Source code for abydos.stemmer._snowball_norwegian

# Copyright 2014-2020 by Christopher C. Little.
# This file is part of Abydos.
# Abydos is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
# Abydos is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with Abydos. If not, see <>.


Snowball Norwegian stemmer

from unicodedata import normalize

from deprecation import deprecated

from ._snowball import _Snowball
from .. import __version__

__all__ = ['SnowballNorwegian', 'sb_norwegian']

[docs]class SnowballNorwegian(_Snowball): """Snowball Norwegian stemmer. The Snowball Norwegian stemmer is defined at: .. versionadded:: 0.3.6 """ _vowels = {'a', 'e', 'i', 'o', 'u', 'y', 'å', 'æ', 'ø'} _s_endings = { 'b', 'c', 'd', 'f', 'g', 'h', 'j', 'l', 'm', 'n', 'o', 'p', 'r', 't', 'v', 'y', 'z', }
[docs] def stem(self, word): """Return Snowball Norwegian stem. Parameters ---------- word : str The word to stem Returns ------- str Word stem Examples -------- >>> stmr = SnowballNorwegian() >>> stmr.stem('lese') 'les' >>> stmr.stem('suspensjon') 'suspensjon' >>> stmr.stem('sikkerhet') 'sikker' .. versionadded:: 0.1.0 .. versionchanged:: 0.3.6 Encapsulated in class """ # lowercase, normalize, and compose word = normalize('NFC', word.lower()) r1_start = min(max(3, self._sb_r1(word)), len(word)) # Step 1 _r1 = word[r1_start:] if _r1[-7:] == 'hetenes': word = word[:-7] elif _r1[-6:] in {'hetene', 'hetens'}: word = word[:-6] elif _r1[-5:] in {'heten', 'heter', 'endes'}: word = word[:-5] elif _r1[-4:] in {'ande', 'ende', 'edes', 'enes', 'erte'}: if word[-4:] == 'erte': word = word[:-2] else: word = word[:-4] elif _r1[-3:] in { 'ede', 'ane', 'ene', 'ens', 'ers', 'ets', 'het', 'ast', 'ert', }: if word[-3:] == 'ert': word = word[:-1] else: word = word[:-3] elif _r1[-2:] in {'en', 'ar', 'er', 'as', 'es', 'et'}: word = word[:-2] elif _r1[-1:] in {'a', 'e'}: word = word[:-1] elif _r1[-1:] == 's': if (len(word) > 1 and word[-2] in self._s_endings) or ( len(word) > 2 and word[-2] == 'k' and word[-3] not in self._vowels ): word = word[:-1] # Step 2 if word[r1_start:][-2:] in {'dt', 'vt'}: word = word[:-1] # Step 3 _r1 = word[r1_start:] if _r1[-7:] == 'hetslov': word = word[:-7] elif _r1[-4:] in {'eleg', 'elig', 'elov', 'slov'}: word = word[:-4] elif _r1[-3:] in {'leg', 'eig', 'lig', 'els', 'lov'}: word = word[:-3] elif _r1[-2:] == 'ig': word = word[:-2] return word
[docs]@deprecated( deprecated_in='0.4.0', removed_in='0.6.0', current_version=__version__, details='Use the SnowballNorwegian.stem method instead.', ) def sb_norwegian(word): """Return Snowball Norwegian stem. This is a wrapper for :py:meth:`SnowballNorwegian.stem`. Parameters ---------- word : str The word to stem Returns ------- str Word stem Examples -------- >>> sb_norwegian('lese') 'les' >>> sb_norwegian('suspensjon') 'suspensjon' >>> sb_norwegian('sikkerhet') 'sikker' .. versionadded:: 0.1.0 """ return SnowballNorwegian().stem(word)
if __name__ == '__main__': import doctest doctest.testmod()