embulk-filter-copy 0.0.1

data/example/config.yml

@@ -0,0 +1,28 @@
+in:
+  type: file
+  path_prefix: ./example/data.tsv
+  parser:
+    type: csv
+    delimiter: "\t"
+    skip_header_lines: 0
+    null_string: ""
+    columns:
+      - { name: id, type: long }
+      - { name: description, type: string }
+      - { name: name, type: string }
+      - { name: payload, type: json}
+    stop_on_invalid_record: true
+
+filters:
+  - type: copy
+    config:
+      filters:
+        - type: remove_columns
+          remove: ["id"]
+      out:
+        type: stdout
+      exec:
+        max_threads: 8
+
+out:
+  type: stdout

data/example/data.tsv

@@ -0,0 +1,5 @@
+0	c20ef94602	c212c89f91	{"a":0,"b":"99"}
+1	330a9fc33a	e25b33b616	{"a":1,"b":"a9"}
+2	707b3b7588	90823c6a1f	{"a":2,"b":"96"}
+3	8d8288e66f		{"a":3,"b":"86"}
+4	c54d8b6481	e56a40571c	{"a":4,"b":"d2"}

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Sun Jan 08 00:35:58 PST 2017
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-3.2.1-bin.zip

data/gradlew

@@ -0,0 +1,169 @@
+#!/usr/bin/env bash
+
+##############################################################################
+##
+##  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
+
+# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
+function splitJvmOpts() {
+    JVM_OPTS=("$@")
+}
+eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
+JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [[ "$(uname)" == "Darwin" ]] && [[ "$HOME" == "$PWD" ]]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"

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/filter/copy.rb

@@ -0,0 +1,8 @@
+Embulk::JavaPlugin.register_filter(
+  "copy", "org.embulk.filter.copy.CopyFilterPlugin",
+  File.expand_path('../../../../classpath', __FILE__))
+
+Embulk::JavaPlugin.register_input(
+    "internal_forward",
+    "org.embulk.filter.copy.plugin.InternalForwardInputPlugin",
+    File.expand_path('../../../../classpath', __FILE__))

data/settings.gradle

@@ -0,0 +1 @@
+rootProject.name = 'embulk-filter-copy'

data/src/main/java/org/embulk/filter/copy/CopyFilterPlugin.java

@@ -0,0 +1,149 @@
+package org.embulk.filter.copy;
+
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.filter.copy.forward.InForwardService;
+import org.embulk.filter.copy.forward.OutForwardEventBuilder;
+import org.embulk.filter.copy.forward.OutForwardService;
+import org.embulk.filter.copy.forward.OutForwardVisitor;
+import org.embulk.filter.copy.plugin.InternalForwardInputPlugin;
+import org.embulk.filter.copy.service.EmbulkExecutorService;
+import org.embulk.filter.copy.service.StandardColumnVisitor;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FilterPlugin;
+import org.embulk.spi.Page;
+import org.embulk.spi.PageBuilder;
+import org.embulk.spi.PageOutput;
+import org.embulk.spi.PageReader;
+import org.embulk.spi.Schema;
+import org.embulk.spi.time.TimestampFormatter;
+import org.slf4j.Logger;
+
+import java.util.List;
+
+public class CopyFilterPlugin
+        implements FilterPlugin
+{
+    private final static Logger logger = Exec.getLogger(CopyFilterPlugin.class);
+
+    public interface EmbulkConfig
+            extends Task
+    {
+        @Config("exec")
+        @ConfigDefault("{}")
+        ConfigSource getExecConfig();
+
+        @Config("filters")
+        @ConfigDefault("[]")
+        List<ConfigSource> getFilterConfig();
+
+        @Config("out")
+        ConfigSource getOutputConfig();
+    }
+
+    public interface PluginTask
+            extends Task, TimestampFormatter.Task,
+            OutForwardService.Task, InForwardService.Task
+    {
+        @Config("config")
+        EmbulkConfig getConfig();
+    }
+
+    private ConfigSource configure(PluginTask task, Schema schema)
+    {
+        ConfigSource inputConfig = Exec.newConfigSource();
+        inputConfig.set("type", InternalForwardInputPlugin.PLUGIN_NAME);
+        inputConfig.set("columns", schema);
+        inputConfig.set("message_tag", task.getMessageTag());
+        inputConfig.set("shutdown_tag", task.getShutdownTag());
+        inputConfig.set("in_forward", task.getInForwardTask());
+        inputConfig.set("default_timestamp_format", task.getDefaultTimestampFormat());
+        inputConfig.set("default_timezone", task.getDefaultTimeZone());
+
+        ConfigSource embulkRunConfig = Exec.newConfigSource();
+        embulkRunConfig.set("exec", task.getConfig().getExecConfig());
+        embulkRunConfig.set("in", inputConfig);
+        embulkRunConfig.set("filters", task.getConfig().getFilterConfig());
+        embulkRunConfig.set("out", task.getConfig().getOutputConfig());
+
+        return embulkRunConfig;
+    }
+
+    private void withEmbulkRun(ConfigSource config, Runnable r)
+    {
+        EmbulkExecutorService embulkExecutorService = new EmbulkExecutorService(Exec.getInjector());
+        embulkExecutorService.executeAsync(config);
+
+        r.run();
+
+        embulkExecutorService.waitExecutionFinished();
+        embulkExecutorService.shutdown();
+    }
+
+    @Override
+    public void transaction(ConfigSource config, Schema inputSchema,
+            FilterPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+        ConfigSource embulkRunConfig = configure(task, inputSchema);
+
+        withEmbulkRun(embulkRunConfig, () ->
+        {
+            Schema outputSchema = inputSchema;
+            control.run(task.dump(), outputSchema);
+            OutForwardService.sendShutdownMessage(task);
+        });
+    }
+
+    @Override
+    public PageOutput open(TaskSource taskSource, final Schema inputSchema,
+            final Schema outputSchema, final PageOutput output)
+    {
+        final PluginTask task = taskSource.loadTask(PluginTask.class);
+        TimestampFormatter timestampFormatter = new TimestampFormatter(
+                task.getJRuby(),
+                task.getDefaultTimestampFormat(),
+                task.getDefaultTimeZone());
+
+        return new PageOutput()
+        {
+            private final PageReader pageReader = new PageReader(inputSchema);
+            private final PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
+            private final StandardColumnVisitor standardColumnVisitor = new StandardColumnVisitor(pageReader, pageBuilder);
+            private final OutForwardService outForwardService = new OutForwardService(task);
+            private final OutForwardEventBuilder eventBuilder = new OutForwardEventBuilder(outputSchema, timestampFormatter);
+            private final OutForwardVisitor outForwardVisitor = new OutForwardVisitor(pageReader, eventBuilder);
+
+            @Override
+            public void add(Page page)
+            {
+                pageReader.setPage(page);
+                while (pageReader.nextRecord()) {
+                    outputSchema.visitColumns(outForwardVisitor);
+                    eventBuilder.emitMessage(outForwardService);
+
+                    outputSchema.visitColumns(standardColumnVisitor);
+                    pageBuilder.addRecord();
+                }
+            }
+
+            @Override
+            public void finish()
+            {
+                outForwardService.finish();
+                pageBuilder.finish();
+            }
+
+            @Override
+            public void close()
+            {
+                outForwardService.close();
+                pageBuilder.close();
+            }
+
+        };
+    }
+}