{"id":61571,"date":"2024-10-13T12:05:18","date_gmt":"2024-10-13T04:05:18","guid":{"rendered":"https:\/\/server.hk\/cnblog\/61571\/"},"modified":"2024-10-13T12:05:18","modified_gmt":"2024-10-13T04:05:18","slug":"hive-%e5%ae%8c%e7%be%8e%e8%a7%a3%e6%9e%90-json-%e9%99%a3%e5%88%97%e7%9a%84%e5%87%bd%e6%95%b8","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/61571\/","title":{"rendered":"Hive \u5b8c\u7f8e\u89e3\u6790 Json \u9663\u5217\u7684\u51fd\u6578"},"content":{"rendered":"<h1 id=\"hive-%e5%ae%8c%e7%be%8e%e8%a7%a3%e6%9e%90-json-%e9%99%a3%e5%88%97%e7%9a%84%e5%87%bd%e6%95%b8-YNGhkQxCuc\">Hive \u5b8c\u7f8e\u89e3\u6790 JSON \u9663\u5217\u7684\u51fd\u6578<\/h1>\n<p>\u5728\u5927\u6578\u64da\u8655\u7406\u7684\u9818\u57df\u4e2d\uff0cApache Hive \u662f\u4e00\u500b\u975e\u5e38\u6d41\u884c\u7684\u6578\u64da\u5009\u5eab\u5de5\u5177\uff0c\u80fd\u5920\u8b93\u7528\u6236\u4f7f\u7528\u985e\u4f3c SQL \u7684\u67e5\u8a62\u8a9e\u8a00\u4f86\u67e5\u8a62\u548c\u5206\u6790\u5b58\u5132\u5728 Hadoop \u4e2d\u7684\u6578\u64da\u3002\u96a8\u8457 JSON \u683c\u5f0f\u7684\u6578\u64da\u8d8a\u4f86\u8d8a\u666e\u904d\uff0cHive \u63d0\u4f9b\u4e86\u4e00\u4e9b\u51fd\u6578\u4f86\u89e3\u6790 JSON \u6578\u64da\uff0c\u7279\u5225\u662f JSON \u9663\u5217\u3002\u672c\u6587\u5c07\u6df1\u5165\u63a2\u8a0e\u5982\u4f55\u5728 Hive \u4e2d\u5b8c\u7f8e\u89e3\u6790 JSON \u9663\u5217\uff0c\u4e26\u63d0\u4f9b\u5be6\u7528\u7684\u7bc4\u4f8b\u548c\u4ee3\u78bc\u3002<\/p>\n<h2 id=\"json-%e9%99%a3%e5%88%97%e7%9a%84%e5%9f%ba%e6%9c%ac%e6%a6%82%e5%bf%b5-YNGhkQxCuc\">JSON \u9663\u5217\u7684\u57fa\u672c\u6982\u5ff5<\/h2>\n<p>JSON\uff08JavaScript Object Notation\uff09\u662f\u4e00\u7a2e\u8f15\u91cf\u7d1a\u7684\u6578\u64da\u4ea4\u63db\u683c\u5f0f\uff0c\u6613\u65bc\u4eba\u985e\u95b1\u8b80\u548c\u7de8\u5beb\uff0c\u540c\u6642\u4e5f\u6613\u65bc\u6a5f\u5668\u89e3\u6790\u548c\u751f\u6210\u3002JSON \u9663\u5217\u662f\u4e00\u7d44\u6709\u5e8f\u7684\u503c\uff0c\u53ef\u4ee5\u5305\u542b\u591a\u7a2e\u6578\u64da\u985e\u578b\uff0c\u5305\u62ec\u5c0d\u8c61\u3001\u6578\u5b57\u3001\u5b57\u7b26\u4e32\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u500b\u7c21\u55ae\u7684 JSON \u9663\u5217\u7bc4\u4f8b\uff1a<\/p>\n<pre><code>[\n    {\"name\": \"Alice\", \"age\": 30},\n    {\"name\": \"Bob\", \"age\": 25},\n    {\"name\": \"Charlie\", \"age\": 35}\n]\n<\/code><\/pre>\n<h2 id=\"hive-%e4%b8%ad%e8%a7%a3%e6%9e%90-json-%e9%99%a3%e5%88%97%e7%9a%84%e5%87%bd%e6%95%b8-YNGhkQxCuc\">Hive \u4e2d\u89e3\u6790 JSON \u9663\u5217\u7684\u51fd\u6578<\/h2>\n<p>\u5728 Hive \u4e2d\uff0c\u89e3\u6790 JSON \u6578\u64da\u4e3b\u8981\u4f9d\u8cf4\u65bc <code>get_json_object<\/code> \u548c <code>json_tuple<\/code> \u9019\u5169\u500b\u51fd\u6578\u3002\u9019\u4e9b\u51fd\u6578\u53ef\u4ee5\u5e6b\u52a9\u7528\u6236\u5f9e JSON \u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u6240\u9700\u7684\u6578\u64da\u3002<\/p>\n<h3 id=\"1-%e4%bd%bf%e7%94%a8-get_json_object-%e5%87%bd%e6%95%b8-YNGhkQxCuc\">1. \u4f7f\u7528 get_json_object \u51fd\u6578<\/h3>\n<p><code>get_json_object<\/code> \u51fd\u6578\u7528\u65bc\u5f9e JSON \u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u7279\u5b9a\u7684\u5b57\u6bb5\u3002\u5176\u8a9e\u6cd5\u5982\u4e0b\uff1a<\/p>\n<pre><code>get_json_object(json_string, json_path)<\/code><\/pre>\n<p>\u5176\u4e2d\uff0c<code>json_string<\/code> \u662f\u8981\u89e3\u6790\u7684 JSON \u5b57\u7b26\u4e32\uff0c<code>json_path<\/code> \u662f\u8981\u63d0\u53d6\u7684\u5b57\u6bb5\u8def\u5f91\u3002\u4ee5\u4e0b\u662f\u4e00\u500b\u793a\u4f8b\uff1a<\/p>\n<pre><code>SELECT get_json_object('{\"name\": \"Alice\", \"age\": 30}', '$.name') AS name;\n<\/code><\/pre>\n<p>\u9019\u5c07\u8fd4\u56de <code>Alice<\/code>\u3002<\/p>\n<h3 id=\"2-%e4%bd%bf%e7%94%a8-json_tuple-%e5%87%bd%e6%95%b8-YNGhkQxCuc\">2. \u4f7f\u7528 json_tuple \u51fd\u6578<\/h3>\n<p><code>json_tuple<\/code> \u51fd\u6578\u53ef\u4ee5\u5f9e JSON \u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u591a\u500b\u5b57\u6bb5\u3002\u5176\u8a9e\u6cd5\u5982\u4e0b\uff1a<\/p>\n<pre><code>json_tuple(json_string, field1, field2, ...)<\/code><\/pre>\n<p>\u4ee5\u4e0b\u662f\u4e00\u500b\u793a\u4f8b\uff1a<\/p>\n<pre><code>SELECT json_tuple('{\"name\": \"Alice\", \"age\": 30}', 'name', 'age') AS (name, age);\n<\/code><\/pre>\n<p>\u9019\u5c07\u8fd4\u56de <code>Alice<\/code> \u548c <code>30<\/code>\u3002<\/p>\n<h2 id=\"%e8%a7%a3%e6%9e%90-json-%e9%99%a3%e5%88%97%e7%9a%84%e5%af%a6%e9%9a%9b%e7%af%84%e4%be%8b-YNGhkQxCuc\">\u89e3\u6790 JSON \u9663\u5217\u7684\u5be6\u969b\u7bc4\u4f8b<\/h2>\n<p>\u5047\u8a2d\u6211\u5011\u6709\u4e00\u500b\u5305\u542b JSON \u9663\u5217\u7684\u8868\u683c\uff0c\u540d\u70ba <code>users<\/code>\uff0c\u5176\u7d50\u69cb\u5982\u4e0b\uff1a<\/p>\n<pre><code>CREATE TABLE users (data STRING);\n<\/code><\/pre>\n<p>\u4e26\u4e14\u6211\u5011\u63d2\u5165\u4e86\u4e00\u4e9b\u6578\u64da\uff1a<\/p>\n<pre><code>INSERT INTO users VALUES\n('[\n    {\"name\": \"Alice\", \"age\": 30},\n    {\"name\": \"Bob\", \"age\": 25},\n    {\"name\": \"Charlie\", \"age\": 35}\n]');\n<\/code><\/pre>\n<p>\u8981\u89e3\u6790\u9019\u500b JSON \u9663\u5217\uff0c\u6211\u5011\u53ef\u4ee5\u4f7f\u7528 <code>explode<\/code> \u51fd\u6578\u4f86\u5c55\u958b\u9663\u5217\uff0c\u7136\u5f8c\u4f7f\u7528 <code>get_json_object<\/code> \u63d0\u53d6\u6bcf\u500b\u5c0d\u8c61\u7684\u5b57\u6bb5\uff1a<\/p>\n<pre><code>SELECT get_json_object(user.value, '$.name') AS name,\n       get_json_object(user.value, '$.age') AS age\nFROM users\nLATERAL VIEW explode(split(data, ',')) user AS value;\n<\/code><\/pre>\n<p>\u9019\u5c07\u8fd4\u56de\u6bcf\u500b\u7528\u6236\u7684\u59d3\u540d\u548c\u5e74\u9f61\u3002<\/p>\n<h2 id=\"%e7%b8%bd%e7%b5%90-YNGhkQxCuc\">\u7e3d\u7d50<\/h2>\n<p>\u5728 Hive \u4e2d\u89e3\u6790 JSON \u9663\u5217\u662f\u4e00\u500b\u76f8\u5c0d\u7c21\u55ae\u7684\u904e\u7a0b\uff0c\u901a\u904e\u4f7f\u7528 <code>get_json_object<\/code> \u548c <code>json_tuple<\/code> \u51fd\u6578\uff0c\u958b\u767c\u8005\u53ef\u4ee5\u8f15\u9b06\u5730\u5f9e JSON \u6578\u64da\u4e2d\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002\u96a8\u8457\u5927\u6578\u64da\u6280\u8853\u7684\u767c\u5c55\uff0c\u638c\u63e1\u9019\u4e9b\u6280\u80fd\u5c07\u5c0d\u6578\u64da\u5206\u6790\u548c\u8655\u7406\u6709\u5f88\u5927\u7684\u5e6b\u52a9\u3002<\/p>\n<p>\u5982\u679c\u60a8\u6b63\u5728\u5c0b\u627e\u9ad8\u6548\u7684 <a href=\"https:\/\/server.hk\">\u9999\u6e2fVPS<\/a> \u89e3\u6c7a\u65b9\u6848\u4f86\u652f\u6301\u60a8\u7684\u5927\u6578\u64da\u9805\u76ee\uff0cServer.HK \u63d0\u4f9b\u591a\u7a2e\u9078\u64c7\uff0c\u6eff\u8db3\u4e0d\u540c\u9700\u6c42\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u63a2\u7d22 Hive \u4e2d\u5b8c\u7f8e\u89e3\u6790 JSON \u9663\u5217\u7684\u51fd\u6578\uff0c\u63d0\u5347\u6578\u64da\u8655\u7406\u6548\u7387\uff0c\u7c21\u5316\u67e5\u8a62\u904e\u7a0b\uff0c\u52a9\u4f60\u8f15\u9b06\u7ba1\u7406\u5927\u6578\u64da\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-61571","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/61571","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=61571"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/61571\/revisions"}],"predecessor-version":[{"id":61572,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/61571\/revisions\/61572"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=61571"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=61571"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=61571"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}