abydos.phonetic._roger_root.roger_root() - 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

abydos.phonetic._roger_root.roger_root() A

↳ Parent: abydos.phonetic._roger_root

Complexity

Conditions

Size

Total Lines	32
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	32
ccs	2
cts	2
cp	1
crap	1
rs	10
c	0
b	0
f	0

# -*- 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._roger_root.

Roger Root phonetic algorithm
"""

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

from unicodedata import normalize as unicode_normalize

from six import text_type
from six.moves import range

from ._phonetic import _Phonetic

__all__ = ['RogerRoot', 'roger_root']


class RogerRoot(_Phonetic):

    """Roger Root code.

    This is Roger Root name coding, described in :cite:`Moore:1977`.
    """

    # '*' is used to prevent combining by _delete_consecutive_repeats()
    _init_patterns = {
        4: {'TSCH': '06'},
        3: {'TSH': '06', 'SCH': '06'},
        2: {
            'CE': '0*0',
            'CH': '06',
            'CI': '0*0',
            'CY': '0*0',
            'DG': '07',
            'GF': '08',
            'GM': '03',
            'GN': '02',
            'KN': '02',
            'PF': '08',
            'PH': '08',
            'PN': '02',
            'SH': '06',
            'TS': '0*0',
            'WR': '04',
        },
        1: {
            'A': '1',
            'B': '09',
            'C': '07',
            'D': '01',
            'E': '1',
            'F': '08',
            'G': '07',
            'H': '2',
            'I': '1',
            'J': '3',
            'K': '07',
            'L': '05',
            'M': '03',
            'N': '02',
            'O': '1',
            'P': '09',
            'Q': '07',
            'R': '04',
            'S': '0*0',
            'T': '01',
            'U': '1',
            'V': '08',
            'W': '4',
            'X': '07',
            'Y': '5',
            'Z': '0*0',
        },
    }

    _med_patterns = {
        4: {'TSCH': '6'},
        3: {'TSH': '6', 'SCH': '6'},
        2: {
            'CE': '0',
            'CH': '6',
            'CI': '0',
            'CY': '0',
            'DG': '7',
            'PH': '8',
            'SH': '6',
            'TS': '0',
        },
        1: {
            'B': '9',
            'C': '7',
            'D': '1',
            'F': '8',
            'G': '7',
            'J': '6',
            'K': '7',
            'L': '5',
            'M': '3',
            'N': '2',
            'P': '9',
            'Q': '7',
            'R': '4',
            'S': '0',
            'T': '1',
            'V': '8',
            'X': '7',
            'Z': '0',
            'A': '*',
            'E': '*',
            'H': '*',
            'I': '*',
            'O': '*',
            'U': '*',
            'W': '*',
            'Y': '*',
        },
    }

    def encode(self, word, max_length=5, zero_pad=True):

        """Return the Roger Root code for a word.

        Parameters
        ----------
        word : str
            The word to transform
        max_length : int
            The maximum length (default 5) of the code to return
        zero_pad : bool
            Pad the end of the return value with 0s to achieve a max_length
            string

        Returns
        -------
        str
            The Roger Root code

        Examples
        --------
        >>> roger_root('Christopher')
        '06401'
        >>> roger_root('Niall')
        '02500'
        >>> roger_root('Smith')
        '00310'
        >>> roger_root('Schmidt')
        '06310'

        """
        # 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)

        code = ''
        pos = 0

        # Do first digit(s) first
        for num in range(4, 0, -1):
            if word[:num] in self._init_patterns[num]:
                code = self._init_patterns[num][word[:num]]
                pos += num
                break

        # Then code subsequent digits
        while pos < len(word):
            for num in range(4, 0, -1):  # pragma: no branch
                if word[pos : pos + num] in self._med_patterns[num]:
                    code += self._med_patterns[num][word[pos : pos + num]]
                    pos += num
                    break

        code = self._delete_consecutive_repeats(code)
        code = code.replace('*', '')

        if zero_pad:
            code += '0' * max_length

        return code[:max_length]


def roger_root(word, max_length=5, zero_pad=True):
    """Return the Roger Root code for a word.

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

    Parameters
    ----------
    word : str
        The word to transform
    max_length : int
        The maximum length (default 5) of the code to return
    zero_pad : bool
        Pad the end of the return value with 0s to achieve a max_length string

    Returns
    -------
    str
        The Roger Root code

    Examples
    --------
    >>> roger_root('Christopher')
    '06401'
    >>> roger_root('Niall')
    '02500'
    >>> roger_root('Smith')
    '00310'
    >>> roger_root('Schmidt')
    '06310'

    """
    return RogerRoot().encode(word, max_length, zero_pad)


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._roger_root.
20
21		Roger Root phonetic algorithm
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	1	from six.moves import range
35
36	1	from ._phonetic import _Phonetic
37
38	1	__all__ = ['RogerRoot', 'roger_root']
39
40
41	1	class RogerRoot(_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...
42		"""Roger Root code.
43
44		This is Roger Root name coding, described in :cite:`Moore:1977`.
45		"""
46
47		# '*' is used to prevent combining by _delete_consecutive_repeats()
48	1	_init_patterns = {
49		4: {'TSCH': '06'},
50		3: {'TSH': '06', 'SCH': '06'},
51		2: {
52		'CE': '0*0',
53		'CH': '06',
54		'CI': '0*0',
55		'CY': '0*0',
56		'DG': '07',
57		'GF': '08',
58		'GM': '03',
59		'GN': '02',
60		'KN': '02',
61		'PF': '08',
62		'PH': '08',
63		'PN': '02',
64		'SH': '06',
65		'TS': '0*0',
66		'WR': '04',
67		},
68		1: {
69		'A': '1',
70		'B': '09',
71		'C': '07',
72		'D': '01',
73		'E': '1',
74		'F': '08',
75		'G': '07',
76		'H': '2',
77		'I': '1',
78		'J': '3',
79		'K': '07',
80		'L': '05',
81		'M': '03',
82		'N': '02',
83		'O': '1',
84		'P': '09',
85		'Q': '07',
86		'R': '04',
87		'S': '0*0',
88		'T': '01',
89		'U': '1',
90		'V': '08',
91		'W': '4',
92		'X': '07',
93		'Y': '5',
94		'Z': '0*0',
95		},
96		}
97
98	1	_med_patterns = {
99		4: {'TSCH': '6'},
100		3: {'TSH': '6', 'SCH': '6'},
101		2: {
102		'CE': '0',
103		'CH': '6',
104		'CI': '0',
105		'CY': '0',
106		'DG': '7',
107		'PH': '8',
108		'SH': '6',
109		'TS': '0',
110		},
111		1: {
112		'B': '9',
113		'C': '7',
114		'D': '1',
115		'F': '8',
116		'G': '7',
117		'J': '6',
118		'K': '7',
119		'L': '5',
120		'M': '3',
121		'N': '2',
122		'P': '9',
123		'Q': '7',
124		'R': '4',
125		'S': '0',
126		'T': '1',
127		'V': '8',
128		'X': '7',
129		'Z': '0',
130		'A': '*',
131		'E': '*',
132		'H': '*',
133		'I': '*',
134		'O': '*',
135		'U': '*',
136		'W': '*',
137		'Y': '*',
138		},
139		}
140
141	1	def encode(self, word, max_length=5, zero_pad=True):
		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...
142		"""Return the Roger Root code for a word.
143
144		Parameters
145		----------
146		word : str
147		The word to transform
148		max_length : int
149		The maximum length (default 5) of the code to return
150		zero_pad : bool
151		Pad the end of the return value with 0s to achieve a max_length
152		string
153
154		Returns
155		-------
156		str
157		The Roger Root code
158
159		Examples
160		--------
161		>>> roger_root('Christopher')
162		'06401'
163		>>> roger_root('Niall')
164		'02500'
165		>>> roger_root('Smith')
166		'00310'
167		>>> roger_root('Schmidt')
168		'06310'
169
170		"""
171		# uppercase, normalize, decompose, and filter non-A-Z out
172	1	word = unicode_normalize('NFKD', text_type(word.upper()))
173	1	word = word.replace('ß', 'SS')
174	1	word = ''.join(c for c in word if c in self._uc_set)
175
176	1	code = ''
177	1	pos = 0
178
179		# Do first digit(s) first
180	1	for num in range(4, 0, -1):
181	1	if word[:num] in self._init_patterns[num]:
182	1	code = self._init_patterns[num][word[:num]]
183	1	pos += num
184	1	break
185
186		# Then code subsequent digits
187	1	while pos < len(word):
188	1	for num in range(4, 0, -1): # pragma: no branch
189	1	if word[pos : pos + num] in self._med_patterns[num]:
190	1	code += self._med_patterns[num][word[pos : pos + num]]
191	1	pos += num
192	1	break
193
194	1	code = self._delete_consecutive_repeats(code)
195	1	code = code.replace('*', '')
196
197	1	if zero_pad:
198	1	code += '0' * max_length
199
200	1	return code[:max_length]
201
202
203	1	def roger_root(word, max_length=5, zero_pad=True):
204		"""Return the Roger Root code for a word.
205
206		This is a wrapper for :py:meth:`RogerRoot.encode`.
207
208		Parameters
209		----------
210		word : str
211		The word to transform
212		max_length : int
213		The maximum length (default 5) of the code to return
214		zero_pad : bool
215		Pad the end of the return value with 0s to achieve a max_length string
216
217		Returns
218		-------
219		str
220		The Roger Root code
221
222		Examples
223		--------
224		>>> roger_root('Christopher')
225		'06401'
226		>>> roger_root('Niall')
227		'02500'
228		>>> roger_root('Smith')
229		'00310'
230		>>> roger_root('Schmidt')
231		'06310'
232
233		"""
234	1	return RogerRoot().encode(word, max_length, zero_pad)
235
236
237		if __name__ == '__main__':
238		import doctest
239
240		doctest.testmod()
241

chrislit / abydos

Push — master ( f43547...71985b )

abydos.phonetic._roger_root.roger_root() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like