{"id":50143,"date":"2023-07-21T01:26:59","date_gmt":"2023-02-20T05:21:07","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/"},"modified":"2024-04-30T14:33:59","modified_gmt":"2024-04-30T06:33:59","slug":"%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/","title":{"rendered":"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c"},"content":{"rendered":"<h1>\u9996\u5148<\/h1>\n<p>\u5728\u6570\u636e\u5206\u6790\u4e2d\uff0c\u7ecf\u5e38\u6709\u4f7f\u7528Apache Spark + Cassandra\u7684\u7ec4\u5408\u6765\u5b9e\u73b0\u7684\u9009\u9879\u3002<\/p>\n<h1>Apache Spark\u662f\u4e00\u79cd\u5f00\u6e90\u7684\u5927\u6570\u636e\u5904\u7406\u6846\u67b6\u3002<\/h1>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d8f9d913a08637a6d9d90\/3-0.png\" alt=\"image.png\" \/><\/div>\n<blockquote><p>\u53ef\u4ee5\u8bbf\u95eeHDFS\u3001Alluxio\u3001Apache Cassandra\u3001Apache HBase\u3001Apache Hive\u7b49\u6570\u767e\u4e2a\u5176\u4ed6\u6570\u636e\u6e90\u4e2d\u7684\u6570\u636e\u3002<\/p><\/blockquote>\n<p>\u5f3a\u5927\u800c\u5206\u5e03\u5f0f\u7684\u6570\u636e\u96c6\uff08Resilient Distributed Dataset\uff0c\u7b80\u79f0RDD\uff09\u3001\u6570\u636e\u6846\u67b6\uff08DataFrame\uff09\u548c\u6570\u636e\u96c6\uff08DataSet\uff09\u7b49\u3002\u3002\u3002<\/p>\n<p>\u6765\u6e90\uff1ahttps:\/\/spark.apache.org\/<\/p>\n<p>\u51fa\u5904\uff1ahttps:\/\/spark.apache.org\/<\/p>\n<h1>Cassandra\u662f\u4ec0\u4e48<\/h1>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d8f9d913a08637a6d9d90\/8-0.png\" alt=\"image.png\" \/><\/div>\n<blockquote><p>\u9ad8\u6548\u5730\u7ba1\u7406\u6d77\u91cf\u6570\u636e\uff0c\u5feb\u901f\u5904\u7406\uff0c\u65e0\u9700\u62c5\u5fe7\u7761\u7720\u4e27\u5931\u3002<\/p><\/blockquote>\n<p>\u5f15\u7528\u6765\u6e90\uff1ahttp:\/\/cassandra.apache.org\/<\/p>\n<p>\u7279\u522b\u662f\u4ece\u4e00\u5f00\u59cb\u5c31\u8003\u8651\u4e86\u53ef\u6269\u5c55\u6027\uff0c\u56e0\u6b64\u53ef\u4ee5\u8f7b\u677e\u5730\u5efa\u7acb\u96c6\u7fa4\u3002<\/p>\n<h1>\u5c06CSV\u6587\u4ef6\u6570\u636e\u4fdd\u5b58\u5230Cassandra\u7684\u793a\u4f8b\u3002<\/h1>\n<p>\u6211\u5c06\u5c1d\u8bd5\u521b\u5efa\u4e00\u4e2a\u5c06CSV\u6587\u4ef6\u4fdd\u5b58\u5230Cassandra\u7684Spark\u793a\u4f8b\uff0c\u56e0\u4e3aSpark\u5177\u6709\u8bb8\u591a\u529f\u80fd\u3002<\/p>\n<h2>\u521b\u5efa\u4e00\u4e2a\u540d\u4e3a&#8221;users.csv&#8221;\u7684\u793a\u4f8b\u6587\u4ef6\u3002<\/h2>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d8f9d913a08637a6d9d90\/15-0.png\" alt=\"image.png\" \/><\/div>\n<h2>\u5728Gradle\u9879\u76ee\u4e2d\u5f15\u5165\u5e93<\/h2>\n<pre class=\"post-pre\"><code><span class=\"k\">dependencies<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"c1\">\/\/ https:\/\/mvnrepository.com\/artifact\/org.scala-lang\/scala-library<\/span>\r\n    <span class=\"n\">compile<\/span> <span class=\"nl\">group:<\/span> <span class=\"s1\">'org.scala-lang'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">name:<\/span> <span class=\"s1\">'scala-library'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">version:<\/span> <span class=\"s1\">'2.11.12'<\/span>\r\n\r\n    <span class=\"c1\">\/\/ https:\/\/mvnrepository.com\/artifact\/org.apache.spark\/spark-core<\/span>\r\n    <span class=\"n\">compile<\/span> <span class=\"nl\">group:<\/span> <span class=\"s1\">'org.apache.spark'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">name:<\/span> <span class=\"s1\">'spark-core_2.11'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">version:<\/span> <span class=\"s1\">'2.3.4'<\/span>\r\n\r\n    <span class=\"c1\">\/\/ https:\/\/mvnrepository.com\/artifact\/com.datastax.spark\/spark-cassandra-connector<\/span>\r\n    <span class=\"n\">compile<\/span> <span class=\"nl\">group:<\/span> <span class=\"s1\">'com.datastax.spark'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">name:<\/span> <span class=\"s1\">'spark-cassandra-connector_2.11'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">version:<\/span> <span class=\"s1\">'2.4.1'<\/span>\r\n\r\n    <span class=\"c1\">\/\/ https:\/\/mvnrepository.com\/artifact\/org.apache.spark\/spark-sql<\/span>\r\n    <span class=\"n\">compile<\/span> <span class=\"nl\">group:<\/span> <span class=\"s1\">'org.apache.spark'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">name:<\/span> <span class=\"s1\">'spark-sql_2.11'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">version:<\/span> <span class=\"s1\">'2.3.4'<\/span>\r\n\r\n    <span class=\"c1\">\/\/ https:\/\/mvnrepository.com\/artifact\/org.apache.spark\/spark-streaming<\/span>\r\n    <span class=\"n\">compile<\/span> <span class=\"nl\">group:<\/span> <span class=\"s1\">'org.apache.spark'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">name:<\/span> <span class=\"s1\">'spark-streaming_2.11'<\/span><span class=\"o\">,<\/span> <span class=\"nl\">version:<\/span> <span class=\"s1\">'2.3.4'<\/span>\r\n\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<h2>\u5c06CSV\u6587\u4ef6\u4fdd\u5b58\u5230Cassandra\uff0c\u7136\u540e\u4ece\u6570\u636e\u5e93\u4e2d\u8fdb\u884c\u68c0\u7d22\u3002<\/h2>\n<pre class=\"post-pre\"><code><span class=\"kn\">package<\/span> <span class=\"nn\">com.test.spark<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">com.datastax.driver.core.Session<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">com.datastax.spark.connector.cql.CassandraConnector<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">java.util.List<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.log4j.Logger<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.SparkConf<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaSparkContext<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.sql.Column<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.sql.Dataset<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.sql.Row<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.sql.SaveMode<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.sql.SparkSession<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"kd\">public<\/span> <span class=\"kd\">class<\/span> <span class=\"nc\">CsvReader<\/span> <span class=\"o\">{<\/span>\r\n\r\n    <span class=\"kd\">private<\/span> <span class=\"kd\">static<\/span> <span class=\"kd\">final<\/span> <span class=\"nc\">Logger<\/span> <span class=\"n\">logger<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">Logger<\/span><span class=\"o\">.<\/span><span class=\"na\">getLogger<\/span><span class=\"o\">(<\/span><span class=\"nc\">CsvReader<\/span><span class=\"o\">.<\/span><span class=\"na\">class<\/span><span class=\"o\">);<\/span>\r\n\r\n    <span class=\"kd\">public<\/span> <span class=\"kd\">static<\/span> <span class=\"kt\">void<\/span> <span class=\"nf\">main<\/span><span class=\"o\">(<\/span><span class=\"nc\">String<\/span><span class=\"o\">[]<\/span> <span class=\"n\">args<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n\r\n        <span class=\"c1\">\/\/ Spark\u8a2d\u5b9a<\/span>\r\n        <span class=\"nc\">SparkConf<\/span> <span class=\"n\">conf<\/span> <span class=\"o\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">SparkConf<\/span><span class=\"o\">();<\/span>\r\n        <span class=\"n\">conf<\/span><span class=\"o\">.<\/span><span class=\"na\">setAppName<\/span><span class=\"o\">(<\/span><span class=\"s\">\"CSVReader\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"n\">conf<\/span><span class=\"o\">.<\/span><span class=\"na\">setMaster<\/span><span class=\"o\">(<\/span><span class=\"s\">\"local[*]\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"n\">conf<\/span><span class=\"o\">.<\/span><span class=\"na\">set<\/span><span class=\"o\">(<\/span><span class=\"s\">\"spark.cassandra.connection.host\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"192.168.10.248\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"n\">conf<\/span><span class=\"o\">.<\/span><span class=\"na\">set<\/span><span class=\"o\">(<\/span><span class=\"s\">\"spark.cassandra.connection.port\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"9042\"<\/span><span class=\"o\">);<\/span>\r\n\r\n        <span class=\"c1\">\/\/ Cassandra\u306ekeyspace\u3068\u30c6\u30fc\u30d6\u30eb\u540d<\/span>\r\n        <span class=\"nc\">String<\/span> <span class=\"n\">keyspace<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"sample\"<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"nc\">String<\/span> <span class=\"n\">tableUser<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"user\"<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"nc\">String<\/span> <span class=\"n\">userCsv<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"C:\\\\data\\\\spark\\\\users.csv\"<\/span><span class=\"o\">;<\/span>\r\n\r\n        <span class=\"nc\">JavaSparkContext<\/span> <span class=\"n\">sc<\/span> <span class=\"o\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">JavaSparkContext<\/span><span class=\"o\">(<\/span><span class=\"n\">conf<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"k\">try<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"nc\">SparkSession<\/span> <span class=\"n\">sparkSession<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">SparkSession<\/span><span class=\"o\">.<\/span><span class=\"na\">builder<\/span><span class=\"o\">().<\/span><span class=\"na\">master<\/span><span class=\"o\">(<\/span><span class=\"s\">\"local\"<\/span><span class=\"o\">).<\/span><span class=\"na\">appName<\/span><span class=\"o\">(<\/span><span class=\"s\">\"CSVReader\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">config<\/span><span class=\"o\">(<\/span><span class=\"s\">\"spark.sql.warehouse.dir\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"file:\/\/\/\/C:\/data\/spark\"<\/span><span class=\"o\">).<\/span><span class=\"na\">getOrCreate<\/span><span class=\"o\">();<\/span>\r\n\r\n            <span class=\"c1\">\/\/ Cassandra\u306e\u30b3\u30cd\u30af\u30b7\u30e7\u30f3<\/span>\r\n            <span class=\"nc\">CassandraConnector<\/span> <span class=\"n\">connector<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CassandraConnector<\/span><span class=\"o\">.<\/span><span class=\"na\">apply<\/span><span class=\"o\">(<\/span><span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">getConf<\/span><span class=\"o\">());<\/span>\r\n\r\n            <span class=\"k\">try<\/span> <span class=\"o\">(<\/span><span class=\"nc\">Session<\/span> <span class=\"n\">session<\/span> <span class=\"o\">=<\/span> <span class=\"n\">connector<\/span><span class=\"o\">.<\/span><span class=\"na\">openSession<\/span><span class=\"o\">())<\/span> <span class=\"o\">{<\/span>\r\n                <span class=\"c1\">\/\/ keyspace\u3042\u308b\u5834\u5408\u306f\u524a\u9664\u3059\u308b<\/span>\r\n                <span class=\"n\">session<\/span><span class=\"o\">.<\/span><span class=\"na\">execute<\/span><span class=\"o\">(<\/span><span class=\"s\">\"DROP KEYSPACE IF EXISTS \"<\/span> <span class=\"o\">+<\/span> <span class=\"n\">keyspace<\/span><span class=\"o\">);<\/span>\r\n\r\n                <span class=\"c1\">\/\/ keyspace\u3092\u4f5c\u6210\u3059\u308b<\/span>\r\n                <span class=\"n\">session<\/span><span class=\"o\">.<\/span><span class=\"na\">execute<\/span><span class=\"o\">(<\/span><span class=\"s\">\"CREATE KEYSPACE \"<\/span> <span class=\"o\">+<\/span> <span class=\"n\">keyspace<\/span>\r\n                        <span class=\"o\">+<\/span> <span class=\"s\">\" WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1}\"<\/span><span class=\"o\">);<\/span>\r\n\r\n                <span class=\"c1\">\/\/ \u30c6\u30fc\u30d6\u30eb\u3092\u4f5c\u6210\u3059\u308b<\/span>\r\n                <span class=\"n\">session<\/span><span class=\"o\">.<\/span><span class=\"na\">execute<\/span><span class=\"o\">(<\/span><span class=\"s\">\"CREATE TABLE \"<\/span> <span class=\"o\">+<\/span> <span class=\"n\">keyspace<\/span> <span class=\"o\">+<\/span> <span class=\"s\">\".\"<\/span> <span class=\"o\">+<\/span> <span class=\"n\">tableUser<\/span>\r\n                        <span class=\"o\">+<\/span> <span class=\"s\">\"(user_id TEXT PRIMARY KEY, user_name TEXT, email_address TEXT, memo TEXT)\"<\/span><span class=\"o\">);<\/span>\r\n            <span class=\"o\">}<\/span>\r\n\r\n            <span class=\"c1\">\/\/ CSV\u304b\u3089\u30c7\u30fc\u30bf\u3092\u53d6\u5f97\u3059\u308b<\/span>\r\n            <span class=\"c1\">\/\/ \u30c6\u30fc\u30d6\u30eb\u5b9a\u7fa9\u306b\u5408\u308f\u305b\u308b\u305f\u3081\u3001\u30ab\u30e9\u30e0\u306eAS\u3082\u91cd\u8981<\/span>\r\n            <span class=\"nc\">Dataset<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">Row<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">csv<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sparkSession<\/span><span class=\"o\">.<\/span><span class=\"na\">read<\/span><span class=\"o\">().<\/span><span class=\"na\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"com.databricks.spark.csv\"<\/span><span class=\"o\">).<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"header\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"true\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"encoding\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"UTF-8\"<\/span><span class=\"o\">).<\/span><span class=\"na\">load<\/span><span class=\"o\">(<\/span><span class=\"n\">userCsv<\/span><span class=\"o\">).<\/span><span class=\"na\">select<\/span><span class=\"o\">(<\/span><span class=\"k\">new<\/span> <span class=\"nc\">Column<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\u30e6\u30fc\u30b6\u30fcID\"<\/span><span class=\"o\">).<\/span><span class=\"na\">as<\/span><span class=\"o\">(<\/span><span class=\"s\">\"user_id\"<\/span><span class=\"o\">),<\/span>\r\n                            <span class=\"k\">new<\/span> <span class=\"nf\">Column<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\u6c0f\u540d\"<\/span><span class=\"o\">).<\/span><span class=\"na\">as<\/span><span class=\"o\">(<\/span><span class=\"s\">\"user_name\"<\/span><span class=\"o\">),<\/span> \r\n                            <span class=\"k\">new<\/span> <span class=\"nf\">Column<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\u30e1\u30fc\u30eb\u30a2\u30c9\u30ec\u30b9\"<\/span><span class=\"o\">).<\/span><span class=\"na\">as<\/span><span class=\"o\">(<\/span><span class=\"s\">\"email_address\"<\/span><span class=\"o\">),<\/span>\r\n                            <span class=\"k\">new<\/span> <span class=\"nf\">Column<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\u5099\u8003\"<\/span><span class=\"o\">).<\/span><span class=\"na\">as<\/span><span class=\"o\">(<\/span><span class=\"s\">\"memo\"<\/span><span class=\"o\">));<\/span>\r\n\r\n            <span class=\"c1\">\/\/ Cassandra\u306b\u4fdd\u5b58<\/span>\r\n            <span class=\"n\">csv<\/span><span class=\"o\">.<\/span><span class=\"na\">write<\/span><span class=\"o\">().<\/span><span class=\"na\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"org.apache.spark.sql.cassandra\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"header\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"true\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"keyspace\"<\/span><span class=\"o\">,<\/span> <span class=\"n\">keyspace<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"table\"<\/span><span class=\"o\">,<\/span> <span class=\"n\">tableUser<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"column\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"user_id\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"column\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"user_name\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"column\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"email_address\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"column\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"memo\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">mode<\/span><span class=\"o\">(<\/span><span class=\"nc\">SaveMode<\/span><span class=\"o\">.<\/span><span class=\"na\">Append<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">save<\/span><span class=\"o\">();<\/span>\r\n\r\n            <span class=\"c1\">\/\/ Cassandra\u304b\u3089\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u51fa\u3059<\/span>\r\n            <span class=\"nc\">Dataset<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">Row<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">dataset<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sparkSession<\/span><span class=\"o\">.<\/span><span class=\"na\">read<\/span><span class=\"o\">().<\/span><span class=\"na\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"org.apache.spark.sql.cassandra\"<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"keyspace\"<\/span><span class=\"o\">,<\/span> <span class=\"n\">keyspace<\/span><span class=\"o\">)<\/span>\r\n                    <span class=\"o\">.<\/span><span class=\"na\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"table\"<\/span><span class=\"o\">,<\/span> <span class=\"n\">tableUser<\/span><span class=\"o\">).<\/span><span class=\"na\">load<\/span><span class=\"o\">();<\/span>\r\n\r\n            <span class=\"c1\">\/\/ \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304b\u3089\u914d\u5217\u3092\u53d6\u5f97\u3059\u308b<\/span>\r\n            <span class=\"nc\">List<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">Row<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">asList<\/span> <span class=\"o\">=<\/span> <span class=\"n\">dataset<\/span><span class=\"o\">.<\/span><span class=\"na\">collectAsList<\/span><span class=\"o\">();<\/span>\r\n            <span class=\"k\">for<\/span> <span class=\"o\">(<\/span><span class=\"nc\">Row<\/span> <span class=\"n\">r<\/span> <span class=\"o\">:<\/span> <span class=\"n\">asList<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n                <span class=\"n\">logger<\/span><span class=\"o\">.<\/span><span class=\"na\">info<\/span><span class=\"o\">(<\/span><span class=\"n\">r<\/span><span class=\"o\">);<\/span>\r\n            <span class=\"o\">}<\/span>\r\n        <span class=\"o\">}<\/span> <span class=\"k\">catch<\/span> <span class=\"o\">(<\/span><span class=\"nc\">Exception<\/span> <span class=\"n\">e<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">logger<\/span><span class=\"o\">.<\/span><span class=\"na\">error<\/span><span class=\"o\">(<\/span><span class=\"n\">e<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"o\">}<\/span> <span class=\"k\">finally<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">stop<\/span><span class=\"o\">();<\/span>\r\n            <span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">close<\/span><span class=\"o\">();<\/span>\r\n        <span class=\"o\">}<\/span>\r\n    <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n\r\n<\/code><\/pre>\n<h2>\u4f7f\u7528\u8005\u8bad\u7ec3\u6765\u5b66\u4e60\uff0c\u4ee5\u751f\u6210\u81ea\u7136\u8bed\u8a00\u6587\u672c\u548c\u4e0b\u4e00\u6b65\u52a8\u4f5c\u7684AI\u6a21\u578b\u3002<\/h2>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d8f9d913a08637a6d9d90\/21-0.png\" alt=\"image.png\" \/><\/div>\n<h2>\u901a\u8fc7JAVA\u68c0\u7d22\u5230\u7684\u7528\u6237\u6570\u636e<\/h2>\n<pre class=\"post-pre\"><code>19\/10\/11 23:18:27 INFO CsvReader: [A000002,yamada.bb@test.com,\u5165\u793e\uff11\uff10\u5e74\u76ee,\u5c71\u7530\u3000\u4e09\u90ce]\r\n19\/10\/11 23:18:27 INFO CsvReader: [A000004,tanaka.bb@test.com,\u5165\u793e\uff13\u5e74\u76ee,\u7530\u4e2d\u3000\u6b21\u90ce]\r\n19\/10\/11 23:18:27 INFO CsvReader: [A000003,tanaka.aa@test.com,\u5165\u793e\uff15\u5e74\u76ee,\u7530\u4e2d\u3000\u4e00\u90ce]\r\n19\/10\/11 23:18:27 INFO CsvReader: [A000001,yamada.aa@test.com,\u5165\u793e\uff11\u5e74\u76ee,\u5c71\u7530\u3000\u592a\u90ce]\r\n<\/code><\/pre>\n<p>\u57fa\u672c\u64cd\u4f5c\u548c\u5176\u4ed6\u8be6\u7ec6\u8d44\u6599\u53ef\u5728\u6307\u5357\u4e2d\u627e\u5230\u3002<br \/>\nSpark\u7f16\u7a0b\u6307\u5357\uff1ahttps:\/\/spark.apache.org\/docs\/2.2.0\/rdd-programming-guide.html<\/p>\n<p>\u4ee5\u4e0a<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u9996\u5148 \u5728\u6570\u636e\u5206\u6790\u4e2d\uff0c\u7ecf\u5e38\u6709\u4f7f\u7528Apache Spark + Cassandra\u7684\u7ec4\u5408\u6765\u5b9e\u73b0\u7684\u9009\u9879\u3002 Apach [&hellip;]<\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-50143","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528spark\u548ccassandra\u8fdb\u884c\u6570\u636e\u534f\u540c\u3002\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c\" \/>\n<meta property=\"og:description\" content=\"\u9996\u5148 \u5728\u6570\u636e\u5206\u6790\u4e2d\uff0c\u7ecf\u5e38\u6709\u4f7f\u7528Apache Spark + Cassandra\u7684\u7ec4\u5408\u6765\u5b9e\u73b0\u7684\u9009\u9879\u3002 Apach [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528spark\u548ccassandra\u8fdb\u884c\u6570\u636e\u534f\u540c\u3002\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-02-20T05:21:07+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-30T06:33:59+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d8f9d913a08637a6d9d90\/3-0.png\" \/>\n<meta name=\"author\" content=\"\u6e05, \u626c\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u6e05, \u626c\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/\",\"name\":\"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-02-20T05:21:07+00:00\",\"dateModified\":\"2024-04-30T06:33:59+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461\",\"name\":\"\u6e05, \u626c\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"caption\":\"\u6e05, \u626c\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528spark\u548ccassandra\u8fdb\u884c\u6570\u636e\u534f\u540c\u3002\/","og_locale":"zh_CN","og_type":"article","og_title":"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c","og_description":"\u9996\u5148 \u5728\u6570\u636e\u5206\u6790\u4e2d\uff0c\u7ecf\u5e38\u6709\u4f7f\u7528Apache Spark + Cassandra\u7684\u7ec4\u5408\u6765\u5b9e\u73b0\u7684\u9009\u9879\u3002 Apach [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528spark\u548ccassandra\u8fdb\u884c\u6570\u636e\u534f\u540c\u3002\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-02-20T05:21:07+00:00","article_modified_time":"2024-04-30T06:33:59+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d8f9d913a08637a6d9d90\/3-0.png"}],"author":"\u6e05, \u626c","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6e05, \u626c","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"3 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/","name":"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-02-20T05:21:07+00:00","dateModified":"2024-04-30T06:33:59+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u4f7f\u7528Spark\u548cCassandra\u8fdb\u884c\u6570\u636e\u534f\u540c"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461","name":"\u6e05, \u626c","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","caption":"\u6e05, \u626c"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8spark%e5%92%8ccassandra%e8%bf%9b%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8d%8f%e5%90%8c%e3%80%82\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50143","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=50143"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50143\/revisions"}],"predecessor-version":[{"id":92483,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50143\/revisions\/92483"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=50143"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=50143"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=50143"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}