unicode-rbnf 2.3.0__tar.gz → 2.4.1__tar.gz

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 (129) hide show
  1. {unicode_rbnf-2.3.0/unicode_rbnf.egg-info → unicode_rbnf-2.4.1}/PKG-INFO +10 -2
  2. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/pyproject.toml +12 -2
  3. unicode_rbnf-2.4.1/tests/test_cs.py +31 -0
  4. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_en.py +4 -3
  5. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_engine.py +16 -4
  6. unicode_rbnf-2.4.1/tests/test_ko.py +8 -0
  7. unicode_rbnf-2.4.1/tests/test_pl.py +59 -0
  8. unicode_rbnf-2.4.1/tests/test_plural_rules.py +85 -0
  9. unicode_rbnf-2.4.1/tests/test_ro.py +17 -0
  10. unicode_rbnf-2.4.1/tests/test_ru.py +29 -0
  11. unicode_rbnf-2.4.1/tests/test_sk.py +41 -0
  12. unicode_rbnf-2.4.1/tests/test_sr.py +31 -0
  13. unicode_rbnf-2.4.1/tests/test_zu.py +36 -0
  14. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/__main__.py +4 -4
  15. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/engine.py +192 -27
  16. unicode_rbnf-2.4.1/unicode_rbnf/ordinals.xml +176 -0
  17. unicode_rbnf-2.4.1/unicode_rbnf/plural_rules.py +186 -0
  18. unicode_rbnf-2.4.1/unicode_rbnf/plurals.xml +256 -0
  19. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/cs.xml +6 -9
  20. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ro.xml +12 -12
  21. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/sk.xml +12 -6
  22. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/sr.xml +30 -18
  23. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/sr_Latn.xml +30 -18
  24. unicode_rbnf-2.4.1/unicode_rbnf/rbnf/zu.xml +120 -0
  25. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1/unicode_rbnf.egg-info}/PKG-INFO +10 -2
  26. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf.egg-info/SOURCES.txt +14 -1
  27. unicode_rbnf-2.4.1/unicode_rbnf.egg-info/requires.txt +8 -0
  28. unicode_rbnf-2.3.0/tests/test_ro.py +0 -6
  29. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/LICENSE.md +0 -0
  30. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/README.md +0 -0
  31. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/setup.cfg +0 -0
  32. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_de.py +0 -0
  33. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_decimal_format.py +0 -0
  34. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_es.py +0 -0
  35. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_fi.py +0 -0
  36. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_fr.py +0 -0
  37. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_load_all.py +2 -2
  38. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/tests/test_sl.py +0 -0
  39. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/__init__.py +0 -0
  40. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/decimal_format.py +0 -0
  41. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/py.typed +0 -0
  42. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/af.xml +0 -0
  43. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ak.xml +0 -0
  44. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/am.xml +0 -0
  45. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ar.xml +0 -0
  46. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/az.xml +0 -0
  47. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/be.xml +0 -0
  48. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/bg.xml +0 -0
  49. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/bs.xml +0 -0
  50. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ca.xml +0 -0
  51. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ccp.xml +0 -0
  52. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/chr.xml +0 -0
  53. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/cy.xml +0 -0
  54. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/da.xml +0 -0
  55. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/de.xml +0 -0
  56. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/de_CH.xml +0 -0
  57. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ee.xml +0 -0
  58. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/el.xml +0 -0
  59. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/en.xml +0 -0
  60. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/en_001.xml +0 -0
  61. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/en_IN.xml +0 -0
  62. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/eo.xml +0 -0
  63. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/es.xml +0 -0
  64. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/es_419.xml +0 -0
  65. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/et.xml +0 -0
  66. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fa.xml +0 -0
  67. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fa_AF.xml +0 -0
  68. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ff.xml +0 -0
  69. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fi.xml +0 -0
  70. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fil.xml +0 -0
  71. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fo.xml +0 -0
