embulk-parser-fluentd_out_file 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 48966ba24342b8320ac3159b13b4af1fe6615caa
+  data.tar.gz: 69cef7b3f095cc9a5daa0aa09fce75695393debe
+SHA512:
+  metadata.gz: 3a6c1bae339f8243bc8a65f15e2dfb8ebbf2072d7e5219ac8a08379c00cf0f5ab510598bff5365f5126f24e4bf2fca017b8ccda8e2f493bae7b441987c21a559
+  data.tar.gz: 33d84958e409618ae4278bbef8c49c7dcff1bec6ef3ac1f1a7306add3c501e448879aad9cd346f7cc45932de245abea8ee1d3814d36093cb2861252f2c7d1f8d

data/.gitignore

@@ -0,0 +1,8 @@
+*.class
+*~
+*.iml
+.idea
+build/
+/classpath/
+/.gradle
+/pkg/

data/.travis.yml

@@ -0,0 +1,7 @@
+language: java
+jdk: oraclejdk7
+
+script: ./gradlew clean test
+
+after_success:
+- ./gradlew check jacocoRootReport

data/CHANGELOG.md

@@ -0,0 +1,3 @@
+## 0.1.0 - 2016-03-19
+
+The first release

data/README.md

@@ -0,0 +1,47 @@
+# Fluentd Out File parser plugin for Embulk
+
+This plugin parses fluentd's out_file formatted files.
+http://docs.fluentd.org/articles/out_file
+
+## Overview
+
+* **Plugin type**: parser
+* **Guess supported**: yes
+
+## Configuration
+
+- **delimiter**: Delimiter character such as \t (string, required)
+- **columns**: Columns (hash, required)
+
+## Example
+
+```yaml
+in:
+  type: any file input plugin type
+  parser:
+    type: fluentd_out_file
+    delimiter: "\t"
+    columns:
+    - {name: time, type: timestamp, format: '%Y-%m-%dT%H:%M:%S%:z'}
+    - {name: tag, type: string}
+    - {name: record, type: json}
+```
+
+(If guess supported) you don't have to write `parser:` section in the configuration file. After writing `in:` section, you can let embulk guess `parser:` section using this command:
+
+```
+$ embulk gem install embulk-parser-fluentd_out_file
+$ embulk guess -g fluentd_out_file config.yml -o guessed.yml
+```
+
+## Build
+
+```
+$ ./gradlew gem  # -t to watch change of files and rebuild continuously
+```
+
+## Test
+
+```
+$ ./gradlew clean test jacocoTestReport
+```

