Merge branch 'master' into master

.gitignore

@@ -6,3 +6,4 @@ dist
 /.tox
 .eggs/
 /venv/
+.venv/

README.rst

@@ -79,8 +79,11 @@ Besides the numerical argument, there are two main optional arguments, ``to:`` a
 * ``am`` (Amharic)
 * ``ar`` (Arabic)
 * ``az`` (Azerbaijani)
-* ``by`` (Belarusian)
-* ``cz`` (Czech)
+* ``be`` (Belarusian)
+* ``bn`` (Bangladeshi)
+* ``ce`` (Chechen)
+* ``cs`` (Czech)
+* ``cy`` (Welsh)
 * ``de`` (German)
 * ``dk`` (Danish)
 * ``en_GB`` (English - Great Britain)
@@ -89,6 +92,7 @@ Besides the numerical argument, there are two main optional arguments, ``to:`` a
 * ``en_NP`` (English - Nepal)
 * ``es`` (Spanish)
 * ``es_CO`` (Spanish - Colombia)
+* ``es_CR`` (Spanish - Costa Rica)
 * ``es_VE`` (Spanish - Venezuela)
 * ``es_GT`` (Spanish - Guatemala)
 * ``eu`` (EURO)
@@ -119,6 +123,7 @@ Besides the numerical argument, there are two main optional arguments, ``to:`` a
 * ``ro`` (Romanian)
 * ``ru`` (Russian)
 * ``te`` (Telugu)
+* ``tet`` (Tetum)
 * ``tg`` (Tajik)
 * ``tr`` (Turkish)
 * ``th`` (Thai)

num2words/README.md

@@ -0,0 +1,70 @@
+# Add new language
+
+for each new language you must create a file `lang_NN.py` where `NN` is the 
+ISO 639-1 or ISO 639-3 [language code](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes).
+
+This class must be a subclass of `Num2Word_EU` and implement at least the following methods
+
+```
+to_cardinal(self, number)
+to_ordinal(self, number)
+``
+
+To integrate your language into the `num2words` module, add the name of  your file
+to the import list in [num2words/__init__.py](num2words/__init__.py) (top of the file),
+and `'nn': lang_NN.Num2Word_NN()` to the `CONVERTER_CLASSES` list in the same file.
+Do not forget to remplace `NN` by the appropriate ISO 639 language code.
+
+The following is a template for a new language class
+
+```
+from .lang_EU import Num2Word_EU
+
+class Num2Word_CY(Num2Word_EU):
+    def setup(self):
+        Num2Word_EU.setup(self)
+
+    def __init__(self):
+        pass
+
+    def to_ordinal(self, number):
+	# implement here your code. number is the integer to be transformed into an ordinal
+        # as a word (str)
+	# which is returned
+	return "NOT IMPLEMENTED"
+
+    def to_cardinal(self, number):
+	# implement here your code. number is the integer to be transformed into an cardinal
+        # as a word (str)
+	# which is returned
+	return "NOT IMPLEMENTED"
+```
+
+You can use as manu auxiliary methods as you need to make your code efficient and readable.
+If you need further options like Gender, Formal/Informal, add those parameters to the methods,
+e.g.
+
+```
+    def to_ordinal(self, number, gender="fem", informal=True)
+	# your code
+	pass
+```
+
+More inspiration can be found in existing `num2words/lang_NN.py` files
+
+## Code validation
+
+In order to get your contribution merged into the main project, your code must test the validation tests.
+For this install the packages needed to test
+
+```
+pip install -r requirements-test.txt
+```
+
+run `tox` and `coverage` to check that the code is well formated and all parts of the code are tested
+
+```
+tox
+python3 -m coverage report -m
+```
+

num2words/__init__.py

@@ -17,21 +17,27 @@
 
 from __future__ import unicode_literals
 
-from . import (lang_AM, lang_AR, lang_AZ, lang_BY, lang_CZ, lang_DE, lang_DK,
-               lang_EN, lang_EN_IN, lang_EN_NG, lang_EN_NP, lang_EO, lang_ES, lang_ES_CO,
+
+from . import (lang_AM, lang_AR, lang_AZ, lang_BE, lang_BN, lang_CA, lang_CE,
+               lang_CS, lang_CY, lang_DE, lang_DK, lang_EN, lang_EN_IN,lang_EN_NP,
+               lang_EN_NG, lang_EO, lang_ES, lang_ES_CO, lang_ES_CR,
                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_SK, lang_SL, lang_SR, lang_SV, lang_TE,
-               lang_TG, lang_TH, lang_TR, lang_UK, lang_VI)
+               lang_TET, 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(),
-    'by': lang_BY.Num2Word_BY(),
-    'cz': lang_CZ.Num2Word_CZ(),
+    'be': lang_BE.Num2Word_BE(),
+    'bn': lang_BN.Num2Word_BN(),
+    'ca': lang_CA.Num2Word_CA(),
+    'ce': lang_CE.Num2Word_CE(),
+    'cs': lang_CS.Num2Word_CS(),
+    'cy': lang_CY.Num2Word_CY(),
     'en': lang_EN.Num2Word_EN(),
     'en_IN': lang_EN_IN.Num2Word_EN_IN(),
     'en_NG': lang_EN_NG.Num2Word_EN_NG(),
@@ -46,6 +52,7 @@
     'eo': lang_EO.Num2Word_EO(),
     'es': lang_ES.Num2Word_ES(),
     'es_CO': lang_ES_CO.Num2Word_ES_CO(),
+    'es_CR': lang_ES_CR.Num2Word_ES_CR(),
     'es_GT': lang_ES_GT.Num2Word_ES_GT(),
     'es_NI': lang_ES_NI.Num2Word_ES_NI(),
     'es_VE': lang_ES_VE.Num2Word_ES_VE(),
@@ -76,8 +83,9 @@
     'nl': lang_NL.Num2Word_NL(),
     'uk': lang_UK.Num2Word_UK(),
     'te': lang_TE.Num2Word_TE(),
+    'tet': lang_TET.Num2Word_TET(),
     'hu': lang_HU.Num2Word_HU(),
-    'is': lang_IS.Num2Word_IS()
+    'is': lang_IS.Num2Word_IS(),
 }
 
 CONVERTES_TYPES = ['cardinal', 'ordinal', 'ordinal_num', 'year', 'currency']

num2words/lang_BY.py → num2words/lang_BE.py

@@ -94,6 +94,17 @@
     9: "дзевяноста",
 }
 
+TWENTIES_ORD = (
+    ("дваццаць", "дваццаці"),
+    ("трыццаць", "трыццаці"),
+    ("сорак", "сарака"),
+    ("пяцьдзясят", "пяцідзясяці"),
+    ("шэсцьдзясят", "шaсцідзясяці"),
+    ("семдзесят", "сямідзесяці"),
+    ("восемдзесят", "васьмідзесяці"),
+    ("дзевяноста", "дзевяноста"),
+)
+
 HUNDREDS = {
     1: "сто",
     2: "дзвесце",
@@ -120,7 +131,7 @@
 }
 
 
-class Num2Word_BY(Num2Word_Base):
+class Num2Word_BE(Num2Word_Base):
     CURRENCY_FORMS = {
         "RUB": (
             ("расійскі рубель", "расійскія рублі", "расійскіх рублёў"),
@@ -138,6 +149,7 @@ class Num2Word_BY(Num2Word_Base):
             ("капейка", "капейкі", "капеек"),
         ),
         "UZS": (("сум", "сумы", "сумаў"), ("тыйін", "тыйіны", "тыйінаў")),
+        "PLN": (("злоты", "злотых", "злотых"), ("грош", "грошы", "грошаў")),
     }
 
     def setup(self):
@@ -204,6 +216,8 @@ def pluralize(self, n, forms):
 
     def to_ordinal(self, number, gender="m"):
         self.verify_ordinal(number)
+        if isinstance(gender, bool) and gender:
+            gender = "f"
         outwords = self.to_cardinal(number, gender).split(" ")
         lastword = outwords[-1].lower()
         try:
@@ -223,8 +237,6 @@ def to_ordinal(self, number, gender="m"):
                 lastword = (
                     self.ords_adjective.get(lastword[:-3], lastword) + "соты"
                 )
-            elif lastword[-5:] == "шэсць":
-                lastword = "шосты"
             elif lastword[-7:] == "дзесяць":
                 lastword = "дзясяты"
             elif lastword[-9:] == "семдзесят":
@@ -242,6 +254,8 @@ def to_ordinal(self, number, gender="m"):
 
             elif lastword[-1] == "н" or lastword[-2] == "н":
                 lastword = lastword[: lastword.rfind("н") + 1] + "ны"
+            elif lastword[-3:] == "наў":
+                lastword = lastword[: lastword.rfind("н") + 1] + "ны"
             elif lastword[-1] == "д" or lastword[-2] == "д":
                 lastword = lastword[: lastword.rfind("д") + 1] + "ны"
 
@@ -254,9 +268,7 @@ def to_ordinal(self, number, gender="m"):
                 lastword = lastword[:-1] + "ая"
 
         if gender == "n":
-            if lastword[-2:] in [
-                "ці", "ца"
-            ]:
+            if lastword[-2:] in ["ці", "ца"]:
                 lastword = lastword[:-2] + "цяе"
             else:
                 lastword = lastword[:-1] + "ае"
@@ -266,16 +278,20 @@ def to_ordinal(self, number, gender="m"):
             outwords[-2] = outwords[-1]
             del outwords[-1]
 
-        if len(outwords) > 2 and "тысяч" in outwords[-1]:
-            if 'сорак' in outwords[-3]:
-                outwords[-3] = outwords[-3].replace('сорак', 'сарака')
-            outwords[-3] = outwords[-3] + outwords[-2] + outwords[-1]
-            del outwords[-1]
-            del outwords[-1]
+        if len(outwords) > 1 and (
+            (any(x[0] in outwords[-1] for x in THOUSANDS.values()))
+            or "тысяч" in outwords[-1]
+        ):
+            new_outwords = []
+            for _w in outwords:
+                replacement = next(
+                    (x for x in TWENTIES_ORD if x[0] in _w), None
+                )
+                if replacement:
+                    _w = _w.replace(replacement[0], replacement[1])
+                new_outwords.append(_w)
+            outwords = ["".join(new_outwords)]
 
-        elif len(outwords) > 1 and "тысяч" in outwords[-1]:
-            outwords[-2] = outwords[-2] + outwords[-1]
-            del outwords[-1]
         return " ".join(outwords).strip()
 
     def _money_verbose(self, number, currency):
@@ -294,8 +310,6 @@ def _cents_verbose(self, number, currency):
         return self._int2word(number, gender)
 
     def _int2word(self, n, gender="m"):
-        if isinstance(gender, bool) and gender:
-            gender = "f"
         if n < 0:
             return " ".join([self.negword, self._int2word(abs(n), gender)])