linux 中依据某列展开为多行

001、 方法1

[root@pc1 test01]# ls
a.txt  test.sh
[root@pc1 test01]# cat a.txt     ## 测试数据， 依据最后一列展开为多行
chrY    2657879 2658063 CTCF    652     GM19239
chrY    2664424 2664734 CTCF    185     hL-hESC,HepG2,HUVEC
chrY    2668277 2668694 CTCF    766     Dnd41,H1-hESC,HepG2,HSMM,HSMMtube,HUVEC,NH-A,A549,ProgFib,AG10803,BJ,GM12864,HCM,HCPEpic,HEEpiC,HFF,HEF-Myc,HPF,HVMF,NHLF,RPTEC,SAEC
[root@pc1 test01]# cat test.sh     ## 展开程序
#!/bin/bash

for i in $(seq $(wc -l < a.txt))
do
        sed -n "$i"p a.txt | awk '{OFS = "\t"; split($NF, ay, ","); len = length(ay); for (i = 1; i <= len; i++) {print $0, ay[i]}}' | awk '{OFS = "\t"; $(NF - 1) = $NF; sub(/\s*\S*$/, ""); print $0}' >> result.txt
done
[root@pc1 test01]# bash test.sh      ## 执行程序
[root@pc1 test01]# ls
a.txt  result.txt  test.sh
[root@pc1 test01]# head result.txt -n 6      ## 运行结果
chrY    2657879 2658063 CTCF    652     GM19239
chrY    2664424 2664734 CTCF    185     hL-hESC
chrY    2664424 2664734 CTCF    185     HepG2
chrY    2664424 2664734 CTCF    185     HUVEC
chrY    2668277 2668694 CTCF    766     Dnd41
chrY    2668277 2668694 CTCF    766     H1-hESC

002、方法2