abydos.stemmer._porter.Porter.__init__() - Code Metrics - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

abydos.stemmer._porter.Porter.init() A
last analyzed 2020-12-31 20:10 UTC

↳ Parent: abydos.stemmer._porter

Complexity

Conditions

Size

Total Lines	14
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	1
CRAP Score	1

Importance

Changes

Metric	Value
eloc	2
dl	0
loc	14
ccs	1
cts	1
cp	1
rs	10
c	0
b	0
f	0
cc	1
nop	2
crap	1

# 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
# 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 unicodedata import normalize

from ._stemmer import _Stemmer

__all__ = ['Porter']


class Porter(_Stemmer):
    """Porter stemmer.

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

    .. versionadded:: 0.3.6
    """

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

    def _m_degree(self, term: str) -> int:
        """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


        .. versionadded:: 0.1.0
        .. versionchanged:: 0.3.6
            Encapsulated in class

        """
        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: str) -> bool:
        """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)


        .. versionadded:: 0.1.0
        .. versionchanged:: 0.3.6
            Encapsulated in class

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

    def _ends_in_doubled_cons(self, term: str) -> bool:
        """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)


        .. versionadded:: 0.1.0
        .. versionchanged:: 0.3.6
            Encapsulated in class

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

    def _ends_in_cvc(self, term: str) -> bool:
        """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)


        .. versionadded:: 0.1.0
        .. versionchanged:: 0.3.6
            Encapsulated in class

        """
        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 __init__(self, early_english: bool = False) -> None:
        """Initialize Porter instance.

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


        .. versionadded:: 0.4.0

        """
        self._early_english = early_english

    def stem(self, word: str) -> str:
        """Return Porter stem.

        Parameters
        ----------
        word : str
            The word to stem

        Returns
        -------
        str
            Word stem

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

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


        .. versionadded:: 0.1.0
        .. versionchanged:: 0.3.6
            Encapsulated in class

        """
        # lowercase, normalize, and compose
        word = normalize('NFC', 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 self._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


if __name__ == '__main__':
    import doctest

    doctest.testmod()


