embulk-parser-regex 0.1.0
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 +20 -0
- data/README.md +55 -0
- data/build.gradle +74 -0
- data/embulk-parser-regex.iml +49 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/gradlew +164 -0
- data/gradlew.bat +90 -0
- data/lib/embulk/guess/regex.rb +141 -0
- data/lib/embulk/parser/regex.rb +3 -0
- data/sample/apache_1/config.yml +23 -0
- data/sample/apache_1/data_apache_1.txt +2 -0
- data/sample/apache_1/pre_config.yml +9 -0
- data/sample/apache_2/config.yml +22 -0
- data/sample/apache_2/data_apache_1.txt +2 -0
- data/sample/apache_2/pre_config.yml +9 -0
- data/sample/simple/config_simple.yml +16 -0
- data/sample/simple/data_simple_1.txt +3 -0
- data/src/main/java/org/embulk/parser/regex/RegexParserPlugin.java +139 -0
- data/src/test/java/org/embulk/parser/regex/TestRegexParserPlugin.java +5 -0
- metadata +95 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 5334bd1ab64c181d169a2eb53c1ae9c0888ee8a2
|
|
4
|
+
data.tar.gz: 03e5d5c3d3183d2ce0bd26cd9dfcf1383fb5a5b3
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 3271593ae11fba49ce1b5171342492249ddfdda1f50c1ad9ca0bed0046fbebdba64efb109cd386bae3d9f3dfb1c24d309fa07d5c32b4a0abdb580810a9f30a1b
|
|
7
|
+
data.tar.gz: ebb736e2051d8604e4ec21f9ddcce9aa449dd36e4ac1bf4ccce4a9376220078597a1a4802204213f3c5ede5c9971f39b16df6303c1f00df37f851c634108fcb3
|
data/.gitignore
ADDED
data/LICENSE.txt
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
Copyright (c) 2015 Ken Morishita, Powered By Yumemi Inc.
|
|
2
|
+
|
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
|
4
|
+
a copy of this software and associated documentation files (the
|
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
|
9
|
+
the following conditions:
|
|
10
|
+
|
|
11
|
+
The above copyright notice and this permission notice shall be
|
|
12
|
+
included in all copies or substantial portions of the Software.
|
|
13
|
+
|
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
# Regex parser plugin for Embulk
|
|
2
|
+
|
|
3
|
+
A simple parser Using Regular Expression.
|
|
4
|
+
|
|
5
|
+
## Overview
|
|
6
|
+
|
|
7
|
+
* **Plugin type**: parser
|
|
8
|
+
* **Guess supported**: yes
|
|
9
|
+
|
|
10
|
+
## Configuration
|
|
11
|
+
|
|
12
|
+
- **regex**: regular expression that must use [Named Capturing Group](https://blogs.oracle.com/xuemingshen/entry/named_capturing_group_in_jdk7) (string, required)
|
|
13
|
+
- **columns**: column definition (list of object)
|
|
14
|
+
- **regexName**: 'Named Capturing Group' can only include `[a-zA-Z0-9]`, so alias group name in regex can be specified (string, default: `<name> attr value`)
|
|
15
|
+
- **skip_if_unmatch**: if false, when a line don't match the regex, raise RuntimeException. If true, skip the line. (boolean, default: `false`)
|
|
16
|
+
|
|
17
|
+
## Example
|
|
18
|
+
|
|
19
|
+
```yaml
|
|
20
|
+
in:
|
|
21
|
+
type: any file input plugin type
|
|
22
|
+
parser:
|
|
23
|
+
type: regex
|
|
24
|
+
regex: ^(?<remoteHost>[.:0-9]+) (?<identity>\S+) (?<user>\S+) \[(?<datetime>[^\]]*)\] "((?<method>\S+) (?<path>\S+) (?<protocol>HTTP/\d+\.\d+)|-)" (?<status>[0-9]+) (?<size>[0-9]+|-) "(?<referer>[^"]*)" "(?<userAgent>[^"]*)" (?<inByte>[0-9]+) (?<outByte>[0-9]+)$
|
|
25
|
+
columns:
|
|
26
|
+
- {name: remote_host, type: string, regexName: remoteHost}
|
|
27
|
+
- {name: identity, type: string}
|
|
28
|
+
- {name: user, type: string}
|
|
29
|
+
- {name: datetime, type: timestamp, format: '%d/%b/%Y:%H:%M:%S %z'}
|
|
30
|
+
- {name: method, type: string}
|
|
31
|
+
- {name: path, type: string}
|
|
32
|
+
- {name: protocol, type: string}
|
|
33
|
+
- {name: status, type: long}
|
|
34
|
+
- {name: size, type: long}
|
|
35
|
+
- {name: referer, type: string}
|
|
36
|
+
- {name: user_agent, type: string, regexName: userAgent}
|
|
37
|
+
- {name: in_byte, type: long, regexName: inByte}
|
|
38
|
+
- {name: out_byte, type: long, regexName: outByte}
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
### Guess
|
|
42
|
+
Some apache LogFormats can be guessed.
|
|
43
|
+
After writing `in:` section, you can let embulk guess `parser:` section using this command:
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
```
|
|
47
|
+
$ embulk gem install embulk-parser-regex
|
|
48
|
+
$ embulk guess -g regex config.yml -o guessed.yml
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
## Build
|
|
52
|
+
|
|
53
|
+
```
|
|
54
|
+
$ ./gradlew gem # -t to watch change of files and rebuild continuously
|
|
55
|
+
```
|
data/build.gradle
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
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
|
+
}
|
|
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
|
+
dependencies {
|
|
19
|
+
compile "org.embulk:embulk-core:0.7.4"
|
|
20
|
+
provided "org.embulk:embulk-core:0.7.4"
|
|
21
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
|
22
|
+
testCompile "junit:junit:4.+"
|
|
23
|
+
}
|
|
24
|
+
|
|
25
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
|
26
|
+
doFirst { file("classpath").deleteDir() }
|
|
27
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
|
28
|
+
into "classpath"
|
|
29
|
+
}
|
|
30
|
+
clean { delete "classpath" }
|
|
31
|
+
|
|
32
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
|
33
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
|
34
|
+
script "${project.name}.gemspec"
|
|
35
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
|
39
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
|
40
|
+
script "pkg/${project.name}-${project.version}.gem"
|
|
41
|
+
}
|
|
42
|
+
|
|
43
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) << {
|
|
44
|
+
println "> Build succeeded."
|
|
45
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
task gemspec {
|
|
49
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
|
50
|
+
inputs.file "build.gradle"
|
|
51
|
+
outputs.file gemspecFile
|
|
52
|
+
doLast { gemspecFile.write($/
|
|
53
|
+
Gem::Specification.new do |spec|
|
|
54
|
+
spec.name = "${project.name}"
|
|
55
|
+
spec.version = "${project.version}"
|
|
56
|
+
spec.authors = ["Ken Morishita"]
|
|
57
|
+
spec.summary = %[Regex parser plugin for Embulk]
|
|
58
|
+
spec.description = %[Parses lines using regular-expression in files read by other file input plugins.]
|
|
59
|
+
spec.email = ["mokemokechicken@gmail.com"]
|
|
60
|
+
spec.licenses = ["MIT"]
|
|
61
|
+
spec.homepage = "https://github.com/mokemokechicken/embulk-parser-regex"
|
|
62
|
+
|
|
63
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
|
64
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
|
65
|
+
spec.require_paths = ["lib"]
|
|
66
|
+
|
|
67
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
|
68
|
+
spec.add_development_dependency 'rake', ['~> 10.0']
|
|
69
|
+
end
|
|
70
|
+
/$)
|
|
71
|
+
}
|
|
72
|
+
}
|
|
73
|
+
clean { delete "${project.name}.gemspec" }
|
|
74
|
+
|
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
|
2
|
+
<module external.linked.project.id="embulk-parser-regex" external.linked.project.path="$MODULE_DIR$" external.root.project.path="$MODULE_DIR$" external.system.id="GRADLE" external.system.module.group="" external.system.module.version="0.1.0" type="JAVA_MODULE" version="4">
|
|
3
|
+
<component name="NewModuleRootManager" inherit-compiler-output="false">
|
|
4
|
+
<output url="file://$MODULE_DIR$/build/classes/main" />
|
|
5
|
+
<output-test url="file://$MODULE_DIR$/build/classes/test" />
|
|
6
|
+
<exclude-output />
|
|
7
|
+
<content url="file://$MODULE_DIR$">
|
|
8
|
+
<sourceFolder url="file://$MODULE_DIR$/src/main/java" isTestSource="false" />
|
|
9
|
+
<sourceFolder url="file://$MODULE_DIR$/src/test/java" isTestSource="true" />
|
|
10
|
+
<sourceFolder url="file://$MODULE_DIR$/src/main/resources" type="java-resource" />
|
|
11
|
+
<sourceFolder url="file://$MODULE_DIR$/src/test/resources" type="java-test-resource" />
|
|
12
|
+
<excludeFolder url="file://$MODULE_DIR$/.gradle" />
|
|
13
|
+
<excludeFolder url="file://$MODULE_DIR$/build" />
|
|
14
|
+
</content>
|
|
15
|
+
<orderEntry type="inheritedJdk" />
|
|
16
|
+
<orderEntry type="sourceFolder" forTests="false" />
|
|
17
|
+
<orderEntry type="library" name="Gradle: org.embulk:embulk-core:0.7.4" level="project" />
|
|
18
|
+
<orderEntry type="library" name="Gradle: com.google.guava:guava:18.0" level="project" />
|
|
19
|
+
<orderEntry type="library" name="Gradle: com.google.inject:guice:4.0" level="project" />
|
|
20
|
+
<orderEntry type="library" name="Gradle: com.google.inject.extensions:guice-multibindings:4.0" level="project" />
|
|
21
|
+
<orderEntry type="library" name="Gradle: javax.inject:javax.inject:1" level="project" />
|
|
22
|
+
<orderEntry type="library" name="Gradle: com.fasterxml.jackson.core:jackson-annotations:2.5.3" level="project" />
