Update keywords_processor.py

keywords_processor.py

@@ -1,60 +1,40 @@
 import gradio as gr
 import re
 from sklearn.feature_extraction.text import CountVectorizer
-import os
 
-def process_keywords(text):
-    # カンマと改行を空白に変換
-    text = re.sub(r"[,\n]+", " ", text)
-    # 英数字と空白以外を削除
-    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)
-    try:
-        vectorizer = CountVectorizer(ngram_range=(1, 3), token_pattern=r"(?u)\b\w+\b")
-        X = vectorizer.fit_transform([text])
-        features = vectorizer.get_feature_names_out()
-        if features.size > 0:
-            print("Generated N-grams:", features)
-        else:
-            print("No N-grams generated from the input.")
-        return features
-    except Exception as e:
-        print(f"Error processing keywords: {str(e)}")
-        return []
+def process_keywords(texts):
+    all_text = " ".join(texts)
+    all_text = re.sub(r"[^\w\s]", "", all_text)  # 英数字と空白以外を削除
+    all_text = re.sub(r"\s+", " ", all_text)  # 連続する空白を一つにする
+    vectorizer = CountVectorizer(ngram_range=(1, 3), token_pattern=r"(?u)\b\w+\b")
+    X = vectorizer.fit_transform([all_text])
+    features = vectorizer.get_feature_names_out()
+    return features
 
 def save_keywords(keywords, filename="output1.txt"):
     with open(filename, 'w', encoding='utf-8') as file:
-        if keywords:
-            for keyword in keywords:
-                print(f"Saving keyword: {keyword}")  # 保存しようとしているキーワードをログに出力
-                file.write(keyword + "\n")
-        else:
-            print("No keywords to save.")  # 保存するキーワードがない場合のログ
+        for keyword in keywords:
+            file.write(keyword + "\n")
     return f"Keywords saved to {filename}"
 
-def process_and_save_keywords(text):
-    keywords = process_keywords(text)
-    # キーワードが生成されたかどうかをチェック
-    if keywords:
-        print("Generated keywords:", ", ".join(keywords))
-    else:
-        print("No keywords generated from the input.")
-
-    save_result = save_keywords(keywords)
-    print(save_result)
-
-    return ", ".join(keywords) if keywords else "No keywords", save_result
+def ngram_generator(main_text, other_texts):
+    texts = [main_text] + other_texts.split(",")
+    keywords = process_keywords(texts)
+    output_text = save_keywords(keywords)
+    return ", ".join(keywords) if keywords else "No keywords", output_text
 
 with gr.Blocks() as demo:
     gr.Markdown("### N-gram Generator and Saver")
-    text_input = gr.Textbox(label="Enter text")
+    main_text_input = gr.Textbox(label="メインキーワード")
+    other_texts_input = gr.Textbox(label="その他のキーワード（カンマ区切り）")
     output_keywords = gr.Textbox(label="Generated N-grams")
     output_message = gr.Textbox(label="Output Message")
     submit_button = gr.Button("Generate and Save N-grams")
 
     submit_button.click(
-        fn=process_and_save_keywords,
-        inputs=text_input,
+        fn=ngram_generator,
+        inputs=[main_text_input, other_texts_input],
         outputs=[output_keywords, output_message]
     )
+
+if __name__ == "__main__":