def get_code_snippet(): database_connection = DataBaseConnection() db = DataBaseConnection.connect_database(database_connection) java_question_df = DataBaseConnection.select_question_java( database_connection, db) java_answer_df = DataBaseConnection.select_answer_java( database_connection, db) java_new_answer = pd.DataFrame(columns=['id', 'code_snippet']) java_new_question = pd.DataFrame(columns=['id', 'code_snippet']) for chunk in java_question_df: for row in chunk.itertuples(): snippet_id = row[1] snippet = row[2] snippet = add_class(snippet) new_row = {'id': snippet_id, 'code_snippet': snippet} java_new_question = java_new_question.append(new_row, ignore_index=True) for chunk in java_answer_df: for row in chunk.itertuples(): snippet_id = row[1] snippet = row[2] snippet = add_class(snippet) new_row = {'id': snippet_id, 'code_snippet': snippet} java_new_answer = java_new_answer.append(new_row, ignore_index=True) return java_new_answer, java_new_question
def get_code_snippet(): database_connection = DataBaseConnection() db = DataBaseConnection.connect_database(database_connection) kotlin_question_df = DataBaseConnection.select_question_kotlin( database_connection, db) kotlin_answer_df = DataBaseConnection.select_answer_kotlin( database_connection, db) kotlin_new_answer = pd.DataFrame(columns=['id', 'code_snippet']) kotlin_new_question = pd.DataFrame(columns=['id', 'code_snippet']) for chunk in kotlin_question_df: for row in chunk.itertuples(): snippet_id = row[1] snippet = row[2] snippet = add_function(snippet) new_row = {'id': snippet_id, 'code_snippet': snippet} kotlin_new_question = kotlin_new_question.append(new_row, ignore_index=True) for chunk in kotlin_answer_df: for row in chunk.itertuples(): snippet_id = row[1] snippet = row[2] snippet = add_function(snippet) new_row = {'id': snippet_id, 'code_snippet': snippet} kotlin_new_answer = kotlin_new_answer.append(new_row, ignore_index=True) return kotlin_new_answer, kotlin_new_question
def main(): database_connection = DataBaseConnection() db = DataBaseConnection.connect_database(database_connection) answer_code_select = DataBaseConnection.select_answer_code(database_connection, db) for chunk in answer_code_select: chunk.set_index('id') answer_final_df = delete_code(chunk) DataBaseConnection.save_final_answer_code(database_connection, db, answer_final_df)
def main(): database_connection = DataBaseConnection() db = DataBaseConnection.connect_database(database_connection) question_code_select = DataBaseConnection.select_question_code( database_connection, db) for chunk in question_code_select: chunk.set_index('id') question_final_df = delete_code(chunk) DataBaseConnection.save_final_question_code(database_connection, db, question_final_df)
def main(): database_connection = DataBaseConnection() db = DataBaseConnection.connect_database(database_connection) question_df = DataBaseConnection.question_code(database_connection, db) for chunk in question_df: question_code_df = pd.DataFrame(columns=[ 'id', 'tags', 'code_snippet', 'answer_count', 'comment_count', 'accepted_answer_id', 'creation_date', 'score', 'view_count', 'owner_user_id', 'favorite_count', 'post_type_id', 'language' ]) for row in chunk.itertuples(): id = row[1] tags = row[2] body = row[3] answer_count = row[4] comment_count = row[5] accepted_answer_id = row[6] creation_date = row[7] score = row[8] view_count = row[9] owner_user_id = row[10] favorite_count = row[11] post_type_id = row[12] pattern = r'<code>(.*?)</code>' code = re.findall(pattern, body, flags=re.DOTALL) for snippet in code: new_row = { 'id': id, 'tags': tags, 'code_snippet': snippet, 'answer_count': answer_count, 'comment_count': comment_count, 'accepted_answer_id': accepted_answer_id, 'creation_date': creation_date, 'score': score, 'view_count': view_count, 'owner_user_id': owner_user_id, 'favorite_count': favorite_count, 'post_type_id': post_type_id, 'language': "" } question_code_save = question_code_df.append(new_row, ignore_index=True) DataBaseConnection.save_question_code(database_connection, db, question_code_save)
def main(): database_connection = DataBaseConnection() db = DataBaseConnection.connect_database(database_connection) answer_df = DataBaseConnection.answer_code(database_connection, db) for chunk in answer_df: answer_code_df = pd.DataFrame(columns=['id', 'code_snippet', 'owner_user_id', 'parent_id', 'post_type_id', 'score', 'language']) for row in chunk.itertuples(): id = row[1] body = row[2] creation_date = row[3] owner_user_id = row[4] parent_id = row[5] post_type_id = row[6] score = row[7] pattern = r'<code>(.*?)</code>' code = re.findall(pattern, body, flags=re.DOTALL) for snippet in code: new_row = {'id': id, 'code_snippet': snippet, 'creation_date': creation_date, 'owner_user_id': owner_user_id, 'parent_id': parent_id, 'post_type_id':post_type_id, 'score': score, 'language': ""} answer_code_save = answer_code_df.append(new_row, ignore_index=True) DataBaseConnection.save_answer_code(database_connection, db, answer_code_save)
def connect_db(): database_connection = DataBaseConnection() db = DataBaseConnection.connect_database(database_connection) return database_connection, db