babosa 1.0.2 → 2.0.0

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.
Files changed (56) hide show
  1. checksums.yaml +5 -5
  2. checksums.yaml.gz.sig +0 -0
  3. data.tar.gz.sig +0 -0
  4. data/Changelog.md +20 -0
  5. data/README.md +83 -121
  6. data/Rakefile +9 -8
  7. data/lib/babosa.rb +2 -4
  8. data/lib/babosa/identifier.rb +104 -129
  9. data/lib/babosa/transliterator/base.rb +57 -54
  10. data/lib/babosa/transliterator/bulgarian.rb +3 -2
  11. data/lib/babosa/transliterator/cyrillic.rb +5 -5
  12. data/lib/babosa/transliterator/danish.rb +3 -3
  13. data/lib/babosa/transliterator/german.rb +3 -2
  14. data/lib/babosa/transliterator/greek.rb +4 -3
  15. data/lib/babosa/transliterator/hindi.rb +138 -0
  16. data/lib/babosa/transliterator/latin.rb +5 -5
  17. data/lib/babosa/transliterator/macedonian.rb +3 -2
  18. data/lib/babosa/transliterator/norwegian.rb +3 -3
  19. data/lib/babosa/transliterator/romanian.rb +3 -2
  20. data/lib/babosa/transliterator/russian.rb +3 -2
  21. data/lib/babosa/transliterator/serbian.rb +29 -27
  22. data/lib/babosa/transliterator/spanish.rb +2 -2
  23. data/lib/babosa/transliterator/swedish.rb +3 -3
  24. data/lib/babosa/transliterator/turkish.rb +8 -0
  25. data/lib/babosa/transliterator/ukrainian.rb +5 -4
  26. data/lib/babosa/transliterator/vietnamese.rb +4 -3
  27. data/lib/babosa/version.rb +3 -1
  28. data/spec/{babosa_spec.rb → identifier_spec.rb} +18 -15
  29. data/spec/spec_helper.rb +15 -6
  30. data/spec/transliterators/base_spec.rb +5 -6
  31. data/spec/transliterators/bulgarian_spec.rb +4 -5
  32. data/spec/transliterators/danish_spec.rb +5 -6
  33. data/spec/transliterators/german_spec.rb +4 -5
  34. data/spec/transliterators/greek_spec.rb +7 -7
  35. data/spec/transliterators/hindi_spec.rb +17 -0
  36. data/spec/transliterators/latin_spec.rb +3 -4
  37. data/spec/transliterators/macedonian_spec.rb +3 -4
  38. data/spec/transliterators/norwegian_spec.rb +4 -4
  39. data/spec/transliterators/polish_spec.rb +3 -5
  40. data/spec/transliterators/romanian_spec.rb +5 -6
  41. data/spec/transliterators/russian_spec.rb +3 -4
  42. data/spec/transliterators/serbian_spec.rb +6 -7
  43. data/spec/transliterators/spanish_spec.rb +4 -5
  44. data/spec/transliterators/swedish_spec.rb +7 -7
  45. data/spec/transliterators/turkish_spec.rb +24 -0
  46. data/spec/transliterators/ukrainian_spec.rb +74 -75
  47. data/spec/transliterators/vietnamese_spec.rb +10 -10
  48. metadata +50 -41
  49. metadata.gz.sig +2 -0
  50. data/lib/babosa/utf8/active_support_proxy.rb +0 -26
  51. data/lib/babosa/utf8/dumb_proxy.rb +0 -49
  52. data/lib/babosa/utf8/java_proxy.rb +0 -22
  53. data/lib/babosa/utf8/mappings.rb +0 -193
  54. data/lib/babosa/utf8/proxy.rb +0 -125
  55. data/lib/babosa/utf8/unicode_proxy.rb +0 -23
  56. data/spec/utf8_proxy_spec.rb +0 -52
data/spec/utf8_proxy_spec.rb DELETED
@@ -1,52 +0,0 @@
1
- # encoding: utf-8
2
- require File.expand_path("../spec_helper", __FILE__)
3
-
4
- PROXIES = [Babosa::UTF8::DumbProxy, Babosa::UTF8::ActiveSupportProxy, Babosa::UTF8::UnicodeProxy]
5
- PROXIES << Babosa::UTF8::JavaProxy if Babosa.jruby15?
6
-
7
- PROXIES.each do |proxy|
8
-
9
- describe proxy do
10
-
11
- around do |example|
12
- begin
13
- old_proxy = Babosa::Identifier.utf8_proxy
14
- Babosa::Identifier.utf8_proxy = proxy
15
- example.run
16
- ensure
17
- Babosa::Identifier.utf8_proxy = old_proxy
18
- end
19
- end
20
-
21
- describe "#normalize_utf8" do
22
- it "should normalize to canonical composed" do
23
- # ÅÉÎØÜ
24
- uncomposed_bytes = [65, 204, 138, 69, 204, 129, 73, 204, 130, 195, 152, 85, 204, 136]
25
- composed_bytes = [195, 133, 195, 137, 195, 142, 195, 152, 195, 156]
26
- uncomposed_string = uncomposed_bytes.pack("C*").unpack("U*").pack("U*")
27
- expect(proxy.normalize_utf8(uncomposed_string).unpack("C*")).to eql(composed_bytes)
28
- end
29
- end
30
-
31
- describe "#upcase" do
32
- it "should upcase the string" do
33
- expect(proxy.upcase("åéîøü")).to eql("ÅÉÎØÜ")
34
- expect("åéîøü".to_identifier.upcase).to eql("ÅÉÎØÜ")
35
- end
36
- end
37
-
38
- describe "#downcase" do
39
- it "should downcase the string" do
40
- expect(proxy.downcase("ÅÉÎØÜ")).to eql("åéîøü")
41
- expect("ÅÉÎØÜ".to_identifier.downcase).to eql("åéîøü")
42
- end
43
- end
44
-
45
- describe 'tidy_bytes' do
46
- it 'should fix invalid UTF-8 strings' do
47
- expect(proxy.tidy_bytes("\x93abc")).to eq('“abc')
48
- end
49
- end
50
-
51
- end
52
- end