embulk-parser-jsonline 0.2.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +11 -0
- data/CHANGELOG.md +20 -0
- data/Gemfile +2 -0
- data/LICENSE.txt +21 -0
- data/README.md +42 -0
- data/Rakefile +3 -0
- data/bench/gen_dummy.rb +5 -0
- data/bench/typecast.yml +17 -0
- data/bench/without_typecast.yml +17 -0
- data/build.gradle +79 -0
- data/classpath/embulk-parser-jsonline-0.2.2.jar +0 -0
- data/embulk-parser-jsonl.gemspec +19 -0
- data/example/compat.yml +21 -0
- data/example/example.yml +18 -0
- data/example/example_without_typecast.yml +18 -0
- data/example/sample.json +2 -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/jsonl.rb +32 -0
- data/lib/embulk/parser/jsonl.rb +3 -0
- data/settings.gradle +1 -0
- data/src/main/java/org/embulk/parser/jsonl/ColumnCaster.java +97 -0
- data/src/main/java/org/embulk/parser/jsonl/ColumnVisitorImpl.java +164 -0
- data/src/main/java/org/embulk/parser/jsonl/JsonRecordValidateException.java +22 -0
- data/src/main/java/org/embulk/parser/jsonl/JsonlParserPlugin.java +225 -0
- data/src/main/java/org/embulk/parser/jsonl/cast/BooleanCast.java +39 -0
- data/src/main/java/org/embulk/parser/jsonl/cast/DoubleCast.java +41 -0
- data/src/main/java/org/embulk/parser/jsonl/cast/JsonCast.java +40 -0
- data/src/main/java/org/embulk/parser/jsonl/cast/LongCast.java +47 -0
- data/src/main/java/org/embulk/parser/jsonl/cast/StringCast.java +82 -0
- data/src/test/java/org/embulk/parser/jsonl/TestColumnCaster.java +256 -0
- data/src/test/java/org/embulk/parser/jsonl/TestJsonlParserPlugin.java +278 -0
- data/src/test/java/org/embulk/parser/jsonl/cast/TestBooleanCast.java +56 -0
- data/src/test/java/org/embulk/parser/jsonl/cast/TestDoubleCast.java +50 -0
- data/src/test/java/org/embulk/parser/jsonl/cast/TestJsonCast.java +80 -0
- data/src/test/java/org/embulk/parser/jsonl/cast/TestLongCast.java +42 -0
- data/src/test/java/org/embulk/parser/jsonl/cast/TestStringCast.java +103 -0
- data/src/test/resources/org/embulk/parser/jsonl/use_column_options.yml +9 -0
- metadata +112 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 9d939f9164a6f198b8c00c49e6067e29562c30ac
|
4
|
+
data.tar.gz: 394db7e4be14fcb4843abc1f0588630a8e6a1ab4
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 88a7874c0a86a47248ed805bdf8047c9211fb4c1c2dbcc291134dda777d442f656c1f723d5fa01bc432a93fccfc781fb8629975f0aa0e668b12a4cf41f53a76a
|
7
|
+
data.tar.gz: fe80abb7dd5c0433c49754b2eb1bf7bef568f2f6c403c8144da4cf9e4d8163d01192ee716ddbc8afefe230ec7795596a7913a05513bedd6293502f72dd3f799e
|
data/.gitignore
ADDED
data/CHANGELOG.md
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
## 0.2.0 - 2016-05-28
|
2
|
+
|
3
|
+
[new feature] Support typecast option [#9](https://github.com/shun0102/embulk-parser-jsonl/pull/9)
|
4
|
+
|
5
|
+
## 0.1.2 - 2016-03-27
|
6
|
+
|
7
|
+
[new feature] Support column_options option [#4](https://github.com/shun0102/embulk-parser-jsonl/pull/4)
|
8
|
+
[maintenance] Upgrade Embulk v0.8.8 [#6](https://github.com/shun0102/embulk-parser-jsonl/pull/6)## 0.1.2 - 2016-03-27
|
9
|
+
|
10
|
+
## 0.1.1 - 2016-03-17
|
11
|
+
|
12
|
+
[fix bug] Avoid org.embulk.spi.json.JsonParseException: Unable to parse empty string [#5](https://github.com/shun0102/embulk-parser-jsonl/pull/5)
|
13
|
+
|
14
|
+
## 0.1.0 - 2016-02-22
|
15
|
+
|
16
|
+
Upgrade Embulk v0.8 and support Json type in Java [#3](https://github.com/shun0102/embulk-parser-jsonl/pull/3)
|
17
|
+
|
18
|
+
## 0.0.1 - 2015-04-04
|
19
|
+
|
20
|
+
The first release!!