|
|
23
|
+
<orderEntry type="library" name="Gradle: com.fasterxml.jackson.core:jackson-core:2.5.3" level="project" />
|
|
24
|
+
<orderEntry type="library" name="Gradle: com.fasterxml.jackson.core:jackson-databind:2.5.3" level="project" />
|
|
25
|
+
<orderEntry type="library" name="Gradle: com.fasterxml.jackson.datatype:jackson-datatype-guava:2.5.3" level="project" />
|
|
26
|
+
<orderEntry type="library" name="Gradle: com.fasterxml.jackson.datatype:jackson-datatype-joda:2.5.3" level="project" />
|
|
27
|
+
<orderEntry type="library" name="Gradle: com.fasterxml.jackson.module:jackson-module-guice:2.5.3" level="project" />
|
|
28
|
+
<orderEntry type="library" name="Gradle: ch.qos.logback:logback-classic:1.1.3" level="project" />
|
|
29
|
+
<orderEntry type="library" name="Gradle: org.slf4j:slf4j-api:1.7.12" level="project" />
|
|
30
|
+
<orderEntry type="library" name="Gradle: org.jruby:jruby-complete:9.0.0.0" level="project" />
|
|
31
|
+
<orderEntry type="library" name="Gradle: com.google.code.findbugs:annotations:3.0.0" level="project" />
|
|
32
|
+
<orderEntry type="library" name="Gradle: org.yaml:snakeyaml:1.14" level="project" />
|
|
33
|
+
<orderEntry type="library" name="Gradle: javax.validation:validation-api:1.1.0.Final" level="project" />
|
|
34
|
+
<orderEntry type="library" name="Gradle: org.apache.bval:bval-jsr303:0.5" level="project" />
|
|
35
|
+
<orderEntry type="library" name="Gradle: io.airlift:slice:0.9" level="project" />
|
|
36
|
+
<orderEntry type="library" name="Gradle: joda-time:joda-time:2.8.1" level="project" />
|
|
37
|
+
<orderEntry type="library" name="Gradle: io.netty:netty-buffer:5.0.0.Alpha1" level="project" />
|
|
38
|
+
<orderEntry type="library" name="Gradle: org.fusesource.jansi:jansi:1.11" level="project" />
|
|
39
|
+
<orderEntry type="library" name="Gradle: com.ibm.icu:icu4j:54.1.1" level="project" />
|
|
40
|
+
<orderEntry type="library" name="Gradle: aopalliance:aopalliance:1.0" level="project" />
|
|
41
|
+
<orderEntry type="library" name="Gradle: ch.qos.logback:logback-core:1.1.3" level="project" />
|
|
42
|
+
<orderEntry type="library" name="Gradle: org.apache.bval:bval-core:0.5" level="project" />
|
|
43
|
+
<orderEntry type="library" name="Gradle: org.apache.commons:commons-lang3:3.1" level="project" />
|
|
44
|
+
<orderEntry type="library" name="Gradle: io.netty:netty-common:5.0.0.Alpha1" level="project" />
|
|
45
|
+
<orderEntry type="library" name="Gradle: commons-beanutils:commons-beanutils-core:1.8.3" level="project" />
|
|
46
|
+
<orderEntry type="library" scope="TEST" name="Gradle: junit:junit:4.12" level="project" />
|
|
47
|
+
<orderEntry type="library" scope="TEST" name="Gradle: org.hamcrest:hamcrest-core:1.3" level="project" />
|
|
48
|
+
</component>
|
|
49
|
+
</module>
|
|
Binary file
|
data/gradlew
ADDED
|
@@ -0,0 +1,164 @@
|
|
|
1
|
+
#!/usr/bin/env bash
|
|
2
|
+
|
|
3
|
+
##############################################################################
|
|
4
|
+
##
|
|
5
|
+
## Gradle start up script for UN*X
|
|
6
|
+
##
|
|
7
|
+
##############################################################################
|
|
8
|
+
|
|
9
|
+
# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
|
|
10
|
+
DEFAULT_JVM_OPTS=""
|
|
11
|
+
|
|
12
|
+
APP_NAME="Gradle"
|
|
13
|
+
APP_BASE_NAME=`basename "$0"`
|
|
14
|
+
|
|
15
|
+
# Use the maximum available, or set MAX_FD != -1 to use that value.
|
|
16
|
+
MAX_FD="maximum"
|
|
17
|
+
|
|
18
|
+
warn ( ) {
|
|
19
|
+
echo "$*"
|
|
20
|
+
}
|
|
21
|
+
|
|
22
|
+
die ( ) {
|
|
23
|
+
echo
|
|
24
|
+
echo "$*"
|
|
25
|
+
echo
|
|
26
|
+
exit 1
|
|
27
|
+
}
|
|
28
|
+
|
|
29
|
+
# OS specific support (must be 'true' or 'false').
|
|
30
|
+
cygwin=false
|
|
31
|
+
msys=false
|
|
32
|
+
darwin=false
|
|
33
|
+
case "`uname`" in
|
|
34
|
+
CYGWIN* )
|
|
35
|
+
cygwin=true
|
|
36
|
+
;;
|
|
37
|
+
Darwin* )
|
|
38
|
+
darwin=true
|
|
39
|
+
;;
|
|
40
|
+
MINGW* )
|
|
41
|
+
msys=true
|
|
42
|
+
;;
|
|
43
|
+
esac
|
|
44
|
+
|
|
45
|
+
# For Cygwin, ensure paths are in UNIX format before anything is touched.
|
|
46
|
+
if $cygwin ; then
|
|
47
|
+
[ -n "$JAVA_HOME" ] && JAVA_HOME=`cygpath --unix "$JAVA_HOME"`
|
|
48
|
+
fi
|
|
49
|
+
|
|
50
|
+
# Attempt to set APP_HOME
|
|
51
|
+
# Resolve links: $0 may be a link
|
|
52
|
+
PRG="$0"
|
|
53
|
+
# Need this for relative symlinks.
|
|
54
|
+
while [ -h "$PRG" ] ; do
|
|
55
|
+
ls=`ls -ld "$PRG"`
|
|
56
|
+
link=`expr "$ls" : '.*-> \(.*\)$'`
|
|
57
|
+
if expr "$link" : '/.*' > /dev/null; then
|
|
58
|
+
PRG="$link"
|
|
59
|
+
else
|
|
60
|
+
PRG=`dirname "$PRG"`"/$link"
|
|
61
|
+
fi
|
|
62
|
+
done
|
|
63
|
+
SAVED="`pwd`"
|
|
64
|
+
cd "`dirname \"$PRG\"`/" >&-
|
|
65
|
+
APP_HOME="`pwd -P`"
|
|
66
|
+
cd "$SAVED" >&-
|
|
67
|
+
|
|
68
|
+
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
|
|
69
|
+
|
|
70
|
+
# Determine the Java command to use to start the JVM.
|
|
71
|
+
if [ -n "$JAVA_HOME" ] ; then
|
|
72
|
+
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
|
|
73
|
+
# IBM's JDK on AIX uses strange locations for the executables
|
|
74
|
+
JAVACMD="$JAVA_HOME/jre/sh/java"
|
|
75
|
+
else
|
|
76
|
+
JAVACMD="$JAVA_HOME/bin/java"
|
|
77
|
+
fi
|
|
78
|
+
if [ ! -x "$JAVACMD" ] ; then
|
|
79
|
+
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
|
|
80
|
+
|
|
81
|
+
Please set the JAVA_HOME variable in your environment to match the
|
|
82
|
+
location of your Java installation."
|
|
83
|
+
fi
|
|
84
|
+
else
|
|
85
|
+
JAVACMD="java"
|
|
86
|
+
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
|
|
87
|
+
|
|
88
|
+
Please set the JAVA_HOME variable in your environment to match the
|
|
89
|
+
location of your Java installation."
|
|
90
|
+
fi
|
|
91
|
+
|
|
92
|
+
# Increase the maximum file descriptors if we can.
|
|
93
|
+
if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
|
|
94
|
+
MAX_FD_LIMIT=`ulimit -H -n`
|
|
95
|
+
if [ $? -eq 0 ] ; then
|
|
96
|
+
if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
|
|
97
|
+
MAX_FD="$MAX_FD_LIMIT"
|
|
98
|
+
fi
|
|
99
|
+
ulimit -n $MAX_FD
|
|
100
|
+
if [ $? -ne 0 ] ; then
|
|
101
|
+
warn "Could not set maximum file descriptor limit: $MAX_FD"
|
|
102
|
+
fi
|
|
103
|
+
else
|
|
104
|
+
warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
|
|
105
|
+
fi
|
|
106
|
+
fi
|
|
107
|
+
|
|
108
|
+
# For Darwin, add options to specify how the application appears in the dock
|
|
109
|
+
if $darwin; then
|
|
110
|
+
GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
|
|
111
|
+
fi
|
|
112
|
+
|
|
113
|
+
# For Cygwin, switch paths to Windows format before running java
|
|
114
|
+
if $cygwin ; then
|
|
115
|
+
APP_HOME=`cygpath --path --mixed "$APP_HOME"`
|
|
116
|
+
CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
|
|
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
|
+
# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
|
|
158
|
+
function splitJvmOpts() {
|
|
159
|
+
JVM_OPTS=("$@")
|
|
160
|
+
}
|
|
161
|
+
eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
|
|
162
|
+
JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
|
|
163
|
+
|
|
164
|
+
exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"
|
data/gradlew.bat
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
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
|
+
@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
|
|
12
|
+
set DEFAULT_JVM_OPTS=
|
|
13
|
+
|
|
14
|
+
set DIRNAME=%~dp0
|
|
15
|
+
if "%DIRNAME%" == "" set DIRNAME=.
|
|
16
|
+
set APP_BASE_NAME=%~n0
|
|
17
|
+
set APP_HOME=%DIRNAME%
|
|
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 Windowz variants
|
|
50
|
+
|
|
51
|
+
if not "%OS%" == "Windows_NT" goto win9xME_args
|
|
52
|
+
if "%@eval[2+2]" == "4" goto 4NT_args
|
|
53
|
+
|
|
54
|
+
:win9xME_args
|
|
55
|
+
@rem Slurp the command line arguments.
|
|
56
|
+
set CMD_LINE_ARGS=
|
|
57
|
+
set _SKIP=2
|
|
58
|
+
|
|
59
|
+
:win9xME_args_slurp
|
|
60
|
+
if "x%~1" == "x" goto execute
|
|
61
|
+
|
|
62
|
+
set CMD_LINE_ARGS=%*
|
|
63
|
+
goto execute
|
|
64
|
+
|
|
65
|
+
:4NT_args
|
|
66
|
+
@rem Get arguments from the 4NT Shell from JP Software
|
|
67
|
+
set CMD_LINE_ARGS=%$
|
|
68
|
+
|
|
69
|
+
:execute
|
|
70
|
+
@rem Setup the command line
|
|
71
|
+
|
|
72
|
+
set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
|
|
73
|
+
|
|
74
|
+
@rem Execute Gradle
|
|
75
|
+
"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
|
|
76
|
+
|
|
77
|
+
:end
|
|
78
|
+
@rem End local scope for the variables with windows NT shell
|
|
79
|
+
if "%ERRORLEVEL%"=="0" goto mainEnd
|
|
80
|
+
|
|
81
|
+
:fail
|
|
82
|
+
rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
|
|
83
|
+
rem the _cmd.exe /c_ return code!
