Last active
July 9, 2020 15:25
-
-
Save eidosam/486c717e5aafcbcdae2193173d9f4a1b to your computer and use it in GitHub Desktop.
Inspect parquet files stored in S3 using `parquet-tools`
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
#!/usr/bin/env bash | |
set -o errexit | |
### ------ Preparation ------ ### | |
# brew tap adoptopenjdk/openjdk && brew cask install adoptopenjdk8 | |
# command -v mvn > /dev/null || brew install maven | |
# command -v parquet-tools > /dev/null || brew install parquet-tools | |
# brew cask list --versions osxfuse > /dev/null || brew cask install osxfuse | |
# command -v goofys > /dev/null || brew install goofys | |
### ------ -------------- --- ### | |
profile=default | |
cmd=head | |
while [ -n "$1" ]; do | |
case $1 in | |
--profile ) | |
shift | |
profile=$1 | |
;; | |
--command ) | |
shift | |
cmd=$1 | |
;; | |
* ) | |
inputfile=$1 | |
;; | |
esac | |
shift | |
done | |
inputfile=${inputfile/s3\:\/\//} | |
key=${inputfile#*/} | |
bucket=${inputfile%%/*} | |
if [[ -z "$key" ]] || [[ -z "$bucket" ]] | |
then | |
echo " | |
Invalid S3 file path | |
" | |
exit 1 | |
fi | |
prefix=`dirname ${key}` | |
file=`basename ${key}` | |
mountingpoint=~/.mounting-points/${prefix} | |
mkdir -p ${mountingpoint} | |
function _umount() { | |
mount | grep ${mountingpoint} > /dev/null && umount ${mountingpoint} || true | |
} | |
trap _umount EXIT | |
goofys \ | |
--profile ${profile} \ | |
${bucket}:${prefix} \ | |
${mountingpoint} | |
parquet-tools ${cmd} ${mountingpoint}/${file} 2> /dev/null |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment