Update keywords_processor.py

keywords_processor.py

@@ -1,10 +1,39 @@
+import gradio as gr
 import re
 from sklearn.feature_extraction.text import CountVectorizer
+import os
 
 def process_keywords(text):
-    """テキストからN-gramを生成してリストとして返す"""
-    text = re.sub(r"[,\\n]+", " ", text)
+    """ テキストからN-gramを生成してリストとして返す """
+    text = re.sub(r"[,\n]+", " ", text)  # 文字列を正規化して、カンマと改行を空白に変換
     vectorizer = CountVectorizer(ngram_range=(1, 3))
     X = vectorizer.fit_transform([text])
     features = vectorizer.get_feature_names_out()
     return features
+
+def save_keywords(keywords, filename="output1.txt"):
+    """ キーワードをファイルに保存 """
+    with open(filename, 'w', encoding='utf-8') as file:
+        for keyword in keywords:
+            file.write(keyword + "\n")
+    return f"Keywords saved to {filename}"
+
+def process_and_save_keywords(text):
+    keywords = process_keywords(text)
+    save_result = save_keywords(keywords)
+    return ", ".join(keywords), save_result
+
+with gr.Blocks() as demo:
+    gr.Markdown("### N-gram Generator and Saver")
+    text_input = gr.Textbox(label="Enter text")
+    output_keywords = gr.Textbox(label="Generated N-grams", readonly=True)
+    output_message = gr.Textbox(label="Output Message", readonly=True)
+    submit_button = gr.Button("Generate and Save N-grams")
+
+    submit_button.click(
+        fn=process_and_save_keywords,
+        inputs=text_input,
+        outputs=[output_keywords, output_message]
+    )
+
+demo.launch()