num2words2 0.1.0.dev1__py3-none-any.whl

num2words2/lang_OC.py

@@ -0,0 +1,135 @@
+# -*- 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
+
+from .base import Num2Word_Base
+
+
+# Occitan language support
+class Num2Word_OC(Num2Word_Base):
+    CURRENCY_FORMS = {
+        'EUR': (('èuro', 'èuros'), ('centim', 'centims')),
+        'USD': (('dollar', 'dollars'), ('cent', 'cents'))
+    }
+
+    def setup(self):
+        self.negword = "minus "
+        self.pointword = "point"
+        self.ones = ['', 'un', 'dos', 'tres', 'quatre', 'cinc', 'sièis', 'sèt', 'uèch', 'nòu']
+        self.tens = ['', 'dètz', 'vint', 'trenta', 'quaranta', 'cinquanta', 'seissanta', 'setanta', 'ochanta', 'nonanta']
+        self.hundred = "cent"
+        self.thousand = "mil"
+        self.million = "milion"
+
+    def to_cardinal(self, number):
+        """Convert a number to its word representation in Occitan."""
+        n = str(number).strip()
+
+        if n.startswith('-'):
+            n = n[1:]
+            ret = self.negword
+        else:
+            ret = ""
+
+        if '.' in n:
+            left, right = n.split('.', 1)
+            ret += self._int_to_word(int(left)) + " " + self.pointword + " "
+            for digit in right:
+                ret += self._int_to_word(int(digit)) + " "
+            return ret.strip()
+        else:
+            return (ret + self._int_to_word(int(n))).strip()
+
+    def _int_to_word(self, number):
+        """Convert an integer to its word representation in Occitan."""
+        if number == 0:
+            return self.ones[0] if self.ones[0] else "zero"
+
+        if number < 0:
+            return self.negword + self._int_to_word(abs(number))
+        elif number < 10:
+            return self.ones[number]
+        elif number < 100:
+            tens_val = number // 10
+            ones_val = number % 10
+            if ones_val == 0:
+                return self.tens[tens_val]
+            else:
+                return self.tens[tens_val] + " " + self.ones[ones_val]
+        elif number < 1000:
+            hundreds_val = number // 100
+            remainder = number % 100
+            result = self.ones[hundreds_val] + " " + self.hundred
+            if remainder:
+                result += " " + self._int_to_word(remainder)
+            return result
+        elif number < 1000000:
+            thousands_val = number // 1000
+            remainder = number % 1000
+            result = self._int_to_word(thousands_val) + " " + self.thousand
+            if remainder:
+                result += " " + self._int_to_word(remainder)
+            return result
+        elif number < 1000000000:
+            millions_val = number // 1000000
+            remainder = number % 1000000
+            result = self._int_to_word(millions_val) + " " + self.million
+            if remainder:
+                result += " " + self._int_to_word(remainder)
+            return result
+        else:
+            return str(number)  # Fallback for very large numbers
+
+    def to_ordinal(self, number):
+        """Convert to ordinal in Occitan."""
+        cardinal = self.to_cardinal(number)
+        # Language-specific ordinal suffix
+        return cardinal + "-en"
+
+    def to_ordinal_num(self, number):
+        """Convert to abbreviated ordinal."""
+        return str(number) + "."
+
+    def to_year(self, val, longval=True):
+        """Convert to year in Occitan."""
+        return self.to_cardinal(val)
+
+    def to_currency(self, val, currency='EUR', cents=True, separator=' ', adjective=False):
+        """Convert to currency in Occitan."""
+        is_negative = False
+        if val < 0:
+            is_negative = True
+            val = abs(val)
+
+        parts = str(val).split('.')
+        left = int(parts[0]) if parts[0] else 0
+        right = int(parts[1][:2].ljust(2, '0')) if len(parts) > 1 and parts[1] else 0
+
+        cr1, cr2 = self.CURRENCY_FORMS.get(currency, list(self.CURRENCY_FORMS.values())[0])
+
+        left_str = self._int_to_word(left)
+        result = left_str + " " + (cr1[1] if left != 1 else cr1[0])
+
+        if cents and right:
+            cents_str = self._int_to_word(right)
+            result += separator + cents_str + " " + (cr2[1] if right != 1 else cr2[0])
+
+        if is_negative:
+            result = self.negword + result
+
+        return result.strip()

num2words2/lang_PA.py

@@ -0,0 +1,159 @@
+# -*- 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
+
+from .base import Num2Word_Base
+
+
+# Punjabi language support
+class Num2Word_PA(Num2Word_Base):
+    CURRENCY_FORMS = {
+        'INR': (('ਰੁਪਈਆ', 'ਰੁਪਏ'), ('ਪੈਸਾ', 'ਪੈਸੇ')),
+        'USD': (('dollar', 'dollars'), ('cent', 'cents')),
+        'EUR': (('euro', 'euros'), ('cent', 'cents')),
+    }
+
+    def setup(self):
+        self.negword = "ਮਾਇਨਸ "
+        self.pointword = "ਦਸ਼ਮਲਵ"
+        self.ones = ['', 'ਇੱਕ', 'ਦੋ', 'ਤਿੰਨ', 'ਚਾਰ', 'ਪੰਜ', 'ਛੇ', 'ਸੱਤ', 'ਅੱਠ', 'ਨੌ']
+        self.tens = ['', 'ਦਸ', 'ਵੀਹ', 'ਤੀਹ', 'ਚਾਲੀ', 'ਪੰਜਾਹ', 'ਸੱਠ', 'ਸੱਤਰ', 'ਅੱਸੀ', 'ਨੱਬੇ']
+        self.teens = ['ਦਸ', 'ਗਿਆਰਾਂ', 'ਬਾਰਾਂ', 'ਤੇਰਾਂ', 'ਚੌਦਾਂ', 'ਪੰਦਰਾਂ', 'ਸੋਲਾਂ', 'ਸਤਾਰਾਂ', 'ਅਠਾਰਾਂ', 'ਉੱਨੀ']
+        self.hundred = "ਸੌ"
+        self.thousand = "ਹਜ਼ਾਰ"
+        self.lakh = "ਲੱਖ"
+        self.crore = "ਕਰੋੜ"
+        self.zero = "ਸਿਫਰ"
+
+    def to_cardinal(self, number):
+        """Convert a number to its word representation in Punjabi."""
+        n = str(number).strip()
+
+        if n.startswith('-'):
+            n = n[1:]
+            ret = self.negword
+        else:
+            ret = ""
+
+        if '.' in n:
+            left, right = n.split('.', 1)
+            ret += self._int_to_word(int(left)) + " " + self.pointword + " "
+            ret += " ".join(self._int_to_word(int(d)) for d in right)
+            return ret.strip()
+        else:
+            return (ret + self._int_to_word(int(n))).strip()
+
+    def _int_to_word(self, number):
+        """Convert an integer to its word representation in Punjabi."""
+        if number == 0:
+            return self.zero
+
+        if number < 0:
+            return self.negword + self._int_to_word(abs(number))
+        elif number < 10:
+            return self.ones[number]
+        elif number < 20:
+            return self.teens[number - 10]
+        elif number < 100:
+            result = self.tens[number // 10]
+            if number % 10:
+                result += " " + self.ones[number % 10]
+            return result
+        elif number < 1000:
+            result = self.ones[number // 100] + " " + self.hundred
+            remainder = number % 100
+            if remainder:
+                result += " " + self._int_to_word(remainder)
+            return result
+        elif number < 100000:  # Lakh
+            result = self._int_to_word(number // 1000) + " " + self.thousand
+            remainder = number % 1000
+            if remainder:
+                result += " " + self._int_to_word(remainder)
+            return result
+        elif number < 10000000:  # Crore
+            result = self._int_to_word(number // 100000) + " " + self.lakh
+            remainder = number % 100000
+            if remainder:
+                result += " " + self._int_to_word(remainder)
+            return result
+        elif number < 1000000000:
+            result = self._int_to_word(number // 10000000) + " " + self.crore
+            remainder = number % 10000000
+            if remainder:
+                result += " " + self._int_to_word(remainder)
+            return result
+        else:
+            return str(number)  # Fallback for very large numbers
+
+    def to_ordinal(self, number):
+        """Convert to ordinal in Punjabi.
+
+        Punjabi ordinals use 'ਵਾਂ' suffix for masculine and 'ਵੀਂ' for feminine.
+        Special forms exist for first few ordinals.
+        """
+        if number == 1:
+            return "ਪਹਿਲਾ"  # first
+        elif number == 2:
+            return "ਦੂਜਾ"  # second
+        elif number == 3:
+            return "ਤੀਜਾ"  # third
+        elif number == 4:
+            return "ਚੌਥਾ"  # fourth
+        elif number == 5:
+            return "ਪੰਜਵਾਂ"  # fifth
+        else:
+            # For other numbers, add ਵਾਂ suffix
+            cardinal = self.to_cardinal(number)
+            return cardinal + "ਵਾਂ"
+
+    def to_ordinal_num(self, number):
+        """Convert to abbreviated ordinal."""
+        return str(number) + "."
+
+    def to_year(self, val, longval=True):
+        """Convert to year in Punjabi."""
+        if val < 0:
+            return "BC " + self.to_cardinal(abs(val))
+        else:
+            return "" + self.to_cardinal(val)
+
+    def to_currency(self, val, currency='INR', cents=True, separator=' ', adjective=False):
+        """Convert to currency in Punjabi."""
+        is_negative = False
+        if val < 0:
+            is_negative = True
+            val = abs(val)
+
+        parts = str(val).split('.')
+        left = int(parts[0]) if parts[0] else 0
+        right = int(parts[1][:2].ljust(2, '0')) if len(parts) > 1 and parts[1] else 0
+
+        cr1, cr2 = self.CURRENCY_FORMS.get(currency, self.CURRENCY_FORMS['INR'])
+
+        left_str = self._int_to_word(left)
+        result = left_str + " " + (cr1[1] if left != 1 else cr1[0])
+
+        if cents and right:
+            cents_str = self._int_to_word(right)
+            result += separator + cents_str + " " + (cr2[1] if right != 1 else cr2[0])
+
+        if is_negative:
+            result = self.negword + result
+
+        return result.strip()

num2words2/lang_PL.py

@@ -0,0 +1,336 @@
+# -*- 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
+
+import itertools
+
+from .base import Num2Word_Base
+from .utils import get_digits, splitbyx
+
+ZERO = ('zero',)
+
+ONES = {
+    1: ('jeden',),
+    2: ('dwa',),
+    3: ('trzy',),
+    4: ('cztery',),
+    5: ('pięć',),
+    6: ('sześć',),
+    7: ('siedem',),
+    8: ('osiem',),
+    9: ('dziewięć',),
+}
+
+ONES_ORDINALS = {
+    1: ('pierwszy', "pierwszo"),
+    2: ('drugi', "dwu"),
+    3: ('trzeci', "trzy"),
+    4: ('czwarty', "cztero"),
+    5: ('piąty', "pięcio"),
+    6: ('szósty', "sześcio"),
+    7: ('siódmy', "siedmio"),
+    8: ('ósmy', "ośmio"),
+    9: ('dziewiąty', "dziewięcio"),
+    10: ('dziesiąty', "dziesięcio"),
+    11: ('jedenasty', "jedenasto"),
+    12: ('dwunasty', "dwunasto"),
+    13: ('trzynasty', "trzynasto"),
+    14: ('czternasty', "czternasto"),
+    15: ('piętnasty', "piętnasto"),
+    16: ('szesnasty', "szesnasto"),
+    17: ('siedemnasty', "siedemnasto"),
+    18: ('osiemnasty', "osiemnasto"),
+    19: ('dziewiętnasty', "dziewiętnasto"),
+}
+
+TENS = {
+    0: ('dziesięć',),
+    1: ('jedenaście',),
+    2: ('dwanaście',),
+    3: ('trzynaście',),
+    4: ('czternaście',),
+    5: ('piętnaście',),
+    6: ('szesnaście',),
+    7: ('siedemnaście',),
+    8: ('osiemnaście',),
+    9: ('dziewiętnaście',),
+}
+
+
+TWENTIES = {
+    2: ('dwadzieścia',),
+    3: ('trzydzieści',),
+    4: ('czterdzieści',),
+    5: ('pięćdziesiąt',),
+    6: ('sześćdziesiąt',),
+    7: ('siedemdziesiąt',),
+    8: ('osiemdziesiąt',),
+    9: ('dziewięćdziesiąt',),
+}
+
+TWENTIES_ORDINALS = {
+    2: ('dwudziesty', "dwudziesto"),
+    3: ('trzydziesty', "trzydiesto"),
+    4: ('czterdziesty', "czterdziesto"),
+    5: ('pięćdziesiąty', "pięćdziesięcio"),
+    6: ('sześćdziesiąty', "sześćdziesięcio"),
+    7: ('siedemdziesiąty', "siedemdziesięcio"),
+    8: ('osiemdziesiąty', "osiemdziesięcio"),
+    9: ('dziewięćdziesiąty', "dziewięćdziesięcio"),
+}
+
+HUNDREDS = {
+    1: ('sto',),
+    2: ('dwieście',),
+    3: ('trzysta',),
+    4: ('czterysta',),
+    5: ('pięćset',),
+    6: ('sześćset',),
+    7: ('siedemset',),
+    8: ('osiemset',),
+    9: ('dziewięćset',),
+}
+
+HUNDREDS_ORDINALS = {
+    1: ('setny', "stu"),
+    2: ('dwusetny', "dwustu"),
+    3: ('trzysetny', "trzystu"),
+    4: ('czterysetny', "czterystu"),
+    5: ('pięćsetny', "pięcset"),
+    6: ('sześćsetny', "sześćset"),
+    7: ('siedemsetny', "siedemset"),
+    8: ('osiemsetny', "ośiemset"),
+    9: ('dziewięćsetny', "dziewięćset"),
+}
+
+THOUSANDS = {
+    1: ('tysiąc', 'tysiące', 'tysięcy'),  # 10^3
+}
+
+prefixes_ordinal = {
+    1: "tysięczny",
+    2: "milionowy",
+    3: "milairdowy"
+}
+
+prefixes = (   # 10^(6*x)
+    "mi",      # 10^6
+    "bi",      # 10^12
+    "try",     # 10^18
+    "kwadry",  # 10^24
+    "kwinty",  # 10^30
+    "seksty",  # 10^36
+    "septy",   # 10^42
+    "okty",    # 10^48
+    "nony",    # 10^54
+    "decy"     # 10^60
+)
+suffixes = ("lion", "liard")  # 10^x or 10^(x+3)
+
+for idx, (p, s) in enumerate(itertools.product(prefixes, suffixes)):
+    name = p + s
+    THOUSANDS[idx + 2] = (name, name + 'y', name + 'ów')
+
+
+class Num2Word_PL(Num2Word_Base):
+    CURRENCY_FORMS = {
+        'PLN': (
+            ('złoty', 'złote', 'złotych'), ('grosz', 'grosze', 'groszy')
+        ),
+        'EUR': (
+            ('euro', 'euro', 'euro'), ('cent', 'centy', 'centów')
+        ),
+        'USD': (
+            (
+                'dolar amerykański',
+                'dolary amerykańskie',
+                'dolarów amerykańskich'
+            ),
+            (
+                'cent',
+                'centy',
+                'centów'
+            )
+        ),
+        'GBP': (
+            (
+                'funt brytyjski',
+                'funty brytyjskie',
+                'funtów brytyjskich'
+            ),
+            (
+                'pens',
+                'pensy',
+                'pensów'
+            )
+        ),
+    }
+
+    def setup(self):
+        self.negword = "minus"
+        self.pointword = "przecinek"
+
+    def to_cardinal(self, number):
+        n = str(number).replace(',', '.')
+        if '.' in n:
+            is_negative = n.startswith('-')
+            abs_n = n[1:] if is_negative else n
+            left, right = abs_n.split('.')
+
+            # Say each decimal digit individually
+            decimal_parts = []
+            for digit in right:
+                if digit == '0':
+                    decimal_parts.append(ZERO[0])
+                else:
+                    decimal_parts.append(ONES[int(digit)][0])
+            decimal_part = ' '.join(decimal_parts)
+
+            result = u'%s %s %s' % (
+                self._int2word(int(left)),
+                self.pointword,
+                decimal_part
+            )
+            if is_negative:
+                result = self.negword + ' ' + result
+            return result
+        else:
+            # Handle negative integers
+            is_negative = n.startswith('-')
+            if is_negative:
+                abs_n = n[1:]
+                result = self._int2word(int(abs_n))
+                return self.negword + ' ' + result
+            else:
+                return self._int2word(int(n))
+
+    def pluralize(self, n, forms):
+        if n == 1:
+            form = 0
+        elif 5 > n % 10 > 1 and (n % 100 < 10 or n % 100 > 20):
+            form = 1
+        else:
+            form = 2
+        return forms[form]
+
+    def last_fragment_to_ordinal(self, last, words, level):
+        n1, n2, n3 = get_digits(last)
+        last_two = n2 * 10 + n1
+        if last_two == 0:
+            words.append(HUNDREDS_ORDINALS[n3][level])
+        elif level == 1 and last == 1:
+            return
+        elif last_two < 20:
+            if n3 > 0:
+                words.append(HUNDREDS[n3][level])
+            words.append(ONES_ORDINALS[last_two][level])
+        elif last_two % 10 == 0:
+            if n3 > 0:
+                words.append(HUNDREDS[n3][level])
+            words.append(TWENTIES_ORDINALS[n2][level])
+        else:
+            if n3 > 0:
+                words.append(HUNDREDS[n3][0])
+            words.append(TWENTIES_ORDINALS[n2][0])
+            words.append(ONES_ORDINALS[n1][0])
+
+    def to_currency(self, val, currency='EUR', cents=True, separator=',',
+                    adjective=False):
+        # Handle integers specially - just add currency name without cents
+        if isinstance(val, int):
+            try:
+                cr1, cr2 = self.CURRENCY_FORMS[currency]
+            except (KeyError, AttributeError):
+                # Fallback to base implementation for unknown currency
+                return super(Num2Word_PL, self).to_currency(
+                    val, currency=currency, cents=cents, separator=separator,
+                    adjective=adjective)
+
+            minus_str = self.negword if val < 0 else ""
+            abs_val = abs(val)
+            money_str = self.to_cardinal(abs_val)
+
+            # For Polish, check if number ends with "jeden" (one)
+            # Numbers ending in compound "jeden" (like 21, 121, 10121) get special treatment
+            # They use the second form (nominative plural for 2-4)
+            if abs_val > 1 and money_str.endswith("jeden"):
+                # Use nominative plural form (2-4) for compound numbers ending with "jeden"
+                currency_str = cr1[1] if len(cr1) > 1 else cr1[0]
+            else:
+                # Use the pluralize method for proper currency form selection
+                currency_str = self.pluralize(abs_val, cr1)
+
+            return (u'%s %s %s' % (minus_str, money_str, currency_str)).strip()
+
+        # For floats, use the parent class implementation
+        return super(Num2Word_PL, self).to_currency(
+            val, currency=currency, cents=cents, separator=separator,
+            adjective=adjective)
+
+    def to_ordinal(self, number):
+        if number % 1 != 0:
+            raise NotImplementedError()
+        words = []
+        fragments = list(splitbyx(str(number), 3))
+        level = 0
+        last = fragments[-1]
+        while last == 0:
+            level = level + 1
+            fragments.pop()
+            last = fragments[-1]
+        if len(fragments) > 1:
+            pre_part = self._int2word(number - (last * 1000**level))
+            words.append(pre_part)
+        self.last_fragment_to_ordinal(last, words, 0 if level == 0 else 1)
+        output = " ".join(words)
+        if last == 1 and level > 0 and output != "":
+            output = output + " "
+        if level > 0:
+            output = output + prefixes_ordinal[level]
+        return output
+
+    def _int2word(self, n):
+        if n == 0:
+            return ZERO[0]
+
+        words = []
+        chunks = list(splitbyx(str(n), 3))
+        i = len(chunks)
+        for x in chunks:
+            i -= 1
+
+            if x == 0:
+                continue
+
+            n1, n2, n3 = get_digits(x)
+
+            if n3 > 0:
+                words.append(HUNDREDS[n3][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(self.pluralize(x, THOUSANDS[i]))
+
+        return ' '.join(words)