data/build.gradle

@@ -0,0 +1,97 @@
+plugins {
+    id "com.jfrog.bintray" version "1.1"
+    id "com.github.jruby-gradle.base" version "0.1.5"
+    id "java"
+    id "checkstyle"
+    id "jacoco"
+}
+import com.github.jrubygradle.JRubyExec
+repositories {
+    mavenCentral()
+    jcenter()
+}
+configurations {
+    provided
+}
+
+version = "0.1.0"
+
+compileJava.options.encoding = 'UTF-8' // source encoding
+sourceCompatibility = 1.7
+targetCompatibility = 1.7
+
+dependencies {
+    compile  "org.embulk:embulk-core:0.8.8"
+    provided "org.embulk:embulk-core:0.8.8"
+
+    testCompile "junit:junit:4.+"
+    testCompile  "org.embulk:embulk-core:0.8.8:tests"
+    testCompile  "org.embulk:embulk-standards:0.8.8"
+}
+
+task classpath(type: Copy, dependsOn: ["jar"]) {
+    doFirst { file("classpath").deleteDir() }
+    from (configurations.runtime - configurations.provided + files(jar.archivePath))
+    into "classpath"
+}
+clean { delete "classpath" }
+
+checkstyle {
+    configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
+    toolVersion = '6.14.1'
+}
+checkstyleMain {
+    configFile = file("${project.rootDir}/config/checkstyle/default.xml")
+    ignoreFailures = true
+}
+checkstyleTest {
+    configFile = file("${project.rootDir}/config/checkstyle/default.xml")
+    ignoreFailures = true
+}
+task checkstyle(type: Checkstyle) {
+    classpath = sourceSets.main.output + sourceSets.test.output
+    source = sourceSets.main.allJava + sourceSets.test.allJava
+}
+
+task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
+    jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
+    script "${project.name}.gemspec"
+    doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
+}
+
+task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
+    jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
+    script "pkg/${project.name}-${project.version}.gem"
+}
+
+task "package"(dependsOn: ["gemspec", "classpath"]) << {
+    println "> Build succeeded."
+    println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
+}
+
+task gemspec {
+    ext.gemspecFile = file("${project.name}.gemspec")
+    inputs.file "build.gradle"
+    outputs.file gemspecFile
+    doLast { gemspecFile.write($/
+Gem::Specification.new do |spec|
+  spec.name          = "${project.name}"
+  spec.version       = "${project.version}"
+  spec.authors       = ["Muga Nishizawa"]
+  spec.summary       = %[Fluentd Out File parser plugin for Embulk]
+  spec.description   = %[Parses Fluentd Out File files read by other file input plugins.]
+  spec.email         = ["muga.nishizawa@gmail.com"]
+  spec.licenses      = ["Apache 2.0"]
+  spec.homepage      = "https://github.com/muga/embulk-parser-fluentd_out_file"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['>= 10.0']
+end
+/$)
+    }
+}
+clean { delete "${project.name}.gemspec" }

data/config/checkstyle/checkstyle.xml

@@ -0,0 +1,128 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE module PUBLIC
+        "-//Puppy Crawl//DTD Check Configuration 1.3//EN"
+        "http://www.puppycrawl.com/dtds/configuration_1_3.dtd">
+<module name="Checker">
+    <!-- https://github.com/facebook/presto/blob/master/src/checkstyle/checks.xml -->
+    <module name="FileTabCharacter"/>
+    <module name="NewlineAtEndOfFile">
+        <property name="lineSeparator" value="lf"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\r"/>
+        <property name="message" value="Line contains carriage return"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value=" \n"/>
+        <property name="message" value="Line has trailing whitespace"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\{\n\n"/>
+        <property name="message" value="Blank line after opening brace"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\n\n\s*\}"/>
+        <property name="message" value="Blank line before closing brace"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\n\n\n"/>
+        <property name="message" value="Multiple consecutive blank lines"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\n\n\Z"/>
+        <property name="message" value="Blank line before end of file"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="Preconditions\.checkNotNull"/>
