Created
January 11, 2024 07:20
-
-
Save Shiina18/008271735840338c6cdc0d76de710240 to your computer and use it in GitHub Desktop.
Merge all csvs with the same columns. Usage `./merge_csv.sh -s source_dir -t target_csv_filepath`. Modification is needed if there may be spaces in filenames.
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
#!/bin/bash | |
# Parse command line arguments using getopts | |
while getopts ":s:t:" opt; do | |
case $opt in | |
s) | |
source_dir="$OPTARG" | |
;; | |
t) | |
target_path="$OPTARG" | |
;; | |
\?) | |
echo "Invalid option: -$OPTARG" >&2 | |
exit 1 | |
;; | |
:) | |
echo "Option -$OPTARG requires an argument." >&2 | |
exit 1 | |
;; | |
esac | |
done | |
# Print source_dir and target_path for debugging | |
echo "Source Directory: $source_dir" | |
echo "Target Path: $target_path" | |
# Get all CSV files in the source directory | |
csv_files=$(ls "$source_dir"/*.csv) | |
# Count the number of CSV files | |
num_files=$(echo $csv_files | wc -w) | |
# Write the header of the first file to the target file | |
head -1 "$(echo $csv_files | cut -d' ' -f1)" > "$target_path" | |
# Append the content of all CSV files to the target file, excluding the header | |
i=0 | |
for file in $csv_files | |
do | |
tail -n +2 "$file" >> "$target_path" | |
i=$((i+1)) | |
echo $((i*100/num_files)) | |
done | pv -N "Processing files" -l -s $num_files > /dev/null |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment