Upload mor.py with huggingface_hub

mor.py

@@ -0,0 +1,39 @@
+import os
+import subprocess
+
+# Java 설치 확인 및 설치
+try:
+    subprocess.run(["java", "-version"], check=True)
+except FileNotFoundError:
+    print("Java is not installed. Installing Java...")
+    subprocess.run(["apt-get", "update"], check=True)
+    subprocess.run(["apt-get", "install", "-y", "default-jdk"], check=True)  # 또는 'openjdk-17-jdk'
+
+# JAVA_HOME 환경 변수 설정
+java_home = "/usr/lib/jvm/java-17-openjdk-amd64"
+if os.path.exists(java_home):
+    os.environ['JAVA_HOME'] = java_home
+else:
+    raise EnvironmentError("JAVA_HOME could not be set because the path does not exist.")
+
+print(f"JAVA_HOME is set to {java_home}")
+
+
+
+from konlpy.tag import Okt, Komoran
+
+komoran = Komoran()
+okt = Okt()
+
+# 토큰화를 위한 형태소 분석
+def tokenize(data):
+    tokenized_data = []
+    tokenized_sentence = okt.pos(data,norm=True, stem=False)
+    for a in tokenized_sentence:
+        if a[1] in ['Verb','Adjective']:
+            tem= komoran.pos(a[0])
+            for word in tem:
+                tokenized_data.append(word[0])
+        else:
+            tokenized_data.append(a[0])
+    return tokenized_data