abydos.stemmer._porter.Porter._ends_in_cvc() - Code Metrics - Inspection of "Merge pull request #149 from chrislit/0.3.6" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( f43547...71985b )

by Chris

created 2018-11-17 08:52 UTC

abydos.stemmer._porter.Porter._ends_in_cvc() A

↳ Parent: abydos.stemmer._porter

Complexity

Conditions

Size

Total Lines	20
Code Lines	6

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

Metric	Value
cc	1
eloc	6
nop	2
dl	0
loc	20
ccs	2
cts	2
cp	1
crap	1
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._porter.

Porter 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 ._stemmer import _Stemmer

__all__ = ['Porter', 'porter']


class Porter(_Stemmer):

    """Porter stemmer.

    The Porter stemmer is described in :cite:`Porter:1980`.
    """

    _vowels = {'a', 'e', 'i', 'o', 'u', 'y'}

    def _m_degree(self, term):
        """Return Porter helper function _m_degree value.

        m-degree is equal to the number of V to C transitions

        Parameters
        ----------
        term : str
            The word for which to calculate the m-degree

        Returns
        -------
        int
            The m-degree as defined in the Porter stemmer definition

        """
        mdeg = 0
        last_was_vowel = False
        for letter in term:
            if letter in self._vowels:
                last_was_vowel = True
            else:
                if last_was_vowel:
                    mdeg += 1
                last_was_vowel = False
        return mdeg

    def _has_vowel(self, term):
        """Return Porter helper function _has_vowel value.

        Parameters
        ----------
        term : str
            The word to scan for vowels

        Returns
        -------
        bool
            True iff a vowel exists in the term (as defined in the Porter
            stemmer definition)

        """
        for letter in term:
            if letter in self._vowels:
                return True
        return False

    def _ends_in_doubled_cons(self, term):
        """Return Porter helper function _ends_in_doubled_cons value.

        Parameters
        ----------
        term : str
            The word to check for a final doubled consonant

        Returns
        -------
        bool
            True iff the stem ends in a doubled consonant (as defined in the
            Porter stemmer definition)

        """
        return (
            len(term) > 1
            and term[-1] not in self._vowels
            and term[-2] == term[-1]
        )

    def _ends_in_cvc(self, term):
        """Return Porter helper function _ends_in_cvc value.

        Parameters
        ----------
        term : str
            The word to scan for cvc

        Returns
        -------
        bool
            True iff the stem ends in cvc (as defined in the Porter stemmer
            definition)

        """
        return len(term) > 2 and (
            term[-1] not in self._vowels
            and term[-2] in self._vowels
            and term[-3] not in self._vowels
            and term[-1] not in tuple('wxY')
        )

    def stem(self, word, early_english=False):

        """Return Porter stem.

        Parameters
        ----------
        word : str
            The word to stem
        early_english : bool
            Set to True in order to remove -eth & -est (2nd & 3rd person
            singular verbal agreement suffixes)

        Returns
        -------
        str
            Word stem

        Examples
        --------
        >>> stmr = Porter()
        >>> stmr.stem('reading')
        'read'
        >>> stmr.stem('suspension')
        'suspens'
        >>> stmr.stem('elusiveness')
        'elus'

        >>> stmr.stem('eateth', early_english=True)
        'eat'

        """
        # lowercase, normalize, and compose
        word = normalize('NFC', text_type(word.lower()))

        # Return word if stem is shorter than 2
        if len(word) < 3:
            return word

        # Re-map consonantal y to Y (Y will be C, y will be V)
        if word[0] == 'y':
            word = 'Y' + word[1:]
        for i in range(1, len(word)):
            if word[i] == 'y' and word[i - 1] in self._vowels:
                word = word[:i] + 'Y' + word[i + 1 :]

        # Step 1a
        if word[-1] == 's':
            if word[-4:] == 'sses':
                word = word[:-2]
            elif word[-3:] == 'ies':
                word = word[:-2]
            elif word[-2:] == 'ss':
                pass
            else:
                word = word[:-1]