+        <property name="message" value="Use of checkNotNull"/>
+    </module>
+
+    <module name="TreeWalker">
+        <module name="EmptyBlock">
+            <property name="option" value="text"/>
+            <property name="tokens" value="
+                LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_IF,
+                LITERAL_FOR, LITERAL_TRY, LITERAL_WHILE, INSTANCE_INIT, STATIC_INIT"/>
+        </module>
+        <module name="EmptyStatement"/>
+        <module name="EmptyForInitializerPad"/>
+        <module name="EmptyForIteratorPad">
+            <property name="option" value="space"/>
+        </module>
+        <module name="MethodParamPad">
+            <property name="allowLineBreaks" value="true"/>
+            <property name="option" value="nospace"/>
+        </module>
+        <module name="ParenPad"/>
+        <module name="TypecastParenPad"/>
+        <module name="NeedBraces"/>
+        <module name="LeftCurly">
+            <property name="option" value="nl"/>
+            <property name="tokens" value="CLASS_DEF, CTOR_DEF, INTERFACE_DEF, METHOD_DEF"/>
+        </module>
+        <module name="LeftCurly">
+            <property name="option" value="eol"/>
+            <property name="tokens" value="
+                 LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_FOR,
+                 LITERAL_IF, LITERAL_SWITCH, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE"/>
+        </module>
+        <module name="RightCurly">
+            <property name="option" value="alone"/>
+        </module>
+        <module name="GenericWhitespace"/>
+        <module name="WhitespaceAfter"/>
+        <module name="NoWhitespaceBefore"/>
+
+        <module name="UpperEll"/>
+        <module name="DefaultComesLast"/>
+        <module name="ArrayTypeStyle"/>
+        <module name="MultipleVariableDeclarations"/>
+        <module name="ModifierOrder"/>
+        <module name="OneStatementPerLine"/>
+        <module name="StringLiteralEquality"/>
+        <module name="MutableException"/>
+        <module name="EqualsHashCode"/>
+        <module name="InnerAssignment"/>
+        <module name="InterfaceIsType"/>
+        <module name="HideUtilityClassConstructor"/>
+
+        <module name="MemberName"/>
+        <module name="LocalVariableName"/>
+        <module name="LocalFinalVariableName"/>
+        <module name="TypeName"/>
+        <module name="PackageName"/>
+        <module name="ParameterName"/>
+        <module name="StaticVariableName"/>
+        <module name="ClassTypeParameterName">
+            <property name="format" value="^[A-Z][0-9]?$"/>
+        </module>
+        <module name="MethodTypeParameterName">
+            <property name="format" value="^[A-Z][0-9]?$"/>
+        </module>
+
+        <module name="AvoidStarImport"/>
+        <module name="RedundantImport"/>
+        <module name="UnusedImports"/>
+        <module name="ImportOrder">
+            <property name="groups" value="*,javax,java"/>
+            <property name="separated" value="true"/>
+            <property name="option" value="bottom"/>
+            <property name="sortStaticImportsAlphabetically" value="true"/>
+        </module>
+
+        <module name="WhitespaceAround">
+            <property name="allowEmptyConstructors" value="true"/>
+            <property name="allowEmptyMethods" value="true"/>
+            <property name="ignoreEnhancedForColon" value="false"/>
+            <property name="tokens" value="
+                ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN,
+                BXOR, BXOR_ASSIGN, COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LE,
+                LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
+                LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN,
+                LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE,
+                LOR, LT, MINUS, MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL,
+                PLUS, PLUS_ASSIGN, QUESTION, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN,
+                STAR, STAR_ASSIGN, TYPE_EXTENSION_AND"/>
+        </module>
+    </module>
+</module>

