v0.5.2

Add Indian locale

CHANGES.rst

@@ -1,6 +1,13 @@
 Changelog
 =========
 
+Version 0.5.2 -- 2015/01/23
+---------------------------
+
+* Added Latvian localization. (#9)
+* Improved Spanish localization. (#10, #13, #14)
+* Improved Lithuanian localization. (#12)
+
 Version 0.5.1 -- 2014/03/14
 ---------------------------
 

README.rst

@@ -35,8 +35,18 @@ Besides the numerical argument, there's two optional arguments.
 
 **ordinal:** A boolean flag indicating to return an ordinal number instead of a cardinal one.
 
-**lang:** The language in which to convert the number. Supported languages are ``en``, ``fr``,
-``de``, ``es``, ``lt`` and ``en_GB``. You can supply values like ``fr_FR``, the code will be
+**lang:** The language in which to convert the number. Supported values are:
+
+* ``en`` (English, default)
+* ``fr`` (French)
+* ``de`` (German)
+* ``es`` (Spanish)
+* ``lt`` (Lithuanian)
+* ``lv`` (Latvian)
+* ``en_GB`` (British English)
+* ``en_IN`` (Indian English)
+
+You can supply values like ``fr_FR``, the code will be
 correctly interpreted. If you supply an unsupported language, ``NotImplementedError`` is raised.
 Therefore, if you want to call ``num2words`` with a fallback, you can do::
 

num2words/__init__.py

@@ -18,18 +18,22 @@ from __future__ import unicode_literals
 
 from . import lang_EN
 from . import lang_EN_GB
+from . import lang_EN_IN
 from . import lang_FR
 from . import lang_DE
 from . import lang_ES
 from . import lang_LT
+from . import lang_LV
 
 CONVERTER_CLASSES = {
     'en': lang_EN.Num2Word_EN(),
     'en_GB': lang_EN_GB.Num2Word_EN_GB(),
+    'en_IN': lang_EN_IN.Num2Word_EN_IN(),
     'fr': lang_FR.Num2Word_FR(),
     'de': lang_DE.Num2Word_DE(),
     'es': lang_ES.Num2Word_ES(),
     'lt': lang_LT.Num2Word_LT(),
+    'lv': lang_LV.Num2Word_LV(),
 }
 
 def num2words(number, ordinal=False, lang='en'):

num2words/lang_EN_IN.py

@@ -0,0 +1,42 @@
+# 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 .lang_EN import Num2Word_EN
+    
+class Num2Word_EN_IN(Num2Word_EN):
+    def set_high_numwords(self, high):
+        self.cards[10**7] = "crore"
+        self.cards[10**5] = "lakh"
+
+
+n2w = Num2Word_EN_IN()
+to_card = n2w.to_cardinal
+to_ord = n2w.to_ordinal
+to_ordnum = n2w.to_ordinal_num
+
+def main():
+    for val in (15000,
+            15*10**5,
+            15*10**6,
+            15*10**7,
+            15*10**8,
+            15*10**9,
+            15*10**10):
+        n2w.test(val)
+
+if __name__ == "__main__":
+    main()

num2words/lang_ES.py

@@ -1,3 +1,5 @@
+#encoding: UTF-8
+
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 
@@ -17,9 +19,6 @@
 from __future__ import unicode_literals
 from .lang_EU import Num2Word_EU
 
-#//TODO: correct orthographics
-#//TODO: error messages
-
 class Num2Word_ES(Num2Word_EU):
 
