Last active
March 16, 2022 20:51
-
-
Save teles/cc1d25a2731edf6504be338d11f444b2 to your computer and use it in GitHub Desktop.
Divide um arquivo CSV em várias partes, salvando
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 | |
# Uso: ./splitcsv.sh "nome-do-arquivo.csv" [numero-de-linhas-por-arquivo] | |
# Divide um arquivo csv em vários | |
filename="$1" | |
total_file_lines=$(cat "$filename" | wc -l) | |
chunk_size=${2:-10000} | |
number_of_files_to_create=$(( total_file_lines / chunk_size + 1)) | |
filename_without_extension=$(echo $filename | sed 's/\.[^.]*$//') | |
mkdir -p "$filename_without_extension" | |
echo "Arquivo: ${filename}" | |
echo "Total de linhas: ${total_file_lines}" | |
echo "Arquivos a serem gerados: ${number_of_files_to_create}" | |
echo -e "Máximo de linhas por arquivo: ${chunk_size}\n" | |
for i in $(seq 0 $number_of_files_to_create); do | |
start=$(( i * chunk_size + 2 )) | |
end=$(( (i + 1) * chunk_size + 1 )) | |
new_file_name="${filename_without_extension}/${i}.csv" | |
sed -n "1p;$start,$end p" "$filename" > "$new_file_name" | |
echo "Arquivo \"${new_file_name}\" criado. Linhas: ${start}...${end}" | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment