abydos.stemmer._paice_husk.paice_husk() - Code Metrics - Inspection of "78a222a9f7d8976f6744d263e3d6d01a2a991c27" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Branch — master (78a222)

by Chris

created 2018-10-26 11:30 UTC

abydos.stemmer._paice_husk.paice_husk() F

↳ Parent: abydos.stemmer._paice_husk

Complexity

Conditions

Size

Total Lines	202
Code Lines	159

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	40
CRAP Score	19

Importance

Changes

Metric	Value
eloc	159
dl	0
loc	202
ccs	40
cts	40
cp	1
rs	0.4199
c	0
b	0
f	0
cc	19
nop	1
crap	19

How to fix Long Method Complexity

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

# Copyright 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._paice_husk.

The stemmer._paice_husk module defines the Paice-Husk Stemmer
"""

from __future__ import unicode_literals

from six.moves import range

__all__ = ['paice_husk']


def paice_husk(word):
    """Return Paice-Husk stem.

    Implementation of the Paice-Husk Stemmer, also known as the Lancaster
    Stemmer, developed by Chris Paice, with the assistance of Gareth Husk

    This is based on the algorithm's description in :cite:`Paice:1990`.

    :param str word: the word to stem
    :returns: the stemmed word
    :rtype: str

    >>> paice_husk('assumption')
    'assum'
    >>> paice_husk('verifiable')
    'ver'
    >>> paice_husk('fancies')
    'fant'
    >>> paice_husk('fanciful')
    'fancy'
    >>> paice_husk('torment')
    'tor'
    """
    rule_table = {
        6: {'ifiabl': (False, 6, None, True), 'plicat': (False, 4, 'y', True)},
        5: {
            'guish': (False, 5, 'ct', True),
            'sumpt': (False, 2, None, True),
            'istry': (False, 5, None, True),
        },
        4: {
            'ytic': (False, 3, 's', True),
            'ceed': (False, 2, 'ss', True),
            'hood': (False, 4, None, False),
            'lief': (False, 1, 'v', True),
            'verj': (False, 1, 't', True),
            'misj': (False, 2, 't', True),
            'iabl': (False, 4, 'y', True),
            'iful': (False, 4, 'y', True),
            'sion': (False, 4, 'j', False),
            'xion': (False, 4, 'ct', True),
            'ship': (False, 4, None, False),
            'ness': (False, 4, None, False),
            'ment': (False, 4, None, False),
            'ript': (False, 2, 'b', True),
            'orpt': (False, 2, 'b', True),
            'duct': (False, 1, None, True),
            'cept': (False, 2, 'iv', True),
            'olut': (False, 2, 'v', True),
            'sist': (False, 0, None, True),
        },
        3: {
            'ied': (False, 3, 'y', False),
            'eed': (False, 1, None, True),
            'ing': (False, 3, None, False),
            'iag': (False, 3, 'y', True),
            'ish': (False, 3, None, False),
            'fuj': (False, 1, 's', True),
            'hej': (False, 1, 'r', True),
            'abl': (False, 3, None, False),
            'ibl': (False, 3, None, True),
            'bil': (False, 2, 'l', False),
            'ful': (False, 3, None, False),
            'ial': (False, 3, None, False),
            'ual': (False, 3, None, False),
            'ium': (False, 3, None, True),
            'ism': (False, 3, None, False),
            'ion': (False, 3, None, False),
            'ian': (False, 3, None, False),
            'een': (False, 0, None, True),
            'ear': (False, 0, None, True),
            'ier': (False, 3, 'y', False),
            'ies': (False, 3, 'y', False),
            'sis': (False, 2, None, True),
            'ous': (False, 3, None, False),
            'ent': (False, 3, None, False),
            'ant': (False, 3, None, False),
            'ist': (False, 3, None, False),
            'iqu': (False, 3, None, True),
            'ogu': (False, 1, None, True),
            'siv': (False, 3, 'j', False),
            'eiv': (False, 0, None, True),
            'bly': (False, 1, None, False),
            'ily': (False, 3, 'y', False),
            'ply': (False, 0, None, True),
            'ogy': (False, 1, None, True),
            'phy': (False, 1, None, True),
            'omy': (False, 1, None, True),
            'opy': (False, 1, None, True),
            'ity': (False, 3, None, False),
            'ety': (False, 3, None, False),
            'lty': (False, 2, None, True),
            'ary': (False, 3, None, False),
            'ory': (False, 3, None, False),
            'ify': (False, 3, None, True),
            'ncy': (False, 2, 't', False),
            'acy': (False, 3, None, False),
        },
        2: {
            'ia': (True, 2, None, True),
            'bb': (False, 1, None, True),
            'ic': (False, 2, None, False),
            'nc': (False, 1, 't', False),
            'dd': (False, 1, None, True),
            'ed': (False, 2, None, False),
            'if': (False, 2, None, False),
            'ag': (False, 2, None, False),
            'gg': (False, 1, None, True),
            'th': (True, 2, None, True),
            'ij': (False, 1, 'd', True),
            'uj': (False, 1, 'd', True),
            'oj': (False, 1, 'd', True),
            'nj': (False, 1, 'd', True),
            'cl': (False, 1, None, True),
            'ul': (False, 2, None, True),
            'al': (False, 2, None, False),
            'll': (False, 1, None, True),
            'um': (True, 2, None, True),
            'mm': (False, 1, None, True),
            'an': (False, 2, None, False),
            'en': (False, 2, None, False),
            'nn': (False, 1, None, True),
            'pp': (False, 1, None, True),
            'er': (False, 2, None, False),
            'ar': (False, 2, None, True),
            'or': (False, 2, None, False),
            'ur': (False, 2, None, False),
            'rr': (False, 1, None, True),
            'tr': (False, 1, None, False),
            'is': (False, 2, None, False),
            'ss': (False, 0, None, True),
            'us': (True, 2, None, True),
            'at': (False, 2, None, False),
            'tt': (False, 1, None, True),
            'iv': (False, 2, None, False),
            'ly': (False, 2, None, False),
            'iz': (False, 2, None, False),
            'yz': (False, 1, 's', True),
        },
        1: {
            'a': (True, 1, None, True),
            'e': (False, 1, None, False),
            'i': ((True, 1, None, True), (False, 1, 'y', False)),
            'j': (False, 1, 's', True),
            's': ((True, 1, None, False), (False, 0, None, True)),
        },
    }

