Merge branch 'master' into strings

savoirfairelinux · Jan 18, 2019 · e459021 · e459021
2 parents 446e918 + 83cfcdc
commit e459021
Show file tree

Hide file tree

Showing 75 changed files with 2,501 additions and 1,446 deletions.
diff --git a/CHANGES.rst b/CHANGES.rst
@@ -1,6 +1,32 @@
 Changelog
 =========
 
+Version 0.5.9 -- 2019/01/10
+---------------------------
+
+* Fix encoding issue on release 0.5.8 (#229)
+* Improve Polish localization (#228)
+
+
+Version 0.5.8 -- 2018/11/17
+---------------------------
+
+* Add Portuguese (Portugal) localization (#198)
+* Add a command line tool to use num2words
+* Use language iso code for Vietnamese
+* Improve Korean localization (#219)
+* Improve Serbian (Latin) localization (#207)
+* Improve testing setup (#220)
+* Improve German localization (#214) (#222)
+* Improve Romanian localization (#215)
+* Improve Spanish localization (#187) (#200)
+* Improve Russian localization (#211) (#212)
+* Improve French localization (23902ab)
+* Improve Arabic localization (#176)
+* Improve Lithuanian and Latvian localization (#185)
+* Improve Ukrainian localization (#183)
+
+
 Version 0.5.7 -- 2018/06/27
 ---------------------------
 

diff --git a/README.rst b/README.rst
@@ -46,8 +46,6 @@ Command line::
 
     $ num2words 10001
     ten thousand and one
-    $ num2words 10123123 --lang es
-    diez millones ciento veintitrés mil ciento veintitrés
     $ num2words 24,120.10
     twenty-four thousand, one hundred and twenty point one
     $ num2words 24,120.10 -l es
@@ -97,12 +95,15 @@ Besides the numerical argument, there are two main optional arguments.
 * ``id`` (Indonesian)
 * ``it`` (Italian)
 * ``ja`` (Japanese)
+* ``ko`` (Korean)
 * ``lt`` (Lithuanian)
 * ``lv`` (Latvian)
 * ``no`` (Norwegian)
 * ``pl`` (Polish)
 * ``pt`` (Portuguese)
 * ``pt_BR`` (Portuguese - Brazilian)
+* ``sl`` (Slovene)
+* ``sr`` (Serbian)
 * ``ro`` (Romanian)
 * ``ru`` (Russian)
 * ``sl`` (Slovene)

diff --git a/bin/num2words b/bin/num2words
@@ -1,5 +1,21 @@
 #!/usr/bin/env python
 # -*- 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
+
 """num2words: convert numbers into words.
 
 Usage:
@@ -22,9 +38,6 @@ Options:
 Examples:
     $ num2words 10001
     ten thousand and one
-    
-    $ num2words 10123123 --lang es
-    diez millones ciento veintitrés mil ciento veintitrés
 
     $ num2words 24,120.10
     twenty-four thousand, one hundred and twenty point one
@@ -35,13 +48,14 @@ Examples:
     $num2words 2.14 -l es --to currency
     dos euros con catorce centimos
 """
+
 from __future__ import print_function, unicode_literals
 import os
 import sys
 from docopt import docopt
 import num2words
 
-__version__ = "0.5.7"
+__version__ = "0.5.9"
 __license__ = "LGPL"
 
 

diff --git a/docker-compose.yml b/docker-compose.yml
@@ -0,0 +1,7 @@
+version: '3.0'
+services:
+  web:
+    image: python:3-alpine
+    command: python3 -m http.server 8080
+    volumes:
+      - .:/num2words
diff --git a/num2words/__init__.py b/num2words/__init__.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 
@@ -47,7 +48,9 @@
 from . import lang_NL
 from . import lang_UK
 from . import lang_SL
+from . import lang_SR
 from . import lang_TH
+from . import lang_KO
 
 CONVERTER_CLASSES = {
     'ar': lang_AR.Num2Word_AR(),
@@ -65,12 +68,14 @@
     'es_VE': lang_ES_VE.Num2Word_ES_VE(),
     'id': lang_ID.Num2Word_ID(),
     'ja': lang_JA.Num2Word_JA(),
+    'ko': lang_KO.Num2Word_KO(),
     '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(),
     'no': lang_NO.Num2Word_NO(),
     'dk': lang_DK.Num2Word_DK(),
     'pt': lang_PT.Num2Word_PT(),

diff --git a/num2words/base.py b/num2words/base.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/compat.py b/num2words/compat.py
@@ -1,5 +1,6 @@
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
-# Copyright (c) 2016, Savoir-faire Linux inc.  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

diff --git a/num2words/currency.py b/num2words/currency.py
@@ -1,3 +1,20 @@
+# -*- 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 division
 
 from decimal import ROUND_HALF_UP, Decimal

diff --git a/num2words/lang_CZ.py b/num2words/lang_CZ.py
@@ -1,4 +1,4 @@
-# -*- encoding: utf-8 -*-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 
@@ -14,6 +14,7 @@
 # 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
@@ -130,6 +131,10 @@ def _int2word(self, n):
         i = len(chunks)
         for x in chunks:
             i -= 1
+
+            if x == 0:
+                continue
+
             n1, n2, n3 = get_digits(x)
 
             if n3 > 0:

diff --git a/num2words/lang_DE.py b/num2words/lang_DE.py
@@ -17,6 +17,8 @@
 
 from __future__ import print_function, unicode_literals
 
+import re
+
 from .lang_EU import Num2Word_EU
 
 
@@ -45,7 +47,7 @@ def setup(self):
         self.errmsg_toobig = "Die Zahl %s muss kleiner als %s sein."
         self.exclude_title = []
 
-        lows = ["non", "okt", "sept", "sext", "quint", "quadr", "tr", "b", "m"]
+        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",
@@ -78,7 +80,9 @@ def merge(self, curr, next):
         ctext, cnum, ntext, nnum = curr + next
 
         if cnum == 1:
-            if nnum < 10 ** 6:
+            if nnum == 100 or nnum == 1000:
+                return ("ein" + ntext, nnum)
+            elif nnum < 10 ** 6:
                 return next
             ctext = "eine"
 
@@ -105,26 +109,47 @@ def merge(self, curr, next):
 
     def to_ordinal(self, value):
         self.verify_ordinal(value)
-        outword = self.to_cardinal(value)
+        outword = self.to_cardinal(value).lower()
         for key in self.ords:
             if outword.endswith(key):
                 outword = outword[:len(outword) - len(key)] + self.ords[key]
                 break
-        return outword + "te"
+
+        res = outword + "te"
+
+        # Exception: "hundertste" is usually preferred over "einhundertste"
+        if res == "eintausendste" or res == "einhundertste":
+            res = res.replace("ein", "", 1)
+        # ... similarly for "millionste" etc.
+        res = re.sub(r'eine ([a-z]+(illion|illiard)ste)$',
+                     lambda m: m.group(1), res)
+        # Ordinals involving "Million" etc. are written without a space.
+        # see https://de.wikipedia.org/wiki/Million#Sprachliches
+        res = re.sub(r' ([a-z]+(illion|illiard)ste)$',
+                     lambda m: m.group(1), res)
+
+        return res
 
     def to_ordinal_num(self, value):
         self.verify_ordinal(value)
         return str(value) + "."
 
     def to_currency(self, val, longval=True, old=False):
-        hightxt = "euro"
-        lowtxt = "cent"
+        hightxt = "Euro"
+        lowtxt = "Cent"
         if old:
-            hightxt = "mark"
-            lowtxt = "pfennig/e"
+            hightxt = "Mark"
+            lowtxt = "Pfennig/e"
+
+        cents = int(round(val*100))
+        res = self.to_splitnum(cents, hightxt=hightxt, lowtxt=lowtxt,
+                               jointxt="und", longval=longval)
+
+        # Handle exception, in german is "ein Euro" and not "eins Euro"
+        if res.startswith("eins "):
+            res = res.replace("eins ", "ein ", 1)
 
-        return self.to_splitnum(val, hightxt=hightxt, lowtxt=lowtxt,
-                                jointxt="und", longval=longval)
+        return res
 
     def to_year(self, val, longval=True):
         if not (val // 100) % 10:

diff --git a/num2words/lang_DK.py b/num2words/lang_DK.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_EN.py b/num2words/lang_EN.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_EN_IN.py b/num2words/lang_EN_IN.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_ES.py b/num2words/lang_ES.py
@@ -1,5 +1,4 @@
-# encoding: UTF-8
-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_ES_CO.py b/num2words/lang_ES_CO.py
@@ -1,5 +1,4 @@
-# encoding: UTF-8
-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_ES_VE.py b/num2words/lang_ES_VE.py
@@ -1,5 +1,4 @@
-# encoding: UTF-8
-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_EU.py b/num2words/lang_EU.py
@@ -1,4 +1,4 @@
-# -*- encoding: utf-8 -*-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_FR.py b/num2words/lang_FR.py
@@ -1,4 +1,4 @@
-# -*- encoding: utf-8 -*-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 
@@ -89,7 +89,7 @@ def to_ordinal(self, value):
     def to_ordinal_num(self, value):
         self.verify_ordinal(value)
         out = str(value)
-        out += {"1": "er"}.get(out[-1], "me")
+        out += "er" if value == 1 else "me"
         return out
 
     def to_currency(self, val, longval=True, old=False):

diff --git a/num2words/lang_FR_BE.py b/num2words/lang_FR_BE.py
@@ -1,4 +1,4 @@
-# -*- encoding: utf-8 -*-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 

diff --git a/num2words/lang_FR_CH.py b/num2words/lang_FR_CH.py
@@ -1,4 +1,4 @@
-# -*- encoding: utf-8 -*-
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.
 
@@ -14,7 +14,6 @@
 # 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 print_function, unicode_literals
 
 from .lang_FR import Num2Word_FR

diff --git a/num2words/lang_FR_DZ.py b/num2words/lang_FR_DZ.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # Copyright (c) 2003, Taro Ogawa.  All Rights Reserved.
 # Copyright (c) 2013, Savoir-faire Linux inc.  All Rights Reserved.