chrislit /
abydos
| @@ 38-76 (lines=39) @@ | ||
| 35 | __all__ = ['Prefix', 'dist_prefix', 'sim_prefix'] |
|
| 36 | ||
| 37 | ||
| 38 | class Prefix(_Distance): |
|
| 39 | """Prefix similiarity and distance.""" |
|
| 40 | ||
| 41 | def sim(self, src, tar): |
|
| 42 | """Return the prefix similarity of two strings. |
|
| 43 | ||
| 44 | Prefix similarity is the ratio of the length of the shorter term that |
|
| 45 | exactly matches the longer term to the length of the shorter term, |
|
| 46 | beginning at the start of both terms. |
|
| 47 | ||
| 48 | Parameters |
|
| 49 | ---------- |
|
| 50 | src : str |
|
| 51 | Source string for comparison |
|
| 52 | tar : str |
|
| 53 | Target string for comparison |
|
| 54 | ||
| 55 | Returns |
|
| 56 | ------- |
|
| 57 | float |
|
| 58 | Prefix similarity |
|
| 59 | ||
| 60 | Examples |
|
| 61 | -------- |
|
| 62 | >>> cmp = Prefix() |
|
| 63 | >>> cmp.sim('cat', 'hat') |
|
| 64 | 0.0 |
|
| 65 | >>> cmp.sim('Niall', 'Neil') |
|
| 66 | 0.25 |
|
| 67 | >>> cmp.sim('aluminum', 'Catalan') |
|
| 68 | 0.0 |
|
| 69 | >>> cmp.sim('ATCG', 'TAGC') |
|
| 70 | 0.0 |
|
| 71 | ||
| 72 | """ |
|
| 73 | if src == tar: |
|
| 74 | return 1.0 |
|
| 75 | if not src or not tar: |
|
| 76 | return 0.0 |
|
| 77 | min_word, max_word = (src, tar) if len(src) < len(tar) else (tar, src) |
|
| 78 | min_len = len(min_word) |
|
| 79 | for i in range(min_len, 0, -1): |
|
| @@ 38-76 (lines=39) @@ | ||
| 35 | __all__ = ['Suffix', 'dist_suffix', 'sim_suffix'] |
|
| 36 | ||
| 37 | ||
| 38 | class Suffix(_Distance): |
|
| 39 | """Suffix similarity and distance.""" |
|
| 40 | ||
| 41 | def sim(self, src, tar): |
|
| 42 | """Return the suffix similarity of two strings. |
|
| 43 | ||
| 44 | Suffix similarity is the ratio of the length of the shorter term that |
|
| 45 | exactly matches the longer term to the length of the shorter term, |
|
| 46 | beginning at the end of both terms. |
|
| 47 | ||
| 48 | Parameters |
|
| 49 | ---------- |
|
| 50 | src : str |
|
| 51 | Source string for comparison |
|
| 52 | tar : str |
|
| 53 | Target string for comparison |
|
| 54 | ||
| 55 | Returns |
|
| 56 | ------- |
|
| 57 | float |
|
| 58 | Suffix similarity |
|
| 59 | ||
| 60 | Examples |
|
| 61 | -------- |
|
| 62 | >>> cmp = Suffix() |
|
| 63 | >>> cmp.sim('cat', 'hat') |
|
| 64 | 0.6666666666666666 |
|
| 65 | >>> cmp.sim('Niall', 'Neil') |
|
| 66 | 0.25 |
|
| 67 | >>> cmp.sim('aluminum', 'Catalan') |
|
| 68 | 0.0 |
|
| 69 | >>> cmp.sim('ATCG', 'TAGC') |
|
| 70 | 0.0 |
|
| 71 | ||
| 72 | """ |
|
| 73 | if src == tar: |
|
| 74 | return 1.0 |
|
| 75 | if not src or not tar: |
|
| 76 | return 0.0 |
|
| 77 | min_word, max_word = (src, tar) if len(src) < len(tar) else (tar, src) |
|
| 78 | min_len = len(min_word) |
|
| 79 | for i in range(min_len, 0, -1): |
|
