Welcome to the world of string encoding formats!
tl;dr - The preferred method for handling quotes and escape characters when storing data in MySQL columns is to use parameterized queries and let the MySQLDatabase driver handle it. Alternatively, you can escape quotes and slashes by doubling them up prior to insertion.
Full example at bottom of link
standard SQL update
# as_json must have escape slashes and quotes doubled
query = """\
UPDATE json_sandbox
SET data = '{}'
WHERE id = 1;
""".format(as_json)
with DBConn(*client.conn_args) as c:
c.cursor.execute(query)
c.connection.commit()
parameterized SQL update
# SQL Driver will do the escaping for you
query = """\
UPDATE json_sandbox
SET data = %s
WHERE id = %s;
"""
with DBConn(*client.conn_args) as c:
c.cursor.execute(query, (as_json, 1))
c.connection.commit()
Invalid JSON SQL
{
"abc": 123,
"quotes": "ain't it great",
"multiLine1": "hello\nworld",
"multiLine3": "hello\r\nuniverse\r\n"
}
Valid JSON SQL
{
"abc": 123,
"quotes": "ain''t it great",
"multiLine1": "hello\\nworld",
"multiLine3": "hello\\r\\nuniverse\\r\\n"
}
Python transform:
# must escape the escape characters, so each slash is doubled
# Some MySQL Python libraries also have an escape() or escape_string() method.
as_json = json.dumps(payload) \
.replace("'", "''") \
.replace('\\', '\\\\')
Full example
import json
import yaml
from DataAccessLayer.mysql_va import get_sql_client, DBConn
client = get_sql_client()
def encode_and_store(payload):
as_json = json.dumps(payload) \
.replace("'", "''") \
.replace('\\', '\\\\')
query = """\
UPDATE json_sandbox
SET data = '{}'
WHERE id = 1;
""".format(as_json)
with DBConn(*client.conn_args) as c:
c.cursor.execute(query)
c.connection.commit()
return
def encode_and_store_2(payload):
as_json = json.dumps(payload)
query = """\
UPDATE json_sandbox
SET data = %s
WHERE id = %s;
"""
with DBConn(*client.conn_args) as c:
c.cursor.execute(query, (as_json, 1))
c.connection.commit()
return
def retrieve_and_decode():
query = """
SELECT * FROM json_sandbox
WHERE id = 1
"""
with DBConn(*client.conn_args) as cnx:
cursor = cnx.dict_cursor
cursor.execute(query)
rows = cursor.fetchall()
as_json = rows[0].get('data')
payload = yaml.safe_load(as_json)
return payload
if __name__ == '__main__':
payload = {
"abc": 123,
"quotes": "ain't it great",
"multiLine1": "hello\nworld",
"multiLine2": """
hello
world
""",
"multiLine3": "hello\r\nuniverse\r\n"
}
encode_and_store(payload)
output_a = retrieve_and_decode()
encode_and_store_2(payload)
output_b = retrieve_and_decode()
print("original: {}".format(payload))
print("method_a: {}".format(output_a))
print("method_b: {}".format(output_b))
print('')
print(output_a['multiLine1'])
print('')
print(output_b['multiLine2'])
print('\nAll Equal?: {}'.format(payload == output_a == output_b))
