embulk-filter-crawler 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4cb84672dc6d8f59c550c3faca25b051abe23209
+  data.tar.gz: 35fa411ca6985bf8815ef79f40c32865cc11b109
+SHA512:
+  metadata.gz: a165c5351f4d4d929ec98f3b4d539cba692fbf6ed8173994a396381d58a02754ba9f36d9e36625ad4e0f2f55bfc31c1e547549fca195e7e726ede28cd7d8758e
+  data.tar.gz: c53e77f4f465f9da0d733a3b0db8b955e3b3c0c6ccf371a34f7487a4a98cf7052987f35974ada23824a1f72a31f1eebaa4351d9f32b54f9e4502e699e7625fba

data/.gitignore

@@ -0,0 +1,13 @@
+*~
+/pkg/
+/tmp/
+*.gemspec
+.gradle/
+/classpath/
+build/
+.idea
+/.settings/
+/.metadata/
+.classpath
+.project
+/bin/

data/LICENSE.txt

@@ -0,0 +1,21 @@
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,49 @@
+# Crawler filter plugin for Embulk
+
+Write short description here and build.gradle file.
+
+## Overview
+
+* **Plugin type**: filter
+
+## Configuration
+
+- **target_key**: base_url column key name (string, require)
+- **max_depth_of_crawling**: max depth of crawling (integer, default: unlimited)
+- **seed_size**: seed_size (string, default: `"myvalue"`)
+- **number_of_crawlers**: parallelism (string, default: 1)
+- **max_pages_to_fetch**: max_pages_to_fetch (string, default: unlimited)
+- **crawl_storage_folder**: crawl_storage_folder (string, require)
+- **politeness_delay**: politeness_delay (integer, default: null)
+- **user_agent_string**: user_agent_string (string, default: null)
+- **keep_input**: keep_input (string, default: `"myvalue"`)
+
+## Example
+
+```yaml
+in:
+  type: mysql
+  host: dbs04
+  user: application
+  password: XXXXXXXX
+  database: iap
+  query: |
+    select url from companies limit 100
+filters:
+  - type: crawler
+    target_key: url
+    number_of_crawlers: 10
+    seed_size: 100
+    max_depth_of_crawling: 4
+    politeness_delay: 100
+    crawl_storage_folder: "/tmp/crawl/%s"
+out:
+  type: stdout
+```
+
+
+## Build
+
+```
+$ ./gradlew gem  # -t to watch change of files and rebuild continuously
+```

data/build.gradle

@@ -0,0 +1,94 @@
+plugins {
+    id "com.jfrog.bintray" version "1.1"
+    id "com.github.jruby-gradle.base" version "0.1.5"
+    id "java"
+    id "checkstyle"
+    id "eclipse"
+}
+import com.github.jrubygradle.JRubyExec
+repositories {
+    mavenCentral()
+    jcenter()
+}
+configurations {
+    provided
+}
+
+version = "0.1.0"
+
+sourceCompatibility = 1.7
+targetCompatibility = 1.7
+
+dependencies {
+    compile  "org.embulk:embulk-core:0.8.3"
+    compile  "edu.uci.ics:crawler4j:4.2"
+    provided "org.embulk:embulk-core:0.8.3"
+    testCompile "junit:junit:4.+"
+}
+
+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       = "${project.version}"
+  spec.authors       = ["toyama0919"]
+  spec.summary       = %[Crawler4J filter plugin for Embulk]
+  spec.description   = %[Crawler4J filter plugin for Embulk]
+  spec.email         = ["toyama0919@gmail.com"]
+  spec.licenses      = ["MIT"]
+  spec.homepage      = "https://github.com/toyama0919/embulk-filter-crawler"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['>= 10.0']
+end
+/$)
+    }
+}
+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/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/filter/crawler.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_filter(
+  "crawler", "org.embulk.filter.crawler.CrawlerFilterPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/filter/crawler/Constants.java

