Update keywords_processor.py

keywords_processor.py

@@ -8,28 +8,23 @@ def process_keywords(text):
     text = re.sub(r"[^\w\s]", "", text)
     # 連続する空白を一つにする
     text = re.sub(r"\s+", " ", text).strip()
-    vectorizer = CountVectorizer(ngram_range=(1, 2), token_pattern=r"(?u)\b\w+\b")
+    vectorizer = CountVectorizer(ngram_range=(1, 2))
     X = vectorizer.fit_transform([text])
     keywords = vectorizer.get_feature_names_out().tolist()
     return keywords
 
-def save_keywords(keywords, filename="output1.txt"):
-    output1_path = os.path.join(os.path.dirname(__file__), filename)
-    with open(output1_path, 'w', encoding='utf-8') as file:
-        for keyword in keywords:
-            file.write(keyword + "\n")
-    return f"Keywords saved to {output1_path}"
-
 def ngram_generator(main_text, other_texts):
-    # main_text と other_texts を結合し、カンマと改行で分割
     texts = [main_text] + re.split(r',|\n', other_texts)
     all_keywords = []
     for text in texts:
         keywords = process_keywords(text)
-        all_keywords.extend(keywords)  # Extend the list of keywords for each text
-    # Remove duplicates and save keywords
+        all_keywords.extend(keywords)
     unique_keywords = list(set(all_keywords))
-    output_text = save_keywords(unique_keywords)
+    output1_path = os.path.join(os.path.dirname(__file__), "output1.txt")
+    with open(output1_path, 'w', encoding='utf-8') as file:
+        for keyword in unique_keywords:
+            file.write(keyword + "\n")
+    output_text = f"Keywords saved to {output1_path}"
     return ", ".join(sorted(unique_keywords)), output_text
 
 if __name__ == "__main__":