Created
November 23, 2017 15:26
-
-
Save kkirsanov/d64a3c2899675e8aa35870c608fe7e12 to your computer and use it in GitHub Desktop.
Disable logical reader in fastavro
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import datetime | |
| from io import BytesIO | |
| from pprint import pprint | |
| from uuid import uuid4 | |
| import fastavro | |
| fastavro._reader.LOGICAL_READERS['long-timestamp-millis'] = lambda d, w, r: d | |
| schema = { | |
| "fields": [ | |
| { | |
| "name": "date", | |
| "type": {'type': 'int', 'logicalType': 'date'} | |
| }, | |
| { | |
| "name": "timestamp-millis", | |
| "type": {'type': 'long', 'logicalType': 'timestamp-millis'} | |
| }, | |
| { | |
| "name": "timestamp-micros", | |
| "type": {'type': 'long', 'logicalType': 'timestamp-micros'} | |
| }, | |
| { | |
| "name": "uuid", | |
| "type": {'type': 'string', 'logicalType': 'uuid'} | |
| }, | |
| { | |
| "name": "time-millis", | |
| "type": {'type': 'int', 'logicalType': 'time-millis'} | |
| }, | |
| { | |
| "name": "time-micros", | |
| "type": {'type': 'long', 'logicalType': 'time-micros'} | |
| } | |
| ], | |
| "namespace": "namespace", | |
| "name": "name", | |
| "type": "record" | |
| } | |
| def serialize(schema, data): | |
| bytes_writer = BytesIO() | |
| fastavro.schemaless_writer(bytes_writer, schema, data) | |
| return bytes_writer.getvalue() | |
| def deserialize(schema, binary): | |
| bytes_writer = BytesIO() | |
| bytes_writer.write(binary) | |
| bytes_writer.seek(0) | |
| res = fastavro.schemaless_reader(bytes_writer, schema) | |
| return res | |
| data1 = { | |
| 'date': datetime.date.today(), | |
| 'timestamp-millis': datetime.datetime.now(), | |
| 'timestamp-micros': datetime.datetime.now(), | |
| 'uuid': uuid4(), | |
| 'time-millis': datetime.datetime.now().time(), | |
| 'time-micros': datetime.datetime.now().time(), | |
| } | |
| binary = serialize(schema, data1) | |
| data2 = deserialize(schema, binary) | |
| pprint(data2) |
Doing this is usually a terrible idea, as it will modify how fastavro decodes datetime on a per-process level. So if you add the fastavro._read.LOGICAL_READERS line, you will modify not only how fastavro is handling timestamp-millis in the module where you add the line of code, but in the entire python program.
This is a recipe for nasty lurking hard-to-find-bugs, and makes the code unmaintainable. Speaking from experience from having found this piece of code added by a junior programmer to a project where it was now causing problems in a completely different part of the codebase.
Just don't.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I think line 8 should be,