Total Complexity | 52 |
Total Lines | 335 |
Duplicated Lines | 30.45 % |
Changes | 0 |
Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
Complex classes like tests.fuzz.fuzz_test_phonetic often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
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 unittest |
||
26 | from random import choice, randint, sample |
||
27 | |||
28 | from abydos.phonetic.alpha_sis import alpha_sis |
||
29 | from abydos.phonetic.bmpm import bmpm |
||
30 | from abydos.phonetic.caverphone import caverphone |
||
31 | from abydos.phonetic.davidson import davidson |
||
32 | from abydos.phonetic.de import haase_phonetik, koelner_phonetik, \ |
||
33 | koelner_phonetik_alpha, koelner_phonetik_num_to_alpha, phonem, \ |
||
34 | reth_schek_phonetik |
||
35 | from abydos.phonetic.dm import dm_soundex |
||
36 | from abydos.phonetic.dolby import dolby |
||
37 | from abydos.phonetic.es import phonetic_spanish, spanish_metaphone |
||
38 | from abydos.phonetic.eudex import eudex |
||
39 | from abydos.phonetic.fr import fonem, henry_early |
||
40 | from abydos.phonetic.hybrid import metasoundex, onca |
||
41 | from abydos.phonetic.metaphone import double_metaphone, metaphone |
||
42 | from abydos.phonetic.mra import mra |
||
43 | from abydos.phonetic.nrl import nrl |
||
44 | from abydos.phonetic.nysiis import nysiis |
||
45 | from abydos.phonetic.parmar_kumbharana import parmar_kumbharana |
||
46 | from abydos.phonetic.phonet import phonet |
||
47 | from abydos.phonetic.pt import soundex_br |
||
48 | from abydos.phonetic.roger_root import roger_root |
||
49 | from abydos.phonetic.russell import russell_index, russell_index_alpha, \ |
||
50 | russell_index_num_to_alpha |
||
51 | from abydos.phonetic.sound_d import sound_d |
||
52 | from abydos.phonetic.soundex import fuzzy_soundex, lein, phonex, phonix, \ |
||
53 | pshp_soundex_first, pshp_soundex_last, refined_soundex, soundex |
||
54 | from abydos.phonetic.spfc import spfc |
||
55 | from abydos.phonetic.statistics_canada import statistics_canada |
||
56 | from abydos.phonetic.sv import norphone, sfinxbis |
||
57 | |||
58 | from . import EXTREME_TEST, _corpus_file, _fuzz, _random_char |
||
59 | |||
60 | algorithms = {'russell_index': lambda name: russell_index(name), |
||
61 | 'russell_index_num_to_alpha': |
||
62 | lambda name: russell_index_num_to_alpha(russell_index(name)), |
||
63 | 'russell_index_alpha': russell_index_alpha, |
||
64 | 'soundex': soundex, |
||
65 | 'reverse_soundex': lambda name: soundex(name, reverse=True), |
||
66 | 'soundex_0pad_ml6': |
||
67 | lambda name: soundex(name, zero_pad=True, max_length=6), |
||
68 | 'soundex_special': lambda name: soundex(name, var='special'), |
||
69 | 'soundex_census': lambda name: soundex(name, var='Census'), |
||
70 | 'refined_soundex': refined_soundex, |
||
71 | 'refined_soundex_vowels': |
||
72 | lambda name: refined_soundex(name, retain_vowels=True), |
||
73 | 'refined_soundex_0pad_ml6': |
||
74 | lambda name: |
||
75 | refined_soundex(name, zero_pad=True, max_length=6), |
||
76 | 'dm_soundex': lambda name: dm_soundex(name), |
||
77 | 'koelner_phonetik': koelner_phonetik, |
||
78 | 'koelner_phonetik_num_to_alpha': |
||
79 | lambda name: |
||
80 | koelner_phonetik_num_to_alpha(koelner_phonetik(name)), |
||
81 | 'koelner_phonetik_alpha': koelner_phonetik_alpha, |
||
82 | 'nysiis': nysiis, |
||
83 | 'nysiis_modified': lambda name: nysiis(name, modified=True), |
||
84 | 'nysiis_ml_inf': |
||
85 | lambda name: nysiis(name, max_length=-1), |
||
86 | 'mra': mra, |
||
87 | 'metaphone': metaphone, |
||
88 | 'double_metaphone': |
||
89 | lambda name: double_metaphone(name), |
||
90 | 'caverphone_1': lambda name: caverphone(name, version=1), |
||
91 | 'caverphone_2': caverphone, |
||
92 | 'alpha_sis': lambda name: alpha_sis(name), |
||
93 | 'fuzzy_soundex': fuzzy_soundex, |
||
94 | 'fuzzy_soundex_0pad_ml8': |
||
95 | lambda name: |
||
96 | fuzzy_soundex(name, max_length=8, zero_pad=True), |
||
97 | 'phonex': phonex, |
||
98 | 'phonex_0pad_ml6': |
||
99 | lambda name: phonex(name, max_length=6, zero_pad=True), |
||
100 | 'phonem': phonem, |
||
101 | 'phonix': phonix, |
||
102 | 'phonix_0pad_ml6': |
||
103 | lambda name: phonix(name, max_length=6, zero_pad=True), |
||
104 | 'sfinxbis': lambda name: sfinxbis(name), |
||
105 | 'sfinxbis_ml6': lambda name: sfinxbis(name, max_length=6), |
||
106 | 'phonet_1': phonet, |
||
107 | 'phonet_2': lambda name: phonet(name, mode=2), |
||
108 | 'phonet_1_none': lambda name: phonet(name, lang='none'), |
||
109 | 'phonet_2_none': lambda name: phonet(name, mode=2, lang='none'), |
||
110 | 'spfc': lambda name: spfc(' '.join((name, name))), |
||
111 | 'statistics_canada': statistics_canada, |
||
112 | 'statistics_canada_ml8': |
||
113 | lambda name: statistics_canada(name, max_length=8), |
||
114 | 'lein': lein, |
||
115 | 'lein_nopad_ml8': |
||
116 | lambda name: lein(name, max_length=8, zero_pad=False), |
||
117 | 'roger_root': roger_root, |
||
118 | 'roger_root_nopad_ml8': |
||
119 | lambda name: roger_root(name, max_length=8, zero_pad=False), |
||
120 | 'onca': onca, |
||
121 | 'onca_nopad_ml8': |
||
122 | lambda name: onca(name, max_length=8, zero_pad=False), |
||
123 | 'eudex': lambda name: eudex(name), |
||
124 | 'haase_phonetik': lambda name: haase_phonetik(name), |
||
125 | 'haase_phonetik_primary': |
||
126 | lambda name: haase_phonetik(name, primary_only=True)[:1], |
||
127 | 'reth_schek_phonetik': reth_schek_phonetik, |
||
128 | 'fonem': fonem, |
||
129 | 'parmar_kumbharana': parmar_kumbharana, |
||
130 | 'davidson': davidson, |
||
131 | 'sound_d': sound_d, |
||
132 | 'sound_d_ml8': lambda name: sound_d(name, max_length=8), |
||
133 | 'pshp_soundex_last': pshp_soundex_last, |
||
134 | 'pshp_soundex_last_german': |
||
135 | lambda name: pshp_soundex_last(name, german=True), |
||
136 | 'pshp_soundex_last_ml8': |
||
137 | lambda name: pshp_soundex_last(name, max_length=8), |
||
138 | 'pshp_soundex_first': pshp_soundex_first, |
||
139 | 'pshp_soundex_first_german': |
||
140 | lambda name: pshp_soundex_first(name, german=True), |
||
141 | 'pshp_soundex_first_ml8': |
||
142 | lambda name: pshp_soundex_first(name, max_length=8), |
||
143 | 'henry_early': henry_early, |
||
144 | 'henry_early_ml8': lambda name: henry_early(name, max_length=8), |
||
145 | 'norphone': norphone, |
||
146 | 'dolby': dolby, |
||
147 | 'dolby_ml4': lambda name: dolby(name, max_length=4), |
||
148 | 'dolby_vowels': lambda name: dolby(name, keep_vowels=True), |
||
149 | 'phonetic_spanish': phonetic_spanish, |
||
150 | 'phonetic_spanish_ml4': |
||
151 | lambda name: phonetic_spanish(name, max_length=4), |
||
152 | 'spanish_metaphone': spanish_metaphone, |
||
153 | 'spanish_metaphone_modified': |
||
154 | lambda name: spanish_metaphone(name, modified=True), |
||
155 | 'spanish_metaphone_ml4': |
||
156 | lambda name: spanish_metaphone(name, max_length=4), |
||
157 | 'metasoundex': metasoundex, |
||
158 | 'metasoundex_es': lambda name: metasoundex(name, lang='es'), |
||
159 | 'soundex_br': soundex_br, |
||
160 | 'nrl': nrl, |
||
161 | 'bmpm': bmpm, |
||
162 | } |
||
163 | |||
164 | |||
165 | class BigListOfNaughtyStringsTestCases(unittest.TestCase): |
||
166 | """Test each phonetic algorithm against the BLNS set. |
||
167 | |||
168 | Here, we test each algorithm against each string, but we only care that it |
||
169 | does not result in an exception. |
||
170 | |||
171 | While not actually a fuzz test, this does serve the purpose of looking for |
||
172 | errors resulting from unanticipated input. |
||
173 | """ |
||
174 | |||
175 | def fuzz_test_blns(self): |
||
176 | """Test each phonetic algorithm against the BLNS set.""" |
||
177 | blns = [] |
||
178 | omit_section = False |
||
179 | with codecs.open(_corpus_file('blns.txt'), encoding='UTF-8') as nsf: |
||
180 | for line in nsf: |
||
181 | line = line[:-1] |
||
182 | if 'Script Injection' in line: |
||
183 | omit_section = True |
||
184 | if 'SQL Injection' in line: |
||
185 | omit_section = False |
||
186 | if line and line[0] != '#': |
||
187 | bmpm_omit = omit_section | (len(line.split()) > 5) |
||
188 | blns.append((bmpm_omit, line)) |
||
189 | |||
190 | for algo in algorithms: |
||
191 | for bmpm_omit, ns in blns: |
||
192 | try: |
||
193 | if not (bmpm_omit and 'bmpm' in algo): |
||
194 | algorithms[algo](ns) |
||
195 | except Exception as inst: |
||
196 | self.fail('Exception "{}" thrown by {} for BLNS: {}' |
||
197 | .format(inst, algo, ns)) |
||
198 | |||
199 | |||
200 | class FuzzedWordsTestCases(unittest.TestCase): |
||
201 | """Test each phonetic algorithm against the base words set.""" |
||
202 | |||
203 | reps = 1000 * (10000 if EXTREME_TEST else 1) |
||
204 | |||
205 | basewords = [] |
||
206 | with codecs.open(_corpus_file('basewords.txt'), |
||
207 | encoding='UTF-8') as basewords_file: |
||
208 | for line in basewords_file: |
||
209 | line = line[:-1] |
||
210 | if line: |
||
211 | basewords.append(line) |
||
212 | |||
213 | def fuzz_test_base(self): |
||
214 | """Test each phonetic algorithm against the unfuzzed base words.""" |
||
215 | for algo in algorithms: |
||
216 | for word in self.basewords: |
||
217 | try: |
||
218 | if not ('bmpm' in algo and len(word) > 12): |
||
219 | algorithms[algo](word) |
||
220 | except Exception as inst: |
||
221 | self.fail('Exception "{}" thrown by {} for word: {}' |
||
222 | .format(inst, algo, word)) |
||
223 | |||
224 | def fuzz_test_20pct(self): |
||
225 | """Fuzz test phonetic algorithms against 20% fuzzed words.""" |
||
226 | for _ in range(self.reps): |
||
227 | fuzzed = _fuzz(choice(self.basewords), fuzziness=0.2) # noqa: S311 |
||
228 | |||
229 | if EXTREME_TEST: |
||
230 | algs = list(algorithms.keys()) |
||
231 | else: |
||
232 | algs = sample(list(algorithms.keys()), k=5) # noqa: S311 |
||
233 | |||
234 | for algo in algs: |
||
235 | try: |
||
236 | if not ('bmpm' in algo and len(fuzzed) > 12): |
||
237 | algorithms[algo](fuzzed) |
||
238 | except Exception as inst: |
||
239 | self.fail('Exception "{}" thrown by {} for word: {}' |
||
240 | .format(inst, algo, fuzzed)) |
||
241 | |||
242 | def fuzz_test_100pct(self): |
||
243 | """Fuzz test phonetic algorithms against 100% fuzzed words.""" |
||
244 | for _ in range(self.reps): |
||
245 | fuzzed = _fuzz(choice(self.basewords), fuzziness=1) # noqa: S311 |
||
246 | |||
247 | if EXTREME_TEST: |
||
248 | algs = list(algorithms.keys()) |
||
249 | else: |
||
250 | algs = sample(list(algorithms.keys()), k=5) # noqa: S311 |
||
251 | |||
252 | for algo in algs: |
||
253 | try: |
||
254 | if not ('bmpm' in algo and len(fuzzed) > 12): |
||
255 | algorithms[algo](fuzzed) |
||
256 | except Exception as inst: |
||
257 | self.fail('Exception "{}" thrown by {} for word: {}' |
||
258 | .format(inst, algo, fuzzed)) |
||
259 | |||
260 | def fuzz_test_fuzz_bmp(self): |
||
261 | """Fuzz test phonetic algorithms against BMP fuzz.""" |
||
262 | for _ in range(self.reps): |
||
263 | fuzzed = ''.join(_random_char(0xffff) for _ in |
||
264 | range(0, randint(8, 16))) # noqa: S311 |
||
265 | |||
266 | if EXTREME_TEST: |
||
267 | algs = list(algorithms.keys()) |
||
268 | else: |
||
269 | algs = sample(list(algorithms.keys()), k=5) # noqa: S311 |
||
270 | |||
271 | for algo in algs: |
||
272 | try: |
||
273 | algorithms[algo](fuzzed) |
||
274 | except Exception as inst: |
||
275 | self.fail('Exception "{}" thrown by {} for word: {}' |
||
276 | .format(inst, algo, fuzzed)) |
||
277 | |||
278 | def fuzz_test_fuzz_bmpsmp_letter(self): |
||
279 | """Fuzz test phonetic algorithms against alphabetic BMP+SMP fuzz.""" |
||
280 | for _ in range(self.reps): |
||
281 | fuzzed = ''.join(_random_char(0x1ffff, ' LETTER ') for _ in |
||
282 | range(0, randint(8, 16))) # noqa: S311 |
||
283 | |||
284 | if EXTREME_TEST: |
||
285 | algs = list(algorithms.keys()) |
||
286 | else: |
||
287 | algs = sample(list(algorithms.keys()), k=5) # noqa: S311 |
||
288 | |||
289 | for algo in algs: |
||
290 | try: |
||
291 | algorithms[algo](fuzzed) |
||
292 | except Exception as inst: |
||
293 | self.fail('Exception "{}" thrown by {} for word: {}' |
||
294 | .format(inst, algo, fuzzed)) |
||
295 | |||
296 | def fuzz_test_fuzz_bmpsmp_latin(self): |
||
297 | """Fuzz test phonetic algorithms against Latin BMP+SMP fuzz.""" |
||
298 | for _ in range(self.reps): |
||
299 | fuzzed = ''.join(_random_char(0x1ffff, 'LATIN ') for _ in |
||
300 | range(0, randint(8, 16))) # noqa: S311 |
||
301 | |||
302 | if EXTREME_TEST: |
||
303 | algs = list(algorithms.keys()) |
||
304 | else: |
||
305 | algs = sample(list(algorithms.keys()), k=5) # noqa: S311 |
||
306 | |||
307 | for algo in algs: |
||
308 | try: |
||
309 | algorithms[algo](fuzzed) |
||
310 | except Exception as inst: |
||
311 | self.fail('Exception "{}" thrown by {} for word: {}' |
||
312 | .format(inst, algo, fuzzed)) |
||
313 | |||
314 | def fuzz_test_fuzz_unicode(self): |
||
315 | """Fuzz test phonetic algorithms against valid Unicode fuzz.""" |
||
316 | for _ in range(self.reps): |
||
317 | fuzzed = ''.join(_random_char() for _ in |
||
318 | range(0, randint(8, 16))) # noqa: S311 |
||
319 | |||
320 | if EXTREME_TEST: |
||
321 | algs = list(algorithms.keys()) |
||
322 | else: |
||
323 | algs = sample(list(algorithms.keys()), k=5) # noqa: S311 |
||
324 | |||
325 | for algo in algs: |
||
326 | try: |
||
327 | algorithms[algo](fuzzed) |
||
328 | except Exception as inst: |
||
329 | self.fail('Exception "{}" thrown by {} for word: {}' |
||
330 | .format(inst, algo, fuzzed)) |
||
331 | |||
332 | |||
333 | if __name__ == '__main__': |
||
334 | unittest.main() |
||
335 |