abydos.stemmer._snowball_dutch.SnowballDutch._undouble() - Code Metrics - Inspection of "0.3.6" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#141)

by Chris

created 2018-11-10 03:25 UTC

SnowballDutch._undouble() A

↳ Parent: abydos.stemmer._snowball_dutch

Complexity

Conditions

Size

Total Lines	17
Code Lines	7

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	4
CRAP Score	4

Importance

Changes

Metric	Value
cc	4
eloc	7
nop	2
dl	0
loc	17
ccs	4
cts	4
cp	1
crap	4
rs	10
c	0
b	0
f	0

# -*- coding: utf-8 -*-

# Copyright 2014-2018 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
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# 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 <http://www.gnu.org/licenses/>.

"""abydos.stemmer._snowball_dutch.

Snowball Dutch stemmer
"""

from __future__ import (
    absolute_import,
    division,
    print_function,
    unicode_literals,
)

from unicodedata import normalize

from six import text_type
from six.moves import range

from ._snowball import _Snowball

__all__ = ['SnowballDutch', 'sb_dutch']


class SnowballDutch(_Snowball):

    """Snowball Dutch stemmer.

    The Snowball Dutch stemmer is defined at:
    http://snowball.tartarus.org/algorithms/dutch/stemmer.html
    """

    _vowels = {'a', 'e', 'i', 'o', 'u', 'y', 'è'}
    _not_s_endings = {'a', 'e', 'i', 'j', 'o', 'u', 'y', 'è'}
    _accented = dict(zip((ord(_) for _ in 'äëïöüáéíóú'), 'aeiouaeiou'))


    def _undouble(self, word):
class Foo:
    def some_method(self, x, y):
        return x + y;
        """Undouble endings -kk, -dd, and -tt.

        Args:
            word (str): The word to stem

        Returns:
            str: The word with doubled endings undoubled

        """
        if (
            len(word) > 1

            and word[-1] == word[-2]

            and word[-1] in {'d', 'k', 't'}

        ):
            return word[:-1]
        return word

    def stem(self, word):

        """Return Snowball Dutch stem.

        Args:
            word (str): The word to stem

        Returns:
            str: Word stem

        Examples:
            >>> stmr = SnowballDutch()
            >>> stmr.stem('lezen')
            'lez'
            >>> stmr.stem('opschorting')
            'opschort'
            >>> stmr.stem('ongrijpbaarheid')
            'ongrijp'

        """
        # lowercase, normalize, decompose, filter umlauts & acutes out, and
        # compose
        word = normalize('NFC', text_type(word.lower()))
        word = word.translate(self._accented)

        for i in range(len(word)):

            if i == 0 and word[0] == 'y':
                word = 'Y' + word[1:]
            elif word[i] == 'y' and word[i - 1] in self._vowels:
                word = word[:i] + 'Y' + word[i + 1 :]
            elif (
                word[i] == 'i'

                and word[i - 1] in self._vowels

                and i + 1 < len(word)

                and word[i + 1] in self._vowels

            ):
                word = word[:i] + 'I' + word[i + 1 :]

        r1_start = max(3, self._sb_r1(word))
        r2_start = self._sb_r2(word)

        # Step 1
        if word[-5:] == 'heden':
            if len(word[r1_start:]) >= 5:
                word = word[:-3] + 'id'
        elif word[-3:] == 'ene':
            if len(word[r1_start:]) >= 3 and (
                word[-4] not in self._vowels and word[-6:-3] != 'gem'

            ):
                word = self._undouble(word[:-3])
        elif word[-2:] == 'en':
            if len(word[r1_start:]) >= 2 and (
                word[-3] not in self._vowels and word[-5:-2] != 'gem'

            ):
                word = self._undouble(word[:-2])
        elif word[-2:] == 'se':
            if (
                len(word[r1_start:]) >= 2

                and word[-3] not in self._not_s_endings

            ):
                word = word[:-2]
        elif word[-1:] == 's':
            if (
                len(word[r1_start:]) >= 1

                and word[-2] not in self._not_s_endings

            ):
                word = word[:-1]

        # Step 2
        e_removed = False
        if word[-1:] == 'e':
            if len(word[r1_start:]) >= 1 and word[-2] not in self._vowels:
                word = self._undouble(word[:-1])
                e_removed = True

        # Step 3a
        if word[-4:] == 'heid':
            if len(word[r2_start:]) >= 4 and word[-5] != 'c':
                word = word[:-4]
                if word[-2:] == 'en':
                    if len(word[r1_start:]) >= 2 and (
                        word[-3] not in self._vowels and word[-5:-2] != 'gem'

                    ):
                        word = self._undouble(word[:-2])

        # Step 3b
        if word[-4:] == 'lijk':
            if len(word[r2_start:]) >= 4:
                word = word[:-4]
                # Repeat step 2
                if word[-1:] == 'e':
                    if (
                        len(word[r1_start:]) >= 1

                        and word[-2] not in self._vowels

                    ):
                        word = self._undouble(word[:-1])
        elif word[-4:] == 'baar':
            if len(word[r2_start:]) >= 4:
                word = word[:-4]
        elif word[-3:] in ('end', 'ing'):
            if len(word[r2_start:]) >= 3:
                word = word[:-3]
                if (
                    word[-2:] == 'ig'

                    and len(word[r2_start:]) >= 2

                    and word[-3] != 'e'

                ):
                    word = word[:-2]
                else:
                    word = self._undouble(word)
        elif word[-3:] == 'bar':
            if len(word[r2_start:]) >= 3 and e_removed:
                word = word[:-3]
        elif word[-2:] == 'ig':
            if len(word[r2_start:]) >= 2 and word[-3] != 'e':
                word = word[:-2]

        # Step 4
        if (
            len(word) >= 4

            and word[-3] == word[-2]

            and word[-2] in {'a', 'e', 'o', 'u'}

            and word[-4] not in self._vowels

            and word[-1] not in self._vowels

            and word[-1] != 'I'

        ):
            word = word[:-2] + word[-1]

        # Change 'Y' and 'U' back to lowercase if survived stemming
        for i in range(0, len(word)):
            if word[i] == 'Y':
                word = word[:i] + 'y' + word[i + 1 :]
            elif word[i] == 'I':
                word = word[:i] + 'i' + word[i + 1 :]

        return word


def sb_dutch(word):
    """Return Snowball Dutch stem.

    This is a wrapper for :py:meth:`SnowballDutch.stem`.

    Args:
        word (str): The word to stem

    Returns:
        str: Word stem

    Examples:
        >>> sb_dutch('lezen')
        'lez'
        >>> sb_dutch('opschorting')
        'opschort'
        >>> sb_dutch('ongrijpbaarheid')
        'ongrijp'

    """
    return SnowballDutch().stem(word)


if __name__ == '__main__':
    import doctest

    doctest.testmod()


1		# -- coding: utf-8 --
2
3		# Copyright 2014-2018 by Christopher C. Little.
4		# This file is part of Abydos.
5		#
6		# Abydos is free software: you can redistribute it and/or modify
7		# it under the terms of the GNU General Public License as published by
8		# the Free Software Foundation, either version 3 of the License, or
9		# (at your option) any later version.
10		#
11		# Abydos is distributed in the hope that it will be useful,
12		# but WITHOUT ANY WARRANTY; without even the implied warranty of
13		# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14		# GNU General Public License for more details.
15		#
16		# You should have received a copy of the GNU General Public License
17		# along with Abydos. If not, see <http://www.gnu.org/licenses/>.
18
19	1	"""abydos.stemmer._snowball_dutch.
20
21		Snowball Dutch stemmer
22		"""
23
24	1	from __future__ import (
25		absolute_import,
26		division,
27		print_function,
28		unicode_literals,
29		)
30
31	1	from unicodedata import normalize
32
33	1	from six import text_type
34	1	from six.moves import range
35
36	1	from ._snowball import _Snowball
37
38	1	__all__ = ['SnowballDutch', 'sb_dutch']
39
40
41	1	class SnowballDutch(_Snowball):
		0 ignored issues – show Unused Code introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report The variable `__class__` seems to be unused. Loading history...
42		"""Snowball Dutch stemmer.
43
44		The Snowball Dutch stemmer is defined at:
45		http://snowball.tartarus.org/algorithms/dutch/stemmer.html
46		"""
47
48	1	_vowels = {'a', 'e', 'i', 'o', 'u', 'y', 'è'}
49	1	_not_s_endings = {'a', 'e', 'i', 'j', 'o', 'u', 'y', 'è'}
50	1	_accented = dict(zip((ord(_) for _ in 'äëïöüáéíóú'), 'aeiouaeiou'))
		0 ignored issues – show Comprehensibility Best Practice introduced 2018-08-02 19:04 UTC by Report Bug Copy Issue Report The variable `_` does not seem to be defined. Loading history...
51
52	1	def _undouble(self, word):
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report This method could be written as a function/class method. If a method does not access any attributes of the class, it could also be implemented as a function or static method. This can help improve readability. For example class Foo: def some_method(self, x, y): return x + y; could be written as class Foo: @classmethod def some_method(cls, x, y): return x + y; Loading history...
53		"""Undouble endings -kk, -dd, and -tt.
54
55		Args:
56		word (str): The word to stem
57
58		Returns:
59		str: The word with doubled endings undoubled
60
61		"""
62	1	if (
63		len(word) > 1
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
64		and word[-1] == word[-2]
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
65		and word[-1] in {'d', 'k', 't'}
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
66		):
67	1	return word[:-1]
68	1	return word
69
70	1	def stem(self, word):
		0 ignored issues – show Bug introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Parameters differ from overridden 'stem' method Loading history...
71		"""Return Snowball Dutch stem.
72
73		Args:
74		word (str): The word to stem
75
76		Returns:
77		str: Word stem
78
79		Examples:
80		>>> stmr = SnowballDutch()
81		>>> stmr.stem('lezen')
82		'lez'
83		>>> stmr.stem('opschorting')
84		'opschort'
85		>>> stmr.stem('ongrijpbaarheid')
86		'ongrijp'
87
88		"""
89		# lowercase, normalize, decompose, filter umlauts & acutes out, and
90		# compose
91	1	word = normalize('NFC', text_type(word.lower()))
92	1	word = word.translate(self._accented)
93
94	1	for i in range(len(word)):
		0 ignored issues – show unused-code introduced 2018-08-02 19:04 UTC by Report Bug Copy Issue Report Consider using enumerate instead of iterating with range and len Loading history...
95	1	if i == 0 and word[0] == 'y':
96	1	word = 'Y' + word[1:]
97	1	elif word[i] == 'y' and word[i - 1] in self._vowels:
98	1	word = word[:i] + 'Y' + word[i + 1 :]
99	1	elif (
100		word[i] == 'i'
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
101		and word[i - 1] in self._vowels
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
102		and i + 1 < len(word)
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
103		and word[i + 1] in self._vowels
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
104		):
105	1	word = word[:i] + 'I' + word[i + 1 :]
106
107	1	r1_start = max(3, self._sb_r1(word))
108	1	r2_start = self._sb_r2(word)
109
110		# Step 1
111	1	if word[-5:] == 'heden':
112	1	if len(word[r1_start:]) >= 5:
113	1	word = word[:-3] + 'id'
114	1	elif word[-3:] == 'ene':
115	1	if len(word[r1_start:]) >= 3 and (
116		word[-4] not in self._vowels and word[-6:-3] != 'gem'
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
117		):
118	1	word = self._undouble(word[:-3])
119	1	elif word[-2:] == 'en':
120	1	if len(word[r1_start:]) >= 2 and (
121		word[-3] not in self._vowels and word[-5:-2] != 'gem'
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
122		):
123	1	word = self._undouble(word[:-2])
124	1	elif word[-2:] == 'se':
125	1	if (
126		len(word[r1_start:]) >= 2
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
127		and word[-3] not in self._not_s_endings
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
128		):
129	1	word = word[:-2]
130	1	elif word[-1:] == 's':
131	1	if (
132		len(word[r1_start:]) >= 1
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
133		and word[-2] not in self._not_s_endings
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
134		):
135	1	word = word[:-1]
136
137		# Step 2
138	1	e_removed = False
139	1	if word[-1:] == 'e':
140	1	if len(word[r1_start:]) >= 1 and word[-2] not in self._vowels:
141	1	word = self._undouble(word[:-1])
142	1	e_removed = True
143
144		# Step 3a
145	1	if word[-4:] == 'heid':
146	1	if len(word[r2_start:]) >= 4 and word[-5] != 'c':
147	1	word = word[:-4]
148	1	if word[-2:] == 'en':
149	1	if len(word[r1_start:]) >= 2 and (
150		word[-3] not in self._vowels and word[-5:-2] != 'gem'
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
151		):
152	1	word = self._undouble(word[:-2])
153
154		# Step 3b
155	1	if word[-4:] == 'lijk':
156	1	if len(word[r2_start:]) >= 4:
157	1	word = word[:-4]
158		# Repeat step 2
159	1	if word[-1:] == 'e':
160	1	if (
161		len(word[r1_start:]) >= 1
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
162		and word[-2] not in self._vowels
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
163		):
164	1	word = self._undouble(word[:-1])
165	1	elif word[-4:] == 'baar':
166	1	if len(word[r2_start:]) >= 4:
167	1	word = word[:-4]
168	1	elif word[-3:] in ('end', 'ing'):
169	1	if len(word[r2_start:]) >= 3:
170	1	word = word[:-3]
171	1	if (
172		word[-2:] == 'ig'
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
173		and len(word[r2_start:]) >= 2
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
174		and word[-3] != 'e'
		0 ignored issues – show Coding Style introduced 2018-11-05 04:21 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
175		):
176	1	word = word[:-2]
177		else:
178	1	word = self._undouble(word)
179	1	elif word[-3:] == 'bar':
180	1	if len(word[r2_start:]) >= 3 and e_removed:
181	1	word = word[:-3]
182	1	elif word[-2:] == 'ig':
183	1	if len(word[r2_start:]) >= 2 and word[-3] != 'e':
184	1	word = word[:-2]
185
186		# Step 4
187	1	if (
188		len(word) >= 4
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history... best-practice introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Too many boolean expressions in if statement (6/5) Loading history...
189		and word[-3] == word[-2]
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
190		and word[-2] in {'a', 'e', 'o', 'u'}
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
191		and word[-4] not in self._vowels
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
192		and word[-1] not in self._vowels
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
193		and word[-1] != 'I'
		0 ignored issues – show Coding Style introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
194		):
195	1	word = word[:-2] + word[-1]
196
197		# Change 'Y' and 'U' back to lowercase if survived stemming
198	1	for i in range(0, len(word)):
199	1	if word[i] == 'Y':
200	1	word = word[:i] + 'y' + word[i + 1 :]
201	1	elif word[i] == 'I':
202	1	word = word[:i] + 'i' + word[i + 1 :]
203
204	1	return word
205
206
207	1	def sb_dutch(word):
208		"""Return Snowball Dutch stem.
209
210		This is a wrapper for :py:meth:`SnowballDutch.stem`.
211
212		Args:
213		word (str): The word to stem
214
215		Returns:
216		str: Word stem
217
218		Examples:
219		>>> sb_dutch('lezen')
220		'lez'
221		>>> sb_dutch('opschorting')
222		'opschort'
223		>>> sb_dutch('ongrijpbaarheid')
224		'ongrijp'
225
226		"""
227	1	return SnowballDutch().stem(word)
228
229
230		if __name__ == '__main__':
231		import doctest
232
233		doctest.testmod()
234

chrislit / abydos

Pull Request — master (#141)

SnowballDutch._undouble() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like