|
data/Gemfile
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 +1,42 @@
|
|
1
|
+
# Jsonl parser plugin for Embulk
|
2
|
+
|
3
|
+
[JSONL (JSON Lines)](http://jsonlines.org/) parser plugin for Embulk
|
4
|
+
|
5
|
+
## Overview
|
6
|
+
|
7
|
+
* **Plugin type**: parser
|
8
|
+
* **Guess supported**: yes
|
9
|
+
|
10
|
+
## Configuration
|
11
|
+
|
12
|
+
- **type**: Specify this parser as jsonl
|
13
|
+
- **columns**: Specify column name and type. See below (array, required)
|
14
|
+
* **stop_on_invalid_record**: Stop bulk load transaction if a file includes invalid record (such as invalid timestamp) (boolean, default: false)
|
15
|
+
* **default_timezone**: Default timezone of the timestamp (string, default: UTC)
|
16
|
+
* **default_timestamp_format**: Default timestamp format of the timestamp (string, default: `%Y-%m-%d %H:%M:%S.%N %z`)
|
17
|
+
* **newline**: Newline character (CRLF, LF or CR) (string, default: CRLF)
|
18
|
+
* **charset**: Character encoding (eg. ISO-8859-1, UTF-8) (string, default: UTF-8)
|
19
|
+
* **default_typecast**: Specify whether to cast values automatically to the specified types or not (boolean, default: true)
|
20
|
+
|
21
|
+
### columns
|
22
|
+
|
23
|
+
* **name**: Name of the column (string, required)
|
24
|
+
* **type**: Type of the column (string, required)
|
25
|
+
* **timezone**: Timezone of the timestamp if type is timestamp (string, default: default_timestamp)
|
26
|
+
* **format**: Format of the timestamp if type is timestamp (string, default: default_format)
|
27
|
+
* **typecast**: Whether cast values or not (boolean, default: default_typecast)
|
28
|
+
|
29
|
+
## Guess
|
30
|
+
|
31
|
+
(If guess supported) you don't have to write `parser:` section in the configuration file. After writing `in:` section, you can let embulk guess `parser:` section using this command:
|
32
|
+
|
33
|
+
```
|
34
|
+
$ embulk gem install embulk-parser-jsonl
|
35
|
+
$ embulk guess -g jsonl config.yml -o guessed.yml
|
36
|
+
```
|
37
|
+
|
38
|
+
## Build
|
39
|
+
|
40
|
+
```
|
41
|
+
$ ./gradlew gem classpath
|
42
|
+
```
|
data/Rakefile
ADDED
data/bench/gen_dummy.rb
ADDED
data/bench/typecast.yml
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: "bench/sample"
|
4
|
+
parser:
|
5
|
+
type: jsonl
|
6
|
+
default_typecast: true
|
7
|
+
columns:
|
8
|
+
- {name: "foo", type: "string"}
|
9
|
+
- {name: "bool", type: "boolean"}
|
10
|
+
- {name: "bool_str", type: "boolean"}
|
11
|
+
- {name: "int", type: "long"}
|
12
|
+
- {name: "int_str", type: "long"}
|
13
|
+
- {name: "double", type: "double"}
|
14
|
+
- {name: "double_str", type: "double"}
|
15
|
+
- {name: "array", type: "json"}
|
16
|
+
out:
|
17
|
+
type: "null"
|
@@ -0,0 +1,17 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: "bench/sample"
|
4
|
+
parser:
|
5
|
+
type: jsonl
|
6
|
+
default_typecast: false
|
7
|
+
columns:
|
8
|
+
- {name: "foo", type: "string"}
|
9
|
+
- {name: "bool", type: "boolean"}
|
10
|
+
- {name: "bool_str", type: "string"}
|
11
|
+
- {name: "int", type: "long"}
|
12
|
+
- {name: "int_str", type: "string"}
|
13
|
+
- {name: "double", type: "double"}
|
14
|
+
