Update app.py

app.py

@@ -14,24 +14,32 @@ openai.api_key = os.getenv("OPENAI_API_KEY")
 
 # 문장 구분 함수
 def split_sentences(text):
-    sentences = re.split(r"(니다|에요|구나|해요|군요|겠어요|시오|해라|예요|아요|데요|대요|세요|어요|게요|구요|고요|나요|하죠)(?![\w])", text)
+    # 주어진 구분 기준을 사용한 정규 표현식
+    sentence_end = r'(니다|에요|구나|해요|군요|겠어요|시오|해라|예요|아요|데요|대요|세요|어요|게요|구요|고요|나요|하죠)(?![\w])'
+    segments = re.split(f'({sentence_end})', text)
+    
     combined_sentences = []
     current_sentence = ""
-    for i in range(0, len(sentences), 2):
-        if i + 1 < len(sentences):
-            sentence = sentences[i] + sentences[i + 1]
-        else:
-            sentence = sentences[i]
-        if len(current_sentence) + len(sentence) > 100:  # 100자를 초과할 경우
-            combined_sentences.append(current_sentence.strip())
-            current_sentence = sentence.strip()
+    
+    for i in range(0, len(segments), 2):
+        segment = segments[i]
+        if i + 1 < len(segments):
+            segment += segments[i + 1]
+        
+        if len(current_sentence) + len(segment) > 100:
+            if current_sentence:
+                combined_sentences.append(current_sentence.strip())
+            current_sentence = segment.strip()
         else:
-            current_sentence += sentence
-        if sentence.endswith(('.', '?', '!')):
+            current_sentence += (' ' if current_sentence else '') + segment.strip()
+        
+        if re.search(sentence_end, segment):
             combined_sentences.append(current_sentence.strip())
             current_sentence = ""
+    
     if current_sentence:
         combined_sentences.append(current_sentence.strip())
+    
     return combined_sentences
 
 def parse_api_response(response):
@@ -114,17 +122,17 @@ def analyze(url, progress=gr.Progress()):
         progress(0, desc="스크립트 추출 중...")
         title, description, script = get_youtube_script(url)
         
-        progress(33, desc="원문 스크립트 처리 중...")
+        progress(0.33, desc="원문 스크립트 처리 중...")
         script_sentences = split_sentences(script)
         script_content = f"# {title}\n\n" + "\n".join(script_sentences)
         
-        progress(66, desc="요약 생성 중...")
+        progress(0.66, desc="요약 생성 중...")
         summary = summarize_text(title, description, script)
         
-        progress(88, desc="요약 내용 정리 중...")
+        progress(0.88, desc="요약 내용 정리 중...")
         summary_content = f"# {title}\n\n{summary}"
         
-        progress(100, desc="완료")
+        progress(1.0, desc="완료")
         return script_content, summary_content
     except Exception as e:
         error_msg = f"처리 중 오류 발생: {str(e)}"