Adds examples to token_set_ratio

rapidfuzz · May 28, 2024 · 2c8c070 · 2c8c070
1 parent c459f9a
commit 2c8c070
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -130,6 +130,12 @@ Scorers in RapidFuzz can be found in the modules `fuzz` and `distance`.
 84.21052631578947
 > fuzz.token_set_ratio("fuzzy was a bear", "fuzzy fuzzy was a bear")
 100.0
+# Returns 100.0 if one string is a subset of the other, regardless of extra content in the longer string
+> fuzz.token_set_ratio("fuzzy was a bear but not a dog", "fuzzy was a bear")
+100.0
+# Score is reduced only when there is explicit disagreement in the two strings
+> fuzz.token_set_ratio("fuzzy was a bear but not a dog", "fuzzy was a bear but not a cat")
+92.3076923076923
 ```
 
 #### Weighted Ratio

diff --git a/src/rapidfuzz/fuzz_py.py b/src/rapidfuzz/fuzz_py.py
@@ -434,6 +434,12 @@ def token_set_ratio(
     83.8709716796875
     >>> fuzz.token_set_ratio("fuzzy was a bear", "fuzzy fuzzy was a bear")
     100.0
+    # Returns 100.0 if one string is a subset of the other, regardless of extra content in the longer string
+    >>> fuzz.token_set_ratio("fuzzy was a bear but not a dog", "fuzzy was a bear")
+    100.0
+    # Score is reduced only when there is explicit disagreement in the two strings
+    >>> fuzz.token_set_ratio("fuzzy was a bear but not a dog", "fuzzy was a bear but not a cat")
+    92.3076923076923
     """
     setupPandas()
     if is_none(s1) or is_none(s2):