abydos.phonetic._nysiis.nysiis() - 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 2018-11-08 03:44 UTC

abydos.phonetic._nysiis.nysiis() A

↳ Parent: abydos.phonetic._nysiis

Complexity

Conditions

Size

Total Lines	37
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

Metric	Value
eloc	2
dl	0
loc	37
ccs	2
cts	2
cp	1
rs	10
c	0
b	0
f	0
cc	1
nop	3
crap	1

# -*- 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.phonetic._nysiis.

The phonetic._nysiis module implements New York State Identification and
Intelligence System (NYSIIS) phonetic encoding.
"""

from __future__ import unicode_literals

from six.moves import range

from ._phonetic import Phonetic

__all__ = ['NYSIIS', 'nysiis']


class NYSIIS(Phonetic):

    """NYSIIS Code.

    The New York State Identification and Intelligence System algorithm is
    defined in :cite:`Taft:1970`.

    The modified version of this algorithm is described in Appendix B of
    :cite:`Lynch:1977`.
    """

    def encode(self, word, max_length=6, modified=False):

        """Return the NYSIIS code for a word.

        Args:
            word (str): The word to transform
            max_length (int): The maximum length (default 6) of the code to
                return
            modified (bool): Indicates whether to use USDA modified NYSIIS

        Returns:
            str: The NYSIIS value

        Examples:
            >>> pe = NYSIIS()
            >>> pe.encode('Christopher')
            'CRASTA'
            >>> pe.encode('Niall')
            'NAL'
            >>> pe.encode('Smith')
            'SNAT'
            >>> pe.encode('Schmidt')
            'SNAD'

            >>> pe.encode('Christopher', max_length=-1)
            'CRASTAFAR'

            >>> pe.encode('Christopher', max_length=8, modified=True)
            'CRASTAFA'
            >>> pe.encode('Niall', max_length=8, modified=True)
            'NAL'
            >>> pe.encode('Smith', max_length=8, modified=True)
            'SNAT'
            >>> pe.encode('Schmidt', max_length=8, modified=True)
            'SNAD'

        """
        # Require a max_length of at least 6
        if max_length > -1:
            max_length = max(6, max_length)

        word = ''.join(c for c in word.upper() if c.isalpha())
        word = word.replace('ß', 'SS')

        # exit early if there are no alphas
        if not word:
            return ''

        original_first_char = word[0]

        if word[:3] == 'MAC':
            word = 'MCC' + word[3:]
        elif word[:2] == 'KN':
            word = 'NN' + word[2:]
        elif word[:1] == 'K':
            word = 'C' + word[1:]
        elif word[:2] in {'PH', 'PF'}:
            word = 'FF' + word[2:]
        elif word[:3] == 'SCH':
            word = 'SSS' + word[3:]
        elif modified:
            if word[:2] == 'WR':
                word = 'RR' + word[2:]
            elif word[:2] == 'RH':
                word = 'RR' + word[2:]
            elif word[:2] == 'DG':
                word = 'GG' + word[2:]
            elif word[:1] in self._uc_v_set:
                word = 'A' + word[1:]

        if modified and word[-1:] in {'S', 'Z'}:
            word = word[:-1]

        if (
            word[-2:] == 'EE'

            or word[-2:] == 'IE'

            or (modified and word[-2:] == 'YE')

        ):
            word = word[:-2] + 'Y'
        elif word[-2:] in {'DT', 'RT', 'RD'}:
            word = word[:-2] + 'D'
        elif word[-2:] in {'NT', 'ND'}:
            word = word[:-2] + ('N' if modified else 'D')
        elif modified:
            if word[-2:] == 'IX':
                word = word[:-2] + 'ICK'
            elif word[-2:] == 'EX':
                word = word[:-2] + 'ECK'
            elif word[-2:] in {'JR', 'SR'}:
                return 'ERROR'

        key = word[:1]

