chrislit /
abydos
| Conditions | 36 |
| Total Lines | 141 |
| Code Lines | 85 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 80 |
| CRAP Score | 36 |
| 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._pshp_soundex_last.PSHPSoundexLast.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 -*- |
||
| 58 | 1 | def encode(self, lname, max_length=4, german=False): |
|
| 59 | """Calculate the PSHP Soundex/Viewex Coding of a last name. |
||
| 60 | |||
| 61 | Args: |
||
| 62 | lname (str): The last name to encode |
||
| 63 | max_length (int): The length of the code returned (defaults to 4) |
||
| 64 | german (bool): Set to True if the name is German (different rules |
||
| 65 | apply) |
||
| 66 | |||
| 67 | Returns: |
||
| 68 | str: The PSHP Soundex/Viewex Coding |
||
| 69 | |||
| 70 | Examples: |
||
| 71 | >>> pe = PSHPSoundexLast() |
||
| 72 | >>> pe.encode('Smith') |
||
| 73 | 'S530' |
||
| 74 | >>> pe.encode('Waters') |
||
| 75 | 'W350' |
||
| 76 | >>> pe.encode('James') |
||
| 77 | 'J500' |
||
| 78 | >>> pe.encode('Schmidt') |
||
| 79 | 'S530' |
||
| 80 | >>> pe.encode('Ashcroft') |
||
| 81 | 'A225' |
||
| 82 | |||
| 83 | """ |
||
| 84 | 1 | lname = unicode_normalize('NFKD', text_type(lname.upper())) |
|
| 85 | 1 | lname = lname.replace('ß', 'SS') |
|
| 86 | 1 | lname = ''.join(c for c in lname if c in self._uc_set) |
|
| 87 | |||
| 88 | # A. Prefix treatment |
||
| 89 | 1 | if lname[:3] == 'VON' or lname[:3] == 'VAN': |
|
| 90 | 1 | lname = lname[3:].strip() |
|
| 91 | |||
| 92 | # The rule implemented below says "MC, MAC become 1". I believe it |
||
| 93 | # meant to say they become M except in German data (where superscripted |
||
| 94 | # 1 indicates "except in German data"). It doesn't make sense for them |
||
| 95 | # to become 1 (BPFV -> 1) or to apply outside German. Unfortunately, |
||
| 96 | # both articles have this error(?). |
||
| 97 | 1 | if not german: |
|
| 98 | 1 | if lname[:3] == 'MAC': |
|
| 99 | 1 | lname = 'M' + lname[3:] |
|
| 100 | 1 | elif lname[:2] == 'MC': |
|
| 101 | 1 | lname = 'M' + lname[2:] |
|
| 102 | |||
| 103 | # The non-German-only rule to strip ' is unnecessary due to filtering |
||
| 104 | |||
| 105 | 1 | if lname[:1] in {'E', 'I', 'O', 'U'}: |
|
| 106 | 1 | lname = 'A' + lname[1:] |
|
| 107 | 1 | elif lname[:2] in {'GE', 'GI', 'GY'}: |
|
| 108 | 1 | lname = 'J' + lname[1:] |
|
| 109 | 1 | elif lname[:2] in {'CE', 'CI', 'CY'}: |
|
| 110 | 1 | lname = 'S' + lname[1:] |
|
| 111 | 1 | elif lname[:3] == 'CHR': |
|
| 112 | 1 | lname = 'K' + lname[1:] |
|
| 113 | 1 | elif lname[:1] == 'C' and lname[:2] != 'CH': |
|
| 114 | 1 | lname = 'K' + lname[1:] |
|
| 115 | |||
| 116 | 1 | if lname[:2] == 'KN': |
|
| 117 | 1 | lname = 'N' + lname[1:] |
|
| 118 | 1 | elif lname[:2] == 'PH': |
|
| 119 | 1 | lname = 'F' + lname[1:] |
|
| 120 | 1 | elif lname[:3] in {'WIE', 'WEI'}: |
|
| 121 | 1 | lname = 'V' + lname[1:] |
|
| 122 | |||
| 123 | 1 | if german and lname[:1] in {'W', 'M', 'Y', 'Z'}: |
|
| 124 | 1 | lname = {'W': 'V', 'M': 'N', 'Y': 'J', 'Z': 'S'}[lname[0]] + lname[ |
|
| 125 | 1: |
||
| 126 | ] |
||
| 127 | |||
| 128 | 1 | code = lname[:1] |
|
| 129 | |||
| 130 | # B. Postfix treatment |
||
| 131 | 1 | if german: # moved from end of postfix treatment due to blocking |
|
| 132 | 1 | if lname[-3:] == 'TES': |
|
| 133 | 1 | lname = lname[:-3] |
|
| 134 | 1 | elif lname[-2:] == 'TS': |
|
| 135 | 1 | lname = lname[:-2] |
|
| 136 | 1 | if lname[-3:] == 'TZE': |
|
| 137 | 1 | lname = lname[:-3] |
|
| 138 | 1 | elif lname[-2:] == 'ZE': |
|
| 139 | 1 | lname = lname[:-2] |
|
| 140 | 1 | if lname[-1:] == 'Z': |
|
| 141 | 1 | lname = lname[:-1] |
|
| 142 | 1 | elif lname[-2:] == 'TE': |
|
| 143 | 1 | lname = lname[:-2] |
|
| 144 | |||
| 145 | 1 | if lname[-1:] == 'R': |
|
| 146 | 1 | lname = lname[:-1] + 'N' |
|
| 147 | 1 | elif lname[-2:] in {'SE', 'CE'}: |
|
| 148 | 1 | lname = lname[:-2] |
|
| 149 | 1 | if lname[-2:] == 'SS': |
|
| 150 | 1 | lname = lname[:-2] |
|
| 151 | 1 | elif lname[-1:] == 'S': |
|
| 152 | 1 | lname = lname[:-1] |
|
| 153 | |||
| 154 | 1 | if not german: |
|
| 155 | 1 | l5_repl = {'STOWN': 'SAWON', 'MPSON': 'MASON'} |
|
| 156 | 1 | l4_repl = { |
|
| 157 | 'NSEN': 'ASEN', |
||
| 158 | 'MSON': 'ASON', |
||
| 159 | 'STEN': 'SAEN', |
||
| 160 | 'STON': 'SAON', |
||
| 161 | } |
||
| 162 | 1 | if lname[-5:] in l5_repl: |
|
| 163 | 1 | lname = lname[:-5] + l5_repl[lname[-5:]] |
|
| 164 | 1 | elif lname[-4:] in l4_repl: |
|
| 165 | 1 | lname = lname[:-4] + l4_repl[lname[-4:]] |
|
| 166 | |||
| 167 | 1 | if lname[-2:] in {'NG', 'ND'}: |
|
| 168 | 1 | lname = lname[:-1] |
|
| 169 | 1 | if not german and lname[-3:] in {'GAN', 'GEN'}: |
|
| 170 | 1 | lname = lname[:-3] + 'A' + lname[-2:] |
|
| 171 | |||
| 172 | # C. Infix Treatment |
||
| 173 | 1 | lname = lname.replace('CK', 'C') |
|
| 174 | 1 | lname = lname.replace('SCH', 'S') |
|
| 175 | 1 | lname = lname.replace('DT', 'T') |
|
| 176 | 1 | lname = lname.replace('ND', 'N') |
|
| 177 | 1 | lname = lname.replace('NG', 'N') |
|
| 178 | 1 | lname = lname.replace('LM', 'M') |
|
| 179 | 1 | lname = lname.replace('MN', 'M') |
|
| 180 | 1 | lname = lname.replace('WIE', 'VIE') |
|
| 181 | 1 | lname = lname.replace('WEI', 'VEI') |
|
| 182 | |||
| 183 | # D. Soundexing |
||
| 184 | # code for X & Y are unspecified, but presumably are 2 & 0 |
||
| 185 | |||
| 186 | 1 | lname = lname.translate(self._trans) |
|
| 187 | 1 | lname = self._delete_consecutive_repeats(lname) |
|
| 188 | |||
| 189 | 1 | code += lname[1:] |
|
| 190 | 1 | code = code.replace('0', '') # rule 1 |
|
| 191 | |||
| 192 | 1 | if max_length != -1: |
|
| 193 | 1 | if len(code) < max_length: |
|
| 194 | 1 | code += '0' * (max_length - len(code)) |
|
| 195 | else: |
||
| 196 | 1 | code = code[:max_length] |
|
| 197 | |||
| 198 | 1 | return code |
|
| 199 | |||
| 235 |
Loading history...