Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).
(word)
| 96 | |
| 97 | |
| 98 | def get_pairs(word): |
| 99 | """Return set of symbol pairs in a word. |
| 100 | Word is represented as tuple of symbols (symbols being variable-length strings). |
| 101 | """ |
| 102 | pairs = set() |
| 103 | prev_char = word[0] |
| 104 | for char in word[1:]: |
| 105 | pairs.add((prev_char, char)) |
| 106 | prev_char = char |
| 107 | return pairs |
| 108 | |
| 109 | |
| 110 | def basic_clean(text): |