{"id":179688,"date":"2024-11-09T03:58:24","date_gmt":"2024-11-08T19:58:24","guid":{"rendered":"https:\/\/server.hk\/cnblog\/179688\/"},"modified":"2024-11-09T03:58:25","modified_gmt":"2024-11-08T19:58:25","slug":"%e5%a6%82%e4%bd%95%e5%9c%a8-spark-%e4%b8%ad%e4%bd%bf%e7%94%a8-hive-%e6%95%b8%e6%93%9a%e5%ba%ab%ef%bc%9f-spark-%e7%9a%84-hive-%e6%95%b8%e6%93%9a%e5%ba%ab","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/179688\/","title":{"rendered":"\u5982\u4f55\u5728 Spark \u4e2d\u4f7f\u7528 Hive \u6578\u64da\u5eab\uff1f (spark \u7684 hive \u6578\u64da\u5eab)"},"content":{"rendered":"<h1 id=\"%e5%a6%82%e4%bd%95%e5%9c%a8-spark-%e4%b8%ad%e4%bd%bf%e7%94%a8-hive-%e6%95%b8%e6%93%9a%e5%ba%ab%ef%bc%9f-hmxWtfOLuN\">\u5982\u4f55\u5728 Spark \u4e2d\u4f7f\u7528 Hive \u6578\u64da\u5eab\uff1f<\/h1>\n<p>Apache Spark \u662f\u4e00\u500b\u5f37\u5927\u7684\u958b\u6e90\u5206\u6563\u5f0f\u8a08\u7b97\u6846\u67b6\uff0c\u5ee3\u6cdb\u61c9\u7528\u65bc\u5927\u6578\u64da\u8655\u7406\u548c\u5206\u6790\u3002Spark \u63d0\u4f9b\u4e86\u8207 Apache Hive \u7684\u96c6\u6210\uff0c\u4f7f\u5f97\u7528\u6236\u80fd\u5920\u8f15\u9b06\u5730\u5728 Spark \u4e2d\u67e5\u8a62\u548c\u8655\u7406 Hive \u6578\u64da\u5eab\u4e2d\u7684\u6578\u64da\u3002\u672c\u6587\u5c07\u4ecb\u7d39\u5982\u4f55\u5728 Spark \u4e2d\u4f7f\u7528 Hive \u6578\u64da\u5eab\uff0c\u5305\u62ec\u74b0\u5883\u8a2d\u7f6e\u3001\u57fa\u672c\u64cd\u4f5c\u548c\u793a\u4f8b\u4ee3\u78bc\u3002<\/p>\n<h2 id=\"%e7%92%b0%e5%a2%83%e8%a8%ad%e7%bd%ae-hmxWtfOLuN\">\u74b0\u5883\u8a2d\u7f6e<\/h2>\n<p>\u5728\u958b\u59cb\u4e4b\u524d\uff0c\u60a8\u9700\u8981\u78ba\u4fdd\u5df2\u7d93\u5b89\u88dd\u4e86\u4ee5\u4e0b\u7d44\u4ef6\uff1a<\/p>\n<ul>\n<li>Apache Spark<\/li>\n<li>Apache Hive<\/li>\n<li>Hadoop\uff08\u53ef\u9078\uff0c\u6839\u64da\u60a8\u7684\u74b0\u5883\u9700\u6c42\uff09<\/li>\n<\/ul>\n<p>\u63a5\u4e0b\u4f86\uff0c\u60a8\u9700\u8981\u914d\u7f6e Spark \u4ee5\u652f\u6301 Hive\u3002\u9019\u901a\u5e38\u6d89\u53ca\u5230\u4ee5\u4e0b\u5e7e\u500b\u6b65\u9a5f\uff1a<\/p>\n<h3 id=\"1-%e9%85%8d%e7%bd%ae-spark-hmxWtfOLuN\">1. \u914d\u7f6e Spark<\/h3>\n<p>\u5728 Spark \u7684\u914d\u7f6e\u6587\u4ef6\u4e2d\uff08\u901a\u5e38\u662f <code>spark-defaults.conf<\/code>\uff09\uff0c\u6dfb\u52a0\u4ee5\u4e0b\u914d\u7f6e\uff1a<\/p>\n<pre><code>spark.sql.hive.metastore.version  = 2.3.7\nspark.sql.hive.metastore.jars    = hive-metastore-2.3.7.jar,hive-exec-2.3.7.jar\nspark.sql.hive.metastore.uris     = thrift:\/\/localhost:9083\n<\/code><\/pre>\n<p>\u9019\u88e1\u7684 <code>metastore.uris<\/code> \u662f Hive Metastore \u7684 URI\uff0c\u60a8\u9700\u8981\u6839\u64da\u5be6\u969b\u60c5\u6cc1\u9032\u884c\u8abf\u6574\u3002<\/p>\n<h3 id=\"2-%e6%b7%bb%e5%8a%a0-hive-%e4%be%9d%e8%b3%b4-hmxWtfOLuN\">2. \u6dfb\u52a0 Hive \u4f9d\u8cf4<\/h3>\n<p>\u5982\u679c\u60a8\u4f7f\u7528\u7684\u662f Maven\uff0c\u60a8\u53ef\u4ee5\u5728 <code>pom.xml<\/code> \u4e2d\u6dfb\u52a0\u4ee5\u4e0b\u4f9d\u8cf4\uff1a<\/p>\n<pre><code>&lt;dependency&gt;\n    &lt;groupId&gt;org.apache.hive&lt;\/groupId&gt;\n    &lt;artifactId&gt;hive-exec&lt;\/artifactId&gt;\n    &lt;version&gt;2.3.7&lt;\/version&gt;\n&lt;\/dependency&gt;\n&lt;dependency&gt;\n    &lt;groupId&gt;org.apache.hive&lt;\/groupId&gt;\n    &lt;artifactId&gt;hive-metastore&lt;\/artifactId&gt;\n    &lt;version&gt;2.3.7&lt;\/version&gt;\n&lt;\/dependency&gt;\n<\/code><\/pre>\n<h2 id=\"%e5%9f%ba%e6%9c%ac%e6%93%8d%e4%bd%9c-hmxWtfOLuN\">\u57fa\u672c\u64cd\u4f5c<\/h2>\n<p>\u4e00\u65e6\u74b0\u5883\u8a2d\u7f6e\u5b8c\u6210\uff0c\u60a8\u5c31\u53ef\u4ee5\u958b\u59cb\u5728 Spark \u4e2d\u4f7f\u7528 Hive \u6578\u64da\u5eab\u4e86\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u57fa\u672c\u64cd\u4f5c\u7684\u793a\u4f8b\uff1a<\/p>\n<h3 id=\"1-%e5%95%9f%e5%8b%95-sparksession-hmxWtfOLuN\">1. \u555f\u52d5 SparkSession<\/h3>\n<p>\u9996\u5148\uff0c\u60a8\u9700\u8981\u5275\u5efa\u4e00\u500b <code>SparkSession<\/code>\uff0c\u9019\u662f\u8207 Hive \u4ea4\u4e92\u7684\u5165\u53e3\uff1a<\/p>\n<pre><code>from pyspark.sql import SparkSession\n\nspark = SparkSession.builder \n    .appName(\"Hive Integration\") \n    .config(\"spark.sql.warehouse.dir\", \"hdfs:\/\/path\/to\/warehouse\") \n    .enableHiveSupport() \n    .getOrCreate()\n<\/code><\/pre>\n<h3 id=\"2-%e5%89%b5%e5%bb%ba-hive-%e8%a1%a8-hmxWtfOLuN\">2. \u5275\u5efa Hive \u8868<\/h3>\n<p>\u60a8\u53ef\u4ee5\u4f7f\u7528 Spark SQL \u5275\u5efa Hive \u8868\uff1a<\/p>\n<pre><code>spark.sql(\"CREATE TABLE IF NOT EXISTS users (id INT, name STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ','\")\n<\/code><\/pre>\n<h3 id=\"3-%e6%8f%92%e5%85%a5%e6%95%b8%e6%93%9a-hmxWtfOLuN\">3. \u63d2\u5165\u6578\u64da<\/h3>\n<p>\u63d2\u5165\u6578\u64da\u5230 Hive \u8868\u4e2d\uff1a<\/p>\n<pre><code>spark.sql(\"INSERT INTO users VALUES (1, 'Alice'), (2, 