utf8 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +4 -0
- data/MIT-LICENSE +20 -0
- data/README.rdoc +46 -0
- data/Rakefile +11 -0
- data/benchmark/active_support.rb +61 -0
- data/benchmark/test.txt +693 -0
- data/ext/utf8/ext.c +21 -0
- data/ext/utf8/ext.h +17 -0
- data/ext/utf8/extconf.rb +7 -0
- data/ext/utf8/string_scanner_utf8.c +68 -0
- data/ext/utf8/string_scanner_utf8.h +6 -0
- data/ext/utf8/string_utf8.c +224 -0
- data/ext/utf8/string_utf8.h +6 -0
- data/ext/utf8/utf8.c +80 -0
- data/ext/utf8/utf8.h +7 -0
- data/lib/utf8.rb +5 -0
- data/lib/utf8/string.rb +19 -0
- data/lib/utf8/string_scanner.rb +21 -0
- data/spec/spec_helper.rb +5 -0
- data/spec/string_scanner_spec.rb +48 -0
- data/spec/string_spec.rb +151 -0
- data/utf8.gemspec +37 -0
- metadata +120 -0
data/lib/utf8.rb
ADDED
data/lib/utf8/string.rb
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
class String
|
2
|
+
# Wraps your string in an UTF8-aware version of String
|
3
|
+
def as_utf8
|
4
|
+
String::UTF8.new(self)
|
5
|
+
end
|
6
|
+
|
7
|
+
class UTF8
|
8
|
+
VERSION = "0.1.0"
|
9
|
+
|
10
|
+
# Gives you access to the raw non-UTF8-aware version of the string
|
11
|
+
def as_raw
|
12
|
+
::String.new(self)
|
13
|
+
end
|
14
|
+
|
15
|
+
alias :size :length
|
16
|
+
alias :chars :each_char
|
17
|
+
alias :slice :[]
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'utf8'
|
2
|
+
|
3
|
+
class StringScanner
|
4
|
+
# Returns an UTF8-aware version of StringScanner wrapping your original string
|
5
|
+
#
|
6
|
+
# NOTE: this will lose all state associated with the current StringScanner instance
|
7
|
+
# (like the current scan position)
|
8
|
+
def as_utf8
|
9
|
+
StringScanner::UTF8.new(self.string.as_utf8)
|
10
|
+
end
|
11
|
+
|
12
|
+
class UTF8
|
13
|
+
# Returns a non-UTF8-aware version of StringScanner wrapping your original string
|
14
|
+
#
|
15
|
+
# NOTE: this will lose all state associated with the current StringScanner::UTF8 instance
|
16
|
+
# (like the current scan position)
|
17
|
+
def as_raw
|
18
|
+
StringScanner.new(self.string)
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,48 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require File.expand_path('../spec_helper', __FILE__)
|
3
|
+
|
4
|
+
describe StringScanner::UTF8 do
|
5
|
+
before(:all) do
|
6
|
+
@char_array = ["怎", "麼", "也", "沒", "人", "寫", "了", "這", "個", "嗎"]
|
7
|
+
@scanner = StringScanner.new(@char_array.join)
|
8
|
+
@utf8_scanner = @scanner.as_utf8
|
9
|
+
end
|
10
|
+
|
11
|
+
it "should extend StringScanner, adding an as_utf8 method that returns a StringScanner::UTF8 instance" do
|
12
|
+
@scanner.should respond_to(:as_utf8)
|
13
|
+
@scanner.as_utf8.class.should eql(StringScanner::UTF8)
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should allow access to a regular (non-utf8-aware) StringScanner based on it's string" do
|
17
|
+
raw = @utf8_scanner.as_raw
|
18
|
+
raw.class.should eql(StringScanner)
|
19
|
+
raw.string.should eql(@utf8_scanner.string)
|
20
|
+
end
|
21
|
+
|
22
|
+
it "#getch should be utf8-aware" do
|
23
|
+
i=0
|
24
|
+
while char = @utf8_scanner.getch
|
25
|
+
char.should eql(@char_array[i])
|
26
|
+
i+=1
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should be able to be reset" do
|
31
|
+
i=0
|
32
|
+
while char = @utf8_scanner.getch
|
33
|
+
char.should eql(@char_array[i])
|
34
|
+
if i == 4
|
35
|
+
break
|
36
|
+
end
|
37
|
+
i+=1
|
38
|
+
end
|
39
|
+
|
40
|
+
@utf8_scanner.reset
|
41
|
+
|
42
|
+
i=0
|
43
|
+
while char = @utf8_scanner.getch
|
44
|
+
char.should eql(@char_array[i])
|
45
|
+
i+=1
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
data/spec/string_spec.rb
ADDED
@@ -0,0 +1,151 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require File.expand_path('../spec_helper', __FILE__)
|
3
|
+
|
4
|
+
describe String::UTF8 do
|
5
|
+
before(:all) do
|
6
|
+
@char_array = ["怎", "麼", "也", "沒", "人", "寫", "了", "這", "個", "嗎"]
|
7
|
+
@str = @char_array.join
|
8
|
+
@utf8 = @str.as_utf8
|
9
|
+
@utf8_len = @char_array.size
|
10
|
+
end
|
11
|
+
|
12
|
+
it "should extend String, adding an as_utf8 method that returns a String::UTF8 instance" do
|
13
|
+
"".should respond_to(:as_utf8)
|
14
|
+
"".as_utf8.class.should eql(String::UTF8)
|
15
|
+
end
|
16
|
+
|
17
|
+
it "should allow access to the underlying raw string" do
|
18
|
+
raw = @utf8.as_raw
|
19
|
+
raw.class.should eql(String)
|
20
|
+
if defined? Encoding
|
21
|
+
raw.length.should eql(@utf8_len)
|
22
|
+
else
|
23
|
+
raw.length.should eql(@str.size)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
it "should wrap all returned strings to be utf8-aware" do
|
28
|
+
@utf8[0].class.should eql(String::UTF8)
|
29
|
+
@utf8.chars.to_a[0].class.should eql(String::UTF8)
|
30
|
+
end
|
31
|
+
|
32
|
+
context "#length and #size" do
|
33
|
+
it "should be utf8-aware" do
|
34
|
+
@utf8.length.should eql(@utf8_len)
|
35
|
+
@utf8.size.should eql(@utf8_len)
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
context "#chars and #each_char" do
|
40
|
+
it "should be utf8-aware" do
|
41
|
+
klass = begin
|
42
|
+
if defined? Encoding
|
43
|
+
Enumerator
|
44
|
+
else
|
45
|
+
Enumerable::Enumerator
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
@utf8.chars.class.should eql(klass)
|
50
|
+
i=0
|
51
|
+
@utf8.chars do |char|
|
52
|
+
char.should_not be_nil
|
53
|
+
i+=1
|
54
|
+
end
|
55
|
+
joined = @utf8.chars.to_a.join
|
56
|
+
@utf8.should eql(joined)
|
57
|
+
@utf8.chars.to_a.size.should eql(@utf8_len)
|
58
|
+
@utf8.chars.to_a.should eql(@char_array)
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
context "[offset] syntax" do
|
63
|
+
it "should be utf8-aware" do
|
64
|
+
@char_array.each_with_index do |char, i|
|
65
|
+
utf8_char = @utf8[i]
|
66
|
+
utf8_char.should eql(char)
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
it "should support negative indices" do
|
71
|
+
utf8_char = @utf8[-5]
|
72
|
+
utf8_char.should eql(@char_array[-5])
|
73
|
+
end
|
74
|
+
|
75
|
+
it "should return nil for out of range indices" do
|
76
|
+
@utf8[100].should be_nil
|
77
|
+
@utf8[-100].should be_nil
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
context "[offset, length] syntax" do
|
82
|
+
it "should be utf8-aware" do
|
83
|
+
utf8_char = @utf8[1, 4]
|
84
|
+
utf8_char.should eql(@char_array[1, 4].join)
|
85
|
+
|
86
|
+
utf8_char = @utf8[0, 6]
|
87
|
+
utf8_char.should eql(@char_array[0, 6].join)
|
88
|
+
|
89
|
+
# this will fail due to a bug in 1.9
|
90
|
+
unless defined? Encoding
|
91
|
+
utf8_char = @utf8[6, 100]
|
92
|
+
utf8_char.should eql(@char_array[6, 100].join)
|
93
|
+
end
|
94
|
+
|
95
|
+
utf8_char = @utf8[-1, 2]
|
96
|
+
utf8_char.should eql(@char_array[-1, 2].join)
|
97
|
+
|
98
|
+
utf8_char = @utf8[-1, 100]
|
99
|
+
utf8_char.should eql(@char_array[-1, 100].join)
|
100
|
+
|
101
|
+
utf8_char = @utf8[0, 0]
|
102
|
+
utf8_char.should eql(@char_array[0, 0].join)
|
103
|
+
end
|
104
|
+
|
105
|
+
it "should return nil for an out of range offset or length" do
|
106
|
+
@utf8[100, 100].should be_nil
|
107
|
+
@utf8[-100, 100].should be_nil
|
108
|
+
@utf8[0, -100].should be_nil
|
109
|
+
end
|
110
|
+
end
|
111
|
+
|
112
|
+
context "[Range] syntax" do
|
113
|
+
it "should be utf8-aware" do
|
114
|
+
utf8_char = @utf8[1..4]
|
115
|
+
utf8_char.should eql(@char_array[1..4].join)
|
116
|
+
|
117
|
+
utf8_char = @utf8[0..6]
|
118
|
+
utf8_char.should eql(@char_array[0..6].join)
|
119
|
+
|
120
|
+
# this will fail due to a bug in 1.9
|
121
|
+
unless defined? Encoding
|
122
|
+
utf8_char = @utf8[6..100]
|
123
|
+
utf8_char.should eql(@char_array[6..100].join)
|
124
|
+
end
|
125
|
+
|
126
|
+
utf8_char = @utf8[-1..2]
|
127
|
+
utf8_char.should eql(@char_array[-1..2].join)
|
128
|
+
|
129
|
+
utf8_char = @utf8[-1..100]
|
130
|
+
utf8_char.should eql(@char_array[-1..100].join)
|
131
|
+
end
|
132
|
+
|
133
|
+
it "should return nil for an out of range offset or length" do
|
134
|
+
@utf8[100..100].should be_nil
|
135
|
+
@utf8[-100..100].should be_nil
|
136
|
+
@utf8[0..-100].should eql("")
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
it "[Regexp] syntax shouldn't be supported yet" do
|
141
|
+
lambda {
|
142
|
+
@utf8[/a/]
|
143
|
+
}.should raise_error(ArgumentError)
|
144
|
+
end
|
145
|
+
|
146
|
+
it "[Regexp, match_index] syntax shouldn't be supported yet" do
|
147
|
+
lambda {
|
148
|
+
@utf8[/(a)/, 1]
|
149
|
+
}.should raise_error(ArgumentError)
|
150
|
+
end
|
151
|
+
end
|
data/utf8.gemspec
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
Gem::Specification.new do |s|
|
4
|
+
s.name = %q{utf8}
|
5
|
+
s.version = "0.1.0"
|
6
|
+
|
7
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
8
|
+
s.authors = ["Brian Lopez"]
|
9
|
+
s.date = %q{2011-01-12}
|
10
|
+
s.email = %q{seniorlopez@gmail.com}
|
11
|
+
s.extensions = ["ext/utf8/extconf.rb"]
|
12
|
+
s.extra_rdoc_files = [
|
13
|
+
"README.rdoc"
|
14
|
+
]
|
15
|
+
s.files = [".gitignore", "MIT-LICENSE", "README.rdoc", "Rakefile", "benchmark/active_support.rb", "benchmark/test.txt", "ext/utf8/ext.c", "ext/utf8/ext.h", "ext/utf8/extconf.rb", "ext/utf8/string_scanner_utf8.c", "ext/utf8/string_scanner_utf8.h", "ext/utf8/string_utf8.c", "ext/utf8/string_utf8.h", "ext/utf8/utf8.c", "ext/utf8/utf8.h", "lib/utf8.rb", "lib/utf8/string.rb", "lib/utf8/string_scanner.rb", "spec/spec_helper.rb", "spec/string_scanner_spec.rb", "spec/string_spec.rb", "utf8.gemspec"]
|
16
|
+
s.homepage = %q{http://github.com/brianmario/utf8}
|
17
|
+
s.require_paths = ["lib", "ext"]
|
18
|
+
s.rubygems_version = %q{1.4.2}
|
19
|
+
s.summary = %q{A lightweight UTF8-aware String class meant for use with Ruby 1.8}
|
20
|
+
s.test_files = ["spec/spec_helper.rb", "spec/string_scanner_spec.rb", "spec/string_spec.rb"]
|
21
|
+
|
22
|
+
if s.respond_to? :specification_version then
|
23
|
+
s.specification_version = 3
|
24
|
+
|
