linux shell学习笔记 3

八．Awk高级应用

   条件操作符

操作符	描述
<	小于
>=	大于等于
<=	小于等于
= =	等于
！=	不等于
~	匹配正则表达式
！~	不匹配正则表达式

逻辑操作符

操作符	描述
&&	and
||	or
!	not

[root@localhost ~]# cat awkfi.sh

#!/bin/bash

echo "210~219网段的访问量是?`awk'{f $1~/^21[0-9]/) print $0}' www.log|wc -l`"

echo "非210~219网段的访问量是:`awk '{if ($1!~/^21[0-9]/) print $0}' www.log|wc -l`"

echo "2004年07月07日的访问量是: `awk '{if ($4~/^\[07\/Jul\/2004/) print $0}' www.log|wc -l`"

echo "2004年07月07日/htm/free_call.php的访问量是? `awk '{if ($4~/^\[07\/Jul\/2004/) print $0}' www.log|awk '{if ($7=="/htm/free_call.php") print $)}' print $0}'|wc -l`"

   awk的内置变量

ARGC	命令行参数个数
ARGV	命令行参数列数
ENVIRON	支持队列中系统环境变量的使用
FILENAME	Awk浏览的文件名
FNR	浏览文件的记录数
FS	设置输入域分割符，等价于命令行的－F选项
NF	浏览记录的域个数
NR	已读的记录数
OFS	输出域分割符
ORS	输出记录分割符
RS	控制记录分割符

[root@localhost ~]# awk -F '#' '{print NF,NR, $0}' grade.txt     F定义域的分隔符，NF代表$0的域的个数，NR代表已经读取的记录数

2 1 85#senior

2 2 87#junior

2 3 75#senior

2 4 75#junior

2 5 86#junior

2 6 97#senior

2 7 56#junior

2 8 76#senior

2 9 52#junior

2 10 65#senior

1 11 you have new mail in /var/spool/mail/root

[root@localhost ~]# awk -F '#' '{print NF,NR$0}' grade.txt

2 185#senior

2 287#junior

2 375#senior

2 475#junior

2 586#junior

2 697#senior

2 756#junior

2 876#senior

2 952#junior

2 1065#senior

1 11you have new mail in /var/spool/mail/root

[root@localhost ~]# cat grade.txt

85#senior

87#junior

75#senior

75#junior

86#junior

97#senior

56#junior

76#senior

52#junior

65#senior

you have new mail in /var/spool/mail/root

[root@localhost ~]# awk -F '#' '{print NF,NR,ENVIRON["USER"],$0}' grade.txt

2 1 root 85#senior

2 2 root 87#junior

2 3 root 75#senior

2 4 root 75#junior

2 5 root 86#junior

2 6 root 97#senior

2 7 root 56#junior

2 8 root 76#senior

2 9 root 52#junior

2 10 root 65#senior

1 11 root you have new mail in /var/spool/mail/root

[root@localhost ~]# awk -F '#' '{print NF,NR,ENVIRON["user"],$0,FILENAME}' grade.txt

2 1  85#senior grade.txt

2 2  87#junior grade.txt

2 3  75#senior grade.txt

2 4  75#junior grade.txt

2 5  86#junior grade.txt

2 6  97#senior grade.txt

2 7  56#junior grade.txt

2 8  76#senior grade.txt

2 9  52#junior grade.txt

2 10  65#senior grade.txt

1 11  you have new mail in /var/spool/mail/root grade.txt

[root@localhost ~]# awk -F '#' '{print NF,NR,ENVIRON["user"],$0,FILENAME,ARGC}' grade.txt

2 1  85#senior grade.txt 2           列出命令行的参数，在这个命令中分别是awk和grade.txt

2 2  87#junior grade.txt 2

2 3  75#senior grade.txt 2

2 4  75#junior grade.txt 2

2 5  86#junior grade.txt 2

2 6  97#senior grade.txt 2

2 7  56#junior grade.txt 2

2 8  76#senior grade.txt 2

2 9  52#junior grade.txt 2

2 10  65#senior grade.txt 2

1 11  you have new mail in /var/spool/mail/root grade.txt 2

[root@localhost ~]# awk -F '#' '{print NF,NR,ENVIRON["user"],$0,FILENAME,ARGC,AR

GV[0]}' grade.txt

2 1  85#senior grade.txt 2 awk          ARGV[0]列出命令行参数中的第一个参数awk

2 2  87#junior grade.txt 2 awk

2 3  75#senior grade.txt 2 awk

2 4  75#junior grade.txt 2 awk

2 5  86#junior grade.txt 2 awk

2 6  97#senior grade.txt 2 awk

2 7  56#junior grade.txt 2 awk

2 8  76#senior grade.txt 2 awk

2 9  52#junior grade.txt 2 awk

2 10  65#senior grade.txt 2 awk

1 11  you have new mail in /var/spool/mail/root grade.txt 2 awk

   字符串函数

  

gsub(r,s)	在整个$0中用s替代r
gsub(r,s,t)	在整个t中用s替代r,t可以是整条记录或一个域
index(s,t)	返回s中字符串t的第一位置
length(s)	返回s长度
match(s,r)	测试s是否包含匹配的字符串
split(s,a,fs)	用fs上将s分成序列a
sprint(fmt,exp)	返回经fmt格式化后代exp
sub(r,s)	用$0中最左边最长的子串替代s
substr(s,p)	返回字符串 s中从p开始往后的部分
substr(s,p,n)	返回字符串s中从p开始长度为n的后缀部分

[root@localhost ~]# awk -F '#' '{if (gsub("#","||")) print $0}' grade.txt

85||senior        if (gsub("#","||"))用||代替$0中的#

87||junior

75||senior

75||junior

86||junior

97||senior

56||junior

76||senior

52||junior

65||senior