Last active
March 13, 2023 09:47
-
-
Save luminoso/0581b7f6760ea9a26b06115c2993f351 to your computer and use it in GitHub Desktop.
jsonlines compressed serialization gz write file
This file contains 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
# reads and writes compressed jsonlines to a file | |
# from bson import json_util | |
# writeall_jsonl_gz('filename.jsonl.gz', objects, dumps=json_util.dumps) | |
import gzip | |
# !python -m pip install jsonlines | |
from typing import List, Dict | |
import jsonlines | |
def writeall_jsonl_gz(filename, payload: List[Dict], dumps=None): | |
with gzip.open(filename, 'wb') as fp: | |
json_writer = jsonlines.Writer(fp, dumps=dumps) | |
json_writer.write_all(payload) | |
def read_jsonl_gz(filename) -> List[Dict]: | |
data = [] | |
with gzip.open(filename, 'rb') as fp: | |
j_reader = jsonlines.Reader(fp) | |
for obj in j_reader: | |
data.append(obj) | |
return data |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment