ltsv 0.0.1
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.
- data/.gitignore +18 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +69 -0
- data/Rakefile +1 -0
- data/lib/ltsv.rb +140 -0
- data/ltsv.gemspec +21 -0
- data/spec/ltsv_spec.rb +75 -0
- data/spec/spec_helper.rb +1 -0
- metadata +72 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 condor
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
# Ltsv
|
2
|
+
|
3
|
+
LTSV: A Parser / Dumper for Labelled Tab-Separated Values (LTSV)
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'ltsv'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install ltsv
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
At first, you should require ltsv:
|
22
|
+
|
23
|
+
require 'ltsv'
|
24
|
+
|
25
|
+
In addition, if you manage gems with bundler, you should add the statement below into your Gemfile:
|
26
|
+
|
27
|
+
gem 'ltsv'
|
28
|
+
|
29
|
+
|
30
|
+
### parsing LTSV
|
31
|
+
|
32
|
+
# parse string
|
33
|
+
string = "label1:value1\tlabel2:value2"
|
34
|
+
values = LTSV.parse(string) # => {:label1 => "value1", :label2 => "value2"}
|
35
|
+
|
36
|
+
# parse via stream
|
37
|
+
# content: as below
|
38
|
+
# label1_1:value1_1\tlabel1_2:value1_2
|
39
|
+
# label2_1:value2_1\tlabel2_2:value2_2
|
40
|
+
stream = File.open("some_file.ltsv", "r")
|
41
|
+
values = LTSV.parse(stream)
|
42
|
+
# => [{:label1_1 => "value1_2", :label1_2 => "value1_2"},
|
43
|
+
# {:label2_1 => "value2_2", :label2_2 => "value2_2"}]
|
44
|
+
|
45
|
+
Current limitation: parsed string should be in one line. If you include any special chars that may affect to the processing( "\r", "\n", "\t", "\\"), you should properly escape it with backslash.
|
46
|
+
|
47
|
+
### loading LTSV file
|
48
|
+
|
49
|
+
# parse via path
|
50
|
+
values = LTSV.parse("some_path.ltsv")
|
51
|
+
|
52
|
+
# parse via stream
|
53
|
+
stream = File.open("some_file.ltsv", "r")
|
54
|
+
values = LTSV.load(stream) # => same as LTSV.parse(stream)
|
55
|
+
|
56
|
+
### dumping into LTSV
|
57
|
+
|
58
|
+
value = {label1: "value1", label2: "value2"}
|
59
|
+
dumped = LTSV.dump(value) # => "label1:value1\tlabel2:value2"
|
60
|
+
|
61
|
+
Dumped objects should respond to :to_hash.
|
62
|
+
|
63
|
+
## Contributing
|
64
|
+
|
65
|
+
1. Fork it
|
66
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
67
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
68
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
69
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/lib/ltsv.rb
ADDED
@@ -0,0 +1,140 @@
|
|
1
|
+
# = ltsv - A parser / dumper for Labelled Tab-Separated Values(LTSV)
|
2
|
+
#
|
3
|
+
# Copyright (C) 2013 TOYODA Naoto.
|
4
|
+
#
|
5
|
+
#
|
6
|
+
module LTSV
|
7
|
+
VERSION = "0.0.1"
|
8
|
+
|
9
|
+
# Parsing given stream or string.
|
10
|
+
# If you specified a stream as the first argument,
|
11
|
+
# this method behaves as same as #load.
|
12
|
+
#
|
13
|
+
# == Arguments:
|
14
|
+
# * _io_or_string_: a target to parse. Possible values are: String, IO.
|
15
|
+
# If you give the string value, it stands the content to parse.
|
16
|
+
# If you give the IO value, it stands the stream which provides the contents to parse.
|
17
|
+
# == Options:
|
18
|
+
# * _symbolize_keys_ : Whether the label will be available as symbol or not.
|
19
|
+
# Default value is true.
|
20
|
+
# * _encoding_ : The encoding of the stream given as the first argument.
|
21
|
+
# It is effective only when the first argument is an instance of IO.
|
22
|
+
# Default value: Encoding.default_external
|
23
|
+
# == Returns:
|
24
|
+
# * An instance of Hash : When you give the string as the first argument.
|
25
|
+
# * An Array of Hash : When you give the IO as the first argument.
|
26
|
+
def parse(io_or_string, options = {})
|
27
|
+
case io_or_string
|
28
|
+
when String
|
29
|
+
parse_string(io_or_string, options)
|
30
|
+
when IO
|
31
|
+
parse_io(io_or_string = {})
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
# Parsing the content of the given stream or path.
|
36
|
+
# If you specified a stream as the first argument,
|
37
|
+
# this method behaves as same as #load.
|
38
|
+
#
|
39
|
+
# == Arguments:
|
40
|
+
# * _io_or_string_: a target to parse. Possible values are: String, IO.
|
41
|
+
# If you give the string value, it stands the path of the file to parse.
|
42
|
+
# If you give the IO value, it stands the stream which provides the contents to parse.
|
43
|
+
# *Note* : If you give the IO value, this method behaves like #parse.
|
44
|
+
# == Options:
|
45
|
+
# * _symbolize_keys_ : Whether the label will be available as symbol or not.
|
46
|
+
# Default value is true.
|
47
|
+
# * _encoding_ : The encoding of the stream given as the first argument.
|
48
|
+
# Default value: Encoding.default_external
|
49
|
+
# == Returns:
|
50
|
+
# * An Array of Hash : Each hash stands for a line of the io or the file.
|
51
|
+
def load(io_or_string, options = {})
|
52
|
+
encoding_opt = options.delete :encoding
|
53
|
+
encoding =
|
54
|
+
encoding_opt ? Encoding.find(encoding_opt) : Encoding.default_external
|
55
|
+
|
56
|
+
case io_or_string
|
57
|
+
when String
|
58
|
+
File.open(io_or_string, "r:#{encoding}"){|f|parse_io(f)}
|
59
|
+
when IO
|
60
|
+
parse_io(io)
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
# Dumping the value given into a new String.
|
65
|
+
# Each special character will be escaped with backslash('\'), and the expression should be contained in a single line.
|
66
|
+
#
|
67
|
+
# == Arguments:
|
68
|
+
# * _value_: a target to dump. It should respond to :to_hash.
|
69
|
+
# == Returns:
|
70
|
+
# * A LTSV String
|
71
|
+
def dump(value)
|
72
|
+
raise ArgumentError, "dump should take an argument of hash" unless
|
73
|
+
value.respond_to? :to_hash
|
74
|
+
|
75
|
+
hash = value.to_hash
|
76
|
+
|
77
|
+
hash.inject('') do |s, kv|
|
78
|
+
s << "\t" if s.bytesize > 0
|
79
|
+
|
80
|
+
(k, v) = kv
|
81
|
+
value = escape v
|
82
|
+
s << k.to_s << ':' << value
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
private
|
87
|
+
|
88
|
+
def parse_io(io, options)#:nodoc:
|
89
|
+
io.map{|l|parse_string l, options}
|
90
|
+
end
|
91
|
+
|
92
|
+
def parse_string(string, options)#:nodoc:
|
93
|
+
symbolize_keys = options.delete(:symbolize_keys)
|
94
|
+
symbolize_keys = true if symbolize_keys.nil?
|
95
|
+
|
96
|
+
string.split("\t").inject({}) do |h, i|
|
97
|
+
(key, value) = i.split(':', 2)
|
98
|
+
key = key.to_sym if symbolize_keys
|
99
|
+
unescape!(value)
|
100
|
+
h[key] = value.empty? ? nil : value
|
101
|
+
h
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
def unescape!(string)#:nodoc:
|
106
|
+
return nil if !string || string == ''
|
107
|
+
|
108
|
+
string.gsub!(/\\([a-z\\])/) do |m|
|
109
|
+
case $1
|
110
|
+
when 'r'
|
111
|
+
"\r"
|
112
|
+
when 'n'
|
113
|
+
"\n"
|
114
|
+
when 't'
|
115
|
+
"\t"
|
116
|
+
when '\\'
|
117
|
+
'\\'
|
118
|
+
else
|
119
|
+
m
|
120
|
+
end
|
121
|
+
end
|
122
|
+
end
|
123
|
+
|
124
|
+
def escape(string)#:nodoc:
|
125
|
+
value = string.kind_of?(String) ? string.dup : string.to_s
|
126
|
+
|
127
|
+
value.gsub!("\\", "\\\\")
|
128
|
+
value.gsub!("\n", "\\n")
|
129
|
+
value.gsub!("\r", "\\r")
|
130
|
+
value.gsub!("\t", "\\t")
|
131
|
+
|
132
|
+
value
|
133
|
+
end
|
134
|
+
|
135
|
+
module_function :load, :parse, :dump, :parse_io, :parse_string, :unescape!, :escape
|
136
|
+
|
137
|
+
class <<self
|
138
|
+
private :parse_io, :parse_string, :unescape!, :escape
|
139
|
+
end
|
140
|
+
end
|
data/ltsv.gemspec
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'ltsv'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "ltsv"
|
8
|
+
gem.version = LTSV::VERSION
|
9
|
+
gem.authors = ["condor"]
|
10
|
+
gem.email = ["condor1226@gmail.com"]
|
11
|
+
gem.description = %q{A Parser / Dumper for LTSV}
|
12
|
+
gem.summary = %q{A Parser / Dumper for LTSV}
|
13
|
+
gem.homepage = "https://github.com/condor/ltsv"
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
|
20
|
+
gem.add_development_dependency 'rspec'
|
21
|
+
end
|
data/spec/ltsv_spec.rb
ADDED
@@ -0,0 +1,75 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe LTSV do
|
4
|
+
|
5
|
+
describe :parse do
|
6
|
+