@@ -0,0 +1,21 @@
+package org.embulk.filter.crawler;
+
+public class Constants
+{
+
+    public static final String URL = "url";
+    public static final String DOMAIN = "domain";
+    public static final String SUBDOMAIN = "subdomain";
+    public static final String PATH = "path";
+    public static final String ANCHOR = "anchor";
+    public static final String PARENT_URL = "parent_url";
+    public static final String CONTENT_CHARSET = "content_charset";
+    public static final String REDIRECT_TO_URL = "redirect_to_url";
+    public static final String LANGUAGE = "language";
+    public static final String STATUS_CODE = "status_code";
+    public static final String TITLE = "title";
+    public static final String TEXT = "text";
+    public static final String HTML = "html";
+
+    private Constants(){}
+}

data/src/main/java/org/embulk/filter/crawler/CrawlStat.java

@@ -0,0 +1,38 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.embulk.filter.crawler;
+
+import java.util.List;
+import java.util.Map;
+
+import com.google.common.collect.Lists;
+
+public class CrawlStat
+{
+    List<Map<String, Object>> pages = Lists.newArrayList();
+
+    public List<Map<String, Object>> getPages()
+    {
+        return pages;
+    }
+
+    public void setPages(List<Map<String, Object>> pages)
+    {
+        this.pages = pages;
+    }
+}

data/src/main/java/org/embulk/filter/crawler/CrawlerFilterPlugin.java

@@ -0,0 +1,221 @@
+package org.embulk.filter.crawler;
+
+import java.io.File;
+import java.util.List;
+import java.util.Map;
+import java.util.UUID;
+
+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.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.type.Types;
+
+import com.google.common.base.Optional;
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.Lists;
+import com.google.common.collect.Maps;
+
+import edu.uci.ics.crawler4j.crawler.CrawlConfig;
+import edu.uci.ics.crawler4j.crawler.CrawlController;
+import edu.uci.ics.crawler4j.fetcher.PageFetcher;
+import edu.uci.ics.crawler4j.robotstxt.RobotstxtConfig;
+import edu.uci.ics.crawler4j.robotstxt.RobotstxtServer;
+
+public class CrawlerFilterPlugin
+        implements FilterPlugin
+{
+    public interface PluginTask
+            extends Task
+    {
+        @Config("max_depth_of_crawling")
+        @ConfigDefault("null")
+        public Optional<Integer> getMaxDepthOfCrawling();
+
+        @Config("number_of_crawlers")
+        @ConfigDefault("1")
+        public int getNumberOfCrawlers();
+
+        @Config("max_pages_to_fetch")
+        @ConfigDefault("-1")
+        public int getMaxPagesToFetch();
+
+        @Config("target_key")
+        public String getTargetKey();
+
+        @Config("crawl_storage_folder")
+        public String getCrawlStorageFolder();
+
+        @Config("politeness_delay")
+        @ConfigDefault("null")
+        public Optional<Integer> getPolitenessDelay();
+
+        @Config("user_agent_string")
+        @ConfigDefault("null")
+        public Optional<String> getUserAgentString();
+
+        @Config("keep_input")
+        @ConfigDefault("true")
+        public boolean getKeepInput();
+
+        @Config("output_prefix")
+        @ConfigDefault("\"\"")
+        public String getOutputPrefix();
+
+        @Config("should_not_visit_pattern")
+        @ConfigDefault("null")
+        public Optional<String> getShouldNotVisitPattern();
+    }
+
+    @Override
+    public void transaction(ConfigSource config, Schema inputSchema,
+            FilterPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+        ImmutableList.Builder<Column> builder = ImmutableList.builder();
+
+        int i = 0;
+        builder.addAll(getOutputColumns(i, task.getOutputPrefix()));
+
+        Schema outputSchema = new Schema(builder.build());
+        control.run(task.dump(), outputSchema);
+    }
+
+    /**
+     * @param i
+     * @param outputPrefix
+     * @return
+     */
+    private List<Column> getOutputColumns(int i, String outputPrefix) {
+        List<Column> list = Lists.newArrayList();
+        list.add(new Column(i++, outputPrefix + Constants.URL, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.DOMAIN, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.SUBDOMAIN, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.PATH, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.ANCHOR, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.PARENT_URL, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.CONTENT_CHARSET, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.REDIRECT_TO_URL, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.LANGUAGE, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.STATUS_CODE, Types.LONG));
+        list.add(new Column(i++, outputPrefix + Constants.TITLE, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.TEXT, Types.STRING));
+        list.add(new Column(i++, outputPrefix + Constants.HTML, Types.STRING));
+        return list;
+    }
+
+    @Override
+    public PageOutput open(TaskSource taskSource, final Schema inputSchema,
+            final Schema outputSchema, final PageOutput output)
+    {
+        final PluginTask task = taskSource.loadTask(PluginTask.class);
+        final Column keyNameColumn = inputSchema.lookupColumn(task.getTargetKey());
+
+        return new PageOutput() {
+            private PageReader reader = new PageReader(inputSchema);
+            private PageBuilder builder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
+            private CrawlController controller = getController();
+
+            @Override
+            public void finish()
+            {
+                for (Object object : controller.getCrawlersLocalData()) {
+                    CrawlStat crawlStat = (CrawlStat) object;
+                    for (Map<String, Object> map : crawlStat.getPages()) {
+                        for (Column outputColumn : outputSchema.getColumns()) {
+                            final Object value = map.get(outputColumn.getName());
+                            setValue(value, outputColumn);
+                        }
+                        builder.addRecord();
+                    }
+                }
+                builder.finish();
+            }
+
+            @Override
+            public void close()
+            {
+                builder.close();
+            }
+
+            @Override
+            public void add(Page page)
+            {
+                reader.setPage(page);
+                while (reader.nextRecord()) {
+                    controller.addSeed(reader.getString(keyNameColumn));
+                }
+                Map<String, Object> customData = Maps.newHashMap();
+                customData.put("output_prefix", task.getOutputPrefix());
+                if (task.getShouldNotVisitPattern().isPresent()) {
+                    customData.put("should_not_visit_pattern", task.getShouldNotVisitPattern().get());
+                }
+                controller.setCustomData(customData);
+                controller.start(EmbulkCrawler.class, task.getNumberOfCrawlers());
+            }
+
+            /**
+             * @param seeds
+             */
+            private void setValue(Object value, Column column)
+            {
+                if (value == null) {
+                    builder.setNull(column);
+                }
+                else if (column.getType().equals(Types.STRING)) {
+                    builder.setString(column, (String) value);
+                }
+                else if (column.getType().equals(Types.LONG)) {
+                    builder.setLong(column, (Integer) value);
+                }
+            }
+
+            /**
+             * @param seeds
+             * @return
+             */
+            private CrawlController getController()
+            {
+                CrawlConfig config = new CrawlConfig();
+                String directoryPath = String.format(task.getCrawlStorageFolder(), UUID.randomUUID());
+                File dir = new File(directoryPath);
+                dir.mkdirs();
+
+                config.setCrawlStorageFolder(directoryPath);
+                if (task.getMaxDepthOfCrawling().isPresent()) {
+                    config.setMaxDepthOfCrawling(task.getMaxDepthOfCrawling().get());
+                }
+
+                config.setMaxPagesToFetch(task.getMaxPagesToFetch());
+                if (task.getPolitenessDelay().isPresent()) {
+                    config.setPolitenessDelay(task.getPolitenessDelay().get());
+                }
+                if (task.getUserAgentString().isPresent()) {
+                    config.setUserAgentString(task.getUserAgentString().get());
+                }
+
+                PageFetcher pageFetcher = new PageFetcher(config);
+                RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
+                RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);
+                CrawlController crawlController = null;
+                try {
+                    crawlController = new CrawlController(config, pageFetcher, robotstxtServer);
+                }
+                catch (Exception e) {
+                    e.printStackTrace();
+                }
+
+                return crawlController;
+            }
+        };
+    }
+}

data/src/main/java/org/embulk/filter/crawler/EmbulkCrawler.java

@@ -0,0 +1,103 @@
+package org.embulk.filter.crawler;
+
+import java.util.Map;
+import java.util.regex.Pattern;
+
+import com.google.common.collect.Maps;
+
+import edu.uci.ics.crawler4j.crawler.Page;
+import edu.uci.ics.crawler4j.crawler.WebCrawler;
+import edu.uci.ics.crawler4j.parser.BinaryParseData;
+import edu.uci.ics.crawler4j.parser.HtmlParseData;
+import edu.uci.ics.crawler4j.parser.ParseData;
+import edu.uci.ics.crawler4j.parser.TextParseData;
+import edu.uci.ics.crawler4j.url.WebURL;
+
+public class EmbulkCrawler extends WebCrawler
+{
+
+    CrawlStat myCrawlStat;
+    Pattern IMAGE_EXTENSIONS = null;
+
+    public EmbulkCrawler()
+    {
+      myCrawlStat = new CrawlStat();
+    }
+
+    private Map<String, Object> params;
+
+    @SuppressWarnings("unchecked")
+    @Override
+    public void onStart()
+    {
+        params = (Map<String, Object>) myController.getCustomData();
+        Object regex = params.get("should_not_visit_pattern");
+        if (regex != null) {
+            IMAGE_EXTENSIONS = Pattern.compile((String)regex);
+        }
+    }
+
+    /**
+     * You should implement this function to specify whether the given url
+     * should be crawled or not (based on your crawling logic).
+     */
+    @Override
+    public boolean shouldVisit(Page referringPage, WebURL url)
+    {
+        String href = url.getURL().toLowerCase();
+        if (IMAGE_EXTENSIONS != null) {
+            if (IMAGE_EXTENSIONS.matcher(href).matches()) {
+                return false;
+            }
+        }
+
+        return url.getDomain().equals(referringPage.getWebURL().getDomain());
+    }
+
+    /**
+     * This function is called when a page is fetched and ready to be processed
+     * by your program.
+     */
+    @Override
+    public void visit(Page page)
+    {
+        final WebURL webURL = page.getWebURL();
+        final String outputPrefix = (String) params.get("output_prefix");
+
+        Map<String, Object> map = Maps.newHashMap();
+        map.put(outputPrefix + Constants.URL, webURL.getURL());
+        map.put(outputPrefix + Constants.DOMAIN, webURL.getDomain());
+        map.put(outputPrefix + Constants.SUBDOMAIN, webURL.getSubDomain());
+        map.put(outputPrefix + Constants.PATH, webURL.getPath());
+        map.put(outputPrefix + Constants.ANCHOR, webURL.getAnchor());
+        map.put(outputPrefix + Constants.PARENT_URL, webURL.getParentUrl());
+        map.put(outputPrefix + Constants.CONTENT_CHARSET, page.getContentCharset());
+        map.put(outputPrefix + Constants.REDIRECT_TO_URL, page.getRedirectedToUrl());
+        map.put(outputPrefix + Constants.LANGUAGE, page.getLanguage());
+        map.put(outputPrefix + Constants.STATUS_CODE, page.getStatusCode());
+
+        ParseData parseData = page.getParseData();
+        if (parseData instanceof HtmlParseData) {
+            HtmlParseData htmlParseData = (HtmlParseData) parseData;
+            map.put(outputPrefix + Constants.TITLE, htmlParseData.getTitle());
+            map.put(outputPrefix + Constants.TEXT, htmlParseData.getText());
+            map.put(outputPrefix + Constants.HTML, htmlParseData.getHtml());
+        }
+        else if (parseData instanceof TextParseData) {
+            TextParseData textParseData = (TextParseData) parseData;
+            map.put(outputPrefix + Constants.TEXT, textParseData.getTextContent());
+        }
+        else if (parseData instanceof BinaryParseData) {
+            BinaryParseData binaryParseData = (BinaryParseData) parseData;
+            map.put(outputPrefix + Constants.HTML, binaryParseData.getHtml());
+        }
+        logger.info("{}", webURL.getURL());
+        myCrawlStat.pages.add(map);
+    }
+
+    @Override
+    public Object getMyLocalData()
+    {
+      return myCrawlStat;
+    }
+}