data/config/checkstyle/default.xml

@@ -0,0 +1,108 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE module PUBLIC
+        "-//Puppy Crawl//DTD Check Configuration 1.3//EN"
+        "http://www.puppycrawl.com/dtds/configuration_1_3.dtd">
+<!--
+     This is a subset of ./checkstyle.xml which allows some loose styles
+-->
+<module name="Checker">
+    <module name="FileTabCharacter"/>
+    <module name="NewlineAtEndOfFile">
+        <property name="lineSeparator" value="lf"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\r"/>
+        <property name="message" value="Line contains carriage return"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value=" \n"/>
+        <property name="message" value="Line has trailing whitespace"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\n\n\n"/>
+        <property name="message" value="Multiple consecutive blank lines"/>
+    </module>
+    <module name="RegexpMultiline">
+        <property name="format" value="\n\n\Z"/>
+        <property name="message" value="Blank line before end of file"/>
+    </module>
+
+    <module name="TreeWalker">
+        <module name="EmptyBlock">
+            <property name="option" value="text"/>
+            <property name="tokens" value="
+                LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_IF,
+                LITERAL_FOR, LITERAL_TRY, LITERAL_WHILE, INSTANCE_INIT, STATIC_INIT"/>
+        </module>
+        <module name="EmptyStatement"/>
+        <module name="EmptyForInitializerPad"/>
+        <module name="EmptyForIteratorPad">
+            <property name="option" value="space"/>
+        </module>
+        <module name="MethodParamPad">
+            <property name="allowLineBreaks" value="true"/>
+            <property name="option" value="nospace"/>
+        </module>
+        <module name="ParenPad"/>
+        <module name="TypecastParenPad"/>
+        <module name="NeedBraces"/>
+        <module name="LeftCurly">
+            <property name="option" value="nl"/>
+            <property name="tokens" value="CLASS_DEF, CTOR_DEF, INTERFACE_DEF, METHOD_DEF"/>
+        </module>
+        <module name="LeftCurly">
+            <property name="option" value="eol"/>
+            <property name="tokens" value="
+                 LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_FOR,
+                 LITERAL_IF, LITERAL_SWITCH, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE"/>
+        </module>
+        <module name="RightCurly">
+            <property name="option" value="alone"/>
+        </module>
+        <module name="GenericWhitespace"/>
+        <module name="WhitespaceAfter"/>
+        <module name="NoWhitespaceBefore"/>
+
+        <module name="UpperEll"/>
+        <module name="DefaultComesLast"/>
+        <module name="ArrayTypeStyle"/>
+        <module name="MultipleVariableDeclarations"/>
+        <module name="ModifierOrder"/>
+        <module name="OneStatementPerLine"/>
+        <module name="StringLiteralEquality"/>
+        <module name="MutableException"/>
+        <module name="EqualsHashCode"/>
+        <module name="InnerAssignment"/>
+        <module name="InterfaceIsType"/>
+        <module name="HideUtilityClassConstructor"/>
+
+        <module name="MemberName"/>
+        <module name="LocalVariableName"/>
+        <module name="LocalFinalVariableName"/>
+        <module name="TypeName"/>
+        <module name="PackageName"/>
+        <module name="ParameterName"/>
+        <module name="StaticVariableName"/>
+        <module name="ClassTypeParameterName">
+            <property name="format" value="^[A-Z][0-9]?$"/>
+        </module>
+        <module name="MethodTypeParameterName">
+            <property name="format" value="^[A-Z][0-9]?$"/>
+        </module>
+
+        <module name="WhitespaceAround">
+            <property name="allowEmptyConstructors" value="true"/>
+            <property name="allowEmptyMethods" value="true"/>
+            <property name="ignoreEnhancedForColon" value="false"/>
+            <property name="tokens" value="
+                ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN,
+                BXOR, BXOR_ASSIGN, COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LE,
+                LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
+                LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN,
+                LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE,
+                LOR, LT, MINUS, MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL,
+                PLUS, PLUS_ASSIGN, QUESTION, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN,
+                STAR, STAR_ASSIGN, TYPE_EXTENSION_AND"/>
+        </module>
+    </module>
+</module>

data/embulk-parser-fluentd_out_file.gemspec

@@ -0,0 +1,18 @@
+
+Gem::Specification.new do |spec|
+  spec.name          = "embulk-parser-fluentd_out_file"
+  spec.version       = "0.1.0"
+  spec.authors       = ["Muga Nishizawa"]
+  spec.summary       = %[Fluentd Out File parser plugin for Embulk]
+  spec.description   = %[Parses Fluentd Out File files read by other file input plugins.]
+  spec.email         = ["muga.nishizawa@gmail.com"]
+  spec.licenses      = ["Apache 2.0"]
+  spec.homepage      = "https://github.com/muga/embulk-parser-fluentd_out_file"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['>= 10.0']
+end

