From 4047d6526a46738ca6676c9a69e1aafb021ee25a Mon Sep 17 00:00:00 2001 From: Armin Date: Fri, 8 Sep 2017 13:17:14 +0200 Subject: [PATCH 1/5] added support for Dutch (NL) language --- num2words/__init__.py | 5 +- num2words/lang_NL.py | 155 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 158 insertions(+), 2 deletions(-) create mode 100644 num2words/lang_NL.py diff --git a/num2words/__init__.py b/num2words/__init__.py index 58eabfb..6589569 100644 --- a/num2words/__init__.py +++ b/num2words/__init__.py @@ -38,7 +38,7 @@ from . import lang_ES_VE from . import lang_ES_CO from . import lang_VN from . import lang_TR - +from . import lang_NL CONVERTER_CLASSES = { 'ar': lang_AR.Num2Word_AR(), @@ -62,7 +62,8 @@ CONVERTER_CLASSES = { 'he': lang_HE.Num2Word_HE(), 'it': lang_IT.Num2Word_IT(), 'vi_VN': lang_VN.Num2Word_VN(), - 'tr': lang_TR.Num2Word_TR() + 'tr': lang_TR.Num2Word_TR(), + 'nl': lang_NL.Num2Word_NL() } def num2words(number, ordinal=False, lang='en'): diff --git a/num2words/lang_NL.py b/num2words/lang_NL.py new file mode 100644 index 0000000..2447f7e --- /dev/null +++ b/num2words/lang_NL.py @@ -0,0 +1,155 @@ +# -*- 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 __future__ import unicode_literals, print_function +from .lang_EU import Num2Word_EU + +class Num2Word_NL(Num2Word_EU): + def set_high_numwords(self, high): + max = 3 + 6*len(high) + + for word, n in zip(high, range(max, 3, -6)): + self.cards[10**n] = word + "iljard" + self.cards[10**(n-3)] = word + "iljoen" + + def setup(self): + self.negword = "min " + self.pointword = "komma" + self.errmsg_floatord = "Het zwevende puntnummer %s kan niet omgezet worden naar een ordernummer." # "Cannot treat float %s as ordinal." + self.errmsg_nonnum = "Alleen nummers (type (%s)) kunnen naar woorden omgezet worden." # "type(((type(%s)) ) not in [long, int, float]" + self.errmsg_negord = "Het negatieve getal %s kan niet omgezet worden naar een ordernummer." # "Cannot treat negative num %s as ordinal." + self.errmsg_toobig = "Het getal %s moet minder zijn dan %s." # "abs(%s) must be less than %s." + self.exclude_title = [] + + lows = ["non", "okt", "sept", "sext", "quint", "quadr", "tr", "b", "m"] + units = ["", "un", "duo", "tre", "quattuor", "quin", "sex", "sept", + "okto", "novem"] + tens = ["dez", "vigint", "trigint", "quadragint", "quinquagint", + "sexagint", "septuagint", "oktogint", "nonagint"] + + + + + self.high_numwords = ["zend"]+self.gen_high_numwords(units, tens, lows) + self.mid_numwords = [(1000, "duizend"), (100, "honderd"), + (90, "negentig"), (80, "tachtig"), (70, "zeventig"), + (60, "zestig"), (50, "vijftig"), (40, "veertig"), + (30, "dertig")] + self.low_numwords = ["twintig", "negentien", "achttien", "zeventien", + "zestien", "vijftien", "veertien", "dertien", + "twaalf", "elf", "tien", "negen", "acht", "zeven", + "zes", "vijf", "vier", "drie", "twee", "één", + "nul"] + + self.ords = {"één": "eerst", + "twee": "tweed", + "drie": "derd", + "vier": "vierd", + "vijf": "vijfd", + "zes": "zesd", + "zeven": "zevend", + "acht": "achtst", + "negen": "negend", + "tien":"tiend", + "elf":"elfde", + "twaalf":"twaalfde", + + "ig": "igst", + "erd": "erdst", + "end": "endst", + "joen": "joenst", + "rd": "rdst"} + + def merge(self, curr, next): + ctext, cnum, ntext, nnum = curr + next + + if cnum == 1: + if nnum < 10**6: + return next + ctext = "een" + + if nnum > cnum: + if nnum >= 10**6: + ctext += " " + val = cnum * nnum + else: + if nnum < 10 < cnum < 100: + if nnum == 1: + ntext = "een" + + if ntext.endswith("e"): + ntext += "ën"#"n" + else: + ntext += "en" + ntext, ctext = ctext, ntext #+ "en" + elif cnum >= 10**6: + ctext += " " + val = cnum + nnum + + word = ctext + ntext + return (word, val) + + def to_ordinal(self, value): + self.verify_ordinal(value) + outword = self.to_cardinal(value) + for key in self.ords: + if outword.endswith(key): + outword = outword[:len(outword) - len(key)] + self.ords[key] + break + return outword + "e" + + def to_ordinal_num(self, value): + self.verify_ordinal(value) + return str(value) + "." + + def to_currency(self, val, longval=True, old=False): + if old: + return self.to_splitnum(val, hightxt="euro/s", lowtxt="cent/s", + jointxt="en",longval=longval) + return super(Num2Word_NL, self).to_currency(val, jointxt="en", + longval=longval) + + def to_year(self, val, longval=True): + if not (val//100)%10: + return self.to_cardinal(val) + return self.to_splitnum(val, hightxt="honderd", longval=longval) + +n2w = Num2Word_NL() +to_card = n2w.to_cardinal +to_ord = n2w.to_ordinal +to_ordnum = n2w.to_ordinal_num + + +def main(): + for val in [1, 7, 8, 12, 17, 62,81, 91, 99, 100, 101, 102, 155, + 180, 300, 308, 832, 1000, 1001, 1061,1062, 1100, 1500, 1701, 3000, + 8280, 8291, 150000, 500000, 3000000, 1000000, 2000001, 1000000000, 2000000000, + -21212121211221211111, -2.121212, -1.0000100]: + n2w.test(val) + + # n2w.test(1325325436067876801768700107601001012212132143210473207540327057320957032975032975093275093275093270957329057320975093272950730) + n2w.test(3000000) + n2w.test(3000000000001) + n2w.test(3000000324566) + print(n2w.to_currency(112121)) + print(n2w.to_year(2000)) + print(n2w.to_year(1820)) + print(n2w.to_year(2001)) + +if __name__ == "__main__": + main() + From 294d350fb9b5c44de7bbb6b2cd04670d2653440f Mon Sep 17 00:00:00 2001 From: Armin Date: Fri, 8 Sep 2017 17:42:30 +0200 Subject: [PATCH 2/5] added NL test cases --- num2words/lang_NL.py | 1 - tests/test_nl.py | 52 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+), 1 deletion(-) create mode 100644 tests/test_nl.py diff --git a/num2words/lang_NL.py b/num2words/lang_NL.py index 2447f7e..a802fd6 100644 --- a/num2words/lang_NL.py +++ b/num2words/lang_NL.py @@ -141,7 +141,6 @@ def main(): -21212121211221211111, -2.121212, -1.0000100]: n2w.test(val) - # n2w.test(1325325436067876801768700107601001012212132143210473207540327057320957032975032975093275093275093270957329057320975093272950730) n2w.test(3000000) n2w.test(3000000000001) n2w.test(3000000324566) diff --git a/tests/test_nl.py b/tests/test_nl.py new file mode 100644 index 0000000..e7a71f4 --- /dev/null +++ b/tests/test_nl.py @@ -0,0 +1,52 @@ +# -*- encoding: utf-8 -*- +# Copyright (c) 2015, 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 unittest import TestCase + +from num2words import num2words + +class Num2WordsNLTest(TestCase): + def test_ordinal_less_than_twenty(self): + self.assertEqual(num2words(7, ordinal=True, lang='nl'), "zevende") + self.assertEqual(num2words(8, ordinal=True, lang='nl'), "achtste") + self.assertEqual(num2words(12, ordinal=True, lang='nl'), "twaalfde") + self.assertEqual(num2words(17, ordinal=True, lang='nl'), "zeventiende") + + def test_ordinal_more_than_twenty(self): + self.assertEqual(num2words(81, ordinal=True, lang='nl'), "eenentachtigste") + + def test_ordinal_at_crucial_number(self): + self.assertEqual(num2words(100, ordinal=True, lang='nl'), "honderdste") + self.assertEqual(num2words(1000, ordinal=True, lang='nl'), "duizendste") + self.assertEqual(num2words(4000, ordinal=True, lang='nl'), "vierduizendste") + self.assertEqual(num2words(2000000, ordinal=True, lang='nl'), "twee miljoenste") + self.assertEqual(num2words(5000000000, ordinal=True, lang='nl'), "vijf miljardste") + + def test_cardinal_at_some_numbers(self): + self.assertEqual(num2words(1013, lang='nl'), "duizenddertien") + self.assertEqual(num2words(2000000, lang='nl'), "twee miljoen") + self.assertEqual(num2words(4000000000, lang='nl'), "vier miljard") + + def test_cardinal_for_decimal_number(self): + self.assertEqual(num2words(3.486, lang='nl'), "drie komma vier acht zes") + + def test_ordinal_for_negative_numbers(self): + self.assertRaises(TypeError, num2words, -12, ordinal=True, lang='nl') + + def test_ordinal_for_floating_numbers(self): + self.assertRaises(TypeError, num2words, 2.453, ordinal=True, lang='nl') \ No newline at end of file From 63fe589b98f4d56a5803623736d9766b1f6ce08f Mon Sep 17 00:00:00 2001 From: Armin Date: Fri, 8 Sep 2017 17:47:23 +0200 Subject: [PATCH 3/5] fixed test bug --- tests/test_nl.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_nl.py b/tests/test_nl.py index e7a71f4..7a32147 100644 --- a/tests/test_nl.py +++ b/tests/test_nl.py @@ -43,7 +43,7 @@ class Num2WordsNLTest(TestCase): self.assertEqual(num2words(4000000000, lang='nl'), "vier miljard") def test_cardinal_for_decimal_number(self): - self.assertEqual(num2words(3.486, lang='nl'), "drie komma vier acht zes") + self.assertEqual(num2words(3.486, lang='nl'), "drie komma vier acht") def test_ordinal_for_negative_numbers(self): self.assertRaises(TypeError, num2words, -12, ordinal=True, lang='nl') From 7fe315eb640f0651711ca927a00f2941a6fd5782 Mon Sep 17 00:00:00 2001 From: Armin Date: Fri, 8 Sep 2017 17:54:25 +0200 Subject: [PATCH 4/5] fixed bug with 12 and 11 --- num2words/lang_NL.py | 4 ++-- tests/test_nl.py | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/num2words/lang_NL.py b/num2words/lang_NL.py index a802fd6..5bbaa0a 100644 --- a/num2words/lang_NL.py +++ b/num2words/lang_NL.py @@ -65,8 +65,8 @@ class Num2Word_NL(Num2Word_EU): "acht": "achtst", "negen": "negend", "tien":"tiend", - "elf":"elfde", - "twaalf":"twaalfde", + "elf":"elfd", + "twaalf":"twaalfd", "ig": "igst", "erd": "erdst", diff --git a/tests/test_nl.py b/tests/test_nl.py index 7a32147..70edebc 100644 --- a/tests/test_nl.py +++ b/tests/test_nl.py @@ -38,6 +38,7 @@ class Num2WordsNLTest(TestCase): self.assertEqual(num2words(5000000000, ordinal=True, lang='nl'), "vijf miljardste") def test_cardinal_at_some_numbers(self): + self.assertEqual(num2words(82, lang='nl'), u'twee\xebntachtig') self.assertEqual(num2words(1013, lang='nl'), "duizenddertien") self.assertEqual(num2words(2000000, lang='nl'), "twee miljoen") self.assertEqual(num2words(4000000000, lang='nl'), "vier miljard") From 4b58b1ee25947a6fd2b0812e747ec6be4f5c0ec2 Mon Sep 17 00:00:00 2001 From: Armin Date: Fri, 8 Sep 2017 19:29:37 +0200 Subject: [PATCH 5/5] updated readme --- README.rst | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.rst b/README.rst index 813e87f..eb944d7 100644 --- a/README.rst +++ b/README.rst @@ -6,7 +6,7 @@ num2words - Convert numbers to words in multiple languages ``num2words`` is a library that converts numbers like ``42`` to words like ``forty-two``. It supports multiple languages (English, Arabic, Danish, French, -German, Hebrew, Italian, Latvian, Norwegian, Polish, Portuguese, Russian, +German, Dutch, Hebrew, Italian, Latvian, Norwegian, Polish, Portuguese, Russian, Spanish and Lithuanian) and can even generate ordinal numbers like ``forty-second`` (altough this last feature is a bit buggy at the moment). @@ -65,6 +65,8 @@ cardinal one. * ``pl`` (Polish) * ``pt_BR`` (Brazilian Portuguese) * ``ru`` (Russian) +* ``nl`` (Dutch) + You can supply values like ``fr_FR``, the code will be correctly interpreted. If you supply an unsupported language, ``NotImplementedError`` is raised.