Linux awk 命令

awk命令概述 ：

awk可用于处理文本文件 (pattern scanning and processing language)

$ awk --help
Usage: awk [POSIX or GNU style options] -f progfile [--] file ...
Usage: awk [POSIX or GNU style options] [--] 'program' file ...
POSIX options:        GNU long options: (standard)
    -f progfile        --file=progfile
    -F fs            --field-separator=fs
    -v var=val        --assign=var=val
Short options:        GNU long options: (extensions)
    -b            --characters-as-bytes
    -c            --traditional
    -C            --copyright
    -d[file]        --dump-variables[=file]
    -e 'program-text'    --source='program-text'
    -E file            --exec=file
    -g            --gen-pot
    -h            --help
    -L [fatal]        --lint[=fatal]
    -n            --non-decimal-data
    -N            --use-lc-numeric
    -O            --optimize
    -p[file]        --profile[=file]
    -P            --posix
    -r            --re-interval
    -S            --sandbox
    -t            --lint-old
    -V            --version


gawk is a pattern scanning and processing language.
By default it reads standard input and writes standard output.

Examples:
    gawk '{ sum += $1 }; END { print sum }' file
    gawk -F: '{ print $1 }' /etc/passwd

实例 ：

################################################

#每行按空格或 tab 键分隔，输出第1，4项
(base) [biocodee@localhost ~]$ head log.txt 
2 this is a test
3 Are you like awk
This's a test
10 There are orange,apple,mongo

(base) [biocodee@localhost ~]$ awk '{print $1,$4}' log.txt
2 a
3 like
This's 
10 orange,apple,mongo
#格式化输出
(base) [biocodee@localhost ~]$ awk '{printf "%-8s %-10s\n",$1,$4}' log.txt
2        a         
3        like      
This's             
10       orange,apple,mongo

#指定分隔符 -F
(base) [biocodee@localhost ~]$ awk -F, '{print $1,$4}' log.txt
2 this is a test 
3 Are you like awk 
This's a test 
10 There are orange 
#使用内建变量
(base) [biocodee@localhost ~]$ awk 'BEGIN{FS=","} {print $1,$2}' log.txt
2 this is a test 
3 Are you like awk 
This's a test 
10 There are orange apple
#多个分隔符：先用空格分割，然后对分割结果再使用","分割
(base) [biocodee@localhost ~]$ awk -F '[ ,]' '{print $1,$2,$5}' log.txt 
2 this test
3 Are awk
This's a 
10 There apple
#设置变量
(base) [biocodee@localhost ~]$ awk -va=1 '{print $1,$1+a}' log.txt 
2 3
3 4
This's 1
10 11
(base) [biocodee@localhost ~]$ awk -va=1 -vb=s '{print $1,$1+a,$1b}' log.txt 
2 3 2s
3 4 3s
This's 1 This'ss
10 11 10s
#执行脚本
$awk -f ***.awk  log.txt 

#过滤第一列大于2的行
awk  '$1>2' log.txt

(base) [biocodee@localhost ~]$ awk  '$1>2' log.txt
3 Are you like awk
This's a test
10 There are orange,apple,mongo
#过滤第一列等于2的行
awk '$1=2' log.txt

(base) [biocodee@localhost ~]$ awk '$1=2' log.txt
2 this is a test
2 Are you like awk
2 a test
2 There are orange,apple,mongo

#过滤第一列大于2并且第二列等于`Are`的行
awk '$1>2 && $2=="Are" {print $1,$2,$3}' log.txt 

(base) [biocodee@localhost ~]$ awk '$1>2 && $2=="Are" {print $1,$2,$3}' log.txt 
3 Are you




##############################################################
#####使用正则，字符串匹配 

#输出第二列（包含"th"）,并打印第二列与第四列
#awk '$2 ~ /th/ {print $2,$4}'  log.txt ; '~'表示模式开始，'//' 中是模式
(base) [biocodee@localhost ~]$ awk '$2 ~ /th/ {print $2,$4}'  log.txt
this a

#忽略大小写 
#awk 'BEGIN{IGNORECASE=1} /this/' log.txt
(base) [biocodee@localhost ~]$ awk 'BEGIN{IGNORECASE=1} /this/' log.txt
2 this is a test
This's a test


#模式取反
#awk '$2 !~ /th/ {print $2,$4}' log.txt
(base) [biocodee@localhost ~]$ awk '$2 !~ /th/ {print $2,$4}' log.txt
Are like
a 
There orange,apple,mongo

#awk '!/th/ {print $2,$4}' log.txt
(base) [biocodee@localhost ~]$ awk '!/th/ {print $2,$4}' log.txt
Are like
a 
There orange,apple,mongo

#`awk` 脚本
关键词 :  BEGIN 和 END 
执行前的语句 ----> BEGIN{***}
处理完所有的行后要执行的语句 ----->  END{}
处理每一行时要执行的语句  -------> {}

(base) [biocodee@localhost blog]$ awk -f score_cal.awk  score.txt 
NAME    NO.   MATH  ENGLISH  COMPUTER   TOTAL
---------------------------------------------
Marry  2143     78       84       77      239
Jack   2321     66       78       45      189
Tom    2122     48       77       71      196
Mike   2537     87       97       95      279
Bob    2415     40       57       62      159
---------------------------------------------
  TOTAL:       319      393      350 
AVERAGE:     63.80    78.60    70.00





##################################################################

#九九乘法表
(base) [biocodee@localhost blog]$ 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

awk运算符

运算符
= += -= = /= %= ^= *=	赋值
?:	C条件表达式
\	\		逻辑或
&&	逻辑与
~ 和 ！~	匹配正则表达式和不匹配正则表达式
空格	连接
+ - ！	一元加，减 和逻辑非
^ *	求幂
++ --	增加或者减少，作为前缀或者后缀
$	字段引用
in	数组成员

reference : runnob 菜鸟教程 awk