embulk-filter-murmur2_partitioner 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 30e51b9119f3728f25fb9dd46c5a78588ff84225
4
+ data.tar.gz: f6e880d3087307c927257d09ccaa1ce4c9a651e5
5
+ SHA512:
6
+ metadata.gz: c7616d23f9b7fa06240ee0804c3f397ad680d2fba2005109b20fb14ec7b5395c57689639ba9c375dbc3b8b1a521b79c03b1626dbe14b9c77af3ac134f1571f5c
7
+ data.tar.gz: 74b7e75a6ef28d13526ae2b707c40c6b934a9ec50a927f74f1da63fa4ce30129d23498749a197e89d34b0432980be5d68635fbd03d427d1b1ec2ac46a7dd9134
@@ -0,0 +1,12 @@
1
+ *~
2
+ /pkg/
3
+ /tmp/
4
+ *.gemspec
5
+ .gradle/
6
+ /classpath/
7
+ build/
8
+ .idea
9
+ /.settings/
10
+ /.metadata/
11
+ .classpath
12
+ .project
@@ -0,0 +1,21 @@
1
+
2
+ MIT License
3
+
4
+ Permission is hereby granted, free of charge, to any person obtaining
5
+ a copy of this software and associated documentation files (the
6
+ "Software"), to deal in the Software without restriction, including
7
+ without limitation the rights to use, copy, modify, merge, publish,
8
+ distribute, sublicense, and/or sell copies of the Software, and to
9
+ permit persons to whom the Software is furnished to do so, subject to
10
+ the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be
13
+ included in all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
18
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
19
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
20
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
21
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
@@ -0,0 +1,29 @@
1
+ # Murmur2 Partitioner filter plugin for Embulk
2
+
3
+ Add partition number that is calculated by Apache Kafka's murmur2 partitioner.
4
+
5
+ ## Overview
6
+
7
+ * **Plugin type**: filter
8
+
9
+ ## Configuration
10
+
11
+ - **key_column**: column as partition key (string, required)
12
+ - **partition_column**: set partition number to this column. unless the column exists, add the column to output schema automatically. (string, default: `"partition"`)
13
+ - **partition_count**: Partition Count (integer, required)
14
+
15
+ ## Example
16
+
17
+ ```yaml
18
+ filters:
19
+ - type: murmur2_partitioner
20
+ key_column: id
21
+ partition_count: 8
22
+ ```
23
+
24
+
25
+ ## Build
26
+
27
+ ```
28
+ $ ./gradlew gem # -t to watch change of files and rebuild continuously
29
+ ```
@@ -0,0 +1,99 @@
1
+ plugins {
2
+ id "com.jfrog.bintray" version "1.1"
3
+ id "com.github.jruby-gradle.base" version "1.5.0"
4
+ id "java"
5
+ id "checkstyle"
6
+ }
7
+ import com.github.jrubygradle.JRubyExec
8
+ repositories {
9
+ mavenCentral()
10
+ jcenter()
11
+ }
12
+ configurations {
13
+ provided
14
+ }
15
+
16
+ version = "0.1.0"
17
+
18
+ sourceCompatibility = 1.8
19
+ targetCompatibility = 1.8
20
+
21
+ dependencies {
22
+ compile "org.embulk:embulk-core:0.9.17"
23
+ provided "org.embulk:embulk-core:0.9.17"
24
+ compile "org.apache.kafka:kafka-clients:2.3.0"
25
+ testCompile "junit:junit:4.+"
26
+ testCompile "org.embulk:embulk-test:0.9.17"
27
+ testCompile "org.embulk:embulk-core:0.9.17:tests"
28
+ }
29
+
30
+ task classpath(type: Copy, dependsOn: ["jar"]) {
31
+ doFirst { file("classpath").deleteDir() }
32
+ from (configurations.runtime - configurations.provided + files(jar.archivePath))
33
+ into "classpath"
34
+ }
35
+ clean { delete "classpath" }
36
+
37
+ checkstyle {
38
+ configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
39
+ toolVersion = '6.14.1'
40
+ }
41
+ checkstyleMain {
42
+ configFile = file("${project.rootDir}/config/checkstyle/default.xml")
43
+ ignoreFailures = true
44
+ }
45
+ checkstyleTest {
46
+ configFile = file("${project.rootDir}/config/checkstyle/default.xml")
47
+ ignoreFailures = true
48
+ }
49
+ task checkstyle(type: Checkstyle) {
50
+ classpath = sourceSets.main.output + sourceSets.test.output
51
+ source = sourceSets.main.allJava + sourceSets.test.allJava
52
+ }
53
+
54
+ task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
55
+ jrubyArgs "-S"
56
+ script "gem"
57
+ scriptArgs "build", "${project.name}.gemspec"
58
+ doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
59
+ }
60
+
61
+ task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
62
+ jrubyArgs "-S"
63
+ script "gem"
64
+ scriptArgs "push", "pkg/${project.name}-${project.version}.gem"
65
+ }
66
+
67
+ task "package"(dependsOn: ["gemspec", "classpath"]) {
68
+ doLast {
69
+ println "> Build succeeded."
70
+ println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
71
+ }
72
+ }
73
+
74
+ task gemspec {
75
+ ext.gemspecFile = file("${project.name}.gemspec")
76
+ inputs.file "build.gradle"
77
+ outputs.file gemspecFile
78
+ doLast { gemspecFile.write($/
79
+ Gem::Specification.new do |spec|
80
+ spec.name = "${project.name}"
81
+ spec.version = "${project.version}"
82
+ spec.authors = ["joker1007"]
83
+ spec.summary = %[Murmur2 Partitioner filter plugin for Embulk]
84
+ spec.description = %[Murmur2 Partitioner]
85
+ spec.email = ["kakyoin.hierophant@gmail.com"]
86
+ spec.licenses = ["MIT"]
87
+ spec.homepage = "https://github.com/joker1007/embulk-filter-murmur2_partitioner"
88
+
89
+ spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
90
+ spec.test_files = spec.files.grep(%r"^(test|spec)/")
91
+ spec.require_paths = ["lib"]
92
+
93
+ spec.add_development_dependency 'bundler', ['~> 1.0']
94
+ spec.add_development_dependency 'rake', ['~> 12.0']
95
+ end
96
+ /$)
97
+ }
98
+ }
99
+ clean { delete "${project.name}.gemspec" }
@@ -0,0 +1,128 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <!DOCTYPE module PUBLIC
3
+ "-//Puppy Crawl//DTD Check Configuration 1.3//EN"
4
+ "http://www.puppycrawl.com/dtds/configuration_1_3.dtd">
5
+ <module name="Checker">
6
+ <!-- https://github.com/facebook/presto/blob/master/src/checkstyle/checks.xml -->
7
+ <module name="FileTabCharacter"/>
8
+ <module name="NewlineAtEndOfFile">
9
+ <property name="lineSeparator" value="lf"/>
10
+ </module>
11
+ <module name="RegexpMultiline">
12
+ <property name="format" value="\r"/>
13
+ <property name="message" value="Line contains carriage return"/>
14
+ </module>
15
+ <module name="RegexpMultiline">
16
+ <property name="format" value=" \n"/>
17
+ <property name="message" value="Line has trailing whitespace"/>
18
+ </module>
19
+ <module name="RegexpMultiline">
20
+ <property name="format" value="\{\n\n"/>
21
+ <property name="message" value="Blank line after opening brace"/>
22
+ </module>
23
+ <module name="RegexpMultiline">
24
+ <property name="format" value="\n\n\s*\}"/>
25
+ <property name="message" value="Blank line before closing brace"/>
26
+ </module>
27
+ <module name="RegexpMultiline">
28
+ <property name="format" value="\n\n\n"/>
29
+ <property name="message" value="Multiple consecutive blank lines"/>
30
+ </module>
31
+ <module name="RegexpMultiline">
32
+ <property name="format" value="\n\n\Z"/>
33
+ <property name="message" value="Blank line before end of file"/>
34
+ </module>
35
+ <module name="RegexpMultiline">
36
+ <property name="format" value="Preconditions\.checkNotNull"/>
37
+ <property name="message" value="Use of checkNotNull"/>
38
+ </module>
39
+
40
+ <module name="TreeWalker">
41
+ <module name="EmptyBlock">
42
+ <property name="option" value="text"/>
43
+ <property name="tokens" value="
44
+ LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_IF,
45
+ LITERAL_FOR, LITERAL_TRY, LITERAL_WHILE, INSTANCE_INIT, STATIC_INIT"/>
46
+ </module>
47
+ <module name="EmptyStatement"/>
48
+ <module name="EmptyForInitializerPad"/>
49
+ <module name="EmptyForIteratorPad">
50
+ <property name="option" value="space"/>
51
+ </module>
52
+ <module name="MethodParamPad">
53
+ <property name="allowLineBreaks" value="true"/>
54
+ <property name="option" value="nospace"/>
55
+ </module>
56
+ <module name="ParenPad"/>
57
+ <module name="TypecastParenPad"/>
58
+ <module name="NeedBraces"/>
59
+ <module name="LeftCurly">
60
+ <property name="option" value="nl"/>
61
+ <property name="tokens" value="CLASS_DEF, CTOR_DEF, INTERFACE_DEF, METHOD_DEF"/>
62
+ </module>
63
+ <module name="LeftCurly">
64
+ <property name="option" value="eol"/>
65
+ <property name="tokens" value="
66
+ LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_FOR,
67
+ LITERAL_IF, LITERAL_SWITCH, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE"/>
68
+ </module>
69
+ <module name="RightCurly">
70
+ <property name="option" value="alone"/>
71
+ </module>
72
+ <module name="GenericWhitespace"/>
73
+ <module name="WhitespaceAfter"/>
74
+ <module name="NoWhitespaceBefore"/>
75
+
76
+ <module name="UpperEll"/>
77
+ <module name="DefaultComesLast"/>
78
+ <module name="ArrayTypeStyle"/>
79
+ <module name="MultipleVariableDeclarations"/>
80
+ <module name="ModifierOrder"/>
81
+ <module name="OneStatementPerLine"/>
82
+ <module name="StringLiteralEquality"/>
83
+ <module name="MutableException"/>
84
+ <module name="EqualsHashCode"/>
85
+ <module name="InnerAssignment"/>
86
+ <module name="InterfaceIsType"/>
87
+ <module name="HideUtilityClassConstructor"/>
88
+
89
+ <module name="MemberName"/>
90
+ <module name="LocalVariableName"/>
91
+ <module name="LocalFinalVariableName"/>
92
+ <module name="TypeName"/>
93
+ <module name="PackageName"/>
94
+ <module name="ParameterName"/>
95
+ <module name="StaticVariableName"/>
96
+ <module name="ClassTypeParameterName">
97
+ <property name="format" value="^[A-Z][0-9]?$"/>
98
+ </module>
99
+ <module name="MethodTypeParameterName">
100
+ <property name="format" value="^[A-Z][0-9]?$"/>
101
+ </module>
102
+
103
+ <module name="AvoidStarImport"/>
104
+ <module name="RedundantImport"/>
105
+ <module name="UnusedImports"/>
106
+ <module name="ImportOrder">
107
+ <property name="groups" value="*,javax,java"/>
108
+ <property name="separated" value="true"/>
109
+ <property name="option" value="bottom"/>
110
+ <property name="sortStaticImportsAlphabetically" value="true"/>
111
+ </module>
112
+
113
+ <module name="WhitespaceAround">
114
+ <property name="allowEmptyConstructors" value="true"/>
115
+ <property name="allowEmptyMethods" value="true"/>
116
+ <property name="ignoreEnhancedForColon" value="false"/>
117
+ <property name="tokens" value="
118
+ ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN,
119
+ BXOR, BXOR_ASSIGN, COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LE,
120
+ LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
121
+ LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN,
122
+ LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE,
123
+ LOR, LT, MINUS, MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL,
124
+ PLUS, PLUS_ASSIGN, QUESTION, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN,
125
+ STAR, STAR_ASSIGN, TYPE_EXTENSION_AND"/>
126
+ </module>
127
+ </module>
128
+ </module>
@@ -0,0 +1,108 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <!DOCTYPE module PUBLIC
3
+ "-//Puppy Crawl//DTD Check Configuration 1.3//EN"
4
+ "http://www.puppycrawl.com/dtds/configuration_1_3.dtd">
5
+ <!--
6
+ This is a subset of ./checkstyle.xml which allows some loose styles
7
+ -->
8
+ <module name="Checker">
9
+ <module name="FileTabCharacter"/>
10
+ <module name="NewlineAtEndOfFile">
11
+ <property name="lineSeparator" value="lf"/>
12
+ </module>
13
+ <module name="RegexpMultiline">
14
+ <property name="format" value="\r"/>
15
+ <property name="message" value="Line contains carriage return"/>
16
+ </module>
17
+ <module name="RegexpMultiline">
18
+ <property name="format" value=" \n"/>
19
+ <property name="message" value="Line has trailing whitespace"/>
20
+ </module>
21
+ <module name="RegexpMultiline">
22
+ <property name="format" value="\n\n\n"/>
23
+ <property name="message" value="Multiple consecutive blank lines"/>
24
+ </module>
25
+ <module name="RegexpMultiline">
26
+ <property name="format" value="\n\n\Z"/>
27
+ <property name="message" value="Blank line before end of file"/>
28
+ </module>
29
+
30
+ <module name="TreeWalker">
31
+ <module name="EmptyBlock">
32
+ <property name="option" value="text"/>
33
+ <property name="tokens" value="
34
+ LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_IF,
35
+ LITERAL_FOR, LITERAL_TRY, LITERAL_WHILE, INSTANCE_INIT, STATIC_INIT"/>
36
+ </module>
37
+ <module name="EmptyStatement"/>
38
+ <module name="EmptyForInitializerPad"/>
39
+ <module name="EmptyForIteratorPad">
40
+ <property name="option" value="space"/>
41
+ </module>
42
+ <module name="MethodParamPad">
43
+ <property name="allowLineBreaks" value="true"/>
44
+ <property name="option" value="nospace"/>
45
+ </module>
46
+ <module name="ParenPad"/>
47
+ <module name="TypecastParenPad"/>
48
+ <module name="NeedBraces"/>
49
+ <module name="LeftCurly">
50
+ <property name="option" value="nl"/>
51
+ <property name="tokens" value="CLASS_DEF, CTOR_DEF, INTERFACE_DEF, METHOD_DEF"/>
52
+ </module>
53
+ <module name="LeftCurly">
54
+ <property name="option" value="eol"/>
55
+ <property name="tokens" value="
56
+ LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_FOR,
57
+ LITERAL_IF, LITERAL_SWITCH, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE"/>
58
+ </module>
59
+ <module name="RightCurly">
60
+ <property name="option" value="alone"/>
61
+ </module>
62
+ <module name="GenericWhitespace"/>
63
+ <module name="WhitespaceAfter"/>
64
+ <module name="NoWhitespaceBefore"/>
65
+
66
+ <module name="UpperEll"/>
67
+ <module name="DefaultComesLast"/>
68
+ <module name="ArrayTypeStyle"/>
69
+ <module name="MultipleVariableDeclarations"/>
70
+ <module name="ModifierOrder"/>
71
+ <module name="OneStatementPerLine"/>
72
+ <module name="StringLiteralEquality"/>
73
+ <module name="MutableException"/>
74
+ <module name="EqualsHashCode"/>
75
+ <module name="InnerAssignment"/>
76
+ <module name="InterfaceIsType"/>
77
+ <module name="HideUtilityClassConstructor"/>
78
+
79
+ <module name="MemberName"/>
80
+ <module name="LocalVariableName"/>
81
+ <module name="LocalFinalVariableName"/>
82
+ <module name="TypeName"/>
83
+ <module name="PackageName"/>
84
+ <module name="ParameterName"/>
85
+ <module name="StaticVariableName"/>
86
+ <module name="ClassTypeParameterName">
87
+ <property name="format" value="^[A-Z][0-9]?$"/>
88
+ </module>
89
+ <module name="MethodTypeParameterName">
90
+ <property name="format" value="^[A-Z][0-9]?$"/>
91
+ </module>
92
+
93
+ <module name="WhitespaceAround">
94
+ <property name="allowEmptyConstructors" value="true"/>
95
+ <property name="allowEmptyMethods" value="true"/>
96
+ <property name="ignoreEnhancedForColon" value="false"/>
97
+ <property name="tokens" value="
98
+ ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN,
99
+ BXOR, BXOR_ASSIGN, COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LE,
100
+ LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
101
+ LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN,
102
+ LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE,
103
+ LOR, LT, MINUS, MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL,
104
+ PLUS, PLUS_ASSIGN, QUESTION, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN,
105
+ STAR, STAR_ASSIGN, TYPE_EXTENSION_AND"/>
106
+ </module>
107
+ </module>
108
+ </module>
@@ -0,0 +1,5 @@
1
+ distributionBase=GRADLE_USER_HOME
2
+ distributionPath=wrapper/dists
3
+ zipStoreBase=GRADLE_USER_HOME
4
+ zipStorePath=wrapper/dists
5
+ distributionUrl=https\://services.gradle.org/distributions/gradle-4.1-bin.zip
data/gradlew ADDED
@@ -0,0 +1,172 @@
1
+ #!/usr/bin/env sh
2
+
3
+ ##############################################################################
4
+ ##
5
+ ## Gradle start up script for UN*X
6
+ ##
7
+ ##############################################################################
8
+
9
+ # Attempt to set APP_HOME
10
+ # Resolve links: $0 may be a link
11
+ PRG="$0"
12
+ # Need this for relative symlinks.
13
+ while [ -h "$PRG" ] ; do
14
+ ls=`ls -ld "$PRG"`
15
+ link=`expr "$ls" : '.*-> \(.*\)$'`
16
+ if expr "$link" : '/.*' > /dev/null; then
17
+ PRG="$link"
18
+ else
19
+ PRG=`dirname "$PRG"`"/$link"
20
+ fi
21
+ done
22
+ SAVED="`pwd`"
23
+ cd "`dirname \"$PRG\"`/" >/dev/null
24
+ APP_HOME="`pwd -P`"
25
+ cd "$SAVED" >/dev/null
26
+
27
+ APP_NAME="Gradle"
28
+ APP_BASE_NAME=`basename "$0"`
29
+
30
+ # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
31
+ DEFAULT_JVM_OPTS=""
32
+
33
+ # Use the maximum available, or set MAX_FD != -1 to use that value.
34
+ MAX_FD="maximum"
35
+
36
+ warn () {
37
+ echo "$*"
38
+ }
39
+
40
+ die () {
41
+ echo
42
+ echo "$*"
43
+ echo
44
+ exit 1
45
+ }
46
+
47
+ # OS specific support (must be 'true' or 'false').
48
+ cygwin=false
49
+ msys=false
50
+ darwin=false
51
+ nonstop=false
52
+ case "`uname`" in
53
+ CYGWIN* )
54
+ cygwin=true
55
+ ;;
56
+ Darwin* )
57
+ darwin=true
58
+ ;;
59
+ MINGW* )
60
+ msys=true
61
+ ;;
62
+ NONSTOP* )
63
+ nonstop=true
64
+ ;;
65
+ esac
66
+
67
+ CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
68
+
69
+ # Determine the Java command to use to start the JVM.
70
+ if [ -n "$JAVA_HOME" ] ; then
71
+ if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
72
+ # IBM's JDK on AIX uses strange locations for the executables
73
+ JAVACMD="$JAVA_HOME/jre/sh/java"
74
+ else
75
+ JAVACMD="$JAVA_HOME/bin/java"
76
+ fi
77
+ if [ ! -x "$JAVACMD" ] ; then
78
+ die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
79
+
80
+ Please set the JAVA_HOME variable in your environment to match the
81
+ location of your Java installation."
82
+ fi
83
+ else
84
+ JAVACMD="java"
85
+ which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
86
+
87
+ Please set the JAVA_HOME variable in your environment to match the
88
+ location of your Java installation."
89
+ fi
90
+
91
+ # Increase the maximum file descriptors if we can.
92
+ if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
93
+ MAX_FD_LIMIT=`ulimit -H -n`
94
+ if [ $? -eq 0 ] ; then
95
+ if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
96
+ MAX_FD="$MAX_FD_LIMIT"
97
+ fi
98
+ ulimit -n $MAX_FD
99
+ if [ $? -ne 0 ] ; then
100
+ warn "Could not set maximum file descriptor limit: $MAX_FD"
101
+ fi
102
+ else
103
+ warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
104
+ fi
105
+ fi
106
+
107
+ # For Darwin, add options to specify how the application appears in the dock
108
+ if $darwin; then
109
+ GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
110
+ fi
111
+
112
+ # For Cygwin, switch paths to Windows format before running java
113
+ if $cygwin ; then
114
+ APP_HOME=`cygpath --path --mixed "$APP_HOME"`
115
+ CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
116
+ JAVACMD=`cygpath --unix "$JAVACMD"`
117
+
118
+ # We build the pattern for arguments to be converted via cygpath
119
+ ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
120
+ SEP=""
121
+ for dir in $ROOTDIRSRAW ; do
122
+ ROOTDIRS="$ROOTDIRS$SEP$dir"
123
+ SEP="|"
124
+ done
125
+ OURCYGPATTERN="(^($ROOTDIRS))"
126
+ # Add a user-defined pattern to the cygpath arguments
127
+ if [ "$GRADLE_CYGPATTERN" != "" ] ; then
128
+ OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
129
+ fi
130
+ # Now convert the arguments - kludge to limit ourselves to /bin/sh
131
+ i=0
132
+ for arg in "$@" ; do
133
+ CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
134
+ CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
135
+
136
+ if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
137
+ eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
138
+ else
139
+ eval `echo args$i`="\"$arg\""
140
+ fi
141
+ i=$((i+1))
142
+ done
143
+ case $i in
144
+ (0) set -- ;;
145
+ (1) set -- "$args0" ;;
146
+ (2) set -- "$args0" "$args1" ;;
147
+ (3) set -- "$args0" "$args1" "$args2" ;;
148
+ (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
149
+ (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
150
+ (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
151
+ (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
152
+ (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
153
+ (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
154
+ esac
155
+ fi
156
+
157
+ # Escape application args
158
+ save () {
159
+ for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
160
+ echo " "
161
+ }
162
+ APP_ARGS=$(save "$@")
163
+
164
+ # Collect all arguments for the java command, following the shell quoting and substitution rules
165
+ eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
166
+
167
+ # by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
168
+ if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
169
+ cd "$(dirname "$0")"
170
+ fi
171
+
172
+ exec "$JAVACMD" "$@"
@@ -0,0 +1,84 @@
1
+ @if "%DEBUG%" == "" @echo off
2
+ @rem ##########################################################################
3
+ @rem
4
+ @rem Gradle startup script for Windows
5
+ @rem
6
+ @rem ##########################################################################
7
+
8
+ @rem Set local scope for the variables with windows NT shell
9
+ if "%OS%"=="Windows_NT" setlocal
10
+
11
+ set DIRNAME=%~dp0
12
+ if "%DIRNAME%" == "" set DIRNAME=.
13
+ set APP_BASE_NAME=%~n0
14
+ set APP_HOME=%DIRNAME%
15
+
16
+ @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
17
+ set DEFAULT_JVM_OPTS=
18
+
19
+ @rem Find java.exe
20
+ if defined JAVA_HOME goto findJavaFromJavaHome
21
+
22
+ set JAVA_EXE=java.exe
23
+ %JAVA_EXE% -version >NUL 2>&1
24
+ if "%ERRORLEVEL%" == "0" goto init
25
+
26
+ echo.
27
+ echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
28
+ echo.
29
+ echo Please set the JAVA_HOME variable in your environment to match the
30
+ echo location of your Java installation.
31
+
32
+ goto fail
33
+
34
+ :findJavaFromJavaHome
35
+ set JAVA_HOME=%JAVA_HOME:"=%
36
+ set JAVA_EXE=%JAVA_HOME%/bin/java.exe
37
+
38
+ if exist "%JAVA_EXE%" goto init
39
+
40
+ echo.
41
+ echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
42
+ echo.
43
+ echo Please set the JAVA_HOME variable in your environment to match the
44
+ echo location of your Java installation.
45
+
46
+ goto fail
47
+
48
+ :init
49
+ @rem Get command-line arguments, handling Windows variants
50
+
51
+ if not "%OS%" == "Windows_NT" goto win9xME_args
52
+
53
+ :win9xME_args
54
+ @rem Slurp the command line arguments.
55
+ set CMD_LINE_ARGS=
56
+ set _SKIP=2
57
+
58
+ :win9xME_args_slurp
59
+ if "x%~1" == "x" goto execute
60
+
61
+ set CMD_LINE_ARGS=%*
62
+
63
+ :execute
64
+ @rem Setup the command line
65
+
66
+ set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
67
+
68
+ @rem Execute Gradle
69
+ "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
70
+
71
+ :end
72
+ @rem End local scope for the variables with windows NT shell
73
+ if "%ERRORLEVEL%"=="0" goto mainEnd
74
+
75
+ :fail
76
+ rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
77
+ rem the _cmd.exe /c_ return code!
