{"id":5785,"date":"2024-11-28T14:18:50","date_gmt":"2024-11-28T06:18:50","guid":{"rendered":"https:\/\/ixyzero.com\/blog\/?p=5785"},"modified":"2024-11-28T14:18:50","modified_gmt":"2024-11-28T06:18:50","slug":"hive-sql%e4%b8%ad%e7%9a%84%e5%8d%95%e5%bc%95%e5%8f%b7%e5%92%8c%e5%8f%8c%e5%bc%95%e5%8f%b7","status":"publish","type":"post","link":"https:\/\/ixyzero.com\/blog\/archives\/5785.html","title":{"rendered":"Hive SQL\u4e2d\u7684\u5355\u5f15\u53f7\u548c\u53cc\u5f15\u53f7"},"content":{"rendered":"\n<p>=Start=<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u7f18\u7531\uff1a<\/h4>\n\n\n\n<p>\u6700\u8fd1\u53c8\u82b1\u8d39\u4e86\u4e00\u4e9b\u65f6\u95f4\u5728\u5904\u7406Hive SQL\u4e2d\u7684\u5355\u53cc\u5f15\u53f7\u95ee\u9898\u4e0a\uff0c\u611f\u89c9\u9700\u8981\u518d\u4e13\u95e8\u8bb0\u5f55\u4e00\u4e0b\uff0c\u65b9\u4fbf\u540e\u9762\u6709\u9700\u8981\u7684\u65f6\u5019\u53c2\u8003\u3002<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">\u6b63\u6587\uff1a<\/h4>\n\n\n\n<h5 class=\"wp-block-heading\">\u53c2\u8003\u89e3\u7b54\uff1a<\/h5>\n\n\n\n<p>\u7b80\u5355\u6765\u8bf4\u5c31\u662f\uff0c<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong><mark style=\"background-color:rgba(0, 0, 0, 0);color:#ff0000\" class=\"has-inline-color\">\u60f3\u663e\u793a\u5305\u542b\u5355\u5f15\u53f7\u7684\u5185\u5bb9\u65f6\uff0c\u7528\u53cc\u5f15\u53f7\u5305\u88f9<\/mark><\/strong>\uff0c\u6682\u65f6\u8fd8\u6ca1\u6709\u627e\u5230\u5982\u4f55\u5728\u5355\u5f15\u53f7\u62ec\u4f4f\u7684\u5b57\u7b26\u4e32\u91cc\u9762\u76f4\u63a5\u628a\u5355\u5f15\u53f7\u7ed9\u663e\u793a\u51fa\u6765\u7684\u529e\u6cd5\uff1b<\/li>\n\n\n\n<li>\u60f3\u663e\u793a\u5305\u542b\u53cc\u5f15\u53f7\u7684\u5185\u5bb9\u65f6\uff0c\u7528\u5355\u5f15\u53f7\u5305\u88f9\uff0c\u6216\u8005\u5bf9\u5185\u90e8\u7684\u53cc\u5f15\u53f7\u505a\u8f6c\u4e49\uff1b<\/li>\n\n\n\n<li><mark style=\"background-color:rgba(0, 0, 0, 0);color:#ff0000\" class=\"has-inline-color\"><strong>\u5982\u679c\u60f3\u51cf\u5c11\u9ebb\u70e6\uff0c\u7528\u53cc\u5f15\u53f7\u5305\u88f9\uff0c\u56e0\u4e3a\u5bf9\u53cc\u5f15\u53f7\u7684\u8f6c\u4e49\u65b9\u4fbf\u4e14\u6709\u6548<\/strong>\u3002<\/mark><\/li>\n<\/ul>\n\n\n\n<p>\u901a\u4e49\u5343\u95ee\u3001\u8c46\u5305\u7b49LLM\u5927\u6a21\u578b\u95ee\u7b54\u4e0a\u7684\u56de\u7b54\u90fd\u4e0d\u9760\u8c31\uff0c\u8fde\u7f16\u8bd1\u5668\u90a3\u4e00\u5173\u68c0\u67e5\u90fd\u8fc7\u4e0d\u53bb\uff08\u63d0\u793a\u5b57\u7b26\u4e32\u672a\u95ed\u5408\uff09\uff0c\u6211\u81ea\u6d4b\u6dfb\u52a0\u8f6c\u4e49\u5b57\u7b26\u7684SQL\u53c8\u65e0\u6cd5\u6b63\u5e38\u5de5\u4f5c\uff0c\u5f53\u524d\u53ea\u80fd\u662f\u5148\u8fd9\u6837\u4e86\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>-- \u6d4b\u8bd5SQL\nwith t1 as (\n    SELECT\n    'a b c' as sep_blank\n    ,'a\\'b\\'c' as sep_single_quote --\u3010a\\c\u3011?\n    ,'a''b''c' as sep_single_quote2 --\u3010abc\u3011\n    ,'\\'' as single_quote --\u3010\\\u3011\u4e3a\u4ec0\u4e48\u4f1a\u663e\u793a\u8fd9\u4e2a\uff1f\u6211\u60f3\u663e\u793a\u7684\u662f\u5355\u5f15\u53f7\u3010'\u3011\n    ,'\\\\\\'' as single_quote2 --\u3010\\\\\u3011\n    ,\"name like 'a b c'\" as value1 --ok\n    ,\"name like \\\"a b c\\\"\" as value2\n)\n\nSELECT\n*\n,regexp_extract(value1,'(name|email)\\\\s{0,}like\\\\s{0,}(\\\\S{2,})',2) as name_like --\u3010'a\u3011\n,regexp_extract(value1,\"(name|email)\\\\s{0,}like\\\\s{0,}'(&#91;^']{2,})'\",2) as name_like2 --\u3010a b c\u3011\u6ee1\u8db3\u76ee\u6807\u8981\u6c42\n,regexp_extract(value2,'(name|email)\\\\s{0,}like\\\\s{0,}(\\\\S{2,})',2) as name2_like --\u3010\"a\u3011\n,regexp_extract(value1,\"(name|email)\\\\s{0,}like\\\\s{0,}&#91;'|\\\"](&#91;^\\\"']{2,})&#91;'|\\\"]\",2) as name1_like2 --ok\n,regexp_extract(value2,\"(name|email)\\\\s{0,}like\\\\s{0,}&#91;'|\\\"](&#91;^\\\"']{2,})&#91;'|\\\"]\",2) as name2_like2 --ok\nFROM\nt1\n;\n\n-- \u4ee5\u4e0b\u662f\u8f93\u51fa\u7684\u7ed3\u679c\na b c\na\\c\nabc\n\\\n\\\\\nname like 'a b c'\nname like \"a b c\"\n'a\na b c\n\"a\na b c\na b c<\/code><\/pre>\n\n\n\n<h5 class=\"wp-block-heading\">\u53c2\u8003\u94fe\u63a5\uff1a<\/h5>\n\n\n\n<p>\u6682\u65e0<\/p>\n\n\n\n<p>=END=<\/p>\n","protected":false},"excerpt":{"rendered":"<p>=Start= \u7f18\u7531\uff1a \u6700\u8fd1\u53c8\u82b1\u8d39\u4e86\u4e00\u4e9b\u65f6\u95f4\u5728\u5904\u7406Hive SQL\u4e2d\u7684\u5355\u53cc\u5f15\u53f7\u95ee\u9898\u4e0a\uff0c\u611f\u89c9\u9700\u8981\u518d\u4e13\u95e8\u8bb0\u5f55\u4e00\u4e0b\uff0c [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14,23,7],"tags":[1261,1262,19,2374,2371,2372,2373],"class_list":["post-5785","post","type-post","status-publish","format-standard","hentry","category-database","category-knowledgebase-2","category-programing","tag-hive","tag-sql","tag-tips","tag-2374","tag-2371","tag-2372","tag-2373"],"views":3249,"_links":{"self":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/5785","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/comments?post=5785"}],"version-history":[{"count":1,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/5785\/revisions"}],"predecessor-version":[{"id":5786,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/5785\/revisions\/5786"}],"wp:attachment":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/media?parent=5785"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/categories?post=5785"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/tags?post=5785"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}