$ awk -v OFS=',' 'FNR==1{cust=FILENAME; sub(/\.csv$/,"",cust)} {print (FNR>1 ? cust : "customer"), $0}' 10000000.csv
customer,first_name,middle_name,last_name,gender,email,phone_number,address,city,state,country,date_order_start,date_order_complete,invoice_number,invoice_date,item,item_price,quantity,cost,job_name,job_price,total_cost
10000000,Chae,Jesusa,Cummings,Female,deifier2040@example.com,555-555-8750,911 Hauser Pike,Moline,Georgia,Cameroon,2016-06-29,2016-07-16,36298,2016-07-17,Acer,493.86,14,354.77,Broken,123.68,898.13
так что с любым awk вы могли бы сделать:
for file in *.csv; do
awk 'script' "$file" > tmp && mv tmp "$file"
done
или с помощью GNU awk для редактирования «на месте»:
$ tail -n +1 10000000.csv 10000001.csv
==> 10000000.csv <==
first_name,middle_name,last_name,gender,email,phone_number,address,city,state,country,date_order_start,date_order_complete,invoice_number,invoice_date,item,item_price,quantity,cost,job_name,job_price,total_cost
Chae,Jesusa,Cummings,Female,deifier2040@example.com,555-555-8750,911 Hauser Pike,Moline,Georgia,Cameroon,2016-06-29,2016-07-16,36298,2016-07-17,Acer,493.86,14,354.77,Broken,123.68,898.13
==> 10000001.csv <==
first_name,middle_name,last_name,gender,email,phone_number,address,city,state,country,date_order_start,date_order_complete,invoice_number,invoice_date,item,item_price,quantity,cost,job_name,job_price,total_cost
Fleta,Rosette,Hurley,Other,tobacconist1857@example.com,1-555-555-1210,35 Freelon Arcade,Beaverton,Rhode Island,Cayman Islands,2009-06-08,2009-06-29,39684,2009-07-01,NVIDIA GeForce GTX 980,474.31,16,395.79,Broken,157.53,1088.04
Bennett,Dennis,George,Male,dona1910@example.com,(555) 555-4131,505 Robert C Levy Arcade,Wellington,Louisiana,Mexico,2019-05-09,2019-05-19,37938,2019-05-21,8GB,187.67,16,205.77,Service,170.21,1007.85
Tommye,Pamula,Diaz,Other,dovelet1967@example.com,555.555.4445,1001 Canby Boulevard,Edinburg,Massachusetts,Gambia,2004-05-02,2004-05-24,31364,2004-05-26,Lenovo,137.21,13,193.63,Replacement,246.43,934.31
Albert,Jerrold,Cohen,Other,bolio2036@example.com,+1-(555)-555-8491,1181 Baden Avenue,Menomonee Falls,Texas,Tajikistan,2019-08-03,2019-08-12,37768,2019-08-15,Intel® Iris™ Graphics 6100,396.46,17,223.02,Service,118.53,960.27
Louetta,Collene,Best,Fluid,dinner1922@example.com,1-555-555-7050,923 Barry Viaduct,Laurel,Illinois,St. Barthélemy,2009-03-02,2009-03-06,39557,2009-03-07,AMD Radeon R9 M395X,133.9,11,198.49,Fix,178.54,1055.32
Kandace,Wesley,Diaz,Female,closterium1820@example.com,+1-(555)-555-5414,341 Garlington Run,Santa Maria,New Jersey,Mexico,2005-10-09,2005-10-10,30543,2005-10-14,Samsung,590.29,5,354.85,Service,292.56,1032.22
.
$ awk -i inplace -v OFS=',' 'FNR==1{cust=FILENAME; sub(/\.csv$/,"",cust)} {print (FNR>1 ? cust : "customer"), $0}' 10000000.csv 10000001.csv
.
$ tail -n +1 10000000.csv 10000001.csv
==> 10000000.csv <==
customer,first_name,middle_name,last_name,gender,email,phone_number,address,city,state,country,date_order_start,date_order_complete,invoice_number,invoice_date,item,item_price,quantity,cost,job_name,job_price,total_cost
10000000,Chae,Jesusa,Cummings,Female,deifier2040@example.com,555-555-8750,911 Hauser Pike,Moline,Georgia,Cameroon,2016-06-29,2016-07-16,36298,2016-07-17,Acer,493.86,14,354.77,Broken,123.68,898.13
==> 10000001.csv <==
customer,first_name,middle_name,last_name,gender,email,phone_number,address,city,state,country,date_order_start,date_order_complete,invoice_number,invoice_date,item,item_price,quantity,cost,job_name,job_price,total_cost
10000001,Fleta,Rosette,Hurley,Other,tobacconist1857@example.com,1-555-555-1210,35 Freelon Arcade,Beaverton,Rhode Island,Cayman Islands,2009-06-08,2009-06-29,39684,2009-07-01,NVIDIA GeForce GTX 980,474.31,16,395.79,Broken,157.53,1088.04
10000001,Bennett,Dennis,George,Male,dona1910@example.com,(555) 555-4131,505 Robert C Levy Arcade,Wellington,Louisiana,Mexico,2019-05-09,2019-05-19,37938,2019-05-21,8GB,187.67,16,205.77,Service,170.21,1007.85
10000001,Tommye,Pamula,Diaz,Other,dovelet1967@example.com,555.555.4445,1001 Canby Boulevard,Edinburg,Massachusetts,Gambia,2004-05-02,2004-05-24,31364,2004-05-26,Lenovo,137.21,13,193.63,Replacement,246.43,934.31
10000001,Albert,Jerrold,Cohen,Other,bolio2036@example.com,+1-(555)-555-8491,1181 Baden Avenue,Menomonee Falls,Texas,Tajikistan,2019-08-03,2019-08-12,37768,2019-08-15,Intel® Iris™ Graphics 6100,396.46,17,223.02,Service,118.53,960.27
10000001,Louetta,Collene,Best,Fluid,dinner1922@example.com,1-555-555-7050,923 Barry Viaduct,Laurel,Illinois,St. Barthélemy,2009-03-02,2009-03-06,39557,2009-03-07,AMD Radeon R9 M395X,133.9,11,198.49,Fix,178.54,1055.32
10000001,Kandace,Wesley,Diaz,Female,closterium1820@example.com,+1-(555)-555-5414,341 Garlington Run,Santa Maria,New Jersey,Mexico,2005-10-09,2005-10-10,30543,2005-10-14,Samsung,590.29,5,354.85,Service,292.56,1032.22
Если у вас слишком много файлов для передачи в командной строке, а запуск через xargs слишком медленный, вот еще один вариант:
awk -i inplace... '
BEGIN {
while ( (getline line < ARGV[1]) > 0 ) {
if ( line ~ /\.csv$/ ) {
ARGV[ARGC] = line
ARGC++
}
}
ARGV[1] = ""
}
{ the "real" script }
' <(ls)
Приведенный выше код считывает вывод ls
как входной файл, а не как аргументы, заполняет массив аргументов теми именами файлов, которые заканчиваются на .csv
, а затем работает с файлами, как если бы они были переданы как аргументы в командной строке.
Вы можете попробовать следующие два подхода:
$ find. -name \*.csv -type f ! -empty -exec \
perl -spe 's/^/,/;
$F //= $ARGV =~ s/\.csv$//r;
s/^/$. == 1 ? "\n$C" : $F/e;
undef $F, close ARGV if eof;
' -- -C="Customer" {} +
Во втором используются функции Gnu sed, в частности, команда F для получения имени файла и опция -s для обработки нескольких файлов не как единого потока, а по отдельности:
$ find. -name \*.csv -type f ! -empty -exec \
sed -se 'F;1s/^/CUSTOMER,/' {} + |
sed -E \
-e 'N;s/.*\.csv(\nCUSTOMER,)/\1/;t' \
-e 's/\.csv\n/,/;s/..//' \
;