  72. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fr.xml +0 -0
  73. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fr_BE.xml +0 -0
  74. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/fr_CH.xml +0 -0
  75. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ga.xml +0 -0
  76. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/he.xml +0 -0
  77. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/hi.xml +0 -0
  78. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/hr.xml +0 -0
  79. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/hu.xml +0 -0
  80. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/hy.xml +0 -0
  81. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/id.xml +0 -0
  82. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/is.xml +0 -0
  83. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/it.xml +0 -0
  84. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ja.xml +0 -0
  85. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ka.xml +0 -0
  86. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/kk.xml +0 -0
  87. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/kl.xml +0 -0
  88. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/km.xml +0 -0
  89. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ko.xml +0 -0
  90. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ky.xml +0 -0
  91. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/lb.xml +0 -0
  92. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/lo.xml +0 -0
  93. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/lrc.xml +0 -0
  94. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/lt.xml +0 -0
  95. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/lv.xml +0 -0
  96. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/mk.xml +0 -0
  97. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ms.xml +0 -0
  98. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/mt.xml +0 -0
  99. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/my.xml +0 -0
  100. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/nb.xml +0 -0
  101. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ne.xml +0 -0
  102. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/nl.xml +0 -0
  103. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/nn.xml +0 -0
  104. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/no.xml +0 -0
  105. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/pl.xml +0 -0
  106. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/pt.xml +0 -0
  107. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/pt_PT.xml +0 -0
  108. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/qu.xml +0 -0
  109. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/root.xml +0 -0
  110. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ru.xml +0 -0
  111. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/se.xml +0 -0
  112. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/sl.xml +0 -0
  113. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/sq.xml +0 -0
  114. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/su.xml +0 -0
  115. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/sv.xml +0 -0
  116. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/sw.xml +0 -0
  117. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/ta.xml +0 -0
  118. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/th.xml +0 -0
  119. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/tr.xml +0 -0
  120. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/uk.xml +0 -0
  121. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/vec.xml +0 -0
  122. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/vi.xml +0 -0
  123. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/yue.xml +0 -0
  124. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/yue_Hans.xml +0 -0
  125. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/zh.xml +0 -0
  126. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf/rbnf/zh_Hant.xml +0 -0
  127. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf.egg-info/dependency_links.txt +0 -0
  128. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf.egg-info/top_level.txt +0 -0
  129. {unicode_rbnf-2.3.0 → unicode_rbnf-2.4.1}/unicode_rbnf.egg-info/zip-safe +0 -0
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.2
1
+ Metadata-Version: 2.4
2
2
  Name: unicode-rbnf
3
- Version: 2.3.0
3
+ Version: 2.4.1
4
4
  Summary: Rule-based number formatting using Unicode CLDR data
5
5
  Author-email: Michael Hansen <mike@rhasspy.org>
6
6
  License: MIT
@@ -20,6 +20,14 @@ Classifier: Programming Language :: Python :: 3.13
20
20
  Requires-Python: >=3.8.0
21
21
  Description-Content-Type: text/markdown
22
22
  License-File: LICENSE.md
23
+ Provides-Extra: dev
24
+ Requires-Dist: black==24.8.0; extra == "dev"
25
+ Requires-Dist: flake8==7.1.1; extra == "dev"
26
+ Requires-Dist: mypy==1.14.0; extra == "dev"
27
+ Requires-Dist: pylint==3.2.7; extra == "dev"
28
+ Requires-Dist: pytest==8.3.4; extra == "dev"
29
+ Requires-Dist: build==1.2.2; extra == "dev"
30
+ Dynamic: license-file
23
31
 
24
32
  # Unicode RBNF
25
33
 
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "unicode-rbnf"
7
- version = "2.3.0"
7
+ version = "2.4.1"
8
8
  license = {text = "MIT"}
9
9
  description = "Rule-based number formatting using Unicode CLDR data"
10
10
  readme = "README.md"
@@ -29,6 +29,16 @@ requires-python = ">=3.8.0"
29
29
  [project.urls]
30
30
  "Source Code" = "https://github.com/rhasspy/unicode-rbnf"
31
31
 
32
+ [project.optional-dependencies]
33
+ dev = [
34
+ "black==24.8.0",
35
+ "flake8==7.1.1",
36
+ "mypy==1.14.0",
37
+ "pylint==3.2.7",
38
+ "pytest==8.3.4",
39
+ "build==1.2.2",
40
+ ]
41
+
32
42
  [tool.setuptools]
33
43
  platforms = ["any"]
34
44
  zip-safe = true
@@ -38,4 +48,4 @@ include-package-data = true
38
48
  include = ["unicode_rbnf"]
39
49
 
40
50
  [tool.setuptools.package-data]
41
- unicode_rbnf = ["rbnf/*.xml"]
51
+ unicode_rbnf = ["rbnf/*.xml", "*.xml"]
@@ -0,0 +1,31 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_czech():
5
+ engine = RbnfEngine.for_language("cs")
6
+
7
+ assert engine.format_number(7).text == "sedm"
8
+ assert engine.format_number(15).text == "patnáct"
9
+
10
+ assert engine.format_number(100).text == "sto"
11
+ assert engine.format_number(150).text == "sto padesát"
12
+ assert engine.format_number(200).text == "dvě stě"
13
+ assert engine.format_number(300).text == "tři sta"
14
+ assert engine.format_number(500).text == "pět set"
15
+
16
+ # A multiplier of one is not spoken: "tisíc", never "jedna tisíc".
17
+ assert engine.format_number(1000).text == "tisíc"
18
+ assert engine.format_number(1100).text == "tisíc sto"
19
+ assert engine.format_number(1234).text == "tisíc dvě stě třicet čtyři"
20
+
21
+ assert engine.format_number(5000).text == "pět tisíc"
22
+ assert engine.format_number(12000).text == "dvanáct tisíc"
23
+
24
+
25
+ def test_czech_thousands_are_masculine():
26
+ engine = RbnfEngine.for_language("cs")
27
+
28
+ # "tisíc" is masculine, so the multiplier is "dva", not the feminine "dvě".
29
+ assert engine.format_number(2000).text == "dva tisíce"
30
+ assert engine.format_number(22000).text == "dvacet dva tisíc"
31
+ assert engine.format_number(21000).text == "dvacet jeden tisíc"
@@ -1,4 +1,4 @@
1
- from unicode_rbnf import RbnfEngine, FormatPurpose
1
+ from unicode_rbnf import FormatPurpose, RbnfEngine
2
2
 
3
3
 
4
4
  def test_english():
@@ -32,11 +32,12 @@ def test_english():
32
32
  # Special rules
33
33
  assert engine.format_number(-1).text == "minus one"
34
34
  assert engine.format_number(float("nan")).text == "not a number"
35
- assert engine.format_number(float("inf")).text == "infinite"
35
+ assert engine.format_number(float("inf")).text == "infinity"
36
36
 
37
37
  # Fractions
38
- assert engine.format_number(3.14).text == "three point fourteen"
38
+ assert engine.format_number(3.14).text == "three point one four"
39
39
  assert engine.format_number("5.3").text == "five point three"
40
+ assert engine.format_number(0.0123).text == "zero point zero one two three"
40
41
 
41
42
  # Ordinals
42
43
  assert engine.format_number(20, FormatPurpose.ORDINAL).text == "twentieth"
@@ -1,13 +1,13 @@
1
1
  import pytest
2
2
 
3
3
  from unicode_rbnf.engine import (
4
+ FormatResult,
5
+ NoRuleForNumberError,
6
+ RbnfEngine,
4
7
  RbnfRule,
5
- TextRulePart,
6
8
  SubRulePart,
7
9
  SubType,
8
- RbnfEngine,
9
- FormatResult,
10
- NoRuleForNumberError,
10
+ TextRulePart,
11
11
  )
12
12
 
13
13
 
@@ -68,6 +68,7 @@ def test_format_number():
68
68
 
69
69
  assert engine.format_number(222) == FormatResult(
70
70
  text="two hundred twenty-two",
71
+ text_ruleset="spellout-cardinal",
71
72
  text_by_ruleset={"spellout-cardinal": "two hundred twenty-two"},
72
73
  )
73
74
 
@@ -88,3 +89,14 @@ def test_no_rules_for_number():
88
89
 
89
90
  with pytest.raises(NoRuleForNumberError):
90
91
  engine.format_number(1, ruleset_names=["does_not_exist"])
92
+
93
+
94
+ def test_parse_remainder_whitespace():
95
+ assert RbnfRule.parse(12.34, "←← x →→→;") == RbnfRule(
96
+ 12,
97
+ parts=[
98
+ SubRulePart(SubType.QUOTIENT),
99
+ TextRulePart(" x"),
100
+ SubRulePart(SubType.REMAINDER, text_before=" "),
101
+ ],
102
+ )
@@ -0,0 +1,8 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_korean():
5
+ engine = RbnfEngine.for_language("ko")
6
+
7
+ assert engine.format_number(20.03).text == "이십점영삼"
8
+ assert engine.format_number(20.0123).text == "이십점영일이삼"
@@ -0,0 +1,59 @@
1
+ from unicode_rbnf import FormatPurpose, RbnfEngine
2
+
3
+
4
+ def test_polish():
5
+ engine = RbnfEngine.for_language("pl")
6
+
7
+ assert engine.format_number(7).text == "siedem"
8
+ assert engine.format_number(15).text == "piętnaście"
9
+ assert engine.format_number(42).text == "czterdzieści dwa"
10
+ assert engine.format_number(100).text == "sto"
11
+ assert engine.format_number(143).text == "sto czterdzieści trzy"
12
+ assert engine.format_number(1000).text == "tysiąc"
13
+ assert engine.format_number(1234).text == "tysiąc dwieście trzydzieści cztery"
14
+ assert engine.format_number(3144).text == "trzy tysiące sto czterdzieści cztery"
15
+ assert engine.format_number(10000).text == "dziesięć tysięcy"
16
+ assert (
17
+ engine.format_number(83145).text
18
+ == "osiemdziesiąt trzy tysiące sto czterdzieści pięć"
19
+ )
20
+
21
+ assert engine.format_number(100000).text == "sto tysięcy"
22
+ assert (
23
+ engine.format_number(683146).text
24
+ == "sześćset osiemdziesiąt trzy tysiące sto czterdzieści sześć"
25
+ )
26
+
27
+ assert engine.format_number(1000000).text == "milion"
28
+ assert engine.format_number(10000000).text == "dziesięć milionów"
29
+ assert engine.format_number(100000000).text == "sto milionów"
30
+ assert engine.format_number(1000000000).text == "miliard"
31
+
32
+ # Special rules
33
+ assert engine.format_number(-1).text == "minus jeden"
34
+ assert engine.format_number(-14).text == "minus czternaście"
35
+ # assert engine.format_number(-14.6).text == "minus czternaście przecinek sześć"
36
+ # assert engine.format_number(-14.89).text == "minus czternaście przecinek osiemdziesiąt dziewięć"
37
+
38
+ # assert engine.format_number(float("nan")).text == "nie jest liczbą"
39
+ # assert engine.format_number(float("inf")).text == "nieskończona"
40
+
41
+ # Fractions
42
+ # assert engine.format_number(3.14).text == "trzy przecinek czternaście"
43
+ # assert engine.format_number("5.3").text == "pięć przecinek trzy"
44
+
45
+ # Years
46
+ assert (
47
+ engine.format_number(1999, FormatPurpose.YEAR).text
48
+ == "tysiąc dziewięćset dziewięćdziesiąt dziewięć"
49
+ )
50
+
51
+
52
+ def test_polish_teens_agreement():
53
+ engine = RbnfEngine.for_language("pl")
54
+
55
+ # Polish puts the teens in "many" and 22 back in "few".
56
+ assert engine.format_number(12000).text == "dwanaście tysięcy"
57
+ assert engine.format_number(13000).text == "trzynaście tysięcy"
58
+ assert engine.format_number(22000).text == "dwadzieścia dwa tysiące"
59
+ assert engine.format_number(112000).text == "sto dwanaście tysięcy"
@@ -0,0 +1,85 @@
1
+ from decimal import Decimal
2
+
3
+ from unicode_rbnf.plural_rules import PluralType, get_plural_category
4
+
5
+
6
+ def test_slovak_few_is_the_whole_integer():
7
+ # Slovak "few" is i = 2..4, so it does not reach into the tens.
8
+ assert get_plural_category("sk", 1) == "one"
9
+ assert get_plural_category("sk", 2) == "few"
10
+ assert get_plural_category("sk", 4) == "few"
11
+ assert get_plural_category("sk", 5) == "other"
12
+ assert get_plural_category("sk", 12) == "other"
13
+ assert get_plural_category("sk", 22) == "other"
14
+ assert get_plural_category("sk", 683) == "other"
15
+
16
+
17
+ def test_russian_looks_at_final_digits():
18
+ assert get_plural_category("ru", 1) == "one"
19
+ assert get_plural_category("ru", 2) == "few"
20
+ assert get_plural_category("ru", 5) == "many"
21
+
22
+ # The teens are "many" even though they end in 1-4.
23
+ assert get_plural_category("ru", 11) == "many"
24
+ assert get_plural_category("ru", 12) == "many"
25
+ assert get_plural_category("ru", 14) == "many"
26
+ assert get_plural_category("ru", 111) == "many"
27
+
28
+ # Past the teens the final digit decides again.
29
+ assert get_plural_category("ru", 21) == "one"
30
+ assert get_plural_category("ru", 22) == "few"
31
+ assert get_plural_category("ru", 25) == "many"
32
+
33
+
34
+ def test_polish_differs_from_russian():
35
+ # Polish puts 12 in "many" and 22 in "few", like Russian, but 1000 and
36
+ # every other i != 1 ending in 0-1 is "many" rather than "one".
37
+ assert get_plural_category("pl", 1) == "one"
38
+ assert get_plural_category("pl", 2) == "few"
39
+ assert get_plural_category("pl", 12) == "many"
40
+ assert get_plural_category("pl", 22) == "few"
41
+ assert get_plural_category("pl", 112) == "many"
42
+
43
+
44
+ def test_two_category_languages():
45
+ for language in ("en", "de", "sv", "bg", "lb"):
46
+ assert get_plural_category(language, 1) == "one"
47
+ assert get_plural_category(language, 2) == "other"
48
+
49
+
50
+ def test_portuguese_counts_zero_as_one():
51
+ assert get_plural_category("pt", 0) == "one"
52
+ assert get_plural_category("pt", 1) == "one"
53
+ assert get_plural_category("pt", 2) == "other"
54
+
55
+
56
+ def test_region_falls_back_to_language():
57
+ # pt_PT has its own rules; en_IN has none and falls back to en.
58
+ assert get_plural_category("pt_PT", 1) == "one"
59
+ assert get_plural_category("en_IN", 1) == "one"
60
+ assert get_plural_category("en_IN", 2) == "other"
61
+
62
+
63
+ def test_unknown_language_is_other():
64
+ assert get_plural_category("zz", 1) == "other"
65
+
66
+
67
+ def test_fractions():
68
+ # Visible fraction digits put Slovak in "many" and English in "other".
69
+ assert get_plural_category("sk", Decimal("1.5")) == "many"
70
+ assert get_plural_category("en", Decimal("1.0")) == "other"
71
+ assert get_plural_category("en", 1) == "one"
72
+
73
+
74
+ def test_ordinal_rules_are_separate():
75
+ # English ordinals: 1st, 2nd, 3rd, 4th -- and 11th/12th/13th.
76
+ assert get_plural_category("en", 1, PluralType.ORDINAL) == "one"
77
+ assert get_plural_category("en", 2, PluralType.ORDINAL) == "two"
78
+ assert get_plural_category("en", 3, PluralType.ORDINAL) == "few"
79
+ assert get_plural_category("en", 4, PluralType.ORDINAL) == "other"
80
+ assert get_plural_category("en", 11, PluralType.ORDINAL) == "other"
81
+ assert get_plural_category("en", 12, PluralType.ORDINAL) == "other"
82
+ assert get_plural_category("en", 21, PluralType.ORDINAL) == "one"
83
+
84
+ # Cardinal English has no "two" category at all.
85
+ assert get_plural_category("en", 2, PluralType.CARDINAL) == "other"
@@ -0,0 +1,17 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_romanian():
5
+ engine = RbnfEngine.for_language("ro")
6
+ assert engine.format_number(-100).text == "minus o sută"
7
+
8
+
9
+ def test_romanian_millions_use_the_article():
10
+ engine = RbnfEngine.for_language("ro")
11
+
12
+ # "un milion", not the standalone numeral "unu".
13
+ assert engine.format_number(1000000).text == "un milion"
14
+ assert engine.format_number(1000000000).text == "un miliard"
15
+
16
+ assert engine.format_number(2000000).text == "două milioane"
17
+ assert engine.format_number(5000000).text == "cinci milioane"
@@ -0,0 +1,29 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_russian_thousands_agreement():
5
+ engine = RbnfEngine.for_language("ru")
6
+
7
+ assert engine.format_number(1000).text == "одна тысяча"
8
+ assert engine.format_number(2000).text == "две тысячи"
9
+ assert engine.format_number(5000).text == "пять тысяч"
10
+
11
+ # The teens take the "many" form even though they end in 1-4.
12
+ assert engine.format_number(11000).text == "одиннадцать тысяч"
13
+ assert engine.format_number(12000).text == "двенадцать тысяч"
14
+ assert engine.format_number(13000).text == "тринадцать тысяч"
15
+ assert engine.format_number(111000).text == "сто одиннадцать тысяч"
16
+ assert engine.format_number(112000).text == "сто двенадцать тысяч"
17
+
18
+ # Past the teens the final digit decides again.
19
+ assert engine.format_number(21000).text == "двадцать одна тысяча"
20
+ assert engine.format_number(22000).text == "двадцать две тысячи"
21
+ assert engine.format_number(25000).text == "двадцать пять тысяч"
22
+
23
+
24
+ def test_russian_millions_agreement():
25
+ engine = RbnfEngine.for_language("ru")
26
+
27
+ assert engine.format_number(1000000).text == "один миллион"
28
+ assert engine.format_number(2000000).text == "два миллиона"
29
+ assert engine.format_number(5000000).text == "пять миллионов"
@@ -0,0 +1,41 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_slovak():
5
+ engine = RbnfEngine.for_language("sk")
6
+
7
+ assert engine.format_number(7).text == "sedem"
8
+ assert engine.format_number(15).text == "pätnásť"
9
+ assert engine.format_number(42).text == "štyridsaťdva"
10
+
11
+ # A multiplier of one is not spoken: "sto", never "jednasto".
12
+ assert engine.format_number(100).text == "sto"
13
+ assert engine.format_number(101).text == "sto jeden"
14
+ assert engine.format_number(150).text == "sto päťdesiat"
15
+ assert engine.format_number(199).text == "sto deväťdesiatdeväť"
16
+
17
+ # From two hundred up, the multiplier joins the word.
18
+ assert engine.format_number(200).text == "dvesto"
19
+ assert engine.format_number(300).text == "tristo"
20
+ assert engine.format_number(500).text == "päťsto"
21
+ assert engine.format_number(999).text == "deväťsto deväťdesiatdeväť"
22
+
23
+ # Likewise "tisíc", never "jedna tisíc".
24
+ assert engine.format_number(1000).text == "tisíc"
25
+ assert engine.format_number(1100).text == "tisíc sto"
26
+ assert engine.format_number(1234).text == "tisíc dvesto tridsaťštyri"
27
+
28
+ # Slovak agreement on "tisíc": 2-4 take the plural "tisíce", 5 and above
29
+ # take the counted form "tisíc". The category follows the whole multiplier,
30
+ # so 12 and 22 take "tisíc" even though they end in 2.
31
+ assert engine.format_number(2000).text == "dve tisíce"
32
+ assert engine.format_number(3000).text == "tri tisíce"
33
+ assert engine.format_number(5000).text == "päť tisíc"
34
+ assert engine.format_number(12000).text == "dvanásť tisíc"
35
+ assert engine.format_number(22000).text == "dvadsaťdve tisíc"
36
+
37
+ assert engine.format_number(100000).text == "sto tisíc"
38
+ assert (
39
+ engine.format_number(683146).text
40
+ == "šesťsto osemdesiattri tisíc sto štyridsaťšesť"
41
+ )
@@ -0,0 +1,31 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_serbian_cyrillic():
5
+ engine = RbnfEngine.for_language("sr")
6
+
7
+ # A multiplier of one is not spoken.
8
+ assert engine.format_number(1000).text == "хиљаду"
9
+ assert engine.format_number(1100).text == "хиљаду сто"
10
+ assert engine.format_number(1000000).text == "милион"
11
+ assert engine.format_number(1000000000).text == "милијарду"
12
+
13
+ # The counted noun agrees with the multiplier.
14
+ assert engine.format_number(2000).text == "две хиљаде"
15
+ assert engine.format_number(5000).text == "пет хиљада"
16
+ assert engine.format_number(2000000).text == "два милиона"
17
+ assert engine.format_number(5000000).text == "пет милиона"
18
+ assert engine.format_number(2000000000).text == "две милијарде"
19
+ assert engine.format_number(5000000000).text == "пет милијарди"
20
+
21
+
22
+ def test_serbian_latin():
23
+ engine = RbnfEngine.for_language("sr_Latn")
24
+
25
+ assert engine.format_number(1000).text == "hiljadu"
26
+ assert engine.format_number(1000000).text == "milion"
27
+ assert engine.format_number(1000000000).text == "milijardu"
28
+
29
+ assert engine.format_number(2000).text == "dve hiljade"
30
+ assert engine.format_number(2000000).text == "dva miliona"
31
+ assert engine.format_number(5000000000).text == "pet milijardi"
@@ -0,0 +1,36 @@
1
+ """Tests for Zulu."""
2
+
3
+ from unicode_rbnf import RbnfEngine
4
+
5
+
6
+ def test_zulu():
7
+ engine = RbnfEngine.for_language("zu")
8
+
9
+ assert engine.format_number(3).text == "kuthathu"
10
+ assert engine.format_number(15).text == "ishumi nanhlanu"
11
+ assert engine.format_number(21).text == "amashumi amabili nanye"
12
+ assert engine.format_number(47).text == "amashumi amane nesikhombisa"
13
+ assert engine.format_number(123).text == "ikhulu namashumi amabili nantathu"
14
+ assert (
15
+ engine.format_number(999).text
16
+ == "amakhulu ayisishiyagalolunye namashumi ayisishiyagalolunye nesishiyagalolunye"
17
+ )
18
+ assert engine.format_number(4000).text == "izinkulungwane ezine"
19
+ assert (
20
+ engine.format_number(8192).text
21
+ == "izinkulungwane eziyisishiyagalombili nekhulu namashumi ayisishiyagalolunye nambili"
22
+ )
23
+
24
+ assert (
25
+ engine.format_number(15123).text
26
+ == "izinkulungwane eziyishumi nanhlanu nekhulu namashumi amabili nantathu"
27
+ )
28
+
29
+ # # 3.5 million
30
+ # assert (
31
+ # engine.format_number(3500000).text
32
+ # == "izigidi ezintathu namakhulu ayishihlanu ezinkulungwane"
33
+ # )
34
+
35
+ # # 12 million
36
+ # assert engine.format_number(12000000).text == "izigidi eziyishumi ezimbili"
@@ -13,16 +13,16 @@ def main() -> None:
13
13
  )
14
14
  parser.add_argument(
15
15
  "--purpose",
16
- choices=[v.value for v in FormatPurpose],
17
- default=FormatPurpose.CARDINAL,
18
- help="Format purpose",
16
+ choices=[v.name for v in FormatPurpose],
17
+ default=FormatPurpose.CARDINAL.name,
18
+ help="Format purpose (default: CARDINAL)",
19
19
  )
20
20
  parser.add_argument("number", nargs="+", help="Number(s) to turn into words")
21
21
  args = parser.parse_args()
22
22
 
23
23
  engine = RbnfEngine.for_language(args.language)
24
24
  for number_str in args.number:
25
- result = engine.format_number(number_str, purpose=FormatPurpose(args.purpose))
25
+ result = engine.format_number(number_str, purpose=FormatPurpose[args.purpose])
26
26
  for ruleset, words in result.text_by_ruleset.items():
27
27
  print(number_str, ruleset, words, sep="|")
28
28