78
+ if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
79
+ exit /b 1
80
+
81
+ :mainEnd
82
+ if "%OS%"=="Windows_NT" endlocal
83
+
84
+ :omega
@@ -0,0 +1,3 @@
1
+ Embulk::JavaPlugin.register_filter(
2
+ "murmur2_partitioner", "org.embulk.filter.murmur2_partitioner.Murmur2PartitionerFilterPlugin",
3
+ File.expand_path('../../../../classpath', __FILE__))
@@ -0,0 +1,27 @@
1
+ package org.embulk.filter.murmur2_partitioner;
2
+
3
+ import org.apache.kafka.common.utils.Utils;
4
+
5
+ import java.io.UnsupportedEncodingException;
6
+
7
+ public class Murmur2Partitioner {
8
+ static int partition(String key, int partitionCount)
9
+ {
10
+ try {
11
+ return partition(key.getBytes("UTF8"), partitionCount);
12
+ } catch (UnsupportedEncodingException e) {
13
+ throw new RuntimeException("Cannot convert string to byte array");
14
+ }
15
+ }
16
+
17
+ static int partition(Long key, int partitionCount)
18
+ {
19
+ byte[] bytes = new byte[]{(byte)((int)(key >>> 56)), (byte)((int)(key >>> 48)), (byte)((int)(key >>> 40)), (byte)((int)(key >>> 32)), (byte)((int)(key >>> 24)), (byte)((int)(key >>> 16)), (byte)((int)(key >>> 8)), key.byteValue()};
20
+ return partition(bytes, partitionCount);
21
+ }
22
+
23
+ static int partition(byte[] bytes, int partitionCount)
24
+ {
25
+ return Utils.toPositive(Utils.murmur2(bytes)) % partitionCount;
26
+ }
27
+ }
@@ -0,0 +1,177 @@
1
+ package org.embulk.filter.murmur2_partitioner;
2
+
3
+ import com.google.common.collect.ImmutableList;
4
+ import org.embulk.config.*;
5
+ import org.embulk.spi.*;
6
+ import org.embulk.spi.type.LongType;
7
+ import org.embulk.spi.type.StringType;
8
+ import org.embulk.spi.type.Types;
9
+
10
+ public class Murmur2PartitionerFilterPlugin
11
+ implements FilterPlugin
12
+ {
13
+ public interface PluginTask
14
+ extends Task
15
+ {
16
+ @Config("key_column")
17
+ public String getKeyColumn();
18
+
19
+ @Config("partition_column")
20
+ @ConfigDefault("\"partition\"")
21
+ public String getPartitionColumn();
22
+
23
+ @Config("partition_count")
24
+ public int getPartitionCount();
25
+ }
26
+
27
+ @Override
28
+ public void transaction(ConfigSource config, Schema inputSchema,
29
+ FilterPlugin.Control control)
30
+ {
31
+ PluginTask task = config.loadConfig(PluginTask.class);
32
+
33
+ ImmutableList.Builder<Column> listBuilder = ImmutableList.builder();
34
+ boolean hasPartitionColumn = false;
35
+ for (Column column : inputSchema.getColumns()) {
36
+ if (column.getName().equals(task.getKeyColumn())) {
37
+ if (!(column.getType() instanceof StringType || column.getType() instanceof LongType)) {
38
+ throw new ConfigException(String.format("Unsupport %s as key_column (name = %s)", column.getType().getName(), column.getName()));
39
+ }
40
+ }
41
+
42
+ if (column.getName().equals(task.getPartitionColumn())) {
43
+ hasPartitionColumn = true;
44
+ }
45
+
46
+ listBuilder.add(column);
47
+ }
48
+ if (!hasPartitionColumn) {
49
+ listBuilder.add(new Column(inputSchema.getColumnCount(), task.getPartitionColumn(), Types.LONG));
50
+ }
51
+
52
+ Schema outputSchema = new Schema(listBuilder.build());
53
+
54
+ control.run(task.dump(), outputSchema);
55
+ }
56
+
57
+ @Override
58
+ public PageOutput open(TaskSource taskSource, Schema inputSchema,
59
+ Schema outputSchema, PageOutput output)
60
+ {
61
+ PluginTask task = taskSource.loadTask(PluginTask.class);
62
+
63
+ Column partitionColumn = outputSchema.getColumns()
64
+ .stream()
65
+ .filter(column -> column.getName().equals(task.getPartitionColumn()))
66
+ .findFirst()
67
+ .orElseThrow(() -> new RuntimeException("partition column is not found"));
68
+
69
+ return new PageOutput() {
70
+ private PageReader pageReader = new PageReader(inputSchema);
71
+ private PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
72
+ private ColumnVisitorImpl columnVisitor = new ColumnVisitorImpl(task.getKeyColumn(), task.getPartitionCount(), partitionColumn, pageReader, pageBuilder);
73
+
74
+ @Override
75
+ public void add(Page page) {
76
+ pageReader.setPage(page);
77
+ while (pageReader.nextRecord()) {
78
+ inputSchema.visitColumns(columnVisitor);
79
+ pageBuilder.addRecord();
