embulk-filter-timestamp_hs 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 646832a578511eb8db66515179cee4d156ccf65a
4
+ data.tar.gz: d6aff4d530da613f5362ee388eb71716dea2d3aa
5
+ SHA512:
6
+ metadata.gz: 5201eacf00f8e760c3ca52aaa22751eaaf3da84dd87458f9a4c5bfbd52f2ad2a20e2b0b9cf633ac631c0b8ea7c8ca58aa2de61447c1c015ab2851519d7a8a79c
7
+ data.tar.gz: 137cca030242677b1f1c2c59258f218a46a6921cca5f4ae35ac3cead56f043a1174e3d9239fc809ef151fe15b2bd5bb80f1a4d1410c35e1d8ff74d0b1ff5ac5d
@@ -0,0 +1,13 @@
1
+ *~
2
+ /pkg/
3
+ /tmp/
4
+ *.gemspec
5
+ .gradle/
6
+ /classpath/
7
+ build/
8
+ .idea
9
+ /.settings/
10
+ /.metadata/
11
+ .classpath
12
+ .project
13
+ *.iml
@@ -0,0 +1,10 @@
1
+ language: java
2
+
3
+ jdk:
4
+ - openjdk7
5
+
6
+ before_install:
7
+ - chmod +x gradlew
8
+
9
+ script:
10
+ - "./gradlew test"
@@ -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 +1,75 @@
1
+ # Timestamp Hs filter plugin for Embulk
2
+
3
+ [![Build Status](https://travis-ci.org/arenahito/embulk-filter-timestamp_hs.svg?branch=master)](https://travis-ci.org/arenahito/embulk-filter-timestamp_hs)
4
+
5
+ Convert string to timestamp at high speed.
6
+
7
+ ## Overview
8
+
9
+ * **Plugin type**: filter
10
+
11
+ ## Configuration
12
+
13
+ - **default_timezone**: Default timezone (string, default: `UTC`)
14
+ - **default_timestamp_format**: Default timezone format by [SimpleDateFormat](http://docs.oracle.com/javase/7/docs/api/java/text/SimpleDateFormat.html) style (string, default: `yyyy-MM-dd hh:mm:ss`)
15
+ - **column_options**: Timestamp column options (hash, required)
16
+ - **timezone**: Timezone (hash, default: `default_timezone`)
17
+ - **format**: Timestamp format (hash, default: `default_timestamp_format`)
18
+
19
+ ## Example
20
+
21
+ ```csv
22
+ 2016-01-01 10:02:30.100,2016-01-01 10:02:30.111
23
+ 2016-01-02 10:02:30.200,2016-01-02 10:02:30.211
24
+ 2016-01-03 10:02:30.300,2016-01-03 10:02:30.311
25
+ 2016-01-04 10:02:30.400,2016-01-04 10:02:30.411
26
+ 2016-01-05 10:02:30.500,2016-01-05 10:02:30.511
27
+ ```
28
+
29
+ ```yaml
30
+ in:
31
+ type: file
32
+ path_prefix: applog
33
+ parser:
34
+ type: csv
35
+ delimiter: ","
36
+ columns:
37
+ - {name: standardTimestamp, type: timestamp, format: '%Y-%m-%d %H:%M:%S.%L'}
38
+ - {name: highSpeedTimestamp, type: string}
39
+
40
+ filters:
41
+ - type: timestamp_hs
42
+ default_timezone: 'UTC'
43
+ column_options:
44
+ highSpeedTimestamp: {format: 'yyyy-MM-dd hh:mm:ss.SSS'}
45
+ ```
46
+
47
+ ```sh
48
+ +-----------------------------+------------------------------+
49
+ | standardTimestamp:timestamp | highSpeedTimestamp:timestamp |
50
+ +-----------------------------+------------------------------+
51
+ | 2016-01-01 10:02:30.100 UTC | 2016-01-01 10:02:30.111 UTC |
52
+ | 2016-01-02 10:02:30.200 UTC | 2016-01-02 10:02:30.211 UTC |
53
+ | 2016-01-03 10:02:30.300 UTC | 2016-01-03 10:02:30.311 UTC |
54
+ | 2016-01-04 10:02:30.400 UTC | 2016-01-04 10:02:30.411 UTC |
55
+ | 2016-01-05 10:02:30.500 UTC | 2016-01-05 10:02:30.511 UTC |
56
+ +-----------------------------+------------------------------+
57
+ ```
58
+
59
+ ## Performance
60
+
61
+ Input file is 1,000,000 lines with one timestamp column.
62
+
63
+ - OS: Windows 10
64
+ - CPU: Core i5 2.67GHz
65
+ - Embulk: 0.8.6
66
+
67
+ Embulk standard timestamp: 240.910s
68
+
69
+ With timestamp_hs filter: 1.902s
70
+
71
+ ## Install
72
+
73
+ ```sh
74
+ $ embulk gem install embulk-filter-timestamp_hs
75
+ ```
@@ -0,0 +1,95 @@
1
+ plugins {
2
+ id "com.jfrog.bintray" version "1.1"
3
+ id "com.github.jruby-gradle.base" version "0.1.5"
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 = 1.7
19
+ targetCompatibility = 1.7
20
+
21
+ dependencies {
22
+ compile "org.embulk:embulk-core:0.8.6"
23
+ provided "org.embulk:embulk-core:0.8.6"
24
+ // compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
25
+ testCompile "junit:junit:4.+"
26
+ testCompile "org.embulk:embulk-core:0.8.6:tests"
27
+ }
28
+
29
+ task classpath(type: Copy, dependsOn: ["jar"]) {
30
+ doFirst { file("classpath").deleteDir() }
31
+ from (configurations.runtime - configurations.provided + files(jar.archivePath))
32
+ into "classpath"
33
+ }
34
+ clean { delete "classpath" }
35
+
36
+ checkstyle {
37
+ configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
38
+ toolVersion = '6.14.1'
39
+ }
40
+ checkstyleMain {
41
+ configFile = file("${project.rootDir}/config/checkstyle/default.xml")
42
+ ignoreFailures = true
43
+ }
44
+ checkstyleTest {
45
+ configFile = file("${project.rootDir}/config/checkstyle/default.xml")
46
+ ignoreFailures = true
47
+ }
48
+ task checkstyle(type: Checkstyle) {
49
+ classpath = sourceSets.main.output + sourceSets.test.output
50
+ source = sourceSets.main.allJava + sourceSets.test.allJava
51
+ }
52
+
53
+ task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
54
+ jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
55
+ script "${project.name}.gemspec"
56
+ doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
57
+ }
58
+
59
+ task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
60
+ jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
61
+ script "pkg/${project.name}-${project.version}.gem"
62
+ }
63
+
64
+ task "package"(dependsOn: ["gemspec", "classpath"]) << {
65
+ println "> Build succeeded."
66
+ println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
67
+ }
68
+
69
+ task gemspec {
70
+ ext.gemspecFile = file("${project.name}.gemspec")
71
+ inputs.file "build.gradle"
72
+ outputs.file gemspecFile
73
+ doLast { gemspecFile.write($/
74
+ Gem::Specification.new do |spec|
75
+ spec.name = "${project.name}"
76
+ spec.version = "${project.version}"
77
+ spec.authors = ["Matsuoka Takashi"]
78
+ spec.summary = %[Timestamp Hs filter plugin for Embulk]
79
+ spec.description = %[Convert string to timestamp at high speed.]
80
+ spec.email = ["mt@xfutures.jp"]
81
+ spec.licenses = ["MIT"]
82
+ spec.homepage = "https://github.com/arenahito/embulk-filter-timestamp_hs"
83
+
84
+ spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
85
+ spec.test_files = spec.files.grep(%r"^(test|spec)/")
86
+ spec.require_paths = ["lib"]
87
+
88
+ #spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
89
+ spec.add_development_dependency 'bundler', ['~> 1.0']
90
+ spec.add_development_dependency 'rake', ['>= 10.0']
91
+ end
92
+ /$)
93
+ }
94
+ }
95
+ 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>