1.

 

 

 

cat file:

>a1

1>a111>a1111>a22>a222>b13>b133

 

将各个title 下边的合在一起 输出如下：

>a1111111>a2222>b1333

 

awk '/^>/&&!a[$1]++||!/^>/'

(可以改写成 awk '/>/{if(!a[$0]++){print $0};next}1' )

 

awk '{if($0~/>/){m=$0}else{a[m]=a[m]"\n"$0}}END{for(i in a)print i,a[i]}'

（if else语句可以next代替，改写成awk '{if(/>/){m=$0}else{a[m]=a[m]"\n"$0}}END{for(i in a)print i,a[i]}'）

 

awk '/>/{!a[$0]++;print}' f1

>a1>a1>a1>a2>a2>b1>b1

 

awk '/>/{print}' f1

>a1>a1>a1>a2>a2>b1>b1

 

awk '/>/{if(!a[$0]++)print $0}' f1

>a1>a2>b1

 

awk '/>/&&!a[$0]++' f1

>a1>a2>b1

 

2.

 

cat file:

aaaaaa

adadaadadadad3a3a3a3a3a3s02a2a2a2a2

 

重复出现1至4次字符的行都输出，重复出现1至4次字符的结果应是

ababaadadadad3a3a3a3s0

 

awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++;l=asort(a)}a[l]<n' file

 

awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++}{for(i in a)print i,a[i]}' f5

a 6a 3d 2a 4d 4a 23 3a 23 2a 10 1s 13 1a 42 5

（i为每行重复出现的字符，a[i]为每行中某个字符重复出现的次数）

 

awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++;len=asort(a)}{for(i in a)print i,a[i]}' f5

1 61 22 31 42 41 22 31 22 24 11 12 13 11 42 5

（a[i]为每行中某个字符重复出现的次数。i为每行中某个字符的数组下标值（每行去重后，每行有哪几个字符），如第一行只有a重复，去重后下标值为1；第二行中a、d重复，下标值为1、2；a3s0行没有重复，所以有下标值1、2、3、4，至于排序为何为4、1、2、3，可参考 awk 'BEGIN{s="a3s0";split(s,a,"");len=asort(a);for(i in a)print i,a[i]}'

4 s1 02 33 a）

 

awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++;len=asort(a)}{print a[len]}' f5

6343215

（a[len]为每行中某个字符重复出现的次数，所以a[len]<n表示取重复次数少于n的行）

 

3.

 

df -h

/dev/sda2        49G   21G   26G  45% /tmpfs            16G     0   16G   0% /dev/shm/dev/sda1       193M   34M  150M  19% /boot

 

AB=`df -h`

echo $AB发现结果是以空格为分隔符如何实现跟df -h一样的换行显示呢？

 

AB="$(df -h)"
echo "$AB"

 

4.

 

 

有一个文件file1：（tab分隔）

track name=STRINGENT_LT_1KBchr3    23232   asdbaskjdbchr3    32434   daffsfchr5    43131   dkfjkdjgkdjgkchr6    4574857   wejwechr7    11313     sjdjsgdchr8    2323     lskdksstrack name=STRINGENT_HIGH_SCOREchr1   1212123      fkekfhdchr2   2322342     erererchr2   43444        sdsdsdchr3    454545      dkfjdkjfkchr5    343434     qsadjhdjhtrack name=STRINGENT_LT_332KBtrack name=STRINGENT_LOW_SCOREchr7   2323232    sdsdsdaaachr10  223232    dssdsdschr19   677675   dlkslk

 

统计不同track name下的数目，结果如下：（tab分隔）

track name=STRINGENT_LT_1KB：6track name=STRINGENT_HIGH_SCORE：5track name=STRINGENT_LT_332KB：0track name=STRINGENT_LOW_SCORE：3

 

awk '{if(/^t/){if(NR>1)print s":"n;n=0;s=$0}else n++}END{print s":"n}' f8

（可以改写成next语句：awk '/^t/{if(NR>1)print s":"n;n=0;s=$0;next}{n++}END{print s":"n}' f8） 

 

awk '{if(/track/){m=$0}else i++;print m,i}' f8

track name=STRINGENT_LT_1KB track name=STRINGENT_LT_1KB 1track name=STRINGENT_LT_1KB 2track name=STRINGENT_LT_1KB 3track name=STRINGENT_LT_1KB 4track name=STRINGENT_LT_1KB 5track name=STRINGENT_LT_1KB 6track name=STRINGENT_HIGH_SCORE 6track name=STRINGENT_HIGH_SCORE 7track name=STRINGENT_HIGH_SCORE 8

 ……

 

awk '{if(/track/){m=$0;i=0}else i++;print m,i}' f8

track name=STRINGENT_LT_1KB 0track name=STRINGENT_LT_1KB 1track name=STRINGENT_LT_1KB 2track name=STRINGENT_LT_1KB 3track name=STRINGENT_LT_1KB 4track name=STRINGENT_LT_1KB 5track name=STRINGENT_LT_1KB 6track name=STRINGENT_HIGH_SCORE 0track name=STRINGENT_HIGH_SCORE 1track name=STRINGENT_HIGH_SCORE 2track name=STRINGENT_HIGH_SCORE 3track name=STRINGENT_HIGH_SCORE 4track name=STRINGENT_HIGH_SCORE 5

……

 

awk '{if(/^t/){m=$0;i=0}else i++}END{print m,i}' f8

track name=STRINGENT_LOW_SCORE 3

 

awk '{if(/^t/){m=$0;a[m]=0}else a[m]++}END{print m,a[m]}' f8

track name=STRINGENT_LOW_SCORE 3

 

awk '{if(/^t/){m=$0;a[m]=0}else a[m]++}END{for(i in a){print i":"a[i]}}' f8

(可以改写成next语句：awk '/^t/{m=$0;a[m]=0;next}{a[m]++}END{for(i in a){print i":"a[i]}}' f8)

track name=STRINGENT_LT_1KB:6track name=STRINGENT_LT_332KB:0track name=STRINGENT_HIGH_SCORE:5track name=STRINGENT_LOW_SCORE:3

 

 

awk '{if(/^t/){if(NR>1)print s;s=$0}}' f8

track name=STRINGENT_LT_1KBtrack name=STRINGENT_HIGH_SCOREtrack name=STRINGENT_LT_332KB

 

awk '{if(/^t/){if(NR>1)print s;s=$0;print s}}' f8

track name=STRINGENT_LT_1KBtrack name=STRINGENT_LT_1KBtrack name=STRINGENT_HIGH_SCOREtrack name=STRINGENT_HIGH_SCOREtrack name=STRINGENT_LT_332KBtrack name=STRINGENT_LT_332KBtrack name=STRINGENT_LOW_SCORE

 

5.

echo "a b|c"|awk -F' |\\|' '{print NF}'

3

echo "a b|c"|awk -F' |\|' '{print NF}'

awk: 警告: 转义序列“\|”被当作单纯的“|”

2

echo "a b|c"|awk -F'[ |]' '{print NF}'

3

 

  awk -v RS='...'

这种写法是可以用少写一个，但不"规范"吧。可以少一个的原因是，最

后落单的那个\，经过 awk 的字符串解释后还是\，与\\的解释结果是一样的。

awk 'BEGIN{RS="...";}

写法就必须写够，一个也不能少。

$ echo -E '\\\'

\\\

$ echo|awk -v v='\\\' '{print "["v"]"}'

[\\]

$ echo|awk -v v='\\\\' '{print "["v"]"}'

[\\]

$ echo|awk -v v='\' '{print "["v"]"}'

[\]

$ echo|awk -v v='\\' '{print "["v"]"}'

[\]

$ echo|awk  'BEGIN{v="\\";}{print "["v"]"}'

[\]

$ echo|awk  'BEGIN{v="\\\";}{print "["v"]"}'

出错 

cat file：

123

123{\

123

123123{\1afewfwfaf

 

怎么才能用awk以{\为行分隔符来分割得到每一段的内容想要得到第一段

123123

 

awk -vRS='{\\\\' 'NR==1'

 

 

6.

 

字符串 'aaabcccaaabbbccc'，连续的字母作为一个子字符串，从左往右，去重复后，变为 'aaabcccbbb' ， awk或sed实现，不使用管道。

 

awk -F '' '{while(i++<=NF){s=s$i;if($i!=$(i+1)){if(!a[s]++)printf s;s=""}}}'

awk -F'ccc' '{sub(/[a]+/,"",$2);print $1FS$2}'

 

7.

seq 9

123456789如何得到以下结果:1 2 32 3 43 4 54 5 65 6 76 7 87 8 98 9

 

seq 9|awk '{a[NR]=$0}END{for(i=1;i<NR;i++)print a[i],a[i+1],a[i+2]}'

seq 9 | awk '{b=($1+1<=9)?$1+1:" ";c=($1+2<=9)?$1+2:" "; print $1" "b" "c}'

seq 9|awk 'NR==1{a=$1};NR==2{b=$1};NR>2{print a,b,$1;a=b;b=$1}END{print a,b}'

 

8.

[root@localhost ~]# a=1

[root@localhost ~]# while read num ; do a=$num ; done < <(seq 5) ; echo $a

5

[root@localhost ~]# for num in $(seq 5) ; do a=$num ; done ; echo $a

5

 seq 5 | while ... 这样的方式是产生一个了shell子进程,自然子进程里的东西不能改变父进程的值

 

9.

 

awk '/<frame name="mainFrame" src="/{print a[match($0,/<frame name="mainFrame" src="\/([^"]*)".*/,a)]}'

grep -Po '(?<=name="mainFrame" src=")[^"]+'

awk -F '[=" ]+' -v RS=">" '/"mainFrame" src="/{print $6}' 

 

10.

实现这样

（a=1且b=1）或者（c=1且d=1）成立时echo pass这样能用if实现么？如何来嵌套？

 

a=1; b=1; c=0; d=0;if [ $a -eq 1 ] && [ $b -eq 1 ];then echo pass;elif [ $c -eq 1 ] && [ $d -eq 1 ];then echo pass;fi

 

a=1; b=1; c=0; d=0; if (((a==1 && b==1 )||(c==1 && d ==1)));then echo pass;fi

 

awk 'BEGIN{a=1;b=1;c=0;d=1;if(((a==1&&b==1)||(c==1&&d==1))){print "pass"}else{print "。。"}}'

 

awk 'BEGIN{a=1; b=1; c=0; d=0;if(a==1&&b==1){print "pass"}else if(c==1&&d==1){print "pass"}else{print "。。"}}'

 

if [[ ($a = 1 && $b = 1) || ($c = 1 && $d = 1) ]];then

    echo Trueelse    echo Falsefi

 

11.

 

awk 'm~/==/&&/^\s*$/{print m}{m=$0}'

 

12.

 

grep -vf B A

awk 'NR==FNR{a[$0];next}{for(i in a){if(match($0,i)>0)next}print}' B A

awk 'NR==FNR{a[$0];next}{for(i in a)if(index($0,i))next}1' B A

 

awk 'FNR==NR{k=k?k"|"$0:$0;next}$0!~k{print}' B A

(awk '{k=k?k"|"$0:$0}END{print k}' BNow|We|ment)

 

13.

