twitter_cldr 3.0.1 → 3.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile +4 -2
- data/History.txt +4 -0
- data/README.md +17 -6
- data/lib/twitter_cldr/resources/postal_codes_importer.rb +12 -1
- data/lib/twitter_cldr/resources/regexp_ast_generator.rb +41 -0
- data/lib/twitter_cldr/resources.rb +1 -0
- data/lib/twitter_cldr/shared/postal_code_generator.rb +50 -0
- data/lib/twitter_cldr/shared/postal_codes.rb +48 -9
- data/lib/twitter_cldr/shared.rb +15 -14
- data/lib/twitter_cldr/utils/regexp_ast.rb +115 -0
- data/lib/twitter_cldr/utils/regexp_sampler.rb +149 -0
- data/lib/twitter_cldr/utils.rb +5 -3
- data/lib/twitter_cldr/version.rb +1 -1
- data/resources/shared/postal_codes.yml +1442 -159
- data/spec/bidi/bidi_spec.rb +1 -1
- data/spec/collation/collation_spec.rb +1 -1
- data/spec/collation/collator_spec.rb +31 -31
- data/spec/collation/implicit_collation_elements_spec.rb +6 -6
- data/spec/collation/sort_key_builder_spec.rb +28 -26
- data/spec/collation/tailoring_spec.rb +1 -1
- data/spec/collation/trie_builder_spec.rb +16 -16
- data/spec/collation/trie_dumps_spec.rb +2 -2
- data/spec/collation/trie_loader_spec.rb +8 -8
- data/spec/collation/trie_spec.rb +61 -61
- data/spec/collation/trie_with_fallback_spec.rb +5 -5
- data/spec/core_ext_spec.rb +1 -1
- data/spec/data_readers/additional_date_format_selector_spec.rb +38 -38
- data/spec/data_readers/date_time_data_reader_spec.rb +2 -2
- data/spec/data_readers/number_data_reader_spec.rb +1 -1
- data/spec/formatters/calendars/datetime_formatter_spec.rb +218 -218
- data/spec/formatters/list_formatter_spec.rb +8 -8
- data/spec/formatters/numbers/abbreviated/abbreviated_number_formatter_spec.rb +14 -14
- data/spec/formatters/numbers/abbreviated/long_decimal_formatter_spec.rb +4 -4
- data/spec/formatters/numbers/abbreviated/short_decimal_formatter_spec.rb +4 -4
- data/spec/formatters/numbers/currency_formatter_spec.rb +11 -11
- data/spec/formatters/numbers/decimal_formatter_spec.rb +3 -3
- data/spec/formatters/numbers/helpers/fraction_spec.rb +3 -3
- data/spec/formatters/numbers/helpers/integer_spec.rb +16 -16
- data/spec/formatters/numbers/number_formatter_spec.rb +21 -21
- data/spec/formatters/numbers/percent_formatter_spec.rb +3 -3
- data/spec/formatters/numbers/rbnf/rbnf_spec.rb +2 -2
- data/spec/formatters/plurals/plural_formatter_spec.rb +41 -41
- data/spec/formatters/plurals/rules_spec.rb +13 -13
- data/spec/localized/localized_array_spec.rb +12 -12
- data/spec/localized/localized_date_spec.rb +33 -33
- data/spec/localized/localized_datetime_spec.rb +11 -11
- data/spec/localized/localized_hash_spec.rb +4 -4
- data/spec/localized/localized_number_spec.rb +36 -36
- data/spec/localized/localized_object_spec.rb +8 -8
- data/spec/localized/localized_string_spec.rb +53 -53
- data/spec/localized/localized_symbol_spec.rb +9 -9
- data/spec/localized/localized_time_spec.rb +10 -10
- data/spec/localized/localized_timespan_spec.rb +8 -8
- data/spec/normalization_spec.rb +6 -6
- data/spec/parsers/number_parser_spec.rb +36 -36
- data/spec/parsers/parser_spec.rb +5 -5
- data/spec/parsers/segmentation_parser_spec.rb +19 -19
- data/spec/parsers/symbol_table_spec.rb +4 -4
- data/spec/parsers/unicode_regex/character_class_spec.rb +19 -19
- data/spec/parsers/unicode_regex/character_range_spec.rb +1 -1
- data/spec/parsers/unicode_regex/character_set_spec.rb +8 -8
- data/spec/parsers/unicode_regex/literal_spec.rb +5 -5
- data/spec/parsers/unicode_regex/unicode_string_spec.rb +2 -2
- data/spec/parsers/unicode_regex_parser_spec.rb +28 -28
- data/spec/resources/loader_spec.rb +32 -32
- data/spec/shared/break_iterator_spec.rb +13 -13
- data/spec/shared/calendar_spec.rb +59 -59
- data/spec/shared/casefolder_spec.rb +5 -5
- data/spec/shared/code_point_spec.rb +46 -46
- data/spec/shared/currencies_spec.rb +7 -7
- data/spec/shared/language_codes_spec.rb +34 -34
- data/spec/shared/languages_spec.rb +30 -30
- data/spec/shared/numbering_system_spec.rb +7 -7
- data/spec/shared/numbers_spec.rb +4 -4
- data/spec/shared/phone_codes_spec.rb +7 -7
- data/spec/shared/postal_code_generator_spec.rb +76 -0
- data/spec/shared/postal_codes_spec.rb +35 -29
- data/spec/shared/territories_spec.rb +40 -40
- data/spec/shared/unicode_regex_spec.rb +71 -71
- data/spec/spec_helper.rb +2 -2
- data/spec/tokenizers/calendars/date_tokenizer_spec.rb +1 -1
- data/spec/tokenizers/calendars/timespan_tokenizer_spec.rb +6 -6
- data/spec/tokenizers/composite_token_spec.rb +3 -3
- data/spec/tokenizers/token_spec.rb +3 -3
- data/spec/twitter_cldr_spec.rb +72 -72
- data/spec/utils/code_points_spec.rb +10 -10
- data/spec/utils/interpolation_spec.rb +32 -32
- data/spec/utils/range_set_spec.rb +36 -36
- data/spec/utils/regexp_ast_spec.rb +44 -0
- data/spec/utils/regexp_sampler_spec.rb +182 -0
- data/spec/utils/yaml/yaml_spec.rb +23 -23
- data/spec/utils_spec.rb +19 -19
- metadata +263 -258
data/spec/shared/numbers_spec.rb
CHANGED
@@ -14,22 +14,22 @@ describe Numbers do
|
|
14
14
|
it 'returns numerical symbols for default locale' do
|
15
15
|
stub(TwitterCldr).locale { :jp }
|
16
16
|
stub(TwitterCldr).get_locale_resource(:jp, :numbers) { { :jp => { :numbers => { :symbols => symbols } } } }
|
17
|
-
TwitterCldr::Shared::Numbers.symbols.
|
17
|
+
expect(TwitterCldr::Shared::Numbers.symbols).to eq(symbols)
|
18
18
|
end
|
19
19
|
|
20
20
|
it 'returns numerical symbols for default locale' do
|
21
21
|
stub(TwitterCldr).get_locale_resource(:np, :numbers) { { :np => { :numbers => { :symbols => symbols } } } }
|
22
|
-
TwitterCldr::Shared::Numbers.symbols(:np).
|
22
|
+
expect(TwitterCldr::Shared::Numbers.symbols(:np)).to eq(symbols)
|
23
23
|
end
|
24
24
|
|
25
25
|
it 'converts locale' do
|
26
26
|
stub(TwitterCldr).get_locale_resource(:'zh-Hant', :numbers) { { :'zh-Hant' => { :numbers => { :symbols => symbols } } } }
|
27
|
-
TwitterCldr::Shared::Numbers.symbols('zh-tw').
|
27
|
+
expect(TwitterCldr::Shared::Numbers.symbols('zh-tw')).to eq(symbols)
|
28
28
|
end
|
29
29
|
|
30
30
|
it 'returns nil if the resource is missing' do
|
31
31
|
stub(TwitterCldr).get_locale_resource(:nop, :numbers) { nil }
|
32
|
-
TwitterCldr::Shared::Numbers.symbols(:nop).
|
32
|
+
expect(TwitterCldr::Shared::Numbers.symbols(:nop)).to be_nil
|
33
33
|
end
|
34
34
|
end
|
35
35
|
end
|
@@ -12,15 +12,15 @@ describe PhoneCodes do
|
|
12
12
|
let(:territories) { PhoneCodes.territories }
|
13
13
|
|
14
14
|
it 'returns an array' do
|
15
|
-
territories.
|
15
|
+
expect(territories).to be_instance_of(Array)
|
16
16
|
end
|
17
17
|
|
18
18
|
it 'returns symbols' do
|
19
|
-
territories.each { |territory| territory.
|
19
|
+
territories.each { |territory| expect(territory).to be_instance_of(Symbol) }
|
20
20
|
end
|
21
21
|
|
22
22
|
it 'returns supported territories' do
|
23
|
-
territories.
|
23
|
+
expect(territories).to include(:br, :fr, :jp)
|
24
24
|
end
|
25
25
|
end
|
26
26
|
|
@@ -31,19 +31,19 @@ describe PhoneCodes do
|
|
31
31
|
before(:each) { mock(PhoneCodes).resource { { territory => code } } }
|
32
32
|
|
33
33
|
it 'returns phone code for a given territory' do
|
34
|
-
PhoneCodes.code_for_territory(territory).
|
34
|
+
expect(PhoneCodes.code_for_territory(territory)).to eq(code)
|
35
35
|
end
|
36
36
|
|
37
37
|
it 'returns nil if the regex is missing' do
|
38
|
-
PhoneCodes.code_for_territory(:foo).
|
38
|
+
expect(PhoneCodes.code_for_territory(:foo)).to be_nil
|
39
39
|
end
|
40
40
|
|
41
41
|
it 'accepts strings' do
|
42
|
-
PhoneCodes.code_for_territory(territory.to_s).
|
42
|
+
expect(PhoneCodes.code_for_territory(territory.to_s)).to eq(code)
|
43
43
|
end
|
44
44
|
|
45
45
|
it 'accepts upper-case strings' do
|
46
|
-
PhoneCodes.code_for_territory(territory.to_s.upcase).
|
46
|
+
expect(PhoneCodes.code_for_territory(territory.to_s.upcase)).to eq(code)
|
47
47
|
end
|
48
48
|
end
|
49
49
|
end
|
@@ -0,0 +1,76 @@
|
|
1
|
+
# encoding: UTF-8
|
2
|
+
|
3
|
+
# Copyright 2012 Twitter, Inc
|
4
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
5
|
+
|
6
|
+
require 'spec_helper'
|
7
|
+
|
8
|
+
include TwitterCldr::Shared
|
9
|
+
include TwitterCldr::Utils
|
10
|
+
|
11
|
+
describe PostalCodeGenerator do
|
12
|
+
let(:generator) do
|
13
|
+
PostalCodeGenerator.new(
|
14
|
+
RegexpAst::Root.new([
|
15
|
+
RegexpAst::Digit.new([], RegexpAst::Quantifier.new(3, 3)),
|
16
|
+
RegexpAst::Literal.new([], nil, '- '),
|
17
|
+
RegexpAst::Word.new([], RegexpAst::Quantifier.new(3, 3))
|
18
|
+
], nil)
|
19
|
+
)
|
20
|
+
end
|
21
|
+
|
22
|
+
let(:blank_generator) do
|
23
|
+
PostalCodeGenerator.new(
|
24
|
+
RegexpAst::Root.new([
|
25
|
+
RegexpAst::Alternation.new([
|
26
|
+
RegexpAst::Literal.new([], nil, ''),
|
27
|
+
RegexpAst::Word.new([], nil)
|
28
|
+
], nil)
|
29
|
+
], nil)
|
30
|
+
)
|
31
|
+
end
|
32
|
+
|
33
|
+
let(:limited_generator) do
|
34
|
+
PostalCodeGenerator.new(
|
35
|
+
RegexpAst::Root.new([
|
36
|
+
RegexpAst::CharacterSet.new([], nil, ['A-C'], false),
|
37
|
+
], nil)
|
38
|
+
)
|
39
|
+
end
|
40
|
+
|
41
|
+
describe "#generate" do
|
42
|
+
it "should generate correctly and not allow dashes to be followed by spaces" do
|
43
|
+
10.times do
|
44
|
+
generator.generate.should match(/\d{3}-\w{3}/)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
describe "#sample" do
|
50
|
+
it "should generate the given number of unique samples" do
|
51
|
+
samples = generator.sample(10)
|
52
|
+
samples.size.should == 10
|
53
|
+
samples.uniq.should == samples
|
54
|
+
samples.each do |sample|
|
55
|
+
sample.should match(/\d{3}-\w{3}/)
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
it "should not return blank samples" do
|
60
|
+
10.times do
|
61
|
+
blank_generator.sample(10).all? do |sample|
|
62
|
+
sample.empty?
|
63
|
+
end.should be_false
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
it "shouldn't loop infinitely if the number of possible samples is less than requested" do
|
68
|
+
limited_generator.sample(10).size.should < 10
|
69
|
+
end
|
70
|
+
|
71
|
+
it "should attempt to generate more samples if the set doesn't contain enough (but shouldn't infinite loop)" do
|
72
|
+
mock.proxy(limited_generator).generate.at_least(10)
|
73
|
+
limited_generator.sample(10).size.should < 10
|
74
|
+
end
|
75
|
+
end
|
76
|
+
end
|
@@ -12,57 +12,63 @@ describe PostalCodes do
|
|
12
12
|
let(:territories) { PostalCodes.territories }
|
13
13
|
|
14
14
|
it 'returns an array' do
|
15
|
-
territories.
|
15
|
+
expect(territories).to be_instance_of(Array)
|
16
16
|
end
|
17
17
|
|
18
18
|
it 'returns symbols' do
|
19
|
-
territories.each { |territory| territory.
|
19
|
+
territories.each { |territory| expect(territory).to be_instance_of(Symbol) }
|
20
20
|
end
|
21
21
|
|
22
22
|
it 'returns supported territories' do
|
23
|
-
territories.
|
23
|
+
expect(territories).to include(:br, :fr, :jp)
|
24
24
|
end
|
25
25
|
end
|
26
26
|
|
27
|
-
describe
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
before(:each) { mock(PostalCodes).resource { { territory => regex } } }
|
32
|
-
|
33
|
-
it 'returns postal code regex for a given territory' do
|
34
|
-
PostalCodes.regex_for_territory(territory).should == regex
|
35
|
-
end
|
36
|
-
|
37
|
-
it 'returns nil if the regex is missing' do
|
38
|
-
PostalCodes.regex_for_territory(:foo).should be_nil
|
27
|
+
describe "#new" do
|
28
|
+
it "should raise an error if the territory isn't supported" do
|
29
|
+
lambda { PostalCodes.for_territory(:xx) }.should raise_error(InvalidTerritoryError)
|
39
30
|
end
|
40
31
|
|
41
32
|
it 'accepts strings' do
|
42
|
-
PostalCodes.
|
33
|
+
PostalCodes.for_territory("us").should be_a(PostalCodes)
|
43
34
|
end
|
44
35
|
|
45
36
|
it 'accepts upper-case strings' do
|
46
|
-
PostalCodes.
|
37
|
+
PostalCodes.for_territory("US").should be_a(PostalCodes)
|
47
38
|
end
|
48
39
|
end
|
49
40
|
|
50
|
-
|
51
|
-
let(:
|
52
|
-
let(:territory) { :br }
|
53
|
-
|
54
|
-
before(:each) { mock(PostalCodes).resource { { territory => regex } } }
|
41
|
+
context "with a PostalCodes instance" do
|
42
|
+
let(:postal_code) { PostalCodes.for_territory(:us) }
|
55
43
|
|
56
|
-
|
57
|
-
|
44
|
+
describe '#regexp' do
|
45
|
+
it 'returns postal code regex for a given territory' do
|
46
|
+
postal_code.regexp.should be_a(Regexp)
|
47
|
+
end
|
58
48
|
end
|
59
49
|
|
60
|
-
|
61
|
-
|
50
|
+
describe '#valid?' do
|
51
|
+
it 'returns true if a given postal code satisfies the regexp' do
|
52
|
+
postal_code.valid?('12345-6789').should be_true
|
53
|
+
end
|
54
|
+
|
55
|
+
it "returns false if a given postal code doesn't satisfy the regexp" do
|
56
|
+
postal_code.valid?('postal-code').should be_false
|
57
|
+
end
|
62
58
|
end
|
63
59
|
|
64
|
-
|
65
|
-
PostalCodes.
|
60
|
+
describe "#sample" do
|
61
|
+
PostalCodes.territories.each do |territory|
|
62
|
+
postal_code = PostalCodes.for_territory(territory)
|
63
|
+
|
64
|
+
it "returns samples that match #{territory}" do
|
65
|
+
postal_code.sample(10).each do |sample|
|
66
|
+
result = postal_code.valid?(sample)
|
67
|
+
puts "Failed with example #{sample}" unless result
|
68
|
+
result.should be_true
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
66
72
|
end
|
67
73
|
end
|
68
|
-
end
|
74
|
+
end
|
@@ -10,109 +10,109 @@ include TwitterCldr::Shared
|
|
10
10
|
describe Territories do
|
11
11
|
describe "#translate_territory" do
|
12
12
|
it "should translate country names from one locale to another" do
|
13
|
-
Territories.translate_territory("Russia", :en, :es).
|
14
|
-
Territories.translate_territory("Rusia", :es, :en).
|
15
|
-
Territories.translate_territory("Spain", :en, :es).
|
16
|
-
Territories.translate_territory("España", :es, :ru).
|
13
|
+
expect(Territories.translate_territory("Russia", :en, :es)).to match_normalized("Rusia")
|
14
|
+
expect(Territories.translate_territory("Rusia", :es, :en)).to match_normalized("Russia")
|
15
|
+
expect(Territories.translate_territory("Spain", :en, :es)).to match_normalized("España")
|
16
|
+
expect(Territories.translate_territory("España", :es, :ru)).to match_normalized("Испания")
|
17
17
|
end
|
18
18
|
|
19
19
|
it "should use alternate/short names" do
|
20
|
-
Territories.translate_territory("Congo (DRC)", :en, :es).
|
21
|
-
Territories.translate_territory("Congo (Republic)", :en, :es).
|
22
|
-
Territories.translate_territory("East Timor", :en, :es).
|
23
|
-
Territories.translate_territory("Falkland Islands (Islas Malvinas)", :en, :es).
|
24
|
-
Territories.translate_territory("Hong Kong", :en, :es).
|
25
|
-
Territories.translate_territory("Ivory Coast", :en, :es).
|
26
|
-
Territories.translate_territory("Macau", :en, :es).
|
27
|
-
Territories.translate_territory("Macedonia (FYROM)", :en, :es).
|
20
|
+
expect(Territories.translate_territory("Congo (DRC)", :en, :es)).to match_normalized("Congo (República Democrática del Congo)")
|
21
|
+
expect(Territories.translate_territory("Congo (Republic)", :en, :es)).to match_normalized("Congo (República)")
|
22
|
+
expect(Territories.translate_territory("East Timor", :en, :es)).to match_normalized("Timor Oriental")
|
23
|
+
expect(Territories.translate_territory("Falkland Islands (Islas Malvinas)", :en, :es)).to match_normalized("Islas Malvinas (Islas Falkland)")
|
24
|
+
expect(Territories.translate_territory("Hong Kong", :en, :es)).to match_normalized("Hong Kong")
|
25
|
+
expect(Territories.translate_territory("Ivory Coast", :en, :es)).to match_normalized("Costa de Marfil")
|
26
|
+
expect(Territories.translate_territory("Macau", :en, :es)).to match_normalized("Macao")
|
27
|
+
expect(Territories.translate_territory("Macedonia (FYROM)", :en, :es)).to match_normalized("Macedonia (ERYM)")
|
28
28
|
end
|
29
29
|
|
30
30
|
it "should be capitalization agnostic" do
|
31
|
-
Territories.translate_territory("russia", :en, :es).
|
32
|
-
Territories.translate_territory("RUSSIA", :en, :es).
|
31
|
+
expect(Territories.translate_territory("russia", :en, :es)).to match_normalized("Rusia")
|
32
|
+
expect(Territories.translate_territory("RUSSIA", :en, :es)).to match_normalized("Rusia")
|
33
33
|
end
|
34
34
|
|
35
35
|
it "defaults the destination language to English (or whatever the global locale is)" do
|
36
|
-
Territories.translate_territory("Rusia", :es).
|
37
|
-
Territories.translate_territory("Россия", :ru).
|
36
|
+
expect(Territories.translate_territory("Rusia", :es)).to match_normalized("Russia")
|
37
|
+
expect(Territories.translate_territory("Россия", :ru)).to match_normalized("Russia")
|
38
38
|
end
|
39
39
|
|
40
40
|
it "defaults source and destination language to English if not given" do
|
41
|
-
Territories.translate_territory("Russia").
|
41
|
+
expect(Territories.translate_territory("Russia")).to match_normalized("Russia")
|
42
42
|
TwitterCldr.locale = :es
|
43
|
-
Territories.translate_territory("Russia").
|
43
|
+
expect(Territories.translate_territory("Russia")).to match_normalized("Rusia")
|
44
44
|
end
|
45
45
|
|
46
46
|
it "successfully translates locale codes that are and are not in the CLDR using the locale map" do
|
47
|
-
Territories.translate_territory("Russia", :en, :'zh-cn').
|
48
|
-
Territories.translate_territory("Russia", :en, :'zh').
|
47
|
+
expect(Territories.translate_territory("Russia", :en, :'zh-cn')).to match_normalized("俄罗斯")
|
48
|
+
expect(Territories.translate_territory("Russia", :en, :'zh')).to match_normalized("俄罗斯")
|
49
49
|
end
|
50
50
|
|
51
51
|
it "should return nil if no translation was found" do
|
52
|
-
Territories.translate_territory("Russia", :en, :blarg).
|
52
|
+
expect(Territories.translate_territory("Russia", :en, :blarg)).to eq(nil)
|
53
53
|
end
|
54
54
|
end
|
55
55
|
|
56
56
|
describe "#from_territory_code_for_locale" do
|
57
57
|
it "should return the territory in the correct locale for the given locale code (i.e. RU in English should be Russia)" do
|
58
|
-
Territories.from_territory_code_for_locale(:ES, :en).
|
59
|
-
Territories.from_territory_code_for_locale(:GB, :es).
|
58
|
+
expect(Territories.from_territory_code_for_locale(:ES, :en)).to match_normalized("Spain")
|
59
|
+
expect(Territories.from_territory_code_for_locale(:GB, :es)).to match_normalized("UK")
|
60
60
|
end
|
61
61
|
|
62
62
|
it "should work with lower-case country codes as well" do
|
63
|
-
Territories.from_territory_code_for_locale(:es, :en).
|
64
|
-
Territories.from_territory_code_for_locale(:gb, :es).
|
63
|
+
expect(Territories.from_territory_code_for_locale(:es, :en)).to match_normalized("Spain")
|
64
|
+
expect(Territories.from_territory_code_for_locale(:gb, :es)).to match_normalized("UK")
|
65
65
|
end
|
66
66
|
|
67
67
|
it "should work with Traditional Chinese" do
|
68
|
-
Territories.from_territory_code_for_locale(:US, :"zh-Hant").
|
68
|
+
expect(Territories.from_territory_code_for_locale(:US, :"zh-Hant")).to match_normalized("美國")
|
69
69
|
end
|
70
70
|
end
|
71
71
|
|
72
72
|
describe "#from_territory_code" do
|
73
73
|
it "should return the language in the default locale for the given locale code" do
|
74
|
-
Territories.from_territory_code(:ES).
|
75
|
-
Territories.from_territory_code(:RU).
|
74
|
+
expect(Territories.from_territory_code(:ES)).to match_normalized("Spain")
|
75
|
+
expect(Territories.from_territory_code(:RU)).to match_normalized("Russia")
|
76
76
|
TwitterCldr.locale = :es
|
77
|
-
Territories.from_territory_code(:ES).
|
77
|
+
expect(Territories.from_territory_code(:ES)).to match_normalized("España")
|
78
78
|
end
|
79
79
|
end
|
80
80
|
|
81
81
|
describe "#all_for" do
|
82
82
|
it "should return a hash of all languages for the given language code" do
|
83
83
|
territories = Territories.all_for(:es)
|
84
|
-
territories.
|
85
|
-
territories[:ru].
|
84
|
+
expect(territories).to be_a(Hash)
|
85
|
+
expect(territories[:ru]).to match_normalized("Rusia")
|
86
86
|
end
|
87
87
|
|
88
88
|
it "should return an empty hash for an invalid language" do
|
89
89
|
territories = Territories.all_for(:blarg)
|
90
|
-
territories.
|
90
|
+
expect(territories).to eq({})
|
91
91
|
end
|
92
92
|
end
|
93
93
|
|
94
94
|
describe "#all" do
|
95
95
|
it "should use the default language to get the language hash" do
|
96
96
|
territories = Territories.all
|
97
|
-
territories.
|
98
|
-
territories[:ru].
|
99
|
-
territories[:de].
|
97
|
+
expect(territories).to be_a(Hash)
|
98
|
+
expect(territories[:ru]).to match_normalized("Russia")
|
99
|
+
expect(territories[:de]).to match_normalized("Germany")
|
100
100
|
|
101
101
|
TwitterCldr.locale = :es
|
102
102
|
territories = Territories.all
|
103
|
-
territories.
|
104
|
-
territories[:ru].
|
105
|
-
territories[:de].
|
103
|
+
expect(territories).to be_a(Hash)
|
104
|
+
expect(territories[:ru]).to match_normalized("Rusia")
|
105
|
+
expect(territories[:de]).to match_normalized("Alemania")
|
106
106
|
end
|
107
107
|
end
|
108
108
|
|
109
109
|
describe "the lack of knowledge about three-digit UN area codes" do
|
110
110
|
it "should not be able to translate three-digit UN area codes" do
|
111
|
-
Territories.translate_territory("Southern Africa", :en, :es).
|
111
|
+
expect(Territories.translate_territory("Southern Africa", :en, :es)).to eq(nil)
|
112
112
|
end
|
113
113
|
|
114
114
|
it "should not be able to name three-digit UN area codes" do
|
115
|
-
Territories.from_territory_code_for_locale(:"18", :es).
|
115
|
+
expect(Territories.from_territory_code_for_locale(:"18", :es)).to eq(nil)
|
116
116
|
end
|
117
117
|
end
|
118
118
|
|
@@ -25,40 +25,40 @@ describe UnicodeRegex do
|
|
25
25
|
|
26
26
|
describe "#compile" do
|
27
27
|
it "should return a UnicodeRegex, parsed and ready to go" do
|
28
|
-
regex.
|
28
|
+
expect(regex).to be_a(UnicodeRegex)
|
29
29
|
end
|
30
30
|
end
|
31
31
|
|
32
32
|
describe "#to_regexp_str" do
|
33
33
|
it "should return the string representation of this regex" do
|
34
|
-
regex.to_regexp_str.
|
34
|
+
expect(regex.to_regexp_str).to eq("(?:[\\141-\\143])")
|
35
35
|
end
|
36
36
|
end
|
37
37
|
|
38
38
|
describe "#to_regexp" do
|
39
39
|
it "should return a ruby Regexp" do
|
40
40
|
if RUBY_VERSION <= "1.8.7"
|
41
|
-
regex.to_regexp.
|
41
|
+
expect(regex.to_regexp).to be_a(Oniguruma::ORegexp)
|
42
42
|
else
|
43
|
-
regex.to_regexp.
|
43
|
+
expect(regex.to_regexp).to be_a(Regexp)
|
44
44
|
end
|
45
45
|
end
|
46
46
|
|
47
47
|
it "should properly turn various basic regexes into strings" do
|
48
|
-
compile("^abc$").to_regexp_str.
|
49
|
-
compile("a(b)c").to_regexp_str.
|
50
|
-
compile("a(?:b)c").to_regexp_str.
|
51
|
-
compile("a{1,3}").to_regexp_str.
|
52
|
-
compile("[abc]").to_regexp_str.
|
48
|
+
expect(compile("^abc$").to_regexp_str).to eq("^(?:\\141)(?:\\142)(?:\\143)$")
|
49
|
+
expect(compile("a(b)c").to_regexp_str).to eq("(?:\\141)((?:\\142))(?:\\143)")
|
50
|
+
expect(compile("a(?:b)c").to_regexp_str).to eq("(?:\\141)(?:(?:\\142))(?:\\143)")
|
51
|
+
expect(compile("a{1,3}").to_regexp_str).to eq("(?:\\141){1,3}")
|
52
|
+
expect(compile("[abc]").to_regexp_str).to eq("(?:[\\141-\\143])")
|
53
53
|
end
|
54
54
|
|
55
55
|
it "should properly turn various complex regexes into strings" do
|
56
|
-
compile("[a-z0-9]").to_regexp_str.
|
57
|
-
compile("[\\u0067-\\u0071]").to_regexp_str.
|
56
|
+
expect(compile("[a-z0-9]").to_regexp_str).to eq("(?:[\\60-\\71]|[\\141-\\172])")
|
57
|
+
expect(compile("[\\u0067-\\u0071]").to_regexp_str).to eq("(?:[\\147-\\161])")
|
58
58
|
end
|
59
59
|
|
60
60
|
it "should properly substitute variables" do
|
61
|
-
compile("$FOO$BAR", symbol_table).to_regexp_str.
|
61
|
+
expect(compile("$FOO$BAR", symbol_table).to_regexp_str).to eq("(?:[\\147-\\153])(?:[\\160-\\163])")
|
62
62
|
end
|
63
63
|
end
|
64
64
|
end
|
@@ -67,10 +67,10 @@ describe UnicodeRegex do
|
|
67
67
|
describe "#match" do
|
68
68
|
it "should substitute variables from the symbol table" do
|
69
69
|
regex = compile("$FOO $BAR", symbol_table)
|
70
|
-
regex.
|
71
|
-
regex.
|
72
|
-
regex.
|
73
|
-
regex.
|
70
|
+
expect(regex).to exactly_match("h r")
|
71
|
+
expect(regex).to exactly_match("j q")
|
72
|
+
expect(regex).not_to exactly_match("h t")
|
73
|
+
expect(regex).not_to exactly_match("c s")
|
74
74
|
end
|
75
75
|
end
|
76
76
|
end
|
@@ -79,40 +79,40 @@ describe UnicodeRegex do
|
|
79
79
|
describe "#match" do
|
80
80
|
it "should match a regex with no char class" do
|
81
81
|
regex = compile("^abc$")
|
82
|
-
regex.
|
83
|
-
regex.
|
82
|
+
expect(regex).to exactly_match("abc")
|
83
|
+
expect(regex).not_to exactly_match("cba")
|
84
84
|
end
|
85
85
|
|
86
86
|
it "should match a regex with a capturing group" do
|
87
87
|
regex = compile("a(b)c")
|
88
88
|
match = regex.match("abc")
|
89
|
-
match.
|
90
|
-
match.captures[0].
|
89
|
+
expect(match).not_to be_nil
|
90
|
+
expect(match.captures[0]).to eq("b")
|
91
91
|
end
|
92
92
|
|
93
93
|
it "should match a regex with a non-capturing group" do
|
94
94
|
regex = compile("a(?:b)c")
|
95
95
|
match = regex.match("abc")
|
96
|
-
match.
|
97
|
-
match.captures.
|
96
|
+
expect(match).not_to be_nil
|
97
|
+
expect(match.captures).to eq([])
|
98
98
|
end
|
99
99
|
|
100
100
|
it "should match a regex with a quantifier" do
|
101
101
|
regex = compile("a{1,3}")
|
102
|
-
regex.
|
103
|
-
regex.
|
104
|
-
regex.
|
105
|
-
regex.
|
106
|
-
regex.
|
102
|
+
expect(regex).to exactly_match("a")
|
103
|
+
expect(regex).to exactly_match("aa")
|
104
|
+
expect(regex).to exactly_match("aaa")
|
105
|
+
expect(regex).not_to exactly_match("aaaa")
|
106
|
+
expect(regex).not_to exactly_match("b")
|
107
107
|
end
|
108
108
|
|
109
109
|
it "should match a regex with a basic char class" do
|
110
110
|
regex = compile("[abc]")
|
111
|
-
regex.
|
112
|
-
regex.
|
113
|
-
regex.
|
114
|
-
regex.
|
115
|
-
regex.
|
111
|
+
expect(regex).to exactly_match("a")
|
112
|
+
expect(regex).to exactly_match("b")
|
113
|
+
expect(regex).to exactly_match("c")
|
114
|
+
expect(regex).not_to exactly_match("ab")
|
115
|
+
expect(regex).not_to exactly_match("d")
|
116
116
|
end
|
117
117
|
end
|
118
118
|
end
|
@@ -121,82 +121,82 @@ describe UnicodeRegex do
|
|
121
121
|
describe "#match" do
|
122
122
|
it "should match a regex with a char class containing a range" do
|
123
123
|
regex = compile("[a-z0-9]")
|
124
|
-
regex.
|
125
|
-
regex.
|
126
|
-
regex.
|
127
|
-
regex.
|
128
|
-
regex.
|
129
|
-
regex.
|
130
|
-
regex.
|
131
|
-
regex.
|
124
|
+
expect(regex).to exactly_match("a")
|
125
|
+
expect(regex).to exactly_match("m")
|
126
|
+
expect(regex).to exactly_match("z")
|
127
|
+
expect(regex).to exactly_match("0")
|
128
|
+
expect(regex).to exactly_match("3")
|
129
|
+
expect(regex).to exactly_match("9")
|
130
|
+
expect(regex).not_to exactly_match("a0")
|
131
|
+
expect(regex).not_to exactly_match("m4")
|
132
132
|
end
|
133
133
|
|
134
134
|
it "should match a regex with a char class containing a unicode range" do
|
135
135
|
regex = compile("[\\u0067-\\u0071]") # g-q
|
136
|
-
regex.
|
137
|
-
regex.
|
138
|
-
regex.
|
139
|
-
regex.
|
136
|
+
expect(regex).to exactly_match("g")
|
137
|
+
expect(regex).to exactly_match("q")
|
138
|
+
expect(regex).to exactly_match("h")
|
139
|
+
expect(regex).not_to exactly_match("z")
|
140
140
|
end
|
141
141
|
|
142
142
|
it "should match a regex containing a character set" do
|
143
143
|
regex = compile("[\\p{Zs}]")
|
144
|
-
regex.
|
145
|
-
regex.
|
146
|
-
regex.
|
144
|
+
expect(regex).to exactly_match([160].pack("U*")) # non-breaking space
|
145
|
+
expect(regex).to exactly_match([5760].pack("U*")) # ogham space mark
|
146
|
+
expect(regex).not_to exactly_match("a")
|
147
147
|
end
|
148
148
|
|
149
149
|
it "should match a regex containing a negated character set" do
|
150
150
|
regex = compile("[\\P{Zs}]")
|
151
|
-
regex.
|
152
|
-
regex.
|
153
|
-
regex.
|
151
|
+
expect(regex).to exactly_match("a")
|
152
|
+
expect(regex).not_to exactly_match([160].pack("U*"))
|
153
|
+
expect(regex).not_to exactly_match([5760].pack("U*"))
|
154
154
|
end
|
155
155
|
|
156
156
|
it "should match a regex containing a character set (alternate syntax)" do
|
157
157
|
regex = compile("[[:Zs:]]")
|
158
|
-
regex.
|
159
|
-
regex.
|
160
|
-
regex.
|
158
|
+
expect(regex).to exactly_match([160].pack("U*")) # non-breaking space
|
159
|
+
expect(regex).to exactly_match([5760].pack("U*")) # ogham space mark
|
160
|
+
expect(regex).not_to exactly_match("a")
|
161
161
|
end
|
162
162
|
|
163
163
|
it "should match a regex containing a negated character set (alternate syntax)" do
|
164
164
|
regex = compile("[[:^Zs:]]")
|
165
|
-
regex.
|
166
|
-
regex.
|
167
|
-
regex.
|
165
|
+
expect(regex).to exactly_match("a")
|
166
|
+
expect(regex).not_to exactly_match([160].pack("U*"))
|
167
|
+
expect(regex).not_to exactly_match([5760].pack("U*"))
|
168
168
|
end
|
169
169
|
|
170
170
|
it "should match a regex with a character set and some quantifiers" do
|
171
171
|
regex = compile("[\\u0067-\\u0071]+")
|
172
|
-
regex.
|
173
|
-
regex.
|
174
|
-
regex.
|
175
|
-
regex.
|
172
|
+
expect(regex).to exactly_match("gg")
|
173
|
+
expect(regex).to exactly_match("gh")
|
174
|
+
expect(regex).to exactly_match("qjk")
|
175
|
+
expect(regex).not_to exactly_match("")
|
176
176
|
end
|
177
177
|
|
178
178
|
it "should match a regex that uses special switches inside the char class" do
|
179
179
|
regex = compile("[\\w]+")
|
180
|
-
regex.
|
181
|
-
regex.
|
182
|
-
regex.
|
183
|
-
regex.
|
180
|
+
expect(regex).to exactly_match("a")
|
181
|
+
expect(regex).to exactly_match("abc")
|
182
|
+
expect(regex).to exactly_match("a0b_1c2")
|
183
|
+
expect(regex).not_to exactly_match("$@#")
|
184
184
|
end
|
185
185
|
|
186
186
|
it "should match a regex that uses negated special switches inside the char class" do
|
187
187
|
regex = compile("[\\W]+")
|
188
|
-
regex.
|
189
|
-
regex.
|
190
|
-
regex.
|
191
|
-
regex.
|
188
|
+
expect(regex).not_to exactly_match("a")
|
189
|
+
expect(regex).not_to exactly_match("abc")
|
190
|
+
expect(regex).not_to exactly_match("a0b_1c2")
|
191
|
+
expect(regex).to exactly_match("$@#")
|
192
192
|
end
|
193
193
|
|
194
194
|
it "should match a regex with a complicated expression inside the char class" do
|
195
195
|
# not [separators U space-tilde] diff [letters diff numbers] (diff is commutative)
|
196
196
|
regex = compile("[^[\\p{Z}\\u0020-\\u007f]-[\\p{L}]-[\\p{N}]]")
|
197
|
-
regex.
|
198
|
-
regex.
|
199
|
-
regex.
|
197
|
+
expect(regex).to exactly_match(" ")
|
198
|
+
expect(regex).to exactly_match(",")
|
199
|
+
expect(regex).not_to exactly_match("a")
|
200
200
|
end
|
201
201
|
end
|
202
202
|
end
|