ffi-icu 0.5.0 → 0.5.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +113 -57
- data/lib/ffi-icu/lib.rb +4 -0
- data/lib/ffi-icu/locale.rb +24 -0
- data/lib/ffi-icu/time_formatting.rb +1 -1
- data/lib/ffi-icu/version.rb +1 -1
- data/spec/locale_spec.rb +6 -0
- data/spec/time_spec.rb +6 -0
- metadata +17 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2075e91bd27944e5725d4379471db7bda9787d7b4a0622e92b71f15d03ed9ef3
|
4
|
+
data.tar.gz: 145eddff12e1d703ed29d01f3661e674439b39ff11c3882fc52633af50e6ca09
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6d63a1b1f93622d80abbc93889fa0e8eea90fa81025de1b4c5bf672a65d8922809100fa55ccc55a3c42599d2b2dfd3c2d69774601f512308783b66c26e9b6a71
|
7
|
+
data.tar.gz: 99fa27ab152f6f52a62d71a850e201ac61149c2c86b3fbb92fd2ff86f1ec942f19394af43e4068338d6a11121cdaadab9d53509da0d93750efeb1d54b960556d
|
data/README.md
CHANGED
@@ -18,9 +18,11 @@ ICU.
|
|
18
18
|
If you get messages that the library or functions are not found, you can
|
19
19
|
set some environment variables to tell ffi-icu where to find it, e.g.:
|
20
20
|
|
21
|
-
|
22
|
-
|
23
|
-
|
21
|
+
```sh
|
22
|
+
$ export FFI_ICU_LIB="icui18n.so"
|
23
|
+
$ export FFI_ICU_VERSION_SUFFIX="_3_8"
|
24
|
+
$ ruby -r ffi-icu program.rb
|
25
|
+
```
|
24
26
|
|
25
27
|
Features
|
26
28
|
========
|
@@ -31,17 +33,16 @@ Character Encoding Detection
|
|
31
33
|
Examples:
|
32
34
|
|
33
35
|
```ruby
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
match.confidence # => 80
|
36
|
+
match = ICU::CharDet.detect(str)
|
37
|
+
match.name # => "UTF-8"
|
38
|
+
match.confidence # => 80
|
38
39
|
```
|
39
40
|
|
40
41
|
or
|
41
42
|
|
42
43
|
```ruby
|
43
|
-
|
44
|
-
|
44
|
+
detector = ICU::CharDet::Detector.new
|
45
|
+
detector.detect(str) => #<struct ICU::CharDet::Detector::Match ...>
|
45
46
|
```
|
46
47
|
|
47
48
|
Why not just use rchardet?
|
@@ -54,16 +55,16 @@ Locale Sensitive Collation
|
|
54
55
|
Examples:
|
55
56
|
|
56
57
|
```ruby
|
57
|
-
|
58
|
+
ICU::Collation.collate("nb", %w[å æ ø]) == %w[æ ø å] #=> true
|
58
59
|
```
|
59
60
|
|
60
61
|
or
|
61
62
|
|
62
63
|
```ruby
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
64
|
+
collator = ICU::Collation::Collator.new("nb")
|
65
|
+
collator.compare("a", "b") #=> -1
|
66
|
+
collator.greater?("z", "a") #=> true
|
67
|
+
collator.collate(%w[å æ ø]) #=> ["æ", "ø", "å"]
|
67
68
|
```
|
68
69
|
|
69
70
|
Text Boundary Analysis
|
@@ -72,9 +73,9 @@ Text Boundary Analysis
|
|
72
73
|
Examples:
|
73
74
|
|
74
75
|
```ruby
|
75
|
-
|
76
|
-
|
77
|
-
|
76
|
+
iterator = ICU::BreakIterator.new(:word, "en_US")
|
77
|
+
iterator.text = "This is a sentence."
|
78
|
+
iterator.to_a #=> [0, 4, 5, 7, 8, 9, 10, 18, 19]
|
78
79
|
```
|
79
80
|
|
80
81
|
Number/Currency Formatting
|
@@ -83,50 +84,107 @@ Number/Currency Formatting
|
|
83
84
|
Examples:
|
84
85
|
|
85
86
|
```ruby
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
87
|
+
# class method interface
|
88
|
+
ICU::NumberFormatting.format_number("en", 1_000) #=> "1,000"
|
89
|
+
ICU::NumberFormatting.format_number("de-DE", 1234.56) #=> "1.234,56"
|
90
|
+
ICU::NumberFormatting.format_currency("en", 123.45, 'USD') #=> "$123.45"
|
91
|
+
ICU::NumberFormatting.format_percent("en", 0.53, 'USD') #=> "53%"
|
92
|
+
ICU::NumberFormatting.spell("en_US", 1_000) #=> "one thousand"
|
93
|
+
|
94
|
+
# reusable formatting objects
|
95
|
+
numf = ICU::NumberFormatting.create('fr-CA')
|
96
|
+
numf.format(1000) #=> "1 000"
|
97
|
+
|
98
|
+
curf = ICU::NumberFormatting.create('en-US', :currency)
|
99
|
+
curf.format(1234.56, 'USD') #=> "$1,234.56"
|
99
100
|
```
|
100
101
|
|
101
102
|
Time Formatting/Parsing
|
102
|
-
|
103
|
+
-----------------------
|
103
104
|
|
104
105
|
Examples:
|
105
106
|
|
106
107
|
```ruby
|
107
|
-
|
108
|
-
|
109
|
-
|
108
|
+
# class method interface
|
109
|
+
f = ICU::TimeFormatting.format(Time.mktime(2015, 11, 12, 15, 21, 16), {:locale => 'cs_CZ', :zone => 'Europe/Prague', :date => :short, :time => :short})
|
110
|
+
f #=> "12.11.15 15:21"
|
110
111
|
|
111
|
-
|
112
|
-
|
113
|
-
|
112
|
+
# reusable formatting objects
|
113
|
+
formatter = ICU::TimeFormatting.create(:locale => 'cs_CZ', :zone => 'Europe/Prague', :date => :long, :time => :none)
|
114
|
+
formatter.format(Time.now) #=> "25. února 2015"
|
114
115
|
```
|
115
116
|
|
116
117
|
```ruby
|
117
|
-
|
118
|
-
|
119
|
-
|
118
|
+
# reusable formatting objects
|
119
|
+
formatter = ICU::TimeFormatting.create(:locale => 'cs_CZ', :zone => 'Europe/Prague', :date => :long, :time => :none)
|
120
|
+
formatter.parse("25. února 2015") #=> Wed Feb 25 00:00:00 +0100 2015
|
120
121
|
```
|
121
122
|
|
122
123
|
For skeleton formatting, visit the [Unicode date field symbol table](https://unicode-org.github.io/icu/userguide/format_parse/datetime/#date-field-symbol-table) page to help find the pattern characters to use.
|
123
124
|
|
124
125
|
```ruby
|
125
|
-
|
126
|
-
|
126
|
+
formatter = ICU::TimeFormatting.create(:locale => 'cs_CZ', :date => :pattern, :time => :pattern, :skeleton => 'MMMMY')
|
127
|
+
formatter.format(Time.now) #=> "únor 2015"
|
127
128
|
|
128
|
-
|
129
|
-
|
129
|
+
formatter = ICU::TimeFormatting.create(:locale => 'cs_CZ', :date => :pattern, :time => :pattern, :skeleton => 'Y')
|
130
|
+
formatter.format(Time.now) #=> "2015"
|
131
|
+
```
|
132
|
+
|
133
|
+
Duration Formatting
|
134
|
+
-------------------
|
135
|
+
|
136
|
+
```ruby
|
137
|
+
# What the various styles look like
|
138
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :long)
|
139
|
+
formatter.format({hours: 8, minutes: 40, seconds: 35}) #=> "8 hours, 40 minutes, 35 seconds"
|
140
|
+
|
141
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :short)
|
142
|
+
formatter.format({hours: 8, minutes: 40, seconds: 35}) #=> "8 hrs, 40 mins, 35 secs"
|
143
|
+
|
144
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :narrow)
|
145
|
+
formatter.format({hours: 8, minutes: 40, seconds: 35}) #=> "8h 40min. 35s."
|
146
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :digital)
|
147
|
+
formatter.format({hours: 8, minutes: 40, seconds: 35}) #=> "8:40:35"
|
148
|
+
|
149
|
+
# How digital & non-digital formats deal with units > hours
|
150
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :narrow)
|
151
|
+
formatter.format({days: 2, hours: 8, minutes: 40, seconds: 35}) #=> "2d 8h 40min. 35s."
|
152
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :digital)
|
153
|
+
formatter.format({days: 2, hours: 8, minutes: 40, seconds: 35}) #=> "2d 8:40:35"
|
154
|
+
|
155
|
+
# Missing or zero parts are omitted
|
156
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :long)
|
157
|
+
formatter.format({days: 2, minutes: 40, seconds:0}) #=> "2 days, 40 minutes"
|
158
|
+
|
159
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :digital)
|
160
|
+
formatter.format({hours: 2, minutes: 40}) #=> "2:40"
|
161
|
+
|
162
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :digital)
|
163
|
+
formatter.format({minutes: 40, seconds: 7}) #=> "40:07"
|
164
|
+
|
165
|
+
# Sub-second parts are folded into seconds for digital display
|
166
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :digital)
|
167
|
+
formatter.format({hours: 5, minutes: 7, seconds: 23, milliseconds: 98, microseconds: 997}) #=> "5:07:23.098997"
|
168
|
+
|
169
|
+
# Zero-extension of sub-second parts in digital style
|
170
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :digital)
|
171
|
+
formatter.format({hours: 5, minutes: 7, seconds: 23, milliseconds: 400}) #=> "5:07:23.400"
|
172
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :digital)
|
173
|
+
formatter.format({hours: 5, minutes: 7, seconds: 23, milliseconds: 400, microseconds: 700}) #=> "5:07:23.400700"
|
174
|
+
|
175
|
+
# All fractional parts except the last are truncated
|
176
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'en-AU', style: :long)
|
177
|
+
formatter.format({days: 2, hours: 7.3, minutes: 40.9, seconds:0.43}) #=> "2 days, 7 hours, 40 minutes, 0.43 seconds"
|
178
|
+
|
179
|
+
# With RU locale
|
180
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'ru', style: :long)
|
181
|
+
formatter.format({hours: 1, minutes: 2, seconds: 3}) #=> "1 час 2 минуты 3 секунды"
|
182
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'ru', style: :long)
|
183
|
+
formatter.format({hours: 10, minutes: 20, seconds: 30}) #=> "10 часов 20 минут 30 секунд"
|
184
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'ru', style: :narrow)
|
185
|
+
formatter.format({hours: 1, minutes: 2, seconds: 3}) #=> "1 ч 2 мин 3 с"
|
186
|
+
formatter = ICU::DurationFormatting::DurationFormatter.new(locale: 'ru', style: :narrow)
|
187
|
+
formatter.format({hours: 10, minutes: 20, seconds: 30}) #=> "10 ч 20 мин 30 с"
|
130
188
|
```
|
131
189
|
|
132
190
|
Transliteration
|
@@ -136,23 +194,21 @@ Example:
|
|
136
194
|
|
137
195
|
```ruby
|
138
196
|
ICU::Transliteration.transliterate('Traditional-Simplified', '沈從文') # => "沈从文"
|
139
|
-
|
140
197
|
```
|
141
198
|
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
Platforms:
|
146
|
-
|
147
|
-
* OS X 10.6 - 10.10
|
148
|
-
* Travis' Linux
|
199
|
+
Locale
|
200
|
+
------
|
149
201
|
|
150
|
-
|
202
|
+
Examples:
|
151
203
|
|
152
|
-
|
153
|
-
|
154
|
-
-
|
155
|
-
|
204
|
+
```ruby
|
205
|
+
locale = ICU::Locale.new('en-US')
|
206
|
+
locale.display_country('en-US') #=> "United States"
|
207
|
+
locale.display_language('es') #=> "inglés"
|
208
|
+
locale.display_name('es') #=> "inglés (Estados Unidos)"
|
209
|
+
locale.display_name_with_context('en-US', [:length_short]) #=> "English (US)"
|
210
|
+
locale.display_name_with_context('en-US', [:length_long]) #=> "English (United States)"
|
211
|
+
```
|
156
212
|
|
157
213
|
TODO:
|
158
214
|
=====
|
data/lib/ffi-icu/lib.rb
CHANGED
@@ -500,5 +500,9 @@ module ICU
|
|
500
500
|
attach_function :ucal_setDefaultTimeZone, "ucal_setDefaultTimeZone#{suffix}", [:pointer, :pointer], :int32_t
|
501
501
|
attach_function :ucal_getDefaultTimeZone, "ucal_getDefaultTimeZone#{suffix}", [:pointer, :int32_t, :pointer], :int32_t
|
502
502
|
|
503
|
+
# ULocaleDisplayNames
|
504
|
+
attach_function :uldn_openForContext, "uldn_openForContext#{suffix}", [:string, :pointer, :int32_t, :pointer], :pointer
|
505
|
+
attach_function :uldn_localeDisplayName, "uldn_localeDisplayName#{suffix}", [:pointer, :string, :pointer, :int32_t, :pointer], :int32_t
|
506
|
+
attach_function :uldn_close, "uldn_close#{suffix}", [:pointer], :void
|
503
507
|
end # Lib
|
504
508
|
end # ICU
|
data/lib/ffi-icu/locale.rb
CHANGED
@@ -42,6 +42,11 @@ module ICU
|
|
42
42
|
|
43
43
|
attr_reader :id
|
44
44
|
|
45
|
+
DISPLAY_CONTEXT = {
|
46
|
+
length_full: 512, # UDISPCTX_LENGTH_FULL = (UDISPCTX_TYPE_DISPLAY_LENGTH<<8) + 0
|
47
|
+
length_short: 513 # UDISPCTX_LENGTH_SHORT = (UDISPCTX_TYPE_DISPLAY_LENGTH<<8) + 1
|
48
|
+
}
|
49
|
+
|
45
50
|
def initialize(id)
|
46
51
|
@id = id.to_s
|
47
52
|
end
|
@@ -96,6 +101,16 @@ module ICU
|
|
96
101
|
end
|
97
102
|
end
|
98
103
|
|
104
|
+
def display_name_with_context(locale, contexts = [])
|
105
|
+
contexts = DISPLAY_CONTEXT.select { |context| contexts.include?(context) }.values
|
106
|
+
|
107
|
+
with_locale_display_name(@id, contexts) do |locale_display_names|
|
108
|
+
Lib::Util.read_uchar_buffer(256) do |buffer, status|
|
109
|
+
Lib.uldn_localeDisplayName(locale_display_names, locale, buffer, buffer.size, status)
|
110
|
+
end
|
111
|
+
end
|
112
|
+
end
|
113
|
+
|
99
114
|
def display_script(locale = nil)
|
100
115
|
locale = locale.to_s unless locale.nil?
|
101
116
|
|
@@ -220,5 +235,14 @@ module ICU
|
|
220
235
|
|
221
236
|
Locale.new(result)
|
222
237
|
end
|
238
|
+
|
239
|
+
def with_locale_display_name(locale, contexts)
|
240
|
+
pointer = FFI::MemoryPointer.new(:int, contexts.length).write_array_of_int(contexts)
|
241
|
+
locale_display_names = ICU::Lib.check_error { |status| ICU::Lib.uldn_openForContext(locale, pointer, contexts.length, status) }
|
242
|
+
|
243
|
+
yield locale_display_names
|
244
|
+
ensure
|
245
|
+
Lib.uldn_close(locale_display_names) if locale_display_names
|
246
|
+
end
|
223
247
|
end
|
224
248
|
end
|
@@ -275,7 +275,7 @@ module ICU
|
|
275
275
|
resolved_hour_cycle = @hour_cycle == :locale ? Locale.new(@locale).keyword('hours') : @hour_cycle
|
276
276
|
|
277
277
|
if HOUR_CYCLE_SYMS.keys.include?(resolved_hour_cycle)
|
278
|
-
new_pattern_str.gsub!(/[hHkK]/, HOUR_CYCLE_SYMS[resolved_hour_cycle])
|
278
|
+
new_pattern_str.gsub!(/[hHkK](?=(?:[^\']|\'[^\']*\')*$)/, HOUR_CYCLE_SYMS[resolved_hour_cycle])
|
279
279
|
end
|
280
280
|
|
281
281
|
# Finally, set the new pattern onto the date time formatter
|
data/lib/ffi-icu/version.rb
CHANGED
data/spec/locale_spec.rb
CHANGED
@@ -123,6 +123,11 @@ module ICU
|
|
123
123
|
expect(Locale.new('zh_CH').display_name('fr')).to eq('chinois (Suisse)')
|
124
124
|
end
|
125
125
|
|
126
|
+
it 'returns the name using display context' do
|
127
|
+
expect(Locale.new('en_US').display_name_with_context('en_HK', [:length_full])).to eq('English (Hong Kong SAR China)')
|
128
|
+
expect(Locale.new('en_US').display_name_with_context('en_HK', [:length_short])).to eq('English (Hong Kong)')
|
129
|
+
end
|
130
|
+
|
126
131
|
it 'returns the script' do
|
127
132
|
expect(Locale.new('ja_Hira_JP').display_script('en')).to eq('Hiragana')
|
128
133
|
expect(Locale.new('ja_Hira_JP').display_script('ru')).to eq('хирагана')
|
@@ -140,6 +145,7 @@ module ICU
|
|
140
145
|
expect(Locale.new('en_VI').display_country('ccp')).to_not be_nil
|
141
146
|
expect(Locale.new('yue_Hant').display_language('ccp')).to_not be_nil
|
142
147
|
expect(Locale.new('en_VI').display_name('ccp')).to_not be_nil
|
148
|
+
expect(Locale.new('ccp').display_name_with_context('en_VI')).to_not be_nil
|
143
149
|
expect(Locale.new('yue_Hant').display_script('ccp')).to_not be_nil
|
144
150
|
expect(Locale.new('en_US_POSIX').display_variant('sl')).to_not be_nil
|
145
151
|
end
|
data/spec/time_spec.rb
CHANGED
@@ -173,6 +173,12 @@ module ICU
|
|
173
173
|
end
|
174
174
|
end
|
175
175
|
|
176
|
+
it 'for lang=fi hour_cycle=h12' do
|
177
|
+
t = Time.new(2021, 04, 01, 13, 05, 0, "+00:00")
|
178
|
+
str = TimeFormatting.format(t, locale: 'fi', zone: 'America/Los_Angeles', date: :long, time: :short, hour_cycle: 'h12')
|
179
|
+
expect(str).to match(/\sklo\s/)
|
180
|
+
end
|
181
|
+
|
176
182
|
it 'works with defaults on a h12 locale' do
|
177
183
|
t = Time.new(2021, 04, 01, 13, 05, 0, "+00:00")
|
178
184
|
str = TimeFormatting.format(t, time: :short, date: :none, locale: 'en_AU', zone: 'UTC', hour_cycle: :locale)
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ffi-icu
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.5.
|
4
|
+
version: 0.5.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jari Bakken
|
@@ -130,8 +130,22 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
130
130
|
- !ruby/object:Gem::Version
|
131
131
|
version: '0'
|
132
132
|
requirements: []
|
133
|
-
rubygems_version: 3.
|
133
|
+
rubygems_version: 3.4.10
|
134
134
|
signing_key:
|
135
135
|
specification_version: 4
|
136
136
|
summary: Simple Ruby FFI wrappers for things I need from ICU.
|
137
|
-
test_files:
|
137
|
+
test_files:
|
138
|
+
- spec/break_iterator_spec.rb
|
139
|
+
- spec/chardet_spec.rb
|
140
|
+
- spec/collation_spec.rb
|
141
|
+
- spec/duration_formatting_spec.rb
|
142
|
+
- spec/lib/version_info_spec.rb
|
143
|
+
- spec/lib_spec.rb
|
144
|
+
- spec/locale_spec.rb
|
145
|
+
- spec/normalization_spec.rb
|
146
|
+
- spec/normalizer_spec.rb
|
147
|
+
- spec/number_formatting_spec.rb
|
148
|
+
- spec/spec_helper.rb
|
149
|
+
- spec/time_spec.rb
|
150
|
+
- spec/transliteration_spec.rb
|
151
|
+
- spec/uchar_spec.rb
|