context 'String argument' do
|
7
|
+
it 'can parse labeled tab separated values into hash' do
|
8
|
+
line = "label1:value1\tlabel2:value2"
|
9
|
+
LTSV.parse(line).should == {:label1 => 'value1', :label2 => 'value2'}
|
10
|
+
end
|
11
|
+
|
12
|
+
it 'can parse the value that contains escape sequences' do
|
13
|
+
|
14
|
+
LTSV.parse("label1:value1\tlabel2:value\\nvalue").should ==
|
15
|
+
{:label1 => 'value1', :label2 => "value\nvalue"}
|
16
|
+
|
17
|
+
LTSV.parse("label1:value1\tlabel2:value\\rvalue").should ==
|
18
|
+
{:label1 => 'value1', :label2 => "value\rvalue"}
|
19
|
+
|
20
|
+
LTSV.parse("label1:value1\tlabel2:value\\tvalue").should ==
|
21
|
+
{:label1 => 'value1', :label2 => "value\tvalue"}
|
22
|
+
|
23
|
+
LTSV.parse("label1:value1\tlabel2:value\\\\value").should ==
|
24
|
+
{:label1 => 'value1', :label2 => "value\\value"}
|
25
|
+
end
|
26
|
+
|
27
|
+
it 'parses the value as-is when the backslash with a following ordinal character' do
|
28
|
+
|
29
|
+
LTSV.parse("label1:value1\tlabel2:value\\avalue").should ==
|
30
|
+
{:label1 => 'value1', :label2 => "value\\avalue"}
|
31
|
+
end
|
32
|
+
|
33
|
+
it 'parses the empty value field as nil' do
|
34
|
+
LTSV.parse("label1:\tlabel2:value2").should ==
|
35
|
+
{:label1 => nil, :label2 => 'value2'}
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
describe :load do
|
41
|
+
end
|
42
|
+
|
43
|
+
describe :dump do
|
44
|
+
|
45
|
+
specify 'dump into the format "label1:value1\tlabel2:value2"' do
|
46
|
+
LTSV.dump({:label1 => "value1", :label2 => "value2"}).should ==
|
47
|
+
"label1:value1\tlabel2:value2"
|
48
|
+
end
|
49
|
+
|
50
|
+
specify 'CRs, LFs, TABs, and backslashes in the value should be escaped' do
|
51
|
+
LTSV.dump({:label1 => "value\rvalue"}).should == "label1:value\\rvalue"
|
52
|
+
LTSV.dump({:label1 => "value\nvalue"}).should == "label1:value\\nvalue"
|
53
|
+
LTSV.dump({:label1 => "value\tvalue"}).should == "label1:value\\tvalue"
|
54
|
+
LTSV.dump({:label1 => "value\\value"}).should == "label1:value\\value"
|
55
|
+
end
|
56
|
+
|
57
|
+
specify ':s in the value should not be escaped' do
|
58
|
+
LTSV.dump({:label1 => "value:value"}).should == "label1:value:value"
|
59
|
+
end
|
60
|
+
|
61
|
+
specify 'should not fail when object to dump responds to :to_hash' do
|
62
|
+
target = Object.new
|
63
|
+
target.instance_eval do
|
64
|
+
def to_hash
|
65
|
+
{:label => 'value'}
|
66
|
+
end
|
67
|
+
end
|
68
|
+
LTSV.dump(target).should == "label:value"
|
69
|
+
end
|
70
|
+
|
71
|
+
specify 'fails when object to dump does not respond to :to_hash' do
|
72
|
+
lambda{LTSV.dump(Object.new)}.should raise_exception(ArgumentError)
|
73
|
+
end
|
74
|
+
end
|
75
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require File.expand_path(File.join(File.dirname(__FILE__), '..', 'lib', 'ltsv'))
|
metadata
ADDED
@@ -0,0 +1,72 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ltsv
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- condor
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-02-07 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
description: A Parser / Dumper for LTSV
|
31
|
+
email:
|
32
|
+
- condor1226@gmail.com
|
33
|
+
executables: []
|
34
|
+
extensions: []
|
35
|
+
extra_rdoc_files: []
|
36
|
+
files:
|
37
|
+
- .gitignore
|
38
|
+
- Gemfile
|
39
|
+
- LICENSE.txt
|
40
|
+
- README.md
|
41
|
+
- Rakefile
|
42
|
+
- lib/ltsv.rb
|
43
|
+
- ltsv.gemspec
|
44
|
+
- spec/ltsv_spec.rb
|
45
|
+
- spec/spec_helper.rb
|
46
|
+
homepage: https://github.com/condor/ltsv
|
47
|
+
licenses: []
|
48
|
+
post_install_message:
|
49
|
+
rdoc_options: []
|
50
|
+
require_paths:
|
51
|
+
- lib
|
52
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
54
|
+
requirements:
|
55
|
+
- - ! '>='
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
version: '0'
|
58
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
59
|
+
none: false
|
60
|
+
requirements:
|
61
|
+
- - ! '>='
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
version: '0'
|
64
|
+
requirements: []
|
65
|
+
rubyforge_project:
|
66
|
+
rubygems_version: 1.8.23
|
67
|
+
signing_key:
|
68
|
+
specification_version: 3
|
69
|
+
summary: A Parser / Dumper for LTSV
|
70
|
+
test_files:
|
71
|
+
- spec/ltsv_spec.rb
|
72
|
+
- spec/spec_helper.rb
|