{"id":50462,"date":"2023-01-30T10:15:30","date_gmt":"2023-11-13T14:02:30","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/"},"modified":"2024-04-29T12:13:47","modified_gmt":"2024-04-29T04:13:47","slug":"%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/","title":{"rendered":"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730"},"content":{"rendered":"<p>\u5728Databricks\u4e0a\u5411\u4efb\u610f\u6570\u636e\u6e90\u5199\u5165\u6570\u636e\u7684\u529f\u80fd<\/p>\n<div>\u9019\u672c\u66f8\u662f\u6284\u8b6f\u7684\uff0c\u4e26\u4e0d\u80fd\u4fdd\u8b49\u5167\u5bb9\u7684\u6e96\u78ba\u6027\u3002\u8acb\u53c3\u8003\u539f\u6587\u4ee5\u7372\u5f97\u6b63\u78ba\u7684\u5167\u5bb9\u3002<\/div>\n<p>\u5bf9\u4e8e\u6ca1\u6709\u73b0\u6709\u6d41\u5f0f\u5199\u5165\u76ee\u6807\u7684\u6570\u636e\u6e90\uff0c\u7ed3\u6784\u5316\u6d41API\u63d0\u4f9b\u4e86\u4e24\u79cd\u65b9\u5f0f\u6765\u5c06\u6d41\u5f0f\u67e5\u8be2\u8f93\u51fa\u5199\u5165\uff0c\u5373`foreachBatch()`\u548c`foreach()`\u3002<\/p>\n<h1>\u901a\u8fc7foreachBatch()\u91cd\u65b0\u4f7f\u7528\u73b0\u6709\u7684\u6279\u5904\u7406\u6570\u636e\u6e90<\/h1>\n<p>\u4f7f\u7528streamingDF.writeStream.foreachBatch(&#8230;)\uff0c\u53ef\u4ee5\u6307\u5b9a\u4e00\u4e2a\u51fd\u6570\u6765\u5904\u7406\u6bcf\u4e2a\u6d41\u5f0f\u67e5\u8be2\u7684\u6bcf\u4e2a\u5fae\u6279\u6b21\u7684\u8f93\u51fa\u6570\u636e\u3002\u8be5\u51fd\u6570\u63a5\u6536\u4e24\u4e2a\u53c2\u6570\uff1a\u4e00\u4e2a\u7528\u4e8e\u4fdd\u5b58\u5fae\u6279\u6b21\u8f93\u51fa\u6570\u636e\u7684DataFrame\u6216Dataset\uff0c\u4ee5\u53ca\u5fae\u6279\u6b21\u7684\u552f\u4e00ID\u3002\u4f7f\u7528foreachBatch\u53ef\u4ee5\u5b9e\u73b0\u4ee5\u4e0b\u529f\u80fd\uff1a<\/p>\n<h2>\u91cd\u590d\u4f7f\u7528\u73b0\u6709\u7684\u6279\u91cf\u6570\u636e\u6e90<\/h2>\n<p>\u5728\u8bb8\u591a\u5b58\u50a8\u7cfb\u7edf\u4e2d\uff0c\u53ef\u80fd\u65e0\u6cd5\u4f7f\u7528\u6d41\u5f0f\u4f20\u8f93\u76ee\u6807\uff0c\u4f46\u5982\u679c\u5df2\u7ecf\u5b58\u5728\u5bf9\u6279\u5904\u7406\u67e5\u8be2\u7684\u6570\u636e\u5199\u5165\u5668\uff0c\u5219\u53ef\u4ee5\u4f7f\u7528foreachBatch\uff08\uff09\u6765\u4f7f\u7528\u6279\u5904\u7406\u6570\u636e\u5199\u5165\u5668\u5bf9\u6bcf\u4e2a\u5fae\u6279\u6b21\u7684\u8f93\u51fa\u8fdb\u884c\u5904\u7406\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u793a\u4f8b\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Cassandra Scala example<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">Azure Synapse Analytics Python example<\/ul>\n<p>\u8fd8\u53ef\u4ee5\u4f7f\u7528foreachBatch()\u6765\u4f7f\u7528\u5176\u4ed6\u8bb8\u591a\u6279\u5904\u7406\u6570\u636e\u6e90\u3002<\/p>\n<h2>\u5bf9\u591a\u4e2a\u5730\u65b9\u7684\u5199\u4f5c<\/h2>\n<p>\u5982\u679c\u8981\u5c06\u6d41\u67e5\u8be2\u7684\u8f93\u51fa\u5199\u5165\u591a\u4e2a\u4f4d\u7f6e\uff0c\u53ef\u4ee5\u7b80\u5355\u5730\u591a\u6b21\u5199\u5165\u6570\u636e\u6846\u67b6\/\u6570\u636e\u96c6\u7684\u8f93\u51fa\u3002\u7136\u800c\uff0c\u6bcf\u6b21\u5199\u5165\u5c1d\u8bd5\u90fd\u53ef\u80fd\u9700\u8981\u91cd\u65b0\u8ba1\u7b97\u8f93\u51fa\u6570\u636e\uff0c\u8fd9\u53ef\u80fd\u5305\u62ec\u91cd\u65b0\u52a0\u8f7d\u8f93\u5165\u6570\u636e\u3002\u4e3a\u4e86\u907f\u514d\u91cd\u65b0\u8ba1\u7b97\uff0c\u53ef\u4ee5\u5c06\u8f93\u51fa\u7684\u6570\u636e\u6846\u67b6\/\u6570\u636e\u96c6\u8fdb\u884c\u7f13\u5b58\uff0c\u5e76\u5c06\u5176\u5199\u5165\u591a\u4e2a\u4f4d\u7f6e\uff0c\u7136\u540e\u89e3\u9664\u7f13\u5b58\u3002\u4ee5\u4e0b\u662f\u6982\u8ff0\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">streamingDF<\/span><span class=\"o\">.<\/span><span class=\"py\">writeStream<\/span><span class=\"o\">.<\/span><span class=\"py\">foreachBatch<\/span> <span class=\"o\">{<\/span> <span class=\"o\">(<\/span><span class=\"n\">batchDF<\/span><span class=\"k\">:<\/span> <span class=\"kt\">DataFrame<\/span><span class=\"o\">,<\/span> <span class=\"n\">batchId<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Long<\/span><span class=\"o\">)<\/span> <span class=\"k\">=&gt;<\/span>\r\n  <span class=\"nv\">batchDF<\/span><span class=\"o\">.<\/span><span class=\"py\">persist<\/span><span class=\"o\">()<\/span>\r\n  <span class=\"nv\">batchDF<\/span><span class=\"o\">.<\/span><span class=\"py\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">format<\/span><span class=\"o\">(...).<\/span><span class=\"py\">save<\/span><span class=\"o\">(...)<\/span>  <span class=\"c1\">\/\/ location 1<\/span>\r\n  <span class=\"nv\">batchDF<\/span><span class=\"o\">.<\/span><span class=\"py\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">format<\/span><span class=\"o\">(...).<\/span><span class=\"py\">save<\/span><span class=\"o\">(...)<\/span>  <span class=\"c1\">\/\/ location 2<\/span>\r\n  <span class=\"nv\">batchDF<\/span><span class=\"o\">.<\/span><span class=\"py\">unpersist<\/span><span class=\"o\">()<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<div>\u6ce8\u610f\uff1a\u5728\u6267\u884c\u591a\u4e2aSpark\u4f5c\u4e1a\u7684batchDF\u65f6\uff0c\u8f93\u5165\u6570\u636e\u901f\u7387\u53ef\u80fd\u4ee5\u5b9e\u9645\u901f\u7387\u7684\u500d\u6570\u6765\u62a5\u544a\uff0c\u53ef\u4ee5\u5728StreamingQueryProgress\u6216\u7b14\u8bb0\u672c\u7684\u901f\u7387\u56fe\u4e2d\u67e5\u770b\u3002\u8fd9\u662f\u56e0\u4e3a\u6bcf\u4e2a\u6279\u6b21\u53ef\u80fd\u4f1a\u591a\u6b21\u52a0\u8f7d\u8f93\u5165\u6570\u636e\u5230\u591a\u4e2aSpark\u4f5c\u4e1a\u4e2d\u3002<\/div>\n<h2>\u5e94\u7528\u9644\u52a0\u7684\u6570\u636e\u6846\u64cd\u4f5c<\/h2>\n<p>\u7531\u4e8e\u5728Spark\u4e2d\uff0c\u5f88\u591a\u60c5\u51b5\u4e0b\u4e0d\u652f\u6301\u589e\u91cf\u8ba1\u5212\u7684\u751f\u6210\uff0c\u6240\u4ee5\u5728\u6d41\u6570\u636e\u6846\u4e2d\uff0c\u4e0d\u652f\u6301\u5f88\u591a\u6570\u636e\u6846\u548c\u6570\u636e\u96c6\u64cd\u4f5c\u3002\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528foreachBatch()\uff0c\u5bf9\u6bcf\u4e2a\u5fae\u6279\u5904\u7406\u7684\u8f93\u51fa\u5e94\u7528\u8fd9\u4e9b\u64cd\u4f5c\u4e2d\u7684\u4e00\u4e9b\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528foreachBatch()\u548cMERGE INTO\u64cd\u4f5c\u5c06\u6d41\u805a\u5408\u5904\u7406\u7684\u8f93\u51fa\u4ee5\u66f4\u65b0\u6a21\u5f0f\u5199\u5165Delta\u8868\u4e2d\u3002\u8be6\u89c1MERGE INTO\u7684\u8be6\u7ec6\u4fe1\u606f\u3002<\/p>\n<div>\n<p>\u91cd\u8981\uff01<\/p>\n<p>foreachBatch()\u4ec5\u63d0\u4f9b\u81f3\u5c11\u4e00\u6b21\u5199\u5165\u4fdd\u8bc1\u3002\u800c\u4e3a\u4e86\u8fdb\u884c\u8f93\u51fa\u53bb\u91cd\u5e76\u786e\u4fdd\u4e00\u6b21\u6027\u5904\u7406\u7684\u4fdd\u8bc1\uff0c\u53ef\u4ee5\u5c06batchId\u4f20\u9012\u7ed9\u51fd\u6570\u3002\u5728\u4efb\u4e00\u60c5\u51b5\u4e0b\uff0c\u60a8\u90fd\u9700\u8981\u81ea\u884c\u5bf9\u7aef\u5230\u7aef\u8bed\u4e49\u8fdb\u884c\u63a8\u7406\u3002<\/p>\n<p>\u7531\u4e8eforeachBatch()\u57fa\u672c\u4e0a\u4f9d\u8d56\u4e8e\u6d41\u5f0f\u67e5\u8be2\u7684\u5fae\u6279\u5904\u7406\u6267\u884c\uff0c\u56e0\u6b64\u65e0\u6cd5\u5728\u8fde\u7eed\u5904\u7406\u6a21\u5f0f\u4e0b\u5de5\u4f5c\u3002\u5f53\u60a8\u5728\u8fde\u7eed\u6a21\u5f0f\u4e0b\u5199\u5165\u6570\u636e\u65f6\uff0c\u8bf7\u6539\u7528foreach()\u3002<\/p>\n<\/div>\n<h1>\u4f7f\u7528foreach()\u5411\u4efb\u610f\u4f4d\u7f6e\u8fdb\u884c\u5199\u5165<\/h1>\n<p>\u5982\u679c\u65e0\u6cd5\u4f7f\u7528foreachBatch()\uff08\u4f8b\u5982\u4f7f\u7528Databricks Runtime 4.2\u6216\u66f4\u4f4e\u7248\u672c\uff0c\u6216\u8005\u6ca1\u6709\u652f\u6301\u7684\u6279\u91cf\u6570\u636e\u5199\u5165\u5668\u7b49\uff09\uff0c\u53ef\u4ee5\u4f7f\u7528foreach()\u6765\u8868\u793a\u81ea\u5b9a\u4e49\u5199\u5165\u903b\u8f91\u3002\u7279\u522b\u5730\uff0c\u53ef\u4ee5\u5c06\u6570\u636e\u5199\u5165\u903b\u8f91\u5206\u4e3a\u4e09\u4e2a\u65b9\u6cd5open()\u3001process()\u548cclose()\u6765\u8868\u793a\u3002<\/p>\n<p>\u8bf7\u53c2\u8003\u4ee5\u4e0b\u4f8b\u5b50\uff1a\u4f7f\u7528Scala\u548cPython\u4e2d\u7684foreach()\u65b9\u6cd5\u5411Amazon DynamoDB\u5199\u5165\u6570\u636e\u3002<\/p>\n<h2>\u4f7f\u7528Scala\u6216Java<\/h2>\n<p>\u5728Scala\u6216Java\u4e2d\uff0c\u6269\u5c55ForeachWriter\u7c7b\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">datasetOfString<\/span><span class=\"o\">.<\/span><span class=\"py\">writeStream<\/span><span class=\"o\">.<\/span><span class=\"py\">foreach<\/span><span class=\"o\">(<\/span>\r\n  <span class=\"k\">new<\/span> <span class=\"nc\">ForeachWriter<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"o\">{<\/span>\r\n\r\n    <span class=\"k\">def<\/span> <span class=\"nf\">open<\/span><span class=\"o\">(<\/span><span class=\"n\">partitionId<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Long<\/span><span class=\"o\">,<\/span> <span class=\"n\">version<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Long<\/span><span class=\"o\">)<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Boolean<\/span> <span class=\"o\">=<\/span> <span class=\"o\">{<\/span>\r\n      <span class=\"c1\">\/\/ Open connection<\/span>\r\n    <span class=\"o\">}<\/span>\r\n\r\n    <span class=\"k\">def<\/span> <span class=\"nf\">process<\/span><span class=\"o\">(<\/span><span class=\"n\">record<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span><span class=\"o\">)<\/span> <span class=\"k\">=<\/span> <span class=\"o\">{<\/span>\r\n      <span class=\"c1\">\/\/ Write string to connection<\/span>\r\n    <span class=\"o\">}<\/span>\r\n\r\n    <span class=\"k\">def<\/span> <span class=\"nf\">close<\/span><span class=\"o\">(<\/span><span class=\"n\">errorOrNull<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Throwable<\/span><span class=\"o\">)<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Unit<\/span> <span class=\"o\">=<\/span> <span class=\"o\">{<\/span>\r\n      <span class=\"c1\">\/\/ Close the connection<\/span>\r\n    <span class=\"o\">}<\/span>\r\n  <span class=\"o\">}<\/span>\r\n<span class=\"o\">).<\/span><span class=\"py\">start<\/span><span class=\"o\">()<\/span>\r\n<\/code><\/pre>\n<h2>\u4f7f\u7528Python<\/h2>\n<p>\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u901a\u8fc7\u4e24\u79cd\u65b9\u5f0f\u8c03\u7528foreach\u3002\u4e00\u79cd\u662f\u4ece\u51fd\u6570\u5185\u90e8\u8c03\u7528\uff0c\u53e6\u4e00\u79cd\u662f\u4ece\u5bf9\u8c61\u5185\u90e8\u8c03\u7528\u3002\u51fd\u6570\u63d0\u4f9b\u4e86\u4e00\u79cd\u7b80\u5355\u7684\u65b9\u6cd5\u6765\u8868\u8fbe\u5904\u7406\u903b\u8f91\uff0c\u4f46\u662f\u5f53\u9700\u8981\u91cd\u65b0\u5904\u7406\u8f93\u5165\u6570\u636e\u4ee5\u6d88\u9664\u751f\u6210\u7684\u6570\u636e\u7684\u91cd\u590d\u65f6\uff0c\u51fd\u6570\u65e0\u6cd5\u5b9e\u73b0\u8fd9\u4e00\u70b9\u3002\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u5fc5\u987b\u5728\u5bf9\u8c61\u5185\u90e8\u6307\u5b9a\u5904\u7406\u903b\u8f91\u3002<\/p>\n<p>\u884c\u3068\u3057\u3066\u5165\u529b\u3092\u53d7\u3051\u53d6\u308b\u95a2\u6570<\/p>\n<p>Python<br \/>\ndef processRow(row):<br \/>\n\/\/ Write row to storage<\/p>\n<p>query = streamingDF.writeStream.foreach(processRow).start()<\/p>\n<p>process\u30e1\u30bd\u30c3\u30c9\u3068\u30aa\u30d7\u30b7\u30e7\u30f3\u3067open\u3068close\u30e1\u30bd\u30c3\u30c9\u3092\u6301\u3064\u30aa\u30d6\u30b8\u30a7\u30af\u30c8<\/p>\n<p>Python<br \/>\nclass ForeachWriter:<br \/>\ndef open(self, partition_id, epoch_id):<br \/>\n\/\/ Open connection. This method is optional in Python.<\/p>\n<p>def process(self, row):<br \/>\n\/\/ Write row to connection. This method is not optional in Python.<\/p>\n<p>def close(self, error):<br \/>\n\/\/ Close the connection. This method is optional in Python.<\/p>\n<p>query = streamingDF.writeStream.foreach(ForeachWriter()).start()<\/p>\n<h2>\u6267\u884c\u8bed\u4e49<\/h2>\n<p>\u5f53\u6d41\u67e5\u8be2\u542f\u52a8\u65f6\uff0cSpark\u4f1a\u4ee5\u4ee5\u4e0b\u65b9\u5f0f\u8c03\u7528\u51fd\u6570\u6216\u5bf9\u8c61\u7684\u65b9\u6cd5\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u3053\u306e\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u306e\u5358\u4e00\u306e\u30b3\u30d4\u30fc\u304c\u3001\u30af\u30a8\u30ea\u30fc\u306e\u5358\u4e00\u306e\u30bf\u30b9\u30af\u3067\u751f\u6210\u3055\u308c\u308b\u3059\u3079\u3066\u306e\u