{"id":5428,"date":"2023-04-18T19:47:43","date_gmt":"2023-04-18T11:47:43","guid":{"rendered":"https:\/\/ixyzero.com\/blog\/?p=5428"},"modified":"2023-04-18T19:47:43","modified_gmt":"2023-04-18T11:47:43","slug":"%e6%8f%90%e5%8f%96sql%e4%b8%ad%e7%9a%84limit%e9%99%90%e5%88%b6%e6%95%b0%e5%80%bc","status":"publish","type":"post","link":"https:\/\/ixyzero.com\/blog\/archives\/5428.html","title":{"rendered":"\u63d0\u53d6SQL\u4e2d\u7684limit\u9650\u5236\u6570\u503c"},"content":{"rendered":"\n

=Start=<\/p>\n\n\n\n

\u7f18\u7531\uff1a<\/h4>\n\n\n\n

\u505a\u654f\u611f\u6570\u636e\u8bbf\u95ee\u76d1\u63a7\u65f6\u6709\u4e2a\u65b9\u5411\u5c31\u662f\u67e5\u8be2SQL\u7684\u5206\u6790\uff0c\u9664\u4e86\u654f\u611f\u8868\u7684\u67e5\u8be2\u9700\u8981\u6ce8\u610f\u4e4b\u5916\uff0c\u67e5\u8be2\u7684\u5927\u5c0f\u548c\u8fd4\u56de\u5927\u5c0f\u4e5f\u662f\u9700\u8981\u91cd\u70b9\u5173\u6ce8\u7684\u5730\u65b9\uff0c\u8fd4\u56de\u5927\u5c0f\u4ec5\u4eceSQL\u8bed\u53e5\u4e2d\u65e0\u6cd5\u5206\u6790\u548c\u4f53\u73b0\uff0c\u8fd9\u4e2a\u9700\u8981\u5728\u7c7b\u4f3cHiveServer2\u8fd9\u6837\u7684\u4e2d\u5fc3\u670d\u52a1\u5c42\u9762\u6216\u8005\u66f4\u5e95\u5c42\u7684\u5404\u6267\u884c\u5f15\u64ce\u4e0a\u505a\u65e5\u5fd7\u6253\u70b9\u624d\u80fd\u8bb0\u5f55\u5230\uff0c\u8fd9\u91cc\u4e3b\u8981\u8bf4\u4e00\u4e0b\u4eceSQL\u67e5\u8be2\u8bed\u53e5\u4e2d\u5982\u4f55\u7c97\u7565\u83b7\u53d6\u67e5\u8be2\u7684\u5927\u5c0f\u3002<\/p>\n\n\n\n

\u6b63\u6587\uff1a<\/h4>\n\n\n\n

\u53c2\u8003\u89e3\u7b54\uff1a<\/h5>\n\n\n\n
\u5b57\u7b26\u4e32\u5207\u5206(\u4e5f\u662f\u6b63\u5219) + \u6b63\u5219\u63d0\u53d6 \u7ed3\u5408\u4f7f\u7528\uff0c\u5b57\u7b26\u4e32\u5207\u5206\u53ef\u4ee5\u6839\u636e\u5207\u5206\u7684\u6570\u7ec4\u5927\u5c0f\u5224\u65ad\u51fa\u73b0\u6b21\u6570\uff0c\u6b63\u5219\u63d0\u53d6\u6bd4\u8f83\u7b80\u5355\u76f4\u63a5\u3002\n\n1. \u5173\u952e\u5728\u4e8e\u5148\u7406\u89e3 limit clause \u7684\u51e0\u79cd\u8bed\u6cd5\u5bf9\u5e94\u683c\u5f0f\n2. \u7136\u540e\u7f16\u5199\u5bf9\u5e94\u6b63\u5219\u7528\u6765\u5339\u914d\u548c\u63d0\u53d6\n3. \u5982\u679c\u6ca1\u6709\u989d\u5916\u9700\u6c42\uff0c\u5176\u5b9e\u7528\u6b63\u5219\u5c31\u80fd\u641e\u5b9a\uff0c\u4e0d\u9700\u8981\u5199UDF\uff0c\u4e0d\u8fc7\u5199UDF\u7684\u597d\u5904\u5728\u4e8e\u5916\u5c42SQL\u7b80\u6d01\u4e00\u4e9b<\/code><\/pre>\n\n\n\n
Limit\u7528\u4e8e\u5bf9\u67e5\u8be2\u7ed3\u679c\u96c6\u6570\u91cf\u8fdb\u884c\u9650\u5236\uff1bOffset \u5219\u5e38\u4e0e Limit \u642d\u914d\uff0c\u610f\u4e3a\u504f\u79fb\uff0c\u8868\u793a\u8df3\u8fc7\u4e00\u5b9a\u6570\u91cf\u7684\u8bb0\u5f55\u3002\n\nLimit \u540e\u9762\u53ef\u63a5\u53d7\u4e00\u4e2a\u53c2\u6570\u6216\u8005\u4e24\u4e2a\u53c2\u6570\uff1a\n\u5f53\u63a5\u53d7\u4e00\u4e2a\u53c2\u6570count\u65f6\uff0c\u8868\u793a\u8fd4\u56de\u7684\u7ed3\u679c\u96c6\u6700\u591a\u6709 count \u6761\u3002\n\u5f53\u4f7f\u7528\u4e24\u4e2a\u53c2\u6570\u65f6\uff0c\u7b2c\u4e00\u4e2a\u53c2\u6570\u8868\u793a\u504f\u79fb\u91cf\uff0c\u5373 offset\uff0c\u8868\u793a\u4ece\u51e0\u4e2a\u8bb0\u5f55\u540e\u5f00\u59cb\u8fd4\u56de\uff0c\u7b2c\u4e8c\u4e2a\u53c2\u6570\u8868\u793a\u6700\u5927\u6570\u91cf\uff0c\u5373 count\uff0c\u8868\u793a\u6700\u591a\u8fd4\u56de\u51e0\u4e2a\u8bb0\u5f55\u3002\u6211\u4eec\u5408\u8d77\u6765\u53ef\u4ee5\u7406\u89e3\u4e3a\uff0c\u8df3\u8fc7\u4e00\u5b9a\u6570\u91cf\uff08offset\uff09\u7684\u8bb0\u5f55\uff0c\u8fd4\u56de\u6700\u591a count \u4e2a\u8bb0\u5f55\u3002\n\nOffset \u5fc5\u987b\u4e0e Limit \u642d\u914d\u4f7f\u7528\uff0c\u4e14\u4e8c\u8005\u90fd\u5fc5\u987b\u662f\u5355\u53c2\u6570\u5f62\u5f0f\u3002Limit \u548c Offset \u642d\u914d\u7684\u4f5c\u7528\u7b49\u540c\u4e8e Limit \u4f7f\u7528\u53cc\u53c2\u6570\u3002offset\u662f\u504f\u79fb\u91cf\uff0cLimit\u540e\u9762\u7684count\u662f\u6700\u5927\u6570\u91cf\u3002\n\nLimit \u548c Offset \u5e38\u642d\u914d\u7528\u4e8e\u6570\u636e\u5206\u9875\uff0c\u662f\u5f88\u591a\u5206\u9875\u5de5\u5177\u7684\u6838\u5fc3\u64cd\u4f5c\u3002\nLimit \u5176\u5b9e\u5b8c\u5168\u53ef\u4ee5\u66ff\u4ee3 Limit + Offset\uff0c\u4f46\u8003\u8651\u5230SQL\u8bed\u53e5\u7684\u53ef\u8bfb\u6027\uff0cLimit + Offset\u7684\u5199\u6cd5\u66f4\u597d\u3002<\/code><\/pre>\n\n\n\n
package com.ixyzero.hive.udf.utils;\n\nimport net.sf.jsqlparser.JSQLParserException;\nimport net.sf.jsqlparser.parser.CCJSqlParserUtil;\nimport net.sf.jsqlparser.statement.Statement;\nimport net.sf.jsqlparser.statement.select.*;\n\nimport java.util.regex.Matcher;\nimport java.util.regex.Pattern;\n\nimport org.apache.hadoop.hive.ql.exec.Description;\nimport org.apache.hadoop.hive.ql.exec.UDF;\n\n\/**\n * @author ixyzero\n * Created on 2023-03-28\n *\/\n\n@Description(name = \"getSqlLimitSize\",\n        value = \"_FUNC_(str) - Get limit size from search sql string.\",\n        extended = \"The value is returned as a string, or NULL if the argument was NULL.\\n\"\n                + \"Example:\\n\"\n                + \"  > SELECT _FUNC_('select * from tbl where col1 = 11 limit 1000;');\\n\"\n                + \"  '1000'\\n\")\n\n\/\/public class getSqlLimitSizeUDF {\npublic class getSqlLimitSizeUDF extends UDF {\n    private static final Pattern commentaryPattern = Pattern.compile(\"\/\\\\\\\\*.*?\\\\\\\\*\/|--.*?\", Pattern.DOTALL);\n    private static final Pattern limitPattern = Pattern.compile(\"\\\\s+limit\\\\s+(\\\\d+)\\\\s*(,|offset)?\\\\s*(\\\\d*)\\\\s*\", Pattern.CASE_INSENSITIVE);\n\n    String ret = \"\";\n\n    \/**\n     * Get limit size from search sql string.\n     *\/\n    public String evaluate(String sql) {\n        if (sql == null || sql.trim().isEmpty()) {\n            return null;\n        }\n        sql = commentaryPattern.matcher(sql).replaceAll(\"\").toLowerCase();\n\n        try {\n            Statement stmt = CCJSqlParserUtil.parse(sql);\n            Select selectStatement = (Select) stmt;\n\n            Matcher m = limitPattern.matcher(sql);\n            if (m.find()) {\n                if (m.group(2) == null) {\n                    ret = m.group(1);\n                } else if (m.group(2).equalsIgnoreCase(\"offset\")) {\n                    ret = m.group(1);\n                } else {\n                    ret = m.group(3);\n                }\n            } else {\n                ret = \"0\";\n            }\n\n        } catch (JSQLParserException e) {\n            \/\/ e.printStackTrace();\n            return null;\n        } catch (Exception e) {\n            \/\/ e.printStackTrace();\n            return null;\n        }\n\n        return ret;\n    }\n\n    public static void main(String[] args) {\n        getSqlLimitSizeUDF getSqlLimitSize = new getSqlLimitSizeUDF();\n        String str = \"select * from tbl where col1 = 11 and col2 = 1001 LIMIT 1000 offset 2\";\n        System.out.println(str);\n        System.out.println(getSqlLimitSize.evaluate(str));\n\n        str = \"select * from tbl where col1 = 11 and col2 = 1001 LIMIT 1000, 2\";\n        System.out.println(str);\n        System.out.println(getSqlLimitSize.evaluate(str));\n\n        str = \"select * from (select * from tbl where col1 = 11 and col2 = 1001 LIMIT 1000)x1\";\n        System.out.println(str);\n        System.out.println(getSqlLimitSize.evaluate(str));\n\n        str = \"select * from tbl where col1 = 11 and col2 = 1001\";\n        System.out.println(str);\n        System.out.println(getSqlLimitSize.evaluate(str));\n    }\n\n}<\/code><\/pre>\n\n\n\n
regexp_extract(lower(regexp_replace(query_sql,'--.+?\\\\n{1,}','')), '\\\\s+limit\\\\s+(\\\\d+)\\\\s*(,|offset)?\\\\s*(\\\\d*)\\\\s*', 0) as limit_info,\nsize(split(lower(regexp_replace(query_sql,'--.+?\\\\n{1,}','')),'\\\\s{1,}limit\\\\s{1,}')) as limit_cnt,<\/code><\/pre>\n\n\n\n
\/*\n\u4e00\u53e5\u8bdd\u7b80\u5355\u603b\u7ed3\uff1a\nlimit \u6709 offset \u7684\u60c5\u51b5\uff0c\u524d\u4e3a\u6570\u91cf\uff0c\u540e\u4e3a\u504f\u79fb\uff08\u6839\u636e\u7ebf\u4e0a\u7684SQL\u6765\u770b\uff0c\u7528offset\u8bed\u6cd5\u7684\u4e0d\u591a\uff0c\u611f\u89c9\u5e94\u8be5\u662f\u4e0e\u5199\u6cd5\u6bd4\u8f83\u9ebb\u70e6\u6709\u5173\uff09\nlimit \u6709 2\u4e2a\u53c2\u6570 \u7684\u60c5\u51b5\uff0c\u524d\u4e3a\u504f\u79fb\uff0c\u540e\u4e3a\u6570\u91cf\nlimit \u6709 1\u4e2a\u53c2\u6570 \u7684\u60c5\u51b5\uff0c\u8868\u793a\u6570\u91cf\n*\/\n\nwith t as (\n  select '2020-12-28' as dt_start, '2021-01-12' as dt_end\n)\n,t2 as (select\nidx, date_add(to_date(dt_start), idx) as dt\nfrom t\nlateral view posexplode(split(space(datediff(t.dt_end,t.dt_start)),' ')) pi as idx, empty\n)\n\n-- \u5f53limit\u540e\u9762\u8ddf\u4e00\u4e2a\u53c2\u6570\u7684\u65f6\u5019\uff0c\u8be5\u53c2\u6570\u8868\u793a\u8981\u53d6\u7684\u6570\u636e\u7684\u6570\u91cf\n-- select idx,dt\n-- from t2\n-- limit 5\n\/*\nidx    dt  \n0    2020-12-28\n1    2020-12-29\n2    2020-12-30\n3    2020-12-31\n4    2021-01-01\n*\/\n\n-- \u5f53limit\u540e\u9762\u8ddf\u4e24\u4e2a\u53c2\u6570\u7684\u65f6\u5019\uff0c\u7b2c\u4e00\u4e2a\u6570\u8868\u793a\u8981\u8df3\u8fc7\u7684\u6570\u91cf\uff0c\u7b2c\u4e8c\u4e2a\u6570\u8868\u793a\u8981\u53d6\u7684\u6570\u91cf\n-- \u4e0b\u9762\u8fd9\u4e2acase\u91cc\u9762\u5c31\u662f\u53ea\u8fd4\u56de2\u884c\n-- select idx,dt\n-- from t2\n-- limit 5,2\n\/*\nidx    dt  \n5    2021-01-02\n6    2021-01-03\n*\/\n\n-- OFFSET\u5b50\u53e5\u5728\u5f00\u59cb\u8fd4\u56de\u884c\u4e4b\u524d\u8df3\u8fc7\u504f\u79fb\u884c\u3002 OFFSET\u5b50\u53e5\u662f\u53ef\u9009\u7684\u3002 \u5982\u679c\u540c\u65f6\u4f7f\u7528LIMIT\u548cOFFSET\u5b50\u53e5\uff0cOFFSET\u4f1a\u5728LIMIT\u7ea6\u675f\u884c\u6570\u4e4b\u524d\u5148\u8df3\u8fc7\u504f\u79fb\u884c\n-- limit 5 offset 2 \u8fd9\u4e2a\u4f8b\u5b50\u7684\u542b\u4e49\u662f\u4eceoffset\u504f\u79fb\u4e3a2\u5f00\u59cb\uff0c\u53d6\u63a5\u4e0b\u6765\u76845\u884c\nselect idx,dt\nfrom t2\nlimit 5 offset 2\n\/*\nidx    dt  \n2    2020-12-30\n3    2020-12-31\n4    2021-01-01\n5    2021-01-02\n6    2021-01-03\n*\/<\/code><\/pre>\n\n\n\n
\u53c2\u8003\u94fe\u63a5\uff1a<\/h5>\n\n\n\n
SQL Limit\u5b50\u53e5
https:\/\/www.yiibai.com\/sql\/sql-limit.html<\/a><\/p>\n\n\n\n
SQL Limit & Offset
https:\/\/m.imooc.com\/wiki\/sqlbase-sqllimitoffset<\/a><\/p>\n\n\n\n
MYSQL LIMIT \u7528\u6cd5
https:\/\/www.runoob.com\/note\/28032<\/a><\/p>\n\n\n\n
regular expression in hive
https:\/\/stackoverflow.com\/questions\/46060475\/regular-expression-in-hive<\/a><\/p>\n\n\n\n
LanguageManual UDF
https:\/\/cwiki.apache.org\/confluence\/display\/Hive\/LanguageManual+UDF#LanguageManualUDF-StringFunctions<\/a><\/p>\n\n\n\n
Using regular expressions to extract a value in Java
https:\/\/stackoverflow.com\/questions\/237061\/using-regular-expressions-to-extract-a-value-in-java<\/a><\/p>\n\n\n\n
hive\u51fd\u6570 — split \u5b57\u7b26\u4e32\u5206\u5272\u51fd\u6570
https:\/\/blog.csdn.net\/lxpbs8851\/article\/details\/18712407<\/a><\/p>\n\n\n\n
Java regex to remove SQL comments from a string
https:\/\/stackoverflow.com\/questions\/10225923\/java-regex-to-remove-sql-comments-from-a-string<\/a><\/p>\n\n\n\n
Use Regular Expressions to Clean SQL Statements
https:\/\/larrysteinle.com\/2011\/02\/09\/use-regular-expressions-to-clean-sql-statements\/<\/a><\/p>\n\n\n\n
Remove single line and multiline comments from string
https:\/\/codegolf.stackexchange.com\/questions\/48326\/remove-single-line-and-multiline-comments-from-string<\/a><\/p>\n\n\n\n
