1.row/column value
$0 whole row
$1..$n one column
awk '{print $1, $4}' netstat.txt
awk '{printf "%-8s %-8s %-8s %-18s %-22s %-15s\n",$1,$2,$3,$4,$5,$6}' netstat.txt
2.filter,comparison operator: ==,!=, >, <, >=, <=
awk '$3==0 && $6=="LISTEN" ' netstat.txt
awk ' $3>0 {print $0}' netstat.txt
awk '$3==0 && $6=="LISTEN" || NR==1 ' netstat.txt
awk '$3==0 && $6=="LISTEN" || NR==1 {printf "%-20s %-20s %s\n",$4,$5,$6}' netstat.txt
3.Built-in vars
$0 | 当前记录(这个变量中存放着整个行的内容) |
$1,$2,...,$n | 当前记录的第n个字段,字段间由FS分隔 |
FS | 输入字段分隔符 默认是空格或Tab |
RS | 输入的记录分隔符, 默认为换行符 |
OFS | 输出字段分隔符, 默认也是空格 |
ORS | 输出的记录分隔符,默认为换行符 |
NF | 当前记录中的字段个数,就是有多少列 |
NR | 已经读出的记录数,就是行号,从1开始,如果有多个文件话,这个值也是不断累加中。 |
FNR | 当前记录数,与NR不同的是,这个值会是各个文件自己的行号 |
FILENAME | 当前输入文件的名字 |
awk '$3==0 && $6=="ESTABLISHED" || NR==1 {printf "%02s %s %-20s %-20s %s\n",NR, FNR, $4,$5,$6}' netstat.txt
awk 'BEGIN{FS=":"} {print $1,$3,$6}' /etc/passwd
awk -F: '{print $1,$3,$6}' /etc/passwd
awk -F '[;:]' '{print $1,$3,$6}' OFS='\t' /etc/passwd
4.String matching
~ 表示模式开始。/ /中是模式。这就是一个正则表达式的匹配。需要表头NR==1
awk '$6 ~ /FIN/ || NR==1 {print NR,$4,$5,$6}' OFS="\t" netstat.txt
awk '$6 ~ /WAIT/ || NR==1 {print NR,$4,$5,$6}' OFS="\t" netstat.txt
awk '/LISTEN/' netstat.txt
awk '$6 ~ /FIN|TIME/ || NR==1 {print NR,$4,$5,$6}' OFS="\t" netstat.txt
!~ or '!/pattern/'
awk '$6 !~ /FIN|TIME/ || NR==1 {print NR,$4,$5,$6}' OFS="\t" netstat.txt
awk '!/WAIT/' netstat.txt
awk '{print NR,$0}' OFS="\t" netstat.txt
awk '/WAIT/ {print NR,$0}' OFS="\t" netstat.txt
awk '!/WAIT/ {print NR,$0}' OFS="\t" netstat.txt
awk '$6 !~ /WAIT/ {print NR,$0}' OFS="\t" netstat.txt
5.Split files
awk 'NR!=1{print > $6}' netstat.txt
awk 'NR!=1{print $4,$5 > $6}' netstat.txt
awk 'NR!=1{if($6 ~ /TIME|ESTABLISHED/) print > "1.txt"; else if($6 ~ /LISTEN/) print > "2.txt"; else print > "3.txt" }' netstat.txt
6.Statistic
ls -l *.cpp *.c *.h | awk '{sum+=$5} END {print sum}'
awk 'NR!=1{a[$6]++;} END {for (i in a) print i ", " a[i];}' netstat.txt
#用户的进程的占了多少内存
ps aux | awk 'NR!=1{a[$1]+=$6;} END { for(i in a) print i ", " a[i]"KB";}'
7.awk scripts
BEGIN{ 这里面放的是执行前的语句 }
{这里面放的是处理每一行时要执行的语句}
END {这里面放的是处理完所有的行后要执行的语句 }
8.ENV vars (1.-v parameter 2. ENVIRON["KEY"] ENVIRON的环境变量需要export)
$ cat score.txt Marry 2143 78 84 77 Jack 2321 66 78 45 Tom 2122 48 77 71 Mike 2537 87 97 95 Bob 2415 40 57 62
x=5 y=10
export y
awk -v val=$x '{print $1, $2, $3, $4+val, $5+ENVIRON["y"]}' OFS="\t" score.txt
9.Others
#从file文件中找出长度大于80的行
awk 'length>80' file
#按连接数查看客户端IP
netstat -ntu | awk '{print $5}' | cut -d: -f1 | sort | uniq -c | sort -nr
#打印99乘法表
$ seq 9 | sed 'H;g' | awk -v RS='' '{for(i=1;i<=NF;i++)printf("%dx%d=%d%s", i, NR, i*NR, i==NR?"\n":"\t")}' 1x1=1 1x2=2 2x2=4 1x3=3 2x3=6 3x3=9 1x4=4 2x4=8 3x4=12 4x4=16 1x5=5 2x5=10 3x5=15 4x5=20 5x5=25 1x6=6 2x6=12 3x6=18 4x6=24 5x6=30 6x6=36 1x7=7 2x7=14 3x7=21 4x7=28 5x7=35 6x7=42 7x7=49 1x8=8 2x8=16 3x8=24 4x8=32 5x8=40 6x8=48 7x8=56 8x8=64 1x9=9 2x9=18 3x9=27 4x9=36 5x9=45 6x9=54 7x9=63 8x9=72 9x9=81
Refers:
http://coolshell.cn/articles/9070.html
内建变量,参看:http://www.gnu.org/software/gawk/manual/gawk.html#Built_002din-Variables
流控方面,参看:http://www.gnu.org/software/gawk/manual/gawk.html#Statements
内建函数,参看:http://www.gnu.org/software/gawk/manual/gawk.html#Built_002din
正则表达式,参看:http://www.gnu.org/software/gawk/manual/gawk.html#Regexp