    def _has_vowel(word):
        for char in word:
            if char in {'a', 'e', 'i', 'o', 'u', 'y'}:
                return True
        return False

    def _acceptable(word):
        if word and word[0] in {'a', 'e', 'i', 'o', 'u'}:
            return len(word) > 1
        return len(word) > 2 and _has_vowel(word[1:])

    def _apply_rule(word, rule, intact):
        old_word = word
        only_intact, del_len, add_str, set_terminate = rule
        # print(word, word[-n:], rule)

        if (not only_intact) or (intact and only_intact):
            if del_len:
                word = word[:-del_len]
            if add_str:
                word += add_str
        else:
            return word, False, intact, terminate

        if _acceptable(word):

            return word, True, False, set_terminate
        else:
            return old_word, False, intact, terminate

    terminate = False
    intact = True
    while not terminate:

        for n in range(6, 0, -1):

            if word[-n:] in rule_table[n]:
                accept = False
                if len(rule_table[n][word[-n:]]) < 4:
                    for rule in rule_table[n][word[-n:]]:
                        (word, accept, intact, terminate) = _apply_rule(
                            word, rule, intact
                        )
                        if accept:
                            break
                else:
                    rule = rule_table[n][word[-n:]]
                    (word, accept, intact, terminate) = _apply_rule(
                        word, rule, intact
                    )

                if accept:
                    break
        else:
            break

    return word


if __name__ == '__main__':
    import doctest

    doctest.testmod()


