fix:update nltk to use punkt_tab

dsoftwareinc · Aug 26, 2024 · f462a58 · f462a58
1 parent fdf3a7c
commit f462a58
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 8 deletions.
diff --git a/forum/similarity/algo/tfidf.py b/forum/similarity/algo/tfidf.py
@@ -14,7 +14,7 @@ def initialize_tfidf():
     try:
         nltk.data.find("tokenizers/punkt")
     except LookupError:
-        nltk.download("punkt")
+        nltk.download("punkt_tab")
 
     stemmer = nltk.stem.porter.PorterStemmer()
     remove_punctuation_map = dict((ord(char), None) for char in string.punctuation)

diff --git a/poetry.lock b/poetry.lock