embulk-parser-avro 0.1.0

data/example/.gitignore

@@ -0,0 +1,3 @@
+Gemfile
+Gemfile.lock
+.bundle

data/example/example.yml

@@ -0,0 +1,22 @@
+in:
+  type: file
+  path_prefix: "items"
+  parser:
+    type: avro
+    avsc : "./item.avsc"
+    columns:
+      - {name: "id", type: "long"}
+      - {name: "code", type: "string"}
+      - {name: "name", type: "string"}
+      - {name: "description", type: "string"}
+      - {name: "flag", type: "boolean"}
+      - {name: "price", type: "long"}
+      - {name: "item_type", type: "string"}
+      - {name: "tags", type: "json"}
+      - {name: "options", type: "json"}
+      - {name: "spec", type: "json"}
+      - {name: "created_at", type: "timestamp", format: "%Y-%m-%dT%H:%M:%S%:z"}
+      - {name: "created_at_utc", type: "timestamp"}
+
+out:
+  type: stdout

data/example/generate.rb

@@ -0,0 +1,94 @@
+require 'avro'
+require 'time'
+
+file = File.open('items.avro', 'wb')
+
+schema = Avro::Schema.parse(File.open("item.avsc", "rb").read)
+
+writer = Avro::IO::DatumWriter.new(schema)
+
+dw = Avro::DataFile::Writer.new(file, writer, schema)
+
+dw << {
+  "id" => 1,
+  "code" => 123456789012345678,
+  "name" => "Desktop",
+  "description" => "Office and Personal Usage",
+  "flag" => true,
+  "created_at" => Time.now.iso8601,
+  "created_at_utc" => Time.now.to_f,
+  "spec" => {"key" => "opt1", "value" => "optvalue1"},
+  "tags" => ["tag1", "tag2"],
+  "price" => 30000,
+  "options" => {"foo" => "bar", "hoge" => nil},
+  "item_type" => "D",
+  "dummy" => nil,
+}
+dw << {
+  "id" => 2,
+  "code" => 123456789012345679,
+  "name" => "Laptop",
+  "flag" => false,
+  "created_at" => Time.now.iso8601,
+  "created_at_utc" => Time.now.to_f,
+  "spec" => {"key" => "opt1", "value" => nil},
+  "price" => 50000,
+  "options" => {},
+  "item_type" => "M",
+}
+dw << {
+  "id" => 3,
+  "code" => 123456789012345680,
+  "name" => "Tablet",
+  "description" => "Personal Usage",
+  "flag" => true,
+  "created_at" => Time.now.iso8601,
+  "created_at_utc" => Time.now.to_f,
+  "tags" => ["tag3"],
+  "spec" => {"key" => "opt1", "value" => "optvalue1"},
+  "options" => {},
+  "item_type" => "M",
+}
+dw << {
+  "id" => 4,
+  "code" => 123456789012345681,
+  "name" => "Mobile",
+  "description" => "Personal Usage",
+  "flag" => true,
+  "created_at" => Time.now.iso8601,
+  "created_at_utc" => Time.now.to_f,
+  "spec" => {"key" => "opt1", "value" => "optvalue1"},
+  "tags" => [],
+  "price" => 10000,
+  "options" => {},
+  "item_type" => "M",
+}
+dw << {
+  "id" => 5,
+  "code" => 123456789012345682,
+  "name" => "Notepad",
+  "flag" => true,
+  "created_at" => Time.now.iso8601,
+  "created_at_utc" => Time.now.to_f,
+  "spec" => {"key" => "opt1", "value" => "optvalue1"},
+  "tags" => ["tag1", "tag2"],
+  "price" => 20000,
+  "options" => {},
+  "item_type" => "M",
+}
+dw << {
+  "id" => 6,
+  "code" => 123456789012345683,
+  "name" => "SmartPhone",
+  "description" => "Multipurpose",
+  "flag" => true,
+  "created_at" => Time.now.iso8601,
+  "created_at_utc" => Time.now.to_f,
+  "spec" => {"key" => "opt1", "value" => "optvalue1"},
+  "tags" => ["tag1", "tag2"],
+  "price" => 40000,
+  "options" => {},
+  "item_type" => "M",
+}
+
+dw.close

data/example/item.avsc

@@ -0,0 +1,27 @@
+{
+  "type" : "record",
+  "name" : "Item",
+  "namespace" : "example.avro",
+  "fields" : [
+    {"name": "id", "type": "int"},
+    {"name": "code", "type": "long"},
+    {"name": "name", "type": "string"},
+    {"name": "description", "type": ["string", "null"]},
+    {"name": "flag", "type": "boolean"},
+    {"name": "created_at", "type": "string"},
+    {"name": "created_at_utc", "type": "float"},
+    {"name": "price", "type": ["double", "null"]},
+    {"name": "spec", "type": {
+      "type": "record",
+      "name": "item_spec",
+      "fields" : [
+        {"name" : "key", "type" : "string"},
+        {"name" : "value", "type" : ["string", "null"]}
+      ]}
+    },
+    {"name": "tags", "type": [{"type": "array", "items": "string"}, "null"]},
+    {"name": "options", "type": {"type": "map", "values": ["string", "null"]}},
+    {"name": "item_type", "type": {"name": "item_type_enum", "type": "enum", "symbols": ["D", "M"]}},
+    {"name": "dummy", "type": "null"}
+  ]
+}

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Jan 13 12:41:02 JST 2016
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.10-bin.zip

data/gradlew

@@ -0,0 +1,160 @@
+#!/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
+
+# 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 "$SAVED" >/dev/null
+
+CLASSPATH=$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 "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$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=$APP_BASE_NAME"
+
+exec "$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/guess/avro.rb

@@ -0,0 +1,61 @@
+module Embulk
+  module Guess
+
+    # TODO implement guess plugin to make this command work:
+    #      $ embulk guess -g "avro" partial-config.yml
+    #
+    #      Depending on the file format the plugin uses, you can use choose
+    #      one of binary guess (GuessPlugin), text guess (TextGuessPlugin),
+    #      or line guess (LineGuessPlugin).
+
+    #class Avro < GuessPlugin
+    #  Plugin.register_guess("avro", self)
+    #
+    #  def guess(config, sample_buffer)
+    #    if sample_buffer[0,2] == GZIP_HEADER
+    #      guessed = {}
+    #      guessed["type"] = "avro"
+    #      guessed["property1"] = "guessed-value"
+    #      return {"parser" => guessed}
+    #    else
+    #      return {}
+    #    end
+    #  end
+    #end
+
+    #class Avro < TextGuessPlugin
+    #  Plugin.register_guess("avro", self)
+    #
+    #  def guess_text(config, sample_text)
+    #    js = JSON.parse(sample_text) rescue nil
+    #    if js && js["mykeyword"] == "keyword"
+    #      guessed = {}
+    #      guessed["type"] = "avro"
+    #      guessed["property1"] = "guessed-value"
+    #      return {"parser" => guessed}
+    #    else
+    #      return {}
+    #    end
+    #  end
+    #end
+
+    #class Avro < LineGuessPlugin
+    #  Plugin.register_guess("avro", self)
+    #
+    #  def guess_lines(config, sample_lines)
+    #    all_line_matched = sample_lines.all? do |line|
+    #      line =~ /mypattern/
+    #    end
+    #    if all_line_matched
+    #      guessed = {}
+    #      guessed["type"] = "avro"
+    #      guessed["property1"] = "guessed-value"
+    #      return {"parser" => guessed}
+    #    else
+    #      return {}
+    #    end
+    #  end
+    #end
+
+  end
+end