embulk-parser-squid_clf_log 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +8 -0
- data/LICENSE.txt +21 -0
- data/README.md +37 -0
- data/build.gradle +99 -0
- data/config/checkstyle/checkstyle.xml +128 -0
- data/config/checkstyle/default.xml +108 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +5 -0
- data/gradlew +172 -0
- data/gradlew.bat +84 -0
- data/lib/embulk/guess/squid_clf_log.rb +61 -0
- data/lib/embulk/parser/squid_clf_log.rb +3 -0
- data/src/main/java/org/embulk/parser/squid_clf_log/SquidClfLogParserPlugin.java +196 -0
- data/src/test/java/org/embulk/parser/squid_clf_log/TestSquidClfLogParserPlugin.java +5 -0
- metadata +87 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: f12d8c5971c2770254ce39cb990e35a444a61fed
|
|
4
|
+
data.tar.gz: 7961699a034dbf0d2012b080c453b3b80f87d1f6
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: fd3bfc608b7a9c895891377f22a496f0efd094d82f9fadc032cd98aff1d684c1c02e9dd5d04d9bbe81694cb3a1899a14778ccefa620955c9bb61915997ca22c6
|
|
7
|
+
data.tar.gz: 45bda7b8127387f8e453b0a90813cbf70d5c2adf1ec4702bf2cda352921768939cff2a4160aed78e3940b88535c9e8c1eeeefa01b6e909dd34787692b9d02122
|
data/.gitignore
ADDED
data/LICENSE.txt
ADDED
|
@@ -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.
|
data/README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
# Squid "Common/Combined Log Format (CLF)" Log parser plugin for Embulk
|
|
2
|
+
|
|
3
|
+
Embulk parser plugin for Squid CLF log (common/combined).
|
|
4
|
+
- Forked from [embulk-parser-apache-log](https://github.com/hiroyuki-sato/embulk-parser-apache-log) (Author: [Hiroyuki Sato](https://github.com/hiroyuki-sato))
|
|
5
|
+
|
|
6
|
+
## Overview
|
|
7
|
+
|
|
8
|
+
* **Plugin type**: parser
|
|
9
|
+
* **Guess supported**: no
|
|
10
|
+
|
|
11
|
+
## Configuration
|
|
12
|
+
|
|
13
|
+
- **format**: log format(common, combined) (string, default: combined)
|
|
14
|
+
|
|
15
|
+
## Example
|
|
16
|
+
|
|
17
|
+
```yaml
|
|
18
|
+
in:
|
|
19
|
+
type: any file input plugin type
|
|
20
|
+
parser:
|
|
21
|
+
type: squid_clf_log
|
|
22
|
+
format: common
|
|
23
|
+
```
|
|
24
|
+
|
|
25
|
+
## Build
|
|
26
|
+
|
|
27
|
+
```
|
|
28
|
+
$ cd embulk-parser-squid_clf_log
|
|
29
|
+
$ ./gradlew gem
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
## Supported log format
|
|
33
|
+
|
|
34
|
+
```
|
|
35
|
+
logformat common %>a %[ui %[un [%tl] "%rm %ru HTTP/%rv" %>Hs %<st %Ss:%Sh
|
|
36
|
+
logformat combined %>a %[ui %[un [%tl] "%rm %ru HTTP/%rv" %>Hs %<st "%{Referer}>h" "%{User-Agent}>h" %Ss:%Sh
|
|
37
|
+
```
|
data/build.gradle
ADDED
|
@@ -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 = "0.2.1"
|
|
17
|
+
|
|
18
|
+
sourceCompatibility = 1.8
|
|
19
|
+
targetCompatibility = 1.8
|
|
20
|
+
|
|
21
|
+
dependencies {
|
|
22
|
+
compile "org.embulk:embulk-core:0.9.23"
|
|
23
|
+
provided "org.embulk:embulk-core:0.9.23"
|
|
24
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
|
25
|
+
testCompile "junit:junit:4.+"
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
|
29
|
+
doFirst { file("classpath").deleteDir() }
|
|
30
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
|
31
|
+
into "classpath"
|
|
32
|
+
}
|
|
33
|
+
clean { delete "classpath" }
|
|
34
|
+
|
|
35
|
+
checkstyle {
|
|
36
|
+
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
|
|
37
|
+
toolVersion = '6.14.1'
|
|
38
|
+
}
|
|
39
|
+
checkstyleMain {
|
|
40
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
41
|
+
ignoreFailures = true
|
|
42
|
+
}
|
|
43
|
+
checkstyleTest {
|
|
44
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
45
|
+
ignoreFailures = true
|
|
46
|
+
}
|
|
47
|
+
task checkstyle(type: Checkstyle) {
|
|
48
|
+
classpath = sourceSets.main.output + sourceSets.test.output
|
|
49
|
+
source = sourceSets.main.allJava + sourceSets.test.allJava
|
|
50
|
+
}
|
|
51
|
+
|
|
52
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
|
53
|
+
jrubyArgs "-S"
|
|
54
|
+
script "gem"
|
|
55
|
+
scriptArgs "build", "${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 "-S"
|
|
61
|
+
script "gem"
|
|
62
|
+
scriptArgs "push", "pkg/${project.name}-${project.version}.gem"
|
|
63
|
+
}
|
|
64
|
+
|
|
65
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) {
|
|
66
|
+
doLast {
|
|
67
|
+
println "> Build succeeded."
|
|
68
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
|
69
|
+
}
|
|
70
|
+
}
|
|
71
|
+
|
|
72
|
+
task gemspec {
|
|
73
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
|
74
|
+
inputs.file "build.gradle"
|
|
75
|
+
outputs.file gemspecFile
|
|
76
|
+
doLast { gemspecFile.write($/
|
|
77
|
+
Gem::Specification.new do |spec|
|
|
78
|
+
spec.name = "${project.name}"
|
|
79
|
+
spec.version = "${project.version}"
|
|
80
|
+
spec.authors = ["Mitsuki Shirase"]
|
|
81
|
+
spec.summary = %[Squid Clf Log parser plugin for Embulk]
|
|
82
|
+
spec.description = %[Parses Squid Clf Log files read by other file input plugins.]
|
|
83
|
+
spec.email = ["lunatilia@users.noreply.github.com"]
|
|
84
|
+
spec.licenses = ["MIT"]
|
|
85
|
+
spec.homepage = "https://github.com/lunatilia/embulk-parser-squid_clf_log"
|
|
86
|
+
|
|
87
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
|
88
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
|
89
|
+
spec.require_paths = ["lib"]
|
|
90
|
+
|
|
91
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
|
92
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
|
93
|
+
spec.add_development_dependency 'rake', ['~> 12.0']
|
|
94
|
+
end
|
|
95
|
+
/$)
|
|
96
|
+
}
|
|
97
|
+
}
|
|
98
|
+
clean { delete "${project.name}.gemspec" }
|
|
99
|
+
|
|
@@ -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>
|
|
Binary file
|
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" "$@"
|
data/gradlew.bat
ADDED
|
@@ -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 +1,61 @@
|
|
|
1
|
+
module Embulk
|
|
2
|
+
module Guess
|
|
3
|
+
|
|
4
|
+
# TODO implement guess plugin to make this command work:
|
|
5
|
+
# $ embulk guess -g "squid_clf_log" partial-config.yml
|
|
6
|
+
#
|
|
7
|
+
# Depending on the file format the plugin uses, you can use choose
|
|
8
|
+
# one of binary guess (GuessPlugin), text guess (TextGuessPlugin),
|
|
9
|
+
# or line guess (LineGuessPlugin).
|
|
10
|
+
|
|
11
|
+
# class SquidClfLog < GuessPlugin
|
|
12
|
+
# Plugin.register_guess("squid_clf_log", self)
|
|
13
|
+
#
|
|
14
|
+
# def guess(config, sample_buffer)
|
|
15
|
+
# if sample_buffer[0,2] == GZIP_HEADER
|
|
16
|
+
# guessed = {}
|
|
17
|
+
# guessed["type"] = "squid_clf_log"
|
|
18
|
+
# guessed["property1"] = "guessed-value"
|
|
19
|
+
# return {"parser" => guessed}
|
|
20
|
+
# else
|
|
21
|
+
# return {}
|
|
22
|
+
# end
|
|
23
|
+
# end
|
|
24
|
+
# end
|
|
25
|
+
|
|
26
|
+
# class SquidClfLog < TextGuessPlugin
|
|
27
|
+
# Plugin.register_guess("squid_clf_log", self)
|
|
28
|
+
#
|
|
29
|
+
# def guess_text(config, sample_text)
|
|
30
|
+
# js = JSON.parse(sample_text) rescue nil
|
|
31
|
+
# if js && js["mykeyword"] == "keyword"
|
|
32
|
+
# guessed = {}
|
|
33
|
+
# guessed["type"] = "squid_clf_log"
|
|
34
|
+
# guessed["property1"] = "guessed-value"
|
|
35
|
+
# return {"parser" => guessed}
|
|
36
|
+
# else
|
|
37
|
+
# return {}
|
|
38
|
+
# end
|
|
39
|
+
# end
|
|
40
|
+
# end
|
|
41
|
+
|
|
42
|
+
# class SquidClfLog < LineGuessPlugin
|
|
43
|
+
# Plugin.register_guess("squid_clf_log", self)
|
|
44
|
+
#
|
|
45
|
+
# def guess_lines(config, sample_lines)
|
|
46
|
+
# all_line_matched = sample_lines.all? do |line|
|
|
47
|
+
# line =~ /mypattern/
|
|
48
|
+
# end
|
|
49
|
+
# if all_line_matched
|
|
50
|
+
# guessed = {}
|
|
51
|
+
# guessed["type"] = "squid_clf_log"
|
|
52
|
+
# guessed["property1"] = "guessed-value"
|
|
53
|
+
# return {"parser" => guessed}
|
|
54
|
+
# else
|
|
55
|
+
# return {}
|
|
56
|
+
# end
|
|
57
|
+
# end
|
|
58
|
+
# end
|
|
59
|
+
|
|
60
|
+
end
|
|
61
|
+
end
|
|
@@ -0,0 +1,196 @@
|
|
|
1
|
+
package org.embulk.parser.squid_clf_log;
|
|
2
|
+
|
|
3
|
+
import org.embulk.config.Config;
|
|
4
|
+
import org.embulk.config.ConfigDefault;
|
|
5
|
+
import org.embulk.config.ConfigDiff;
|
|
6
|
+
import org.embulk.config.ConfigSource;
|
|
7
|
+
import org.embulk.config.Task;
|
|
8
|
+
import org.embulk.config.TaskSource;
|
|
9
|
+
import org.embulk.spi.ParserPlugin;
|
|
10
|
+
import org.embulk.spi.FileInput;
|
|
11
|
+
import org.embulk.spi.PageOutput;
|
|
12
|
+
import org.embulk.spi.Schema;
|
|
13
|
+
import org.embulk.spi.SchemaConfig;
|
|
14
|
+
|
|
15
|
+
import org.embulk.spi.Exec;
|
|
16
|
+
import org.embulk.spi.PageBuilder;
|
|
17
|
+
import org.embulk.spi.util.LineDecoder;
|
|
18
|
+
import org.embulk.spi.type.TimestampType;
|
|
19
|
+
import org.embulk.spi.time.TimestampParser;
|
|
20
|
+
import org.embulk.spi.time.TimestampParseException;
|
|
21
|
+
import org.embulk.spi.ColumnConfig;
|
|
22
|
+
import java.util.ArrayList;
|
|
23
|
+
|
|
24
|
+
//import static org.embulk.spi.type.Types.BOOLEAN;
|
|
25
|
+
//import static org.embulk.spi.type.Types.DOUBLE;
|
|
26
|
+
//import static org.embulk.spi.type.Types.LONG;
|
|
27
|
+
import static org.embulk.spi.type.Types.STRING;
|
|
28
|
+
import static org.embulk.spi.type.Types.TIMESTAMP;
|
|
29
|
+
|
|
30
|
+
import java.util.regex.Matcher;
|
|
31
|
+
import java.util.regex.Pattern;
|
|
32
|
+
|
|
33
|
+
import com.google.common.base.Throwables;
|
|
34
|
+
|
|
35
|
+
import org.slf4j.Logger;
|
|
36
|
+
|
|
37
|
+
public class SquidClfLogParserPlugin
|
|
38
|
+
implements ParserPlugin
|
|
39
|
+
{
|
|
40
|
+
private static final Logger logger = Exec.getLogger(SquidClfLogParserPlugin.class);
|
|
41
|
+
|
|
42
|
+
public enum LogFormat
|
|
43
|
+
{
|
|
44
|
+
combined("combined"),
|
|
45
|
+
common("common");
|
|
46
|
+
private final String string;
|
|
47
|
+
|
|
48
|
+
private LogFormat(String string)
|
|
49
|
+
{
|
|
50
|
+
this.string = string;
|
|
51
|
+
}
|
|
52
|
+
public String getString()
|
|
53
|
+
{
|
|
54
|
+
return string;
|
|
55
|
+
}
|
|
56
|
+
}
|
|
57
|
+
public interface PluginTask
|
|
58
|
+
extends Task, LineDecoder.DecoderTask, TimestampParser.Task
|
|
59
|
+
{
|
|
60
|
+
|
|
61
|
+
@Config("format")
|
|
62
|
+
@ConfigDefault("\"combined\"")
|
|
63
|
+
public LogFormat getFormat();
|
|
64
|
+
|
|
65
|
+
@Config("stop_on_invalid_record")
|
|
66
|
+
@ConfigDefault("true")
|
|
67
|
+
Boolean getStopOnInvalidRecord();
|
|
68
|
+
}
|
|
69
|
+
|
|
70
|
+
@Override
|
|
71
|
+
public void transaction(ConfigSource config, ParserPlugin.Control control)
|
|
72
|
+
{
|
|
73
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
|
74
|
+
ArrayList<ColumnConfig> columns = new ArrayList<ColumnConfig>();
|
|
75
|
+
final LogFormat format = task.getFormat();
|
|
76
|
+
|
|
77
|
+
columns.add(new ColumnConfig("client-src-ip-address" ,STRING ,config));
|
|
78
|
+
columns.add(new ColumnConfig("request-username-ident",STRING ,config));
|
|
79
|
+
columns.add(new ColumnConfig("request-username" ,STRING ,config));
|
|
80
|
+
columns.add(new ColumnConfig("request-time" ,TIMESTAMP,config));
|
|
81
|
+
columns.add(new ColumnConfig("request-method" ,STRING ,config));
|
|
82
|
+
columns.add(new ColumnConfig("request-url" ,STRING ,config));
|
|
83
|
+
columns.add(new ColumnConfig("request-protocol" ,STRING ,config));
|
|
84
|
+
columns.add(new ColumnConfig("response-status" ,STRING ,config));
|
|
85
|
+
columns.add(new ColumnConfig("response-bytes" ,STRING ,config));
|
|
86
|
+
|
|
87
|
+
// combined
|
|
88
|
+
if( format == LogFormat.combined ){
|
|
89
|
+
columns.add(new ColumnConfig("referer" ,STRING ,config));
|
|
90
|
+
columns.add(new ColumnConfig("user-agent" ,STRING ,config));
|
|
91
|
+
}
|
|
92
|
+
|
|
93
|
+
// squid status
|
|
94
|
+
columns.add(new ColumnConfig("squid-status" ,STRING ,config));
|
|
95
|
+
columns.add(new ColumnConfig("squid-hierarchy-status",STRING ,config));
|
|
96
|
+
|
|
97
|
+
Schema schema = new SchemaConfig(columns).toSchema();
|
|
98
|
+
control.run(task.dump(), schema);
|
|
99
|
+
}
|
|
100
|
+
|
|
101
|
+
private static interface ParserIntlTask extends Task, TimestampParser.Task {}
|
|
102
|
+
private static interface ParserIntlColumnOption extends Task, TimestampParser.TimestampColumnOption {}
|
|
103
|
+
|
|
104
|
+
@Override
|
|
105
|
+
public void run(TaskSource taskSource, Schema schema,
|
|
106
|
+
FileInput input, PageOutput output)
|
|
107
|
+
{
|
|
108
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
109
|
+
LineDecoder lineDecoder = new LineDecoder(input,task);
|
|
110
|
+
PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), schema, output);
|
|
111
|
+
String line = null;
|
|
112
|
+
final LogFormat format = task.getFormat();
|
|
113
|
+
|
|
114
|
+
Pattern accessLogPattern = Pattern.compile(getAccessLogRegex(format),
|
|
115
|
+
Pattern.CASE_INSENSITIVE
|
|
116
|
+
| Pattern.DOTALL);
|
|
117
|
+
Matcher accessLogEntryMatcher;
|
|
118
|
+
// TODO: Switch to a newer TimestampParser constructor after a reasonable interval.
|
|
119
|
+
// Traditional constructor is used here for compatibility.
|
|
120
|
+
final ConfigSource configSource = Exec.newConfigSource();
|
|
121
|
+
configSource.set("format", "%d/%b/%Y:%T %z");
|
|
122
|
+
configSource.set("timezone", task.getDefaultTimeZone());
|
|
123
|
+
final TimestampParser time_parser = new TimestampParser(
|
|
124
|
+
Exec.newConfigSource().loadConfig(ParserIntlTask.class),
|
|
125
|
+
configSource.loadConfig(ParserIntlColumnOption.class));
|
|
126
|
+
|
|
127
|
+
while( input.nextFile() ){
|
|
128
|
+
while(true){
|
|
129
|
+
line = lineDecoder.poll();
|
|
130
|
+
|
|
131
|
+
if( line == null ){
|
|
132
|
+
break;
|
|
133
|
+
}
|
|
134
|
+
accessLogEntryMatcher = accessLogPattern.matcher(line);
|
|
135
|
+
|
|
136
|
+
if(!accessLogEntryMatcher.matches()){
|
|
137
|
+
if (task.getStopOnInvalidRecord()) {
|
|
138
|
+
throw new RuntimeException("unmatched line" + line);
|
|
139
|
+
} else {
|
|
140
|
+
logger.info("unable to parse line: " + line);
|
|
141
|
+
continue;
|
|
142
|
+
}
|
|
143
|
+
}
|
|
144
|
+
|
|
145
|
+
pageBuilder.setString(0,accessLogEntryMatcher.group(1));
|
|
146
|
+
pageBuilder.setString(1,accessLogEntryMatcher.group(2));
|
|
147
|
+
pageBuilder.setString(2,accessLogEntryMatcher.group(3));
|
|
148
|
+
try {
|
|
149
|
+
pageBuilder.setTimestamp(3,time_parser.parse(accessLogEntryMatcher.group(4)));
|
|
150
|
+
} catch(TimestampParseException ex) {
|
|
151
|
+
if (task.getStopOnInvalidRecord()) {
|
|
152
|
+
throw Throwables.propagate(ex);
|
|
153
|
+
} else {
|
|
154
|
+
logger.info("unable to parse time from line: " + line);
|
|
155
|
+
continue;
|
|
156
|
+
}
|
|
157
|
+
}
|
|
158
|
+
pageBuilder.setString(4,accessLogEntryMatcher.group(5));
|
|
159
|
+
pageBuilder.setString(5,accessLogEntryMatcher.group(6));
|
|
160
|
+
pageBuilder.setString(6,accessLogEntryMatcher.group(7));
|
|
161
|
+
pageBuilder.setString(7,accessLogEntryMatcher.group(8));
|
|
162
|
+
pageBuilder.setString(8,accessLogEntryMatcher.group(9));
|
|
163
|
+
pageBuilder.setString(9,accessLogEntryMatcher.group(10));
|
|
164
|
+
pageBuilder.setString(10,accessLogEntryMatcher.group(11));
|
|
165
|
+
if( format == LogFormat.combined ){
|
|
166
|
+
pageBuilder.setString(11,accessLogEntryMatcher.group(12));
|
|
167
|
+
pageBuilder.setString(12,accessLogEntryMatcher.group(13));
|
|
168
|
+
}
|
|
169
|
+
pageBuilder.addRecord();
|
|
170
|
+
}
|
|
171
|
+
}
|
|
172
|
+
pageBuilder.finish();
|
|
173
|
+
}
|
|
174
|
+
|
|
175
|
+
private String getAccessLogRegex(LogFormat type)
|
|
176
|
+
{
|
|
177
|
+
final String nospace = "(\\S+)"; // a single token (no spaces)
|
|
178
|
+
final String timestamp = "\\[([^\\]]+)\\]"; // something between [ and ]
|
|
179
|
+
final String quotestr = "\"(.*?)\""; // a quoted string
|
|
180
|
+
final String uint = "(\\d+)"; // unsigned integer
|
|
181
|
+
final String query = "\"(\\S+)\\s(.*?)\\s(\\S+{4}\\/\\d+\\.\\d+)\""; // method, path, protocol
|
|
182
|
+
final String sqstat = "(\\S+)\\:(\\S+)"; // squid status
|
|
183
|
+
|
|
184
|
+
String rex;
|
|
185
|
+
|
|
186
|
+
if( type == LogFormat.combined ){
|
|
187
|
+
rex = "^" + String.join( " ", nospace, nospace, nospace, timestamp, query,
|
|
188
|
+
uint, nospace, quotestr, quotestr, sqstat) + "$";
|
|
189
|
+
} else {
|
|
190
|
+
rex = "^" + String.join( " ", nospace, nospace, nospace, timestamp, query,
|
|
191
|
+
uint, nospace, sqstat) + "$";
|
|
192
|
+
}
|
|
193
|
+
|
|
194
|
+
return rex;
|
|
195
|
+
}
|
|
196
|
+
}
|
metadata
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: embulk-parser-squid_clf_log
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.2.1
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Mitsuki Shirase
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2020-03-18 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: Parses Squid Clf Log files read by other file input plugins.
|
|
42
|
+
email:
|
|
43
|
+
- lunatilia@users.noreply.github.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-parser-squid_clf_log-0.2.1.jar
|
|
53
|
+
- config/checkstyle/checkstyle.xml
|
|
54
|
+
- config/checkstyle/default.xml
|
|
55
|
+
- gradle/wrapper/gradle-wrapper.jar
|
|
56
|
+
- gradle/wrapper/gradle-wrapper.properties
|
|
57
|
+
- gradlew
|
|
58
|
+
- gradlew.bat
|
|
59
|
+
- lib/embulk/guess/squid_clf_log.rb
|
|
60
|
+
- lib/embulk/parser/squid_clf_log.rb
|
|
61
|
+
- src/main/java/org/embulk/parser/squid_clf_log/SquidClfLogParserPlugin.java
|
|
62
|
+
- src/test/java/org/embulk/parser/squid_clf_log/TestSquidClfLogParserPlugin.java
|
|
63
|
+
homepage: https://github.com/lunatilia/embulk-parser-squid_clf_log
|
|
64
|
+
licenses:
|
|
65
|
+
- MIT
|
|
66
|
+
metadata: {}
|
|
67
|
+
post_install_message:
|
|
68
|
+
rdoc_options: []
|
|
69
|
+
require_paths:
|
|
70
|
+
- lib
|
|
71
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
72
|
+
requirements:
|
|
73
|
+
- - ">="
|
|
74
|
+
- !ruby/object:Gem::Version
|
|
75
|
+
version: '0'
|
|
76
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
77
|
+
requirements:
|
|
78
|
+
- - ">="
|
|
79
|
+
- !ruby/object:Gem::Version
|
|
80
|
+
version: '0'
|
|
81
|
+
requirements: []
|
|
82
|
+
rubyforge_project:
|
|
83
|
+
rubygems_version: 2.6.8
|
|
84
|
+
signing_key:
|
|
85
|
+
specification_version: 4
|
|
86
|
+
summary: Squid Clf Log parser plugin for Embulk
|
|
87
|
+
test_files: []
|