30c7\u30fc\u30bf\u306b\u8cac\u4efb\u3092\u6301\u3061\u307e\u3059\u3002\u8a00\u3044\u63db\u3048\u308b\u3068\u3001\u5206\u6563\u51e6\u7406\u3067\u751f\u6210\u3055\u308c\u305f\u30c7\u30fc\u30bf\u306e\u4e00\u3064\u306e\u30d1\u30fc\u30c6\u30a3\u30b7\u30e7\u30f3\u306e\u51e6\u7406\u306b\u4e00\u3064\u306e\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u304c\u8cac\u4efb\u3092\u6301\u3061\u307e\u3059\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u305d\u308c\u305e\u308c\u306e\u30bf\u30b9\u30af\u306f\u3001\u63d0\u4f9b\u3055\u308c\u305f\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u306e\u6700\u65b0\u306e\u30b7\u30ea\u30a2\u30e9\u30a4\u30ba\u3055\u308c\u305f\u3001\u3042\u308b\u3044\u306f\u3001\u30c7\u30b7\u30ea\u30a2\u30e9\u30a4\u30ba\u3055\u308c\u305f\u30b3\u30d4\u30fc\u3092\u53d6\u5f97\u3059\u308b\u306e\u3067\u3001\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u306f\u30b7\u30ea\u30a2\u30e9\u30a4\u30ba\u53ef\u80fd\u3067\u306a\u304f\u3066\u306f\u306a\u308a\u307e\u305b\u3093\u3002\u3053\u306e\u305f\u3081\u3001\u30c7\u30fc\u30bf\u66f8\u304d\u8fbc\u307f\u306b\u304a\u3051\u308b\u3044\u304b\u306a\u308b\u521d\u671f\u5316\u51e6\u7406\u306f\u3001\u4ed6\u30bf\u30b9\u30af\u304c\u30c7\u30fc\u30bf\u751f\u6210\u3092\u3067\u304d\u308b\u3053\u3068\u3092\u610f\u5473\u3059\u308bopen()\u30e1\u30bd\u30c3\u30c9\u306e\u547c\u3073\u51fa\u3057\u306e\u5f8c\u306b\u884c\u3046\u3053\u3068\u3092\u5f37\u304f\u304a\u52e7\u3081\u3057\u307e\u3059\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30e1\u30bd\u30c3\u30c9\u306e\u30e9\u30a4\u30d5\u30b5\u30a4\u30af\u30eb\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>partition_id\u3092\u6301\u3064\u305d\u308c\u305e\u308c\u306e\u30d1\u30fc\u30c6\u30a3\u30b7\u30e7\u30f3\u306b\u5bfe\u3057\u3066:<\/p>\n<p>epoch_id\u3092\u6301\u3064\u305d\u308c\u305e\u308c\u306e\u30b9\u30c8\u30ea\u30fc\u30df\u30f3\u30b0\u30c7\u30fc\u30bf\u306e\u30d0\u30c3\u30c1\/\u30a8\u30dd\u30c3\u30af\u306b\u5bfe\u3057\u3066:<\/p>\n<p>open(partitionId, epochId)\u304c\u30b3\u30fc\u30eb\u3055\u308c\u307e\u3059\u3002<\/p>\n<p>open(&#8230;)\u304ctrue\u3092\u8fd4\u3059\u3068\u3001\u30d1\u30fc\u30c6\u30a3\u30b7\u30e7\u30f3\u3068\u30d0\u30c3\u30c1\/\u30a8\u30dd\u30c3\u30af\u306e\u305d\u308c\u305e\u308c\u306e\u884c\u306b\u5bfe\u3057\u3066process(row)\u304c\u30b3\u30fc\u30eb\u3055\u308c\u307e\u3059\u3002<br \/>\n\u884c\u3092\u51e6\u7406\u3057\u3066\u3044\u308b\u9593\u306b\u30a8\u30e9\u30fc\u304c\u767a\u751f\u3059\u308b\u3068close(error)\u30e1\u30bd\u30c3\u30c9\u304c\u30b3\u30fc\u30eb\u3055\u308c\u307e\u3059<\/p>\n<p>open()\u30e1\u30bd\u30c3\u30c9\u304c\u5b58\u5728\u3057\u3001(\u623b\u308a\u5024\u306b\u95a2\u4fc2\u306a\u304f)\u623b\u308a\u5024\u304c\u8fd4\u5374\u3055\u308c\u308b\u3068\u3001JVM\u3084Python\u30d7\u30ed\u30bb\u30b9\u304c\u9014\u4e2d\u3067\u30af\u30e9\u30c3\u30b7\u30e5\u3057\u306a\u3044\u9650\u308a\u3001(\u5b58\u5728\u3059\u308b\u5834\u5408\u306b\u306f)close()\u30e1\u30bd\u30c3\u30c9\u304c\u30b3\u30fc\u30eb\u3055\u308c\u307e\u3059\u3002<\/p>\n<div>\u6ce8\u610f\uff1a\u5728\u5904\u7406\u8f93\u5165\u6570\u636e\u53d1\u751f\u6545\u969c\uff0c\u5e76\u9700\u8981\u8fdb\u884c\u91cd\u590d\u6392\u9664\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528open()\u65b9\u6cd5\u7684partitionId\u548cepochId\u3002\u8fd9\u53d6\u51b3\u4e8e\u67e5\u8be2\u7684\u6267\u884c\u6a21\u5f0f\u3002\u5982\u679c\u5728\u5fae\u6279\u5904\u7406\u6a21\u5f0f\u4e0b\u6267\u884c\u6d41\u67e5\u8be2\uff0c\u5219\u4fdd\u8bc1\u6bcf\u4e2a\u5177\u6709\u552f\u4e00\u5143\u7ec4\uff08partition_id\uff0cepoch_id\uff09\u8868\u793a\u7684\u5206\u533a\u5177\u6709\u76f8\u540c\u7684\u6570\u636e\u3002\u56e0\u6b64\uff0c\uff08partition_id\uff0cepoch_id\uff09\u53ef\u4ee5\u7528\u4e8e\u91cd\u590d\u6392\u9664\u3001\u4e8b\u52a1\u6027\u5730\u63d0\u4ea4\u6570\u636e\u6216\u5b9e\u73b0exactly-once\u4fdd\u8bc1\u3002\u4f46\u662f\uff0c\u5982\u679c\u6d41\u67e5\u8be2\u5728\u8fde\u7eed\u6a21\u5f0f\u4e0b\u6267\u884c\uff0c\u5219\u65e0\u6cd5\u63d0\u4f9b\u4fdd\u8bc1\uff0c\u56e0\u6b64\u4e0d\u5e94\u8be5\u5c06\u5176\u7528\u4e8e\u91cd\u590d\u6392\u9664\u3002<\/div>\n<h3>Databricks \u514d\u8d39\u8bd5\u7528<\/h3>\n<p>Databricks \u514d\u8d39\u8bd5\u7528<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5728Databricks\u4e0a\u5411\u4efb\u610f\u6570\u636e\u6e90\u5199\u5165\u6570\u636e\u7684\u529f\u80fd \u9019\u672c\u66f8\u662f\u6284\u8b6f\u7684\uff0c\u4e26\u4e0d\u80fd\u4fdd\u8b49\u5167\u5bb9\u7684\u6e96\u78ba\u6027\u3002\u8acb\u53c3\u8003\u539f\u6587\u4ee5\u7372\u5f97\u6b63 [&hellip;]<\/p>\n","protected":false},"author":8,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-50462","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>\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730 - 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\/\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730\u3002\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730\" \/>\n<meta property=\"og:description\" content=\"\u5728Databricks\u4e0a\u5411\u4efb\u610f\u6570\u636e\u6e90\u5199\u5165\u6570\u636e\u7684\u529f\u80fd \u9019\u672c\u66f8\u662f\u6284\u8b6f\u7684\uff0c\u4e26\u4e0d\u80fd\u4fdd\u8b49\u5167\u5bb9\u7684\u6e96\u78ba\u6027\u3002\u8acb\u53c3\u8003\u539f\u6587\u4ee5\u7372\u5f97\u6b63 [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730\u3002\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-13T14:02:30+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-29T04:13:47+00:00\" \/>\n<meta name=\"author\" content=\"\u96c5, \u609f\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u96c5, \u609f\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 \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\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/\",\"name\":\"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730 - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-11-13T14:02:30+00:00\",\"dateModified\":\"2024-04-29T04:13:47+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/f044a4b7fa4ee2701702942002419ca6\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730\"}]},{\"@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\/f044a4b7fa4ee2701702942002419ca6\",\"name\":\"\u96c5, \u609f\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g\",\"caption\":\"\u96c5, \u609f\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/yawu\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730 - 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\/\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730\u3002\/","og_locale":"zh_CN","og_type":"article","og_title":"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730","og_description":"\u5728Databricks\u4e0a\u5411\u4efb\u610f\u6570\u636e\u6e90\u5199\u5165\u6570\u636e\u7684\u529f\u80fd \u9019\u672c\u66f8\u662f\u6284\u8b6f\u7684\uff0c\u4e26\u4e0d\u80fd\u4fdd\u8b49\u5167\u5bb9\u7684\u6e96\u78ba\u6027\u3002\u8acb\u53c3\u8003\u539f\u6587\u4ee5\u7372\u5f97\u6b63 [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730\u3002\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-11-13T14:02:30+00:00","article_modified_time":"2024-04-29T04:13:47+00:00","author":"\u96c5, \u609f","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u96c5, \u609f","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"1 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/","name":"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730 - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-11-13T14:02:30+00:00","dateModified":"2024-04-29T04:13:47+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/f044a4b7fa4ee2701702942002419ca6"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%e3%80%82\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u5c06\u4efb\u610f\u7684\u6570\u636e\u5199\u5165Spark\u7ed3\u6784\u5316\u6d41\u5230\u4efb\u4f55\u6570\u636e\u76ee\u7684\u5730"}]},{"@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\/f044a4b7fa4ee2701702942002419ca6","name":"\u96c5, \u609f","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g","caption":"\u96c5, \u609f"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/yawu\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%86%e4%bb%bb%e6%84%8f%e7%9a%84%e6%95%b0%e6%8d%ae%e5%86%99%e5%85%a5spark%e7%bb%93%e6%9e%84%e5%8c%96%e6%b5%81%e5%88%b0%e4%bb%bb%e4%bd%95%e6%95%b0%e6%8d%ae%e7%9b%ae%e7%9a%84%e5%9c%b0%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\/50462","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\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=50462"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50462\/revisions"}],"predecessor-version":[{"id":85210,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50462\/revisions\/85210"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=50462"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=50462"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=50462"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}