embulk-output-cassandra 0.1.0

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/output/cassandra.rb

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

data/src/main/java/org/embulk/output/cassandra/CassandraOutputPlugin.java

@@ -0,0 +1,283 @@
+package org.embulk.output.cassandra;
+
+import com.datastax.driver.core.BoundStatement;
+import com.datastax.driver.core.Cluster;
+import com.datastax.driver.core.ColumnMetadata;
+import com.datastax.driver.core.KeyspaceMetadata;
+import com.datastax.driver.core.PreparedStatement;
+import com.datastax.driver.core.Session;
+import com.datastax.driver.core.SocketOptions;
+import com.datastax.driver.core.TableMetadata;
+import com.datastax.driver.core.querybuilder.Insert;
+import com.datastax.driver.core.querybuilder.QueryBuilder;
+import com.google.common.base.Optional;
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.ImmutableMap;
+import com.google.common.collect.Lists;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskReport;
+import org.embulk.config.TaskSource;
+import org.embulk.output.cassandra.setter.CassandraColumnSetter;
+import org.embulk.output.cassandra.setter.CassandraColumnSetterFactory;
+import org.embulk.output.cassandra.setter.ColumnSetterVisitor;
+import org.embulk.spi.Exec;
+import org.embulk.spi.OutputPlugin;
+import org.embulk.spi.Page;
+import org.embulk.spi.PageReader;
+import org.embulk.spi.Schema;
+import org.embulk.spi.TransactionalPageOutput;
+import org.slf4j.Logger;
+
+import java.net.InetSocketAddress;
+import java.util.List;
+import java.util.Map;
+
+public class CassandraOutputPlugin
+        implements OutputPlugin
+{
+    public interface PluginTask
+            extends Task
+    {
+        @Config("hosts")
+        public List<String> gethosts();
+
+        @Config("port")
+        @ConfigDefault("9042")
+        public int getPort();
+
+        @Config("username")
+        @ConfigDefault("null")
+        public Optional<String> getUsername();
+
+        @Config("password")
+        @ConfigDefault("null")
+        public Optional<String> getPassword();
+
+        @Config("cluster_name")
+        @ConfigDefault("null")
+        public Optional<String> getClustername();
+
+        @Config("keyspace")
+        public String getKeyspace();
+
+        @Config("table")
+        public String getTable();
+
+        @Config("if_not_exists")
+        @ConfigDefault("false")
+        public Boolean getIfNotExists();
+
+        @Config("ttl")
+        @ConfigDefault("null")
+        public Optional<Integer> getTtl();
+
+        @Config("idempotent")
+        @ConfigDefault("false")
+        public Boolean getIdempotent();
+
+        @Config("connect_timeout")
+        @ConfigDefault("5000")
+        public int getConnectTimeout();
+
+        @Config("request_timeout")
+        @ConfigDefault("12000")
+        public int getRequestTimeout();
+    }
+
+    private final Logger logger = Exec.getLogger(CassandraOutputPlugin.class);
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config,
+            Schema schema, int taskCount,
+            OutputPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        return resume(task.dump(), schema, taskCount, control);
+    }
+
+    @Override
+    public ConfigDiff resume(TaskSource taskSource,
+            Schema schema, int taskCount,
+            OutputPlugin.Control control)
+    {
+        control.run(taskSource);
+        return Exec.newConfigDiff();
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource,
+            Schema schema, int taskCount,
+            List<TaskReport> successTaskReports)
+    {
+    }
+
+    @Override
+    public TransactionalPageOutput open(TaskSource taskSource, Schema schema, int taskIndex)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+        PageReader pageReader = new PageReader(schema);
+        Cluster cluster = getCluster(task);
+
+        Session session = cluster.newSession();
+
+        KeyspaceMetadata keyspaceMetadata = cluster.getMetadata().getKeyspace(task.getKeyspace());
+        if (keyspaceMetadata == null) {
+            throw new RuntimeException("keyspace `" + task.getKeyspace() + "` is not found");
+        }
+
+        TableMetadata tableMetadata = keyspaceMetadata.getTable(task.getTable());
+        if (tableMetadata == null) {
+            throw new RuntimeException("table `" + task.getTable() + "` is not found");
+        }
+
+        Insert insert = QueryBuilder.insertInto(task.getKeyspace(), task.getTable());
+        if (task.getIfNotExists()) {
+            insert.ifNotExists();
+        }
+        if (task.getTtl().isPresent()) {
+            insert.using(QueryBuilder.ttl(task.getTtl().get()));
+        }
+
+        ImmutableMap.Builder<String, CassandraColumnSetter> columnSettersBuilder = ImmutableMap.builder();
+        ImmutableList.Builder<String> uuidColumnsBuilder = ImmutableList.builder();
+        for (ColumnMetadata column : tableMetadata.getColumns()) {
+            insert.value(column.getName(), QueryBuilder.bindMarker(column.getName()));
+            columnSettersBuilder.put(column.getName(), CassandraColumnSetterFactory.createColumnSetter(column, cluster));
+            switch (column.getType().getName()) {
+                case UUID:
+                case TIMEUUID:
+                    uuidColumnsBuilder.add(column.getName());
+            }
+        }
+        Map<String, CassandraColumnSetter> columnSetters = columnSettersBuilder.build();
+        List<String> uuidColumns = uuidColumnsBuilder.build();
+        List<ColumnSetterVisitor> columnVisitors = Lists.transform(schema.getColumns(), (column) ->
+                new ColumnSetterVisitor(pageReader, columnSetters.get(column.getName())));
+
+        logger.info("Insert Query: {}", insert.getQueryString());
+
+        PreparedStatement prepared = session.prepare(insert);
+        if (task.getIdempotent()) {
+            prepared.setIdempotent(task.getIdempotent());
+        }
+
+        return new PluginPageOuput(cluster, session, pageReader, tableMetadata, uuidColumns, columnSetters, columnVisitors, prepared, task);
+    }
+
+    private Cluster getCluster(PluginTask task)
+    {
+        Cluster.Builder builder = Cluster.builder();
+        for (String host : task.gethosts()) {
+            builder.addContactPointsWithPorts(new InetSocketAddress(host, task.getPort()));
+        }
+
+        if (task.getUsername().isPresent()) {
+            builder.withCredentials(task.getUsername().get(), task.getPassword().orNull());
+        }
+
+        if (task.getClustername().isPresent()) {
+            builder.withClusterName(task.getClustername().get());
+        }
+
+        builder.withSocketOptions(
+                new SocketOptions()
+                        .setConnectTimeoutMillis(task.getConnectTimeout())
+                        .setReadTimeoutMillis(task.getRequestTimeout()));
+
+        return builder.build();
+    }
+
+    public class PluginPageOuput implements TransactionalPageOutput
+    {
+        private final Cluster cluster;
+        private final Session session;
+        private final PageReader pageReader;
+        private final TableMetadata tableMetadata;
+        private final List<String> uuidColumns;
+        private final Map<String, CassandraColumnSetter> columnSetters;
+        private final List<ColumnSetterVisitor> columnVisitors;
+        private final PreparedStatement prepared;
+        private final PluginTask task;
+        private long counter = 0;
+        private long nextLoggingCount = 1;
+
+        public PluginPageOuput(
+                Cluster cluster,
+                Session session,
+                PageReader pageReader,
+                TableMetadata tableMetadata,
+                List<String> uuidColumns,
+                Map<String, CassandraColumnSetter> columnSetters,
+                List<ColumnSetterVisitor> columnVisitors,
+                PreparedStatement prepared,
+                PluginTask task)
+        {
+            this.cluster = cluster;
+            this.session = session;
+            this.pageReader = pageReader;
+            this.tableMetadata = tableMetadata;
+            this.uuidColumns = uuidColumns;
+            this.columnSetters = columnSetters;
+            this.columnVisitors = columnVisitors;
+            this.prepared = prepared;
+            this.task = task;
+        }
+
+        @Override
+        public void add(Page page)
+        {
+            pageReader.setPage(page);
+            while (pageReader.nextRecord()) {
+                BoundStatement statement = prepared.bind();
+
+                for (String uuidColumn : uuidColumns) {
+                    columnSetters.get(uuidColumn).setNullValue(statement);
+                }
+
+                for (int i = 0; i < pageReader.getSchema().getColumns().size(); i++) {
+                    ColumnSetterVisitor visitor = columnVisitors.get(i);
+                    visitor.setStatement(statement);
+                    if (visitor.hasSetter()) {
+                        pageReader.getSchema().getColumn(i).visit(visitor);
+                    }
+                }
+                session.execute(statement);
+                counter++;
+                if (counter >= nextLoggingCount) {
+                    logger.info("Inserted {} records", counter);
+                    nextLoggingCount = nextLoggingCount * 2;
+                }
+            }
+        }
+
+        @Override
+        public void finish()
+        {
+        }
+
+        @Override
+        public void close()
+        {
+            session.close();
+            cluster.close();
+        }
+
+        @Override
+        public void abort()
+        {
+        }
+
+        @Override
+        public TaskReport commit()
+        {
+            TaskReport report = Exec.newTaskReport();
+            report.set("inserted_record_count", counter);
+            return report;
+        }
+    }
+}