 

 

二维数组

awk 'BEGIN{for(i=1;i<=3;i++)for(j=1;j<=4;j++)a[i,j]=i*j;for(x in a){split(x,b,SUBSEP);print b[1]"*"b[2]"="a[x]}}'

 

找出文件A有文件B没有的行

awk 'BEGIN{for(i=1;i<=3;i++){for(j=1;j<=4;j++){s=s"R"i"C"j;print s}}}'

或者awk 'BEGIN{for(i=1;i<=3;i++)for(j=1;j<=4;j++)print "R"i"C"j}'

awk 'BEGIN{for(i=1;i<=3;i++)for(j=1;j<=4;j++)a["R"i"C"j];for(i in a)print i}'

awk '{for(i=1;i<=3;i++)for(j=1;j<=4;j++)a["R"i"C"j]}END{for(i in a)print i}' file

 

awk 'BEGIN{for(i=1;i<=3;i++){for(j=1;j<=4;j++){s="R"i"C"j;print s>"file"}}}'

awk 'NR==FNR{a[$2];next}{for(i in a){if($0==i)next}print}’

 

 14.

 

awk   '{ORS=NR%2?"\n":" "}1' 

awk 'NR==1{print;next}NR%2==0{lastline=$0;next}{print lastline,$0}'

awk 'NR%2==0{m=$0}NR%2==1{print m,$0}'

awk 'NR==1{print}NR%2==0{x=NR;m=$0}x{getline s;print m,s}'

awk 'NR==1{print}NR%2==0{x=NR;m=$0}x&&NR-x==1{print m,$0}'

awk 'NR==1{print}{a[NR]=$0}END{for(i=1;i<=NR;i++){if(i%2==0)print a[i],a[i+1]}}'

 

 

15.

 

\1代表你前面第一个\( \)里面的内容  \2代表第二个，以此例推

awk --re-interval 'NR==1{a=gensub(/.*(.{10})/,"\\1",1);print a+0}'

awk -F '' '{m=substr($0,NF-9,NF);gsub(/0+/,"",m);print m}'

 

 16.

awk '{a[$1]=$2;b[$1]=$1}END{for(i=1;i<=asort(b,c);i++)print b[c[i]],a[b[c[i]]],i%3==1?++n:n}'

 

cat file:

1        a

3        s2        f5        g7        j4        t9        r6        w8        l

 

根据第一行排序第二行

awk '{a[$1]=$2}END{for(i=1;i<=NR;i++)print i,a[i]}'

awk '{a[$1]=$2}END{for(i=1;i<=asort(a,c);i++)print i,a[i]}'

 

$ cat file

aaa 125ddd 123bbb 128ccc 120

$ awk '{a[$2]=$0}END{for(i=1;i<=asort(a);i++)print a[i]}' file

aaa 125bbb 128ccc 120ddd 123

$ awk '{a[$2]=$0}END{for(i=1;i<=asorti(a,b);i++)print a[b[i]]}' file

ccc 120ddd 123aaa 125bbb 128

 

echo "8 11111 9" | awk '{split($0,a," ");for(i=1;i<=asort(a,c);i++)print i,a[i],c[i]}'

1 8 82 11111 93 9 11111

 

echo "8 11111 9" | awk '{split($0,a," ");for(i=1;i<=asort(a);i++)print i,a[i],c[i]}'

1 8 2 9 3 11111

 

echo "8 11111 9" | awk '{split($0,a," ");for(i=1;i<=asort(a,c);i++)print i,a[2],c[2]}'

1 11111 92 11111 93 11111 9 

 

17.

 

var="'(]\\{}\$\""

 

18.

 

  #! /bin/sh

    A=B  echo  $A    echo  $A

 

19.

 

awk '/ve/||(sub($2,$2 FS $NF) && NF--)' OFS='\t'

awk '/ap/{for(i=1;i<=NF;i++){if(i==3)printf $NF"\t"$i"\t";else if($i==$NF)print "";else{printf $i"\t"}}next}1' 

 

20.

 

awk 'NR==FNR{a[$1" "$2" "$3]=$1;b[$1]++}NR>FNR{counter=0;for(i in a)if($1==a[i]){split(i,m," ");i || $2>m[3] || (m[2]==$2 && m[3]==$3))counter++}print NR,counter}' f1 f1

 

awk 'NR==FNR{a[$1" "$2" "$3]=$1;b[$1]++}NR>FNR{counter=0;for(i in a){if($1==a[i]){split(i,m," ");] || $2>m[3] || ( m[2]==$2 && m[3]==$3))counter++;else next;if(counter == b[$1])print $0}}}' f1 f1

 

 21.

awk '{if($1==x){s=s","$2}else{if(NR>1){print s}s=$1"\t"$2}x=$1}END{print s}'

awk '{x[$1]=length(x[$1])?x[$1]","$2:$2}END{for(i in x)print i"\t"x[i]}'

awk '{x[$1]=length(x[$1])?x[$1]","$2:$2;len=asorti(x,b)}END{for(i=1;i<=len;i++)print b[i],x[b[i]]}' f5

 

awk '/track/{x=NR;a[x]=$0}x{print x,NR,a[x],NR-x}'

 

7720 98

7720 99

7720 218

7720 219

7720 220

awk '{a[$1]=$2}{printf a[$1]","}'

awk -v RS='7720' '{printf ","$1}'

awk '{x=$1;if($1==x){s=s","$2}}END{print x,s}'

awk '{if($1==x){s=s","$2}else{if(NR>1){print s}s=$1"\t"$2}x=$1}END{print s}'

awk '{if($1==x){if($2==y+1)s=s"-"$2;else s=s","$2}else{if(NR>1){print s}s=$1"\t"$2}x=$1;y=$2}END{gsub(/-[^,]*-/,"-",s);print s}'

 

 

22.

   练习题（排序合并）

 

awk '{m=gensub(/([^0-9]+).*/,"\\1",1,$2);n=gensub(/[^0-9]+(.*)/,"\\1",1,$2);t=$1" "sprintf("%s%10[t]=$1;b[t]=m;c[t]=n}END{for(i=0;i++<asorti(c,d);){print d[i],a[d[i]]}}'

apple cat        12 apple

apple cat       106 appleapple cat       107 appleapple cat       108 appleapple cat       109 appleapple cat       123 appleapple cat       125 applepear dog        11 pearpear dog       101 pearpear dog       103 pearpear dog       104 pearpear dog       105 pearpear mouse       106 pearpear mouse       107 pearpear mouse       108 pearpear mouse       109 pearpear mouse       123 pearpear mouse       125 pear

 

awk '{m=gensub(/([^0-9]+).*/,"\\1",1,$2);n=gensub(/[^0-9]+(.*)/,"\\1",1,$2);t=$1" "sprintf("%s%10s",m,n);a[t]=$1;b[t]=m;c[t]=n}END{for(i=0;i++<asorti(c,d);){if(!k)printf "%s: ",a[d[i]]}}'

awk '{m=gensub(/([^0-9]+).*/,"\\1",1,$2);n=gensub(/[^0-9]+(.*)/,"\\1",1,$2);t=$1" "sprintf("%s%10s",m,n);a[t]=$1;b[t]=m;c[t]=n}END{for(i=0;i++<asorti(c,d);){if(!k)printf "%s: ",a[d[i]];if(k&&k!=a[d[i]]){printf "%s\n%s: ",s,a[d[i]];s=""}}}'

 

 

23.

 

awk '{a[$1];for(i=1;i++<NF;)b[$1,i]=b[$1,i]!=""?b[$1,i]"/"$i:$i}END{for(i in a){printf i;for(j=1;j++<NF;)printf " "b[i,j];print ""}}'

 

awk '{if(a[$1]){split(a[$1],b," ");a[$1]=$1" "b[2]"/"$2" "b[3]"/"$3" "b[4]"/"$4}else{a[$1]=$0}}END{l=asort(a);for(i=1;i<=l;i++)print a[i]}' file

 

24.

 

awk -F '' '{if($3~4)print $0>"a";else print$0>"b"}' f5

awk -F '' '$3~4{print $0>"e"}$3~5{print$0>"f"}' f5awk '/^..4/{print $0>"g"}/^..5/{print$0>"h"}' f5awk '{m=substr($0,3,1);if(m==4)print $0>"c";else{print $0>"d"}}' f5awk '{print >substr($0,3,1)".txt"}'