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/fluentd_out_file.rb

@@ -0,0 +1,97 @@
+module Embulk
+  module Guess
+    require 'embulk/guess/schema_guess'
+
+    class FluentdOutFileGuessPlugin < LineGuessPlugin
+      Plugin.register_guess("fluentd_out_file", self)
+
+      DELIMITER_CANDIDATES = [
+        "\t", ",", "|"
+      ]
+
+      def guess_lines(config, sample_lines)
+        return {} unless config.fetch("parser", {}).fetch("type", "fluentd_out_file") == "fluentd_out_file"
+
+        parser_config = config["parser"] || {}
+
+        # guess delimiter
+        if parser_config["type"] == "fluentd_out_file" && parser_config["delimiter"]
+          delim = parser_config["delimiter"]
+        else
+          delim = guess_delimiter(sample_lines)
+          unless delim
+            # not fluentd_out_file file
+            return {}
+          end
+        end
+
+        parser_guessed = DataSource.new.merge(parser_config).merge({"type" => "fluentd_out_file", "delimiter" => delim})
+
+        # guess schema
+        sample_records = sample_lines.map {|line| line.split(delim)}
+        column_types = SchemaGuess.types_from_array_records(sample_records || [])
+        if column_types.size > 3
+          # not fluentd_out_file file
+          return {}
+        end
+        schema = []
+        column_types.each do |type|
+          if type.is_a?(SchemaGuess::TimestampTypeMatch)
+            schema << {"name" => "time", "type" => type, "format" => type.format}
+          elsif type == "string"
+            schema << {"name" => "tag", "type" => type}
+          elsif type == "json"
+            schema << {"name" => "record", "type" => type}
+          else
+            # not fluentd_out_file file
+            return {}
+          end
+        end
+        parser_guessed["columns"] = schema
+
+        return {"parser" => parser_guessed}
+      end
+
+      private # ported from csv_guess.rb temporarily
+
+      def guess_delimiter(sample_lines)
+        delim_weights = DELIMITER_CANDIDATES.map do |d|
+          counts = sample_lines.map {|line| line.count(d) }
+          total = array_sum(counts)
+          if total > 0
+            stddev = array_standard_deviation(counts)
+            stddev = 0.000000001 if stddev == 0.0
+            weight = total / stddev
+            [d, weight]
+          else
+            [nil, 0]
+          end
+        end
+
+        delim, weight = *delim_weights.sort_by {|d,weight| weight }.last
+        if delim != nil && weight > 1
+          return delim
+        else
+          return nil
+        end
+      end
+
+      def array_sum(array)
+        array.inject(0) {|r,i| r += i }
+      end
+
+      def array_avg(array)
+        array.inject(0.0) {|r,i| r += i } / array.size
+      end
+
+      def array_variance(array)
+        avg = array_avg(array)
+        array.inject(0.0) {|r,i| r += (i - avg) ** 2 } / array.size
+      end
+
+      def array_standard_deviation(array)
+        Math.sqrt(array_variance(array))
+      end
+    end
+  end
+end

data/lib/embulk/parser/fluentd_out_file.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_parser(
+  "fluentd_out_file", "org.embulk.parser.fluentd_out_file.FluentdOutFileParserPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/parser/fluentd_out_file/FluentdOutFileParserPlugin.java

