6587\u672c\u5206\u5272\u6210\u5355\u8bcd\u3002<\/p>\n<pre><code class=\"language-json\">PUT \/my_index\n{\n  &quot;settings&quot;: {\n    &quot;analysis&quot;: {\n      &quot;analyzer&quot;: {\n        &quot;my_analyzer&quot;: {\n          &quot;type&quot;: &quot;standard&quot;\n        }\n      }\n    }\n  }\n}\n<\/code><\/pre>\n<p>\u4e0a\u8ff0\u793a\u4f8b\u4e2d\uff0c\u521b\u5efa\u4e86\u4e00\u4e2a\u540d\u4e3a <code>my_index<\/code> \u7684\u7d22\u5f15\uff0c\u5e76\u5b9a\u4e49\u4e86\u4e00\u4e2a\u540d\u4e3a <code>my_analyzer<\/code> \u7684\u5206\u6790\u5668\uff0c\u4f7f\u7528\u4e86 <code>standard<\/code> \u5206\u8bcd\u5668\u3002<\/p>\n<h3><a id=\"2%E8%87%AA%E5%AE%9A%E4%B9%89%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%9A\" class=\"anchor\" aria-hidden=\"true\"><span class=\"octicon octicon-link\"><\/span><\/a>2. <strong>\u81ea\u5b9a\u4e49\u5206\u8bcd\u5668\uff1a<\/strong><\/h3>\n<p>\u9664\u4e86\u4f7f\u7528\u9ed8\u8ba4\u7684\u5206\u8bcd\u5668\u5916\uff0c\u4f60\u8fd8\u53ef\u4ee5\u81ea\u5b9a\u4e49\u5206\u8bcd\u5668\uff0c\u6839\u636e\u5177\u4f53\u9700\u6c42\u5b9a\u4e49\u5206\u8bcd\u89c4\u5219\u3002<\/p>\n<pre><code class=\"language-json\">PUT \/my_index\n{\n  &quot;settings&quot;: {\n    &quot;analysis&quot;: {\n      &quot;analyzer&quot;: {\n        &quot;my_analyzer&quot;: {\n          &quot;type&quot;: &quot;custom&quot;,\n          &quot;tokenizer&quot;: &quot;whitespace&quot;  \/\/ \u4f7f\u7528\u7a7a\u683c\u4f5c\u4e3a\u5206\u8bcd\u5668\n        }\n      }\n    }\n  }\n}\n<\/code><\/pre>\n<p>\u4e0a\u8ff0\u793a\u4f8b\u4e2d\uff0c\u521b\u5efa\u4e86\u4e00\u4e2a\u81ea\u5b9a\u4e49\u7684\u5206\u6790\u5668 <code>my_analyzer<\/code>\uff0c\u4f7f\u7528\u4e86 <code>whitespace<\/code> \u5206\u8bcd\u5668\uff0c\u8be5\u5206\u8bcd\u5668\u7b80\u5355\u5730\u4f7f\u7528\u7a7a\u683c\u6765\u5206\u5272\u6587\u672c\u3002<\/p>\n<h3><a id=\"3%E5%85%B6%E4%BB%96%E5%86%85%E7%BD%AE%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%9A\" class=\"anchor\" aria-hidden=\"true\"><span class=\"octicon octicon-link\"><\/span><\/a>3. <strong>\u5176\u4ed6\u5185\u7f6e\u5206\u8bcd\u5668\uff1a<\/strong><\/h3>\n<p>Elasticsearch\u8fd8\u63d0\u4f9b\u4e86\u5176\u4ed6\u4e00\u4e9b\u5185\u7f6e\u7684\u5206\u8bcd\u5668\uff0c\u4f8b\u5982 <code>standard<\/code>\u3001<code>whitespace<\/code>\u3001<code>keyword<\/code>\u3001<code>pattern<\/code>\u3001<code>uax_url_email<\/code> \u7b49\uff0c\u53ef\u4ee5\u6839\u636e\u9700\u8981\u9009\u62e9\u5408\u9002\u7684\u5206\u8bcd\u5668\u3002<\/p>\n<h3><a id=\"4%E5%88%86%E8%AF%8D%E5%99%A8%E7%9A%84%E5%BA%94%E7%94%A8%EF%BC%9A\" class=\"anchor\" aria-hidden=\"true\"><span class=\"octicon octicon-link\"><\/span><\/a>4. <strong>\u5206\u8bcd\u5668\u7684\u5e94\u7528\uff1a<\/strong><\/h3>\n<p>\u5728\u5b9a\u4e49\u6587\u6863\u6620\u5c04\uff08Mapping\uff09\u65f6\uff0c\u53ef\u4ee5\u4e3a\u6bcf\u4e2a\u5b57\u6bb5\u6307\u5b9a\u5206\u8bcd\u5668\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u6620\u5c04\u5b9a\u4e49\u7684\u793a\u4f8b\uff1a<\/p>\n<pre><code class=\"language-json\">PUT \/my_index\/_mapping\n{\n  &quot;properties&quot;: {\n    &quot;content&quot;: {\n      &quot;type&quot;: &quot;text&quot;,\n      &quot;analyzer&quot;: &quot;my_analyzer&quot;  \/\/ \u6307\u5b9a\u5206\u8bcd\u5668\n    }\n  }\n}\n<\/code><\/pre>\n<p>\u5728\u4e0a\u8ff0\u6620\u5c04\u4e2d\uff0c<code>content<\/code> \u5b57\u6bb5\u4f7f\u7528\u4e86\u4e4b\u524d\u5b9a\u4e49\u7684 <code>my_analyzer<\/code> \u5206\u8bcd\u5668\u3002<\/p>\n<p>\u901a\u8fc7\u5b9a\u4e49\u548c\u914d\u7f6e\u5206\u8bcd\u5668\uff0c\u4f60\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u4f18\u5316\u5168\u6587\u68c0\u7d22\u7684\u6548\u679c\uff0c\u786e\u4fdd\u641c\u7d22\u7ed3\u679c\u66f4\u7b26\u5408\u671f\u671b\u3002\u5728\u5b9e\u9645\u4f7f\u7528\u4e2d\uff0c\u53ef\u4ee5\u6839\u636e\u4e0d\u540c\u7684\u4e1a\u52a1\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5206\u8bcd\u5668\u548c\u5206\u6790\u5668\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5728Elasticsearch\u4e2d\uff0c\u5206\u8bcd\u5668\uff08Tokenizer\uff09\u662f\u7528\u4e8e\u5c06\u6587\u672c\u5206\u5272\u6210\u8bcd\u6761\u7684\u7ec4\u4ef6\uff0c\u5b83\u901a\u5e38\u662f\u5206\u6790\u8fc7\u7a0b\u4e2d\u7684 [&hellip;]<\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[125],"tags":[],"class_list":["post-16434","post","type-post","status-publish","format-standard","hentry","category-elasticsearch"],"_links":{"self":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts\/16434","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/comments?post=16434"}],"version-history":[{"count":2,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts\/16434\/revisions"}],"predecessor-version":[{"id":48413,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/posts\/16434\/revisions\/48413"}],"wp:attachment":[{"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/media?parent=16434"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/categories?post=16434"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/wx.kaifamiao.info\/index.php\/wp-json\/wp\/v2\/tags?post=16434"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}