abydos.phonetic._nysiis.NYSIIS.__init__() - Code Metrics - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

abydos.phonetic._nysiis.NYSIIS.init() A
last analyzed 2020-12-31 20:10 UTC

↳ Parent: abydos.phonetic._nysiis

Complexity

Conditions

Size

Total Lines	20
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	2

Importance

Changes

Metric	Value
eloc	5
dl	0
loc	20
ccs	2
cts	2
cp	1
rs	10
c	0
b	0
f	0
cc	2
nop	3
crap	2

# 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.phonetic._nysiis.

New York State Identification and Intelligence System (NYSIIS) phonetic
encoding
"""

from ._phonetic import _Phonetic

__all__ = ['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`.

    .. versionadded:: 0.3.6
    """

    def __init__(self, max_length: int = 6, modified: bool = False) -> None:
        """Initialize AlphaSIS instance.

        Parameters
        ----------
        max_length : int
            The maximum length (default 6) of the code to return
        modified : bool
            Indicates whether to use USDA modified NYSIIS


        .. versionadded:: 0.4.0

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

        self._modified = modified

    def encode(self, word: str) -> str:
        """Return the NYSIIS code for a word.

        Parameters
        ----------
        word : str
            The word to transform

        Returns
        -------
        str
            The NYSIIS value

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

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

        >>> pe_8m = NYSIIS(max_length=8, modified=True)
        >>> pe_8m.encode('Christopher')
        'CRASTAFA'
        >>> pe_8m.encode('Niall')
        'NAL'
        >>> pe_8m.encode('Smith')
        'SNAT'
        >>> pe_8m.encode('Schmidt')
        'SNAD'


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

        """

        word = ''.join(c for c in word.upper() if c.isalpha())

        # 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 self._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 self._modified and word[-1:] in {'S', 'Z'}:
            word = word[:-1]

        if (
            word[-2:] == 'EE'
            or word[-2:] == 'IE'
            or (self._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 self._modified else 'D')
        elif self._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 self._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 (
                self._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 (
                self._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 self._modified and word[i : i + 3] == 'GHT':
                word = word[:i] + 'TTT' + word[i + 3 :]
                skip = 2
            elif self._modified and word[i : i + 2] == 'DG':
                word = word[:i] + 'GG' + word[i + 2 :]
                skip = 1
            elif self._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 self._modified and key[:1] == 'A':
            key = original_first_char + key[1:]

        if self._max_length > 0:
            key = key[: self._max_length]

        return key


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.phonetic._nysiis.
18
19	1	New York State Identification and Intelligence System (NYSIIS) phonetic
20		encoding
21		"""
22
23		from ._phonetic import _Phonetic
24
25	1	__all__ = ['NYSIIS']
26
27
28		class NYSIIS(_Phonetic):
29		"""NYSIIS Code.
30
31		The New York State Identification and Intelligence System algorithm is
32	1	defined in :cite:`Taft:1970`.
33
34	1	The modified version of this algorithm is described in Appendix B of
35		:cite:`Lynch:1977`.
36	1
37	1	.. versionadded:: 0.3.6
38		"""
39	1
40		def __init__(self, max_length: int = 6, modified: bool = False) -> None:
41		"""Initialize AlphaSIS instance.
42	1
43		Parameters
44		----------
45		max_length : int
46		The maximum length (default 6) of the code to return
47		modified : bool
48		Indicates whether to use USDA modified NYSIIS
49
50
51		.. versionadded:: 0.4.0
52
53		"""
54	1	self._max_length = max_length
55		# Require a max_length of at least 6
56		if self._max_length > -1:
57		self._max_length = max(6, self._max_length)
58
59		self._modified = modified
60
61		def encode(self, word: str) -> str:
62		"""Return the NYSIIS code for a word.
63
64		Parameters
65		----------
66		word : str
67		The word to transform
68	1
69		Returns
70	1	-------
71	1	str
72		The NYSIIS value
73	1
74		Examples
75	1	--------
76		>>> pe = NYSIIS()
77		>>> pe.encode('Christopher')
78		'CRASTA'
79		>>> pe.encode('Niall')
80		'NAL'
81		>>> pe.encode('Smith')
82		'SNAT'
83		>>> pe.encode('Schmidt')
84		'SNAD'
85
86		>>> NYSIIS(max_length=-1).encode('Christopher')
87		'CRASTAFAR'
88
89		>>> pe_8m = NYSIIS(max_length=8, modified=True)
90		>>> pe_8m.encode('Christopher')
91		'CRASTAFA'
92		>>> pe_8m.encode('Niall')
93		'NAL'
94		>>> pe_8m.encode('Smith')
95		'SNAT'
96		>>> pe_8m.encode('Schmidt')
97		'SNAD'
98
99
100		.. versionadded:: 0.1.0
101		.. versionchanged:: 0.3.6
102		Encapsulated in class
103
104		"""
105
106		word = ''.join(c for c in word.upper() if c.isalpha())
107
108		# exit early if there are no alphas
109		if not word:
110		return ''
111
112		original_first_char = word[0]
113
114		if word[:3] == 'MAC':
115		word = 'MCC' + word[3:]
116		elif word[:2] == 'KN':
117		word = 'NN' + word[2:]
118		elif word[:1] == 'K':
119		word = 'C' + word[1:]
120	1	elif word[:2] in {'PH', 'PF'}:
121	1	word = 'FF' + word[2:]
122		elif word[:3] == 'SCH':
123		word = 'SSS' + word[3:]
124	1	elif self._modified:
125	1	if word[:2] == 'WR':
126		word = 'RR' + word[2:]
127	1	elif word[:2] == 'RH':
128		word = 'RR' + word[2:]
129	1	elif word[:2] == 'DG':
130	1	word = 'GG' + word[2:]
131	1	elif word[:1] in self._uc_v_set:
132	1	word = 'A' + word[1:]
133	1
134	1	if self._modified and word[-1:] in {'S', 'Z'}:
135	1	word = word[:-1]
136	1
137	1	if (
138	1	word[-2:] == 'EE'
139	1	or word[-2:] == 'IE'
140	1	or (self._modified and word[-2:] == 'YE')
141	1	):
142	1	word = word[:-2] + 'Y'
143	1	elif word[-2:] in {'DT', 'RT', 'RD'}:
144	1	word = word[:-2] + 'D'
145	1	elif word[-2:] in {'NT', 'ND'}:
146	1	word = word[:-2] + ('N' if self._modified else 'D')
147	1	elif self._modified:
148		if word[-2:] == 'IX':
149	1	word = word[:-2] + 'ICK'
150	1	elif word[-2:] == 'EX':
151		word = word[:-2] + 'ECK'
152	1	elif word[-2:] in {'JR', 'SR'}:
153		return 'ERROR'
154
155		key = word[:1]
156
157	1	skip = 0
158	1	for i in range(1, len(word)):
159	1	if i >= len(word):
160	1	continue
161	1	elif skip:
162	1	skip -= 1
163	1	continue
164	1	elif word[i : i + 2] == 'EV':
165	1	word = word[:i] + 'AF' + word[i + 2 :]
166	1	skip = 1
167	1	elif word[i] in self._uc_v_set:
168	1	word = word[:i] + 'A' + word[i + 1 :]
169		elif self._modified and i != len(word) - 1 and word[i] == 'Y':
170	1	word = word[:i] + 'A' + word[i + 1 :]
171		elif word[i] == 'Q':
172	1	word = word[:i] + 'G' + word[i + 1 :]
173	1	elif word[i] == 'Z':
174	1	word = word[:i] + 'S' + word[i + 1 :]
175	1	elif word[i] == 'M':
176	1	word = word[:i] + 'N' + word[i + 1 :]
177	1	elif word[i : i + 2] == 'KN':
178	1	word = word[:i] + 'N' + word[i + 2 :]
179	1	elif word[i] == 'K':
180	1	word = word[:i] + 'C' + word[i + 1 :]
181	1	elif (
182	1	self._modified
183	1	and i == len(word) - 3
184	1	and word[i : i + 3] == 'SCH'
185	1	):
186	1	word = word[:i] + 'SSA'
187	1	skip = 2
188	1	elif word[i : i + 3] == 'SCH':
189	1	word = word[:i] + 'SSS' + word[i + 3 :]
190	1	skip = 2
191	1	elif (
192	1	self._modified
193	1	and i == len(word) - 2
194	1	and word[i : i + 2] == 'SH'
195	1	):
196	1	word = word[:i] + 'SA'
197		skip = 1
198		elif word[i : i + 2] == 'SH':
199		word = word[:i] + 'SS' + word[i + 2 :]
200		skip = 1
201	1	elif word[i : i + 2] == 'PH':
202	1	word = word[:i] + 'FF' + word[i + 2 :]
203	1	skip = 1
204	1	elif self._modified and word[i : i + 3] == 'GHT':
205	1	word = word[:i] + 'TTT' + word[i + 3 :]
206	1	skip = 2
207		elif self._modified and word[i : i + 2] == 'DG':
208		word = word[:i] + 'GG' + word[i + 2 :]
209		skip = 1
210		elif self._modified and word[i : i + 2] == 'WR':
211	1	word = word[:i] + 'RR' + word[i + 2 :]
212	1	skip = 1
213	1	elif word[i] == 'H' and (
214	1	word[i - 1] not in self._uc_v_set
215	1	or word[i + 1 : i + 2] not in self._uc_v_set
216	1	):
217	1	word = word[:i] + word[i - 1] + word[i + 1 :]
218	1	elif word[i] == 'W' and word[i - 1] in self._uc_v_set:
219	1	word = word[:i] + word[i - 1] + word[i + 1 :]
220	1
221	1	if word[i : i + skip + 1] != key[-1:]:
222	1	key += word[i : i + skip + 1]
223	1
224	1	key = self._delete_consecutive_repeats(key)
225	1
226	1	if key[-1:] == 'S':
227	1	key = key[:-1]
228	1	if key[-2:] == 'AY':
229		key = key[:-2] + 'Y'
230		if key[-1:] == 'A':
231		key = key[:-1]
232	1	if self._modified and key[:1] == 'A':
233	1	key = original_first_char + key[1:]
234	1
235		if self._max_length > 0:
236	1	key = key[: self._max_length]
237	1
238		return key
239	1
240
241	1	if __name__ == '__main__':
242	1	import doctest
243	1
244		doctest.testmod()
245

chrislit / abydos

abydos.phonetic._nysiis.NYSIIS.__init__() A last analyzed 2020-12-31 20:10 UTC

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like

abydos.phonetic._nysiis.NYSIIS.init() A
last analyzed 2020-12-31 20:10 UTC