chrislit /
abydos
| @@ 189-219 (lines=31) @@ | ||
| 186 | return 1 - sim_prefix(src, tar) |
|
| 187 | ||
| 188 | ||
| 189 | def sim_suffix(src, tar): |
|
| 190 | """Return the suffix similarity of two strings. |
|
| 191 | ||
| 192 | Suffix similarity is the ratio of the length of the shorter term that |
|
| 193 | exactly matches the longer term to the length of the shorter term, |
|
| 194 | beginning at the end of both terms. |
|
| 195 | ||
| 196 | :param str src: source string for comparison |
|
| 197 | :param str tar: target string for comparison |
|
| 198 | :returns: suffix similarity |
|
| 199 | :rtype: float |
|
| 200 | ||
| 201 | >>> sim_suffix('cat', 'hat') |
|
| 202 | 0.6666666666666666 |
|
| 203 | >>> sim_suffix('Niall', 'Neil') |
|
| 204 | 0.25 |
|
| 205 | >>> sim_suffix('aluminum', 'Catalan') |
|
| 206 | 0.0 |
|
| 207 | >>> sim_suffix('ATCG', 'TAGC') |
|
| 208 | 0.0 |
|
| 209 | """ |
|
| 210 | if src == tar: |
|
| 211 | return 1.0 |
|
| 212 | if not src or not tar: |
|
| 213 | return 0.0 |
|
| 214 | min_word, max_word = (src, tar) if len(src) < len(tar) else (tar, src) |
|
| 215 | min_len = len(min_word) |
|
| 216 | for i in range(min_len, 0, -1): |
|
| 217 | if min_word[-i:] == max_word[-i:]: |
|
| 218 | return i / min_len |
|
| 219 | return 0.0 |
|
| 220 | ||
| 221 | ||
| 222 | def dist_suffix(src, tar): |
|
| @@ 133-163 (lines=31) @@ | ||
| 130 | return 1 - sim_length(src, tar) |
|
| 131 | ||
| 132 | ||
| 133 | def sim_prefix(src, tar): |
|
| 134 | """Return the prefix similarity of two strings. |
|
| 135 | ||
| 136 | Prefix similarity is the ratio of the length of the shorter term that |
|
| 137 | exactly matches the longer term to the length of the shorter term, |
|
| 138 | beginning at the start of both terms. |
|
| 139 | ||
| 140 | :param str src: source string for comparison |
|
| 141 | :param str tar: target string for comparison |
|
| 142 | :returns: prefix similarity |
|
| 143 | :rtype: float |
|
| 144 | ||
| 145 | >>> sim_prefix('cat', 'hat') |
|
| 146 | 0.0 |
|
| 147 | >>> sim_prefix('Niall', 'Neil') |
|
| 148 | 0.25 |
|
| 149 | >>> sim_prefix('aluminum', 'Catalan') |
|
| 150 | 0.0 |
|
| 151 | >>> sim_prefix('ATCG', 'TAGC') |
|
| 152 | 0.0 |
|
| 153 | """ |
|
| 154 | if src == tar: |
|
| 155 | return 1.0 |
|
| 156 | if not src or not tar: |
|
| 157 | return 0.0 |
|
| 158 | min_word, max_word = (src, tar) if len(src) < len(tar) else (tar, src) |
|
| 159 | min_len = len(min_word) |
|
| 160 | for i in range(min_len, 0, -1): |
|
| 161 | if min_word[:i] == max_word[:i]: |
|
| 162 | return i / min_len |
|
| 163 | return 0.0 |
|
| 164 | ||
| 165 | ||
| 166 | def dist_prefix(src, tar): |
|
