embulk-output-redshift 0.6.1 → 0.6.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4befc609ebdd8278a0dc58d63c464d710bde3ed7
-  data.tar.gz: d65e65a04861aba8e25b33d3ccb5ae6f0a406bc9
+  metadata.gz: 6b2e8b89ca25df20d98cf01a706f0b9667d291c7
+  data.tar.gz: 58536c435cfce02d53f966305515c703c782797f
 SHA512:
-  metadata.gz: 5675fe7972621547f61caa17f303461c98c5bee60f5354f06ae42ae0e1546a22ccf1ae339b08436fc1b49ac9022228f8192ccdcfbbe956d50ff74a7cbfc45b56
-  data.tar.gz: 63b40e72eed84caa98c178fefa3e603ef7ee2661af0d65126ec9ce38181a428a7072ce6fe6fe5995c7f3643ca539b7aba7138dd81b06497b3ffa5230b5cb0bcb
+  metadata.gz: 23d34857b174f1782c2c487d4c631a22d0aa5e0c6ff809e29302ccd8c1c0d51cf30012428453fdc43a47638b2681ba338ffb3f0c8786583db71e039dedffb84e
+  data.tar.gz: 0cd7a1c77dae1c65381197da11468c63a35db75972a81237e35fc30f1f894b36b486c75b2680bb4e63a9d710f07923e96cb022ca5e54a2b8479230ea82e6118f

data/README.md

@@ -5,14 +5,15 @@ Redshift output plugins for Embulk loads records to Redshift.
 ## Overview
 
 * **Plugin type**: output
-* **Load all or nothing**: depnds on the mode. see below.
-* **Resume supported**: depnds on the mode. see below.
+* **Load all or nothing**: depends on the mode. see below.
+* **Resume supported**: depends on the mode. see below.
 
 ## Configuration
 
 - **host**: database host name (string, required)
 - **port**: database port number (integer, default: 5439)
 - **user**: database login user name (string, required)
+- **ssl**: use SSL to connect to the database (string, default: "disable". "enable" uses SSL without server-side validation and "verify" checks the certificate. For compatibility reasons, "true" behaves as "enable" and "false" behaves as "disable".)
 - **password**: database login password (string, default: "")
 - **database**: destination database name (string, required)
 - **schema**: destination schema name (string, default: "public")
@@ -23,6 +24,9 @@ Redshift output plugins for Embulk loads records to Redshift.
 - **s3_bucket**: S3 bucket name for temporary files
 - **s3_key_prefix**: S3 key prefix for temporary files (string, default:"")
 - **options**: extra connection properties (hash, default: {})
+- **retry_limit** max retry count for database operations (integer, default: 12)
+- **retry_wait** initial retry wait time in milliseconds (integer, default: 1000 (1 second))
+- **max_retry_wait** upper limit of retry wait, which will be doubled at every retry (integer, default: 1800000 (30 minutes))
 - **mode**: "insert", "insert_direct", "truncate_insert", "replace" or "merge". See below. (string, required)
 - **merge_keys**: key column names for merging records in merge mode (string array, required in merge mode)
 - **batch_size**: size of a single batch insert (integer, default: 16777216)
@@ -100,6 +104,7 @@ out:
   type: redshift
   host: myinstance.us-west-2.redshift.amazonaws.com
   user: pg
+  ssl: enable
   password: ""
   database: my_database
   table: my_table
@@ -120,10 +125,10 @@ out:
 ### Build
 
 ```
-$ ./gradlew gem
+$ ../gradlew gem
 ```
 
 ### Security
 This plugin requires AWS access credentials so that it may write temporary files to S3. There are two security options, Standard and Federated.
 To use Standard security, give **aws_key_id** and **secret_access_key**. To use Federated mode, also give the **iam_user_name** field.
-Federated mode really means temporary credentials, so that a man-in-the-middle attack will see AWS credentials that are only valid for 1 calendar day after the transaction.
+Federated mode really means temporary credentials, so that a man-in-the-middle attack will see AWS credentials that are only valid for 1 calendar day after the transaction.

data/src/main/java/org/embulk/output/RedshiftOutputPlugin.java

@@ -4,6 +4,8 @@ import java.util.List;
 import java.util.Properties;
 import java.io.IOException;
 import java.sql.SQLException;
+
+import org.embulk.output.jdbc.MergeConfig;
 import org.slf4j.Logger;
 import com.google.common.base.Optional;
 import com.google.common.collect.ImmutableSet;
@@ -17,6 +19,7 @@ import org.embulk.output.jdbc.AbstractJdbcOutputPlugin;
 import org.embulk.output.jdbc.BatchInsert;
 import org.embulk.output.redshift.RedshiftOutputConnector;
 import org.embulk.output.redshift.RedshiftCopyBatchInsert;
+import org.embulk.output.redshift.Ssl;
 
 public class RedshiftOutputPlugin
         extends AbstractJdbcOutputPlugin
@@ -62,6 +65,10 @@ public class RedshiftOutputPlugin
         @Config("s3_key_prefix")
         @ConfigDefault("\"\"")
         public String getS3KeyPrefix();
+
+        @Config("ssl")
+        @ConfigDefault("disable")
+        public Ssl getSsl();
     }
 
     @Override
@@ -95,16 +102,18 @@ public class RedshiftOutputPlugin
         // Socket options TCP_KEEPCNT, TCP_KEEPIDLE, and TCP_KEEPINTVL are not configurable.
         props.setProperty("tcpKeepAlive", "true");
 
-        // TODO
-        //switch task.getSssl() {
-        //when "disable":
-        //    break;
-        //when "enable":
-        //    props.setProperty("sslfactory", "org.postgresql.ssl.NonValidatingFactory");  // disable server-side validation
-        //when "verify":
-        //    props.setProperty("ssl", "true");
-        //    break;
-        //}
+        switch (t.getSsl()) {
+        case DISABLE:
+           break;
+        case ENABLE:
+            // See http://docs.aws.amazon.com/redshift/latest/mgmt/connecting-ssl-support.html
+           props.setProperty("ssl", "true");
+           props.setProperty("sslfactory", "org.postgresql.ssl.NonValidatingFactory"); // disable server-side validation
+           break;
+        case VERIFY:
+           props.setProperty("ssl", "true");
+           break;
+        }
 
         if (!retryableMetadataOperation) {
             // non-retryable batch operation uses longer timeout
@@ -140,9 +149,9 @@ public class RedshiftOutputPlugin
     }
 
     @Override
-    protected BatchInsert newBatchInsert(PluginTask task, Optional<List<String>> mergeKeys) throws IOException, SQLException
+    protected BatchInsert newBatchInsert(PluginTask task, Optional<MergeConfig> mergeConfig) throws IOException, SQLException
     {
-        if (mergeKeys.isPresent()) {
+        if (mergeConfig.isPresent()) {
             throw new UnsupportedOperationException("Redshift output plugin doesn't support 'merge_direct' mode. Use 'merge' mode instead.");
         }
         RedshiftPluginTask t = (RedshiftPluginTask) task;

data/src/main/java/org/embulk/output/redshift/RedshiftOutputConnection.java

@@ -4,6 +4,9 @@ import java.util.List;
 import java.sql.Connection;
 import java.sql.SQLException;
 import java.sql.Statement;
+
+import com.google.common.base.Optional;
+import org.embulk.output.jdbc.MergeConfig;
 import org.slf4j.Logger;
 import org.embulk.spi.Exec;
 import org.embulk.output.jdbc.JdbcOutputConnection;
@@ -122,7 +125,7 @@ public class RedshiftOutputConnection
     }
 
     @Override
-    protected String buildCollectMergeSql(List<String> fromTables, JdbcSchema schema, String toTable, List<String> mergeKeys) throws SQLException
+    protected String buildCollectMergeSql(List<String> fromTables, JdbcSchema schema, String toTable, MergeConfig mergeConfig) throws SQLException
     {
         StringBuilder sb = new StringBuilder();
 
@@ -137,6 +140,7 @@ public class RedshiftOutputConnection
             quoteIdentifierString(sb, fromTables.get(i));
         }
         sb.append(") S WHERE (");
+        List<String> mergeKeys = mergeConfig.getMergeKeys();
         for(int i=0; i < mergeKeys.size(); i++) {
             if (i != 0) { sb.append(" AND "); }
             sb.append("S.");

data/src/main/java/org/embulk/output/redshift/Ssl.java

@@ -0,0 +1,37 @@
+package org.embulk.output.redshift;
+
+import com.fasterxml.jackson.annotation.JsonCreator;
+import com.fasterxml.jackson.annotation.JsonValue;
+
+import org.embulk.config.ConfigException;
+
+public enum Ssl
+{
+    ENABLE,
+    DISABLE,
+    VERIFY;
+
+    @JsonValue
+    @Override
+    public String toString()
+    {
+        return this.name().toLowerCase();
+    }
+
+    @JsonCreator
+    public static Ssl fromString(String value)
+    {
+        switch(value) {
+        case "enable":
+        case "true":
+            return ENABLE;
+        case "disable":
+        case "false":
+            return DISABLE;
+        case "verify":
+            return VERIFY;
+        default:
+            throw new ConfigException(String.format("Unknown SSL value '%s'. Supported values are enable, true, disable, false or verify.", value));
+        }
+    }
+}

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: embulk-output-redshift
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.6.2
 platform: ruby
 authors:
 - Sadayuki Furuhashi
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2016-06-23 00:00:00.000000000 Z
+date: 2016-08-10 00:00:00.000000000 Z
 dependencies: []
 description: Inserts or updates records to a table.
 email:
@@ -24,15 +24,16 @@ files:
 - src/main/java/org/embulk/output/redshift/RedshiftCopyBatchInsert.java
 - src/main/java/org/embulk/output/redshift/RedshiftOutputConnection.java
 - src/main/java/org/embulk/output/redshift/RedshiftOutputConnector.java
+- src/main/java/org/embulk/output/redshift/Ssl.java
 - classpath/aws-java-sdk-core-1.10.33.jar
 - classpath/aws-java-sdk-kms-1.10.33.jar
 - classpath/aws-java-sdk-s3-1.10.33.jar
 - classpath/aws-java-sdk-sts-1.10.33.jar
 - classpath/commons-codec-1.6.jar
 - classpath/commons-logging-1.1.3.jar
-- classpath/embulk-output-jdbc-0.6.1.jar
-- classpath/embulk-output-postgresql-0.6.1.jar
-- classpath/embulk-output-redshift-0.6.1.jar
+- classpath/embulk-output-jdbc-0.6.2.jar
+- classpath/embulk-output-postgresql-0.6.2.jar
+- classpath/embulk-output-redshift-0.6.2.jar
 - classpath/httpclient-4.3.6.jar
 - classpath/httpcore-4.3.3.jar
 - classpath/postgresql-9.4-1205-jdbc41.jar