chrislit /
abydos
| Conditions | 56 |
| Total Lines | 181 |
| Code Lines | 111 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 96 |
| CRAP Score | 56 |
| 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.phonetic._henry_early.HenryEarly.encode() 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 -*- |
||
| 59 | 1 | def encode(self, word, max_length=3): |
|
| 60 | """Calculate the early version of the Henry code for a word. |
||
| 61 | |||
| 62 | Parameters |
||
| 63 | ---------- |
||
| 64 | word : str |
||
| 65 | The word to transform |
||
| 66 | max_length : int |
||
| 67 | The length of the code returned (defaults to 3) |
||
| 68 | |||
| 69 | Returns |
||
| 70 | ------- |
||
| 71 | str |
||
| 72 | The early Henry code |
||
| 73 | |||
| 74 | Examples |
||
| 75 | -------- |
||
| 76 | >>> henry_early('Marchand') |
||
| 77 | 'MRC' |
||
| 78 | >>> henry_early('Beaulieu') |
||
| 79 | 'BL' |
||
| 80 | >>> henry_early('Beaumont') |
||
| 81 | 'BM' |
||
| 82 | >>> henry_early('Legrand') |
||
| 83 | 'LGR' |
||
| 84 | >>> henry_early('Pelletier') |
||
| 85 | 'PLT' |
||
| 86 | |||
| 87 | """ |
||
| 88 | 1 | word = unicode_normalize('NFKD', text_type(word.upper())) |
|
| 89 | 1 | word = ''.join(c for c in word if c in self._uc_set) |
|
| 90 | |||
| 91 | 1 | if not word: |
|
| 92 | 1 | return '' |
|
| 93 | |||
| 94 | # Rule Ia seems to be covered entirely in II |
||
| 95 | |||
| 96 | # Rule Ib |
||
| 97 | 1 | if word[0] in self._uc_vy_set: |
|
| 98 | # Ib1 |
||
| 99 | 1 | if ( |
|
| 100 | word[1:2] in self._uc_c_set - {'M', 'N'} |
||
| 101 | and word[2:3] in self._uc_c_set |
||
| 102 | ) or ( |
||
| 103 | word[1:2] in self._uc_c_set and word[2:3] not in self._uc_c_set |
||
| 104 | ): |
||
| 105 | 1 | if word[0] == 'Y': |
|
| 106 | 1 | word = 'I' + word[1:] |
|
| 107 | # Ib2 |
||
| 108 | 1 | elif word[1:2] in {'M', 'N'} and word[2:3] in self._uc_c_set: |
|
| 109 | 1 | if word[0] == 'E': |
|
| 110 | 1 | word = 'A' + word[1:] |
|
| 111 | 1 | elif word[0] in {'I', 'U', 'Y'}: |
|
| 112 | 1 | word = 'E' + word[1:] |
|
| 113 | # Ib3 |
||
| 114 | 1 | elif word[:2] in self._diph: |
|
| 115 | 1 | word = self._diph[word[:2]] + word[2:] |
|
| 116 | # Ib4 |
||
| 117 | 1 | elif word[1:2] in self._uc_vy_set and word[0] == 'Y': |
|
| 118 | 1 | word = 'I' + word[1:] |
|
| 119 | |||
| 120 | 1 | code = '' |
|
| 121 | 1 | skip = 0 |
|
| 122 | |||
| 123 | # Rule II |
||
| 124 | 1 | for pos, char in enumerate(word): |
|
| 125 | 1 | nxch = word[pos + 1 : pos + 2] |
|
| 126 | 1 | prev = word[pos - 1 : pos] |
|
| 127 | |||
| 128 | 1 | if skip: |
|
| 129 | 1 | skip -= 1 |
|
| 130 | 1 | elif char in self._uc_vy_set: |
|
| 131 | 1 | code += char |
|
| 132 | # IIc |
||
| 133 | 1 | elif char == nxch: |
|
| 134 | 1 | skip = 1 |
|
| 135 | 1 | code += char |
|
| 136 | 1 | elif word[pos : pos + 2] in {'CQ', 'DT', 'SC'}: |
|
| 137 | 1 | continue |
|
| 138 | # IIb |
||
| 139 | 1 | elif char in self._simple: |
|
| 140 | 1 | code += self._simple[char] |
|
| 141 | 1 | elif char in {'C', 'G', 'P', 'Q', 'S'}: |
|
| 142 | 1 | if char == 'C': |
|
| 143 | 1 | if nxch in {'A', 'O', 'U', 'L', 'R'}: |
|
| 144 | 1 | code += 'K' |
|
| 145 | 1 | elif nxch in {'E', 'I', 'Y'}: |
|
| 146 | 1 | code += 'S' |
|
| 147 | 1 | elif nxch == 'H': |
|
| 148 | 1 | if word[pos + 2 : pos + 3] in self._uc_vy_set: |
|
| 149 | 1 | code += 'C' |
|
| 150 | else: # CHR, CHL, etc. |
||
| 151 | 1 | code += 'K' |
|
| 152 | else: |
||
| 153 | 1 | code += 'C' |
|
| 154 | 1 | elif char == 'G': |
|
| 155 | 1 | if nxch in {'A', 'O', 'U', 'L', 'R'}: |
|
| 156 | 1 | code += 'G' |
|
| 157 | 1 | elif nxch in {'E', 'I', 'Y'}: |
|
| 158 | 1 | code += 'J' |
|
| 159 | 1 | elif nxch == 'N': |
|
| 160 | 1 | code += 'N' |
|
| 161 | 1 | elif char == 'P': |
|
| 162 | 1 | if nxch != 'H': |
|
| 163 | 1 | code += 'P' |
|
| 164 | else: |
||
| 165 | 1 | code += 'F' |
|
| 166 | 1 | elif char == 'Q': |
|
| 167 | 1 | if word[pos + 1 : pos + 3] in {'UE', 'UI', 'UY'}: |
|
| 168 | 1 | code += 'G' |
|
| 169 | else: # QUA, QUO, etc. |
||
| 170 | 1 | code += 'K' |
|
| 171 | else: # S... |
||
| 172 | 1 | if word[pos : pos + 6] == 'SAINTE': |
|
| 173 | 1 | code += 'X' |
|
| 174 | 1 | skip = 5 |
|
| 175 | 1 | elif word[pos : pos + 5] == 'SAINT': |
|
| 176 | 1 | code += 'X' |
|
| 177 | 1 | skip = 4 |
|
| 178 | 1 | elif word[pos : pos + 3] == 'STE': |
|
| 179 | 1 | code += 'X' |
|
| 180 | 1 | skip = 2 |
|
| 181 | 1 | elif word[pos : pos + 2] == 'ST': |
|
| 182 | 1 | code += 'X' |
|
| 183 | 1 | skip = 1 |
|
| 184 | 1 | elif nxch in self._uc_c_set: |
|
| 185 | 1 | continue |
|
| 186 | else: |
||
| 187 | 1 | code += 'S' |
|
| 188 | # IId |
||
| 189 | 1 | elif char == 'H' and prev in self._uc_c_set: |
|
| 190 | 1 | continue |
|
| 191 | 1 | elif char in self._uc_c_set - { |
|
| 192 | 'L', |
||
| 193 | 'R', |
||
| 194 | } and nxch in self._uc_c_set - {'L', 'R'}: |
||
| 195 | 1 | continue |
|
| 196 | 1 | elif char == 'L' and nxch in {'M', 'N'}: |
|
| 197 | 1 | continue |
|
| 198 | 1 | elif ( |
|
| 199 | char in {'M', 'N'} |
||
| 200 | and prev in self._uc_vy_set |
||
| 201 | and nxch in self._uc_c_set |
||
| 202 | ): |
||
| 203 | 1 | continue |
|
| 204 | # IIa |
||
| 205 | else: |
||
| 206 | 1 | code += char |
|
| 207 | |||
| 208 | # IIe1 |
||
| 209 | 1 | if code[-4:] in {'AULT', 'EULT', 'OULT'}: |
|
| 210 | 1 | code = code[:-2] |
|
| 211 | # The following are blocked by rules above |
||
| 212 | # elif code[-4:-3] in _vows and code[-3:] == 'MPS': |
||
| 213 | # code = code[:-3] |
||
| 214 | # elif code[-3:-2] in _vows and code[-2:] in {'MB', 'MP', 'ND', |
||
| 215 | # 'NS', 'NT'}: |
||
| 216 | # code = code[:-2] |
||
| 217 | 1 | elif code[-2:-1] == 'R' and code[-1:] in self._uc_c_set: |
|
| 218 | 1 | code = code[:-1] |
|
| 219 | # IIe2 |
||
| 220 | 1 | elif code[-2:-1] in self._uc_vy_set and code[-1:] in { |
|
| 221 | 'D', |
||
| 222 | 'M', |
||
| 223 | 'N', |
||
| 224 | 'S', |
||
| 225 | 'T', |
||
| 226 | }: |
||
| 227 | 1 | code = code[:-1] |
|
| 228 | 1 | elif code[-2:] == 'ER': |
|
| 229 | 1 | code = code[:-1] |
|
| 230 | |||
| 231 | # Drop non-initial vowels |
||
| 232 | 1 | code = code[:1] + code[1:].translate( |
|
| 233 | {65: '', 69: '', 73: '', 79: '', 85: '', 89: ''} |
||
| 234 | ) |
||
| 235 | |||
| 236 | 1 | if max_length != -1: |
|
| 237 | 1 | code = code[:max_length] |
|
| 238 | |||
| 239 | 1 | return code |
|
| 240 | |||
| 280 |