- {name: "double_str", type: "string"}
|
15
|
+
- {name: "array", type: "json"}
|
16
|
+
out:
|
17
|
+
type: "null"
|
data/build.gradle
ADDED
@@ -0,0 +1,79 @@
|
|
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 "jacoco"
|
6
|
+
}
|
7
|
+
import com.github.jrubygradle.JRubyExec
|
8
|
+
repositories {
|
9
|
+
mavenCentral()
|
10
|
+
jcenter()
|
11
|
+
}
|
12
|
+
configurations {
|
13
|
+
provided
|
14
|
+
}
|
15
|
+
|
16
|
+
version = "0.2.2"
|
17
|
+
|
18
|
+
compileJava.options.encoding = 'UTF-8' // source encoding
|
19
|
+
sourceCompatibility = 1.7
|
20
|
+
targetCompatibility = 1.7
|
21
|
+
|
22
|
+
dependencies {
|
23
|
+
compile "org.embulk:embulk-core:0.8.8"
|
24
|
+
provided "org.embulk:embulk-core:0.8.8"
|
25
|
+
|
26
|
+
testCompile "junit:junit:4.+"
|
27
|
+
testCompile "org.embulk:embulk-core:0.8.8:tests"
|
28
|
+
testCompile "org.embulk:embulk-standards:0.8.8"
|
29
|
+
}
|
30
|
+
|
31
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
32
|
+
doFirst { file("classpath").deleteDir() }
|
33
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
34
|
+
into "classpath"
|
35
|
+
}
|
36
|
+
clean { delete "classpath" }
|
37
|
+
|
38
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
39
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
40
|
+
script "${project.name}.gemspec"
|
41
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
42
|
+
}
|
43
|
+
|
44
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
45
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
46
|
+
script "pkg/${project.name}-${project.version}.gem"
|
47
|
+
}
|
48
|
+
|
49
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) << {
|
50
|
+
println "> Build succeeded."
|
51
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
52
|
+
}
|
53
|
+
|
54
|
+
task gemspec {
|
55
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
56
|
+
inputs.file "build.gradle"
|
57
|
+
outputs.file gemspecFile
|
58
|
+
doLast { gemspecFile.write($/
|
59
|
+
Gem::Specification.new do |spec|
|
60
|
+
spec.name = "${project.name}"
|
61
|
+
spec.version = "${project.version}"
|
62
|
+
spec.authors = ["locona"]
|
63
|
+
spec.summary = "Jsonl parser plugin for Embulk"
|
64
|
+
spec.description = "Parses Jsonl files read by other file input plugins."
|
65
|
+
spec.email = ["locona.0810@gmail.com"]
|
66
|
+
spec.licenses = ["MIT"]
|
67
|
+
spec.homepage = "https://github.com/3-shake/embulk-parser-jsonline"
|
68
|
+
|
69
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
70
|
+
spec.test_files = spec.files.grep(%r{^(test|spec)/})
|
71
|
+
spec.require_paths = ["lib"]
|
72
|
+
|
73
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
74
|
+
spec.add_development_dependency 'rake', ['~> 10.0']
|
75
|
+
end
|
76
|
+
/$)
|
77
|
+
}
|
78
|
+
}
|
79
|
+
clean { delete "${project.name}.gemspec" }
|
Binary file
|
@@ -0,0 +1,19 @@
|
|
1
|
+
|
2
|
+
Gem::Specification.new do |spec|
|
3
|
+
spec.name = "embulk-parser-jsonl"
|
4
|
+
spec.version = "0.2.0"
|
5
|
+
spec.authors = ["Shunsuke Mikami"]
|
6
|
+
spec.summary = "Jsonl parser plugin for Embulk"
|
7
|
+
spec.description = "Parses Jsonl files read by other file input plugins."
|
8
|
+
spec.email = ["shun0102@gmail.com"]
|
9
|
+
spec.licenses = ["MIT"]
|
10
|
+
spec.homepage = "https://github.com/shun0102/embulk-parser-jsonl"
|
11
|
+
|
12
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
13
|
+
spec.test_files = spec.files.grep(%r{^(test|spec)/})
|
14
|
+
spec.require_paths = ["lib"]
|
15
|
+
|
16
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
17
|
+
spec.add_development_dependency 'rake', ['~> 10.0']
|
18
|
+
spec.add_runtime_dependency 'jar-dependencies', "~> 0.3.11"
|
19
|
+
end
|
data/example/compat.yml
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: "example/sample"
|
4
|
+
parser:
|
5
|
+
type: jsonl
|
6
|
+
columns:
|
7
|
+
- {name: "foo", type: "string"}
|
8
|
+
- {name: "bool", type: "boolean"}
|
9
|
+
- {name: "bool_str", type: "boolean"}
|
10
|
+
- {name: "int", type: "string"}
|
11
|
+
- {name: "int_str", type: "string"}
|
12
|
+
- {name: "time", type: "timestamp", format: '%Y-%m-%d %H:%M:%S'}
|
13
|
+
- {name: "double", type: "double"}
|
14
|
+
- {name: "double_str", type: "string"}
|
15
|
+
- {name: "array", type: "json"}
|
16
|
+
column_options:
|
17
|
+
bool_str: {type: "boolean"}
|
18
|
+
int_str: {type: "long"}
|
19
|
+
double_str: {type: "double"}
|
20
|
+
out:
|
21
|
+
type: stdout
|
data/example/example.yml
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: "example/sample"
|
4
|
+
parser:
|
5
|
+
type: jsonl
|
6
|
+
# default_typecast: true # default: true
|
7
|
+
columns:
|
8
|
+
- {name: "foo", type: "string"}
|
9
|
+
- {name: "bool", type: "boolean"}
|
10
|
+
- {name: "bool_str", type: "boolean"}
|
11
|
+
- {name: "int", type: "long"}
|
12
|
+
- {name: "int_str", type: "long"}
|
13
|
+
- {name: "time", type: "timestamp", format: '%Y-%m-%d %H:%M:%S'}
|
14
|
+
- {name: "double", type: "double"}
|
15
|
+
- {name: "double_str", type: "double"}
|
16
|
+
- {name: "array", type: "json"}
|
17
|
+
out:
|
18
|
+
type: stdout
|
@@ -0,0 +1,18 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: "example/sample"
|
4
|
+
parser:
|
5
|
+
type: jsonl
|
6
|
+
default_typecast: false
|
7
|
+
columns:
|
8
|
+
- {name: "foo", type: "string"}
|
9
|
+
- {name: "bool", type: "boolean"}
|
10
|
+
- {name: "bool_str", type: "string"}
|
11
|
+
- {name: "int", type: "long"}
|
12
|
+
- {name: "int_str", type: "string"}
|
13
|
+
- {name: "time", type: "timestamp", format: '%Y-%m-%d %H:%M:%S'}
|
14
|
+
- {name: "double", type: "double"}
|
15
|
+
- {name: "double_str", type: "string"}
|
16
|
+
- {name: "array", type: "json"}
|
17
|
+
out:
|
18
|
+
type: stdout
|
data/example/sample.json
ADDED
@@ -0,0 +1,2 @@
|
|
1
|
+
{"foo": "bar", "bool": true, "bool_str": "true", "int": 42, "int_str": "42", "time": "2016-3-2 00:39:18", "double": 2.4, "double_str": "2.4", "array": [1, 2, 3]}
|
2
|
+
{"foo": null, "bool": false, "bool_str": "false", "int": 42, "int_str": "42", "time": "2016-3-2 00:39:18", "double": 2.4, "double_str": "2.4", "array": [{"inner": "hoge"}, {"inner": 1.5}]}
|
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 +1,32 @@
|
|
1
|
+
require 'json'
|
2
|
+
require "embulk/parser/jsonl.rb"
|
3
|
+
|
4
|
+
module Embulk
|
5
|
+
module Guess
|
6
|
+
# $ embulk guess -g "jsonl" partial-config.yml
|
7
|
+
|
8
|
+
class Jsonl < LineGuessPlugin # TODO should use GuessPlugin instead of LineGuessPlugin
|
9
|
+
Plugin.register_guess("jsonl", self)
|
10
|
+
|
11
|
+
def guess_lines(config, sample_lines)
|
12
|
+
#return {} unless config.fetch("parser", {}).fetch("type", "jsonl") == "jsonl"
|
13
|
+
|
14
|
+
rows = []
|
15
|
+
|
16
|
+
columns = {}
|
17
|
+
sample_lines.each do |line|
|
18
|
+
rows << JSON.parse(line)
|
19
|
+
end
|
20
|
+
|
21
|
+
columns = Embulk::Guess::SchemaGuess.from_hash_records(rows).map do |c|
|
22
|
+
column = {name: c.name, type: c.type}
|
23
|
+
column[:format] = c.format if c.format
|
24
|
+
column
|
25
|
+
end
|
26
|
+
parser_guessed = {"type" => "jsonl"}
|
27
|
+
parser_guessed["columns"] = columns
|
28
|
+
return {"parser" => parser_guessed}
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
data/settings.gradle
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
rootProject.name = 'embulk-parser-jsonline'
|