tests.fuzz.fuzz_test_phonetic.BigListOfNaughtyStringsTestCases.fuzz_test_blns() - Code Metrics - Inspection of "fuzz branch" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#100)

by Chris

created 2018-09-30 04:56 UTC

BigListOfNaughtyStringsTestCases.fuzz_test_blns() D

↳ Parent: tests.fuzz.fuzz_test_phonetic

Complexity

Conditions

Size

Total Lines	23
Code Lines	21

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	12
eloc	21
nop	1
dl	0
loc	23
rs	4.8
c	0
b	0
f	0

How to fix Complexity

# -*- 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.tests.fuzz.test_phonetic.

This module contains fuzz tests for abydos.phonetic
"""

import codecs
import os
import random
import unittest

from abydos.phonetic import alpha_sis, bmpm, caverphone, davidson, \
    dm_soundex, dolby, double_metaphone, eudex, fonem, fuzzy_soundex, \
    haase_phonetik, henry_early, koelner_phonetik, koelner_phonetik_alpha, \
    koelner_phonetik_num_to_alpha, lein, metaphone, metasoundex, mra, \
    norphone, nysiis, onca, parmar_kumbharana, phonem, phonet, \
    phonetic_spanish, phonex, phonix, pshp_soundex_first, pshp_soundex_last, \
    refined_soundex, reth_schek_phonetik, roger_root, russell_index, \
    russell_index_alpha, russell_index_num_to_alpha, sfinxbis, sound_d, \
    soundex, spanish_metaphone, spfc, statistics_canada

from . import fuzz, random_char

algorithms = {'russell_index': lambda name: russell_index(name),
              'russell_index_num_to_alpha':
                  lambda name: russell_index_num_to_alpha(russell_index(name)),
              'russell_index_alpha': russell_index_alpha,
              'soundex': soundex,
              'reverse_soundex': lambda name: soundex(name, reverse=True),
              'soundex_0pad_ml6':
                  lambda name: soundex(name, zero_pad=True, maxlength=6),
              'soundex_special': lambda name: soundex(name, var='special'),
              'soundex_census': lambda name: soundex(name, var='Census'),
              'refined_soundex': refined_soundex,
              'refined_soundex_vowels':
                  lambda name: refined_soundex(name, retain_vowels=True),
              'refined_soundex_0pad_ml6':
                  lambda name:
                  refined_soundex(name, zero_pad=True, maxlength=6),
              'dm_soundex': lambda name: dm_soundex(name),
              'koelner_phonetik': koelner_phonetik,
              'koelner_phonetik_num_to_alpha':
                  lambda name:
                  koelner_phonetik_num_to_alpha(koelner_phonetik(name)),
              'koelner_phonetik_alpha': koelner_phonetik_alpha,
              'nysiis': nysiis,
              'nysiis_modified': lambda name: nysiis(name, modified=True),
              'nysiis_ml_inf':
                  lambda name: nysiis(name, maxlength=float('inf')),
              'mra': mra,
              'metaphone': metaphone,
              'double_metaphone':
                  lambda name: double_metaphone(name),
              'caverphone_1': lambda name: caverphone(name, version=1),
              'caverphone_2': caverphone,
              'alpha_sis': lambda name: alpha_sis(name),
              'fuzzy_soundex': fuzzy_soundex,
              'fuzzy_soundex_0pad_ml8':
                  lambda name: fuzzy_soundex(name, maxlength=8, zero_pad=True),
              'phonex': phonex,
              'phonex_0pad_ml6':
                  lambda name: phonex(name, maxlength=6, zero_pad=True),
              'phonem': phonem,
              'phonix': phonix,
              'phonix_0pad_ml6':
                  lambda name: phonix(name, maxlength=6, zero_pad=True),
              'sfinxbis': lambda name: sfinxbis(name),
              'sfinxbis_ml6': lambda name: sfinxbis(name, maxlength=6),
              'phonet_1': phonet,
              'phonet_2': lambda name: phonet(name, mode=2),
              'phonet_1_none': lambda name: phonet(name, lang='none'),
              'phonet_2_none': lambda name: phonet(name, mode=2, lang='none'),
              'spfc': lambda name: spfc(' '.join((name, name))),
              'statistics_canada': statistics_canada,
              'statistics_canada_ml8':
                  lambda name: statistics_canada(name, maxlength=8),
              'lein': lein,
              'lein_nopad_ml8':
                  lambda name: lein(name, maxlength=8, zero_pad=False),
              'roger_root': roger_root,
              'roger_root_nopad_ml8':
                  lambda name: roger_root(name, maxlength=8, zero_pad=False),
              'onca': onca,
              'onca_nopad_ml8':
                  lambda name: onca(name, maxlength=8, zero_pad=False),
              'eudex': lambda name: eudex(name),
              'haase_phonetik': lambda name: haase_phonetik(name),
              'haase_phonetik_primary':
                  lambda name: haase_phonetik(name, primary_only=True)[:1],
              'reth_schek_phonetik': reth_schek_phonetik,
              'fonem': fonem,
              'parmar_kumbharana': parmar_kumbharana,
              'davidson': davidson,
              'sound_d': sound_d,
              'sound_d_ml8': lambda name: sound_d(name, maxlength=8),
              'pshp_soundex_last': pshp_soundex_last,
              'pshp_soundex_last_german':
                  lambda name: pshp_soundex_last(name, german=True),
              'pshp_soundex_last_ml8':
                  lambda name: pshp_soundex_last(name, maxlength=8),
              'pshp_soundex_first': pshp_soundex_first,
              'pshp_soundex_first_german':
                  lambda name: pshp_soundex_first(name, german=True),
              'pshp_soundex_first_ml8':
                  lambda name: pshp_soundex_first(name, maxlength=8),
              'henry_early': henry_early,
              'henry_early_ml8': lambda name: henry_early(name, maxlength=8),
              'norphone': norphone,
              'dolby': dolby,
              'dolby_ml4': lambda name: dolby(name, maxlength=4),
              'dolby_vowels': lambda name: dolby(name, keep_vowels=True),
              'phonetic_spanish': phonetic_spanish,
              'phonetic_spanish_ml4':
                  lambda name: phonetic_spanish(name, maxlength=4),
              'spanish_metaphone': spanish_metaphone,
              'spanish_metaphone_modified':
                  lambda name: spanish_metaphone(name, modified=True),
              'spanish_metaphone_ml4':
                  lambda name: spanish_metaphone(name, maxlength=4),
              'metasoundex': metasoundex,
              'metasoundex_es': lambda name: metasoundex(name, language='es'),
              'bmpm': bmpm,
              }


TESTDIR = os.path.dirname(__file__)

EXTREME_TEST = False  # Set to True to test EVERY single case (NB: takes hours)

if not EXTREME_TEST and os.path.isfile(TESTDIR + '/EXTREME_TEST'):
    # EXTREME_TEST file detected -- switching to EXTREME_TEST mode...
    EXTREME_TEST = True
if not EXTREME_TEST and os.path.isfile(TESTDIR + '/../EXTREME_TEST'):
    # EXTREME_TEST file detected -- switching to EXTREME_TEST mode...
    EXTREME_TEST = True


class BigListOfNaughtyStringsTestCases(unittest.TestCase):
    """Test each phonetic algorithm against the BLNS set.

    Here, we test each algorithm against each string, but we only care that it
    does not result in an exception.

    While not actually a fuzz test, this does serve the purpose of looking for
    errors resulting from unanticipated input.
    """

    def fuzz_test_blns(self):
        """Test each phonetic algorithm against the BLNS set."""
        blns = []
        omit_section = False
        with codecs.open(TESTDIR+'/corpora/blns.txt', encoding='UTF-8') as nsf:
            for line in nsf:
                line = line[:-1]
                if 'Script Injection' in line:
                    omit_section = True
                if 'SQL Injection' in line:
                    omit_section = False
                if line and line[0] != '#':
                    bmpm_omit = omit_section | (len(line.split()) > 5)
                    blns.append((bmpm_omit, line))

        for algo in algorithms:
            for bmpm_omit, ns in blns:
                try:
                    if not (bmpm_omit and 'bmpm' in algo):
                        algorithms[algo](ns)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for BLNS: {}'
                              .format(inst, algo, ns))


class FuzzedWordsTestCases(unittest.TestCase):
    """Test each phonetic algorithm against the base words set."""

    reps = 100000 * (100 if EXTREME_TEST else 1)

    basewords = []
    with codecs.open(TESTDIR + '/corpora/basewords.txt',
                     encoding='UTF-8') as basewords_file:
        for line in basewords_file:
            line = line[:-1]
            if line:
                basewords.append(line)

    def fuzz_test_base(self):
        """Test each phonetic algorithm against the unfuzzed base words."""
        for algo in algorithms:
            for word in self.basewords:
                try:
                    if not ('bmpm' in algo and len(word) > 12):
                        algorithms[algo](word)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for word: {}'
                              .format(inst, algo, word))

    def fuzz_test_20pct(self):

        """Fuzz test phonetic algorithms against 20% fuzzed words."""
        for _ in range(self.reps):
            fuzzed = fuzz(random.choice(self.basewords), fuzziness=0.2)

            if EXTREME_TEST:
                algs = list(algorithms.keys())
            else:
                algs = random.choices(list(algorithms.keys()), k=5)

            for algo in algs:
                try:
                    if not ('bmpm' in algo and len(fuzzed) > 12):
                        algorithms[algo](fuzzed)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for word: {}'
                              .format(inst, algo, fuzzed))

    def fuzz_test_100pct(self):

        """Fuzz test phonetic algorithms against 100% fuzzed words."""
        for _ in range(self.reps):
            fuzzed = fuzz(random.choice(self.basewords), fuzziness=1)

            if EXTREME_TEST:
                algs = list(algorithms.keys())
            else:
                algs = random.choices(list(algorithms.keys()), k=5)

            for algo in algs:
                try:
                    if not ('bmpm' in algo and len(fuzzed) > 12):
                        algorithms[algo](fuzzed)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for word: {}'
                              .format(inst, algo, fuzzed))

    def fuzz_test_fuzz_bmp(self):

        """Fuzz test phonetic algorithms against BMP fuzz."""
        for _ in range(self.reps):
            fuzzed = ''.join(random_char(0xffff) for _ in
                             range(0, random.randint(8, 16)))

            if EXTREME_TEST:
                algs = list(algorithms.keys())
            else:
                algs = random.choices(list(algorithms.keys()), k=5)

            for algo in algs:
                try:
                    algorithms[algo](fuzzed)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for word: {}'
                              .format(inst, algo, fuzzed))

    def fuzz_test_fuzz_bmpsmp_letter(self):

        """Fuzz test phonetic algorithms against alphabetic BMP+SMP fuzz."""
        for _ in range(self.reps):
            fuzzed = ''.join(random_char(0x1ffff, ' LETTER ') for _ in
                             range(0, random.randint(8, 16)))

            if EXTREME_TEST:
                algs = list(algorithms.keys())
            else:
                algs = random.choices(list(algorithms.keys()), k=5)

            for algo in algs:
                try:
                    algorithms[algo](fuzzed)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for word: {}'
                              .format(inst, algo, fuzzed))

    def fuzz_test_fuzz_bmpsmp_latin(self):

        """Fuzz test phonetic algorithms against Latin BMP+SMP fuzz."""
        for _ in range(self.reps):
            fuzzed = ''.join(random_char(0x1ffff, 'LATIN ') for _ in
                             range(0, random.randint(8, 16)))

            if EXTREME_TEST:
                algs = list(algorithms.keys())
            else:
                algs = random.choices(list(algorithms.keys()), k=5)

            for algo in algs:
                try:
                    algorithms[algo](fuzzed)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for word: {}'
                              .format(inst, algo, fuzzed))

    def fuzz_test_fuzz_unicode(self):

        """Fuzz test phonetic algorithms against valid Unicode fuzz."""
        for _ in range(self.reps):
            fuzzed = ''.join(random_char() for _ in
                             range(0, random.randint(8, 16)))

            if EXTREME_TEST:
                algs = list(algorithms.keys())
            else:
                algs = random.choices(list(algorithms.keys()), k=5)

            for algo in algs:
                try:
                    algorithms[algo](fuzzed)
                except Exception as inst:
                    self.fail('Exception "{}" thrown by {} for word: {}'
                              .format(inst, algo, fuzzed))


if __name__ == '__main__':
    unittest.main()


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		"""abydos.tests.fuzz.test_phonetic.
20
21		This module contains fuzz tests for abydos.phonetic
22		"""
23
24		import codecs
25		import os
26		import random
27		import unittest
28
29		from abydos.phonetic import alpha_sis, bmpm, caverphone, davidson, \
30		dm_soundex, dolby, double_metaphone, eudex, fonem, fuzzy_soundex, \
31		haase_phonetik, henry_early, koelner_phonetik, koelner_phonetik_alpha, \
32		koelner_phonetik_num_to_alpha, lein, metaphone, metasoundex, mra, \
33		norphone, nysiis, onca, parmar_kumbharana, phonem, phonet, \
34		phonetic_spanish, phonex, phonix, pshp_soundex_first, pshp_soundex_last, \
35		refined_soundex, reth_schek_phonetik, roger_root, russell_index, \
36		russell_index_alpha, russell_index_num_to_alpha, sfinxbis, sound_d, \
37		soundex, spanish_metaphone, spfc, statistics_canada
38
39		from . import fuzz, random_char
40
41		algorithms = {'russell_index': lambda name: russell_index(name),
42		'russell_index_num_to_alpha':
43		lambda name: russell_index_num_to_alpha(russell_index(name)),
44		'russell_index_alpha': russell_index_alpha,
45		'soundex': soundex,
46		'reverse_soundex': lambda name: soundex(name, reverse=True),
47		'soundex_0pad_ml6':
48		lambda name: soundex(name, zero_pad=True, maxlength=6),
49		'soundex_special': lambda name: soundex(name, var='special'),
50		'soundex_census': lambda name: soundex(name, var='Census'),
51		'refined_soundex': refined_soundex,
52		'refined_soundex_vowels':
53		lambda name: refined_soundex(name, retain_vowels=True),
54		'refined_soundex_0pad_ml6':
55		lambda name:
56		refined_soundex(name, zero_pad=True, maxlength=6),
57		'dm_soundex': lambda name: dm_soundex(name),
58		'koelner_phonetik': koelner_phonetik,
59		'koelner_phonetik_num_to_alpha':
60		lambda name:
61		koelner_phonetik_num_to_alpha(koelner_phonetik(name)),
62		'koelner_phonetik_alpha': koelner_phonetik_alpha,
63		'nysiis': nysiis,
64		'nysiis_modified': lambda name: nysiis(name, modified=True),
65		'nysiis_ml_inf':
66		lambda name: nysiis(name, maxlength=float('inf')),
67		'mra': mra,
68		'metaphone': metaphone,
69		'double_metaphone':
70		lambda name: double_metaphone(name),
71		'caverphone_1': lambda name: caverphone(name, version=1),
72		'caverphone_2': caverphone,
73		'alpha_sis': lambda name: alpha_sis(name),
74		'fuzzy_soundex': fuzzy_soundex,
75		'fuzzy_soundex_0pad_ml8':
76		lambda name: fuzzy_soundex(name, maxlength=8, zero_pad=True),
77		'phonex': phonex,
78		'phonex_0pad_ml6':
79		lambda name: phonex(name, maxlength=6, zero_pad=True),
80		'phonem': phonem,
81		'phonix': phonix,
82		'phonix_0pad_ml6':
83		lambda name: phonix(name, maxlength=6, zero_pad=True),
84		'sfinxbis': lambda name: sfinxbis(name),
85		'sfinxbis_ml6': lambda name: sfinxbis(name, maxlength=6),
86		'phonet_1': phonet,
87		'phonet_2': lambda name: phonet(name, mode=2),
88		'phonet_1_none': lambda name: phonet(name, lang='none'),
89		'phonet_2_none': lambda name: phonet(name, mode=2, lang='none'),
90		'spfc': lambda name: spfc(' '.join((name, name))),
91		'statistics_canada': statistics_canada,
92		'statistics_canada_ml8':
93		lambda name: statistics_canada(name, maxlength=8),
94		'lein': lein,
95		'lein_nopad_ml8':
96		lambda name: lein(name, maxlength=8, zero_pad=False),
97		'roger_root': roger_root,
98		'roger_root_nopad_ml8':
99		lambda name: roger_root(name, maxlength=8, zero_pad=False),
100		'onca': onca,
101		'onca_nopad_ml8':
102		lambda name: onca(name, maxlength=8, zero_pad=False),
103		'eudex': lambda name: eudex(name),
104		'haase_phonetik': lambda name: haase_phonetik(name),
105		'haase_phonetik_primary':
106		lambda name: haase_phonetik(name, primary_only=True)[:1],
107		'reth_schek_phonetik': reth_schek_phonetik,
108		'fonem': fonem,
109		'parmar_kumbharana': parmar_kumbharana,
110		'davidson': davidson,
111		'sound_d': sound_d,
112		'sound_d_ml8': lambda name: sound_d(name, maxlength=8),
113		'pshp_soundex_last': pshp_soundex_last,
114		'pshp_soundex_last_german':
115		lambda name: pshp_soundex_last(name, german=True),
116		'pshp_soundex_last_ml8':
117		lambda name: pshp_soundex_last(name, maxlength=8),
118		'pshp_soundex_first': pshp_soundex_first,
119		'pshp_soundex_first_german':
120		lambda name: pshp_soundex_first(name, german=True),
121		'pshp_soundex_first_ml8':
122		lambda name: pshp_soundex_first(name, maxlength=8),
123		'henry_early': henry_early,
124		'henry_early_ml8': lambda name: henry_early(name, maxlength=8),
125		'norphone': norphone,
126		'dolby': dolby,
127		'dolby_ml4': lambda name: dolby(name, maxlength=4),
128		'dolby_vowels': lambda name: dolby(name, keep_vowels=True),
129		'phonetic_spanish': phonetic_spanish,
130		'phonetic_spanish_ml4':
131		lambda name: phonetic_spanish(name, maxlength=4),
132		'spanish_metaphone': spanish_metaphone,
133		'spanish_metaphone_modified':
134		lambda name: spanish_metaphone(name, modified=True),
135		'spanish_metaphone_ml4':
136		lambda name: spanish_metaphone(name, maxlength=4),
137		'metasoundex': metasoundex,
138		'metasoundex_es': lambda name: metasoundex(name, language='es'),
139		'bmpm': bmpm,
140		}
141
142
143		TESTDIR = os.path.dirname(__file__)
144
145		EXTREME_TEST = False # Set to True to test EVERY single case (NB: takes hours)
146
147		if not EXTREME_TEST and os.path.isfile(TESTDIR + '/EXTREME_TEST'):
148		# EXTREME_TEST file detected -- switching to EXTREME_TEST mode...
149		EXTREME_TEST = True
150		if not EXTREME_TEST and os.path.isfile(TESTDIR + '/../EXTREME_TEST'):
151		# EXTREME_TEST file detected -- switching to EXTREME_TEST mode...
152		EXTREME_TEST = True
153
154
155		class BigListOfNaughtyStringsTestCases(unittest.TestCase):
156		"""Test each phonetic algorithm against the BLNS set.
157
158		Here, we test each algorithm against each string, but we only care that it
159		does not result in an exception.
160
161		While not actually a fuzz test, this does serve the purpose of looking for
162		errors resulting from unanticipated input.
163		"""
164
165		def fuzz_test_blns(self):
166		"""Test each phonetic algorithm against the BLNS set."""
167		blns = []
168		omit_section = False
169		with codecs.open(TESTDIR+'/corpora/blns.txt', encoding='UTF-8') as nsf:
170		for line in nsf:
171		line = line[:-1]
172		if 'Script Injection' in line:
173		omit_section = True
174		if 'SQL Injection' in line:
175		omit_section = False
176		if line and line[0] != '#':
177		bmpm_omit = omit_section \| (len(line.split()) > 5)
178		blns.append((bmpm_omit, line))
179
180		for algo in algorithms:
181		for bmpm_omit, ns in blns:
182		try:
183		if not (bmpm_omit and 'bmpm' in algo):
184		algorithms[algo](ns)
185		except Exception as inst:
186		self.fail('Exception "{}" thrown by {} for BLNS: {}'
187		.format(inst, algo, ns))
188
189
190		class FuzzedWordsTestCases(unittest.TestCase):
191		"""Test each phonetic algorithm against the base words set."""
192
193		reps = 100000 * (100 if EXTREME_TEST else 1)
194
195		basewords = []
196		with codecs.open(TESTDIR + '/corpora/basewords.txt',
197		encoding='UTF-8') as basewords_file:
198		for line in basewords_file:
199		line = line[:-1]
200		if line:
201		basewords.append(line)
202
203		def fuzz_test_base(self):
204		"""Test each phonetic algorithm against the unfuzzed base words."""
205		for algo in algorithms:
206		for word in self.basewords:
207		try:
208		if not ('bmpm' in algo and len(word) > 12):
209		algorithms[algo](word)
210		except Exception as inst:
211		self.fail('Exception "{}" thrown by {} for word: {}'
212		.format(inst, algo, word))
213
214	View Code Duplication	def fuzz_test_20pct(self):
		0 ignored issues – show Duplication introduced 2018-09-30 05:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
215		"""Fuzz test phonetic algorithms against 20% fuzzed words."""
216		for _ in range(self.reps):
217		fuzzed = fuzz(random.choice(self.basewords), fuzziness=0.2)
218
219		if EXTREME_TEST:
220		algs = list(algorithms.keys())
221		else:
222		algs = random.choices(list(algorithms.keys()), k=5)
223
224		for algo in algs:
225		try:
226		if not ('bmpm' in algo and len(fuzzed) > 12):
227		algorithms[algo](fuzzed)
228		except Exception as inst:
229		self.fail('Exception "{}" thrown by {} for word: {}'
230		.format(inst, algo, fuzzed))
231
232	View Code Duplication	def fuzz_test_100pct(self):
		0 ignored issues – show Duplication introduced 2018-09-30 05:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
233		"""Fuzz test phonetic algorithms against 100% fuzzed words."""
234		for _ in range(self.reps):
235		fuzzed = fuzz(random.choice(self.basewords), fuzziness=1)
236
237		if EXTREME_TEST:
238		algs = list(algorithms.keys())
239		else:
240		algs = random.choices(list(algorithms.keys()), k=5)
241
242		for algo in algs:
243		try:
244		if not ('bmpm' in algo and len(fuzzed) > 12):
245		algorithms[algo](fuzzed)
246		except Exception as inst:
247		self.fail('Exception "{}" thrown by {} for word: {}'
248		.format(inst, algo, fuzzed))
249
250	View Code Duplication	def fuzz_test_fuzz_bmp(self):
		0 ignored issues – show Duplication introduced 2018-09-30 05:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
251		"""Fuzz test phonetic algorithms against BMP fuzz."""
252		for _ in range(self.reps):
253		fuzzed = ''.join(random_char(0xffff) for _ in
254		range(0, random.randint(8, 16)))
255
256		if EXTREME_TEST:
257		algs = list(algorithms.keys())
258		else:
259		algs = random.choices(list(algorithms.keys()), k=5)
260
261		for algo in algs:
262		try:
263		algorithms[algo](fuzzed)
264		except Exception as inst:
265		self.fail('Exception "{}" thrown by {} for word: {}'
266		.format(inst, algo, fuzzed))
267
268	View Code Duplication	def fuzz_test_fuzz_bmpsmp_letter(self):
		0 ignored issues – show Duplication introduced 2018-09-30 05:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
269		"""Fuzz test phonetic algorithms against alphabetic BMP+SMP fuzz."""
270		for _ in range(self.reps):
271		fuzzed = ''.join(random_char(0x1ffff, ' LETTER ') for _ in
272		range(0, random.randint(8, 16)))
273
274		if EXTREME_TEST:
275		algs = list(algorithms.keys())
276		else:
277		algs = random.choices(list(algorithms.keys()), k=5)
278
279		for algo in algs:
280		try:
281		algorithms[algo](fuzzed)
282		except Exception as inst:
283		self.fail('Exception "{}" thrown by {} for word: {}'
284		.format(inst, algo, fuzzed))
285
286	View Code Duplication	def fuzz_test_fuzz_bmpsmp_latin(self):
		0 ignored issues – show Duplication introduced 2018-09-30 05:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
287		"""Fuzz test phonetic algorithms against Latin BMP+SMP fuzz."""
288		for _ in range(self.reps):
289		fuzzed = ''.join(random_char(0x1ffff, 'LATIN ') for _ in
290		range(0, random.randint(8, 16)))
291
292		if EXTREME_TEST:
293		algs = list(algorithms.keys())
294		else:
295		algs = random.choices(list(algorithms.keys()), k=5)
296
297		for algo in algs:
298		try:
299		algorithms[algo](fuzzed)
300		except Exception as inst:
301		self.fail('Exception "{}" thrown by {} for word: {}'
302		.format(inst, algo, fuzzed))
303
304	View Code Duplication	def fuzz_test_fuzz_unicode(self):
		0 ignored issues – show Duplication introduced 2018-09-30 05:07 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
305		"""Fuzz test phonetic algorithms against valid Unicode fuzz."""
306		for _ in range(self.reps):
307		fuzzed = ''.join(random_char() for _ in
308		range(0, random.randint(8, 16)))
309
310		if EXTREME_TEST:
311		algs = list(algorithms.keys())
312		else:
313		algs = random.choices(list(algorithms.keys()), k=5)
314
315		for algo in algs:
316		try:
317		algorithms[algo](fuzzed)
318		except Exception as inst:
319		self.fail('Exception "{}" thrown by {} for word: {}'
320		.format(inst, algo, fuzzed))
321
322
323		if __name__ == '__main__':
324		unittest.main()
325

chrislit / abydos

Pull Request — master (#100)

BigListOfNaughtyStringsTestCases.fuzz_test_blns() D

Complexity

Size

Duplication

Importance

How to fix Complexity

Complexity

Duplication Side-by-Side

Filter issues like