     #//CHECK: Is this sufficient??
@@ -27,7 +26,7 @@ class Num2Word_ES(Num2Word_EU):
         max = 3 + 6*len(high)
 
         for word, n in zip(high, range(max, 3, -6)):
-            self.cards[10**(n-3)] = word + "ill\xf2n"
+            self.cards[10**(n-3)] = word + "illón"
 
 
     def setup(self):
@@ -35,17 +34,17 @@ class Num2Word_ES(Num2Word_EU):
         self.high_numwords = self.gen_high_numwords([], [], lows)
         self.negword = "menos "
         self.pointword = "punto"
-        self.errmsg_nonnum = "Only numbers may be converted to words."
-        self.errmsg_toobig = "Number is too large to convert to words."
+        self.errmsg_nonnum = "Solo números pueden ser convertidos a palabras."
+        self.errmsg_toobig = "Numero muy grande para ser convertido a palabras."
         self.gender_stem = "o"
         self.exclude_title = ["y", "menos", "punto"]
         self.mid_numwords = [(1000, "mil"), (100, "cien"), (90, "noventa"),
                              (80, "ochenta"), (70, "setenta"), (60, "sesenta"),
                              (50, "cincuenta"), (40, "cuarenta"), (30, "treinta")]
-        self.low_numwords = ["vientinueve", "vientiocho", "vientisiete",
-                             "vientis\xE8is", "vienticinco", "vienticuatro",
-                             "vientitr\xE8s", "vientid\xF2s", "vientiuno",
-                             "viente", "diecinueve", "dieciocho", "diecisiete",
+        self.low_numwords = ["veintinueve", "veintiocho", "veintisiete",
+                             "veintiséis", "veinticinco", "veinticuatro",
+                             "veintitrés", "veintidós", "veintiuno",
+                             "veinte", "diecinueve", "dieciocho", "diecisiete",
                              "dieciseis", "quince", "catorce", "trece", "doce",
                              "once", "diez", "nueve", "ocho", "siete", "seis",
                              "cinco", "cuatro", "tres", "dos", "uno", "cero"]
@@ -55,10 +54,32 @@ class Num2Word_ES(Num2Word_EU):
                       4 : "cuart",
                       5 : "quint",
                       6 : "sext",
-                      7  : "s\xE8ptim",
+                      7 : "séptim",
                       8 : "octav",
                       9 : "noven",
-                      10 : "d\xE8cim" }
+                     10 : "décim",
+                     20 : "vigésim",
+                     30 : "trigésim",
+                     40 : "quadragésim",
+                     50 : "quincuagésim",
+                     60 : "sexagésim",
+                     70 : "septuagésim",
+                     80 : "octogésim",
+                     90 : "nonagésim",
+                    100 : "centésim",
+                    200 : "ducentésim",
+                    300 : "tricentésim",
+                    400 : "cuadrigentésim",
+                    500 : "quingentésim",
+                    600 : "sexcentésim",
+                    700 : "septigentésim",
+                    800 : "octigentésim",
+                    900 : "noningentésim",
+                    1e3 : "milésim",
+                    1e6 : "millonésim",
+                    1e9 : "billonésim",
+                   1e12 : "trillonésim",
+                   1e15 : "cuadrillonésim" }
 
 
     def merge(self, curr, next):
@@ -68,7 +89,7 @@ class Num2Word_ES(Num2Word_EU):
             if nnum < 1000000:
                 return next
             ctext = "un"
-        elif cnum == 100:
+        elif cnum == 100 and not nnum == 1000:
             ctext += "t" + self.gender_stem
 
         if nnum < cnum:
@@ -95,15 +116,40 @@ class Num2Word_ES(Num2Word_EU):
 
     def to_ordinal(self, value):
         self.verify_ordinal(value)
+        text = ""
         try:
-            return self.ords[value] + self.gender_stem
+            if value == 0:
+                text = ""
+            elif value <= 10:
+                text = "%s%s" % (self.ords[value], self.gender_stem)
+            elif value <= 12:
+                text = "%s%s%s" % (self.ords[10], self.gender_stem, self.to_ordinal(value - 10))
+            elif value <= 100:
+                dec = (value / 10) * 10
+                text = "%s%s %s" % (self.ords[dec], self.gender_stem, self.to_ordinal(value - dec))
+            elif value <= 1e3:
+                cen = (value / 100) * 100
+                text = "%s%s %s" % (self.ords[cen], self.gender_stem, self.to_ordinal(value - cen))
+            elif value < 1e18:
+                # dec contains the following:
+                # [ 1e3,  1e6): 1e3
+                # [ 1e6,  1e9): 1e6
+                # [ 1e9, 1e12): 1e9
+                # [1e12, 1e15): 1e12
+                # [1e15, 1e18): 1e15
+                dec = 10 ** ((((len(str(int(value))) - 1) / 3 - 1) + 1) * 3)
+                part = int(float(value / dec) * dec)
+                cardinal = self.to_cardinal(part / dec) if part / dec != 1 else ""
+                text = "%s%s%s %s" % (cardinal, self.ords[dec], self.gender_stem, self.to_ordinal(value - part))
+            else:
+                text = self.to_cardinal(value)
         except KeyError:
-            return self.to_cardinal(value)
+            text = self.to_cardinal(value)
+        return text.strip()
 
     def to_ordinal_num(self, value):
         self.verify_ordinal(value)
-        # Correct for fem?
-        return "%s\xB0"%value
+        return "%s%s" % (value, "º" if self.gender_stem == 'o' else "ª")
 
 
     def to_currency(self, val, longval=True, old=False):

num2words/lang_LT.py

@@ -17,12 +17,12 @@
 u"""
 >>> from textwrap import fill
 
->>> ' '.join([str(i) for i in splitby3('1')])
-'1'
->>> ' '.join([str(i) for i in splitby3('1123')])
-'1 123'
->>> ' '.join([str(i) for i in splitby3('1234567890')])
-'1 234 567 890'
+>>> print(' '.join([str(i) for i in splitby3('1')]))
+1
+>>> print(' '.join([str(i) for i in splitby3('1123')]))
+1 123
+>>> print(' '.join([str(i) for i in splitby3('1234567890')]))
+1 234 567 890
 
 >>> print(' '.join([n2w(i) for i in range(10)]))
 nulis vienas du trys keturi penki šeši septyni aštuoni devyni
@@ -36,34 +36,34 @@ nulis dešimt dvidešimt trisdešimt keturiasdešimt penkiasdešimt
 šešiasdešimt septyniasdešimt aštuoniasdešimt devyniasdešimt
 
 >>> print(n2w(100))
-šimtas
+vienas šimtas
 >>> print(n2w(101))
-šimtas vienas
+vienas šimtas vienas
 >>> print(n2w(110))
-šimtas dešimt
+vienas šimtas dešimt
 >>> print(n2w(115))
-šimtas penkiolika
+vienas šimtas penkiolika
 >>> print(n2w(123))
-šimtas dvidešimt trys
+vienas šimtas dvidešimt trys
 >>> print(n2w(1000))
-tūkstantis
+vienas tūkstantis
 >>> print(n2w(1001))
-tūkstantis vienas
+vienas tūkstantis vienas
 >>> print(n2w(2012))
 du tūkstančiai dvylika
 
 >>> print(fill(n2w(1234567890)))
-milijardas du šimtai trisdešimt keturi milijonai penki šimtai
+vienas milijardas du šimtai trisdešimt keturi milijonai penki šimtai
 šešiasdešimt septyni tūkstančiai aštuoni šimtai devyniasdešimt
 
 >>> print(fill(n2w(215461407892039002157189883901676)))
 du šimtai penkiolika naintilijonų keturi šimtai šešiasdešimt vienas
 oktilijonas keturi šimtai septyni septilijonai aštuoni šimtai
 devyniasdešimt du sikstilijonai trisdešimt devyni kvintilijonai du
-kvadrilijonai šimtas penkiasdešimt septyni trilijonai šimtas
-aštuoniasdešimt devyni milijardai aštuoni šimtai aštuoniasdešimt trys
-milijonai devyni šimtai vienas tūkstantis šeši šimtai septyniasdešimt
-šeši
+kvadrilijonai vienas šimtas penkiasdešimt septyni trilijonai vienas
+šimtas aštuoniasdešimt devyni milijardai aštuoni šimtai
+aštuoniasdešimt trys milijonai devyni šimtai vienas tūkstantis šeši
+šimtai septyniasdešimt šeši
 
