diff --git a/test_unstructured/cleaners/test_core.py b/test_unstructured/cleaners/test_core.py index 6414292d99..212b5ce57b 100644 --- a/test_unstructured/cleaners/test_core.py +++ b/test_unstructured/cleaners/test_core.py @@ -75,7 +75,7 @@ def test_clean_ordered_bullets(text, expected): ("She had a flower in her hair.", "She had a flower in her hair."), ("The coffin was placed in the grave.", "The coffin was placed in the grave."), ("The buffle zone was clearly marked.", "The buffle zone was clearly marked."), - ("The craſtsman worked with dedication.", "The craftsman worked with dedication."), + ("The laſt chapter was the best.", "The last chapter was the best."), ("The symbol ʪ is very rare.", "The symbol ls is very rare."), ("The word 'cœur' means 'heart' in French.", "The word 'coeur' means 'heart' in French."), ("The word 'Œuvre' refers to the works", "The word 'OEuvre' refers to the works"), diff --git a/unstructured/cleaners/core.py b/unstructured/cleaners/core.py index b64c7bd19c..3698aec47e 100644 --- a/unstructured/cleaners/core.py +++ b/unstructured/cleaners/core.py @@ -89,7 +89,7 @@ def clean_ligatures(text) -> str: "fl": "fl", "ffi": "ffi", "ffl": "ffl", - "ſt": "ft", + "ſt": "st", # U+FB05 LATIN SMALL LIGATURE LONG S T -> "st" (per Unicode NFKC) "ʪ": "ls", "œ": "oe", "Œ": "OE",