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 save_code_df(java_new_answer, java_new_question):
database_connection, db = connect_db()
DataBaseConnection.save_java_answer_update(database_connection, db,
java_new_answer)
DataBaseConnection.save_java_question_update(database_connection, db,
java_new_question)
def connect_db():
database_connection = DataBaseConnection()
db = DataBaseConnection.connect_database(database_connection)
return database_connection, db
def get_snippet_answer():
java_answers = pd.DataFrame(columns=[
'id', 'code_snippet', 'valid_file', 'upperel', 'typename',
'summaryjavadoc', 'operatorwrap', 'fallthrough', 'nofinalizer',
'javadocsingle', 'variablename', 'methodname', 'modifierorder',
'multiplevariable', 'braces', 'parenpad', 'methodparenpad',
'nolinewrap', 'overloadmethod', 'javadocparagraph',
'javadocindentation', 'javadocmethod', 'abbreviation', 'leftcurly',
'rightcurly', 'whitespace', 'emptyline', 'emptyblock', 'separatorwrap',
'indentation', 'commentindentation', 'annotation', 'toplevel',
'arraytype', 'invalidposition', 'membername', 'filetabcharacter',
'switchdefault', 'importerror', 'parametername'
])
connection, db = get_connection()
answer_df = DataBaseConnection.select_java_answer_update(connection, db)
for java_chunk in answer_df:
for row in java_chunk.itertuples():
snippet_id = row[1]
snippet = row[2]
temp_file(snippet, "Answer_Class.java")
exception_count, upper_l_count, type_name_count, summary_javadoc_count, operator_wrap_count, fall_through_count, no_finalizer_count, javadoc_single_count, variable_name_count, method_name_count, modifier_order_count, multiple_variable_count, braces_count, paren_pad_count, method_paren_pad_count, no_line_wrap_count, overload_method_count, javadoc_paragraph_count, javadoc_indentation_count, javadoc_method_count, abbreviation_count, left_curly_count, right_curly_count, right_curly2_count, whitespace_count, empty_line_count, empty_block_count, separator_wrap_count, indentation_count, comment_indentation_count, annotation_count, top_level_count, array_type_count, invalid_position_count, member_name_count, file_tab_character_count, switch_default_count, import_error_count, parameter_name_count = checkstyle_cmd(
)
if exception_count != 0:
java_file = False
else:
java_file = True
new_row = {
'id': snippet_id,
'code_snippet': snippet,
'valid_file': java_file,
'upperel': upper_l_count,
'typename': type_name_count,
'summaryjavadoc': summary_javadoc_count,
'operatorwrap': operator_wrap_count,
'fallthrough': fall_through_count,
'nofinalizer': no_finalizer_count,
'javadocsingle': javadoc_single_count,
'variablename': variable_name_count,
'methodname': method_name_count,
'modifierorder': modifier_order_count,
'multiplevariable': multiple_variable_count,
'braces': braces_count,
'parenpad': paren_pad_count,
'methodparenpad': method_paren_pad_count,
'nolinewrap': no_line_wrap_count,
'overloadmethod': overload_method_count,
'javadocparagraph': javadoc_paragraph_count,
'javadocindentation': javadoc_indentation_count,
'javadocmethod': javadoc_method_count,
'abbreviation': abbreviation_count,
'leftcurly': left_curly_count,
'rightcurly': right_curly_count + right_curly2_count,
'whitespace': whitespace_count,
'emptyline': empty_line_count,
'emptyblock': empty_block_count,
'separatorwrap': separator_wrap_count,
'indentation': indentation_count,
'commentindentation': comment_indentation_count,
'annotation': annotation_count,
'toplevel': top_level_count,
'arraytype': array_type_count,
'invalidposition': invalid_position_count,
'membername': member_name_count,
'filetabcharacter': file_tab_character_count,
'switchdefault': switch_default_count,
'importerror': import_error_count,
'parametername': parameter_name_count
}
java_answers = java_answers.append(new_row, ignore_index=True)
save_answer(java_answers)
def save_question(question_df):
connection, db = get_connection()
DataBaseConnection.save_checkstyle_questions(connection, db, question_df)
def save_answer(answer_df):
connection, db = get_connection()
DataBaseConnection.save_checkstyle_answers(connection, db, answer_df)
def get_snippet():
kotlin_answers = pd.DataFrame(columns=[
'id', 'code_snippet', 'valid_file', 'indention_error',
'semicolon_error', 'wildcard_error', 'blank_line_error',
'whitespace_error', 'return_error', 'redundant_error', 'break_error'
])
kotlin_questions = pd.DataFrame(columns=[
'id', 'code_snippet', 'valid_file', 'indention_error',
'semicolon_error', 'wildcard_error', 'blank_line_error',
'whitespace_error', 'return_error', 'redundant_error', 'break_error'
])
connection, db = get_connection()
answer_df = DataBaseConnection.select_kotlin_answer_update(connection, db)
question_df = DataBaseConnection.select_kotlin_question_update(
connection, db)
for kotlin_chunk in answer_df:
for row in kotlin_chunk.itertuples():
snippet_id = row[1]
snippet = row[2]
temp_file(snippet)
indentation_error_count, semicolon_error_count, wildcard_error_count, blank_lines_error_count, whitespace_error_count, return_error_count, redundant_error_count, break_error_count, kotlin_file_error_count = ktlint_cmd(
)
if kotlin_file_error_count != 0:
kotlin_file = False
else:
kotlin_file = True
new_row = {
'id': snippet_id,
'code_snippet': snippet,
'valid_file': kotlin_file,
'indention_error': indentation_error_count,
'semicolon_error': semicolon_error_count,
'wildcard_error': wildcard_error_count,
'blank_line_error': blank_lines_error_count,
'whitespace_error': whitespace_error_count,
'return_error': return_error_count,
'redundant_error': redundant_error_count,
'break_error': break_error_count
}
kotlin_answers = kotlin_answers.append(new_row, ignore_index=True)
for kotlin_chunk in question_df:
for row in kotlin_chunk.itertuples():
snippet_id = row[1]
snippet = row[2]
temp_file(snippet)
indentation_error_count, semicolon_error_count, wildcard_error_count, blank_lines_error_count, whitespace_error_count, return_error_count, redundant_error_count, break_error_count, kotlin_file_error_count = ktlint_cmd(
)
if kotlin_file_error_count != 0:
kotlin_file = False
else:
kotlin_file = True
new_row = {
'id': snippet_id,
'code_snippet': snippet,
'valid_file': kotlin_file,
'indention_error': indentation_error_count,
'semicolon_error': semicolon_error_count,
'wildcard_error': wildcard_error_count,
'blank_line_error': blank_lines_error_count,
'whitespace_error': whitespace_error_count,
'return_error': return_error_count,
'redundant_error': redundant_error_count,
'break_error': break_error_count
}
kotlin_questions = kotlin_questions.append(new_row,
ignore_index=True)
return kotlin_answers, kotlin_questions
def save_df(answer_df, question_df):
connection, db = get_connection()
DataBaseConnection.save_ktlint_answers(connection, db, answer_df)
DataBaseConnection.save_ktlint_questions(connection, db, question_df)