1		# Copyright 2014-2020 by Christopher C. Little.
2		# This file is part of Abydos.
3		#
4		# Abydos is free software: you can redistribute it and/or modify
5		# it under the terms of the GNU General Public License as published by
6		# the Free Software Foundation, either version 3 of the License, or
7		# (at your option) any later version.
8		#
9		# Abydos is distributed in the hope that it will be useful,
10		# but WITHOUT ANY WARRANTY; without even the implied warranty of
11		# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12		# GNU General Public License for more details.
13		#
14		# You should have received a copy of the GNU General Public License
15		# along with Abydos. If not, see <http://www.gnu.org/licenses/>.
16
17		"""abydos.stemmer._porter.
18
19	1	Porter stemmer
20		"""
21
22		from unicodedata import normalize
23
24	1	from ._stemmer import _Stemmer
25
26		__all__ = ['Porter']
27
28
29		class Porter(_Stemmer):
30		"""Porter stemmer.
31	1
32		The Porter stemmer is described in :cite:`Porter:1980`.
33	1
34		.. versionadded:: 0.3.6
35	1	"""
36	1
37		_vowels = {'a', 'e', 'i', 'o', 'u', 'y'}
38	1
39	1	def _m_degree(self, term: str) -> int:
40		"""Return Porter helper function _m_degree value.
41	1
42		m-degree is equal to the number of V to C transitions
43
44	1	Parameters
45		----------
46		term : str
47		The word for which to calculate the m-degree
48
49		Returns
50		-------
51		int
52	1	The m-degree as defined in the Porter stemmer definition
53
54	1
55		.. versionadded:: 0.1.0
56		.. versionchanged:: 0.3.6
57		Encapsulated in class
58
59		"""
60		mdeg = 0
61		last_was_vowel = False
62		for letter in term:
63		if letter in self._vowels:
64		last_was_vowel = True
65		else:
66		if last_was_vowel:
67		mdeg += 1
68		last_was_vowel = False
69		return mdeg
70
71		def _has_vowel(self, term: str) -> bool:
72		"""Return Porter helper function _has_vowel value.
73
74		Parameters
75	1	----------
76	1	term : str
77	1	The word to scan for vowels
78	1
79	1	Returns
80		-------
81	1	bool
82	1	True iff a vowel exists in the term (as defined in the Porter
83	1	stemmer definition)
84	1
85
86	1	.. versionadded:: 0.1.0
87		.. versionchanged:: 0.3.6
88		Encapsulated in class
89
90		"""
91		for letter in term:
92		if letter in self._vowels:
93		return True
94		return False
95
96		def _ends_in_doubled_cons(self, term: str) -> bool:
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	1	bool
107	1	True iff the stem ends in a doubled consonant (as defined in the
108	1	Porter stemmer definition)
109	1
110
111	1	.. versionadded:: 0.1.0
112		.. versionchanged:: 0.3.6
113		Encapsulated in class
114
115		"""
116		return (
117		len(term) > 1
118		and term[-1] not in self._vowels
119		and term[-2] == term[-1]
120		)
121
122		def _ends_in_cvc(self, term: str) -> bool:
123		"""Return Porter helper function _ends_in_cvc value.
124
125		Parameters
126		----------
127		term : str
128		The word to scan for cvc
129
130		Returns
131	1	-------
132		bool
133		True iff the stem ends in cvc (as defined in the Porter stemmer
134		definition)
135
136
137	1	.. versionadded:: 0.1.0
138		.. versionchanged:: 0.3.6
139		Encapsulated in class
140
141		"""
142		return len(term) > 2 and (
143		term[-1] not in self._vowels
144		and term[-2] in self._vowels
145		and term[-3] not in self._vowels
146		and term[-1] not in tuple('wxY')
147		)
148
149		def __init__(self, early_english: bool = False) -> None:
150		"""Initialize Porter instance.
151
152		Parameters
153		----------
154		early_english : bool
155		Set to True in order to remove -eth & -est (2nd & 3rd person
156		singular verbal agreement suffixes)
157	1
158
159		.. versionadded:: 0.4.0
160
161		"""
162		self._early_english = early_english
163
164	1	def stem(self, word: str) -> str:
165		"""Return Porter stem.
166
167		Parameters
168		----------
169		word : str
170		The word to stem
171
172		Returns
173		-------
174		str
175		Word stem
176
177	1	Examples
178		--------
179	1	>>> stmr = Porter()
180		>>> stmr.stem('reading')
181		'read'
182		>>> stmr.stem('suspension')
183		'suspens'
184		>>> stmr.stem('elusiveness')
185		'elus'
186
187		>>> stmr = Porter(early_english=True)
188		>>> stmr.stem('eateth')
189		'eat'
190
191
192		.. versionadded:: 0.1.0
193		.. versionchanged:: 0.3.6
194		Encapsulated in class
195
196		"""
197		# lowercase, normalize, and compose
198		word = normalize('NFC', word.lower())
199
200		# Return word if stem is shorter than 2
201		if len(word) < 3:
202		return word
203
204		# Re-map consonantal y to Y (Y will be C, y will be V)
205		if word[0] == 'y':
206		word = 'Y' + word[1:]
207		for i in range(1, len(word)):
208		if word[i] == 'y' and word[i - 1] in self._vowels:
209		word = word[:i] + 'Y' + word[i + 1 :]
210
211		# Step 1a
212		if word[-1] == 's':
213	1	if word[-4:] == 'sses':
214		word = word[:-2]
215		elif word[-3:] == 'ies':
216	1	word = word[:-2]
217	1	elif word[-2:] == 'ss':
218		pass
219		else:
220	1	word = word[:-1]
221	1
222	1	# Step 1b
223	1	step1b_flag = False
224	1	if word[-3:] == 'eed':
225		if self._m_degree(word[:-3]) > 0:
226		word = word[:-1]
227	1	elif word[-2:] == 'ed':
228	1	if self._has_vowel(word[:-2]):
229	1	word = word[:-2]
230	1	step1b_flag = True
231	1	elif word[-3:] == 'ing':
232	1	if self._has_vowel(word[:-3]):
233	1	word = word[:-3]
234		step1b_flag = True
235	1	elif self._early_english:
236		if word[-3:] == 'est':
237		if self._has_vowel(word[:-3]):
238	1	word = word[:-3]
239	1	step1b_flag = True
240	1	elif word[-3:] == 'eth':
241	1	if self._has_vowel(word[:-3]):
242	1	word = word[:-3]
243	1	step1b_flag = True
244	1
245	1	if step1b_flag:
246	1	if word[-2:] in {'at', 'bl', 'iz'}:
247	1	word += 'e'
248	1	elif self._ends_in_doubled_cons(word) and word[-1] not in {
249	1	'l',
250	1	's',
251	1	'z',
252	1	}:
253	1	word = word[:-1]
254	1	elif self._m_degree(word) == 1 and self._ends_in_cvc(word):
255	1	word += 'e'
256	1
257	1	# Step 1c
258	1	if word[-1] in {'Y', 'y'} and self._has_vowel(word[:-1]):
259		word = word[:-1] + 'i'
260	1
261	1	# Step 2
262	1	if len(word) > 1:
263	1	if word[-2] == 'a':
264		if word[-7:] == 'ational':
265		if self._m_degree(word[:-7]) > 0:
266		word = word[:-5] + 'e'
267		elif word[-6:] == 'tional':
268	1	if self._m_degree(word[:-6]) > 0:
269	1	word = word[:-2]
270	1	elif word[-2] == 'c':
271		if word[-4:] in {'enci', 'anci'}:
272		if self._m_degree(word[:-4]) > 0:
273	1	word = word[:-1] + 'e'
274	1	elif word[-2] == 'e':
275		if word[-4:] == 'izer':
276		if self._m_degree(word[:-4]) > 0:
277	1	word = word[:-1]
278	1	elif word[-2] == 'g':
279	1	if word[-4:] == 'logi':
280	1	if self._m_degree(word[:-4]) > 0:
281	1	word = word[:-1]
282	1	elif word[-2] == 'l':
283	1	if word[-3:] == 'bli':
284	1	if self._m_degree(word[:-3]) > 0:
285	1	word = word[:-1] + 'e'
286	1	elif word[-4:] == 'alli':
287	1	if self._m_degree(word[:-4]) > 0:
288	1	word = word[:-2]
289	1	elif word[-5:] == 'entli':
290	1	if self._m_degree(word[:-5]) > 0:
291	1	word = word[:-2]
292	1	elif word[-3:] == 'eli':
293	1	if self._m_degree(word[:-3]) > 0:
294	1	word = word[:-2]
295	1	elif word[-5:] == 'ousli':
296	1	if self._m_degree(word[:-5]) > 0:
297	1	word = word[:-2]
298	1	elif word[-2] == 'o':
299	1	if word[-7:] == 'ization':
300	1	if self._m_degree(word[:-7]) > 0:
301	1	word = word[:-5] + 'e'
302	1	elif word[-5:] == 'ation':
303	1	if self._m_degree(word[:-5]) > 0:
304	1	word = word[:-3] + 'e'
305	1	elif word[-4:] == 'ator':
306	1	if self._m_degree(word[:-4]) > 0:
307	1	word = word[:-2] + 'e'
308	1	elif word[-2] == 's':
309	1	if word[-5:] == 'alism':
310	1	if self._m_degree(word[:-5]) > 0:
311	1	word = word[:-3]
312	1	elif word[-7:] in {'iveness', 'fulness', 'ousness'}:
313	1	if self._m_degree(word[:-7]) > 0:
314	1	word = word[:-4]
315	1	elif word[-2] == 't':
316	1	if word[-5:] == 'aliti':
317	1	if self._m_degree(word[:-5]) > 0:
318	1	word = word[:-3]
319	1	elif word[-5:] == 'iviti':
320	1	if self._m_degree(word[:-5]) > 0:
321	1	word = word[:-3] + 'e'
322	1	elif word[-6:] == 'biliti':
323	1	if self._m_degree(word[:-6]) > 0:
324	1	word = word[:-5] + 'le'
325	1
326	1	# Step 3
327	1	if word[-5:] in 'icate':
328	1	if self._m_degree(word[:-5]) > 0:
329	1	word = word[:-3]
330	1	elif word[-5:] == 'ative':
331	1	if self._m_degree(word[:-5]) > 0:
332	1	word = word[:-5]
333	1	elif word[-5:] in {'alize', 'iciti'}:
334	1	if self._m_degree(word[:-5]) > 0:
335	1	word = word[:-3]
336	1	elif word[-4:] == 'ical':
337	1	if self._m_degree(word[:-4]) > 0:
338	1	word = word[:-2]
339	1	elif word[-3:] == 'ful':
340		if self._m_degree(word[:-3]) > 0:
341		word = word[:-3]
342	1	elif word[-4:] == 'ness':
343	1	if self._m_degree(word[:-4]) > 0:
344	1	word = word[:-4]
345	1
346	1	# Step 4
347	1	if word[-2:] == 'al':
348	1	if self._m_degree(word[:-2]) > 1:
349	1	word = word[:-2]
350	1	elif word[-4:] in {'ance', 'ence'}:
351	1	if self._m_degree(word[:-4]) > 1:
352	1	word = word[:-4]
353	1	elif word[-2:] in {'er', 'ic'}:
354	1	if self._m_degree(word[:-2]) > 1:
355	1	word = word[:-2]
356	1	elif word[-4:] in {'able', 'ible'}:
357	1	if self._m_degree(word[:-4]) > 1:
358	1	word = word[:-4]
359	1	elif word[-3:] == 'ant':
360		if self._m_degree(word[:-3]) > 1:
361		word = word[:-3]
362	1	elif word[-5:] == 'ement':
363	1	if self._m_degree(word[:-5]) > 1:
364	1	word = word[:-5]
365	1	elif word[-4:] == 'ment':
366	1	if self._m_degree(word[:-4]) > 1:
367	1	word = word[:-4]
368	1	elif word[-3:] == 'ent':
369	1	if self._m_degree(word[:-3]) > 1:
370	1	word = word[:-3]
371	1	elif word[-4:] in {'sion', 'tion'}:
372	1	if self._m_degree(word[:-3]) > 1:
373	1	word = word[:-3]
374	1	elif word[-2:] == 'ou':
375	1	if self._m_degree(word[:-2]) > 1:
376	1	word = word[:-2]
377	1	elif word[-3:] in {'ism', 'ate', 'iti', 'ous', 'ive', 'ize'}:
378	1	if self._m_degree(word[:-3]) > 1:
379	1	word = word[:-3]
380	1
381	1	# Step 5a
382	1	if word[-1] == 'e':
383	1	if self._m_degree(word[:-1]) > 1:
384	1	word = word[:-1]
385	1	elif self._m_degree(word[:-1]) == 1 and not self._ends_in_cvc(
386	1	word[:-1]
387	1	):
388	1	word = word[:-1]
389	1
390	1	# Step 5b
391	1	if word[-2:] == 'll' and self._m_degree(word) > 1:
392	1	word = word[:-1]
393	1
394	1	# Change 'Y' back to 'y' if it survived stemming
395		for i in range(len(word)):
396		if word[i] == 'Y':
397	1	word = word[:i] + 'y' + word[i + 1 :]
398	1
399	1	return word
400	1
401
402		if __name__ == '__main__':
403	1	import doctest
404
405		doctest.testmod()
406

chrislit / abydos

abydos.stemmer._porter.Porter.__init__() A last analyzed 2020-12-31 20:10 UTC

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like

abydos.stemmer._porter.Porter.init() A
last analyzed 2020-12-31 20:10 UTC