awk
内置变量：
FS ：定义输入字段分隔符 Field Separator ，同 F
RS ：定义输入记录分隔符 Record Separator
OFS ：定义输出字段分隔符 Out Field Separator
ORS ：定义输出记录分隔符 Out Record Separator
NF ：数据文件中的字段总数，可以简单理解为 列数
NR ：已处理的输入记录数，可以简单理解为 行数
也可以通过 v 参数自定义变量或传递外部变量
$ less -S example.gtf | awk '{print $9}'
gene_id
gene_id
gene_id
gene_id
gene_id
gene_id
gene_id
gene_id
root 13:24:36 ~/data/Data
$ less -S example.gtf | awk 'BEGIN {FS="\t"} {print $9}'
gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "RP11-34P13.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "RP11-34P13.1-201"; level 3; havana_gene "OTTHUMG00000000961";
gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "RP11-34P13.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "RP11-34P13.1-201"; level 3; havana_gene "OTTHUMG00000000961";
$ less -S example.gtf | awk 'BEGIN {FS="\t"} {print NR,$9}' |less -S
1 gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_co
2 gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_co
3 gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_co
4 gene_id "ENSG00000223972"; transcript_id "ENSG00000223972"; gene_type "protein_co
5 gene_id "ENSG00000223972"; transcript_id "ENST00000450305"; gene_type "protein_co
6 gene_id "ENSG00000223972"; transcript_id "ENST00000450305"; gene_type "protein_co
7 gene_id "ENSG00000223972"; transcript_id "ENST00000450305"; gene_type "protein_co
8 gene_id "ENSG00000223972"; transcript_id "ENST00000450305"; gene_type "protein_co
9 gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_co
10 gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_c
11 gene_id "ENSG00000223972"; transcript_id "ENST00000450305"; gene_type "protein_c
12 gene_id "ENSG00000223972"; transcript_id "ENST00000450305"; gene_type "protein_c
13 gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_c
14 gene_id "ENSG00000223972"; transcript_id "ENST00000456328"; gene_type "protein_c
:
