embulk-parser-fixed 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +5 -0
- data/.ruby-version +1 -0
- data/.travis.yml +12 -0
- data/Gemfile +2 -0
- data/LICENSE.txt +21 -0
- data/README.md +36 -0
- data/Rakefile +8 -0
- data/embulk-parser-fixed.gemspec +21 -0
- data/gemfiles/embulk-latest +4 -0
- data/lib/embulk/guess/unpack.rb +63 -0
- data/lib/embulk/parser/fixed.rb +58 -0
- data/test/capture_io.rb +45 -0
- data/test/embulk/parser/test_fixed.rb +52 -0
- data/test/embulk_run_helper.rb +19 -0
- data/test/prepare_embulk.rb +5 -0
- data/test/run-test.rb +15 -0
- metadata +135 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: de264839a5caf9e90ab09ac915ac9554d2407418
|
4
|
+
data.tar.gz: bf15e9204a7c44c0d97ab63613ddb6984670d751
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: e612d874078ca2409fa39503e45cf74d41f2dd183e9f8d69ca6b249de10a767c9f981afd18be651b9c3a2c4b58c064aa7ab0477ed678370cd9a55254d21f6322
|
7
|
+
data.tar.gz: aba8fd7dd76f21e303aabce2edc95b8b5b0ce2da256d7c366136ddca7e838c11b805ed5ae5a259f52119766bab73b54618652d60c06cada2b7b0b2e1f36d6e8d
|
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
jruby-9.1.5.0
|
data/.travis.yml
ADDED
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 +1,36 @@
|
|
1
|
+
[](https://travis-ci.org/kakoni/embulk-parser-fixed)
|
2
|
+
|
3
|
+
# Fixed width parser plugin for Embulk
|
4
|
+
|
5
|
+
Fixed width parser. Useful for parsing fixed width format files.
|
6
|
+
Can be used to transform `FirstSecond Third` line to `{key: "First", key2: "Second", key3: "Third"}`
|
7
|
+
|
8
|
+
## Overview
|
9
|
+
|
10
|
+
* **Plugin type**: parser
|
11
|
+
* **Guess supported**: no
|
12
|
+
|
13
|
+
## Configuration
|
14
|
+
|
15
|
+
- **columns**: declares the list of columns, their types and positions as range in input. Values will be assigned to these in order.
|
16
|
+
- **strip_whitespace**: Strip whitespace from parsed values. (bool, default: true)
|
17
|
+
|
18
|
+
## Example
|
19
|
+
|
20
|
+
```yaml
|
21
|
+
in:
|
22
|
+
type: any file input plugin type
|
23
|
+
parser:
|
24
|
+
type: unpack
|
25
|
+
columns:
|
26
|
+
- {name: first, type: string, pos: 0..1}
|
27
|
+
- {name: second, type: string, pos: 3..7}
|
28
|
+
- {name: third, type: string, pos: 10..12}
|
29
|
+
|
30
|
+
```
|
31
|
+
|
32
|
+
## Install plugin
|
33
|
+
|
34
|
+
```
|
35
|
+
$ embulk gem install embulk-parser-fixed
|
36
|
+
```
|
data/Rakefile
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
|
2
|
+
Gem::Specification.new do |spec|
|
3
|
+
spec.name = "embulk-parser-fixed"
|
4
|
+
spec.version = "0.1.0"
|
5
|
+
spec.authors = ["Karri Niemel\u{e4}"]
|
6
|
+
spec.summary = "Fixed width parser plugin for Embulk"
|
7
|
+
spec.description = "Parses fixed width files read by other file input plugins."
|
8
|
+
spec.email = ["kakoni@gmail.com"]
|
9
|
+
spec.licenses = ["MIT"]
|
10
|
+
spec.homepage = "https://github.com/kakoni/embulk-parser-fixed"
|
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 'embulk', ['>= 0.8.9']
|
17
|
+
spec.add_development_dependency 'bundler', ['>= 1.10.6']
|
18
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
19
|
+
spec.add_development_dependency 'test-unit'
|
20
|
+
spec.add_development_dependency 'test-unit-rr'
|
21
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
module Embulk
|
2
|
+
module Guess
|
3
|
+
|
4
|
+
# TODO implement guess plugin to make this command work:
|
5
|
+
# $ embulk guess -g "unpack" 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
|
+
#require "embulk/parser/unpack.rb"
|
12
|
+
|
13
|
+
#class Unpack < GuessPlugin
|
14
|
+
# Plugin.register_guess("unpack", self)
|
15
|
+
#
|
16
|
+
# def guess(config, sample_buffer)
|
17
|
+
# if sample_buffer[0,2] == GZIP_HEADER
|
18
|
+
# guessed = {}
|
19
|
+
# guessed["type"] = "unpack"
|
20
|
+
# guessed["property1"] = "guessed-value"
|
21
|
+
# return {"parser" => guessed}
|
22
|
+
# else
|
23
|
+
# return {}
|
24
|
+
# end
|
25
|
+
# end
|
26
|
+
#end
|
27
|
+
|
28
|
+
#class Unpack < TextGuessPlugin
|
29
|
+
# Plugin.register_guess("unpack", self)
|
30
|
+
#
|
31
|
+
# def guess_text(config, sample_text)
|
32
|
+
# js = JSON.parse(sample_text) rescue nil
|
33
|
+
# if js && js["mykeyword"] == "keyword"
|
34
|
+
# guessed = {}
|
35
|
+
# guessed["type"] = "unpack"
|
36
|
+
# guessed["property1"] = "guessed-value"
|
37
|
+
# return {"parser" => guessed}
|
38
|
+
# else
|
39
|
+
# return {}
|
40
|
+
# end
|
41
|
+
# end
|
42
|
+
#end
|
43
|
+
|
44
|
+
#class Unpack < LineGuessPlugin
|
45
|
+
# Plugin.register_guess("unpack", self)
|
46
|
+
#
|
47
|
+
# def guess_lines(config, sample_lines)
|
48
|
+
# all_line_matched = sample_lines.all? do |line|
|
49
|
+
# line =~ /mypattern/
|
50
|
+
# end
|
51
|
+
# if all_line_matched
|
52
|
+
# guessed = {}
|
53
|
+
# guessed["type"] = "unpack"
|
54
|
+
# guessed["property1"] = "guessed-value"
|
55
|
+
# return {"parser" => guessed}
|
56
|
+
# else
|
57
|
+
# return {}
|
58
|
+
# end
|
59
|
+
# end
|
60
|
+
#end
|
61
|
+
|
62
|
+
end
|
63
|
+
end
|
@@ -0,0 +1,58 @@
|
|
1
|
+
module Embulk
|
2
|
+
module Parser
|
3
|
+
|
4
|
+
class Fixed < ParserPlugin
|
5
|
+
Plugin.register_parser("fixed", self)
|
6
|
+
|
7
|
+
def self.transaction(config, &control)
|
8
|
+
decoder_task = config.load_config(Java::LineDecoder::DecoderTask)
|
9
|
+
|
10
|
+
# configuration code:
|
11
|
+
task = {
|
12
|
+
"decoder" => DataSource.from_java(decoder_task.dump),
|
13
|
+
"schema" => config.param("columns", :array, default: []),
|
14
|
+
"strip_whitespace" => config.param("strip_whitespace", :bool, default: true)
|
15
|
+
}
|
16
|
+
|
17
|
+
columns = []
|
18
|
+
task["schema"].each do |column|
|
19
|
+
name = column["name"]
|
20
|
+
type = column["type"].to_sym
|
21
|
+
columns << Column.new(nil, name, type)
|
22
|
+
end
|
23
|
+
|
24
|
+
yield(task, columns)
|
25
|
+
end
|
26
|
+
|
27
|
+
def init
|
28
|
+
@decoder = task.param("decoder", :hash).load_task(Java::LineDecoder::DecoderTask)
|
29
|
+
@schema = @task["schema"]
|
30
|
+
@strip_whitespace = task["strip_whitespace"]
|
31
|
+
end
|
32
|
+
|
33
|
+
|
34
|
+
def run(file_input)
|
35
|
+
decoder = Java::LineDecoder.new(file_input.to_java, @decoder)
|
36
|
+
while decoder.nextFile
|
37
|
+
while line = decoder.poll
|
38
|
+
process_line(line)
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
page_builder.finish
|
43
|
+
end
|
44
|
+
|
45
|
+
private
|
46
|
+
|
47
|
+
def process_line(line)
|
48
|
+
values = @schema.map do |column|
|
49
|
+
range = Range.new(*column["pos"].split("..").map(&:to_i)) if column["pos"]
|
50
|
+
val = line.slice(range)
|
51
|
+
val.strip if @strip_whitespace
|
52
|
+
end
|
53
|
+
page_builder.add(values)
|
54
|
+
end
|
55
|
+
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
data/test/capture_io.rb
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
module CaptureIo
|
2
|
+
def capture(output = :out, &block)
|
3
|
+
_, out = swap_io(output, &block)
|
4
|
+
out
|
5
|
+
end
|
6
|
+
|
7
|
+
def silence(&block)
|
8
|
+
block_result = nil
|
9
|
+
swap_io(:out) do
|
10
|
+
block_result,_ = swap_io(:err, &block)
|
11
|
+
end
|
12
|
+
block_result
|
13
|
+
end
|
14
|
+
|
15
|
+
def swap_io(output = :out, &block)
|
16
|
+
java_import 'java.io.PrintStream'
|
17
|
+
java_import 'java.io.ByteArrayOutputStream'
|
18
|
+
java_import 'java.lang.System'
|
19
|
+
|
20
|
+
ruby_original_stream = output == :out ? $stdout.dup : $stderr.dup
|
21
|
+
java_original_stream = System.send(output) # :out or :err
|
22
|
+
ruby_buf = StringIO.new
|
23
|
+
java_buf = ByteArrayOutputStream.new
|
24
|
+
|
25
|
+
case output
|
26
|
+
when :out
|
27
|
+
$stdout = ruby_buf
|
28
|
+
System.setOut(PrintStream.new(java_buf))
|
29
|
+
when :err
|
30
|
+
$stderr = ruby_buf
|
31
|
+
System.setErr(PrintStream.new(java_buf))
|
32
|
+
end
|
33
|
+
|
34
|
+
[block.call, ruby_buf.string + java_buf.toString]
|
35
|
+
ensure
|
36
|
+
case output
|
37
|
+
when :out
|
38
|
+
$stdout = ruby_original_stream
|
39
|
+
System.setOut(java_original_stream)
|
40
|
+
when :err
|
41
|
+
$stderr = ruby_original_stream
|
42
|
+
System.setErr(java_original_stream)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,52 @@
|
|
1
|
+
require "prepare_embulk"
|
2
|
+
require "embulk/parser/fixed"
|
3
|
+
require "embulk/data_source"
|
4
|
+
|
5
|
+
|
6
|
+
module Embulk
|
7
|
+
module Parser
|
8
|
+
class FixedTest < Test::Unit::TestCase
|
9
|
+
|
10
|
+
class TestProcessLine < self
|
11
|
+
|
12
|
+
def test_foo
|
13
|
+
mock(page_builder).add(["eka", "Toka", "Kolmas", "Neljas"])
|
14
|
+
line = "ekaTokaKolmas Neljas"
|
15
|
+
plugin.send(:process_line, line)
|
16
|
+
end
|
17
|
+
|
18
|
+
def plugin
|
19
|
+
@plugin ||= Fixed.new(DataSource[task], schema, page_builder)
|
20
|
+
end
|
21
|
+
|
22
|
+
def page_builder
|
23
|
+
@page_builder ||= Object.new
|
24
|
+
end
|
25
|
+
|
26
|
+
def task
|
27
|
+
{
|
28
|
+
"decoder" => {"Charset" => "UTF-8", "Newline" => "CRLF"},
|
29
|
+
"schema" => columns,
|
30
|
+
"strip_whitespace" => true,
|
31
|
+
}
|
32
|
+
end
|
33
|
+
|
34
|
+
def columns
|
35
|
+
[
|
36
|
+
{"name" => "foo", "type" => :string, "pos" => "0..2"},
|
37
|
+
{"name" => "bar", "type" => :string, "pos" => "3..6"},
|
38
|
+
{"name" => "baz", "type" => :string, "pos" => "7..12"},
|
39
|
+
{"name" => "qux", "type" => :string, "pos" => "14..19"},
|
40
|
+
]
|
41
|
+
end
|
42
|
+
|
43
|
+
def schema
|
44
|
+
columns.map do |column|
|
45
|
+
Column.new(nil, column["name"], column["type"].to_sym)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
require "capture_io"
|
2
|
+
|
3
|
+
module EmbulkRunHelper
|
4
|
+
include CaptureIo
|
5
|
+
|
6
|
+
def embulk_guess(seed_path, dest_path)
|
7
|
+
silence do
|
8
|
+
embulk_exec(%W(guess -g query_string #{seed_path} -o #{dest_path}))
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
def embulk_run(yaml_path)
|
13
|
+
embulk_exec(%W(run #{yaml_path}))
|
14
|
+
end
|
15
|
+
|
16
|
+
def embulk_exec(cli_options = [])
|
17
|
+
Embulk.run(cli_options)
|
18
|
+
end
|
19
|
+
end
|
data/test/run-test.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
base_dir = File.expand_path(File.join(File.dirname(__FILE__), ".."))
|
4
|
+
lib_dir = File.join(base_dir, "lib")
|
5
|
+
test_dir = File.join(base_dir, "test")
|
6
|
+
|
7
|
+
require "test-unit"
|
8
|
+
require "test/unit/rr"
|
9
|
+
|
10
|
+
$LOAD_PATH.unshift(lib_dir)
|
11
|
+
$LOAD_PATH.unshift(test_dir)
|
12
|
+
|
13
|
+
ENV["TEST_UNIT_MAX_DIFF_TARGET_STRING_SIZE"] ||= "5000"
|
14
|
+
|
15
|
+
exit Test::Unit::AutoRunner.run(true, test_dir, ARGV + %w(--collector=dir))
|
metadata
ADDED
@@ -0,0 +1,135 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-parser-fixed
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Karri Niemelä
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-05 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: 0.8.9
|
19
|
+
name: embulk
|
20
|
+
prerelease: false
|
21
|
+
type: :development
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.8.9
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
requirement: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 1.10.6
|
33
|
+
name: bundler
|
34
|
+
prerelease: false
|
35
|
+
type: :development
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 1.10.6
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
requirement: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - ">="
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: '10.0'
|
47
|
+
name: rake
|
48
|
+
prerelease: false
|
49
|
+
type: :development
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
requirement: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - ">="
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '0'
|
61
|
+
name: test-unit
|
62
|
+
prerelease: false
|
63
|
+
type: :development
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
requirement: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
name: test-unit-rr
|
76
|
+
prerelease: false
|
77
|
+
type: :development
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
description: Parses fixed width files read by other file input plugins.
|
84
|
+
email:
|
85
|
+
- kakoni@gmail.com
|
86
|
+
executables: []
|
87
|
+
extensions: []
|
88
|
+
extra_rdoc_files: []
|
89
|
+
files:
|
90
|
+
- ".gitignore"
|
91
|
+
- ".ruby-version"
|
92
|
+
- ".travis.yml"
|
93
|
+
- Gemfile
|
94
|
+
- LICENSE.txt
|
95
|
+
- README.md
|
96
|
+
- Rakefile
|
97
|
+
- embulk-parser-fixed.gemspec
|
98
|
+
- gemfiles/embulk-latest
|
99
|
+
- lib/embulk/guess/unpack.rb
|
100
|
+
- lib/embulk/parser/fixed.rb
|
101
|
+
- test/capture_io.rb
|
102
|
+
- test/embulk/parser/test_fixed.rb
|
103
|
+
- test/embulk_run_helper.rb
|
104
|
+
- test/prepare_embulk.rb
|
105
|
+
- test/run-test.rb
|
106
|
+
homepage: https://github.com/kakoni/embulk-parser-fixed
|
107
|
+
licenses:
|
108
|
+
- MIT
|
109
|
+
metadata: {}
|
110
|
+
post_install_message:
|
111
|
+
rdoc_options: []
|
112
|
+
require_paths:
|
113
|
+
- lib
|
114
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
115
|
+
requirements:
|
116
|
+
- - ">="
|
117
|
+
- !ruby/object:Gem::Version
|
118
|
+
version: '0'
|
119
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
120
|
+
requirements:
|
121
|
+
- - ">="
|
122
|
+
- !ruby/object:Gem::Version
|
123
|
+
version: '0'
|
124
|
+
requirements: []
|
125
|
+
rubyforge_project:
|
126
|
+
rubygems_version: 2.6.6
|
127
|
+
signing_key:
|
128
|
+
specification_version: 4
|
129
|
+
summary: Fixed width parser plugin for Embulk
|
130
|
+
test_files:
|
131
|
+
- test/capture_io.rb
|
132
|
+
- test/embulk/parser/test_fixed.rb
|
133
|
+
- test/embulk_run_helper.rb
|
134
|
+
- test/prepare_embulk.rb
|
135
|
+
- test/run-test.rb
|