abydos.phonetic._pshp_soundex_first.pshp_soundex_first() - Code Metrics - Inspection of "Merge pull request #149 from chrislit/0.3.6" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( f43547...71985b )

by Chris

created 2018-11-17 08:52 UTC

pshp_soundex_first() A

↳ Parent: abydos.phonetic._pshp_soundex_first

Complexity

Conditions

Size

Total Lines	44
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

Metric	Value
cc	1
eloc	2
nop	3
dl	0
loc	44
ccs	2
cts	2
cp	1
crap	1
rs	10
c	0
b	0
f	0

# -*- 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._pshp_soundex_first.

PSHP Soundex/Viewex Coding for first names
"""

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__ = ['PSHPSoundexFirst', 'pshp_soundex_first']


class PSHPSoundexFirst(_Phonetic):

    """PSHP Soundex/Viewex Coding of a first name.

    This coding is based on :cite:`Hershberg:1976`.

    Reference was also made to the German version of the same:
    :cite:`Hershberg:1979`.

    A separate class, :py:class:`PSHPSoundexLast` is used for last names.
    """

    _trans = dict(
        zip(
            (ord(_) for _ in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'),

            '01230120022455012523010202',
        )
    )

    def encode(self, fname, max_length=4, german=False):

        """Calculate the PSHP Soundex/Viewex Coding of a first name.

        Parameters
        ----------
        fname : str
            The first name to encode
        max_length : int
            The length of the code returned (defaults to 4)
        german : bool
            Set to True if the name is German (different rules apply)

        Returns
        -------
        str
            The PSHP Soundex/Viewex Coding

        Examples
        --------
        >>> pe = PSHPSoundexFirst()
        >>> pe.encode('Smith')
        'S530'
        >>> pe.encode('Waters')
        'W352'
        >>> pe.encode('James')
        'J700'
        >>> pe.encode('Schmidt')
        'S500'
        >>> pe.encode('Ashcroft')
        'A220'
        >>> pe.encode('John')
        'J500'
        >>> pe.encode('Colin')
        'K400'
        >>> pe.encode('Niall')
        'N400'
        >>> pe.encode('Sally')
        'S400'
        >>> pe.encode('Jane')
        'J500'

        """
        fname = unicode_normalize('NFKD', text_type(fname.upper()))
        fname = fname.replace('ß', 'SS')
        fname = ''.join(c for c in fname if c in self._uc_set)

        # special rules
        if fname == 'JAMES':
            code = 'J7'
        elif fname == 'PAT':
            code = 'P7'

        else:
            # A. Prefix treatment
            if fname[:2] in {'GE', 'GI', 'GY'}:
                fname = 'J' + fname[1:]
            elif fname[:2] in {'CE', 'CI', 'CY'}:
                fname = 'S' + fname[1:]
            elif fname[:3] == 'CHR':
                fname = 'K' + fname[1:]
            elif fname[:1] == 'C' and fname[:2] != 'CH':
                fname = 'K' + fname[1:]

            if fname[:2] == 'KN':
                fname = 'N' + fname[1:]
            elif fname[:2] == 'PH':
                fname = 'F' + fname[1:]
            elif fname[:3] in {'WIE', 'WEI'}:
                fname = 'V' + fname[1:]

            if german and fname[:1] in {'W', 'M', 'Y', 'Z'}:
                fname = {'W': 'V', 'M': 'N', 'Y': 'J', 'Z': 'S'}[
                    fname[0]
                ] + fname[1:]

            code = fname[:1]

            # B. Soundex coding
            # code for Y unspecified, but presumably is 0
            fname = fname.translate(self._trans)
            fname = self._delete_consecutive_repeats(fname)

            code += fname[1:]
            syl_ptr = code.find('0')
            syl2_ptr = code[syl_ptr + 1 :].find('0')
            if syl_ptr != -1 and syl2_ptr != -1 and syl2_ptr - syl_ptr > -1:
                code = code[: syl_ptr + 2]

            code = code.replace('0', '')  # rule 1

        if max_length != -1:
            if len(code) < max_length:
                code += '0' * (max_length - len(code))
            else:
                code = code[:max_length]

        return code


def pshp_soundex_first(fname, max_length=4, german=False):
    """Calculate the PSHP Soundex/Viewex Coding of a first name.

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

    Parameters
    ----------
    fname : str
        The first name to encode
    max_length : int
        The length of the code returned (defaults to 4)
    german : bool
        Set to True if the name is German (different rules apply)

    Returns
    -------
    str
        The PSHP Soundex/Viewex Coding

    Examples
    --------
    >>> pshp_soundex_first('Smith')
    'S530'
    >>> pshp_soundex_first('Waters')
    'W352'
    >>> pshp_soundex_first('James')
    'J700'
    >>> pshp_soundex_first('Schmidt')
    'S500'
    >>> pshp_soundex_first('Ashcroft')
    'A220'
    >>> pshp_soundex_first('John')
    'J500'
    >>> pshp_soundex_first('Colin')
    'K400'
    >>> pshp_soundex_first('Niall')
    'N400'
    >>> pshp_soundex_first('Sally')
    'S400'
    >>> pshp_soundex_first('Jane')
    'J500'

    """
    return PSHPSoundexFirst().encode(fname, max_length, german)


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._pshp_soundex_first.
20
21		PSHP Soundex/Viewex Coding for first names
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__ = ['PSHPSoundexFirst', 'pshp_soundex_first']
38
39
40	1	class PSHPSoundexFirst(_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		"""PSHP Soundex/Viewex Coding of a first name.
42
43		This coding is based on :cite:`Hershberg:1976`.
44
45		Reference was also made to the German version of the same:
46		:cite:`Hershberg:1979`.
47
48		A separate class, :py:class:`PSHPSoundexLast` is used for last names.
49		"""
50
51	1	_trans = dict(
52		zip(
53		(ord(_) for _ in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'),
		0 ignored issues – show Comprehensibility Best Practice introduced 2018-10-24 06:00 UTC by Report Bug Copy Issue Report The variable `_` does not seem to be defined. Loading history...
54		'01230120022455012523010202',
55		)
56		)
57
58	1	def encode(self, fname, max_length=4, german=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...
59		"""Calculate the PSHP Soundex/Viewex Coding of a first name.
60
61		Parameters
62		----------
63		fname : str
64		The first name to encode
65		max_length : int
66		The length of the code returned (defaults to 4)
67		german : bool
68		Set to True if the name is German (different rules apply)
69
70		Returns
71		-------
72		str
73		The PSHP Soundex/Viewex Coding
74
75		Examples
76		--------
77		>>> pe = PSHPSoundexFirst()
78		>>> pe.encode('Smith')
79		'S530'
80		>>> pe.encode('Waters')
81		'W352'
82		>>> pe.encode('James')
83		'J700'
84		>>> pe.encode('Schmidt')
85		'S500'
86		>>> pe.encode('Ashcroft')
87		'A220'
88		>>> pe.encode('John')
89		'J500'
90		>>> pe.encode('Colin')
91		'K400'
92		>>> pe.encode('Niall')
93		'N400'
94		>>> pe.encode('Sally')
95		'S400'
96		>>> pe.encode('Jane')
97		'J500'
98
99		"""
100	1	fname = unicode_normalize('NFKD', text_type(fname.upper()))
101	1	fname = fname.replace('ß', 'SS')
102	1	fname = ''.join(c for c in fname if c in self._uc_set)
103
104		# special rules
105	1	if fname == 'JAMES':
106	1	code = 'J7'
107	1	elif fname == 'PAT':
108	1	code = 'P7'
109
110		else:
111		# A. Prefix treatment
112	1	if fname[:2] in {'GE', 'GI', 'GY'}:
113	1	fname = 'J' + fname[1:]
114	1	elif fname[:2] in {'CE', 'CI', 'CY'}:
115	1	fname = 'S' + fname[1:]
116	1	elif fname[:3] == 'CHR':
117	1	fname = 'K' + fname[1:]
118	1	elif fname[:1] == 'C' and fname[:2] != 'CH':
119	1	fname = 'K' + fname[1:]
120
121	1	if fname[:2] == 'KN':
122	1	fname = 'N' + fname[1:]
123	1	elif fname[:2] == 'PH':
124	1	fname = 'F' + fname[1:]
125	1	elif fname[:3] in {'WIE', 'WEI'}:
126	1	fname = 'V' + fname[1:]
127
128	1	if german and fname[:1] in {'W', 'M', 'Y', 'Z'}:
129	1	fname = {'W': 'V', 'M': 'N', 'Y': 'J', 'Z': 'S'}[
130		fname[0]
131		] + fname[1:]
132
133	1	code = fname[:1]
134
135		# B. Soundex coding
136		# code for Y unspecified, but presumably is 0
137	1	fname = fname.translate(self._trans)
138	1	fname = self._delete_consecutive_repeats(fname)
139
140	1	code += fname[1:]
141	1	syl_ptr = code.find('0')
142	1	syl2_ptr = code[syl_ptr + 1 :].find('0')
143	1	if syl_ptr != -1 and syl2_ptr != -1 and syl2_ptr - syl_ptr > -1:
144	1	code = code[: syl_ptr + 2]
145
146	1	code = code.replace('0', '') # rule 1
147
148	1	if max_length != -1:
149	1	if len(code) < max_length:
150	1	code += '0' * (max_length - len(code))
151		else:
152	1	code = code[:max_length]
153
154	1	return code
155
156
157	1	def pshp_soundex_first(fname, max_length=4, german=False):
158		"""Calculate the PSHP Soundex/Viewex Coding of a first name.
159
160		This is a wrapper for :py:meth:`PSHPSoundexFirst.encode`.
161
162		Parameters
163		----------
164		fname : str
165		The first name to encode
166		max_length : int
167		The length of the code returned (defaults to 4)
168		german : bool
169		Set to True if the name is German (different rules apply)
170
171		Returns
172		-------
173		str
174		The PSHP Soundex/Viewex Coding
175
176		Examples
177		--------
178		>>> pshp_soundex_first('Smith')
179		'S530'
180		>>> pshp_soundex_first('Waters')
181		'W352'
182		>>> pshp_soundex_first('James')
183		'J700'
184		>>> pshp_soundex_first('Schmidt')
185		'S500'
186		>>> pshp_soundex_first('Ashcroft')
187		'A220'
188		>>> pshp_soundex_first('John')
189		'J500'
190		>>> pshp_soundex_first('Colin')
191		'K400'
192		>>> pshp_soundex_first('Niall')
193		'N400'
194		>>> pshp_soundex_first('Sally')
195		'S400'
196		>>> pshp_soundex_first('Jane')
197		'J500'
198
199		"""
200	1	return PSHPSoundexFirst().encode(fname, max_length, german)
201
202
203		if __name__ == '__main__':
204		import doctest
205
206		doctest.testmod()
207

chrislit / abydos

Push — master ( f43547...71985b )

pshp_soundex_first() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like