embulk-output-sqlserver 0.5.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 76d8fb06a79d4382fab1f378b165ab10518fe9ef
+  data.tar.gz: cc766e5eeff96a7a1e74e00893a01beb58a13e83
+SHA512:
+  metadata.gz: e39ecf1f59e3b3c555733821925e0a098be114b1d15844c6bcb1f8349de93168cb46bbfc999f427f5231f061d89bfae509e875d9d480e366224e639385dccd54
+  data.tar.gz: 45419b194e670602d291ff1e1ee5ecedb0c7a6d9b236340e056ce82a37b1cdc7838dd01cc03ebafa41470f10b5cef673ea25f85a902b4a625ffaab7501a00968

data/README.md

@@ -0,0 +1,95 @@
+# SQL Server output plugins for Embulk
+
+SQL Server output plugins for Embulk loads records to SQL Server.
+
+## Overview
+
+* **Plugin type**: output
+* **Load all or nothing**: depnds on the mode. see bellow.
+* **Resume supported**: depnds on the mode. see bellow.
+
+## Configuration
+
+- **driver_path**: path to the jar file of the SQL Server JDBC driver (string)
+- **host**: database host name (string, required)
+- **port**: database port number (integer, default: 1433)
+- **integratedSecutiry**: whether to use integrated authentication or not. The `sqljdbc_auth.dll` must be located on Java library path if using integrated authentication. : (boolean, default: false)
+```
+rem C:\drivers\sqljdbc_auth.dll
+embulk "-J-Djava.library.path=C:\drivers" run input-sqlserver.yml
+```
+- **user**: database login user name (string, required if not using integrated authentication)
+- **password**: database login password (string, default: "")
+- **instance**: destination instance name (string, default: use the default instance)
+- **database**: destination database name (string, default: use the default database)
+- **url**: URL of the JDBC connection (string, optional)
+- **table**: destination table name (string, required)
+- **options**: extra connection properties (hash, default: {})
+- **mode**: "insert", "insert_direct", "truncate_insert" or "replace". See bellow. (string, required)
+- **batch_size**: size of a single batch insert (integer, default: 16777216)
+- **default_timezone**: If input column type (embulk type) is timestamp, this plugin needs to format the timestamp into a SQL string. This default_timezone option is used to control the timezone. You can overwrite timezone for each columns using column_options option. (string, default: `UTC`)
+- **column_options**: advanced: a key-value pairs where key is a column name and value is options for the column.
+  - **type**: type of a column when this plugin creates new tables (e.g. `VARCHAR(255)`, `INTEGER NOT NULL UNIQUE`). This used when this plugin creates intermediate tables (insert, insert_truncate and merge modes), when it creates the target table (insert_direct, merge_direct and replace modes), and when it creates nonexistent target table automatically. (string, default: depends on input column type. `BIGINT` if input column type is long, `BOOLEAN` if boolean, `DOUBLE PRECISION` if double, `CLOB` if string, `TIMESTAMP` if timestamp)
+  - **value_type**: This plugin converts input column type (embulk type) into a database type to build a INSERT statement. This value_type option controls the type of the value in a INSERT statement. (string, default: depends on input column type. Available values options are: `byte`, `short`, `int`, `long`, `double`, `float`, `boolean`, `string`, `nstring`, `date`, `time`, `timestamp`, `decimal`, `null`, `pass`)
+  - **timestamp_format**: If input column type (embulk type) is timestamp and value_type is `string` or `nstring`, this plugin needs to format the timestamp value into a string. This timestamp_format option is used to control the format of the timestamp. (string, default: `%Y-%m-%d %H:%M:%S.%6N`)
+  - **timezone**: If input column type (embulk type) is timestamp, this plugin needs to format the timestamp value into a SQL string. In this cases, this timezone option is used to control the timezone. (string, value of default_timezone option is used by default)
+
+### Modes
+
+* **insert**:
+  * Behavior: This mode writes rows to some intermediate tables first. If all those tasks run correctly, runs `INSERT INTO <target_table> SELECT * FROM <intermediate_table_1> UNION ALL SELECT * FROM <intermediate_table_2> UNION ALL ...` query. If the target table doesn't exist, it is created automatically.
+  * Transactional: Yes. This mode successfully writes all rows, or fails with writing zero rows.
+  * Resumable: Yes.
+* **insert_direct**:
+  * Behavior: This mode inserts rows to the target table directly. If the target table doesn't exist, it is created automatically.
+  * Transactional: No. If fails, the target table could have some rows inserted.
+  * Resumable: No.
+* **truncate_insert**:
+  * Behavior: Same with `insert` mode excepting that it truncates the target table right before the last `INSERT ...` query.
+  * Transactional: Yes.
+  * Resumable: Yes.
+* **replace**:
+  * Behavior: This mode writes rows to an intermediate table first. If all those tasks run correctly, drops the target table and alters the name of the intermediate table into the target table name.
+  * Transactional: No. If fails, the target table could be dropped (because SQL Server can't rollback DDL).
+  * Resumable: No.
+
+### Example
+
+```yaml
+out:
+  type: sqlserver
+  driver_path: C:\drivers\sqljdbc41.jar
+  host: localhost
+  user: myuser
+  password: ""
+  instance: MSSQLSERVER
+  database: my_database
+  table: my_table
+  mode: insert
+```
+
+Advanced configuration:
+
+```yaml
+out:
+  type: sqlserver
+  driver_path: C:\drivers\sqljdbc41.jar
+  host: localhost
+  user: myuser
+  password: ""
+  instance: MSSQLSERVER
+  database: my_database
+  table: my_table
+  mode: insert_direct
+  column_options:
+    my_col_1: {type: 'TEXT'}
+    my_col_3: {type: 'INT NOT NULL'}
+    my_col_4: {value_type: string, timestamp_format: `%Y-%m-%d %H:%M:%S %z`, timezone: '-0700'}
+    my_col_5: {type: 'DECIMAL(18,9)', value_type: pass}
+```
+
+### Build
+
+```
+$ ./gradlew gem
+```

data/build.gradle

@@ -0,0 +1,6 @@
+[compileTestJava]*.options*.encoding = 'UTF-8'
+
+dependencies {
+    compile project(':embulk-output-jdbc')
+    testCompile files('../embulk-output-jdbc/build/classes/test/')
+}

data/lib/embulk/output/sqlserver.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_output(
+  :sqlserver, "org.embulk.output.SQLServerOutputPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

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

@@ -0,0 +1,151 @@
+package org.embulk.output;
+
+import java.io.IOException;
+import java.sql.SQLException;
+import java.util.List;
+import java.util.Properties;
+
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.output.jdbc.AbstractJdbcOutputPlugin;
+import org.embulk.output.jdbc.BatchInsert;
+import org.embulk.output.jdbc.StandardBatchInsert;
+import org.embulk.output.jdbc.setter.ColumnSetterFactory;
+import org.embulk.output.sqlserver.SQLServerOutputConnector;
+import org.embulk.output.sqlserver.setter.SQLServerColumnSetterFactory;
+import org.joda.time.DateTimeZone;
+
+import com.google.common.base.Optional;
+import com.google.common.collect.ImmutableSet;
+
+public class SQLServerOutputPlugin
+        extends AbstractJdbcOutputPlugin
+{
+    public interface SQLServerPluginTask
+            extends PluginTask
+    {
+        @Config("driver_path")
+        @ConfigDefault("null")
+        public Optional<String> getDriverPath();
+
+        @Config("host")
+        @ConfigDefault("null")
+        public Optional<String> getHost();
+
+        @Config("port")
+        @ConfigDefault("1433")
+        public int getPort();
+
+        @Config("instance")
+        @ConfigDefault("null")
+        public Optional<String> getInstance();
+
+        @Config("database")
+        @ConfigDefault("null")
+        public Optional<String> getDatabase();
+
+        @Config("integratedSecurity")
+        @ConfigDefault("null")
+        public Optional<Boolean> getIntegratedSecurity();
+
+        @Config("url")
+        @ConfigDefault("null")
+        public Optional<String> getUrl();
+
+        @Config("user")
+        @ConfigDefault("null")
+        public Optional<String> getUser();
+
+        @Config("password")
+        @ConfigDefault("\"\"")
+        public Optional<String> getPassword();
+
+    }
+
+    @Override
+    protected Class<? extends PluginTask> getTaskClass()
+    {
+        return SQLServerPluginTask.class;
+    }
+
+    @Override
+    protected Features getFeatures(PluginTask task)
+    {
+        return new Features()
+            .setMaxTableNameLength(128)
+            .setSupportedModes(ImmutableSet.of(Mode.INSERT, Mode.INSERT_DIRECT, Mode.TRUNCATE_INSERT, Mode.REPLACE))
+            .setIgnoreMergeKeys(false);
+    }
+
+    @Override
+    protected SQLServerOutputConnector getConnector(PluginTask task, boolean retryableMetadataOperation)
+    {
+        SQLServerPluginTask sqlServerTask = (SQLServerPluginTask) task;
+
+        if (sqlServerTask.getDriverPath().isPresent()) {
+            loadDriverJar(sqlServerTask.getDriverPath().get());
+        }
+
+        String url;
+        if (sqlServerTask.getUrl().isPresent()) {
+            if (sqlServerTask.getHost().isPresent()
+                    || sqlServerTask.getInstance().isPresent()
+                    || sqlServerTask.getDatabase().isPresent()
+                    || sqlServerTask.getIntegratedSecurity().isPresent()) {
+                throw new IllegalArgumentException("'host', 'port', 'instance', 'database' and 'integratedSecurity' parameters are invalid if 'url' parameter is set.");
+            }
+            url = sqlServerTask.getUrl().get();
+        } else {
+            if (!sqlServerTask.getHost().isPresent()) {
+                throw new IllegalArgumentException("Field 'host' is not set.");
+            }
+            if (!sqlServerTask.getDatabase().isPresent()) {
+                throw new IllegalArgumentException("Field 'database' is not set.");
+            }
+            StringBuilder urlBuilder = new StringBuilder();
+            if (sqlServerTask.getInstance().isPresent()) {
+                urlBuilder.append(String.format("jdbc:sqlserver://%s\\%s:%d",
+                        sqlServerTask.getHost().get(), sqlServerTask.getInstance().get(), sqlServerTask.getPort()));
+            } else {
+                urlBuilder.append(String.format("jdbc:sqlserver://%s:%d",
+                        sqlServerTask.getHost().get(), sqlServerTask.getPort()));
+            }
+            if (sqlServerTask.getDatabase().isPresent()) {
+                urlBuilder.append(";databaseName=" + sqlServerTask.getDatabase().get());
+            }
+            if (sqlServerTask.getIntegratedSecurity().isPresent() && sqlServerTask.getIntegratedSecurity().get()) {
+                urlBuilder.append(";integratedSecurity=" + sqlServerTask.getIntegratedSecurity().get());
+            } else {
+                if (!sqlServerTask.getUser().isPresent()) {
+                    throw new IllegalArgumentException("Field 'user' is not set.");
+                }
+                if (!sqlServerTask.getPassword().isPresent()) {
+                    throw new IllegalArgumentException("Field 'password' is not set.");
+                }
+            }
+            url = urlBuilder.toString();
+        }
+
+
+        Properties props = new Properties();
+        props.putAll(sqlServerTask.getOptions());
+
+        props.setProperty("user", sqlServerTask.getUser().get());
+        logger.info("Connecting to {} options {}", url, props);
+        props.setProperty("password", sqlServerTask.getPassword().get());
+
+        return new SQLServerOutputConnector(url, props, null);
+    }
+
+    @Override
+    protected BatchInsert newBatchInsert(PluginTask task, Optional<List<String>> mergeKeys) throws IOException, SQLException
+    {
+        return new StandardBatchInsert(getConnector(task, true), mergeKeys);
+    }
+
+    @Override
+    protected ColumnSetterFactory newColumnSetterFactory(BatchInsert batch, DateTimeZone defaultTimeZone)
+    {
+        return new SQLServerColumnSetterFactory(batch, defaultTimeZone);
+    }
+}

data/src/main/java/org/embulk/output/sqlserver/SQLServerOutputConnection.java

@@ -0,0 +1,124 @@
+package org.embulk.output.sqlserver;
+
+import java.sql.Connection;
+import java.sql.SQLException;
+import java.sql.Statement;
+import java.util.Arrays;
+
+import org.embulk.output.jdbc.JdbcColumn;
+import org.embulk.output.jdbc.JdbcOutputConnection;
+import org.embulk.output.jdbc.JdbcSchema;
+
+public class SQLServerOutputConnection
+        extends JdbcOutputConnection
+{
+    public SQLServerOutputConnection(Connection connection, String schemaName, boolean autoCommit)
+            throws SQLException
+    {
+        super(connection, schemaName);
+        connection.setAutoCommit(autoCommit);
+    }
+
+    @Override
+    protected String buildRenameTableSql(String fromTable, String toTable)
+    {
+        StringBuilder sb = new StringBuilder();
+        sb.append("EXEC sp_rename ");
+        sb.append(quoteIdentifierString(fromTable));
+        sb.append(", ");
+        sb.append(quoteIdentifierString(toTable));
+        sb.append(", 'OBJECT'");
+        return sb.toString();
+    }
+
+    @Override
+    protected String buildColumnTypeName(JdbcColumn c)
+    {
+        switch(c.getSimpleTypeName()) {
+        case "BOOLEAN":
+            return "BIT";
+        case "CLOB":
+            return "TEXT";
+        case "TIMESTAMP":
+            return "DATETIME2";
+        default:
+            return super.buildColumnTypeName(c);
+        }
+    }
+
+    @Override
+    protected void setSearchPath(String schema) throws SQLException
+    {
+        // NOP
+    }
+
+    @Override
+    public void dropTableIfExists(String tableName) throws SQLException
+    {
+        if (tableExists(tableName)) {
+            dropTable(tableName);
+        }
+    }
+
+    @Override
+    protected void dropTableIfExists(Statement stmt, String tableName) throws SQLException
+    {
+        if (tableExists(tableName)) {
+            dropTable(stmt, tableName);
+        }
+    }
+
+    @Override
+    public void createTableIfNotExists(String tableName, JdbcSchema schema) throws SQLException
+    {
+        if (!tableExists(tableName)) {
+            createTable(tableName, schema);
+        }
+    }
+
+    public void createTable(String tableName, JdbcSchema schema) throws SQLException
+    {
+        Statement stmt = connection.createStatement();
+        try {
+            String sql = buildCreateTableSql(tableName, schema);
+            executeUpdate(stmt, sql);
+            commitIfNecessary(connection);
+        } catch (SQLException ex) {
+            throw safeRollback(connection, ex);
+        } finally {
+            stmt.close();
+        }
+    }
+
+    protected String buildCreateTableSql(String name, JdbcSchema schema)
+    {
+        StringBuilder sb = new StringBuilder();
+
+        sb.append("CREATE TABLE ");
+        quoteIdentifierString(sb, name);
+        sb.append(buildCreateTableSchemaSql(schema));
+        return sb.toString();
+    }
+
+    private static final String[] SIMPLE_TYPE_NAMES = {
+        "BIT", "FLOAT",
+    };
+
+    @Override
+    protected ColumnDeclareType getColumnDeclareType(String convertedTypeName, JdbcColumn col)
+    {
+        if (Arrays.asList(SIMPLE_TYPE_NAMES).contains(convertedTypeName)) {
+            return ColumnDeclareType.SIMPLE;
+        }
+        return super.getColumnDeclareType(convertedTypeName, col);
+    }
+
+    /*
+    @Override
+    public Charset getTableNameCharset() throws SQLException
+    {
+        return getOracleCharset().getJavaCharset();
+    }
+
+    */
+}

data/src/main/java/org/embulk/output/sqlserver/SQLServerOutputConnector.java

@@ -0,0 +1,49 @@
+package org.embulk.output.sqlserver;
+
+import java.sql.Connection;
+import java.sql.DriverManager;
+import java.sql.SQLException;
+import java.util.Properties;
+
+import org.embulk.output.jdbc.JdbcOutputConnector;
+
+public class SQLServerOutputConnector
+        implements JdbcOutputConnector
+{
+    private final String url;
+    private final Properties properties;
+    private final String schemaName;
+
+    public SQLServerOutputConnector(String url, Properties properties, String schemaName)
+    {
+        try {
+            Class.forName("com.microsoft.sqlserver.jdbc.SQLServerDriver");
+        } catch (Exception ex) {
+            throw new RuntimeException(ex);
+        }
+        this.url = url;
+        this.properties = properties;
+        this.schemaName = schemaName;
+    }
+
+    @Override
+    public SQLServerOutputConnection connect(boolean autoCommit) throws SQLException
+    {
+        Connection c = DriverManager.getConnection(url, properties);
+        if (c == null) {
+            // driver.connect returns null when url is "jdbc:mysql://...".
+            throw new SQLException("Invalid url : " + url);
+        }
+
+        try {
+            SQLServerOutputConnection con = new SQLServerOutputConnection(c, schemaName, autoCommit);
+            c = null;
+            return con;
+
+        } finally {
+            if (c != null) {
+                c.close();
+            }
+        }
+    }
+}