|
|
84
|
+
if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
|
|
85
|
+
exit /b 1
|
|
86
|
+
|
|
87
|
+
:mainEnd
|
|
88
|
+
if "%OS%"=="Windows_NT" endlocal
|
|
89
|
+
|
|
90
|
+
:omega
|
|
@@ -0,0 +1,141 @@
|
|
|
1
|
+
module Embulk
|
|
2
|
+
module Guess
|
|
3
|
+
|
|
4
|
+
# TODO implement guess plugin to make this command work:
|
|
5
|
+
# $ embulk guess -g "regex" 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 Regex < LineGuessPlugin
|
|
12
|
+
Plugin.register_guess("regex", self)
|
|
13
|
+
|
|
14
|
+
def guess_lines(config, sample_lines)
|
|
15
|
+
guesser_list = []
|
|
16
|
+
guesser_list << apache_common(config, sample_lines)
|
|
17
|
+
guesser_list << apache_combined(config, sample_lines)
|
|
18
|
+
guesser_list << apache_combinedio(config, sample_lines)
|
|
19
|
+
guesser_list << apache_x_forwarded_for + apache_combined(config, sample_lines)
|
|
20
|
+
guesser_list << apache_x_forwarded_for + apache_combinedio(config, sample_lines)
|
|
21
|
+
guesser_list.each do |g|
|
|
22
|
+
return {"parser" => g.guessed} if g.match_all?(sample_lines)
|
|
23
|
+
end
|
|
24
|
+
return {}
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
def apache_x_forwarded_for
|
|
28
|
+
RegexApacheLogGuesser.new
|
|
29
|
+
.ip_or_minus(:x_forwarded_for, regexName: 'forwardedFor')
|
|
30
|
+
end
|
|
31
|
+
|
|
32
|
+
def apache_common(config, sample_lines)
|
|
33
|
+
RegexApacheLogGuesser.new
|
|
34
|
+
.ip(:remote_host, regexName: 'remoteHost').token(:identity).token(:user)
|
|
35
|
+
.kakko(:datetime, format: '%d/%b/%Y:%H:%M:%S %z', type: 'timestamp')
|
|
36
|
+
.method_path_protocol
|
|
37
|
+
.integer(:status).integer_or_minus(:size)
|
|
38
|
+
end
|
|
39
|
+
|
|
40
|
+
def apache_combined(config, sample_lines)
|
|
41
|
+
apache_common(config, sample_lines)
|
|
42
|
+
.string(:referer).string(:user_agent, regexName: 'userAgent')
|
|
43
|
+
end
|
|
44
|
+
|
|
45
|
+
def apache_combinedio(config, sample_lines)
|
|
46
|
+
apache_combined(config, sample_lines)
|
|
47
|
+
.integer(:in_byte, regexName: 'inByte').integer(:out_byte, regexName: 'outByte')
|
|
48
|
+
end
|
|
49
|
+
end
|
|
50
|
+
|
|
51
|
+
class RegexApacheLogGuesser
|
|
52
|
+
attr_reader :columns, :patterns
|
|
53
|
+
|
|
54
|
+
def initialize(patterns=nil, columns=nil)
|
|
55
|
+
@patterns = (patterns || [])
|
|
56
|
+
@columns = (columns || [])
|
|
57
|
+
end
|
|
58
|
+
|
|
59
|
+
def +(guesser)
|
|
60
|
+
RegexApacheLogGuesser.new(@patterns + guesser.patterns, @columns + guesser.columns)
|
|
61
|
+
end
|
|
62
|
+
|
|
63
|
+
def match_all?(lines)
|
|
64
|
+
ptn = compile
|
|
65
|
+
lines.all? {|line| ptn.match(line)}
|
|
66
|
+
end
|
|
67
|
+
|
|
68
|
+
def guessed
|
|
69
|
+
ret = {}
|
|
70
|
+
ret["type"] = "regex"
|
|
71
|
+
ret["regex"] = pattern_str
|
|
72
|
+
ret["columns"] = columns
|
|
73
|
+
ret
|
|
74
|
+
end
|
|
75
|
+
|
|
76
|
+
def compile
|
|
77
|
+
Regexp.compile pattern_str
|
|
78
|
+
end
|
|
79
|
+
|
|
80
|
+
def pattern_str
|
|
81
|
+
'^' + @patterns.join(' ') + '$'
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
def ip(name, opts={})
|
|
85
|
+
@patterns << "(?<#{opts[:regexName] || name}>[.:0-9]+)"
|
|
86
|
+
@columns << {:name => name, :type => 'string'}.merge(opts)
|
|
87
|
+
self
|
|
88
|
+
end
|
|
89
|
+
|
|
90
|
+
def ip_or_minus(name, opts={})
|
|
91
|
+
@patterns << "(?<#{opts[:regexName] || name}>[.:0-9]+|-)"
|
|
92
|
+
@columns << {:name => name, :type => 'string'}.merge(opts)
|
|
93
|
+
self
|
|
94
|
+
end
|
|
95
|
+
|
|
96
|
+
def token(name, opts={})
|
|
97
|
+
@patterns << "(?<#{opts[:regexName] || name}>\\S+)"
|
|
98
|
+
@columns << {:name => name, :type => 'string'}.merge(opts)
|
|
99
|
+
self
|
|
100
|
+
end
|
|
101
|
+
|
|
102
|
+
def string(name, opts={})