@@ -0,0 +1,178 @@
+package org.embulk.parser.fluentd_out_file;
+
+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.spi.Column;
+import org.embulk.spi.DataException;
+import org.embulk.spi.Exec;
+import org.embulk.spi.PageBuilder;
+import org.embulk.spi.ParserPlugin;
+import org.embulk.spi.FileInput;
+import org.embulk.spi.PageOutput;
+import org.embulk.spi.Schema;
+import org.embulk.spi.SchemaConfig;
+import org.embulk.spi.SchemaConfigException;
+import org.embulk.spi.json.JsonParseException;
+import org.embulk.spi.json.JsonParser;
+import org.embulk.spi.time.Timestamp;
+import org.embulk.spi.time.TimestampParseException;
+import org.embulk.spi.time.TimestampParser;
+import org.embulk.spi.type.Types;
+import org.embulk.spi.util.LineDecoder;
+import org.embulk.spi.util.Timestamps;
+import org.msgpack.value.Value;
+import org.slf4j.Logger;
+
+public class FluentdOutFileParserPlugin
+        implements ParserPlugin
+{
+    // @see http://docs.fluentd.org/articles/out_file#format
+
+    public interface PluginTask
+            extends Task, LineDecoder.DecoderTask, TimestampParser.Task
+    {
+        @Config("delimiter")
+        @ConfigDefault("\"\\t\"")
+        char getDelimiterChar();
+
+        @Config("columns")
+        SchemaConfig getSchemaConfig();
+    }
+
+    private final Logger log;
+
+    public FluentdOutFileParserPlugin()
+    {
+        log = Exec.getLogger(FluentdOutFileParserPlugin.class);
+    }
+
+    @Override
+    public void transaction(ConfigSource config, ParserPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        Schema schema = task.getSchemaConfig().toSchema();
+        validateSchema(schema);
+
+        control.run(task.dump(), schema);
+    }
+
+    private void validateSchema(Schema schema)
+    {
+        if (schema.getColumnCount() > 3) {
+            throw new SchemaConfigException("The size of columns must not be greater than 3: " + schema.getColumnCount());
+        }
+
+        for (Column column : schema.getColumns()) {
+            if (!column.getType().equals(Types.TIMESTAMP) &&
+                    !column.getType().equals(Types.STRING) &&
+                    !column.getType().equals(Types.JSON)) {
+                throw new SchemaConfigException("columns must not include 'long' and 'double' types.");
+            }
+        }
+    }
+
+    @Override
+    public void run(TaskSource taskSource, Schema schema,
+            FileInput input, PageOutput output)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+        final char delimiter = task.getDelimiterChar();
+
+        final TimestampParser[] timestampParsers = Timestamps.newTimestampColumnParsers(task, task.getSchemaConfig());
+        final JsonParser jsonParser = new JsonParser();
+
+        long lineNumber;
+        int linePos;
+        String line;
+        int columnIndex;
+
+        try (final PageBuilder pageBuilder = newPageBuilder(schema, output);
+                final LineDecoder decoder = new LineDecoder(input, task)) {
+            while (decoder.nextFile()) {
+                lineNumber = 0;
+
+                while ((line = decoder.poll()) != null) {
+                    lineNumber++;
+                    linePos = 0;
+                    columnIndex = 0;
+
+                    try {
+                        // parse time
+                        if (isTimestampType(schema.getColumn(columnIndex))) {
+                            Column column = schema.getColumn(columnIndex);
+
+                            int i = indexOf(delimiter, linePos, line);
+                            Timestamp timestamp = timestampParsers[column.getIndex()].parse(line.substring(linePos, i));
+                            pageBuilder.setTimestamp(column, timestamp);
+
+                            linePos = i + 1;
+                            columnIndex += 1;
+                        }
+
+                        // parse tag
+                        if (isStringType(schema.getColumn(columnIndex))) {
+                            Column column = schema.getColumn(columnIndex);
+
+                            int i = indexOf(delimiter, linePos, line);
+                            pageBuilder.setString(column, line.substring(linePos, i));
+
+                            linePos = i + 1;
+                            columnIndex += 1;
+                        }
+
+                        // parse record
+                        Column column = schema.getColumn(columnIndex);
+                        Value value = jsonParser.parse(line.substring(linePos));
+
+                        pageBuilder.setJson(column, value);
+
+                        pageBuilder.addRecord();
+                    }
+                    catch (FluentdOutFileRecordValidateException | StringIndexOutOfBoundsException |
+                            TimestampParseException | JsonParseException e) {
+                        log.warn(String.format("Skipped record %d (%s): %s", lineNumber, e.getMessage(), line));
+                    }
+                }
+            }
+
+            pageBuilder.finish();
+        }
+    }
+
+    private PageBuilder newPageBuilder(Schema schema, PageOutput output)
+    {
+        return new PageBuilder(Exec.getBufferAllocator(), schema, output);
+    }
+
+    private static boolean isTimestampType(Column column)
+    {
+        return column.getType().equals(Types.TIMESTAMP);
+    }
+
+    private static boolean isStringType(Column column)
+    {
+        return column.getType().equals(Types.STRING);
+    }
+
+    private static int indexOf(char c, int fromPos, String inLine)
+    {
+        int i = inLine.indexOf(c, fromPos);
+        if (i < 0) {
+            throw new FluentdOutFileRecordValidateException("Too few columns");
+        }
+        return i;
+    }
+
+    static class FluentdOutFileRecordValidateException
+            extends DataException
+    {
+        FluentdOutFileRecordValidateException(String message)
+        {
+            super(message);
+        }
+    }
+}

data/src/test/java/org/embulk/parser/fluentd_out_file/TestFluentdOutFileParserPlugin.java