25
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
26
|
+
s.add_development_dependency(%q<rake-compiler>, [">= 0.7.5"])
|
27
|
+
s.add_development_dependency(%q<rspec>, [">= 0"])
|
28
|
+
else
|
29
|
+
s.add_dependency(%q<rake-compiler>, [">= 0.7.5"])
|
30
|
+
s.add_dependency(%q<rspec>, [">= 0"])
|
31
|
+
end
|
32
|
+
else
|
33
|
+
s.add_dependency(%q<rake-compiler>, [">= 0.7.5"])
|
34
|
+
s.add_dependency(%q<rspec>, [">= 0"])
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
metadata
ADDED
@@ -0,0 +1,120 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: utf8
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Brian Lopez
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2011-01-12 00:00:00 -08:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: rake-compiler
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 9
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
- 7
|
33
|
+
- 5
|
34
|
+
version: 0.7.5
|
35
|
+
type: :development
|
36
|
+
version_requirements: *id001
|
37
|
+
- !ruby/object:Gem::Dependency
|
38
|
+
name: rspec
|
39
|
+
prerelease: false
|
40
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ">="
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
hash: 3
|
46
|
+
segments:
|
47
|
+
- 0
|
48
|
+
version: "0"
|
49
|
+
type: :development
|
50
|
+
version_requirements: *id002
|
51
|
+
description:
|
52
|
+
email: seniorlopez@gmail.com
|
53
|
+
executables: []
|
54
|
+
|
55
|
+
extensions:
|
56
|
+
- ext/utf8/extconf.rb
|
57
|
+
extra_rdoc_files:
|
58
|
+
- README.rdoc
|
59
|
+
files:
|
60
|
+
- .gitignore
|
61
|
+
- MIT-LICENSE
|
62
|
+
- README.rdoc
|
63
|
+
- Rakefile
|
64
|
+
- benchmark/active_support.rb
|
65
|
+
- benchmark/test.txt
|
66
|
+
- ext/utf8/ext.c
|
67
|
+
- ext/utf8/ext.h
|
68
|
+
- ext/utf8/extconf.rb
|
69
|
+
- ext/utf8/string_scanner_utf8.c
|
70
|
+
- ext/utf8/string_scanner_utf8.h
|
71
|
+
- ext/utf8/string_utf8.c
|
72
|
+
- ext/utf8/string_utf8.h
|
73
|
+
- ext/utf8/utf8.c
|
74
|
+
- ext/utf8/utf8.h
|
75
|
+
- lib/utf8.rb
|
76
|
+
- lib/utf8/string.rb
|
77
|
+
- lib/utf8/string_scanner.rb
|
78
|
+
- spec/spec_helper.rb
|
79
|
+
- spec/string_scanner_spec.rb
|
80
|
+
- spec/string_spec.rb
|
81
|
+
- utf8.gemspec
|
82
|
+
has_rdoc: true
|
83
|
+
homepage: http://github.com/brianmario/utf8
|
84
|
+
licenses: []
|
85
|
+
|
86
|
+
post_install_message:
|
87
|
+
rdoc_options: []
|
88
|
+
|
89
|
+
require_paths:
|
90
|
+
- lib
|
91
|
+
- ext
|
92
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
93
|
+
none: false
|
94
|
+
requirements:
|
95
|
+
- - ">="
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
hash: 3
|
98
|
+
segments:
|
99
|
+
- 0
|
100
|
+
version: "0"
|
101
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
102
|
+
none: false
|
103
|
+
requirements:
|
104
|
+
- - ">="
|
105
|
+
- !ruby/object:Gem::Version
|
106
|
+
hash: 3
|
107
|
+
segments:
|
108
|
+
- 0
|
109
|
+
version: "0"
|
110
|
+
requirements: []
|
111
|
+
|
112
|
+
rubyforge_project:
|
113
|
+
rubygems_version: 1.4.2
|
114
|
+
signing_key:
|
115
|
+
specification_version: 3
|
116
|
+
summary: A lightweight UTF8-aware String class meant for use with Ruby 1.8
|
117
|
+
test_files:
|
118
|
+
- spec/spec_helper.rb
|
119
|
+
- spec/string_scanner_spec.rb
|
120
|
+
- spec/string_spec.rb
|