|
|
103
|
+
@patterns << "\"(?<#{opts[:regexName] || name}>[^\"]*)\""
|
|
104
|
+
@columns << {:name => name, :type => 'string'}.merge(opts)
|
|
105
|
+
self
|
|
106
|
+
end
|
|
107
|
+
|
|
108
|
+
def string_or_minus(name, opts={})
|
|
109
|
+
@patterns << "\"(?<#{opts[:regexName] || name}>[^\"]*|-)\""
|
|
110
|
+
@columns << {:name => name, :type => 'string'}.merge(opts)
|
|
111
|
+
self
|
|
112
|
+
end
|
|
113
|
+
|
|
114
|
+
def integer(name, opts={})
|
|
115
|
+
@patterns << "(?<#{opts[:regexName] || name}>[0-9]+)"
|
|
116
|
+
@columns << {:name => name, :type => 'long'}.merge(opts)
|
|
117
|
+
self
|
|
118
|
+
end
|
|
119
|
+
|
|
120
|
+
def integer_or_minus(name, opts={})
|
|
121
|
+
@patterns << "(?<#{opts[:regexName] || name}>[0-9]+|-)"
|
|
122
|
+
@columns << {:name => name, :type => 'long'}.merge(opts)
|
|
123
|
+
self
|
|
124
|
+
end
|
|
125
|
+
|
|
126
|
+
def kakko(name, opts={})
|
|
127
|
+
@patterns << "\\[(?<#{opts[:regexName] || name}>[^\\]]*)\\]"
|
|
128
|
+
@columns << {:name => name, :type => 'string'}.merge(opts)
|
|
129
|
+
self
|
|
130
|
+
end
|
|
131
|
+
|
|
132
|
+
def method_path_protocol
|
|
133
|
+
@patterns << '"((?<method>\S+) (?<path>\S+) (?<protocol>HTTP/\d+\.\d+)|-)"'
|
|
134
|
+
@columns << {:name => 'method', :type => 'string'}
|
|
135
|
+
@columns << {:name => 'path', :type => 'string'}
|
|
136
|
+
@columns << {:name => 'protocol', :type => 'string'}
|
|
137
|
+
self
|
|
138
|
+
end
|
|
139
|
+
end
|
|
140
|
+
end
|
|
141
|
+
end
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
in:
|
|
2
|
+
type: file
|
|
3
|
+
path_prefix: sample/apache_1/data_apache_
|
|
4
|
+
parser:
|
|
5
|
+
charset: UTF-8
|
|
6
|
+
newline: LF
|
|
7
|
+
type: regex
|
|
8
|
+
regex: ^(?<remoteHost>[.:0-9]+) (?<identity>\S+) (?<user>\S+) \[(?<datetime>[^\]]*)\] "((?<method>\S+) (?<path>\S+) (?<protocol>HTTP/\d+\.\d+)|-)" (?<status>[0-9]+) (?<size>[0-9]+|-) "(?<referer>[^"]*)" "(?<userAgent>[^"]*)" (?<inByte>[0-9]+) (?<outByte>[0-9]+)$
|
|
9
|
+
columns:
|
|
10
|
+
- {name: remote_host, type: string, regexName: remoteHost}
|
|
11
|
+
- {name: identity, type: string}
|
|
12
|
+
- {name: user, type: string}
|
|
13
|
+
- {name: datetime, type: timestamp, format: '%d/%b/%Y:%H:%M:%S %z'}
|
|
14
|
+
- {name: method, type: string}
|
|
15
|
+
- {name: path, type: string}
|
|
16
|
+
- {name: protocol, type: string}
|
|
17
|
+
- {name: status, type: long}
|
|
18
|
+
- {name: size, type: long}
|
|
19
|
+
- {name: referer, type: string}
|
|
20
|
+
- {name: user_agent, type: string, regexName: userAgent}
|
|
21
|
+
- {name: in_byte, type: long, regexName: inByte}
|
|
22
|
+
- {name: out_byte, type: long, regexName: outByte}
|
|
23
|
+
out: {type: stdout}
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
in:
|
|
2
|
+
type: file
|
|
3
|
+
path_prefix: sample/apache_2/data_apache_
|
|
4
|
+
parser:
|
|
5
|
+
charset: UTF-8
|
|
6
|
+
newline: LF
|
|
7
|
+
type: regex
|
|
8
|
+
regex: ^(?<forwardedFor>[.:0-9]+|-) (?<remoteHost>[.:0-9]+) (?<identity>\S+) (?<user>\S+) \[(?<datetime>[^\]]*)\] "((?<method>\S+) (?<path>\S+) (?<protocol>HTTP/\d+\.\d+)|-)" (?<status>[0-9]+) (?<size>[0-9]+|-) "(?<referer>[^"]*)" "(?<userAgent>[^"]*)"$
|
|
9
|
+
columns:
|
|
10
|
+
- {name: x_forwarded_for, type: string, regexName: forwardedFor}
|
|
11
|
+
- {name: remote_host, type: string, regexName: remoteHost}
|
|
12
|
+
- {name: identity, type: string}
|
|
13
|
+
- {name: user, type: string}
|
|
14
|
+
- {name: datetime, type: timestamp, format: '%d/%b/%Y:%H:%M:%S %z'}
|
|
15
|
+
- {name: method, type: string}
|
|
16
|
+
- {name: path, type: string}
|
|
17
|
+
- {name: protocol, type: string}
|
|
18
|
+
- {name: status, type: long}
|
|
19
|
+
- {name: size, type: long}