@@ -0,0 +1,185 @@
+package org.embulk.parser.fluentd_out_file;
+
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.ImmutableMap;
+import com.google.common.collect.Lists;
+import org.embulk.EmbulkTestRuntime;
+import org.embulk.config.ConfigException;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.TaskSource;
+import org.embulk.parser.fluentd_out_file.FluentdOutFileParserPlugin.PluginTask;
+import org.embulk.spi.ColumnConfig;
+import org.embulk.spi.FileInput;
+import org.embulk.spi.FileInputRunner;
+import org.embulk.spi.ParserPlugin;
+import org.embulk.spi.Schema;
+import org.embulk.spi.SchemaConfig;
+import org.embulk.spi.SchemaConfigException;
+import org.embulk.spi.TestPageBuilderReader.MockPageOutput;
+import org.embulk.spi.time.Timestamp;
+import org.embulk.spi.type.Type;
+import org.embulk.spi.type.Types;
+import org.embulk.spi.util.InputStreamFileInput;
+import org.embulk.spi.util.Pages;
+import org.embulk.standards.LocalFileInputPlugin;
+import org.junit.Before;
+import org.junit.Rule;
+import org.junit.Test;
+
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.List;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+import static org.junit.Assert.fail;
+import static org.msgpack.value.ValueFactory.newMap;
+import static org.msgpack.value.ValueFactory.newString;
+
+public class TestFluentdOutFileParserPlugin
+{
+    @Rule
+    public EmbulkTestRuntime runtime = new EmbulkTestRuntime();
+
+    private ConfigSource config;
+    private FluentdOutFileParserPlugin plugin;
+    private FileInputRunner runner;
+    private MockPageOutput output;
+
+    @Before
+    public void createResources()
+    {
+        config = config().set("type", "fluentd_out_file");
+        plugin = new FluentdOutFileParserPlugin();
+        runner = new FileInputRunner(new LocalFileInputPlugin());
+        output = new MockPageOutput();
+    }
+
+    @Test
+    public void checkDefaultValues()
+    {
+        ConfigSource config = this.config.deepCopy()
+                .set("columns", ImmutableList.of(
+                        ImmutableMap.of("name", "date_code", "type", "string"))
+                );
+        PluginTask task = config.loadConfig(PluginTask.class);
+        assertEquals('\t', task.getDelimiterChar());
+    }
+
+    @Test(expected = ConfigException.class)
+    public void checkColumnsRequired()
+    {
+        ConfigSource config = this.config.deepCopy();
+        config.loadConfig(PluginTask.class);
+    }
+
+    @Test
+    public void checkSchemaValidation()
+    {
+        { // columns size must not be greater than 3.
+            ConfigSource config = this.config.deepCopy()
+                    .set("columns", ImmutableList.of(
+                            ImmutableMap.of("name", "_c0", "type", "string"),
+                            ImmutableMap.of("name", "_c1", "type", "string"),
+                            ImmutableMap.of("name", "_c2", "type", "string"),
+                            ImmutableMap.of("name", "_c3", "type", "string"))
+                    );
+            try {
+                plugin.transaction(config, null);
+                fail();
+            }
+            catch (Throwable t) {
+                assertTrue(t instanceof SchemaConfigException);
+            }
+        }
+        { // columns must not include 'long' and 'double' typed columns.
+            ConfigSource config = this.config.deepCopy()
+                    .set("columns", ImmutableList.of(
+                            ImmutableMap.of("name", "_c0", "type", "long"),
+                            ImmutableMap.of("name", "_c1", "type", "double"))
+                    );
+            try {
+                plugin.transaction(config, null);
+                fail();
+            }
+            catch (Throwable t) {
+                assertTrue(t instanceof SchemaConfigException);
+            }
+        }
+    }
+
+    @Test
+    public void checkTransaction()
+            throws Exception
+    {
+        SchemaConfig schema = schema(
+                column("time", Types.TIMESTAMP, config().set("format", "%Y-%m-%dT%H:%M:%S")),
+                column("tag", Types.STRING),
+                column("record", Types.JSON));
+        ConfigSource config = this.config.deepCopy().set("columns", schema);
+
+        transaction(config, fileInput(
+                "2014-06-08T23:59:40\tfile.server.logs\t{\"field1\":\"value1\",\"field2\":\"value2\"}"
+        ));
+
+        List<Object[]> records = Pages.toObjects(schema.toSchema(), output.pages);
+        assertEquals(1, records.size());
+        for (Object[] record : records) {
+            assertEquals(Timestamp.ofEpochSecond(1402271980L), record[0]); // 2014-06-08T23:59:40UTC
+            assertEquals("file.server.logs", record[1]);
+            assertEquals(newMap(newString("field1"), newString("value1"), newString("field2"), newString("value2")), record[2]);
+        }
+    }
+
+    private FileInput fileInput(String... lines)
+            throws Exception
+    {
+        StringBuilder sb = new StringBuilder();
+        for (String line : lines) {
+            sb.append(line).append("\n");
+        }
+
+        ByteArrayInputStream in = new ByteArrayInputStream(sb.toString().getBytes());
+        return new InputStreamFileInput(runtime.getBufferAllocator(), provider(in));
+    }
+
+    private InputStreamFileInput.IteratorProvider provider(InputStream... inputStreams)
+            throws IOException
+    {
+        return new InputStreamFileInput.IteratorProvider(
+                ImmutableList.copyOf(inputStreams));
+    }
+
+    private ConfigSource config()
+    {
+        return runtime.getExec().newConfigSource();
+    }
+
+    private SchemaConfig schema(ColumnConfig... columns)
+    {
+        return new SchemaConfig(Lists.newArrayList(columns));
+    }
+
+    private ColumnConfig column(String name, Type type)
+    {
+        return column(name, type, config());
+    }
+
+    private ColumnConfig column(String name, Type type, ConfigSource config)
+    {
+        return new ColumnConfig(name, type, config);
+    }
+
+    private void transaction(ConfigSource config, final FileInput input)
+    {
+        plugin.transaction(config, new ParserPlugin.Control()
+        {
+            @Override
+            public void run(TaskSource taskSource, Schema schema)
+            {
+                plugin.run(taskSource, schema, input, output);
+            }
+        });
+    }
+}

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification
+name: embulk-parser-fluentd_out_file
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Muga Nishizawa
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2016-03-20 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  name: bundler
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  name: rake
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: Parses Fluentd Out File files read by other file input plugins.
+email:
+- muga.nishizawa@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .travis.yml
+- CHANGELOG.md
+- README.md
+- build.gradle
+- config/checkstyle/checkstyle.xml
+- config/checkstyle/default.xml
+- embulk-parser-fluentd_out_file.gemspec
+- gradle/wrapper/gradle-wrapper.jar
+- gradle/wrapper/gradle-wrapper.properties
+- gradlew
+- gradlew.bat
+- lib/embulk/guess/fluentd_out_file.rb
+- lib/embulk/parser/fluentd_out_file.rb
+- src/main/java/org/embulk/parser/fluentd_out_file/FluentdOutFileParserPlugin.java
+- src/test/java/org/embulk/parser/fluentd_out_file/TestFluentdOutFileParserPlugin.java
+- classpath/embulk-parser-fluentd_out_file-0.1.0.jar
+homepage: https://github.com/muga/embulk-parser-fluentd_out_file
+licenses:
+- Apache 2.0
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.1.9
+signing_key:
+specification_version: 4
+summary: Fluentd Out File parser plugin for Embulk
+test_files: []