embulk-input-clickhouse 0.1.0

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Tue Oct 02 20:27:31 JST 2018
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-4.1-all.zip

data/gradlew

@@ -0,0 +1,172 @@
+#!/usr/bin/env sh
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Attempt to set APP_HOME
+# Resolve links: $0 may be a link
+PRG="$0"
+# Need this for relative symlinks.
+while [ -h "$PRG" ] ; do
+    ls=`ls -ld "$PRG"`
+    link=`expr "$ls" : '.*-> \(.*\)$'`
+    if expr "$link" : '/.*' > /dev/null; then
+        PRG="$link"
+    else
+        PRG=`dirname "$PRG"`"/$link"
+    fi
+done
+SAVED="`pwd`"
+cd "`dirname \"$PRG\"`/" >/dev/null
+APP_HOME="`pwd -P`"
+cd "$SAVED" >/dev/null
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn () {
+    echo "$*"
+}
+
+die () {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+nonstop=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+  NONSTOP* )
+    nonstop=true
+    ;;
+esac
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+if [ -n "$JAVA_HOME" ] ; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
+        # IBM's JDK on AIX uses strange locations for the executables
+        JAVACMD="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# For Darwin, add options to specify how the application appears in the dock
+if $darwin; then
+    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
+fi
+
+# For Cygwin, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
+    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$JAVACMD"`
+
+    # We build the pattern for arguments to be converted via cygpath
+    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
+    SEP=""
+    for dir in $ROOTDIRSRAW ; do
+        ROOTDIRS="$ROOTDIRS$SEP$dir"
+        SEP="|"
+    done
+    OURCYGPATTERN="(^($ROOTDIRS))"
+    # Add a user-defined pattern to the cygpath arguments
+    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
+        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
+    fi
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    i=0
+    for arg in "$@" ; do
+        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
+        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
+
+        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
+            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
+        else
+            eval `echo args$i`="\"$arg\""
+        fi
+        i=$((i+1))
+    done
+    case $i in
+        (0) set -- ;;
+        (1) set -- "$args0" ;;
+        (2) set -- "$args0" "$args1" ;;
+        (3) set -- "$args0" "$args1" "$args2" ;;
+        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
+        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
+        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
+        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
+        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
+        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
+    esac
+fi
+
+# Escape application args
+save () {
+    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
+    echo " "
+}
+APP_ARGS=$(save "$@")
+
+# Collect all arguments for the java command, following the shell quoting and substitution rules
+eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "$@"

data/gradlew.bat

@@ -0,0 +1,84 @@
+@if "%DEBUG%" == "" @echo off
+@rem ##########################################################################
+@rem
+@rem  Gradle startup script for Windows
+@rem
+@rem ##########################################################################
+
+@rem Set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" setlocal
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+set DEFAULT_JVM_OPTS=
+
+@rem Find java.exe
+if defined JAVA_HOME goto findJavaFromJavaHome
+
+set JAVA_EXE=java.exe
+%JAVA_EXE% -version >NUL 2>&1
+if "%ERRORLEVEL%" == "0" goto init
+
+echo.
+echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:findJavaFromJavaHome
+set JAVA_HOME=%JAVA_HOME:"=%
+set JAVA_EXE=%JAVA_HOME%/bin/java.exe
+
+if exist "%JAVA_EXE%" goto init
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:init
+@rem Get command-line arguments, handling Windows variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+
+:win9xME_args
+@rem Slurp the command line arguments.
+set CMD_LINE_ARGS=
+set _SKIP=2
+
+:win9xME_args_slurp
+if "x%~1" == "x" goto execute
+
+set CMD_LINE_ARGS=%*
+
+:execute
+@rem Setup the command line
+
+set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
+
+@rem Execute Gradle
+"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
+
+:end
+@rem End local scope for the variables with windows NT shell
+if "%ERRORLEVEL%"=="0" goto mainEnd
+
+:fail
+rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
+rem the _cmd.exe /c_ return code!
+if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
+exit /b 1
+
+:mainEnd
+if "%OS%"=="Windows_NT" endlocal
+
+:omega

data/lib/embulk/input/clickhouse.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_input(
+  "clickhouse", "org.embulk.input.clickhouse.ClickhouseInputPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/input/clickhouse/ClickHouseColumnGetterFactory.java

@@ -0,0 +1,40 @@
+package org.embulk.input.clickhouse;
+
+import org.embulk.input.clickhouse.getter.ArrayColumnGetter;
+import org.embulk.input.clickhouse.getter.BigIntegerColumnGetter;
+import org.embulk.input.clickhouse.getter.TupleColumnGetter;
+import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
+import org.embulk.input.jdbc.JdbcColumn;
+import org.embulk.input.jdbc.JdbcColumnOption;
+import org.embulk.input.jdbc.JdbcInputConnection;
+import org.embulk.input.jdbc.getter.ColumnGetter;
+import org.embulk.input.jdbc.getter.ColumnGetterFactory;
+import org.embulk.spi.PageBuilder;
+import org.joda.time.DateTimeZone;
+
+public class ClickHouseColumnGetterFactory extends ColumnGetterFactory
+{
+
+    public ClickHouseColumnGetterFactory(PageBuilder to, DateTimeZone defaultTimeZone)
+    {
+        super(to, defaultTimeZone);
+    }
+
+    @Override
+    public ColumnGetter newColumnGetter(JdbcInputConnection con, AbstractJdbcInputPlugin.PluginTask task, JdbcColumn column, JdbcColumnOption option)
+    {
+        if (column.getTypeName().toLowerCase().equals("uint64")) {
+            return new BigIntegerColumnGetter(to, getToType(option), column.getTypeName());
+        }
+
+        if (column.getSqlType() == java.sql.Types.ARRAY) {
+            return new ArrayColumnGetter(to, getToType(option));
+        }
+
+        if (column.getTypeName().startsWith("Tuple")) {
+            return new TupleColumnGetter(to, getToType(option));
+        }
+
+        return super.newColumnGetter(con, task, column, option);
+    }
+}

data/src/main/java/org/embulk/input/clickhouse/ClickHouseInputConnection.java

@@ -0,0 +1,15 @@
+package org.embulk.input.clickhouse;
+
+import org.embulk.input.jdbc.JdbcInputConnection;
+
+import java.sql.Connection;
+import java.sql.SQLException;
+
+public class ClickHouseInputConnection extends JdbcInputConnection
+{
+    public ClickHouseInputConnection(Connection connection, String schemaName)
+            throws SQLException
+    {
+        super(connection, schemaName);
+    }
+}

data/src/main/java/org/embulk/input/clickhouse/ClickhouseInputPlugin.java

@@ -0,0 +1,184 @@
+package org.embulk.input.clickhouse;
+
+import com.google.common.base.Optional;
+
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.TaskReport;
+import org.embulk.config.TaskSource;
+import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
+import org.embulk.input.jdbc.JdbcInputConnection;
+import org.embulk.input.jdbc.getter.ColumnGetterFactory;
+import org.embulk.spi.InputPlugin;
+import org.embulk.spi.PageBuilder;
+import org.embulk.spi.PageOutput;
+import org.embulk.spi.Schema;
+import org.joda.time.DateTimeZone;
+
+import java.sql.Connection;
+import java.sql.DriverManager;
+import java.sql.SQLException;
+import java.util.List;
+import java.util.Properties;
+
+import ru.yandex.clickhouse.settings.ClickHouseConnectionSettings;
+
+public class ClickhouseInputPlugin extends AbstractJdbcInputPlugin
+{
+    public interface ClickHousePluginTask
+        extends AbstractJdbcInputPlugin.PluginTask
+    {
+        @Config("driver_path")
+        @ConfigDefault("null")
+        public Optional<String> getDriverPath();
+
+        @Config("host")
+        public String getHost();
+
+        @Config("port")
+        @ConfigDefault("8123")
+        public int getPort();
+
+        @Config("user")
+        @ConfigDefault("null")
+        public Optional<String> getUser();
+
+        @Config("password")
+        @ConfigDefault("null")
+        public Optional<String> getPassword();
+
+        @Config("database")
+        public String getDatabase();
+
+        @Config("buffer_size")
+        @ConfigDefault("65536")
+        public Optional<Integer> getBufferSize();
+
+        @Config("apache_buffer_size")
+        @ConfigDefault("65536")
+        public Optional<Integer> getApacheBufferSize();
+
+        @Config("connect_timeout")
+        @ConfigDefault("30000")
+        public int getConnectTimeout();
+
+        @Config("socket_timeout")
+        @ConfigDefault("10000")
+        public int getSocketTimeout();
+
+        /**
+         * Timeout for data transfer. socketTimeout + dataTransferTimeout is sent to ClickHouse as max_execution_time.
+         * ClickHouse rejects request execution if its time exceeds max_execution_time
+         */
+        @Config("data_transfer_timeout")
+        @ConfigDefault("10000")
+        public Optional<Integer> getDataTransferTimeout();
+
+        @Config("keep_alive_timeout")
+        @ConfigDefault("30000")
+        public Optional<Integer> getKeepAliveTimeout();
+    }
+
+    @Override
+    protected Class<? extends AbstractJdbcInputPlugin.PluginTask> getTaskClass()
+    {
+        return ClickHousePluginTask.class;
+    }
+
+    @Override
+    protected JdbcInputConnection newConnection(AbstractJdbcInputPlugin.PluginTask task) throws SQLException
+    {
+        final String driverClass = "ru.yandex.clickhouse.ClickHouseDriver";
+
+        ClickHousePluginTask t = (ClickHousePluginTask) task;
+
+        loadDriver(driverClass, t.getDriverPath());
+
+        Properties props = new Properties();
+        if (t.getUser().isPresent()) {
+            props.setProperty("user", t.getUser().get());
+        }
+        if (t.getPassword().isPresent()) {
+            props.setProperty("password", t.getPassword().get());
+        }
+
+        // ClickHouse Connection Options
+        if (t.getApacheBufferSize().isPresent()) {
+            props.setProperty(ClickHouseConnectionSettings.APACHE_BUFFER_SIZE.getKey(), String.valueOf(t.getApacheBufferSize().get())); // byte?
+        }
+        if (t.getBufferSize().isPresent()) {
+            props.setProperty(ClickHouseConnectionSettings.BUFFER_SIZE.getKey(), String.valueOf(t.getBufferSize().get())); // byte?
+        }
+        if (t.getDataTransferTimeout().isPresent()) {
+            props.setProperty(ClickHouseConnectionSettings.DATA_TRANSFER_TIMEOUT.getKey(), String.valueOf(t.getDataTransferTimeout().get())); // seconds
+        }
+        if (t.getKeepAliveTimeout().isPresent()) {
+            props.setProperty(ClickHouseConnectionSettings.KEEP_ALIVE_TIMEOUT.getKey(), String.valueOf(t.getKeepAliveTimeout().get())); // seconds
+        }
+
+        props.setProperty(ClickHouseConnectionSettings.SOCKET_TIMEOUT.getKey(), String.valueOf(t.getSocketTimeout())); // seconds
+        props.setProperty(ClickHouseConnectionSettings.CONNECTION_TIMEOUT.getKey(), String.valueOf(t.getConnectTimeout())); // seconds
+        props.putAll(t.getOptions());
+
+        final String url = String.format("jdbc:clickhouse://%s:%d/%s", t.getHost(), t.getPort(), t.getDatabase());
+
+        logConnectionProperties(url, props);
+
+        Connection con = DriverManager.getConnection(url, props);
+        try {
+            ClickHouseInputConnection c = new ClickHouseInputConnection(con, null);
+            con = null;
+            return c;
+        }
+        finally {
+            if (con != null) {
+                con.close();
+            }
+        }
+    }
+
+    @Override
+    protected ColumnGetterFactory newColumnGetterFactory(PageBuilder pageBuilder, DateTimeZone dateTimeZone)
+    {
+        return new ClickHouseColumnGetterFactory(pageBuilder, dateTimeZone);
+    }
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config, InputPlugin.Control control)
+    {
+        // TBD
+        return super.transaction(config, control);
+    }
+
+    @Override
+    public ConfigDiff resume(TaskSource taskSource, Schema schema, int taskCount, InputPlugin.Control control)
+    {
+        // TBD
+        return super.resume(taskSource, schema, taskCount, control);
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource, Schema schema, int taskCount, List<TaskReport> successTaskReports)
+    {
+        //TBD
+        super.cleanup(taskSource, schema, taskCount, successTaskReports);
+    }
+
+    @Override
+    public TaskReport run(TaskSource taskSource, Schema schema, int taskIndex, PageOutput output)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        //TBD
+        return super.run(taskSource, schema, taskIndex, output);
+    }
+
+    @Override
+    public ConfigDiff guess(ConfigSource config)
+    {
+        //TBD
+        return super.guess(config);
+    }
+}