|
|
20
|
+
- {name: referer, type: string}
|
|
21
|
+
- {name: user_agent, type: string, regexName: userAgent}
|
|
22
|
+
out: {type: stdout}
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
in:
|
|
2
|
+
type: file
|
|
3
|
+
path_prefix: sample/simple/data_simple_
|
|
4
|
+
parser:
|
|
5
|
+
charset: UTF-8
|
|
6
|
+
newline: LF
|
|
7
|
+
type: regex
|
|
8
|
+
regex: '^(?<name>[^|]+)\|(?<age>[0-9]+)\|(?<time>[^|]+)$'
|
|
9
|
+
skip_if_unmatch: true
|
|
10
|
+
columns:
|
|
11
|
+
- {name: name, type: string}
|
|
12
|
+
- {name: age, type: long}
|
|
13
|
+
- {name: time, type: timestamp, format: '%Y-%m-%d %H:%M:%S %z'}
|
|
14
|
+
out:
|
|
15
|
+
type: stdout
|
|
16
|
+
|
|
@@ -0,0 +1,139 @@
|
|
|
1
|
+
package org.embulk.parser.regex;
|
|
2
|
+
|
|
3
|
+
// Many Copies from
|
|
4
|
+
// https://github.com/frsyuki/embulk-parser-msgpack/blob/master/src/main/java/org/embulk/parser/msgpack/MsgpackParserPlugin.java
|
|
5
|
+
|
|
6
|
+
import com.google.common.base.Optional;
|
|
7
|
+
import org.embulk.EmbulkEmbed;
|
|
8
|
+
import org.embulk.config.*;
|
|
9
|
+
import org.embulk.spi.*;
|
|
10
|
+
import org.embulk.spi.time.TimestampFormatter;
|
|
11
|
+
import org.embulk.spi.time.TimestampParser;
|
|
12
|
+
import org.embulk.spi.type.*;
|
|
13
|
+
import org.embulk.spi.util.DynamicColumnSetter;
|
|
14
|
+
import org.embulk.spi.util.LineDecoder;
|
|
15
|
+
import org.embulk.spi.util.Timestamps;
|
|
16
|
+
import org.embulk.spi.util.dynamic.*;
|
|
17
|
+
|
|
18
|
+
import java.util.HashMap;
|
|
19
|
+
import java.util.Map;
|
|
20
|
+
import java.util.regex.Matcher;
|
|
21
|
+
import java.util.regex.Pattern;
|
|
22
|
+
|
|
23
|
+
public class RegexParserPlugin implements ParserPlugin {
|
|
24
|
+
|
|
25
|
+
public interface PluginTask extends Task, LineDecoder.DecoderTask, TimestampParser.Task {
|
|
26
|
+
@Config("regex")
|
|
27
|
+
public String getRegex();
|
|
28
|
+
|
|
29
|
+
@Config("columns")
|
|
30
|
+
public SchemaConfig getSchemaConfig();
|
|
31
|
+
|
|
32
|
+
@Config("skip_if_unmatch")
|
|
33
|
+
@ConfigDefault("false")
|
|
34
|
+
public boolean getSkipIfUnmatch();
|
|
35
|
+
}
|
|
36
|
+
|
|
37
|
+
public interface PluginTaskFormatter
|
|
38
|
+
extends Task, TimestampFormatter.Task {
|
|
39
|
+
}
|
|
40
|
+
|
|
41
|
+
private interface TimestampColumnOption
|
|
42
|
+
extends Task, TimestampFormatter.TimestampColumnOption {
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
public void transaction(ConfigSource config, ParserPlugin.Control control) {
|
|
46
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
|
47
|
+
control.run(task.dump(), task.getSchemaConfig().toSchema());
|
|
48
|
+
}
|
|
49
|
+
|
|
50
|
+
@Override
|
|
51
|
+
public void run(TaskSource taskSource, Schema schema, FileInput input, PageOutput output) {
|
|
52
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
53
|
+
LineDecoder lineDecoder = new LineDecoder(input, task);
|
|
54
|
+
PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), schema, output);
|
|
55
|
+
TimestampParser[] timestampParsers = Timestamps.newTimestampColumnParsers(task, task.getSchemaConfig());
|
|
56
|
+
|
|
57
|
+
Pattern pattern = Pattern.compile(task.getRegex());
|
|
58
|
+
Map<String, DynamicColumnSetter> setterMap = setupSetters(pageBuilder, task.getSchemaConfig(),
|
|
59
|
+
timestampParsers, taskSource.loadTask(PluginTaskFormatter.class));
|
|
60
|
+
|
|
61
|
+
while (input.nextFile()) {
|
|
62
|
+
while (true) {
|
|
63
|
+
String line = lineDecoder.poll();
|
|
64
|
+
if (line == null) {
|
|
65
|
+
break;
|
|
66
|
+
}
|
|
67
|
+
Matcher matcher = pattern.matcher(line);
|
|
68
|
+
if (!matcher.matches()) {
|
|
69
|
+
if (task.getSkipIfUnmatch()) {
|
|
70
|
+
// TODO: How to Log?
