AWK 按行数拆分文件

[root@ibiomed ~]# cat > test.sh
#!/bin/bash
## function: split file by specified line count
## parameter 1: file name to be splitted
## parameter 2: line number of new files

filename=$1
fileline=$2

echo "filename=$filename"
echo "fileline=$fileline"

awk -v count=$fileline 'BEGIN{i=0} {  print $0 > sprintf("%s_%d",FILENAME,i) ; if (NR>=(i+1)*count) { close(sprintf("%s_%d",FILENAME,i)); i++;} }' $filename

echo "=====finish====="
[root@ibiomed ~]# cat > temp.txt
>ACTL6A_1
GGATAGTTTCCAAGCTATTT
>ACTL6A_3
TTTGCTAATGGTCGTTCTAC
>ACTL6A_5
GTTGAAGGACATAGCCATCG
>ACTL6A_7
ACTGCAATTCCAGTCCACGA
[root@ibiomed ~]# chmod 777 test.sh
[root@ibiomed ~]# ./test.sh temp.txt 2
[root@ibiomed ~]# more temp.txt_0
>ACTL6A_1
GGATAGTTTCCAAGCTATTT

This works. New files with new file names, i.e. :

#!/bin/bash
## function: split file by specified line count
## parameter 1: file name to be splitted
## parameter 2: line number of new files
 
filename=$1
fileline=$2
 
echo "filename=$filename"
echo "fileline=$fileline"
 
#awk -v count=$fileline 'BEGIN{i=0} {  print $0 > sprintf("%s_%d",FILENAME,i) ; if (NR>=(i+1)*count) { close(sprintf("%s_%d",FILENAME,i)); i++;} }' $filename
awk -v count=$fileline 'BEGIN{i=0; NEWFILE="test"} { if (NR<(i+1)*count) { NEWFILE=gensub(/>/,"",1,$0);}  print $0 > sprintf("%s.fa",NEWFILE) ; if (NR>=(i+1)*count) { close(sprintf("%s.fa",NEWFILE)); i++;} }' $filename

echo "=====finish====="
 

REF

https://www.cnblogs.com/cyttina/p/7471221.html

原文地址:https://www.cnblogs.com/emanlee/p/13905310.html