Java code to delete comments from an input string
https:\/\/codereview.stackexchange.com\/questions\/178220\/java-code-to-delete-comments-from-an-input-string<\/a><\/p>\n\n\n\n
Comments Within SQL Statements
https:\/\/docs.oracle.com\/cd\/B14117_01\/server.101\/b10759\/sql_elements006.htm<\/a><\/p>\n\n\n\n
SQL Comments
https:\/\/www.w3schools.com\/sql\/sql_comments.asp<\/a><\/p>\n\n\n\n
HiveServer2 Overview
https:\/\/cwiki.apache.org\/confluence\/display\/Hive\/HiveServer2+Overview<\/a><\/p>\n\n\n\n
Hive\u67b6\u6784\u4e4bHiveServer2(14)
https:\/\/juejin.cn\/post\/6910568483126411278<\/a><\/p>\n\n\n\n
HiveServer2
https:\/\/www.docs4dev.com\/docs\/zh\/apache-hive\/3.1.1\/reference\/Setting_up_HiveServer2.html<\/a><\/p>\n\n\n\n
Hive\u67b6\u6784\u53ca\u539f\u7406
https:\/\/zhuanlan.zhihu.com\/p\/346668930<\/a><\/p>\n\n\n\n
Hive SQL\u5e95\u5c42\u6267\u884c\u8fc7\u7a0b\u8be6\u7ec6\u5256\u6790\uff08\u597d\u6587\u6536\u85cf\uff09
https:\/\/mp.weixin.qq.com\/s\/7yffuvCr17naOS7GeV8tTQ<\/a><\/p>\n\n\n\n
Spark SQL\u5e95\u5c42\u6267\u884c\u6d41\u7a0b\u8be6\u89e3\uff08\u597d\u6587\u6536\u85cf\uff09
https:\/\/mp.weixin.qq.com\/s\/CWdBLhgUrLxlsavTFhA0rA<\/a><\/p>\n\n\n\n
\u4e00\u8d77\u4e86\u89e3\u4e00\u4e0bHiveServer2
https:\/\/mp.weixin.qq.com\/s\/iGxPWGp9oGeRuI7j_iglww<\/a><\/p>\n\n\n\n
hiveserver2 \u662f\u4ec0\u4e48\uff1f
https:\/\/blog.csdn.net\/u010738184\/article\/details\/80534147<\/a><\/p>\n\n\n\n
=END=<\/p>\n","protected":false},"excerpt":{"rendered":"
=Start= \u7f18\u7531\uff1a \u505a\u654f\u611f\u6570\u636e\u8bbf\u95ee\u76d1\u63a7\u65f6\u6709\u4e2a\u65b9\u5411\u5c31\u662f\u67e5\u8be2SQL\u7684\u5206\u6790\uff0c\u9664\u4e86\u654f\u611f\u8868\u7684\u67e5\u8be2\u9700\u8981\u6ce8\u610f\u4e4b\u5916\uff0c\u67e5\u8be2\u7684 […]<\/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":[1261,1938,438,377,1262,1560],"class_list":["post-5428","post","type-post","status-publish","format-standard","hentry","category-database","category-knowledgebase-2","category-programing","tag-hive","tag-limit","tag-offset","tag-regex","tag-sql","tag-udf"],"views":1385,"_links":{"self":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/5428","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=5428"}],"version-history":[{"count":1,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/5428\/revisions"}],"predecessor-version":[{"id":5429,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/5428\/revisions\/5429"}],"wp:attachment":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/media?parent=5428"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/categories?post=5428"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/tags?post=5428"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}