-
-
Save tom-clickhouse/d11e56ea677be787dac1198017a64141 to your computer and use it in GitHub Desktop.
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
INSERT INTO wikistat WITH | |
parseDateTimeBestEffort(extract(_file, '^pageviews-([\\d\\-]+)\\.gz$')) AS time, | |
splitByChar(' ', line) AS values, | |
splitByChar('.', values[1]) AS projects | |
SELECT | |
time, | |
projects[1] AS project, | |
projects[2] AS subproject, | |
decodeURLComponent(values[2]) AS path, | |
CAST(values[3], 'UInt64') AS hits | |
FROM s3Cluster('default', | |
'https://clickhouse-public-datasets.s3.amazonaws.com/wikistat/original/pageviews-20220{1..6}*.gz', | |
'LineAsString') | |
WHERE length(values) >= 3 | |
SETTINGS | |
parallel_distributed_insert_select = 2, | |
max_insert_threads = 16; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment