chrislit /
abydos
| Conditions | 14 |
| Total Lines | 197 |
| Code Lines | 152 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 40 |
| CRAP Score | 14 |
| Changes | 0 | ||
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
Complex classes like abydos.stemmer._schinke.schinke() 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 -*- |
||
| 34 | 1 | def schinke(word): |
|
| 35 | """Return the stem of a word according to the Schinke stemmer. |
||
| 36 | |||
| 37 | This is defined in :cite:`Schinke:1996`. |
||
| 38 | |||
| 39 | :param str word: the word to stem |
||
| 40 | :returns: a dict of the noun- and verb-stemmed word |
||
| 41 | :rtype: dict |
||
| 42 | |||
| 43 | >>> schinke('atque') |
||
| 44 | {'n': 'atque', 'v': 'atque'} |
||
| 45 | >>> schinke('census') |
||
| 46 | {'n': 'cens', 'v': 'censu'} |
||
| 47 | >>> schinke('virum') |
||
| 48 | {'n': 'uir', 'v': 'uiru'} |
||
| 49 | >>> schinke('populusque') |
||
| 50 | {'n': 'popul', 'v': 'populu'} |
||
| 51 | >>> schinke('senatus') |
||
| 52 | {'n': 'senat', 'v': 'senatu'} |
||
| 53 | """ |
||
| 54 | 1 | word = normalize('NFKD', text_type(word.lower())) |
|
| 55 | 1 | word = ''.join( |
|
| 56 | c |
||
| 57 | for c in word |
||
| 58 | if c |
||
| 59 | in { |
||
| 60 | 'a', |
||
| 61 | 'b', |
||
| 62 | 'c', |
||
| 63 | 'd', |
||
| 64 | 'e', |
||
| 65 | 'f', |
||
| 66 | 'g', |
||
| 67 | 'h', |
||
| 68 | 'i', |
||
| 69 | 'j', |
||
| 70 | 'k', |
||
| 71 | 'l', |
||
| 72 | 'm', |
||
| 73 | 'n', |
||
| 74 | 'o', |
||
| 75 | 'p', |
||
| 76 | 'q', |
||
| 77 | 'r', |
||
| 78 | 's', |
||
| 79 | 't', |
||
| 80 | 'u', |
||
| 81 | 'v', |
||
| 82 | 'w', |
||
| 83 | 'x', |
||
| 84 | 'y', |
||
| 85 | 'z', |
||
| 86 | } |
||
| 87 | ) |
||
| 88 | |||
| 89 | # Rule 2 |
||
| 90 | 1 | word = word.replace('j', 'i').replace('v', 'u') |
|
| 91 | |||
| 92 | # Rule 3 |
||
| 93 | 1 | keep_que = { |
|
| 94 | 'at', |
||
| 95 | 'quo', |
||
| 96 | 'ne', |
||
| 97 | 'ita', |
||
| 98 | 'abs', |
||
| 99 | 'aps', |
||
| 100 | 'abus', |
||
| 101 | 'adae', |
||
| 102 | 'adus', |
||
| 103 | 'deni', |
||
| 104 | 'de', |
||
| 105 | 'sus', |
||
| 106 | 'obli', |
||
| 107 | 'perae', |
||
| 108 | 'plenis', |
||
| 109 | 'quando', |
||
| 110 | 'quis', |
||
| 111 | 'quae', |
||
| 112 | 'cuius', |
||
| 113 | 'cui', |
||
| 114 | 'quem', |
||
| 115 | 'quam', |
||
| 116 | 'qua', |
||
| 117 | 'qui', |
||
| 118 | 'quorum', |
||
| 119 | 'quarum', |
||
| 120 | 'quibus', |
||
| 121 | 'quos', |
||
| 122 | 'quas', |
||
| 123 | 'quotusquis', |
||
| 124 | 'quous', |
||
| 125 | 'ubi', |
||
| 126 | 'undi', |
||
| 127 | 'us', |
||
| 128 | 'uter', |
||
| 129 | 'uti', |
||
| 130 | 'utro', |
||
| 131 | 'utribi', |
||
| 132 | 'tor', |
||
| 133 | 'co', |
||
| 134 | 'conco', |
||
| 135 | 'contor', |
||
| 136 | 'detor', |
||
| 137 | 'deco', |
||
| 138 | 'exco', |
||
| 139 | 'extor', |
||
| 140 | 'obtor', |
||
