Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).
(word)
| 36 | |
| 37 | |
| 38 | def get_pairs(word): |
| 39 | """Return set of symbol pairs in a word. |
| 40 | Word is represented as tuple of symbols (symbols being variable-length strings). |
| 41 | """ |
| 42 | pairs = set() |
| 43 | prev_char = word[0] |
| 44 | for char in word[1:]: |
| 45 | pairs.add((prev_char, char)) |
| 46 | prev_char = char |
| 47 | return pairs |
| 48 | |
| 49 | |
| 50 | def basic_clean(text): |