abydos.phonetic._dolby.dolby() - 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 2018-11-14 09:08 UTC

abydos.phonetic._dolby.dolby() A

↳ Parent: abydos.phonetic._dolby

Complexity

Conditions

Size

Total Lines	68
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

Metric	Value
cc	1
eloc	2
nop	4
dl	0
loc	68
ccs	2
cts	2
cp	1
crap	1
rs	10
c	0
b	0
f	0

How to fix Long Method

# -*- 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.phonetic._dolby.

Dolby Code
"""

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

from unicodedata import normalize as unicode_normalize

from six import text_type

from ._phonetic import Phonetic

__all__ = ['Dolby', 'dolby']


class Dolby(Phonetic):

    """Dolby Code.

    This follows "A Spelling Equivalent Abbreviation Algorithm For Personal
    Names" from :cite:`Dolby:1970` and :cite:`Cunningham:1969`.
    """

    def encode(self, word, max_length=-1, keep_vowels=False, vowel_char='*'):

        r"""Return the Dolby Code of a name.

        Parameters
        ----------
        word : str
            The word to transform
        max_length : int
            Maximum length of the returned Dolby code -- this also activates
            the fixed-length code mode if it is greater than 0
        keep_vowels : bool
            If True, retains all vowel markers
        vowel_char : str
            The vowel marker character (default to \*)

        Returns
        -------
        str
            The Dolby Code

        Examples
        --------
        >>> pe = Dolby()
        >>> pe.encode('Hansen')
        'H*NSN'
        >>> pe.encode('Larsen')
        'L*RSN'
        >>> pe.encode('Aagaard')
        '*GR'
        >>> pe.encode('Braaten')
        'BR*DN'
        >>> pe.encode('Sandvik')
        'S*NVK'
        >>> pe.encode('Hansen', max_length=6)
        'H*NS*N'
        >>> pe.encode('Larsen', max_length=6)
        'L*RS*N'
        >>> pe.encode('Aagaard', max_length=6)
        '*G*R  '
        >>> pe.encode('Braaten', max_length=6)
        'BR*D*N'
        >>> pe.encode('Sandvik', max_length=6)
        'S*NF*K'

        >>> pe.encode('Smith')
        'SM*D'
        >>> pe.encode('Waters')
        'W*DRS'
        >>> pe.encode('James')
        'J*MS'
        >>> pe.encode('Schmidt')
        'SM*D'
        >>> pe.encode('Ashcroft')
        '*SKRFD'
        >>> pe.encode('Smith', max_length=6)
        'SM*D  '
        >>> pe.encode('Waters', max_length=6)
        'W*D*RS'
        >>> pe.encode('James', max_length=6)
        'J*M*S '
        >>> pe.encode('Schmidt', max_length=6)
        'SM*D  '
        >>> pe.encode('Ashcroft', max_length=6)
        '*SKRFD'

        """
        # uppercase, normalize, decompose, and filter non-A-Z out
        word = unicode_normalize('NFKD', text_type(word.upper()))
        word = word.replace('ß', 'SS')
        word = ''.join(c for c in word if c in self._uc_set)

        # Rule 1 (FL2)
        if word[:3] in {'MCG', 'MAG', 'MAC'}:
            word = 'MK' + word[3:]
        elif word[:2] == 'MC':
            word = 'MK' + word[2:]

        # Rule 2 (FL3)
        pos = len(word) - 2
        while pos > -1:
            if word[pos : pos + 2] in {
                'DT',

                'LD',

                'ND',

                'NT',

                'RC',

                'RD',

                'RT',

                'SC',

                'SK',

                'ST',

            }:
                word = word[: pos + 1] + word[pos + 2 :]
                pos += 1
            pos -= 1

        # Rule 3 (FL4)
        # Although the rule indicates "after the first letter", the test cases
        # make it clear that these apply to the first letter also.
        word = word.replace('X', 'KS')
        word = word.replace('CE', 'SE')
        word = word.replace('CI', 'SI')
        word = word.replace('CY', 'SI')

        # not in the rule set, but they seem to have intended it
        word = word.replace('TCH', 'CH')

        pos = word.find('CH', 1)
        while pos != -1:
            if word[pos - 1 : pos] not in self._uc_vy_set:
                word = word[:pos] + 'S' + word[pos + 1 :]
            pos = word.find('CH', pos + 1)

        word = word.replace('C', 'K')
        word = word.replace('Z', 'S')

        word = word.replace('WR', 'R')
        word = word.replace('DG', 'G')
        word = word.replace('QU', 'K')
        word = word.replace('T', 'D')
        word = word.replace('PH', 'F')

        # Rule 4 (FL5)
        # Although the rule indicates "after the first letter", the test cases
        # make it clear that these apply to the first letter also.
        pos = word.find('K', 0)
        while pos != -1:
            if pos > 1 and word[pos - 1 : pos] not in self._uc_vy_set | {
                'L',

                'N',

                'R',

            }:
                word = word[: pos - 1] + word[pos:]
                pos -= 1
            pos = word.find('K', pos + 1)

        # Rule FL6
        if max_length > 0 and word[-1:] == 'E':
            word = word[:-1]

        # Rule 5 (FL7)
        word = self._delete_consecutive_repeats(word)

        # Rule 6 (FL8)
        if word[:2] == 'PF':
            word = word[1:]
        if word[-2:] == 'PF':
            word = word[:-1]
        elif word[-2:] == 'GH':
            if word[-3:-2] in self._uc_vy_set:
                word = word[:-2] + 'F'
            else:
                word = word[:-2] + 'G'
        word = word.replace('GH', '')

        # Rule FL9
        if max_length > 0:
            word = word.replace('V', 'F')

        # Rules 7-9 (FL10-FL12)
        first = 1 + (1 if max_length > 0 else 0)
        code = ''
        for pos, char in enumerate(word):
            if char in self._uc_vy_set:
                if first or keep_vowels:
                    code += vowel_char
                    first -= 1
            elif pos > 0 and char in {'W', 'H'}:
                continue
            else:
                code += char

        if max_length > 0:

            # Rule FL13
            if len(code) > max_length and code[-1:] == 'S':
                code = code[:-1]
            if keep_vowels:
                code = code[:max_length]
            else:
                # Rule FL14
                code = code[: max_length + 2]
                # Rule FL15
                while len(code) > max_length:
                    vowels = len(code) - max_length
                    excess = vowels - 1
                    word = code
                    code = ''
                    for char in word:
                        if char == vowel_char:
                            if vowels:
                                code += char
                                vowels -= 1
                        else:
                            code += char
                    code = code[: max_length + excess]

            # Rule FL16
            code += ' ' * (max_length - len(code))

        return code


def dolby(word, max_length=-1, keep_vowels=False, vowel_char='*'):
    r"""Return the Dolby Code of a name.

    This is a wrapper for :py:meth:`Dolby.encode`.

    Parameters
    ----------
    word : str
        The word to transform
    max_length : int
        Maximum length of the returned Dolby code -- this also activates the
        fixed-length code mode if it is greater than 0
    keep_vowels : bool
        If True, retains all vowel markers
    vowel_char : str
        The vowel marker character (default to \*)

    Returns
    -------
    str
        The Dolby Code

    Examples
    --------
    >>> dolby('Hansen')
    'H*NSN'
    >>> dolby('Larsen')
    'L*RSN'
    >>> dolby('Aagaard')
    '*GR'
    >>> dolby('Braaten')
    'BR*DN'
    >>> dolby('Sandvik')
    'S*NVK'
    >>> dolby('Hansen', max_length=6)
    'H*NS*N'
    >>> dolby('Larsen', max_length=6)
    'L*RS*N'
    >>> dolby('Aagaard', max_length=6)
    '*G*R  '
    >>> dolby('Braaten', max_length=6)
    'BR*D*N'
    >>> dolby('Sandvik', max_length=6)
    'S*NF*K'

    >>> dolby('Smith')
    'SM*D'
    >>> dolby('Waters')
    'W*DRS'
    >>> dolby('James')
    'J*MS'
    >>> dolby('Schmidt')
    'SM*D'
    >>> dolby('Ashcroft')
    '*SKRFD'
    >>> dolby('Smith', max_length=6)
    'SM*D  '
    >>> dolby('Waters', max_length=6)
    'W*D*RS'
    >>> dolby('James', max_length=6)
    'J*M*S '
    >>> dolby('Schmidt', max_length=6)
    'SM*D  '
    >>> dolby('Ashcroft', max_length=6)
    '*SKRFD'

    """
    return Dolby().encode(word, max_length, keep_vowels, vowel_char)


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.phonetic._dolby.
20
21		Dolby Code
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 as unicode_normalize
32
33	1	from six import text_type
34
35	1	from ._phonetic import Phonetic
36
37	1	__all__ = ['Dolby', 'dolby']
38
39
40	1	class Dolby(Phonetic):
		0 ignored issues – show Unused Code introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report The variable `__class__` seems to be unused. Loading history...
41		"""Dolby Code.
42
43		This follows "A Spelling Equivalent Abbreviation Algorithm For Personal
44		Names" from :cite:`Dolby:1970` and :cite:`Cunningham:1969`.
45		"""
46
47	1	def encode(self, word, max_length=-1, keep_vowels=False, vowel_char='*'):
		0 ignored issues – show Bug introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Parameters differ from overridden 'encode' method Loading history...
48		r"""Return the Dolby Code of a name.
49
50		Parameters
51		----------
52		word : str
53		The word to transform
54		max_length : int
55		Maximum length of the returned Dolby code -- this also activates
56		the fixed-length code mode if it is greater than 0
57		keep_vowels : bool
58		If True, retains all vowel markers
59		vowel_char : str
60		The vowel marker character (default to \*)
61
62		Returns
63		-------
64		str
65		The Dolby Code
66
67		Examples
68		--------
69		>>> pe = Dolby()
70		>>> pe.encode('Hansen')
71		'H*NSN'
72		>>> pe.encode('Larsen')
73		'L*RSN'
74		>>> pe.encode('Aagaard')
75		'*GR'
76		>>> pe.encode('Braaten')
77		'BR*DN'
78		>>> pe.encode('Sandvik')
79		'S*NVK'
80		>>> pe.encode('Hansen', max_length=6)
81		'HNSN'
82		>>> pe.encode('Larsen', max_length=6)
83		'LRSN'
84		>>> pe.encode('Aagaard', max_length=6)
85		'GR '
86		>>> pe.encode('Braaten', max_length=6)
87		'BRDN'
88		>>> pe.encode('Sandvik', max_length=6)
89		'SNFK'
90
91		>>> pe.encode('Smith')
92		'SM*D'
93		>>> pe.encode('Waters')
94		'W*DRS'
95		>>> pe.encode('James')
96		'J*MS'
97		>>> pe.encode('Schmidt')
98		'SM*D'
99		>>> pe.encode('Ashcroft')
100		'*SKRFD'
101		>>> pe.encode('Smith', max_length=6)
102		'SM*D '
103		>>> pe.encode('Waters', max_length=6)
104		'WDRS'
105		>>> pe.encode('James', max_length=6)
106		'JMS '
107		>>> pe.encode('Schmidt', max_length=6)
108		'SM*D '
109		>>> pe.encode('Ashcroft', max_length=6)
110		'*SKRFD'
111
112		"""
113		# uppercase, normalize, decompose, and filter non-A-Z out
114	1	word = unicode_normalize('NFKD', text_type(word.upper()))
115	1	word = word.replace('ß', 'SS')
116	1	word = ''.join(c for c in word if c in self._uc_set)
117
118		# Rule 1 (FL2)
119	1	if word[:3] in {'MCG', 'MAG', 'MAC'}:
120	1	word = 'MK' + word[3:]
121	1	elif word[:2] == 'MC':
122	1	word = 'MK' + word[2:]
123
124		# Rule 2 (FL3)
125	1	pos = len(word) - 2
126	1	while pos > -1:
127	1	if word[pos : pos + 2] in {
128		'DT',
		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...
129		'LD',
		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...
130		'ND',
		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...
131		'NT',
		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...
132		'RC',
		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...
133		'RD',
		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...
134		'RT',
		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...
135		'SC',
		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...
136		'SK',
		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...
137		'ST',
		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...
138		}:
139	1	word = word[: pos + 1] + word[pos + 2 :]
140	1	pos += 1
141	1	pos -= 1
142
143		# Rule 3 (FL4)
144		# Although the rule indicates "after the first letter", the test cases
145		# make it clear that these apply to the first letter also.
146	1	word = word.replace('X', 'KS')
147	1	word = word.replace('CE', 'SE')
148	1	word = word.replace('CI', 'SI')
149	1	word = word.replace('CY', 'SI')
150
151		# not in the rule set, but they seem to have intended it
152	1	word = word.replace('TCH', 'CH')
153
154	1	pos = word.find('CH', 1)
155	1	while pos != -1:
156	1	if word[pos - 1 : pos] not in self._uc_vy_set:
157	1	word = word[:pos] + 'S' + word[pos + 1 :]
158	1	pos = word.find('CH', pos + 1)
159
160	1	word = word.replace('C', 'K')
161	1	word = word.replace('Z', 'S')
162
163	1	word = word.replace('WR', 'R')
164	1	word = word.replace('DG', 'G')
165	1	word = word.replace('QU', 'K')
166	1	word = word.replace('T', 'D')
167	1	word = word.replace('PH', 'F')
168
169		# Rule 4 (FL5)
170		# Although the rule indicates "after the first letter", the test cases
171		# make it clear that these apply to the first letter also.
172	1	pos = word.find('K', 0)
173	1	while pos != -1:
174	1	if pos > 1 and word[pos - 1 : pos] not in self._uc_vy_set \| {
175		'L',
		0 ignored issues – show Coding Style introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
176		'N',
		0 ignored issues – show Coding Style introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
177		'R',
		0 ignored issues – show Coding Style introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
178		}:
179	1	word = word[: pos - 1] + word[pos:]
180	1	pos -= 1
181	1	pos = word.find('K', pos + 1)
182
183		# Rule FL6
184	1	if max_length > 0 and word[-1:] == 'E':
185	1	word = word[:-1]
186
187		# Rule 5 (FL7)
188	1	word = self._delete_consecutive_repeats(word)
189
190		# Rule 6 (FL8)
191	1	if word[:2] == 'PF':
192	1	word = word[1:]
193	1	if word[-2:] == 'PF':
194	1	word = word[:-1]
195	1	elif word[-2:] == 'GH':
196	1	if word[-3:-2] in self._uc_vy_set:
197	1	word = word[:-2] + 'F'
198		else:
199	1	word = word[:-2] + 'G'
200	1	word = word.replace('GH', '')
201
202		# Rule FL9
203	1	if max_length > 0:
204	1	word = word.replace('V', 'F')
205
206		# Rules 7-9 (FL10-FL12)
207	1	first = 1 + (1 if max_length > 0 else 0)
208	1	code = ''
209	1	for pos, char in enumerate(word):
210	1	if char in self._uc_vy_set:
211	1	if first or keep_vowels:
212	1	code += vowel_char
213	1	first -= 1
214	1	elif pos > 0 and char in {'W', 'H'}:
215	1	continue
216		else:
217	1	code += char
218
219	1	if max_length > 0:
		0 ignored issues – show unused-code introduced 2018-10-20 00:45 UTC by Report Bug Copy Issue Report Too many nested blocks (6/5) Loading history...
220		# Rule FL13
221	1	if len(code) > max_length and code[-1:] == 'S':
222	1	code = code[:-1]
223	1	if keep_vowels:
224	1	code = code[:max_length]
225		else:
226		# Rule FL14
227	1	code = code[: max_length + 2]
228		# Rule FL15
229	1	while len(code) > max_length:
230	1	vowels = len(code) - max_length
231	1	excess = vowels - 1
232	1	word = code
233	1	code = ''
234	1	for char in word:
235	1	if char == vowel_char:
236	1	if vowels:
237	1	code += char
238	1	vowels -= 1
239		else:
240	1	code += char
241	1	code = code[: max_length + excess]
242
243		# Rule FL16
244	1	code += ' ' * (max_length - len(code))
245
246	1	return code
247
248
249	1	def dolby(word, max_length=-1, keep_vowels=False, vowel_char='*'):
250		r"""Return the Dolby Code of a name.
251
252		This is a wrapper for :py:meth:`Dolby.encode`.
253
254		Parameters
255		----------
256		word : str
257		The word to transform
258		max_length : int
259		Maximum length of the returned Dolby code -- this also activates the
260		fixed-length code mode if it is greater than 0
261		keep_vowels : bool
262		If True, retains all vowel markers
263		vowel_char : str
264		The vowel marker character (default to \*)
265
266		Returns
267		-------
268		str
269		The Dolby Code
270
271		Examples
272		--------
273		>>> dolby('Hansen')
274		'H*NSN'
275		>>> dolby('Larsen')
276		'L*RSN'
277		>>> dolby('Aagaard')
278		'*GR'
279		>>> dolby('Braaten')
280		'BR*DN'
281		>>> dolby('Sandvik')
282		'S*NVK'
283		>>> dolby('Hansen', max_length=6)
284		'HNSN'
285		>>> dolby('Larsen', max_length=6)
286		'LRSN'
287		>>> dolby('Aagaard', max_length=6)
288		'GR '
289		>>> dolby('Braaten', max_length=6)
290		'BRDN'
291		>>> dolby('Sandvik', max_length=6)
292		'SNFK'
293
294		>>> dolby('Smith')
295		'SM*D'
296		>>> dolby('Waters')
297		'W*DRS'
298		>>> dolby('James')
299		'J*MS'
300		>>> dolby('Schmidt')
301		'SM*D'
302		>>> dolby('Ashcroft')
303		'*SKRFD'
304		>>> dolby('Smith', max_length=6)
305		'SM*D '
306		>>> dolby('Waters', max_length=6)
307		'WDRS'
308		>>> dolby('James', max_length=6)
309		'JMS '
310		>>> dolby('Schmidt', max_length=6)
311		'SM*D '
312		>>> dolby('Ashcroft', max_length=6)
313		'*SKRFD'
314
315		"""
316	1	return Dolby().encode(word, max_length, keep_vowels, vowel_char)
317
318
319		if __name__ == '__main__':
320		import doctest
321
322		doctest.testmod()
323

chrislit / abydos

Pull Request — master (#141)

abydos.phonetic._dolby.dolby() A

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like