embulk 0.1.0

data/embulk-standards/src/test/java/org/embulk/standards/TestS3FileInputPlugin.java

@@ -0,0 +1,43 @@
+package org.embulk.standards;
+
+import static org.junit.Assert.*;
+
+import java.util.List;
+
+import org.junit.Test;
+import org.mockito.Mockito;
+
+import com.amazonaws.services.s3.AmazonS3Client;
+import com.amazonaws.services.s3.model.ListObjectsRequest;
+import com.amazonaws.services.s3.model.ObjectListing;
+import com.amazonaws.services.s3.model.S3ObjectSummary;
+import com.google.common.collect.ImmutableList;
+
+public class TestS3FileInputPlugin
+{
+    @Test
+    public void listS3FilesByPrefix()
+    {
+        // AWSS3Client returns list1 for the first iteration and list2 next.
+        List<S3ObjectSummary> list1 = ImmutableList.<S3ObjectSummary> of(bucket("in/", 0), bucket("in/file/", 0),
+                bucket("in/file/sample.csv.gz", 12345));
+        List<S3ObjectSummary> list2 = ImmutableList.<S3ObjectSummary> of(bucket("sample2.csv.gz", 0));
+        ObjectListing ol = Mockito.mock(ObjectListing.class);
+
+        Mockito.doReturn(list1).doReturn(list2).when(ol).getObjectSummaries();
+        AmazonS3Client client = Mockito.mock(AmazonS3Client.class);
+        Mockito.doReturn(ol).when(client).listObjects(Mockito.any(ListObjectsRequest.class));
+        Mockito.doReturn("in/file/").doReturn(null).when(ol).getNextMarker();
+
+        // It counts only size != 0 files.
+        assertEquals(1, S3FileInputPlugin.listS3FilesByPrefix(client, "bucketName", "prefix").size());
+    }
+
+    private S3ObjectSummary bucket(String key, long size)
+    {
+        S3ObjectSummary bucket = new S3ObjectSummary();
+        bucket.setKey(key);
+        bucket.setSize(size);
+        return bucket;
+    }
+}

data/embulk.gemspec

@@ -0,0 +1,27 @@
+$LOAD_PATH.push File.expand_path("../lib", __FILE__)
+require 'embulk/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "embulk"
+  gem.version       = Embulk::VERSION
+
+  gem.summary       = %q{Embulk, a plugin-based parallel bulk data loader}
+  gem.description   = %q{Embulk is an open-source, plugin-based bulk data loader to scale and simplify data management across heterogeneous data stores. It can collect and ship any kinds of data in high throughput with transaction control.}
+  gem.authors       = ["Sadayuki Furuhashi"]
+  gem.email         = ["frsyuki@gmail.com"]
+  gem.license       = "Apache 2.0"
+  gem.homepage      = "https://github.com/embulk/embulk"
+
+  gem.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.require_paths = ["lib"]
+  gem.has_rdoc      = false
+
+  gem.add_development_dependency 'bundler', ['>= 1.0']
+  gem.add_development_dependency 'rake', ['>= 0.10.0']
+  gem.add_development_dependency 'rspec', ['~> 2.11']
+  gem.add_development_dependency 'json', ['~> 1.7']
+  gem.add_development_dependency 'yard', ['~> 0.8.7']
+  gem.add_development_dependency 'kramdown', ['~> 1.5.0']
+end

data/examples/config.yml

@@ -0,0 +1,34 @@
+#exec:
+#  transaction_time: 2015-01-17 00:00:00 UTC
+#  transaction_timezone: UTC
+in:
+  type: file
+  paths:
+    - examples/csv/
+  #parser:
+  #  type: csv
+  #  newline: LF
+  #  columns:
+  #    - {name: date_code, type: string}
+  #    - {name: customer_code, type: long}
+  #    - {name: product_code, type: string}
+  #    - {name: employee_code, type: string}
+  #  file_decoders:
+  #    - type: gzip
+out:
+  type: file
+  directory: tmp/
+  file_name: output
+  file_ext: csv
+  #encoders:
+  #  - type: gzip
+  #    level: 9
+  formatter:
+    type: csv
+    timezone: Etc/UTC
+#in:
+#  type: file
+#  paths:
+#    - benchmark/
+#out:
+#  type: "null"

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Jan 21 18:25:48 PST 2015
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.1-bin.zip

data/gradlew

@@ -0,0 +1,164 @@
+#!/usr/bin/env bash
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn ( ) {
+    echo "$*"
+}
+
+die ( ) {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+esac
+
+# For Cygwin, ensure paths are in UNIX format before anything is touched.
+if $cygwin ; then
+    [ -n "$JAVA_HOME" ] && JAVA_HOME=`cygpath --unix "$JAVA_HOME"`
+fi
+
+# 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\"`/" >&-
+APP_HOME="`pwd -P`"
+cd "$SAVED" >&-
+
+CLASSPATH=$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" ] ; 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"`
+
+    # 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=$APP_BASE_NAME"
+
+exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"

data/gradlew.bat

@@ -0,0 +1,90 @@
+@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
+
+@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=
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@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 Windowz variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+if "%@eval[2+2]" == "4" goto 4NT_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=%*
+goto execute
+
+:4NT_args
+@rem Get arguments from the 4NT Shell from JP Software
+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.rb

@@ -0,0 +1,16 @@
+module Embulk
+  if RUBY_PLATFORM =~ /java/i
+    def self.java?
+      true
+    end
+  else
+    def self.java?
+      false
+    end
+  end
+
+  require 'embulk/error'
+  require 'embulk/plugin'
+  require 'embulk/buffer'
+  require 'embulk/data_source'
+end

data/lib/embulk/buffer.rb

@@ -0,0 +1,17 @@
+
+module Embulk
+  class Buffer < String
+    if Embulk.java?
+      def self.from_java_object(java_buffer)
+        byte_list = org.jruby.util.ByteList.new(java_buffer.array(), java_buffer.offset(), java_buffer.limit(), false)
+        buffer = new
+        buffer.replace(org.jruby.RubyString.new(JRuby.runtime, self, byte_list).dup)  # TODO simplify
+        buffer
+      end
+
+      def java_object
+        Java::Buffer.wrap(to_java_bytes)
+      end
+    end
+  end
+end

data/lib/embulk/column.rb

@@ -0,0 +1,47 @@
+module Embulk
+
+  class Column < Struct.new(:index, :name, :type)
+    def initialize(index, name, type)
+      super(index, name, type)
+    end
+
+    if Embulk.java?
+      def self.from_java_object(java_column)
+        Column.new(
+          java_column.getIndex,
+          java_column.getName,
+          Type.from_java_object(java_column.getType))
+      end
+
+      def java_object
+        Java::Column.new(index, name, Type.to_java_object(type))
+      end
+    end
+  end
+
+  module Type
+    if Embulk.java?
+      def self.from_java_object(java_type)
+        java_type.getName.to_sym
+      end
+
+      def self.to_java_object(ruby_type)
+        case ruby_type
+        when :boolean
+          Java::Types::BOOLEAN
+        when :long
+          Java::Types::LONG
+        when :double
+          Java::Types::DOUBLE
+        when :string
+          Java::Types::STRING
+        when :timestamp
+          Java::Types::TIMESTAMP
+        else
+          raise ArgumentError, "Unknown type #{ruby_type.inspect}: supported types are :boolean, :long, :double, :string and :timestamp"
+        end
+      end
+    end
+  end
+
+end