mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-10 19:57:17 +03:00
Fix comments and examples for levenshtein_compare (#12113)
This commit is contained in:
parent
a3b15c9f53
commit
794cea6907
|
@ -22,7 +22,7 @@ cpdef bint levenshtein_compare(input_text: str, pattern_text: str, fuzzy: int =
|
|||
max_edits = fuzzy
|
||||
else:
|
||||
# allow at least two edits (to allow at least one transposition) and up
|
||||
# to 20% of the pattern string length
|
||||
# to 30% of the pattern string length
|
||||
max_edits = max(2, round(0.3 * len(pattern_text)))
|
||||
return levenshtein(input_text, pattern_text, max_edits) <= max_edits
|
||||
|
||||
|
|
|
@ -384,14 +384,14 @@ the more specific attributes `FUZZY1`..`FUZZY9` you can specify the maximum
|
|||
allowed edit distance directly.
|
||||
|
||||
```python
|
||||
# Match lowercase with fuzzy matching (allows 2 edits)
|
||||
# Match lowercase with fuzzy matching (allows 3 edits)
|
||||
pattern = [{"LOWER": {"FUZZY": "definitely"}}]
|
||||
|
||||
# Match custom attribute values with fuzzy matching (allows 2 edits)
|
||||
# Match custom attribute values with fuzzy matching (allows 3 edits)
|
||||
pattern = [{"_": {"country": {"FUZZY": "Kyrgyzstan"}}}]
|
||||
|
||||
# Match with exact Levenshtein edit distance limits (allows 3 edits)
|
||||
pattern = [{"_": {"country": {"FUZZY3": "Kyrgyzstan"}}}]
|
||||
# Match with exact Levenshtein edit distance limits (allows 4 edits)
|
||||
pattern = [{"_": {"country": {"FUZZY4": "Kyrgyzstan"}}}]
|
||||
```
|
||||
|
||||
#### Regex and fuzzy matching with lists {id="regex-fuzzy-lists", version="3.5"}
|
||||
|
|
Loading…
Reference in New Issue
Block a user