unicode-rbnf 1.2.0__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 (110) hide show
  1. unicode_rbnf-1.2.0/LICENSE.md +21 -0
  2. unicode_rbnf-1.2.0/MANIFEST.in +2 -0
  3. unicode_rbnf-1.2.0/PKG-INFO +69 -0
  4. unicode_rbnf-1.2.0/README.md +48 -0
  5. unicode_rbnf-1.2.0/setup.cfg +21 -0
  6. unicode_rbnf-1.2.0/setup.py +46 -0
  7. unicode_rbnf-1.2.0/tests/test_de.py +9 -0
  8. unicode_rbnf-1.2.0/tests/test_en.py +52 -0
  9. unicode_rbnf-1.2.0/tests/test_engine.py +76 -0
  10. unicode_rbnf-1.2.0/tests/test_es.py +8 -0
  11. unicode_rbnf-1.2.0/tests/test_fr.py +6 -0
  12. unicode_rbnf-1.2.0/unicode_rbnf/VERSION +1 -0
  13. unicode_rbnf-1.2.0/unicode_rbnf/__init__.py +13 -0
  14. unicode_rbnf-1.2.0/unicode_rbnf/__main__.py +29 -0
  15. unicode_rbnf-1.2.0/unicode_rbnf/engine.py +532 -0
  16. unicode_rbnf-1.2.0/unicode_rbnf/py.typed +0 -0
  17. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/af.xml +109 -0
  18. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ak.xml +74 -0
  19. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/am.xml +64 -0
  20. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ar.xml +303 -0
  21. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/az.xml +113 -0
  22. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/be.xml +412 -0
  23. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/bg.xml +511 -0
  24. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/bs.xml +133 -0
  25. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ca.xml +282 -0
  26. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ccp.xml +67 -0
  27. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/chr.xml +69 -0
  28. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/cs.xml +142 -0
  29. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/cy.xml +120 -0
  30. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/da.xml +194 -0
  31. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/de.xml +237 -0
  32. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/de_CH.xml +230 -0
  33. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ee.xml +109 -0
  34. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/el.xml +320 -0
  35. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/en.xml +206 -0
  36. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/en_001.xml +14 -0
  37. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/en_IN.xml +200 -0
  38. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/eo.xml +56 -0
  39. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/es.xml +323 -0
  40. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/es_419.xml +50 -0
  41. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/et.xml +55 -0
  42. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fa.xml +70 -0
  43. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fa_AF.xml +67 -0
  44. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ff.xml +102 -0
  45. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fi.xml +1408 -0
  46. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fil.xml +74 -0
  47. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fo.xml +128 -0
  48. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fr.xml +239 -0
  49. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fr_BE.xml +211 -0
  50. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/fr_CH.xml +212 -0
  51. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ga.xml +241 -0
  52. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/he.xml +344 -0
  53. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/hi.xml +197 -0
  54. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/hr.xml +223 -0
  55. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/hu.xml +147 -0
  56. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/hy.xml +54 -0
  57. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/id.xml +62 -0
  58. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/is.xml +128 -0
  59. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/it.xml +629 -0
  60. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ja.xml +98 -0
  61. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ka.xml +80 -0
  62. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/kk.xml +126 -0
  63. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/kl.xml +86 -0
  64. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/km.xml +65 -0
  65. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ko.xml +276 -0
  66. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ky.xml +194 -0
  67. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/lb.xml +227 -0
  68. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/lo.xml +61 -0
  69. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/lrc.xml +70 -0
  70. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/lt.xml +124 -0
  71. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/lv.xml +98 -0
  72. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/mk.xml +109 -0
  73. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ms.xml +67 -0
  74. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/mt.xml +264 -0
  75. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/my.xml +62 -0
  76. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/nb.xml +13 -0
  77. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ne.xml +188 -0
  78. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/nl.xml +126 -0
  79. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/nn.xml +83 -0
  80. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/no.xml +347 -0
  81. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/pl.xml +438 -0
  82. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/pt.xml +212 -0
  83. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/pt_PT.xml +200 -0
  84. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/qu.xml +59 -0
  85. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ro.xml +105 -0
  86. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/root.xml +724 -0
  87. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ru.xml +1565 -0
  88. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/se.xml +51 -0
  89. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/sk.xml +97 -0
  90. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/sl.xml +145 -0
  91. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/sq.xml +79 -0
  92. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/sr.xml +165 -0
  93. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/sr_Latn.xml +166 -0
  94. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/su.xml +56 -0
  95. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/sv.xml +258 -0
  96. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/sw.xml +64 -0
  97. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/ta.xml +101 -0
  98. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/th.xml +61 -0
  99. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/tr.xml +108 -0
  100. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/uk.xml +139 -0
  101. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/vec.xml +423 -0
  102. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/vi.xml +80 -0
  103. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/yue.xml +191 -0
  104. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/yue_Hans.xml +192 -0
  105. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/zh.xml +286 -0
  106. unicode_rbnf-1.2.0/unicode_rbnf/rbnf/zh_Hant.xml +252 -0
  107. unicode_rbnf-1.2.0/unicode_rbnf.egg-info/PKG-INFO +69 -0
  108. unicode_rbnf-1.2.0/unicode_rbnf.egg-info/SOURCES.txt +109 -0
  109. unicode_rbnf-1.2.0/unicode_rbnf.egg-info/dependency_links.txt +1 -0
  110. unicode_rbnf-1.2.0/unicode_rbnf.egg-info/top_level.txt +1 -0
@@ -0,0 +1,21 @@
1
+ MIT License
2
+
3
+ Copyright (c) 2023 Michael Hansen
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in all
13
+ copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21
+ SOFTWARE.
@@ -0,0 +1,2 @@
1
+ include LICENSE.md
2
+ include unicode_rbnf/rbnf/*.xml
@@ -0,0 +1,69 @@
1
+ Metadata-Version: 2.1
2
+ Name: unicode_rbnf
3
+ Version: 1.2.0
4
+ Summary: Rule-based number formatting using Unicode CLDR data
5
+ Home-page: http://github.com/rhasspy/unicode-rbnf
6
+ Author: Michael Hansen
7
+ Author-email: mike@rhasspy.org
8
+ License: MIT
9
+ Keywords: rbnf unicode number format
10
+ Classifier: Development Status :: 3 - Alpha
11
+ Classifier: Intended Audience :: Developers
12
+ Classifier: Topic :: Text Processing :: Linguistic
13
+ Classifier: License :: OSI Approved :: MIT License
14
+ Classifier: Programming Language :: Python :: 3.8
15
+ Classifier: Programming Language :: Python :: 3.9
16
+ Classifier: Programming Language :: Python :: 3.10
17
+ Classifier: Programming Language :: Python :: 3.11
18
+ Classifier: Programming Language :: Python :: 3.12
19
+ Description-Content-Type: text/markdown
20
+ License-File: LICENSE.md
21
+
22
+ # Unicode RBNF
23
+
24
+ A pure Python implementation of [rule based number formatting](https://icu-project.org/docs/papers/a_rule_based_approach_to_number_spellout/) (RBNF) using the [Unicode Common Locale Data Repository](https://cldr.unicode.org) (CLDR).
25
+
26
+ This lets you spell out numbers for a large number of locales:
27
+
28
+ ``` python
29
+ from unicode_rbnf import RbnfEngine
30
+
31
+ engine = RbnfEngine.for_language("en")
32
+ assert engine.format_number(1234) == "one thousand two hundred thirty-four"
33
+ ```
34
+
35
+ Depending on the locale, different rulesets are supported as well:
36
+
37
+ ``` python
38
+ from unicode_rbnf import RbnfEngine, RulesetName
39
+
40
+ engine = RbnfEngine.for_language("en")
41
+ assert engine.format_number(1999, RulesetName.YEAR) == "nineteen ninety-nine"
42
+ assert engine.format_number(11, RulesetName.ORDINAL) == "eleventh"
43
+ ```
44
+
45
+ ## Supported locales
46
+
47
+ See: https://github.com/unicode-org/cldr/tree/release-44/common/rbnf
48
+
49
+ ## Engine implementation
50
+
51
+ Not [all features](https://unicode-org.github.io/icu-docs/apidoc/released/icu4c/classRuleBasedNumberFormat.html) of the RBNF engine are implemented. The following features are available:
52
+
53
+ * Literal text (`hundred`)
54
+ * Quotient substitution (`<<` or `←←`)
55
+ * Reminder substitution (`>>` or `→→`)
56
+ * Optional substitution (`[...]`)
57
+ * Rule substituton (`←%ruleset_name←`)
58
+ * Rule replacement (`=%ruleset_name=`)
59
+ * Special rules:
60
+ * Negative numbers (`-x`)
61
+ * Improper fractions (`x.x`)
62
+ * Not a number (`NaN`)
63
+ * Infinity (`Inf`)
64
+
65
+ Some features that will need to be added eventually:
66
+
67
+ * Proper fraction rules (`0.x`)
68
+ * Preceding reminder substitution (`>>>` or `→→→`)
69
+ * Number format strings (`==`)
@@ -0,0 +1,48 @@
1
+ # Unicode RBNF
2
+
3
+ A pure Python implementation of [rule based number formatting](https://icu-project.org/docs/papers/a_rule_based_approach_to_number_spellout/) (RBNF) using the [Unicode Common Locale Data Repository](https://cldr.unicode.org) (CLDR).
4
+
5
+ This lets you spell out numbers for a large number of locales:
6
+
7
+ ``` python
8
+ from unicode_rbnf import RbnfEngine
9
+
10
+ engine = RbnfEngine.for_language("en")
11
+ assert engine.format_number(1234) == "one thousand two hundred thirty-four"
12
+ ```
13
+
14
+ Depending on the locale, different rulesets are supported as well:
15
+
16
+ ``` python
17
+ from unicode_rbnf import RbnfEngine, RulesetName
18
+
19
+ engine = RbnfEngine.for_language("en")
20
+ assert engine.format_number(1999, RulesetName.YEAR) == "nineteen ninety-nine"
21
+ assert engine.format_number(11, RulesetName.ORDINAL) == "eleventh"
22
+ ```
23
+
24
+ ## Supported locales
25
+
26
+ See: https://github.com/unicode-org/cldr/tree/release-44/common/rbnf
27
+
28
+ ## Engine implementation
29
+
30
+ Not [all features](https://unicode-org.github.io/icu-docs/apidoc/released/icu4c/classRuleBasedNumberFormat.html) of the RBNF engine are implemented. The following features are available:
31
+
32
+ * Literal text (`hundred`)
33
+ * Quotient substitution (`<<` or `←←`)
34
+ * Reminder substitution (`>>` or `→→`)
35
+ * Optional substitution (`[...]`)
36
+ * Rule substituton (`←%ruleset_name←`)
37
+ * Rule replacement (`=%ruleset_name=`)
38
+ * Special rules:
39
+ * Negative numbers (`-x`)
40
+ * Improper fractions (`x.x`)
41
+ * Not a number (`NaN`)
42
+ * Infinity (`Inf`)
43
+
44
+ Some features that will need to be added eventually:
45
+
46
+ * Proper fraction rules (`0.x`)
47
+ * Preceding reminder substitution (`>>>` or `→→→`)
48
+ * Number format strings (`==`)
@@ -0,0 +1,21 @@
1
+ [flake8]
2
+ max-line-length = 88
3
+ ignore =
4
+ E501,
5
+ W503,
6
+ E203,
7
+ D202,
8
+ W504
9
+
10
+ [isort]
11
+ multi_line_output = 3
12
+ include_trailing_comma = True
13
+ force_grid_wrap = 0
14
+ use_parentheses = True
15
+ line_length = 88
16
+ indent = " "
17
+
18
+ [egg_info]
19
+ tag_build =
20
+ tag_date = 0
21
+
@@ -0,0 +1,46 @@
1
+ #!/usr/bin/env python3
2
+ from pathlib import Path
3
+
4
+ import setuptools
5
+ from setuptools import setup
6
+
7
+ module_name = "unicode_rbnf"
8
+ this_dir = Path(__file__).parent
9
+ module_dir = this_dir / module_name
10
+ data_files = list((module_dir / "rbnf").glob("*.xml"))
11
+
12
+ version_path = module_dir / "VERSION"
13
+ data_files.append(version_path)
14
+ version = version_path.read_text(encoding="utf-8").strip()
15
+
16
+ long_description = (this_dir / "README.md").read_text()
17
+
18
+ # -----------------------------------------------------------------------------
19
+
20
+ setup(
21
+ name=module_name,
22
+ version=version,
23
+ description="Rule-based number formatting using Unicode CLDR data",
24
+ long_description=long_description,
25
+ long_description_content_type="text/markdown",
26
+ url="http://github.com/rhasspy/unicode-rbnf",
27
+ author="Michael Hansen",
28
+ author_email="mike@rhasspy.org",
29
+ license="MIT",
30
+ packages=setuptools.find_packages(),
31
+ package_data={
32
+ module_name: [str(p.relative_to(module_dir)) for p in data_files] + ["py.typed"]
33
+ },
34
+ classifiers=[
35
+ "Development Status :: 3 - Alpha",
36
+ "Intended Audience :: Developers",
37
+ "Topic :: Text Processing :: Linguistic",
38
+ "License :: OSI Approved :: MIT License",
39
+ "Programming Language :: Python :: 3.8",
40
+ "Programming Language :: Python :: 3.9",
41
+ "Programming Language :: Python :: 3.10",
42
+ "Programming Language :: Python :: 3.11",
43
+ "Programming Language :: Python :: 3.12",
44
+ ],
45
+ keywords="rbnf unicode number format",
46
+ )
@@ -0,0 +1,9 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_german():
5
+ engine = RbnfEngine.for_language("de")
6
+ assert engine.format_number(13) == "dreizehn"
7
+
8
+ # \xad = soft hyphen
9
+ assert engine.format_number(32) == "zwei\xadund\xaddreißig"
@@ -0,0 +1,52 @@
1
+ from unicode_rbnf import RbnfEngine, RulesetName
2
+
3
+
4
+ def test_english():
5
+ engine = RbnfEngine.for_language("en")
6
+
7
+ assert engine.format_number(7) == "seven"
8
+ assert engine.format_number(15) == "fifteen"
9
+ assert engine.format_number(42) == "forty-two"
10
+ assert engine.format_number(100) == "one hundred"
11
+ assert engine.format_number(143) == "one hundred forty-three"
12
+ assert engine.format_number(1000) == "one thousand"
13
+ assert engine.format_number(1234) == "one thousand two hundred thirty-four"
14
+ assert engine.format_number(3144) == "three thousand one hundred forty-four"
15
+ assert engine.format_number(10000) == "ten thousand"
16
+ assert engine.format_number(83145) == "eighty-three thousand one hundred forty-five"
17
+ assert engine.format_number(100000) == "one hundred thousand"
18
+ assert (
19
+ engine.format_number(683146)
20
+ == "six hundred eighty-three thousand one hundred forty-six"
21
+ )
22
+ assert engine.format_number(1000000) == "one million"
23
+ assert engine.format_number(10000000) == "ten million"
24
+ assert engine.format_number(100000000) == "one hundred million"
25
+ assert engine.format_number(1000000000) == "one billion"
26
+
27
+ # Special rules
28
+ assert engine.format_number(-1) == "minus one"
29
+ assert engine.format_number(float("nan")) == "not a number"
30
+ assert engine.format_number(float("inf")) == "infinite"
31
+
32
+ # Fractions
33
+ assert (
34
+ engine.format_number(3.14, ruleset_name=RulesetName.CARDINAL)
35
+ == "three point fourteen"
36
+ )
37
+ assert (
38
+ engine.format_number("5.3", ruleset_name=RulesetName.CARDINAL)
39
+ == "five point three"
40
+ )
41
+
42
+ # Ordinals
43
+ assert engine.format_number(20, ruleset_name=RulesetName.ORDINAL) == "twentieth"
44
+ assert engine.format_number(30, ruleset_name=RulesetName.ORDINAL) == "thirtieth"
45
+ assert engine.format_number(99, ruleset_name=RulesetName.ORDINAL) == "ninety-ninth"
46
+ assert engine.format_number(11, ruleset_name=RulesetName.ORDINAL) == "eleventh"
47
+
48
+ # Years
49
+ assert (
50
+ engine.format_number(1999, ruleset_name=RulesetName.YEAR)
51
+ == "nineteen ninety-nine"
52
+ )
@@ -0,0 +1,76 @@
1
+ from unicode_rbnf.engine import (
2
+ RbnfRule,
3
+ TextRulePart,
4
+ SubRulePart,
5
+ SubType,
6
+ RbnfEngine,
7
+ RulesetName,
8
+ DEFAULT_LANGUAGE,
9
+ )
10
+
11
+
12
+ def test_parse_text():
13
+ assert RbnfRule.parse(1, "one;") == RbnfRule(1, parts=[TextRulePart("one")])
14
+
15
+
16
+ def test_parse_sub():
17
+ assert RbnfRule.parse(100, "←← hundred[ →→];") == RbnfRule(
18
+ 100,
19
+ parts=[
20
+ SubRulePart(SubType.QUOTIENT),
21
+ TextRulePart(" hundred"),
22
+ SubRulePart(SubType.REMAINDER, is_optional=True, text_before=" "),
23
+ ],
24
+ )
25
+
26
+
27
+ def test_parse_ruleset_name():
28
+ assert RbnfRule.parse(
29
+ 100, "←%spellout-cardinal-masculine←­hundert[­→→];"
30
+ ) == RbnfRule(
31
+ 100,
32
+ parts=[
33
+ SubRulePart(SubType.QUOTIENT, ruleset_name="spellout-cardinal-masculine"),
34
+ TextRulePart("­hundert"),
35
+ SubRulePart(SubType.REMAINDER, is_optional=True, text_before="­"),
36
+ ],
37
+ )
38
+
39
+
40
+ def test_find_rule():
41
+ engine = RbnfEngine()
42
+ engine.add_rule(2, "two;")
43
+ engine.add_rule(20, "twenty[-→→];")
44
+ engine.add_rule(100, "←← hundred[ →→];")
45
+
46
+ ruleset = engine.rulesets[DEFAULT_LANGUAGE][RulesetName.CARDINAL]
47
+
48
+ rule_2 = ruleset.find_rule(2)
49
+ assert rule_2 is not None
50
+ assert rule_2.value == 2
51
+
52
+ rule_20 = ruleset.find_rule(25)
53
+ assert rule_20 is not None
54
+ assert rule_20.value == 20
55
+
56
+ rule_100 = ruleset.find_rule(222)
57
+ assert rule_100 is not None
58
+ assert rule_100.value == 100
59
+
60
+
61
+ def test_format_number():
62
+ engine = RbnfEngine()
63
+ engine.add_rule(2, "two;")
64
+ engine.add_rule(20, "twenty[-→→];")
65
+ engine.add_rule(100, "←← hundred[ →→];")
66
+
67
+ assert engine.format_number(222) == "two hundred twenty-two"
68
+
69
+
70
+ def test_zero_rules():
71
+ engine = RbnfEngine()
72
+ engine.add_rule(0, "abc=%ruleset_2=def;", ruleset_name="ruleset_1")
73
+ engine.add_rule(0, " efg=%ruleset_3= hij;", ruleset_name="ruleset_2")
74
+ engine.add_rule(1, "one;", ruleset_name="ruleset_3")
75
+
76
+ assert engine.format_number(1, ruleset_name="ruleset_1") == "abc efgone hijdef"
@@ -0,0 +1,8 @@
1
+ from unicode_rbnf import RbnfEngine
2
+
3
+
4
+ def test_german():
5
+ engine = RbnfEngine.for_language("es")
6
+ assert engine.format_number(5) == "cinco"
7
+ assert engine.format_number(2) == "dos"
8
+ assert engine.format_number(5.2) == "cinco coma dos"
@@ -0,0 +1,6 @@
1
+ from unicode_rbnf import RbnfEngine, RulesetName
2
+
3
+
4
+ def test_french():
5
+ engine = RbnfEngine.for_language("fr")
6
+ assert engine.format_number(88) == "quatre-vingt-huit"
@@ -0,0 +1 @@
1
+ 1.2.0
@@ -0,0 +1,13 @@
1
+ from pathlib import Path
2
+
3
+ from .engine import RbnfEngine, RulesetName
4
+
5
+ _DIR = Path(__file__).parent
6
+
7
+ __version__ = (_DIR / "VERSION").read_text(encoding="utf-8").strip()
8
+
9
+ __all__ = [
10
+ "__version__",
11
+ "RbnfEngine",
12
+ "RulesetName",
13
+ ]
@@ -0,0 +1,29 @@
1
+ import argparse
2
+
3
+ from unicode_rbnf import RbnfEngine, RulesetName
4
+
5
+
6
+ def main() -> None:
7
+ parser = argparse.ArgumentParser()
8
+ parser.add_argument(
9
+ "--language",
10
+ choices=RbnfEngine.get_supported_languages(),
11
+ required=True,
12
+ help="Language code",
13
+ )
14
+ parser.add_argument(
15
+ "--rule",
16
+ choices=[v.value for v in RulesetName],
17
+ help="Ruleset name",
18
+ )
19
+ parser.add_argument("number", nargs="+", help="Number(s) to turn into words")
20
+ args = parser.parse_args()
21
+
22
+ engine = RbnfEngine.for_language(args.language)
23
+ for number_str in args.number:
24
+ words = engine.format_number(number_str, ruleset_name=args.rule)
25
+ print(words)
26
+
27
+
28
+ if __name__ == "__main__":
29
+ main()