 >>> print(fill(n2w(719094234693663034822824384220291)))
 septyni šimtai devyniolika naintilijonų devyniasdešimt keturi
@@ -82,7 +82,7 @@ naintilijonas
 vienas litas, nulis centų
 
 >>> print(to_currency(1234.56, 'LTL'))
-tūkstantis du šimtai trisdešimt keturi litai, penkiasdešimt šeši centai
+vienas tūkstantis du šimtai trisdešimt keturi litai, penkiasdešimt šeši centai
 
 >>> print(to_currency(-1251985, cents = False))
 minus dvylika tūkstančių penki šimtai devyniolika litų, 85 centai
@@ -177,13 +177,14 @@ def int2word(n):
     words = []
     chunks = list(splitby3(str(n)))
     i = len(chunks)
+
     for x in chunks:
         i -= 1
         n1, n2, n3 = get_digits(x)
 
         if n3 > 0:
-            if n3 > 1:
             words.append(ONES[n3][0])
+            if n3 > 1:
                 words.append(HUNDRED[1])
             else:
                 words.append(HUNDRED[0])
@@ -193,7 +194,7 @@ def int2word(n):
 
         if n2 == 1:
             words.append(TENS[n1][0])
-        elif n1 > 0 and not (i > 0 and x == 1):
+        elif n1 > 0:
             words.append(ONES[n1][0])
 
         if i > 0:

num2words/lang_LV.py

@@ -0,0 +1,285 @@
+# -*- 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
+u"""
+>>> from textwrap import fill
+
+>>> ' '.join([str(i) for i in splitby3('1')])
+u'1'
+>>> ' '.join([str(i) for i in splitby3('1123')])
+u'1 123'
+>>> ' '.join([str(i) for i in splitby3('1234567890')])
+u'1 234 567 890'
+
+>>> print(' '.join([n2w(i) for i in range(10)]))
+nulle viens divi trīs četri pieci seši septiņi astoņi deviņi
+
+>>> print(fill(' '.join([n2w(i+10) for i in range(10)])))
+desmit vienpadsmit divpadsmit trīspadsmit četrpadsmit piecpadsmit
+sešpadsmit septiņpadsmit astoņpadsmit deviņpadsmit
+
+>>> print(fill(' '.join([n2w(i*10) for i in range(10)])))
+nulle desmit divdesmit trīsdesmit četrdesmit piecdesmit sešdesmit
+septiņdesmit astoņdesmit deviņdesmit
+
+>>> print(n2w(100))
+simts
+>>> print(n2w(101))
+simtu viens
+>>> print(n2w(110))
+simts desmit
+>>> print(n2w(115))
+simts piecpadsmit
+>>> print(n2w(123))
+simts divdesmit trīs
+>>> print(n2w(1000))
+tūkstotis
+>>> print(n2w(1001))
+tūkstotis viens
+>>> print(n2w(2012))
+divi tūkstoši divpadsmit
+
+>>> print(fill(n2w(1234567890)))
+miljards divi simti trīsdesmit četri miljoni pieci simti sešdesmit
+septiņi tūkstoši astoņi simti deviņdesmit
+
+>>> print(fill(n2w(215461407892039002157189883901676)))
+divi simti piecpadsmit nontiljoni četri simti sešdesmit viens
+oktiljons četri simti septiņi septiljoni astoņi simti deviņdesmit divi
+sikstiljoni trīsdesmit deviņi kvintiljoni divi kvadriljoni simts
+piecdesmit septiņi triljoni simts astoņdesmit deviņi miljardi astoņi
+simti astoņdesmit trīs miljoni deviņi simti viens tūkstotis seši simti
+septiņdesmit seši
+
+>>> print(fill(n2w(719094234693663034822824384220291)))
+septiņi simti deviņpadsmit nontiljoni deviņdesmit četri oktiljoni divi
+simti trīsdesmit četri septiljoni seši simti deviņdesmit trīs
+sikstiljoni seši simti sešdesmit trīs kvintiljoni trīsdesmit četri
+kvadriljoni astoņi simti divdesmit divi triljoni astoņi simti
+divdesmit četri miljardi trīs simti astoņdesmit četri miljoni divi
+simti divdesmit tūkstoši divi simti deviņdesmit viens
+
+# TODO: fix this:
+# >>> print(fill(n2w(1000000000000000000000000000000)))
+# nontiljons
+
+>>> print(to_currency(1.0, 'EUR'))
+viens eiro, nulle centu
+
+>>> print(to_currency(1.0, 'LVL'))
+viens lats, nulle santīmu
+
+>>> print(to_currency(1234.56, 'EUR'))
+tūkstotis divi simti trīsdesmit četri eiro, piecdesmit seši centi
+
+>>> print(to_currency(1234.56, 'LVL'))
+tūkstotis divi simti trīsdesmit četri lati, piecdesmit seši santīmi
+
+>>> print(to_currency(10111, 'EUR', seperator=' un'))
+simtu viens eiro un vienpadsmit centi
+
+>>> print(to_currency(10121, 'LVL', seperator=' un'))
+simtu viens lats un divdesmit viens santīms
+
+>>> print(to_currency(-1251985, cents = False))
+mīnus divpadsmit tūkstoši pieci simti deviņpadsmit eiro, 85 centi
+"""
+from __future__ import unicode_literals
+
+ZERO = (u'nulle',)
+
+ONES = {
+    1: (u'viens',),
+    2: (u'divi',),
+    3: (u'trīs',),
+    4: (u'četri',),
+    5: (u'pieci',),
+    6: (u'seši',),
+    7: (u'septiņi',),
+    8: (u'astoņi',),
+    9: (u'deviņi',),
+}
+
+TENS = {
+    0: (u'desmit',),
+    1: (u'vienpadsmit',),
+    2: (u'divpadsmit',),
+    3: (u'trīspadsmit',),
+    4: (u'četrpadsmit',),
+    5: (u'piecpadsmit',),
+    6: (u'sešpadsmit',),
+    7: (u'septiņpadsmit',),
+    8: (u'astoņpadsmit',),
+    9: (u'deviņpadsmit',),
+}
+
+TWENTIES = {
+    2: (u'divdesmit',),
+    3: (u'trīsdesmit',),
+    4: (u'četrdesmit',),
+    5: (u'piecdesmit',),
+    6: (u'sešdesmit',),
+    7: (u'septiņdesmit',),
+    8: (u'astoņdesmit',),
+    9: (u'deviņdesmit',),
+}
+
+HUNDRED = (u'simts', u'simti', u'simtu')
+
+THOUSANDS = {
+    1: (u'tūkstotis', u'tūkstoši', u'tūkstošu'),
+    2: (u'miljons', u'miljoni', u'miljonu'),
+    3: (u'miljards', u'miljardi', u'miljardu'),
+    4: (u'triljons', u'triljoni', u'triljonu'),
+    5: (u'kvadriljons', u'kvadriljoni', u'kvadriljonu'),
+    6: (u'kvintiljons', u'kvintiljoni', u'kvintiljonu'),
+    7: (u'sikstiljons', u'sikstiljoni', u'sikstiljonu'),
+    8: (u'septiljons', u'septiljoni', u'septiljonu'),
+    9: (u'oktiljons', u'oktiljoni', u'oktiljonu'),
+    10: (u'nontiljons', u'nontiljoni', u'nontiljonu'),
+}
+
+CURRENCIES = {
+    'LVL': (
+        (u'lats', u'lati', u'latu'), (u'santīms', u'santīmi', u'santīmu')
+    ),
+    'EUR': (
+        (u'eiro', u'eiro', u'eiro'), (u'cents', u'centi', u'centu')
+    ),
+}
+
+
+def splitby3(n):
+    length = len(n)
+    if length > 3:
+        start = length % 3
+        if start > 0:
+            yield int(n[:start])
+        for i in range(start, length, 3):
+            yield int(n[i:i+3])
+    else:
+        yield int(n)
+
+
+def get_digits(n):
+    return [int(x) for x in reversed(list(('%03d' % n)[-3:]))]
+
+
+def pluralize(n, forms):
+    # gettext implementation:
+    # (n%10==1 && n%100!=11 ? 0 : n != 0 ? 1 : 2)
+
+    form = 0 if (n % 10 == 1 and n % 100 != 11) else 1 if n != 0 else 2
+
+    return forms[form]
+
+
+def int2word(n):
+    if n == 0:
+        return ZERO[0]
+
+    words = []
+    chunks = list(splitby3(str(n)))
+    i = len(chunks)
+    for x in chunks:
+        i -= 1
+        n1, n2, n3 = get_digits(x)
+
+        # print str(n3) + str(n2) + str(n1)
+
+        if n3 > 0:
+            if n3 == 1 and n2 == 0 and n1 > 0:
+                words.append(HUNDRED[2])
+            elif n3 > 1:
+                words.append(ONES[n3][0])
+                words.append(HUNDRED[1])
+            else:
+                words.append(HUNDRED[0])
+
+        if n2 > 1:
+            words.append(TWENTIES[n2][0])
+
+        if n2 == 1:
+            words.append(TENS[n1][0])
+        elif n1 > 0 and not (i > 0 and x == 1):
+            words.append(ONES[n1][0])
+
+        if i > 0:
+            words.append(pluralize(x, THOUSANDS[i]))
+
+    return ' '.join(words)
+
+
+def n2w(n):
+    n = str(n).replace(',', '.')
+    if '.' in n:
+        left, right = n.split('.')
+        return u'%s kablelis %s' % (int2word(int(left)), int2word(int(right)))
+    else:
+        return int2word(int(n))
+
+
+def to_currency(n, currency='EUR', cents=True, seperator=','):
+    if type(n) == int:
+        if n < 0:
+            minus = True
+        else:
+            minus = False
+
+        n = abs(n)
+        left = n / 100
+        right = n % 100
+    else:
+        n = str(n).replace(',', '.')
+        if '.' in n:
+            left, right = n.split('.')
+        else:
+            left, right = n, 0
+        left, right = int(left), int(right)
+        minus = False
+    cr1, cr2 = CURRENCIES[currency]
+
+    if minus:
+        minus_str = "mīnus "
+    else:
+        minus_str = ""
+
+    if cents:
+        cents_str = int2word(right)
+    else:
+        cents_str = "%02d" % right
+
+    return u'%s%s %s%s %s %s' % (
+        minus_str,
+        int2word(left),
+        pluralize(left, cr1),
+        seperator,
+        cents_str,
+        pluralize(right, cr2)
+    )
+
+
+class Num2Word_LV(object):
+    def to_cardinal(self, number):
+        return n2w(number)
+
+    def to_ordinal(self, number):
+        raise NotImplementedError()
+
+
+if __name__ == '__main__':
+    import doctest
+    doctest.testmod()

setup.py

@@ -17,8 +17,9 @@ LONG_DESC = open('README.rst', 'rt').read() + '\n\n' + open('CHANGES.rst', 'rt')
 
 setup(
     name='num2words',
-    version='0.5.1',
+    version='0.5.2',
     description='Modules to convert numbers to words. Easily extensible.',
+    long_description=LONG_DESC,
     license='LGPL',
     author='Taro Ogawa <tso at users sourceforge net>',
     author_email='tos@users.sourceforge.net',