| 141 | 'optor', |
||
| 142 | 'retor', |
||
| 143 | 'reco', |
||
| 144 | 'attor', |
||
| 145 | 'inco', |
||
| 146 | 'intor', |
||
| 147 | 'praetor', |
||
| 148 | } |
||
| 149 | 1 | if word[-3:] == 'que': |
|
| 150 | # This diverges from the paper by also returning 'que' itself unstemmed |
||
| 151 | 1 | if word[:-3] in keep_que or word == 'que': |
|
| 152 | 1 | return {'n': word, 'v': word} |
|
| 153 | else: |
||
| 154 | 1 | word = word[:-3] |
|
| 155 | |||
| 156 | # Base case will mean returning the words as is |
||
| 157 | 1 | noun = word |
|
| 158 | 1 | verb = word |
|
| 159 | |||
| 160 | # Rule 4 |
||
| 161 | 1 | n_endings = { |
|
| 162 | 4: {'ibus'}, |
||
| 163 | 3: {'ius'}, |
||
| 164 | 2: { |
||
| 165 | 'is', |
||
| 166 | 'nt', |
||
| 167 | 'ae', |
||
| 168 | 'os', |
||
| 169 | 'am', |
||
| 170 | 'ud', |
||
| 171 | 'as', |
||
| 172 | 'um', |
||
| 173 | 'em', |
||
| 174 | 'us', |
||
| 175 | 'es', |
||
| 176 | 'ia', |
||
| 177 | }, |
||
| 178 | 1: {'a', 'e', 'i', 'o', 'u'}, |
||
| 179 | } |
||
| 180 | 1 | for endlen in range(4, 0, -1): |
|
| 181 | 1 | if word[-endlen:] in n_endings[endlen]: |
|
| 182 | 1 | if len(word) - 2 >= endlen: |
|
| 183 | 1 | noun = word[:-endlen] |
|
| 184 | else: |
||
| 185 | 1 | noun = word |
|
| 186 | 1 | break |
|
| 187 | |||
| 188 | 1 | v_endings_strip = { |
|
| 189 | 6: {}, |
||
| 190 | 5: {}, |
||
| 191 | 4: {'mini', 'ntur', 'stis'}, |
||
| 192 | 3: {'mur', 'mus', 'ris', 'sti', 'tis', 'tur'}, |
||
| 193 | 2: {'ns', 'nt', 'ri'}, |
||
| 194 | 1: {'m', 'r', 's', 't'}, |
||
| 195 | } |
||
| 196 | 1 | v_endings_alter = { |
|
| 197 | 6: {'iuntur'}, |
||
| 198 | 5: {'beris', 'erunt', 'untur'}, |
||
| 199 | 4: {'iunt'}, |
||
| 200 | 3: {'bor', 'ero', 'unt'}, |
||
| 201 | 2: {'bo'}, |
||
| 202 | 1: {}, |
||
| 203 | } |
||
| 204 | 1 | for endlen in range(6, 0, -1): |
|
| 205 | 1 | if word[-endlen:] in v_endings_strip[endlen]: |
|
| 206 | 1 | if len(word) - 2 >= endlen: |
|
| 207 | 1 | verb = word[:-endlen] |
|
| 208 | else: |
||
| 209 | 1 | verb = word |
|
| 210 | 1 | break |
|
| 211 | 1 | if word[-endlen:] in v_endings_alter[endlen]: |
|
| 212 | 1 | if word[-endlen:] in {'iuntur', 'erunt', 'untur', 'iunt', 'unt'}: |
|
| 213 | 1 | new_word = word[:-endlen] + 'i' |
|
| 214 | 1 | addlen = 1 |
|
| 215 | 1 | elif word[-endlen:] in {'beris', 'bor', 'bo'}: |
|
| 216 | 1 | new_word = word[:-endlen] + 'bi' |
|
| 217 | 1 | addlen = 2 |
|
| 218 | else: |
||
| 219 | 1 | new_word = word[:-endlen] + 'eri' |
|
| 220 | 1 | addlen = 3 |
|
| 221 | |||
| 222 | # Technically this diverges from the paper by considering the |
||
| 223 | # length of the stem without the new suffix |
||
| 224 | 1 | if len(new_word) >= 2 + addlen: |
|
| 225 | 1 | verb = new_word |
|
| 226 | else: |
||
| 227 | 1 | verb = word |
|
| 228 | 1 | break |
|
| 229 | |||
| 230 | 1 | return {'n': noun, 'v': verb} |
|
| 231 | |||
| 237 |
