legalese 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +17 -0
- data/Rakefile +53 -0
- data/VERSION +1 -0
- data/lib/legalese.rb +13 -0
- data/lib/legalese/legalese_parser.treetop +70 -0
- data/test/examples/paragraphs.rb +22 -0
- data/test/examples/sections.rb +35 -0
- data/test/examples/text_blocks.rb +11 -0
- data/test/helper.rb +10 -0
- data/test/test_legalese.rb +29 -0
- metadata +91 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Levin Alexander
|
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.rdoc
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
= legalese
|
2
|
+
|
3
|
+
Description goes here.
|
4
|
+
|
5
|
+
== Note on Patches/Pull Requests
|
6
|
+
|
7
|
+
* Fork the project.
|
8
|
+
* Make your feature addition or bug fix.
|
9
|
+
* Add tests for it. This is important so I don't break it in a
|
10
|
+
future version unintentionally.
|
11
|
+
* Commit, do not mess with rakefile, version, or history.
|
12
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
13
|
+
* Send me a pull request. Bonus points for topic branches.
|
14
|
+
|
15
|
+
== Copyright
|
16
|
+
|
17
|
+
Copyright (c) 2009 Levin Alexander. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "legalese"
|
8
|
+
gem.summary = %Q{parser and grammar for german legal texts}
|
9
|
+
gem.description = ""
|
10
|
+
gem.email = "mail@levinalex.net"
|
11
|
+
gem.homepage = "http://github.com/levinalex/legalese"
|
12
|
+
gem.authors = ["Levin Alexander"]
|
13
|
+
gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
|
14
|
+
gem.add_development_dependency "yard", ">= 0"
|
15
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
16
|
+
end
|
17
|
+
Jeweler::GemcutterTasks.new
|
18
|
+
rescue LoadError
|
19
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
20
|
+
end
|
21
|
+
|
22
|
+
require 'rake/testtask'
|
23
|
+
Rake::TestTask.new(:test) do |test|
|
24
|
+
test.libs << 'lib' << 'test'
|
25
|
+
test.pattern = 'test/**/test_*.rb'
|
26
|
+
test.verbose = true
|
27
|
+
end
|
28
|
+
|
29
|
+
begin
|
30
|
+
require 'rcov/rcovtask'
|
31
|
+
Rcov::RcovTask.new do |test|
|
32
|
+
test.libs << 'test'
|
33
|
+
test.pattern = 'test/**/test_*.rb'
|
34
|
+
test.verbose = true
|
35
|
+
end
|
36
|
+
rescue LoadError
|
37
|
+
task :rcov do
|
38
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
task :test => :check_dependencies
|
43
|
+
|
44
|
+
task :default => :test
|
45
|
+
|
46
|
+
begin
|
47
|
+
require 'yard'
|
48
|
+
YARD::Rake::YardocTask.new
|
49
|
+
rescue LoadError
|
50
|
+
task :yardoc do
|
51
|
+
abort "YARD is not available. In order to run yardoc, you must: sudo gem install yard"
|
52
|
+
end
|
53
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.1
|
data/lib/legalese.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
$LOAD_PATH.unshift File.join(File.dirname(__FILE__), "legalese")
|
2
|
+
|
3
|
+
require "treetop"
|
4
|
+
require "polyglot"
|
5
|
+
require "legalese_parser"
|
6
|
+
|
7
|
+
|
8
|
+
class Legalese
|
9
|
+
def self.parse(text)
|
10
|
+
match = LegaleseGrammarParser.new.parse(text.strip)
|
11
|
+
match.content if match
|
12
|
+
end
|
13
|
+
end
|
@@ -0,0 +1,70 @@
|
|
1
|
+
grammar LegaleseGrammar
|
2
|
+
rule document
|
3
|
+
(block_element)* {
|
4
|
+
def content
|
5
|
+
elements.map{ |e| e.content }.compact
|
6
|
+
end
|
7
|
+
}
|
8
|
+
end
|
9
|
+
|
10
|
+
rule section
|
11
|
+
marker:section_marker blocks:(!section data:block_element)* {
|
12
|
+
def content
|
13
|
+
[:section, { :name => marker.name }, blocks.elements.map { |e| e.data.content }]
|
14
|
+
end
|
15
|
+
}
|
16
|
+
end
|
17
|
+
|
18
|
+
rule section_marker
|
19
|
+
"§" number newlines {
|
20
|
+
def name
|
21
|
+
number.text_value.to_i
|
22
|
+
end
|
23
|
+
}
|
24
|
+
end
|
25
|
+
|
26
|
+
rule paragraph
|
27
|
+
marker:paragraph_marker blocks:(!paragraph !section data:block_element)* {
|
28
|
+
def content
|
29
|
+
[:para, { :name => marker.name }, blocks.elements.map { |e| e.data.content }]
|
30
|
+
end
|
31
|
+
}
|
32
|
+
end
|
33
|
+
|
34
|
+
rule paragraph_marker
|
35
|
+
"(" number ")" newlines {
|
36
|
+
def name
|
37
|
+
number.text_value.to_i
|
38
|
+
end
|
39
|
+
}
|
40
|
+
end
|
41
|
+
|
42
|
+
rule text_block
|
43
|
+
(!blank_lines .)+ newlines* {
|
44
|
+
def content
|
45
|
+
[:text_block, text_value.strip]
|
46
|
+
end
|
47
|
+
}
|
48
|
+
end
|
49
|
+
|
50
|
+
rule newlines
|
51
|
+
"\n"+
|
52
|
+
end
|
53
|
+
|
54
|
+
rule blank_lines
|
55
|
+
"\n" "\n"+ {
|
56
|
+
def content
|
57
|
+
nil
|
58