        # Step 1b
        step1b_flag = False
        if word[-3:] == 'eed':
            if self._m_degree(word[:-3]) > 0:
                word = word[:-1]
        elif word[-2:] == 'ed':
            if self._has_vowel(word[:-2]):
                word = word[:-2]
                step1b_flag = True
        elif word[-3:] == 'ing':
            if self._has_vowel(word[:-3]):
                word = word[:-3]
                step1b_flag = True
        elif early_english:
            if word[-3:] == 'est':
                if self._has_vowel(word[:-3]):
                    word = word[:-3]
                    step1b_flag = True
            elif word[-3:] == 'eth':
                if self._has_vowel(word[:-3]):
                    word = word[:-3]
                    step1b_flag = True

        if step1b_flag:
            if word[-2:] in {'at', 'bl', 'iz'}:
                word += 'e'
            elif self._ends_in_doubled_cons(word) and word[-1] not in {
                'l',

                's',

                'z',

            }:
                word = word[:-1]
            elif self._m_degree(word) == 1 and self._ends_in_cvc(word):
                word += 'e'

        # Step 1c
        if word[-1] in {'Y', 'y'} and self._has_vowel(word[:-1]):
            word = word[:-1] + 'i'

        # Step 2
        if len(word) > 1:
            if word[-2] == 'a':
                if word[-7:] == 'ational':
                    if self._m_degree(word[:-7]) > 0:
                        word = word[:-5] + 'e'
                elif word[-6:] == 'tional':
                    if self._m_degree(word[:-6]) > 0:
                        word = word[:-2]
            elif word[-2] == 'c':
                if word[-4:] in {'enci', 'anci'}:
                    if self._m_degree(word[:-4]) > 0:
                        word = word[:-1] + 'e'
            elif word[-2] == 'e':
                if word[-4:] == 'izer':
                    if self._m_degree(word[:-4]) > 0:
                        word = word[:-1]
            elif word[-2] == 'g':
                if word[-4:] == 'logi':
                    if self._m_degree(word[:-4]) > 0:
                        word = word[:-1]
            elif word[-2] == 'l':
                if word[-3:] == 'bli':
                    if self._m_degree(word[:-3]) > 0:
                        word = word[:-1] + 'e'
                elif word[-4:] == 'alli':
                    if self._m_degree(word[:-4]) > 0:
                        word = word[:-2]
                elif word[-5:] == 'entli':
                    if self._m_degree(word[:-5]) > 0:
                        word = word[:-2]
                elif word[-3:] == 'eli':
                    if self._m_degree(word[:-3]) > 0:
                        word = word[:-2]
                elif word[-5:] == 'ousli':
                    if self._m_degree(word[:-5]) > 0:
                        word = word[:-2]
            elif word[-2] == 'o':
                if word[-7:] == 'ization':
                    if self._m_degree(word[:-7]) > 0:
                        word = word[:-5] + 'e'
                elif word[-5:] == 'ation':
                    if self._m_degree(word[:-5]) > 0:
                        word = word[:-3] + 'e'
                elif word[-4:] == 'ator':
                    if self._m_degree(word[:-4]) > 0:
                        word = word[:-2] + 'e'
            elif word[-2] == 's':
                if word[-5:] == 'alism':
                    if self._m_degree(word[:-5]) > 0:
                        word = word[:-3]
                elif word[-7:] in {'iveness', 'fulness', 'ousness'}:
                    if self._m_degree(word[:-7]) > 0:
                        word = word[:-4]
            elif word[-2] == 't':
                if word[-5:] == 'aliti':
                    if self._m_degree(word[:-5]) > 0:
                        word = word[:-3]
                elif word[-5:] == 'iviti':
                    if self._m_degree(word[:-5]) > 0:
                        word = word[:-3] + 'e'
                elif word[-6:] == 'biliti':
                    if self._m_degree(word[:-6]) > 0:
                        word = word[:-5] + 'le'

        # Step 3
        if word[-5:] in 'icate':
            if self._m_degree(word[:-5]) > 0:
                word = word[:-3]
        elif word[-5:] == 'ative':
            if self._m_degree(word[:-5]) > 0:
                word = word[:-5]
        elif word[-5:] in {'alize', 'iciti'}:
            if self._m_degree(word[:-5]) > 0:
                word = word[:-3]
        elif word[-4:] == 'ical':
            if self._m_degree(word[:-4]) > 0:
                word = word[:-2]
        elif word[-3:] == 'ful':
            if self._m_degree(word[:-3]) > 0:
                word = word[:-3]
        elif word[-4:] == 'ness':
            if self._m_degree(word[:-4]) > 0:
                word = word[:-4]

        # Step 4
        if word[-2:] == 'al':
            if self._m_degree(word[:-2]) > 1:
                word = word[:-2]
        elif word[-4:] in {'ance', 'ence'}:
            if self._m_degree(word[:-4]) > 1:
                word = word[:-4]
        elif word[-2:] in {'er', 'ic'}:
            if self._m_degree(word[:-2]) > 1:
                word = word[:-2]
        elif word[-4:] in {'able', 'ible'}:
            if self._m_degree(word[:-4]) > 1:
                word = word[:-4]
        elif word[-3:] == 'ant':
            if self._m_degree(word[:-3]) > 1:
                word = word[:-3]
        elif word[-5:] == 'ement':
            if self._m_degree(word[:-5]) > 1:
                word = word[:-5]
        elif word[-4:] == 'ment':
            if self._m_degree(word[:-4]) > 1:
                word = word[:-4]
        elif word[-3:] == 'ent':
            if self._m_degree(word[:-3]) > 1:
                word = word[:-3]
        elif word[-4:] in {'sion', 'tion'}:
            if self._m_degree(word[:-3]) > 1:
                word = word[:-3]
        elif word[-2:] == 'ou':
            if self._m_degree(word[:-2]) > 1:
                word = word[:-2]
        elif word[-3:] in {'ism', 'ate', 'iti', 'ous', 'ive', 'ize'}:
            if self._m_degree(word[:-3]) > 1:
                word = word[:-3]

        # Step 5a
        if word[-1] == 'e':
            if self._m_degree(word[:-1]) > 1:
                word = word[:-1]
            elif self._m_degree(word[:-1]) == 1 and not self._ends_in_cvc(
                word[:-1]

            ):
                word = word[:-1]

        # Step 5b
        if word[-2:] == 'll' and self._m_degree(word) > 1:
            word = word[:-1]

        # Change 'Y' back to 'y' if it survived stemming
        for i in range(len(word)):

            if word[i] == 'Y':
                word = word[:i] + 'y' + word[i + 1 :]

        return word


def porter(word, early_english=False):
    """Return Porter stem.

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

    Parameters
    ----------
    word : str
        The word to stem
    early_english : bool
        Set to True in order to remove -eth & -est (2nd & 3rd person singular
        verbal agreement suffixes)

    Returns
    -------
    str
        Word stem

    Examples
    --------
    >>> porter('reading')
    'read'
    >>> porter('suspension')
    'suspens'
    >>> porter('elusiveness')
    'elus'

    >>> porter('eateth', early_english=True)
    'eat'

    """
    return Porter().stem(word, early_english)


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._porter.
20
21		Porter 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 ._stemmer import _Stemmer
37
38	1	__all__ = ['Porter', 'porter']
39
40
41	1	class Porter(_Stemmer):
		0 ignored issues – show Unused Code introduced 2018-11-10 01:42 UTC by Report Bug Copy Issue Report The variable `__class__` seems to be unused. Loading history...
42		"""Porter stemmer.
43
44		The Porter stemmer is described in :cite:`Porter:1980`.
45		"""
46
47	1	_vowels = {'a', 'e', 'i', 'o', 'u', 'y'}
48
49	1	def _m_degree(self, term):
50		"""Return Porter helper function _m_degree value.
51
52		m-degree is equal to the number of V to C transitions
53
54		Parameters
55		----------
56		term : str
57		The word for which to calculate the m-degree
58
59		Returns
60		-------
61		int
62		The m-degree as defined in the Porter stemmer definition
63
64		"""
65	1	mdeg = 0
66	1	last_was_vowel = False
67	1	for letter in term:
68	1	if letter in self._vowels:
69	1	last_was_vowel = True
70		else:
71	1	if last_was_vowel:
72	1	mdeg += 1
73	1	last_was_vowel = False
74	1	return mdeg
75
76	1	def _has_vowel(self, term):
77		"""Return Porter helper function _has_vowel value.
78
79		Parameters
80		----------
81		term : str
82		The word to scan for vowels
83
84		Returns
85		-------
86		bool
87		True iff a vowel exists in the term (as defined in the Porter
88		stemmer definition)
89
90		"""
91	1	for letter in term:
92	1	if letter in self._vowels:
93	1	return True
94	1	return False
95
96	1	def _ends_in_doubled_cons(self, term):
97		"""Return Porter helper function _ends_in_doubled_cons value.
98
99		Parameters
100		----------
101		term : str
102		The word to check for a final doubled consonant
103
104		Returns
105		-------
106		bool
107		True iff the stem ends in a doubled consonant (as defined in the
108		Porter stemmer definition)
109
110		"""
111	1	return (
112		len(term) > 1
113		and term[-1] not in self._vowels
114		and term[-2] == term[-1]
115		)
116
117	1	def _ends_in_cvc(self, term):
118		"""Return Porter helper function _ends_in_cvc value.
119
120		Parameters
121		----------
122		term : str
123		The word to scan for cvc
124
125		Returns
126		-------
127		bool
128		True iff the stem ends in cvc (as defined in the Porter stemmer
129		definition)
130
131		"""
132	1	return len(term) > 2 and (
133		term[-1] not in self._vowels
134		and term[-2] in self._vowels
135		and term[-3] not in self._vowels
136		and term[-1] not in tuple('wxY')
137		)
138
139	1	def stem(self, word, early_english=False):
		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...
140		"""Return Porter stem.
141
142		Parameters
143		----------
144		word : str
145		The word to stem
146		early_english : bool
147		Set to True in order to remove -eth & -est (2nd & 3rd person
148		singular verbal agreement suffixes)
149
150		Returns
151		-------
152		str
153		Word stem
154
155		Examples
156		--------
157		>>> stmr = Porter()
158		>>> stmr.stem('reading')
159		'read'
160		>>> stmr.stem('suspension')
161		'suspens'
162		>>> stmr.stem('elusiveness')
163		'elus'
164
165		>>> stmr.stem('eateth', early_english=True)
166		'eat'
167
168		"""
169		# lowercase, normalize, and compose
170	1	word = normalize('NFC', text_type(word.lower()))
171
172		# Return word if stem is shorter than 2
173	1	if len(word) < 3:
174	1	return word
175
176		# Re-map consonantal y to Y (Y will be C, y will be V)
177	1	if word[0] == 'y':
178	1	word = 'Y' + word[1:]
179	1	for i in range(1, len(word)):
180	1	if word[i] == 'y' and word[i - 1] in self._vowels:
181	1	word = word[:i] + 'Y' + word[i + 1 :]
182
183		# Step 1a
184	1	if word[-1] == 's':
185	1	if word[-4:] == 'sses':
186	1	word = word[:-2]
187	1	elif word[-3:] == 'ies':
188	1	word = word[:-2]
189	1	elif word[-2:] == 'ss':
190	1	pass
191		else:
192	1	word = word[:-1]
193
194		# Step 1b
195	1	step1b_flag = False
196	1	if word[-3:] == 'eed':
197	1	if self._m_degree(word[:-3]) > 0:
198	1	word = word[:-1]
199	1	elif word[-2:] == 'ed':
200	1	if self._has_vowel(word[:-2]):
201	1	word = word[:-2]
202	1	step1b_flag = True
203	1	elif word[-3:] == 'ing':
204	1	if self._has_vowel(word[:-3]):
205	1	word = word[:-3]
206	1	step1b_flag = True
207	1	elif early_english:
208	1	if word[-3:] == 'est':
209	1	if self._has_vowel(word[:-3]):
210	1	word = word[:-3]
211	1	step1b_flag = True
212	1	elif word[-3:] == 'eth':
213	1	if self._has_vowel(word[:-3]):
214	1	word = word[:-3]
215	1	step1b_flag = True
216
217	1	if step1b_flag:
218	1	if word[-2:] in {'at', 'bl', 'iz'}:
219	1	word += 'e'
220	1	elif self._ends_in_doubled_cons(word) and word[-1] not in {
221		'l',
		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...
222		's',
		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...
223		'z',
		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...
224		}:
225	1	word = word[:-1]
226	1	elif self._m_degree(word) == 1 and self._ends_in_cvc(word):
227	1	word += 'e'
228
229		# Step 1c
230	1	if word[-1] in {'Y', 'y'} and self._has_vowel(word[:-1]):
231	1	word = word[:-1] + 'i'
232
233		# Step 2
234	1	if len(word) > 1:
235	1	if word[-2] == 'a':
236	1	if word[-7:] == 'ational':
237	1	if self._m_degree(word[:-7]) > 0:
238	1	word = word[:-5] + 'e'
239	1	elif word[-6:] == 'tional':
240	1	if self._m_degree(word[:-6]) > 0:
241	1	word = word[:-2]
242	1	elif word[-2] == 'c':
243	1	if word[-4:] in {'enci', 'anci'}:
244	1	if self._m_degree(word[:-4]) > 0:
245	1	word = word[:-1] + 'e'
246	1	elif word[-2] == 'e':
247	1	if word[-4:] == 'izer':
248	1	if self._m_degree(word[:-4]) > 0:
249	1	word = word[:-1]
250	1	elif word[-2] == 'g':
251	1	if word[-4:] == 'logi':
252	1	if self._m_degree(word[:-4]) > 0:
253	1	word = word[:-1]
254	1	elif word[-2] == 'l':
255	1	if word[-3:] == 'bli':
256	1	if self._m_degree(word[:-3]) > 0:
257	1	word = word[:-1] + 'e'
258	1	elif word[-4:] == 'alli':
259	1	if self._m_degree(word[:-4]) > 0:
260	1	word = word[:-2]
261	1	elif word[-5:] == 'entli':
262	1	if self._m_degree(word[:-5]) > 0:
263	1	word = word[:-2]
264	1	elif word[-3:] == 'eli':
265	1	if self._m_degree(word[:-3]) > 0:
266	1	word = word[:-2]
267	1	elif word[-5:] == 'ousli':
268	1	if self._m_degree(word[:-5]) > 0:
269	1	word = word[:-2]
270	1	elif word[-2] == 'o':
271	1	if word[-7:] == 'ization':
272	1	if self._m_degree(word[:-7]) > 0:
273	1	word = word[:-5] + 'e'
274	1	elif word[-5:] == 'ation':
275	1	if self._m_degree(word[:-5]) > 0:
276	1	word = word[:-3] + 'e'
277	1	elif word[-4:] == 'ator':
278	1	if self._m_degree(word[:-4]) > 0:
279	1	word = word[:-2] + 'e'
280	1	elif word[-2] == 's':
281	1	if word[-5:] == 'alism':
282	1	if self._m_degree(word[:-5]) > 0:
283	1	word = word[:-3]
284	1	elif word[-7:] in {'iveness', 'fulness', 'ousness'}:
285	1	if self._m_degree(word[:-7]) > 0:
286	1	word = word[:-4]
287	1	elif word[-2] == 't':
288	1	if word[-5:] == 'aliti':
289	1	if self._m_degree(word[:-5]) > 0:
290	1	word = word[:-3]
291	1	elif word[-5:] == 'iviti':
292	1	if self._m_degree(word[:-5]) > 0:
293	1	word = word[:-3] + 'e'
294	1	elif word[-6:] == 'biliti':
295	1	if self._m_degree(word[:-6]) > 0:
296	1	word = word[:-5] + 'le'
297
298		# Step 3
299	1	if word[-5:] in 'icate':
300	1	if self._m_degree(word[:-5]) > 0:
301	1	word = word[:-3]
302	1	elif word[-5:] == 'ative':
303	1	if self._m_degree(word[:-5]) > 0:
304	1	word = word[:-5]
305	1	elif word[-5:] in {'alize', 'iciti'}:
306	1	if self._m_degree(word[:-5]) > 0:
307	1	word = word[:-3]
308	1	elif word[-4:] == 'ical':
309	1	if self._m_degree(word[:-4]) > 0:
310	1	word = word[:-2]
311	1	elif word[-3:] == 'ful':
312	1	if self._m_degree(word[:-3]) > 0:
313	1	word = word[:-3]
314	1	elif word[-4:] == 'ness':
315	1	if self._m_degree(word[:-4]) > 0:
316	1	word = word[:-4]
317
318		# Step 4
319	1	if word[-2:] == 'al':
320	1	if self._m_degree(word[:-2]) > 1:
321	1	word = word[:-2]
322	1	elif word[-4:] in {'ance', 'ence'}:
323	1	if self._m_degree(word[:-4]) > 1:
324	1	word = word[:-4]
325	1	elif word[-2:] in {'er', 'ic'}:
326	1	if self._m_degree(word[:-2]) > 1:
327	1	word = word[:-2]
328	1	elif word[-4:] in {'able', 'ible'}:
329	1	if self._m_degree(word[:-4]) > 1:
330	1	word = word[:-4]
331	1	elif word[-3:] == 'ant':
332	1	if self._m_degree(word[:-3]) > 1:
333	1	word = word[:-3]
334	1	elif word[-5:] == 'ement':
335	1	if self._m_degree(word[:-5]) > 1:
336	1	word = word[:-5]
337	1	elif word[-4:] == 'ment':
338	1	if self._m_degree(word[:-4]) > 1:
339	1	word = word[:-4]
340	1	elif word[-3:] == 'ent':
341	1	if self._m_degree(word[:-3]) > 1:
342	1	word = word[:-3]
343	1	elif word[-4:] in {'sion', 'tion'}:
344	1	if self._m_degree(word[:-3]) > 1:
345	1	word = word[:-3]
346	1	elif word[-2:] == 'ou':
347	1	if self._m_degree(word[:-2]) > 1:
348	1	word = word[:-2]
349	1	elif word[-3:] in {'ism', 'ate', 'iti', 'ous', 'ive', 'ize'}:
350	1	if self._m_degree(word[:-3]) > 1:
351	1	word = word[:-3]
352
353		# Step 5a
354	1	if word[-1] == 'e':
355	1	if self._m_degree(word[:-1]) > 1:
356	1	word = word[:-1]
357	1	elif self._m_degree(word[:-1]) == 1 and not self._ends_in_cvc(
358		word[:-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...
359		):
360	1	word = word[:-1]
361
362		# Step 5b
363	1	if word[-2:] == 'll' and self._m_degree(word) > 1:
364	1	word = word[:-1]
365
366		# Change 'Y' back to 'y' if it survived stemming
367	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...
368	1	if word[i] == 'Y':
369	1	word = word[:i] + 'y' + word[i + 1 :]
370
371	1	return word
372
373
374	1	def porter(word, early_english=False):
375		"""Return Porter stem.
376
377		This is a wrapper for :py:meth:`Porter.stem`.
378
379		Parameters
380		----------
381		word : str
382		The word to stem
383		early_english : bool
384		Set to True in order to remove -eth & -est (2nd & 3rd person singular
385		verbal agreement suffixes)
386
387		Returns
388		-------
389		str
390		Word stem
391
392		Examples
393		--------
394		>>> porter('reading')
395		'read'
396		>>> porter('suspension')
397		'suspens'
398		>>> porter('elusiveness')
399		'elus'
400
401		>>> porter('eateth', early_english=True)
402		'eat'
403
404		"""
405	1	return Porter().stem(word, early_english)
406
407
408		if __name__ == '__main__':
409		import doctest
410
411		doctest.testmod()
412

chrislit / abydos

Push — master ( f43547...71985b )

abydos.stemmer._porter.Porter._ends_in_cvc() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like