fix language codes

savoirfairelinux · Jul 27, 2023 · 3377ee5 · 3377ee5
1 parent 872510d
commit 3377ee5
Show file tree

Hide file tree

Showing 9 changed files with 351 additions and 299 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/README.rst b/README.rst
@@ -73,15 +73,15 @@ Besides the numerical argument, there are two main optional arguments, ``to:`` a
 * ``year``
 * ``currency``
 
-**lang:** The language in which to convert the number. Supported values are:
+**lang:** The language in which to convert the number, in the ISO 639-1 code format. Supported values are:
 
 * ``en`` (English, default)
 * ``am`` (Amharic)
 * ``ar`` (Arabic)
 * ``az`` (Azerbaijani)
-* ``cz`` (Czech)
+* ``cs`` (Czech)
 * ``de`` (German)
-* ``dk`` (Danish)
+* ``da`` (Danish)
 * ``en_GB`` (English - Great Britain)
 * ``en_IN`` (English - India)
 * ``en_NG`` (English - Nigeria)
@@ -104,7 +104,7 @@ Besides the numerical argument, there are two main optional arguments, ``to:`` a
 * ``ja`` (Japanese)
 * ``kn`` (Kannada)
 * ``ko`` (Korean)
-* ``kz`` (Kazakh)
+* ``kk`` (Kazakh)
 * ``lt`` (Lithuanian)
 * ``lv`` (Latvian)
 * ``no`` (Norwegian)

diff --git a/num2words/__init__.py b/num2words/__init__.py
@@ -17,70 +17,112 @@
 
 from __future__ import unicode_literals
 
-from . import (lang_AM, lang_AR, lang_AZ, lang_CZ, lang_DE, lang_DK, lang_EN,
-               lang_EN_IN, lang_EN_NG, lang_EO, lang_ES, lang_ES_CO,
-               lang_ES_GT, lang_ES_NI, lang_ES_VE, lang_FA, lang_FI, lang_FR,
-               lang_FR_BE, lang_FR_CH, lang_FR_DZ, lang_HE, lang_HU, lang_ID,
-               lang_IS, lang_IT, lang_JA, lang_KN, lang_KO, lang_KZ, lang_LT,
-               lang_LV, lang_NL, lang_NO, lang_PL, lang_PT, lang_PT_BR,
-               lang_RO, lang_RU, lang_SL, lang_SR, lang_SV, lang_TE, lang_TG,
-               lang_TH, lang_TR, lang_UK, lang_VI)
+from . import (
+    lang_AM,
+    lang_AR,
+    lang_AZ,
+    lang_CS,
+    lang_DA,
+    lang_DE,
+    lang_EN,
+    lang_EN_IN,
+    lang_EN_NG,
+    lang_EO,
+    lang_ES,
+    lang_ES_CO,
+    lang_ES_GT,
+    lang_ES_NI,
+    lang_ES_VE,
+    lang_FA,
+    lang_FI,
+    lang_FR,
+    lang_FR_BE,
+    lang_FR_CH,
+    lang_FR_DZ,
+    lang_HE,
+    lang_HU,
+    lang_ID,
+    lang_IS,
+    lang_IT,
+    lang_JA,
+    lang_KK,
+    lang_KN,
+    lang_KO,
+    lang_LT,
+    lang_LV,
+    lang_NL,
+    lang_NO,
+    lang_PL,
+    lang_PT,
+    lang_PT_BR,
+    lang_RO,
+    lang_RU,
+    lang_SL,
+    lang_SR,
+    lang_SV,
+    lang_TE,
+    lang_TG,
+    lang_TH,
+    lang_TR,
+    lang_UK,
+    lang_VI,
+)
 
 CONVERTER_CLASSES = {
-    'am': lang_AM.Num2Word_AM(),
-    'ar': lang_AR.Num2Word_AR(),
-    'az': lang_AZ.Num2Word_AZ(),
-    'cz': lang_CZ.Num2Word_CZ(),
-    'en': lang_EN.Num2Word_EN(),
-    'en_IN': lang_EN_IN.Num2Word_EN_IN(),
-    'en_NG': lang_EN_NG.Num2Word_EN_NG(),
-    'fa': lang_FA.Num2Word_FA(),
-    'fr': lang_FR.Num2Word_FR(),
-    'fr_CH': lang_FR_CH.Num2Word_FR_CH(),
-    'fr_BE': lang_FR_BE.Num2Word_FR_BE(),
-    'fr_DZ': lang_FR_DZ.Num2Word_FR_DZ(),
-    'de': lang_DE.Num2Word_DE(),
-    'fi': lang_FI.Num2Word_FI(),
-    'eo': lang_EO.Num2Word_EO(),
-    'es': lang_ES.Num2Word_ES(),
-    'es_CO': lang_ES_CO.Num2Word_ES_CO(),
-    'es_GT': lang_ES_GT.Num2Word_ES_GT(),
-    'es_NI': lang_ES_NI.Num2Word_ES_NI(),
-    'es_VE': lang_ES_VE.Num2Word_ES_VE(),
-    'id': lang_ID.Num2Word_ID(),
-    'ja': lang_JA.Num2Word_JA(),
-    'kn': lang_KN.Num2Word_KN(),
-    'ko': lang_KO.Num2Word_KO(),
-    'kz': lang_KZ.Num2Word_KZ(),
-    'lt': lang_LT.Num2Word_LT(),
-    'lv': lang_LV.Num2Word_LV(),
-    'pl': lang_PL.Num2Word_PL(),
-    'ro': lang_RO.Num2Word_RO(),
-    'ru': lang_RU.Num2Word_RU(),
-    'sl': lang_SL.Num2Word_SL(),
-    'sr': lang_SR.Num2Word_SR(),
-    'sv': lang_SV.Num2Word_SV(),
-    'no': lang_NO.Num2Word_NO(),
-    'dk': lang_DK.Num2Word_DK(),
-    'pt': lang_PT.Num2Word_PT(),
-    'pt_BR': lang_PT_BR.Num2Word_PT_BR(),
-    'he': lang_HE.Num2Word_HE(),
-    'it': lang_IT.Num2Word_IT(),
-    'vi': lang_VI.Num2Word_VI(),
-    'tg': lang_TG.Num2Word_TG(),
-    'th': lang_TH.Num2Word_TH(),
-    'tr': lang_TR.Num2Word_TR(),
-    'nl': lang_NL.Num2Word_NL(),
-    'uk': lang_UK.Num2Word_UK(),
-    'te': lang_TE.Num2Word_TE(),
-    'hu': lang_HU.Num2Word_HU(),
-    'is': lang_IS.Num2Word_IS()
+    "am": lang_AM.Num2Word_AM(),
+    "ar": lang_AR.Num2Word_AR(),
+    "az": lang_AZ.Num2Word_AZ(),
+    "cs": lang_CS.Num2Word_CS(),
+    "en": lang_EN.Num2Word_EN(),
+    "en_IN": lang_EN_IN.Num2Word_EN_IN(),
+    "en_NG": lang_EN_NG.Num2Word_EN_NG(),
+    "fa": lang_FA.Num2Word_FA(),
+    "fr": lang_FR.Num2Word_FR(),
+    "fr_CH": lang_FR_CH.Num2Word_FR_CH(),
+    "fr_BE": lang_FR_BE.Num2Word_FR_BE(),
+    "fr_DZ": lang_FR_DZ.Num2Word_FR_DZ(),
+    "de": lang_DE.Num2Word_DE(),
+    "fi": lang_FI.Num2Word_FI(),
+    "eo": lang_EO.Num2Word_EO(),
+    "es": lang_ES.Num2Word_ES(),
+    "es_CO": lang_ES_CO.Num2Word_ES_CO(),
+    "es_GT": lang_ES_GT.Num2Word_ES_GT(),
+    "es_NI": lang_ES_NI.Num2Word_ES_NI(),
+    "es_VE": lang_ES_VE.Num2Word_ES_VE(),
+    "id": lang_ID.Num2Word_ID(),
+    "ja": lang_JA.Num2Word_JA(),
+    "kn": lang_KN.Num2Word_KN(),
+    "ko": lang_KO.Num2Word_KO(),
+    "kk": lang_KK.Num2Word_KK(),
+    "lt": lang_LT.Num2Word_LT(),
+    "lv": lang_LV.Num2Word_LV(),
+    "pl": lang_PL.Num2Word_PL(),
+    "ro": lang_RO.Num2Word_RO(),
+    "ru": lang_RU.Num2Word_RU(),
+    "sl": lang_SL.Num2Word_SL(),
+    "sr": lang_SR.Num2Word_SR(),
+    "sv": lang_SV.Num2Word_SV(),
+    "no": lang_NO.Num2Word_NO(),
+    "da": lang_DA.Num2Word_DA(),
+    "pt": lang_PT.Num2Word_PT(),
+    "pt_BR": lang_PT_BR.Num2Word_PT_BR(),
+    "he": lang_HE.Num2Word_HE(),
+    "it": lang_IT.Num2Word_IT(),
+    "vi": lang_VI.Num2Word_VI(),
+    "tg": lang_TG.Num2Word_TG(),
+    "th": lang_TH.Num2Word_TH(),
+    "tr": lang_TR.Num2Word_TR(),
+    "nl": lang_NL.Num2Word_NL(),
+    "uk": lang_UK.Num2Word_UK(),
+    "te": lang_TE.Num2Word_TE(),
+    "hu": lang_HU.Num2Word_HU(),
+    "is": lang_IS.Num2Word_IS(),
 }
 
-CONVERTES_TYPES = ['cardinal', 'ordinal', 'ordinal_num', 'year', 'currency']
+CONVERTES_TYPES = ["cardinal", "ordinal", "ordinal_num", "year", "currency"]
 
 
-def num2words(number, ordinal=False, lang='en', to='cardinal', **kwargs):
+def num2words(number, ordinal=False, lang="en", to="cardinal", **kwargs):
     # We try the full language first
     if lang not in CONVERTER_CLASSES:
         # ... and then try only the first 2 letters
@@ -94,9 +136,9 @@ def num2words(number, ordinal=False, lang='en', to='cardinal', **kwargs):
 
     # backwards compatible
     if ordinal:
-        to = 'ordinal'
+        to = "ordinal"
 
     if to not in CONVERTES_TYPES:
         raise NotImplementedError()
 
-    return getattr(converter, 'to_{}'.format(to))(number, **kwargs)
+    return getattr(converter, "to_{}".format(to))(number, **kwargs)
diff --git a/num2words/lang_CZ.py → num2words/lang_CS.py b/num2words/lang_CZ.py → num2words/lang_CS.py
@@ -20,95 +20,92 @@
 from .base import Num2Word_Base
 from .utils import get_digits, splitbyx
 
-ZERO = ('nula',)
+ZERO = ("nula",)
 
 ONES = {
-    1: ('jedna',),
-    2: ('dva',),
-    3: ('tři',),
-    4: ('čtyři',),
-    5: ('pět',),
-    6: ('šest',),
-    7: ('sedm',),
-    8: ('osm',),
-    9: ('devět',),
+    1: ("jedna",),
+    2: ("dva",),
+    3: ("tři",),
+    4: ("čtyři",),
+    5: ("pět",),
+    6: ("šest",),
+    7: ("sedm",),
+    8: ("osm",),
+    9: ("devět",),
 }
 
 TENS = {
-    0: ('deset',),
-    1: ('jedenáct',),
-    2: ('dvanáct',),
-    3: ('třináct',),
-    4: ('čtrnáct',),
-    5: ('patnáct',),
-    6: ('šestnáct',),
-    7: ('sedmnáct',),
-    8: ('osmnáct',),
-    9: ('devatenáct',),
+    0: ("deset",),
+    1: ("jedenáct",),
+    2: ("dvanáct",),
+    3: ("třináct",),
+    4: ("čtrnáct",),
+    5: ("patnáct",),
+    6: ("šestnáct",),
+    7: ("sedmnáct",),
+    8: ("osmnáct",),
+    9: ("devatenáct",),
 }
 
 TWENTIES = {
-    2: ('dvacet',),
-    3: ('třicet',),
-    4: ('čtyřicet',),
-    5: ('padesát',),
-    6: ('šedesát',),
-    7: ('sedmdesát',),
-    8: ('osmdesát',),
-    9: ('devadesát',),
+    2: ("dvacet",),
+    3: ("třicet",),
+    4: ("čtyřicet",),
+    5: ("padesát",),
+    6: ("šedesát",),
+    7: ("sedmdesát",),
+    8: ("osmdesát",),
+    9: ("devadesát",),
 }
 
 HUNDREDS = {
-    1: ('sto',),
-    2: ('dvěstě',),
-    3: ('třista',),
-    4: ('čtyřista',),
-    5: ('pětset',),
-    6: ('šestset',),
-    7: ('sedmset',),
-    8: ('osmset',),
-    9: ('devětset',),
+    1: ("sto",),
+    2: ("dvěstě",),
+    3: ("třista",),
+    4: ("čtyřista",),
+    5: ("pětset",),
+    6: ("šestset",),
+    7: ("sedmset",),
+    8: ("osmset",),
+    9: ("devětset",),
 }
 
 THOUSANDS = {
-    1: ('tisíc', 'tisíce', 'tisíc'),  # 10^3
-    2: ('milion', 'miliony', 'milionů'),  # 10^6
-    3: ('miliarda', 'miliardy', 'miliard'),  # 10^9
-    4: ('bilion', 'biliony', 'bilionů'),  # 10^12
-    5: ('biliarda', 'biliardy', 'biliard'),  # 10^15
-    6: ('trilion', 'triliony', 'trilionů'),  # 10^18
-    7: ('triliarda', 'triliardy', 'triliard'),  # 10^21
-    8: ('kvadrilion', 'kvadriliony', 'kvadrilionů'),  # 10^24
-    9: ('kvadriliarda', 'kvadriliardy', 'kvadriliard'),  # 10^27
-    10: ('quintillion', 'quintilliony', 'quintillionů'),  # 10^30
+    1: ("tisíc", "tisíce", "tisíc"),  # 10^3
+    2: ("milion", "miliony", "milionů"),  # 10^6
+    3: ("miliarda", "miliardy", "miliard"),  # 10^9
+    4: ("bilion", "biliony", "bilionů"),  # 10^12
+    5: ("biliarda", "biliardy", "biliard"),  # 10^15
+    6: ("trilion", "triliony", "trilionů"),  # 10^18
+    7: ("triliarda", "triliardy", "triliard"),  # 10^21
+    8: ("kvadrilion", "kvadriliony", "kvadrilionů"),  # 10^24
+    9: ("kvadriliarda", "kvadriliardy", "kvadriliard"),  # 10^27
+    10: ("quintillion", "quintilliony", "quintillionů"),  # 10^30
 }
 
 
-class Num2Word_CZ(Num2Word_Base):
+class Num2Word_CS(Num2Word_Base):
     CURRENCY_FORMS = {
-        'CZK': (
-            ('koruna', 'koruny', 'korun'), ('halíř', 'halíře', 'haléřů')
-        ),
-        'EUR': (
-            ('euro', 'euro', 'euro'), ('cent', 'centy', 'centů')
-        ),
+        "CZK": (("koruna", "koruny", "korun"), ("halíř", "halíře", "haléřů")),
+        "EUR": (("euro", "euro", "euro"), ("cent", "centy", "centů")),
     }
 
     def setup(self):
         self.negword = "mínus"
         self.pointword = "celá"
 
     def to_cardinal(self, number):
-        n = str(number).replace(',', '.')
-        if '.' in n:
-            left, right = n.split('.')
-            leading_zero_count = len(right) - len(right.lstrip('0'))
-            decimal_part = ((ZERO[0] + ' ') * leading_zero_count +
-                            self._int2word(int(right)))
-            return u'%s %s %s' % (
+        n = str(number).replace(",", ".")
+        if "." in n:
+            left, right = n.split(".")
+            leading_zero_count = len(right) - len(right.lstrip("0"))
+            decimal_part = (ZERO[0] + " ") * leading_zero_count + self._int2word(
+                int(right)
+            )
+            return "%s %s %s" % (
                 self._int2word(int(left)),
                 self.pointword,
-                decimal_part
+                decimal_part,
             )
         else:
             return self._int2word(int(n))
@@ -154,4 +151,4 @@ def _int2word(self, n):
             if i > 0:
                 words.append(self.pluralize(x, THOUSANDS[i]))
 
-        return ' '.join(words)
+        return " ".join(words)