|
|
71
|
+
continue;
|
|
72
|
+
} else {
|
|
73
|
+
throw new RuntimeException("Unmatched Line: " + line);
|
|
74
|
+
}
|
|
75
|
+
}
|
|
76
|
+
|
|
77
|
+
for (Map.Entry<String, DynamicColumnSetter> pair : setterMap.entrySet()) {
|
|
78
|
+
String value = matcher.group(pair.getKey());
|
|
79
|
+
if (value == null) {
|
|
80
|
+
pair.getValue().setNull();
|
|
81
|
+
} else {
|
|
82
|
+
pair.getValue().set(value);
|
|
83
|
+
}
|
|
84
|
+
}
|
|
85
|
+
pageBuilder.addRecord();
|
|
86
|
+
}
|
|
87
|
+
}
|
|
88
|
+
pageBuilder.finish();
|
|
89
|
+
}
|
|
90
|
+
|
|
91
|
+
private Map<String, DynamicColumnSetter> setupSetters(PageBuilder pageBuilder,
|
|
92
|
+
SchemaConfig schema,
|
|
93
|
+
TimestampParser[] timestampParsers,
|
|
94
|
+
TimestampFormatter.Task formatterTask) {
|
|
95
|
+
Map<String, DynamicColumnSetter> setterMap = new HashMap<>();
|
|
96
|
+
|
|
97
|
+
int index = -1;
|
|
98
|
+
for (ColumnConfig c : schema.getColumns()) {
|
|
99
|
+
index++;
|
|
100
|
+
String name = c.getName();
|
|
101
|
+
Type type = c.getType();
|
|
102
|
+
Column column = c.toColumn(index);
|
|
103
|
+
String regexName = c.getOption().get(String.class, "regexName", name);
|
|
104
|
+
|
|
105
|
+
DefaultValueSetter defaultValue = new NullDefaultValueSetter();
|
|
106
|
+
DynamicColumnSetter setter;
|
|
107
|
+
|
|
108
|
+
if (type instanceof BooleanType) {
|
|
109
|
+
setter = new BooleanColumnSetter(pageBuilder, column, defaultValue);
|
|
110
|
+
|
|
111
|
+
} else if (type instanceof LongType) {
|
|
112
|
+
setter = new LongColumnSetter(pageBuilder, column, defaultValue);
|
|
113
|
+
|
|
114
|
+
} else if (type instanceof DoubleType) {
|
|
115
|
+
setter = new DoubleColumnSetter(pageBuilder, column, defaultValue);
|
|
116
|
+
|
|
117
|
+
} else if (type instanceof StringType) {
|
|
118
|
+
TimestampFormatter formatter = new TimestampFormatter(formatterTask,
|
|
119
|
+
Optional.of(c.getOption().loadConfig(TimestampColumnOption.class)));
|
|
120
|
+
setter = new StringColumnSetter(pageBuilder, column, defaultValue, formatter);
|
|
121
|
+
|
|
122
|
+
} else if (type instanceof TimestampType) {
|
|
123
|
+
// TODO use flexible time format like Ruby's Time.parse
|
|
124
|
+
TimestampParser parser = timestampParsers[column.getIndex()];
|
|
125
|
+
setter = new TimestampColumnSetter(pageBuilder, column, defaultValue, parser);
|
|
126
|
+
|
|
127
|
+
} else {
|
|
128
|
+
throw new ConfigException("Unknown column type: " + type);
|
|
129
|
+
}
|
|
130
|
+
setterMap.put(regexName, setter);
|
|
131
|
+
}
|
|
132
|
+
|
|
133
|
+
return setterMap;
|
|
134
|
+
}
|
|
135
|
+
|
|
136
|
+
}
|
|
137
|
+
|
|
138
|
+
|
|
139
|
+
|
metadata
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: embulk-parser-regex
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Ken Morishita
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2015-08-31 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: bundler
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - "~>"
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '1.0'
|
|
20
|
+
type: :development
|
|
21
|
+
prerelease: false
|
|
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
|
+
name: rake
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - "~>"
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '10.0'
|
|
34
|
+
type: :development
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - "~>"
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '10.0'
|
|
41
|
+
description: Parses lines using regular-expression in files read by other file input
|
|
42
|
+
plugins.
|
|
43
|
+
email:
|
|
44
|
+
- mokemokechicken@gmail.com
|
|
45
|
+
executables: []
|
|
46
|
+
extensions: []
|
|
47
|
+
extra_rdoc_files: []
|
|
48
|
+
files:
|
|
49
|
+
- ".gitignore"
|
|
50
|
+
- LICENSE.txt
|
|
51
|
+
- README.md
|
|
52
|
+
- build.gradle
|
|
53
|
+
- classpath/embulk-parser-regex-0.1.0.jar
|
|
54
|
+
- embulk-parser-regex.iml
|
|
55
|
+
- gradle/wrapper/gradle-wrapper.jar
|
|
56
|
+
- gradle/wrapper/gradle-wrapper.properties
|
|
57
|
+
- gradlew
|
|
58
|
+
- gradlew.bat
|
|
59
|
+
- lib/embulk/guess/regex.rb
|
|
60
|
+
- lib/embulk/parser/regex.rb
|
|
61
|
+
- sample/apache_1/config.yml
|
|
62
|
+
- sample/apache_1/data_apache_1.txt
|
|
63
|
+
- sample/apache_1/pre_config.yml
|
|
64
|
+
- sample/apache_2/config.yml
|
|
65
|
+
- sample/apache_2/data_apache_1.txt
|
|
66
|
+
- sample/apache_2/pre_config.yml
|
|
67
|
+
- sample/simple/config_simple.yml
|
|
68
|
+
- sample/simple/data_simple_1.txt
|
|
69
|
+
- src/main/java/org/embulk/parser/regex/RegexParserPlugin.java
|
|
70
|
+
- src/test/java/org/embulk/parser/regex/TestRegexParserPlugin.java
|
|
71
|
+
homepage: https://github.com/mokemokechicken/embulk-parser-regex
|
|
72
|
+
licenses:
|
|
73
|
+
- MIT
|
|
74
|
+
metadata: {}
|
|
75
|
+
post_install_message:
|
|
76
|
+
rdoc_options: []
|
|
77
|
+
require_paths:
|
|
78
|
+
- lib
|
|
79
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
80
|
+
requirements:
|
|
81
|
+
- - ">="
|
|
82
|
+
- !ruby/object:Gem::Version
|
|
83
|
+
version: '0'
|
|
84
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
85
|
+
requirements:
|
|
86
|
+
- - ">="
|
|
87
|
+
- !ruby/object:Gem::Version
|
|
88
|
+
version: '0'
|
|
89
|
+
requirements: []
|
|
90
|
+
rubyforge_project:
|
|
91
|
+
rubygems_version: 2.2.2
|
|
92
|
+
signing_key:
|
|
93
|
+
specification_version: 4
|
|
94
|
+
summary: Regex parser plugin for Embulk
|
|
95
|
+
test_files: []
|