1		# -- coding: utf-8 --
2
3		# Copyright 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._paice_husk.
20
21		The stemmer._paice_husk module defines the Paice-Husk Stemmer
22		"""
23
24	1	from __future__ import unicode_literals
25
26	1	from six.moves import range
27
28	1	__all__ = ['paice_husk']
29
30
31	1	def paice_husk(word):
32		"""Return Paice-Husk stem.
33
34		Implementation of the Paice-Husk Stemmer, also known as the Lancaster
35		Stemmer, developed by Chris Paice, with the assistance of Gareth Husk
36
37		This is based on the algorithm's description in :cite:`Paice:1990`.
38
39		:param str word: the word to stem
40		:returns: the stemmed word
41		:rtype: str
42
43		>>> paice_husk('assumption')
44		'assum'
45		>>> paice_husk('verifiable')
46		'ver'
47		>>> paice_husk('fancies')
48		'fant'
49		>>> paice_husk('fanciful')
50		'fancy'
51		>>> paice_husk('torment')
52		'tor'
53		"""
54	1	rule_table = {
55		6: {'ifiabl': (False, 6, None, True), 'plicat': (False, 4, 'y', True)},
56		5: {
57		'guish': (False, 5, 'ct', True),
58		'sumpt': (False, 2, None, True),
59		'istry': (False, 5, None, True),
60		},
61		4: {
62		'ytic': (False, 3, 's', True),
63		'ceed': (False, 2, 'ss', True),
64		'hood': (False, 4, None, False),
65		'lief': (False, 1, 'v', True),
66		'verj': (False, 1, 't', True),
67		'misj': (False, 2, 't', True),
68		'iabl': (False, 4, 'y', True),
69		'iful': (False, 4, 'y', True),
70		'sion': (False, 4, 'j', False),
71		'xion': (False, 4, 'ct', True),
72		'ship': (False, 4, None, False),
73		'ness': (False, 4, None, False),
74		'ment': (False, 4, None, False),
75		'ript': (False, 2, 'b', True),
76		'orpt': (False, 2, 'b', True),
77		'duct': (False, 1, None, True),
78		'cept': (False, 2, 'iv', True),
79		'olut': (False, 2, 'v', True),
80		'sist': (False, 0, None, True),
81		},
82		3: {
83		'ied': (False, 3, 'y', False),
84		'eed': (False, 1, None, True),
85		'ing': (False, 3, None, False),
86		'iag': (False, 3, 'y', True),
87		'ish': (False, 3, None, False),
88		'fuj': (False, 1, 's', True),
89		'hej': (False, 1, 'r', True),
90		'abl': (False, 3, None, False),
91		'ibl': (False, 3, None, True),
92		'bil': (False, 2, 'l', False),
93		'ful': (False, 3, None, False),
94		'ial': (False, 3, None, False),
95		'ual': (False, 3, None, False),
96		'ium': (False, 3, None, True),
97		'ism': (False, 3, None, False),
98		'ion': (False, 3, None, False),
99		'ian': (False, 3, None, False),
100		'een': (False, 0, None, True),
101		'ear': (False, 0, None, True),
102		'ier': (False, 3, 'y', False),
103		'ies': (False, 3, 'y', False),
104		'sis': (False, 2, None, True),
105		'ous': (False, 3, None, False),
106		'ent': (False, 3, None, False),
107		'ant': (False, 3, None, False),
108		'ist': (False, 3, None, False),
109		'iqu': (False, 3, None, True),
110		'ogu': (False, 1, None, True),
111		'siv': (False, 3, 'j', False),
112		'eiv': (False, 0, None, True),
113		'bly': (False, 1, None, False),
114		'ily': (False, 3, 'y', False),
115		'ply': (False, 0, None, True),
116		'ogy': (False, 1, None, True),
117		'phy': (False, 1, None, True),
118		'omy': (False, 1, None, True),
119		'opy': (False, 1, None, True),
120		'ity': (False, 3, None, False),
121		'ety': (False, 3, None, False),
122		'lty': (False, 2, None, True),
123		'ary': (False, 3, None, False),
124		'ory': (False, 3, None, False),
125		'ify': (False, 3, None, True),
126		'ncy': (False, 2, 't', False),
127		'acy': (False, 3, None, False),
128		},
129		2: {
130		'ia': (True, 2, None, True),
131		'bb': (False, 1, None, True),
132		'ic': (False, 2, None, False),
133		'nc': (False, 1, 't', False),
134		'dd': (False, 1, None, True),
135		'ed': (False, 2, None, False),
136		'if': (False, 2, None, False),
137		'ag': (False, 2, None, False),
138		'gg': (False, 1, None, True),
139		'th': (True, 2, None, True),
140		'ij': (False, 1, 'd', True),
141		'uj': (False, 1, 'd', True),
142		'oj': (False, 1, 'd', True),
143		'nj': (False, 1, 'd', True),
144		'cl': (False, 1, None, True),
145		'ul': (False, 2, None, True),
146		'al': (False, 2, None, False),
147		'll': (False, 1, None, True),
148		'um': (True, 2, None, True),
149		'mm': (False, 1, None, True),
150		'an': (False, 2, None, False),
151		'en': (False, 2, None, False),
152		'nn': (False, 1, None, True),
153		'pp': (False, 1, None, True),
154		'er': (False, 2, None, False),
155		'ar': (False, 2, None, True),
156		'or': (False, 2, None, False),
157		'ur': (False, 2, None, False),
158		'rr': (False, 1, None, True),
159		'tr': (False, 1, None, False),
160		'is': (False, 2, None, False),
161		'ss': (False, 0, None, True),
162		'us': (True, 2, None, True),
163		'at': (False, 2, None, False),
164		'tt': (False, 1, None, True),
165		'iv': (False, 2, None, False),
166		'ly': (False, 2, None, False),
167		'iz': (False, 2, None, False),
168		'yz': (False, 1, 's', True),
169		},
170		1: {
171		'a': (True, 1, None, True),
172		'e': (False, 1, None, False),
173		'i': ((True, 1, None, True), (False, 1, 'y', False)),
174		'j': (False, 1, 's', True),
175		's': ((True, 1, None, False), (False, 0, None, True)),
176		},
177		}
178
179	1	def _has_vowel(word):
180	1	for char in word:
181	1	if char in {'a', 'e', 'i', 'o', 'u', 'y'}:
182	1	return True
183	1	return False
184
185	1	def _acceptable(word):
186	1	if word and word[0] in {'a', 'e', 'i', 'o', 'u'}:
187	1	return len(word) > 1
188	1	return len(word) > 2 and _has_vowel(word[1:])
189
190	1	def _apply_rule(word, rule, intact):
191	1	old_word = word
192	1	only_intact, del_len, add_str, set_terminate = rule
193		# print(word, word[-n:], rule)
194
195	1	if (not only_intact) or (intact and only_intact):
196	1	if del_len:
197	1	word = word[:-del_len]
198	1	if add_str:
199	1	word += add_str
200		else:
201	1	return word, False, intact, terminate
202
203	1	if _acceptable(word):
		0 ignored issues – show unused-code introduced 2018-08-26 09:00 UTC by Report Bug Copy Issue Report Unnecessary "else" after "return" Loading history...
204	1	return word, True, False, set_terminate
205		else:
206	1	return old_word, False, intact, terminate
207
208	1	terminate = False
209	1	intact = True
210	1	while not terminate:
		0 ignored issues – show unused-code introduced 2018-08-26 09:00 UTC by Report Bug Copy Issue Report Too many nested blocks (6/5) Loading history...
211	1	for n in range(6, 0, -1):
		0 ignored issues – show Coding Style Naming introduced 2018-10-23 05:52 UTC by Report Bug Copy Issue Report The name `n` does not conform to the variable naming conventions (`(([a-z][a-z0-9_]{2,30})\|(_[a-z0-9_]*))$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
212	1	if word[-n:] in rule_table[n]:
213	1	accept = False
214	1	if len(rule_table[n][word[-n:]]) < 4:
215	1	for rule in rule_table[n][word[-n:]]:
216	1	(word, accept, intact, terminate) = _apply_rule(
217		word, rule, intact
218		)
219	1	if accept:
220	1	break
221		else:
222	1	rule = rule_table[n][word[-n:]]
223	1	(word, accept, intact, terminate) = _apply_rule(
224		word, rule, intact
225		)
226
227	1	if accept:
228	1	break
229		else:
230	1	break
231
232	1	return word
233
234
235		if __name__ == '__main__':
236		import doctest
237
238		doctest.testmod()
239

chrislit / abydos

Branch — master (78a222)

abydos.stemmer._paice_husk.paice_husk() F

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Long Method Complexity

Long Method

Complexity

Duplication Side-by-Side

Filter issues like