|
+
end
|
59
|
+
}
|
60
|
+
end
|
61
|
+
|
62
|
+
rule block_element
|
63
|
+
section / paragraph / text_block / blank_lines
|
64
|
+
end
|
65
|
+
|
66
|
+
rule number
|
67
|
+
[0-9]+
|
68
|
+
end
|
69
|
+
|
70
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
[
|
2
|
+
[:para, {:name => 1}, [
|
3
|
+
[:text_block, "Hello World\nFirst Section"],
|
4
|
+
[:text_block, "Second Paragraph"]]],
|
5
|
+
[:para, {:name => 2}, [
|
6
|
+
[:text_block, "Second Section"],
|
7
|
+
[:text_block, "Last Paragraph"]]
|
8
|
+
]
|
9
|
+
]
|
10
|
+
|
11
|
+
__END__
|
12
|
+
|
13
|
+
(1)
|
14
|
+
Hello World
|
15
|
+
First Section
|
16
|
+
|
17
|
+
Second Paragraph
|
18
|
+
|
19
|
+
(2)
|
20
|
+
Second Section
|
21
|
+
|
22
|
+
Last Paragraph
|
@@ -0,0 +1,35 @@
|
|
1
|
+
[
|
2
|
+
[:section, {:name => 1}, [
|
3
|
+
[:para, {:name => 1}, [
|
4
|
+
[:text_block, "Hello World"],
|
5
|
+
[:text_block, "Two Parts"]]],
|
6
|
+
[:para, {:name => 2}, [
|
7
|
+
[:text_block, "First Section, Second Paragraph"]]]
|
8
|
+
]],
|
9
|
+
[:section, {:name => 2}, [
|
10
|
+
[:para, {:name => 1}, [
|
11
|
+
[:text_block, "Something"]]],
|
12
|
+
[:para, {:name => 2}, [
|
13
|
+
[:text_block, "Something else"]]]
|
14
|
+
]]
|
15
|
+
]
|
16
|
+
|
17
|
+
__END__
|
18
|
+
|
19
|
+
§1
|
20
|
+
|
21
|
+
(1)
|
22
|
+
Hello World
|
23
|
+
|
24
|
+
Two Parts
|
25
|
+
|
26
|
+
(2)
|
27
|
+
First Section, Second Paragraph
|
28
|
+
|
29
|
+
§2
|
30
|
+
|
31
|
+
(1)
|
32
|
+
Something
|
33
|
+
|
34
|
+
(2)
|
35
|
+
Something else
|
data/test/helper.rb
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestLegalese < Test::Unit::TestCase
|
4
|
+
|
5
|
+
should "have a parse method" do
|
6
|
+
assert_nothing_raised do
|
7
|
+
Legalese.parse("hello world")
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
[
|
12
|
+
["empty text", "", []]
|
13
|
+
].each do |note, input, expected|
|
14
|
+
should "parse #{note} correctly" do
|
15
|
+
assert_equal expected, Legalese.parse(input)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
Dir[File.join(File.dirname(__FILE__), "examples/**/*.rb")].each do |fname|
|
20
|
+
should "parse #{fname} correctly" do
|
21
|
+
expected, input = File.read(fname).split("__END__")
|
22
|
+
expected = eval(expected)
|
23
|
+
|
24
|
+
actual = Legalese.parse(input)
|
25
|
+
|
26
|
+
assert_equal actual, expected
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
metadata
ADDED
@@ -0,0 +1,91 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: legalese
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Levin Alexander
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-12-30 00:00:00 +01:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: thoughtbot-shoulda
|
17
|
+
type: :development
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: "0"
|
24
|
+
version:
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: yard
|
27
|
+
type: :development
|
28
|
+
version_requirement:
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: "0"
|
34
|
+
version:
|
35
|
+
description: ""
|
36
|
+
email: mail@levinalex.net
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files:
|
42
|
+
- LICENSE
|
43
|
+
- README.rdoc
|
44
|
+
files:
|
45
|
+
- .document
|
46
|
+
- .gitignore
|
47
|
+
- LICENSE
|
48
|
+
- README.rdoc
|
49
|
+
- Rakefile
|
50
|
+
- VERSION
|
51
|
+
- lib/legalese.rb
|
52
|
+
- lib/legalese/legalese_parser.treetop
|
53
|
+
- test/examples/paragraphs.rb
|
54
|
+
- test/examples/sections.rb
|
55
|
+
- test/examples/text_blocks.rb
|
56
|
+
- test/helper.rb
|
57
|
+
- test/test_legalese.rb
|
58
|
+
has_rdoc: true
|
59
|
+
homepage: http://github.com/levinalex/legalese
|
60
|
+
licenses: []
|
61
|
+
|
62
|
+
post_install_message:
|
63
|
+
rdoc_options:
|
64
|
+
- --charset=UTF-8
|
65
|
+
require_paths:
|
66
|
+
- lib
|
67
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - ">="
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: "0"
|
72
|
+
version:
|
73
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - ">="
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: "0"
|
78
|
+
version:
|
79
|
+
requirements: []
|
80
|
+
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 1.3.5
|
83
|
+
signing_key:
|
84
|
+
specification_version: 3
|
85
|
+
summary: parser and grammar for german legal texts
|
86
|
+
test_files:
|
87
|
+
- test/examples/paragraphs.rb
|
88
|
+
- test/examples/sections.rb
|
89
|
+
- test/examples/text_blocks.rb
|
90
|
+
- test/helper.rb
|
91
|
+
- test/test_legalese.rb
|