        skip = 0
        for i in range(1, len(word)):
            if i >= len(word):
                continue
            elif skip:
                skip -= 1
                continue
            elif word[i : i + 2] == 'EV':
                word = word[:i] + 'AF' + word[i + 2 :]
                skip = 1
            elif word[i] in self._uc_v_set:
                word = word[:i] + 'A' + word[i + 1 :]
            elif modified and i != len(word) - 1 and word[i] == 'Y':
                word = word[:i] + 'A' + word[i + 1 :]
            elif word[i] == 'Q':
                word = word[:i] + 'G' + word[i + 1 :]
            elif word[i] == 'Z':
                word = word[:i] + 'S' + word[i + 1 :]
            elif word[i] == 'M':
                word = word[:i] + 'N' + word[i + 1 :]
            elif word[i : i + 2] == 'KN':
                word = word[:i] + 'N' + word[i + 2 :]
            elif word[i] == 'K':
                word = word[:i] + 'C' + word[i + 1 :]
            elif modified and i == len(word) - 3 and word[i : i + 3] == 'SCH':
                word = word[:i] + 'SSA'
                skip = 2
            elif word[i : i + 3] == 'SCH':
                word = word[:i] + 'SSS' + word[i + 3 :]
                skip = 2
            elif modified and i == len(word) - 2 and word[i : i + 2] == 'SH':
                word = word[:i] + 'SA'
                skip = 1
            elif word[i : i + 2] == 'SH':
                word = word[:i] + 'SS' + word[i + 2 :]
                skip = 1
            elif word[i : i + 2] == 'PH':
                word = word[:i] + 'FF' + word[i + 2 :]
                skip = 1
            elif modified and word[i : i + 3] == 'GHT':
                word = word[:i] + 'TTT' + word[i + 3 :]
                skip = 2
            elif modified and word[i : i + 2] == 'DG':
                word = word[:i] + 'GG' + word[i + 2 :]
                skip = 1
            elif modified and word[i : i + 2] == 'WR':
                word = word[:i] + 'RR' + word[i + 2 :]
                skip = 1
            elif word[i] == 'H' and (
                word[i - 1] not in self._uc_v_set

                or word[i + 1 : i + 2] not in self._uc_v_set

            ):
                word = word[:i] + word[i - 1] + word[i + 1 :]
            elif word[i] == 'W' and word[i - 1] in self._uc_v_set:
                word = word[:i] + word[i - 1] + word[i + 1 :]

            if word[i : i + skip + 1] != key[-1:]:
                key += word[i : i + skip + 1]

        key = self._delete_consecutive_repeats(key)

        if key[-1:] == 'S':
            key = key[:-1]
        if key[-2:] == 'AY':
            key = key[:-2] + 'Y'
        if key[-1:] == 'A':
            key = key[:-1]
        if modified and key[:1] == 'A':
            key = original_first_char + key[1:]

        if max_length > 0:
            key = key[:max_length]

        return key


def nysiis(word, max_length=6, modified=False):
    """Return the NYSIIS code for a word.

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

    Args:
        word (str): The word to transform
        max_length (int): The maximum length (default 6) of the code to return
        modified (bool): Indicates whether to use USDA modified NYSIIS

    Returns:
        str: The NYSIIS value

    Examples:
        >>> nysiis('Christopher')
        'CRASTA'
        >>> nysiis('Niall')
        'NAL'
        >>> nysiis('Smith')
        'SNAT'
        >>> nysiis('Schmidt')
        'SNAD'

        >>> nysiis('Christopher', max_length=-1)
        'CRASTAFAR'

        >>> nysiis('Christopher', max_length=8, modified=True)
        'CRASTAFA'
        >>> nysiis('Niall', max_length=8, modified=True)
        'NAL'
        >>> nysiis('Smith', max_length=8, modified=True)
        'SNAT'
        >>> nysiis('Schmidt', max_length=8, modified=True)
        'SNAD'

    """
    return NYSIIS().encode(word, max_length, modified)


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.phonetic._nysiis.
20
21		The phonetic._nysiis module implements New York State Identification and
22		Intelligence System (NYSIIS) phonetic encoding.
23		"""
24
25	1	from __future__ import unicode_literals
26
27	1	from six.moves import range
28
29	1	from ._phonetic import Phonetic
30
31	1	__all__ = ['NYSIIS', 'nysiis']
32
33
34	1	class NYSIIS(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...
35		"""NYSIIS Code.
36
37		The New York State Identification and Intelligence System algorithm is
38		defined in :cite:`Taft:1970`.
39
40		The modified version of this algorithm is described in Appendix B of
41		:cite:`Lynch:1977`.
42		"""
43
44	1	def encode(self, word, max_length=6, modified=False):
		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...
45		"""Return the NYSIIS code for a word.
46
47		Args:
48		word (str): The word to transform
49		max_length (int): The maximum length (default 6) of the code to
50		return
51		modified (bool): Indicates whether to use USDA modified NYSIIS
52
53		Returns:
54		str: The NYSIIS value
55
56		Examples:
57		>>> pe = NYSIIS()
58		>>> pe.encode('Christopher')
59		'CRASTA'
60		>>> pe.encode('Niall')
61		'NAL'
62		>>> pe.encode('Smith')
63		'SNAT'
64		>>> pe.encode('Schmidt')
65		'SNAD'
66
67		>>> pe.encode('Christopher', max_length=-1)
68		'CRASTAFAR'
69
70		>>> pe.encode('Christopher', max_length=8, modified=True)
71		'CRASTAFA'
72		>>> pe.encode('Niall', max_length=8, modified=True)
73		'NAL'
74		>>> pe.encode('Smith', max_length=8, modified=True)
75		'SNAT'
76		>>> pe.encode('Schmidt', max_length=8, modified=True)
77		'SNAD'
78
79		"""
80		# Require a max_length of at least 6
81	1	if max_length > -1:
82	1	max_length = max(6, max_length)
83
84	1	word = ''.join(c for c in word.upper() if c.isalpha())
85	1	word = word.replace('ß', 'SS')
86
87		# exit early if there are no alphas
88	1	if not word:
89	1	return ''
90
91	1	original_first_char = word[0]
92
93	1	if word[:3] == 'MAC':
94	1	word = 'MCC' + word[3:]
95	1	elif word[:2] == 'KN':
96	1	word = 'NN' + word[2:]
97	1	elif word[:1] == 'K':
98	1	word = 'C' + word[1:]
99	1	elif word[:2] in {'PH', 'PF'}:
100	1	word = 'FF' + word[2:]
101	1	elif word[:3] == 'SCH':
102	1	word = 'SSS' + word[3:]
103	1	elif modified:
104	1	if word[:2] == 'WR':
105	1	word = 'RR' + word[2:]
106	1	elif word[:2] == 'RH':
107	1	word = 'RR' + word[2:]
108	1	elif word[:2] == 'DG':
109	1	word = 'GG' + word[2:]
110	1	elif word[:1] in self._uc_v_set:
111	1	word = 'A' + word[1:]
112
113	1	if modified and word[-1:] in {'S', 'Z'}:
114	1	word = word[:-1]
115
116	1	if (
117		word[-2:] == 'EE'
		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...
118		or word[-2:] == 'IE'
		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...
119		or (modified and word[-2:] == 'YE')
		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...
120		):
121	1	word = word[:-2] + 'Y'
122	1	elif word[-2:] in {'DT', 'RT', 'RD'}:
123	1	word = word[:-2] + 'D'
124	1	elif word[-2:] in {'NT', 'ND'}:
125	1	word = word[:-2] + ('N' if modified else 'D')
126	1	elif modified:
127	1	if word[-2:] == 'IX':
128	1	word = word[:-2] + 'ICK'
129	1	elif word[-2:] == 'EX':
130	1	word = word[:-2] + 'ECK'
131	1	elif word[-2:] in {'JR', 'SR'}:
132	1	return 'ERROR'
133
134	1	key = word[:1]
135
136	1	skip = 0
137	1	for i in range(1, len(word)):
138	1	if i >= len(word):
139	1	continue
140	1	elif skip:
141	1	skip -= 1
142	1	continue
143	1	elif word[i : i + 2] == 'EV':
144	1	word = word[:i] + 'AF' + word[i + 2 :]
145	1	skip = 1
146	1	elif word[i] in self._uc_v_set:
147	1	word = word[:i] + 'A' + word[i + 1 :]
148	1	elif modified and i != len(word) - 1 and word[i] == 'Y':
149	1	word = word[:i] + 'A' + word[i + 1 :]
150	1	elif word[i] == 'Q':
151	1	word = word[:i] + 'G' + word[i + 1 :]
152	1	elif word[i] == 'Z':
153	1	word = word[:i] + 'S' + word[i + 1 :]
154	1	elif word[i] == 'M':
155	1	word = word[:i] + 'N' + word[i + 1 :]
156	1	elif word[i : i + 2] == 'KN':
157	1	word = word[:i] + 'N' + word[i + 2 :]
158	1	elif word[i] == 'K':
159	1	word = word[:i] + 'C' + word[i + 1 :]
160	1	elif modified and i == len(word) - 3 and word[i : i + 3] == 'SCH':
161	1	word = word[:i] + 'SSA'
162	1	skip = 2
163	1	elif word[i : i + 3] == 'SCH':
164	1	word = word[:i] + 'SSS' + word[i + 3 :]
165	1	skip = 2
166	1	elif modified and i == len(word) - 2 and word[i : i + 2] == 'SH':
167	1	word = word[:i] + 'SA'
168	1	skip = 1
169	1	elif word[i : i + 2] == 'SH':
170	1	word = word[:i] + 'SS' + word[i + 2 :]
171	1	skip = 1
172	1	elif word[i : i + 2] == 'PH':
173	1	word = word[:i] + 'FF' + word[i + 2 :]
174	1	skip = 1
175	1	elif modified and word[i : i + 3] == 'GHT':
176	1	word = word[:i] + 'TTT' + word[i + 3 :]
177	1	skip = 2
178	1	elif modified and word[i : i + 2] == 'DG':
179	1	word = word[:i] + 'GG' + word[i + 2 :]
180	1	skip = 1
181	1	elif modified and word[i : i + 2] == 'WR':
182	1	word = word[:i] + 'RR' + word[i + 2 :]
183	1	skip = 1
184	1	elif word[i] == 'H' and (
185		word[i - 1] not in self._uc_v_set
		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...
186		or word[i + 1 : i + 2] not in self._uc_v_set
		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...
187		):
188	1	word = word[:i] + word[i - 1] + word[i + 1 :]
189	1	elif word[i] == 'W' and word[i - 1] in self._uc_v_set:
190	1	word = word[:i] + word[i - 1] + word[i + 1 :]
191
192	1	if word[i : i + skip + 1] != key[-1:]:
193	1	key += word[i : i + skip + 1]
194
195	1	key = self._delete_consecutive_repeats(key)
196
197	1	if key[-1:] == 'S':
198	1	key = key[:-1]
199	1	if key[-2:] == 'AY':
200	1	key = key[:-2] + 'Y'
201	1	if key[-1:] == 'A':
202	1	key = key[:-1]
203	1	if modified and key[:1] == 'A':
204	1	key = original_first_char + key[1:]
205
206	1	if max_length > 0:
207	1	key = key[:max_length]
208
209	1	return key
210
211
212	1	def nysiis(word, max_length=6, modified=False):
213		"""Return the NYSIIS code for a word.
214
215		This is a wrapper for :py:meth:`Metaphone.encode`.
216
217		Args:
218		word (str): The word to transform
219		max_length (int): The maximum length (default 6) of the code to return
220		modified (bool): Indicates whether to use USDA modified NYSIIS
221
222		Returns:
223		str: The NYSIIS value
224
225		Examples:
226		>>> nysiis('Christopher')
227		'CRASTA'
228		>>> nysiis('Niall')
229		'NAL'
230		>>> nysiis('Smith')
231		'SNAT'
232		>>> nysiis('Schmidt')
233		'SNAD'
234
235		>>> nysiis('Christopher', max_length=-1)
236		'CRASTAFAR'
237
238		>>> nysiis('Christopher', max_length=8, modified=True)
239		'CRASTAFA'
240		>>> nysiis('Niall', max_length=8, modified=True)
241		'NAL'
242		>>> nysiis('Smith', max_length=8, modified=True)
243		'SNAT'
244		>>> nysiis('Schmidt', max_length=8, modified=True)
245		'SNAD'
246
247		"""
248	1	return NYSIIS().encode(word, max_length, modified)
249
250
251		if __name__ == '__main__':
252		import doctest
253
254		doctest.testmod()
255

chrislit / abydos

Pull Request — master (#141)

abydos.phonetic._nysiis.nysiis() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like