add kannada language support (#243)

* add kannada support

* add Kannada Language support

* add tests for kannada

* reformatted

* change lang param

* fix tests

* add condition

* add modifier

* add few more test cases

* fix test

* fix test

* modify test

* fix flake8

* fix isort

* add more tests

* add unicode prefix

* edit tests for float numbers

* add more tests

* add unicode prefix in tests

* add Kannada language

README.rst

@@ -95,6 +95,7 @@ Besides the numerical argument, there are two main optional arguments.
 * ``id`` (Indonesian)
 * ``it`` (Italian)
 * ``ja`` (Japanese)
+* ``kn`` (Kannada)
 * ``ko`` (Korean)
 * ``lt`` (Lithuanian)
 * ``lv`` (Latvian)

num2words/__init__.py

@@ -20,9 +20,9 @@ from __future__ import unicode_literals
 from . import (lang_AR, lang_CZ, lang_DE, lang_DK, lang_EN, lang_EN_IN,
                lang_ES, lang_ES_CO, lang_ES_VE, lang_FI, lang_FR, lang_FR_BE,
                lang_FR_CH, lang_FR_DZ, lang_HE, lang_ID, lang_IT, lang_JA,
-               lang_KO, lang_LT, lang_LV, lang_NL, lang_NO, lang_PL, lang_PT,
+               lang_KN, lang_KO, lang_LT, lang_LV, lang_NL, lang_NO, lang_PL,
-               lang_PT_BR, lang_RO, lang_RU, lang_SL, lang_SR, lang_TH,
+               lang_PT, lang_PT_BR, lang_RO, lang_RU, lang_SL, lang_SR,
-               lang_TR, lang_UK, lang_VI)
+               lang_TH, lang_TR, lang_UK, lang_VI)
 
 CONVERTER_CLASSES = {
     'ar': lang_AR.Num2Word_AR(),
@@ -40,6 +40,7 @@ CONVERTER_CLASSES = {
     '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(),
     'lt': lang_LT.Num2Word_LT(),
     'lv': lang_LV.Num2Word_LV(),
@@ -73,8 +74,10 @@ def num2words(number, ordinal=False, lang='en', to='cardinal', **kwargs):
     if lang not in CONVERTER_CLASSES:
         raise NotImplementedError()
     converter = CONVERTER_CLASSES[lang]
+
     if isinstance(number, str):
         number = converter.str_to_number(number)
+
     # backwards compatible
     if ordinal:
         return converter.to_ordinal(number)

num2words/lang_KN.py

@@ -0,0 +1,182 @@
+# -*- encoding: utf-8 -*-
+# Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
+# Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
+
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2.1 of the License, or (at your option) any later version.
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# Lesser General Public License for more details.
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+# MA 02110-1301 USA
+
+from __future__ import unicode_literals
+
+from .base import Num2Word_Base
+
+
+class Num2Word_KN(Num2Word_Base):
+    def set_high_numwords(self, high):
+        for n, word in self.high_numwords:
+            self.cards[10 ** n] = word
+
+    def setup(self):
+        self.low_numwords = [
+            "ತೊಂಬತ್ತೊಂಬತ್ತು",
+            "ತೊಂಬತ್ತೆಂಟು",
+            "ತೊಂಬತ್ತೇಳು",
+            "ತೊಂಬತ್ತಾರು",
+            "ತೊಂಬತ್ತೈದು",
+            "ತೊಂಬತ್ತ ನಾಲ್ಕು",
+            "ತೊಂಬತ್ತ ಮೂರು",
+            "ತೊಂಬತ್ತೆರಡು",
+            "ತೊಂಬತ್ತೊಂದು",
+            "ತೊಂಬತ್ತು",
+            "ಎಂಬತ್ತೊಂಬತ್ತು",
+            "ಎಂಬತ್ತೆಂಟು",
+            "ಎಂಬತ್ತೇಳು",
+            "ಎಂಬತ್ತಾರು",
+            "ಎಂಬತ್ತೈದು",
+            "ಎಂಬತ್ತ್ ನಾಲ್ಕು",
+            "ಎಂಬತ್ತ್ ಮೂರು",
+            "ಎಂಬತ್ತೆರಡು",
+            "ಎಂಬತ್ತೊಂದು",
+            "ಎಂಬತ್ತು",
+            "ಎಪ್ಪತ್ತೊಂಬತ್ತು",
+            "ಎಪ್ಪತ್ತೆಂಟು",
+            "ಎಪ್ಪತ್ತೇಳು",
+            "ಎಪ್ಪತ್ತಾರು",
+            "ಎಪ್ಪತ್ತೈದು",
+            "ಎಪ್ಪತ್ತ್ ನಾಲ್ಕು",
+            "ಎಪ್ಪತ್ತ್ ಮೂರು",
+            "ಎಪ್ಪತ್ತೆರಡು",
+            "ಎಪ್ಪತ್ತೊಂದು",
+            "ಎಪ್ಪತ್ತು",
+            "ಅರವತ್ತೊಂಬತ್ತು",
+            "ಅರವತ್ತೆಂಟು",
+            "ಅರವತ್ತೇಳು",
+            "ಅರವತ್ತಾರು",
+            "ಅರವತ್ತೈದು",
+            "ಅರವತ್ತ್ ನಾಲ್ಕು",
+            "ಅರವತ್ತ್ ಮೂರು",
+            "ಅರವತ್ತೆರಡು",
+            "ಅರವತ್ತೊಂದು",
+            "ಅರವತ್ತು",
+            "ಐವತ್ತೊಂಬತ್ತು",
+            "ಐವತ್ತೆಂಟು",
+            "ಐವತ್ತೇಳು",
+            "ಐವತ್ತಾರು",
+            "ಐವತ್ತೈದು",
+            "ಐವತ್ತ್ನಾಲ್ಕು",
+            "ಐವತ್ತಮೂರು",
+            "ಐವತ್ತೆರಡು",
+            "ಐವತ್ತೊಂದು",
+            "ಐವತ್ತು",
+            "ನಲವತ್ತೊಂಬತ್ತು",
+            "ನಲವತ್ತೆಂಟು",
+            "ನಲವತ್ತೇಳು",
+            "ನಲವತ್ತಾರು",
+            "ನಲವತ್ತೈದು",
+            "ನಲವತ್ತ್ ನಾಲ್ಕು",
+            "ನಲವತ್ತ್ ಮೂರು",
+            "ನಲವತ್ತ್ ಎರಡು",
+            "ನಲವತ್ತೊಂದು",
+            "ನಲವತ್ತು",
+            "ಮೂವತ್ತ್ ಒಂಬತ್ತು",
+            "ಮೂವತ್ಎಂಟು",
+            "ಮೂವತ್ಏಳು",
+            "ಮೂವತ್ಆರು",
+            "ಮೂವತ್ತ್ ಐದು",
+            "ಮೂವತ್ತ್ ನಾಲ್ಕು",
+            "ಮೂವತ್ತ್ ಮೂರು",
+            "ಮೂವತ್ತ್ಎರಡು",
+            "ಮೂವತ್ತ್ಒಂದು",
+            "ಮೂವತ್ತು",
+            "ಇಪ್ಪತ್ತ್ಒಂಬತ್ತು",
+            "ಇಪ್ಪತ್ತ್ಎಂಟು",
+            "ಇಪ್ಪತ್ತ್ಏಳು",
+            "ಇಪ್ಪತ್ತ್ಆರು",
+            "ಇಪ್ಪತ್ತ್ ಐದು",
+            "ಇಪ್ಪತ್ತ್ ನಾಲ್ಕು",
+            "ಇಪ್ಪತ್ತ್ ಮೂರು",
+            "ಇಪ್ಪತ್ತ್ ಎರಡು",
+            "ಇಪ್ಪತ್ತ್ ಒಂದು",
+            "ಇಪ್ಪತ್ತು",
+            "ಹತ್ತೊಂಬತ್ತು",
+            "ಹದಿನೆಂಟು",
+            "ಹದಿನೇಳು",
+            "ಹದಿನಾರು",
+            "ಹದಿನೈದು",
+            "ಹದಿನಾಲ್ಕು",
+            "ಹದಿಮೂರು",
+            "ಹನ್ನೆರಡು",
+            "ಹನ್ನೊಂದು",
+            "ಹತ್ತು",
+            "ಒಂಬತ್ತು",
+            "ಎಂಟು",
+            "ಏಳು",
+            "ಆರು",
+            "ಐದು",
+            "ನಾಲ್ಕು",
+            "ಮೂರು",
+            "ಎರಡು",
+            "ಒಂದು",
+            "ಸೊನ್ನೆ",
+        ]
+
+        self.mid_numwords = [(100, "ನೂರು")]
+
+        self.high_numwords = [(7, "ಕೋಟಿ"), (5, "ಒಂದು ಲಕ್ಷ"), (3, "ಸಾವಿರ")]
+
+        self.pointword = "ಬಿಂದು"
+
+        self.modifiers = [
+            "್",
+            "ಾ",
+            "ಿ",
+            "ೀ",
+            "ೀ",
+            "ು",
+            "ೂ",
+            "ೃ",
+            "ೆ",
+            "ೇ",
+            "ೈ",
+            "ೊ",
+            "ೋ",
+            "ೌ",
+            "ೕ",
+        ]
+
+    def merge(self, lpair, rpair):
+        ltext, lnum = lpair
+        rtext, rnum = rpair
+        if lnum == 1 and rnum < 100:
+            return (rtext, rnum)
+        elif 100 > lnum > rnum:
+            return ("%s-%s" % (ltext, rtext), lnum + rnum)
+        elif lnum >= 100 > rnum:
+            if ltext[-1] in self.modifiers:
+                return ("%s %s" % (ltext[:-1], rtext), lnum + rnum)
+            else:
+                return ("%s %s" % (ltext + "ದ", rtext), lnum + rnum)
+        elif rnum > lnum:
+            return ("%s %s" % (ltext, rtext), lnum * rnum)
+        return ("%s %s" % (ltext, rtext), lnum + rnum)
+
+    def to_ordinal_num(self, value):
+        self.verify_ordinal(value)
+        return "%s%s" % (value, self.to_ordinal(value))
+
+    def to_ordinal(self, value):
+        self.verify_ordinal(value)
+        outwords = self.to_cardinal(value)
+        if outwords[-1] in self.modifiers:
+            outwords = outwords[:-1]
+        ordinal_num = outwords + "ನೇ"
+        return ordinal_num

tests/test_kn.py

@@ -0,0 +1,67 @@
+# -*- coding: utf-8 -*-
+# Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
+# Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
+
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2.1 of the License, or (at your option) any later version.
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# Lesser General Public License for more details.
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+# MA 02110-1301 USA
+
+
+from unittest import TestCase
+
+from num2words import num2words
+
+
+class Num2WordsKNTest(TestCase):
+    def test_numbers(self):
+        self.assertEqual(num2words(42, lang="kn"), u"ನಲವತ್ತ್ ಎರಡು")
+        self.assertEqual(num2words(893, lang="kn"), u"ಎಂಟು ನೂರ ತೊಂಬತ್ತ ಮೂರು")
+        self.assertEqual(
+            num2words(1729, lang="kn"), u"ಒಂದು ಸಾವಿರ ಏಳು ನೂರ ಇಪ್ಪತ್ತ್ಒಂಬತ್ತು"
+        )
+        self.assertEqual(num2words(123, lang="kn"), u"ಒಂದು ನೂರ ಇಪ್ಪತ್ತ್ ಮೂರು")
+        self.assertEqual(num2words(32211, lang="kn"),
+                         u"ಮೂವತ್ತ್ಎರಡು ಸಾವಿರ ಎರಡು ನೂರ ಹನ್ನೊಂದು")
+
+    def test_cardinal_for_float_number(self):
+        self.assertEqual(num2words(3.14, lang="kn"), u"ಮೂರು ಬಿಂದು ಒಂದು ನಾಲ್ಕು")
+        self.assertEqual(num2words(1.61803, lang="kn"),
+                         u"ಒಂದು ಬಿಂದು ಆರು ಒಂದು ಎಂಟು ಸೊನ್ನೆ ಮೂರು")
+
+    def test_ordinal(self):
+        self.assertEqual(
+            num2words(1, lang='kn', to='ordinal'),
+            u'ಒಂದನೇ'
+        )
+        self.assertEqual(
+            num2words(22, lang='kn', to='ordinal'),
+            u'ಇಪ್ಪತ್ತ್ ಎರಡನೇ'
+        )
+        self.assertEqual(
+            num2words(12, lang='kn', to='ordinal'),
+            u'ಹನ್ನೆರಡನೇ'
+        )
+        self.assertEqual(
+            num2words(130, lang='kn', to='ordinal'),
+            u'ಒಂದು ನೂರ ಮೂವತ್ತನೇ'
+        )
+        self.assertEqual(
+            num2words(1003, lang='kn', to='ordinal'),
+            u'ಒಂದು ಸಾವಿರದ ಮೂರನೇ'
+        )
+
+    def test_ordinal_num(self):
+        self.assertEqual(num2words(2, lang="kn", ordinal=True), u"ಎರಡನೇ")
+        self.assertEqual(num2words(5, lang="kn", ordinal=True), u"ಐದನೇ")
+        self.assertEqual(num2words(16, lang="kn", ordinal=True), u"ಹದಿನಾರನೇ")
+        self.assertEqual(num2words(113, lang="kn", ordinal=True),
+                         u"ಒಂದು ನೂರ ಹದಿಮೂರನೇ")