'Bob')\")\n<\/code><\/pre>\n<h3 id=\"4-%e6%9f%a5%e8%a9%a2%e6%95%b8%e6%93%9a-hmxWtfOLuN\">4. \u67e5\u8a62\u6578\u64da<\/h3>\n<p>\u4f7f\u7528 Spark SQL \u67e5\u8a62 Hive \u8868\u4e2d\u7684\u6578\u64da\uff1a<\/p>\n<pre><code>result = spark.sql(\"SELECT * FROM users\")\nresult.show()\n<\/code><\/pre>\n<h2 id=\"%e7%b8%bd%e7%b5%90-hmxWtfOLuN\">\u7e3d\u7d50<\/h2>\n<p>\u5728 Spark \u4e2d\u4f7f\u7528 Hive \u6578\u64da\u5eab\u53ef\u4ee5\u5927\u5927\u7c21\u5316\u5927\u6578\u64da\u8655\u7406\u7684\u6d41\u7a0b\u3002\u901a\u904e\u7c21\u55ae\u7684\u914d\u7f6e\u548c\u57fa\u672c\u7684 SQL \u64cd\u4f5c\uff0c\u60a8\u53ef\u4ee5\u8f15\u9b06\u5730\u5728 Spark \u4e2d\u67e5\u8a62\u548c\u8655\u7406 Hive \u6578\u64da\u3002\u9019\u7a2e\u96c6\u6210\u4e0d\u50c5\u63d0\u9ad8\u4e86\u6578\u64da\u8655\u7406\u7684\u6548\u7387\uff0c\u9084\u4f7f\u5f97\u6578\u64da\u5206\u6790\u8b8a\u5f97\u66f4\u52a0\u9748\u6d3b\u3002<\/p>\n<p>\u5982\u679c\u60a8\u6b63\u5728\u5c0b\u627e\u9ad8\u6548\u7684 <a href=\"https:\/\/server.hk\">VPS<\/a> \u89e3\u6c7a\u65b9\u6848\u4f86\u904b\u884c\u60a8\u7684 Spark \u548c Hive \u74b0\u5883\uff0cServer.HK \u63d0\u4f9b\u4e86\u591a\u7a2e\u9078\u64c7\uff0c\u9069\u5408\u5404\u7a2e\u9700\u6c42\u3002\u7121\u8ad6\u662f <a href=\"https:\/\/server.hk\">\u9999\u6e2fVPS<\/a> \u9084\u662f\u5176\u4ed6\u985e\u578b\u7684 <a href=\"https:\/\/server.hk\">\u4f3a\u670d\u5668<\/a>\uff0c\u6211\u5011\u90fd\u80fd\u70ba\u60a8\u63d0\u4f9b\u7a69\u5b9a\u7684\u652f\u6301\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4e86\u89e3\u5982\u4f55\u5728 Spark \u4e2d\u4f7f\u7528 Hive \u6578\u64da\u5eab\uff0c\u8f15\u9b06\u6574\u5408\u5927\u6578\u64da\u8655\u7406\u8207\u67e5\u8a62\uff0c\u63d0\u5347\u6578\u64da\u5206\u6790\u6548\u7387\u3002<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-179688","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/179688","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"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=179688"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/179688\/revisions"}],"predecessor-version":[{"id":179689,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/179688\/revisions\/179689"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=179688"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=179688"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=179688"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}