80
+ }
81
+ }
82
+
83
+ @Override
84
+ public void finish() {
85
+ pageBuilder.finish();
86
+ }
87
+
88
+ @Override
89
+ public void close() {
90
+ pageBuilder.close();
91
+ }
92
+ };
93
+ }
94
+
95
+ static class ColumnVisitorImpl implements ColumnVisitor
96
+ {
97
+ private String keyColumn;
98
+ private int partitionCount;
99
+ private Column partitionColumn;
100
+ private PageReader pageReader;
101
+ private PageBuilder pageBuilder;
102
+
103
+ ColumnVisitorImpl(String keyColumn, int partitionCount, Column partitionColumn, PageReader pageReader, PageBuilder pageBuilder) {
104
+ this.keyColumn = keyColumn;
105
+ this.partitionCount = partitionCount;
106
+ this.partitionColumn = partitionColumn;
107
+ this.pageReader = pageReader;
108
+ this.pageBuilder = pageBuilder;
109
+ }
110
+
111
+ @Override
112
+ public void booleanColumn(Column column) {
113
+ if (pageReader.isNull(column)) {
114
+ pageBuilder.setNull(column);
115
+ return;
116
+ }
117
+ pageBuilder.setBoolean(column, pageReader.getBoolean(column));
118
+ }
119
+
120
+ @Override
121
+ public void longColumn(Column column) {
122
+ if (pageReader.isNull(column)) {
123
+ pageBuilder.setNull(column);
124
+ return;
125
+ }
126
+
127
+ if (column.getName().equals(keyColumn)) {
128
+ int partition = Murmur2Partitioner.partition(pageReader.getLong(column), partitionCount);
129
+ pageBuilder.setLong(partitionColumn, partition);
130
+ }
131
+
132
+ pageBuilder.setLong(column, pageReader.getLong(column));
133
+ }
134
+
135
+ @Override
136
+ public void doubleColumn(Column column) {
137
+ if (pageReader.isNull(column)) {
138
+ pageBuilder.setNull(column);
139
+ return;
140
+ }
141
+ pageBuilder.setDouble(column, pageReader.getDouble(column));
142
+ }
143
+
144
+ @Override
145
+ public void stringColumn(Column column) {
146
+ if (pageReader.isNull(column)) {
147
+ pageBuilder.setNull(column);
148
+ return;
149
+ }
150
+
151
+ if (column.getName().equals(keyColumn)) {
152
+ int partition = Murmur2Partitioner.partition(pageReader.getString(column), partitionCount);
153
+ pageBuilder.setLong(partitionColumn, partition);
154
+ }
155
+
156
+ pageBuilder.setString(column, pageReader.getString(column));
157
+ }
158
+
159
+ @Override
160
+ public void timestampColumn(Column column) {
161
+ if (pageReader.isNull(column)) {
162
+ pageBuilder.setNull(column);
163
+ return;
164
+ }
165
+ pageBuilder.setTimestamp(column, pageReader.getTimestamp(column));
166
+ }
167
+
168
+ @Override
169
+ public void jsonColumn(Column column) {
170
+ if (pageReader.isNull(column)) {
171
+ pageBuilder.setNull(column);
172
+ return;
173
+ }
174
+ pageBuilder.setJson(column, pageReader.getJson(column));
175
+ }
176
+ }
177
+ }
@@ -0,0 +1,86 @@
1
+ package org.embulk.filter.murmur2_partitioner;
2
+
3
+ import org.embulk.EmbulkEmbed;
4
+ import org.embulk.EmbulkTestRuntime;
5
+ import org.embulk.config.ConfigSource;
6
+ import org.embulk.spi.*;
7
+ import org.embulk.spi.TestPageBuilderReader.MockPageOutput;
8
+ import org.embulk.spi.type.Type;
9
+ import org.embulk.spi.type.Types;
10
+ import org.embulk.spi.util.Pages;
11
+ import org.embulk.test.EmbulkTests;
12
+ import org.junit.Rule;
13
+ import org.junit.Test;
14
+
15
+ import java.io.IOException;
16
+ import java.util.List;
17
+
18
+ import static org.junit.Assert.assertEquals;
19
+
20
+ public class TestMurmur2PartitionerFilterPlugin
21
+ {
22
+ @Rule
23
+ public EmbulkTestRuntime runtime = new EmbulkTestRuntime();
24
+
25
+ private ConfigSource configSource()
26
+ {
27
+ return EmbulkEmbed.newSystemConfigLoader().fromYamlString(EmbulkTests.readResource("org/embulk/filter/murmur2_partitioner/config.yml"));
28
+ }
29
+
30
+ private Schema inputSchema()
31
+ {
32
+ return schema("key", Types.STRING);
33
+ }
34
+
35
+ private List<Object[]> records;
36
+ private List<Column> outputColumns;
37
+
38
+ @Test
39
+ public void testFilter() throws IOException
40
+ {
41
+ Schema inputSchema = inputSchema();
42
+ MockPageOutput output = new MockPageOutput();
43
+ FilterPlugin plugin = new Murmur2PartitionerFilterPlugin();
44
+ List<Page> pages = PageTestUtils.buildPage(runtime.getBufferAllocator(), inputSchema, "hoge", "fuga", "foo", "bar");
45
+
46
+ plugin.transaction(configSource(), inputSchema(), (taskSource, outputSchema) -> {
47
+ outputColumns = outputSchema.getColumns();
48
+
49
+ try (PageOutput out = plugin.open(taskSource, inputSchema(), outputSchema, output)) {
50
+ for (Page page : pages) {
51
+ out.add(page);
52
+ }
53
+ out.finish();
54
+ }
55
+
56
+ records = Pages.toObjects(outputSchema, output.pages);
57
+ });
58
+
59
+ assertEquals(2, outputColumns.size());
60
+ assertEquals("key", outputColumns.get(0).getName());
61
+ assertEquals("partition", outputColumns.get(1).getName());
62
+ assertEquals(Types.LONG, outputColumns.get(1).getType());
63
+
64
+ assertEquals(4, records.size());
65
+
66
+ assertEquals("hoge", records.get(0)[0]);
67
+ assertEquals(32L, records.get(0)[1]);
68
+ assertEquals("fuga", records.get(1)[0]);
69
+ assertEquals(77L, records.get(1)[1]);
70
+ assertEquals("foo", records.get(2)[0]);
71
+ assertEquals(56L, records.get(2)[1]);
72
+ assertEquals("bar", records.get(3)[0]);
73
+ assertEquals(105L, records.get(3)[1]);
74
+ }
75
+
76
+ public static Schema schema(Object... nameAndTypes)
77
+ {
78
+ Schema.Builder builder = Schema.builder();
79
+ for (int i = 0; i < nameAndTypes.length; i += 2) {
80
+ String name = (String) nameAndTypes[i];
81
+ Type type = (Type) nameAndTypes[i + 1];
82
+ builder.add(name, type);
83
+ }
84
+ return builder.build();
85
+ }
86
+ }
@@ -0,0 +1,2 @@
1
+ key_column: key
2
+ partition_count: 120
metadata ADDED
@@ -0,0 +1,93 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: embulk-filter-murmur2_partitioner
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - joker1007
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2019-10-28 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ requirement: !ruby/object:Gem::Requirement
15
+ requirements:
16
+ - - "~>"
17
+ - !ruby/object:Gem::Version
18
+ version: '1.0'
19
+ name: bundler
20
+ prerelease: false
21
+ type: :development
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '1.0'
27
+ - !ruby/object:Gem::Dependency
28
+ requirement: !ruby/object:Gem::Requirement
29
+ requirements:
30
+ - - "~>"
31
+ - !ruby/object:Gem::Version
32
+ version: '12.0'
33
+ name: rake
34
+ prerelease: false
35
+ type: :development
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '12.0'
41
+ description: Murmur2 Partitioner
42
+ email:
43
+ - kakyoin.hierophant@gmail.com
44
+ executables: []
45
+ extensions: []
46
+ extra_rdoc_files: []
47
+ files:
48
+ - ".gitignore"
49
+ - LICENSE.txt
50
+ - README.md
51
+ - build.gradle
52
+ - classpath/embulk-filter-murmur2_partitioner-0.1.0.jar
53
+ - classpath/kafka-clients-2.3.0.jar
54
+ - classpath/lz4-java-1.6.0.jar
55
+ - classpath/slf4j-api-1.7.26.jar
56
+ - classpath/snappy-java-1.1.7.3.jar
57
+ - classpath/zstd-jni-1.4.0-1.jar
58
+ - config/checkstyle/checkstyle.xml
59
+ - config/checkstyle/default.xml
60
+ - gradle/wrapper/gradle-wrapper.jar
61
+ - gradle/wrapper/gradle-wrapper.properties
62
+ - gradlew
63
+ - gradlew.bat
64
+ - lib/embulk/filter/murmur2_partitioner.rb
65
+ - src/main/java/org/embulk/filter/murmur2_partitioner/Murmur2Partitioner.java
66
+ - src/main/java/org/embulk/filter/murmur2_partitioner/Murmur2PartitionerFilterPlugin.java
67
+ - src/test/java/org/embulk/filter/murmur2_partitioner/TestMurmur2PartitionerFilterPlugin.java
68
+ - src/test/resources/org/embulk/filter/murmur2_partitioner/config.yml
69
+ homepage: https://github.com/joker1007/embulk-filter-murmur2_partitioner
70
+ licenses:
71
+ - MIT
72
+ metadata: {}
73
+ post_install_message:
74
+ rdoc_options: []
75
+ require_paths:
76
+ - lib
77
+ required_ruby_version: !ruby/object:Gem::Requirement
78
+ requirements:
79
+ - - ">="
80
+ - !ruby/object:Gem::Version
81
+ version: '0'
82
+ required_rubygems_version: !ruby/object:Gem::Requirement
83
+ requirements:
84
+ - - ">="
85
+ - !ruby/object:Gem::Version
86
+ version: '0'
87
+ requirements: []
88
+ rubyforge_project:
89
+ rubygems_version: 2.6.8
90
+ signing_key:
91
+ specification_version: 4
92
+ summary: Murmur2 Partitioner filter plugin for Embulk
93
+ test_files: []