Update keywords_processor.py

keywords_processor.py

@@ -1,31 +1,17 @@
 import os
-import gradio as gr
-import re
-from sklearn.feature_extraction.text import CountVectorizer
 
-def process_keywords(text):
-    # カンマと改行を空白に置換
-    text = re.sub(r"[,\n]+", " ", text)
-    vectorizer = CountVectorizer(ngram_range=(1, 3))
-    X = vectorizer.fit_transform([text])
-    keywords = vectorizer.get_feature_names_out().tolist()
-    return keywords
-
-def ngram_generator(main_text, other_texts):
-    # main_textとother_textsを単一のテキストとして連結
-    full_text = main_text + " " + other_texts
-    keywords = process_keywords(full_text)
+def save_raw_text(main_text, other_texts):
+    # メインテキストとその他のテキストを改行で結合
+    combined_text = main_text + "\\n" + other_texts
+    # 結合したテキストを output1.txt に保存
     output1_path = os.path.join(os.path.dirname(__file__), "output1.txt")
     with open(output1_path, 'w', encoding='utf-8') as file:
-        for keyword in sorted(keywords):
-            file.write(keyword + "\n")
-    output_text = f"Keywords saved to {output1_path}"
-    return ", ".join(sorted(keywords)), output_text
+        file.write(combined_text)
+    return f"Text saved to {output1_path}"
 
 if __name__ == "__main__":
     import sys
     main_text = sys.argv[1] if len(sys.argv) > 1 else ""
     other_texts = sys.argv[2] if len(sys.argv) > 2 else ""
-    keywords, output_text = ngram_generator(main_text, other_texts)
-    print(keywords)
+    output_text = save_raw_text(main_text, other_texts)
     print(output_text)