data/src/test/java/org/embulk/filter/crawler/TestCrawlerFilterPlugin.java

@@ -0,0 +1,5 @@
+package org.embulk.filter.crawler;
+
+public class TestCrawlerFilterPlugin
+{
+}

metadata

@@ -0,0 +1,131 @@
+--- !ruby/object:Gem::Specification
+name: embulk-filter-crawler
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- toyama0919
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2016-03-25 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: Crawler4J filter plugin for Embulk
+email:
+- toyama0919@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- LICENSE.txt
+- README.md
+- build.gradle
+- config/checkstyle/checkstyle.xml
+- config/checkstyle/default.xml
+- gradle/wrapper/gradle-wrapper.jar
+- gradle/wrapper/gradle-wrapper.properties
+- gradlew
+- gradlew.bat
+- lib/embulk/filter/crawler.rb
+- src/main/java/org/embulk/filter/crawler/Constants.java
+- src/main/java/org/embulk/filter/crawler/CrawlStat.java
+- src/main/java/org/embulk/filter/crawler/CrawlerFilterPlugin.java
+- src/main/java/org/embulk/filter/crawler/EmbulkCrawler.java
+- src/test/java/org/embulk/filter/crawler/TestCrawlerFilterPlugin.java
+- classpath/apache-mime4j-core-0.7.2.jar
+- classpath/apache-mime4j-dom-0.7.2.jar
+- classpath/asm-debug-all-4.1.jar
+- classpath/aspectjrt-1.6.11.jar
+- classpath/bcmail-jdk15-1.45.jar
+- classpath/bcprov-jdk15-1.45.jar
+- classpath/boilerpipe-1.1.0.jar
+- classpath/commons-codec-1.9.jar
+- classpath/commons-compress-1.5.jar
+- classpath/commons-logging-1.2.jar
+- classpath/crawler4j-4.2.jar
+- classpath/dom4j-1.6.1.jar
+- classpath/embulk-filter-crawler-0.1.0.jar
+- classpath/fontbox-1.8.4.jar
+- classpath/geronimo-stax-api_1.0_spec-1.0.1.jar
+- classpath/httpclient-4.4.jar
+- classpath/httpcore-4.4.jar
+- classpath/isoparser-1.0-RC-1.jar
+- classpath/jdom-1.0.jar
+- classpath/je-5.0.73.jar
+- classpath/jempbox-1.8.4.jar
+- classpath/jhighlight-1.0.jar
+- classpath/juniversalchardet-1.0.3.jar
+- classpath/lidalia-slf4j-ext-1.0.0.jar
+- classpath/metadata-extractor-2.6.2.jar
+- classpath/netcdf-4.2-min.jar
+- classpath/pdfbox-1.8.4.jar
+- classpath/poi-3.10-beta2.jar
+- classpath/poi-ooxml-3.10-beta2.jar
+- classpath/poi-ooxml-schemas-3.10-beta2.jar
+- classpath/poi-scratchpad-3.10-beta2.jar
+- classpath/rome-0.9.jar
+- classpath/tagsoup-1.2.1.jar
+- classpath/tika-core-1.5.jar
+- classpath/tika-parsers-1.5.jar
+- classpath/vorbis-java-core-0.1-tests.jar
+- classpath/vorbis-java-core-0.1.jar
+- classpath/vorbis-java-tika-0.1.jar
+- classpath/xercesImpl-2.8.1.jar
+- classpath/xml-apis-1.3.03.jar
+- classpath/xmlbeans-2.3.0.jar
+- classpath/xmpcore-5.1.2.jar
+- classpath/xz-1.2.jar
+homepage: https://github.com/toyama0919/embulk-filter-crawler
+licenses:
+- MIT
+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: Crawler4J filter plugin for Embulk
+test_files: []