unicode-rbnf 2.0.0__tar.gz → 2.2.0__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.
- {unicode_rbnf-2.0.0/unicode_rbnf.egg-info → unicode_rbnf-2.2.0}/PKG-INFO +10 -6
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/README.md +2 -0
- unicode_rbnf-2.2.0/pyproject.toml +41 -0
- unicode_rbnf-2.2.0/tests/test_de.py +56 -0
- unicode_rbnf-2.2.0/tests/test_decimal_format.py +9 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/tests/test_es.py +1 -0
- unicode_rbnf-2.2.0/tests/test_load_all.py +9 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/__init__.py +4 -3
- unicode_rbnf-2.2.0/unicode_rbnf/decimal_format.py +53 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/engine.py +26 -5
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0/unicode_rbnf.egg-info}/PKG-INFO +10 -6
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf.egg-info/SOURCES.txt +5 -7
- unicode_rbnf-2.2.0/unicode_rbnf.egg-info/zip-safe +1 -0
- unicode_rbnf-2.0.0/MANIFEST.in +0 -2
- unicode_rbnf-2.0.0/setup.py +0 -46
- unicode_rbnf-2.0.0/tests/test_de.py +0 -18
- unicode_rbnf-2.0.0/unicode_rbnf/VERSION +0 -1
- unicode_rbnf-2.0.0/unicode_rbnf/rbnf/en_001.xml +0 -14
- unicode_rbnf-2.0.0/unicode_rbnf/rbnf/es_419.xml +0 -50
- unicode_rbnf-2.0.0/unicode_rbnf/rbnf/nb.xml +0 -13
- unicode_rbnf-2.0.0/unicode_rbnf/rbnf/root.xml +0 -724
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/LICENSE.md +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/setup.cfg +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/tests/test_en.py +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/tests/test_engine.py +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/tests/test_fi.py +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/tests/test_fr.py +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/tests/test_ro.py +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/__main__.py +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/py.typed +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/af.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ak.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/am.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ar.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/az.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/be.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/bg.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/bs.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ca.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ccp.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/chr.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/cs.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/cy.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/da.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/de.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/de_CH.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ee.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/el.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/en.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/en_IN.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/eo.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/es.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/et.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fa.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fa_AF.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ff.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fi.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fil.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fo.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fr.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fr_BE.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/fr_CH.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ga.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/he.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/hi.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/hr.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/hu.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/hy.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/id.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/is.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/it.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ja.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ka.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/kk.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/kl.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/km.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ko.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ky.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/lb.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/lo.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/lrc.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/lt.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/lv.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/mk.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ms.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/mt.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/my.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ne.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/nl.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/nn.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/no.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/pl.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/pt.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/pt_PT.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/qu.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ro.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ru.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/se.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/sk.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/sl.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/sq.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/sr.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/sr_Latn.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/su.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/sv.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/sw.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/ta.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/th.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/tr.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/uk.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/vec.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/vi.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/yue.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/yue_Hans.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/zh.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf/rbnf/zh_Hant.xml +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf.egg-info/dependency_links.txt +0 -0
- {unicode_rbnf-2.0.0 → unicode_rbnf-2.2.0}/unicode_rbnf.egg-info/top_level.txt +0 -0
|
@@ -1,12 +1,12 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
|
-
Name:
|
|
3
|
-
Version: 2.
|
|
2
|
+
Name: unicode-rbnf
|
|
3
|
+
Version: 2.2.0
|
|
4
4
|
Summary: Rule-based number formatting using Unicode CLDR data
|
|
5
|
-
|
|
6
|
-
Author: Michael Hansen
|
|
7
|
-
Author-email: mike@rhasspy.org
|
|
5
|
+
Author-email: Michael Hansen <mike@rhasspy.org>
|
|
8
6
|
License: MIT
|
|
9
|
-
|
|
7
|
+
Project-URL: Source Code, https://github.com/rhasspy/unicode-rbnf
|
|
8
|
+
Keywords: rbnf,unicode,number,format
|
|
9
|
+
Platform: any
|
|
10
10
|
Classifier: Development Status :: 3 - Alpha
|
|
11
11
|
Classifier: Intended Audience :: Developers
|
|
12
12
|
Classifier: Topic :: Text Processing :: Linguistic
|
|
@@ -16,6 +16,8 @@ Classifier: Programming Language :: Python :: 3.9
|
|
|
16
16
|
Classifier: Programming Language :: Python :: 3.10
|
|
17
17
|
Classifier: Programming Language :: Python :: 3.11
|
|
18
18
|
Classifier: Programming Language :: Python :: 3.12
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
20
|
+
Requires-Python: >=3.8.0
|
|
19
21
|
Description-Content-Type: text/markdown
|
|
20
22
|
License-File: LICENSE.md
|
|
21
23
|
|
|
@@ -97,3 +99,5 @@ Some features that will need to be added eventually:
|
|
|
97
99
|
* Proper fraction rules (`0.x`)
|
|
98
100
|
* Preceding reminder substitution (`>>>` or `→→→`)
|
|
99
101
|
* Number format strings (`==`)
|
|
102
|
+
* Decimal format patterns (`#,##0.00`)
|
|
103
|
+
* Plural replacements (`$(ordinal,one{st}...)`)
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["setuptools>=62.3"]
|
|
3
|
+
build-backend = "setuptools.build_meta"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "unicode-rbnf"
|
|
7
|
+
version = "2.2.0"
|
|
8
|
+
license = {text = "MIT"}
|
|
9
|
+
description = "Rule-based number formatting using Unicode CLDR data"
|
|
10
|
+
readme = "README.md"
|
|
11
|
+
authors = [
|
|
12
|
+
{name = "Michael Hansen", email = "mike@rhasspy.org"}
|
|
13
|
+
]
|
|
14
|
+
keywords = ["rbnf", "unicode", "number", "format"]
|
|
15
|
+
classifiers = [
|
|
16
|
+
"Development Status :: 3 - Alpha",
|
|
17
|
+
"Intended Audience :: Developers",
|
|
18
|
+
"Topic :: Text Processing :: Linguistic",
|
|
19
|
+
"License :: OSI Approved :: MIT License",
|
|
20
|
+
"Programming Language :: Python :: 3.8",
|
|
21
|
+
"Programming Language :: Python :: 3.9",
|
|
22
|
+
"Programming Language :: Python :: 3.10",
|
|
23
|
+
"Programming Language :: Python :: 3.11",
|
|
24
|
+
"Programming Language :: Python :: 3.12",
|
|
25
|
+
"Programming Language :: Python :: 3.13",
|
|
26
|
+
]
|
|
27
|
+
requires-python = ">=3.8.0"
|
|
28
|
+
|
|
29
|
+
[project.urls]
|
|
30
|
+
"Source Code" = "https://github.com/rhasspy/unicode-rbnf"
|
|
31
|
+
|
|
32
|
+
[tool.setuptools]
|
|
33
|
+
platforms = ["any"]
|
|
34
|
+
zip-safe = true
|
|
35
|
+
include-package-data = true
|
|
36
|
+
|
|
37
|
+
[tool.setuptools.packages.find]
|
|
38
|
+
include = ["unicode_rbnf"]
|
|
39
|
+
|
|
40
|
+
[tool.setuptools.package-data]
|
|
41
|
+
unicode_rbnf = ["rbnf/*.xml"]
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
from unicode_rbnf import RbnfEngine
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
def test_german():
|
|
5
|
+
engine = RbnfEngine.for_language("de")
|
|
6
|
+
assert engine.format_number(1).text == "eins"
|
|
7
|
+
assert engine.format_number(2).text == "zwei"
|
|
8
|
+
assert engine.format_number(3).text == "drei"
|
|
9
|
+
assert engine.format_number(4).text == "vier"
|
|
10
|
+
assert engine.format_number(5).text == "fünf"
|
|
11
|
+
assert engine.format_number(6).text == "sechs"
|
|
12
|
+
assert engine.format_number(7).text == "sieben"
|
|
13
|
+
assert engine.format_number(8).text == "acht"
|
|
14
|
+
assert engine.format_number(9).text == "neun"
|
|
15
|
+
assert engine.format_number(10).text == "zehn"
|
|
16
|
+
assert engine.format_number(11).text == "elf"
|
|
17
|
+
assert engine.format_number(12).text == "zwölf"
|
|
18
|
+
assert engine.format_number(13).text == "dreizehn"
|
|
19
|
+
assert engine.format_number(14).text == "vierzehn"
|
|
20
|
+
assert engine.format_number(15).text == "fünfzehn"
|
|
21
|
+
assert engine.format_number(16).text == "sechzehn"
|
|
22
|
+
assert engine.format_number(17).text == "siebzehn"
|
|
23
|
+
assert engine.format_number(18).text == "achtzehn"
|
|
24
|
+
assert engine.format_number(19).text == "neunzehn"
|
|
25
|
+
assert engine.format_number(20).text == "zwanzig"
|
|
26
|
+
assert engine.format_number(21).text == "einundzwanzig"
|
|
27
|
+
assert engine.format_number(22).text == "zweiundzwanzig"
|
|
28
|
+
assert engine.format_number(23).text == "dreiundzwanzig"
|
|
29
|
+
assert engine.format_number(24).text == "vierundzwanzig"
|
|
30
|
+
assert engine.format_number(25).text == "fünfundzwanzig"
|
|
31
|
+
assert engine.format_number(26).text == "sechsundzwanzig"
|
|
32
|
+
assert engine.format_number(27).text == "siebenundzwanzig"
|
|
33
|
+
assert engine.format_number(28).text == "achtundzwanzig"
|
|
34
|
+
assert engine.format_number(29).text == "neunundzwanzig"
|
|
35
|
+
assert engine.format_number(30).text == "dreißig"
|
|
36
|
+
assert engine.format_number(32).text == "zweiunddreißig"
|
|
37
|
+
assert engine.format_number(100).text == "einhundert"
|
|
38
|
+
assert engine.format_number(101).text == "einhunderteins"
|
|
39
|
+
assert engine.format_number(120).text == "einhundertzwanzig"
|
|
40
|
+
assert engine.format_number(121).text == "einhunderteinundzwanzig"
|
|
41
|
+
assert engine.format_number(200).text == "zweihundert"
|
|
42
|
+
assert engine.format_number(1000).text == "eintausend"
|
|
43
|
+
assert engine.format_number(1001).text == "eintausendeins"
|
|
44
|
+
assert engine.format_number(1100).text == "eintausendeinhundert"
|
|
45
|
+
assert engine.format_number(1234).text == "eintausendzweihundertvierunddreißig"
|
|
46
|
+
|
|
47
|
+
# All genders, cases
|
|
48
|
+
assert set(engine.format_number(1).text_by_ruleset.values()) == {
|
|
49
|
+
"ein",
|
|
50
|
+
"eins",
|
|
51
|
+
"eine",
|
|
52
|
+
"eines",
|
|
53
|
+
"einer",
|
|
54
|
+
"einem",
|
|
55
|
+
"einen",
|
|
56
|
+
}
|
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
from unicode_rbnf.decimal_format import format_decimal
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
def test_format_decimal() -> None:
|
|
5
|
+
assert format_decimal(12345.6789, "#,##0.00") == "12,345.68"
|
|
6
|
+
assert format_decimal(5, "0000.00") == "0005.00"
|
|
7
|
+
assert format_decimal(12345.6, "#,##0.0#") == "12,345.6"
|
|
8
|
+
assert format_decimal(0.1, "#,##0.00") == "0.10"
|
|
9
|
+
assert format_decimal(12345, "#,##0") == "12,345"
|
|
@@ -6,6 +6,7 @@ def test_german():
|
|
|
6
6
|
assert engine.format_number(5).text == "cinco"
|
|
7
7
|
assert engine.format_number(2).text == "dos"
|
|
8
8
|
assert engine.format_number(5.2).text == "cinco coma dos"
|
|
9
|
+
assert engine.format_number(21).text == "veintiuno"
|
|
9
10
|
|
|
10
11
|
# All genders
|
|
11
12
|
assert set(engine.format_number(1).text_by_ruleset.values()) == {
|
|
@@ -1,10 +1,11 @@
|
|
|
1
|
-
|
|
1
|
+
"""Rule-based number formatting using Unicode CLDR data."""
|
|
2
|
+
|
|
3
|
+
import importlib.metadata
|
|
2
4
|
|
|
3
5
|
from .engine import FormatOptions, FormatPurpose, FormatResult, RbnfEngine
|
|
4
6
|
|
|
5
|
-
|
|
7
|
+
__version__ = importlib.metadata.version("unicode_rbnf")
|
|
6
8
|
|
|
7
|
-
__version__ = (_DIR / "VERSION").read_text(encoding="utf-8").strip()
|
|
8
9
|
|
|
9
10
|
__all__ = [
|
|
10
11
|
"__version__",
|
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
"""Handle decimal formatting.
|
|
2
|
+
|
|
3
|
+
See: https://unicode-org.github.io/icu-docs/apidoc/released/icu4c/classicu_1_1DecimalFormat.html
|
|
4
|
+
"""
|
|
5
|
+
|
|
6
|
+
from decimal import Decimal
|
|
7
|
+
from typing import Union
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
def format_decimal(value: Union[int, float, str, Decimal], pattern: str) -> str:
|
|
11
|
+
"""Format a number according to a simplified ICU DecimalFormat pattern."""
|
|
12
|
+
# Split the pattern into integer and fractional parts
|
|
13
|
+
if "." in pattern:
|
|
14
|
+
integer_part, fractional_part = pattern.split(".")
|
|
15
|
+
else:
|
|
16
|
+
integer_part, fractional_part = pattern, ""
|
|
17
|
+
|
|
18
|
+
# Determine grouping (e.g., thousands separator)
|
|
19
|
+
grouping = "," in integer_part
|
|
20
|
+
min_integer_digits = integer_part.replace(",", "").count("0")
|
|
21
|
+
|
|
22
|
+
# Determine the number of decimal places
|
|
23
|
+
min_fraction_digits = fractional_part.count("0")
|
|
24
|
+
max_fraction_digits = len(fractional_part)
|
|
25
|
+
|
|
26
|
+
# Round the number to the maximum fractional digits
|
|
27
|
+
format_str = f"{{:.{max_fraction_digits}f}}"
|
|
28
|
+
rounded_value = format_str.format(value)
|
|
29
|
+
|
|
30
|
+
# Split the rounded value into integer and fractional parts
|
|
31
|
+
if fractional_part:
|
|
32
|
+
integer_value, fractional_value = rounded_value.split(".")
|
|
33
|
+
fractional_value = fractional_value[:max_fraction_digits].rstrip("0")
|
|
34
|
+
else:
|
|
35
|
+
integer_value, fractional_value = rounded_value, ""
|
|
36
|
+
|
|
37
|
+
# Apply integer padding
|
|
38
|
+
if len(integer_value) < min_integer_digits:
|
|
39
|
+
integer_value = integer_value.zfill(min_integer_digits)
|
|
40
|
+
|
|
41
|
+
# Apply grouping
|
|
42
|
+
if grouping:
|
|
43
|
+
# pylint: disable=consider-using-f-string
|
|
44
|
+
integer_value = "{:,}".format(int(integer_value))
|
|
45
|
+
|
|
46
|
+
# Combine integer and fractional parts
|
|
47
|
+
if min_fraction_digits > 0:
|
|
48
|
+
fractional_value = fractional_value.ljust(min_fraction_digits, "0")
|
|
49
|
+
formatted_number = f"{integer_value}.{fractional_value}"
|
|
50
|
+
else:
|
|
51
|
+
formatted_number = integer_value
|
|
52
|
+
|
|
53
|
+
return formatted_number
|
|
@@ -1,4 +1,5 @@
|
|
|
1
1
|
import logging
|
|
2
|
+
import re
|
|
2
3
|
from abc import ABC
|
|
3
4
|
from bisect import bisect_left
|
|
4
5
|
from dataclasses import dataclass, field
|
|
@@ -110,6 +111,9 @@ class SubRulePart(RbnfRulePart):
|
|
|
110
111
|
ruleset_name: Optional[str] = None
|
|
111
112
|
"""Ruleset name to use during substitution (None for current ruleset name)."""
|
|
112
113
|
|
|
114
|
+
format_pattern: Optional[str] = None
|
|
115
|
+
"""DecimalFormat pattern (e.g., #,##0.00)."""
|
|
116
|
+
|
|
113
117
|
|
|
114
118
|
@dataclass
|
|
115
119
|
class ReplaceRulePart(RbnfRulePart):
|
|
@@ -292,6 +296,17 @@ class RbnfRule:
|
|
|
292
296
|
|
|
293
297
|
assert isinstance(part, TextRulePart)
|
|
294
298
|
part.text += c
|
|
299
|
+
elif c in ("#", "0", ",", "."):
|
|
300
|
+
# decimal format pattern (e.g., #,##0.00)
|
|
301
|
+
assert isinstance(part, SubRulePart)
|
|
302
|
+
assert state in (
|
|
303
|
+
ParseState.SUB_REMAINDER,
|
|
304
|
+
ParseState.SUB_QUOTIENT,
|
|
305
|
+
), state
|
|
306
|
+
if part.format_pattern is None:
|
|
307
|
+
part.format_pattern = ""
|
|
308
|
+
|
|
309
|
+
part.format_pattern += c
|
|
295
310
|
else:
|
|
296
311
|
raise ValueError(f"Got {c} in {state}")
|
|
297
312
|
|
|
@@ -459,7 +474,7 @@ class RbnfEngine:
|
|
|
459
474
|
raise ValueError("Missing identity/language element")
|
|
460
475
|
|
|
461
476
|
language = lang_elem.attrib["type"]
|
|
462
|
-
if language != self.language:
|
|
477
|
+
if (language != self.language) and (not self.language.startswith(language)):
|
|
463
478
|
raise ValueError(f"Expected language {self.language}, got {language}")
|
|
464
479
|
|
|
465
480
|
for group_elem in root.findall("rbnf//ruleset"):
|
|
@@ -473,7 +488,7 @@ class RbnfEngine:
|
|
|
473
488
|
continue
|
|
474
489
|
|
|
475
490
|
value_str = rule_elem.attrib["value"]
|
|
476
|
-
radix = int(rule_elem.attrib.get("radix", 10))
|
|
491
|
+
radix = int(re.sub(r"[^0-9]+", "", rule_elem.attrib.get("radix", "10")))
|
|
477
492
|
|
|
478
493
|
self.add_rule(
|
|
479
494
|
value_str,
|
|
@@ -584,8 +599,12 @@ class RbnfEngine:
|
|
|
584
599
|
if part.text:
|
|
585
600
|
yield part.text
|
|
586
601
|
elif isinstance(part, SubRulePart):
|
|
587
|
-
|
|
588
|
-
|
|
602
|
+
sub_part: SubRulePart = part
|
|
603
|
+
|
|
604
|
+
if part.type == SubType.QUOTIENT:
|
|
605
|
+
if (q == 0) and (
|
|
606
|
+
sub_part.is_optional or (part.ruleset_name is None)
|
|
607
|
+
):
|
|
589
608
|
# Rulesets can use quotients of zero
|
|
590
609
|
continue
|
|
591
610
|
|
|
@@ -599,7 +618,9 @@ class RbnfEngine:
|
|
|
599
618
|
if part.text_after:
|
|
600
619
|
yield part.text_after
|
|
601
620
|
elif part.type == SubType.REMAINDER:
|
|
602
|
-
if (r == 0) and (
|
|
621
|
+
if (r == 0) and (
|
|
622
|
+
sub_part.is_optional or (part.ruleset_name is None)
|
|
623
|
+
):
|
|
603
624
|
# Rulesets can use remainders of zero
|
|
604
625
|
continue
|
|
605
626
|
|
|
@@ -1,12 +1,12 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
|
-
Name:
|
|
3
|
-
Version: 2.
|
|
2
|
+
Name: unicode-rbnf
|
|
3
|
+
Version: 2.2.0
|
|
4
4
|
Summary: Rule-based number formatting using Unicode CLDR data
|
|
5
|
-
|
|
6
|
-
Author: Michael Hansen
|
|
7
|
-
Author-email: mike@rhasspy.org
|
|
5
|
+
Author-email: Michael Hansen <mike@rhasspy.org>
|
|
8
6
|
License: MIT
|
|
9
|
-
|
|
7
|
+
Project-URL: Source Code, https://github.com/rhasspy/unicode-rbnf
|
|
8
|
+
Keywords: rbnf,unicode,number,format
|
|
9
|
+
Platform: any
|
|
10
10
|
Classifier: Development Status :: 3 - Alpha
|
|
11
11
|
Classifier: Intended Audience :: Developers
|
|
12
12
|
Classifier: Topic :: Text Processing :: Linguistic
|
|
@@ -16,6 +16,8 @@ Classifier: Programming Language :: Python :: 3.9
|
|
|
16
16
|
Classifier: Programming Language :: Python :: 3.10
|
|
17
17
|
Classifier: Programming Language :: Python :: 3.11
|
|
18
18
|
Classifier: Programming Language :: Python :: 3.12
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
20
|
+
Requires-Python: >=3.8.0
|
|
19
21
|
Description-Content-Type: text/markdown
|
|
20
22
|
License-File: LICENSE.md
|
|
21
23
|
|
|
@@ -97,3 +99,5 @@ Some features that will need to be added eventually:
|
|
|
97
99
|
* Proper fraction rules (`0.x`)
|
|
98
100
|
* Preceding reminder substitution (`>>>` or `→→→`)
|
|
99
101
|
* Number format strings (`==`)
|
|
102
|
+
* Decimal format patterns (`#,##0.00`)
|
|
103
|
+
* Plural replacements (`$(ordinal,one{st}...)`)
|
|
@@ -1,24 +1,26 @@
|
|
|
1
1
|
LICENSE.md
|
|
2
|
-
MANIFEST.in
|
|
3
2
|
README.md
|
|
3
|
+
pyproject.toml
|
|
4
4
|
setup.cfg
|
|
5
|
-
setup.py
|
|
6
5
|
tests/test_de.py
|
|
6
|
+
tests/test_decimal_format.py
|
|
7
7
|
tests/test_en.py
|
|
8
8
|
tests/test_engine.py
|
|
9
9
|
tests/test_es.py
|
|
10
10
|
tests/test_fi.py
|
|
11
11
|
tests/test_fr.py
|
|
12
|
+
tests/test_load_all.py
|
|
12
13
|
tests/test_ro.py
|
|
13
|
-
unicode_rbnf/VERSION
|
|
14
14
|
unicode_rbnf/__init__.py
|
|
15
15
|
unicode_rbnf/__main__.py
|
|
16
|
+
unicode_rbnf/decimal_format.py
|
|
16
17
|
unicode_rbnf/engine.py
|
|
17
18
|
unicode_rbnf/py.typed
|
|
18
19
|
unicode_rbnf.egg-info/PKG-INFO
|
|
19
20
|
unicode_rbnf.egg-info/SOURCES.txt
|
|
20
21
|
unicode_rbnf.egg-info/dependency_links.txt
|
|
21
22
|
unicode_rbnf.egg-info/top_level.txt
|
|
23
|
+
unicode_rbnf.egg-info/zip-safe
|
|
22
24
|
unicode_rbnf/rbnf/af.xml
|
|
23
25
|
unicode_rbnf/rbnf/ak.xml
|
|
24
26
|
unicode_rbnf/rbnf/am.xml
|
|
@@ -38,11 +40,9 @@ unicode_rbnf/rbnf/de_CH.xml
|
|
|
38
40
|
unicode_rbnf/rbnf/ee.xml
|
|
39
41
|
unicode_rbnf/rbnf/el.xml
|
|
40
42
|
unicode_rbnf/rbnf/en.xml
|
|
41
|
-
unicode_rbnf/rbnf/en_001.xml
|
|
42
43
|
unicode_rbnf/rbnf/en_IN.xml
|
|
43
44
|
unicode_rbnf/rbnf/eo.xml
|
|
44
45
|
unicode_rbnf/rbnf/es.xml
|
|
45
|
-
unicode_rbnf/rbnf/es_419.xml
|
|
46
46
|
unicode_rbnf/rbnf/et.xml
|
|
47
47
|
unicode_rbnf/rbnf/fa.xml
|
|
48
48
|
unicode_rbnf/rbnf/fa_AF.xml
|
|
@@ -78,7 +78,6 @@ unicode_rbnf/rbnf/mk.xml
|
|
|
78
78
|
unicode_rbnf/rbnf/ms.xml
|
|
79
79
|
unicode_rbnf/rbnf/mt.xml
|
|
80
80
|
unicode_rbnf/rbnf/my.xml
|
|
81
|
-
unicode_rbnf/rbnf/nb.xml
|
|
82
81
|
unicode_rbnf/rbnf/ne.xml
|
|
83
82
|
unicode_rbnf/rbnf/nl.xml
|
|
84
83
|
unicode_rbnf/rbnf/nn.xml
|
|
@@ -88,7 +87,6 @@ unicode_rbnf/rbnf/pt.xml
|
|
|
88
87
|
unicode_rbnf/rbnf/pt_PT.xml
|
|
89
88
|
unicode_rbnf/rbnf/qu.xml
|
|
90
89
|
unicode_rbnf/rbnf/ro.xml
|
|
91
|
-
unicode_rbnf/rbnf/root.xml
|
|
92
90
|
unicode_rbnf/rbnf/ru.xml
|
|
93
91
|
unicode_rbnf/rbnf/se.xml
|
|
94
92
|
unicode_rbnf/rbnf/sk.xml
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
|
unicode_rbnf-2.0.0/MANIFEST.in
DELETED
unicode_rbnf-2.0.0/setup.py
DELETED
|
@@ -1,46 +0,0 @@
|
|
|
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
|
-
)
|
|
@@ -1,18 +0,0 @@
|
|
|
1
|
-
from unicode_rbnf import RbnfEngine
|
|
2
|
-
|
|
3
|
-
|
|
4
|
-
def test_german():
|
|
5
|
-
engine = RbnfEngine.for_language("de")
|
|
6
|
-
assert engine.format_number(13).text == "dreizehn"
|
|
7
|
-
assert engine.format_number(32).text == "zweiunddreißig"
|
|
8
|
-
|
|
9
|
-
# All genders, cases
|
|
10
|
-
assert set(engine.format_number(1).text_by_ruleset.values()) == {
|
|
11
|
-
"ein",
|
|
12
|
-
"eins",
|
|
13
|
-
"eine",
|
|
14
|
-
"eines",
|
|
15
|
-
"einer",
|
|
16
|
-
"einem",
|
|
17
|
-
"einen",
|
|
18
|
-
}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
2.0.0
|
|
@@ -1,14 +0,0 @@
|
|
|
1
|
-
<?xml version="1.0" encoding="UTF-8" ?>
|
|
2
|
-
<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd">
|
|
3
|
-
<!--
|
|
4
|
-
Copyright © 1991-2015 Unicode, Inc.
|
|
5
|
-
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
|
|
6
|
-
For terms of use, see http://www.unicode.org/copyright.html
|
|
7
|
-
-->
|
|
8
|
-
<ldml>
|
|
9
|
-
<identity>
|
|
10
|
-
<version number="$Revision$"/>
|
|
11
|
-
<language type="en"/>
|
|
12
|
-
<territory type="001"/>
|
|
13
|
-
</identity>
|
|
14
|
-
</ldml>
|
|
@@ -1,50 +0,0 @@
|
|
|
1
|
-
<?xml version="1.0" encoding="UTF-8" ?>
|
|
2
|
-
<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd">
|
|
3
|
-
<!--
|
|
4
|
-
Copyright © 1991-2014 Unicode, Inc.
|
|
5
|
-
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
|
|
6
|
-
For terms of use, see http://www.unicode.org/copyright.html
|
|
7
|
-
-->
|
|
8
|
-
<ldml>
|
|
9
|
-
<identity>
|
|
10
|
-
<version number="$Revision$"/>
|
|
11
|
-
<language type="es"/>
|
|
12
|
-
<territory type="419"/>
|
|
13
|
-
</identity>
|
|
14
|
-
<rbnf>
|
|
15
|
-
<rulesetGrouping type="OrdinalRules">
|
|
16
|
-
<ruleset type="dord-mascabbrev" access="private">
|
|
17
|
-
<rbnfrule value="0">º;</rbnfrule>
|
|
18
|
-
<rbnfrule value="1">ᵉʳ;</rbnfrule>
|
|
19
|
-
<rbnfrule value="2">º;</rbnfrule>
|
|
20
|
-
<rbnfrule value="3">ᵉʳ;</rbnfrule>
|
|
21
|
-
<rbnfrule value="4">º;</rbnfrule>
|
|
22
|
-
<rbnfrule value="20">→→;</rbnfrule>
|
|
23
|
-
<rbnfrule value="100">→→;</rbnfrule>
|
|
24
|
-
</ruleset>
|
|
25
|
-
<ruleset type="digits-ordinal-masculine-adjective">
|
|
26
|
-
<rbnfrule value="-x">−→→;</rbnfrule>
|
|
27
|
-
<rbnfrule value="0">=#,##0==%%dord-mascabbrev=.;</rbnfrule>
|
|
28
|
-
</ruleset>
|
|
29
|
-
<ruleset type="digits-ordinal-masculine">
|
|
30
|
-
<rbnfrule value="-x">−→→;</rbnfrule>
|
|
31
|
-
<rbnfrule value="0">=#,##0=º.;</rbnfrule>
|
|
32
|
-
</ruleset>
|
|
33
|
-
<ruleset type="digits-ordinal-feminine">
|
|
34
|
-
<rbnfrule value="-x">−→→;</rbnfrule>
|
|
35
|
-
<rbnfrule value="0">=#,##0=ª.;</rbnfrule>
|
|
36
|
-
</ruleset>
|
|
37
|
-
<ruleset type="digits-ordinal-masculine-plural">
|
|
38
|
-
<rbnfrule value="-x">−→→;</rbnfrule>
|
|
39
|
-
<rbnfrule value="0">=#,##0=ᵒˢ.;</rbnfrule>
|
|
40
|
-
</ruleset>
|
|
41
|
-
<ruleset type="digits-ordinal-feminine-plural">
|
|
42
|
-
<rbnfrule value="-x">−→→;</rbnfrule>
|
|
43
|
-
<rbnfrule value="0">=#,##0=ᵃˢ.;</rbnfrule>
|
|
44
|
-
</ruleset>
|
|
45
|
-
<ruleset type="digits-ordinal">
|
|
46
|
-
<rbnfrule value="0">=%digits-ordinal-masculine=;</rbnfrule>
|
|
47
|
-
</ruleset>
|
|
48
|
-
</rulesetGrouping>
|
|
49
|
-
</rbnf>
|
|
50
|
-
</ldml>
|
|
@@ -1,13 +0,0 @@
|
|
|
1
|
-
<?xml version="1.0" encoding="UTF-8" ?>
|
|
2
|
-
<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd">
|
|
3
|
-
<!-- Copyright © 1991-2020 Unicode, Inc.
|
|
4
|
-
For terms of use, see http://www.unicode.org/copyright.html
|
|
5
|
-
Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
|
|
6
|
-
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
|
|
7
|
-
-->
|
|
8
|
-
<ldml>
|
|
9
|
-
<identity>
|
|
10
|
-
<version number="$Revision$"/>
|
|
11
|
-
<language type="nb"/>
|
|
12
|
-
</identity>
|
|
13
|
-
</ldml>
|