awk題目3
- 2020 年 1 月 6 日
- 筆記
1.
http://bbs.chinaunix.net/thread-4157887-1-1.html
cat file:
>a1 1 >a1 11 >a1 111 >a2 2 >a2 22 >b1 3 >b1 33
將各個title 下邊的合在一起 輸出如下： >a1 1 11 111 >a2 2 22 >b1 3 33
awk '/^>/&&!a[$1]++||!/^>/'
(可以改寫成 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語句可以next代替，改寫成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[$0]++' f1 >a1 >a2 >b1
2.
http://bbs.chinaunix.net/forum.php?mod=viewthread&tid=4157497&page=1#pid24299288
cat file:
aaaaaa adada adadadad 3a3a3 a3a3 a3s0 2a2a2a2a2
重複出現1至4次字元的行都輸出，重複出現1至4次字元的結果應是 ababa adadadad 3a3a3 a3s0
awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++;l=asort(a)}a[l]<n' file
awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++}{for(i in a)print i,a[i]}' f5 a 6 a 3 d 2 a 4 d 4 a 2 3 3 a 2 3 2 a 1 0 1 s 1 3 1 a 4 2 5
（i為每行重複出現的字元，a[i]為每行中某個字元重複出現的次數）
awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++;len=asort(a)}{for(i in a)print i,a[i]}' f5 1 6 1 2 2 3 1 4 2 4 1 2 2 3 1 2 2 2 4 1 1 1 2 1 3 1 1 4 2 5
（a[i]為每行中某個字元重複出現的次數。i為每行中某個字元的數組下標值（每行去重後，每行有哪幾個字元），如第一行只有a重複，去重後下標值為1；第二行中a、d重複，下標值為1、2；a3s0行沒有重複，所以有下標值1、2、3、4，至於排序為何為4、1、2、3，可參考 awk 'BEGIN{s="a3s0";split(s,a,"");len=asort(a);for(i in a)print i,a[i]}' 4 s 1 0 2 3 3 a）
awk -v n=5 -F '' '{delete a;for(i=1;i<=NF;i++)a[$i]++;len=asort(a)}{print a[len]}' f5 6 3 4 3 2 1 5
（a[len]為每行中某個字元重複出現的次數，所以a[len]<n表示取重複次數少於n的行）
3.
http://bbs.chinaunix.net/forum.php?mod=viewthread&tid=4157298&page=1#pid24298104
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 $AB 發現結果是以空格為分隔符 如何實現跟df -h一樣的換行顯示呢？
AB="$(df -h)" echo "$AB"
4.
http://bbs.chinaunix.net/forum.php?mod=viewthread&tid=4156330&page=1#pid24293665
有一個文件file1：（tab分隔） track name=STRINGENT_LT_1KB chr3 23232 asdbaskjdb chr3 32434 daffsf chr5 43131 dkfjkdjgkdjgk chr6 4574857 wejwe chr7 11313 sjdjsgd chr8 2323 lskdkss track name=STRINGENT_HIGH_SCORE chr1 1212123 fkekfhd chr2 2322342 ererer chr2 43444 sdsdsd chr3 454545 dkfjdkjfk chr5 343434 qsadjhdjh track name=STRINGENT_LT_332KB track name=STRINGENT_LOW_SCORE chr7 2323232 sdsdsdaaa chr10 223232 dssdsds chr19 677675 dlkslk
統計不同track name下的數目，結果如下：（tab分隔） track name=STRINGENT_LT_1KB：6 track name=STRINGENT_HIGH_SCORE：5 track name=STRINGENT_LT_332KB：0 track 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
（可以改寫成next語句：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 1 track name=STRINGENT_LT_1KB 2 track name=STRINGENT_LT_1KB 3 track name=STRINGENT_LT_1KB 4 track name=STRINGENT_LT_1KB 5 track name=STRINGENT_LT_1KB 6 track name=STRINGENT_HIGH_SCORE 6 track name=STRINGENT_HIGH_SCORE 7 track name=STRINGENT_HIGH_SCORE 8
……
awk '{if(/track/){m=$0;i=0}else i++;print m,i}' f8 track name=STRINGENT_LT_1KB 0 track name=STRINGENT_LT_1KB 1 track name=STRINGENT_LT_1KB 2 track name=STRINGENT_LT_1KB 3 track name=STRINGENT_LT_1KB 4 track name=STRINGENT_LT_1KB 5 track name=STRINGENT_LT_1KB 6 track name=STRINGENT_HIGH_SCORE 0 track name=STRINGENT_HIGH_SCORE 1 track name=STRINGENT_HIGH_SCORE 2 track name=STRINGENT_HIGH_SCORE 3 track name=STRINGENT_HIGH_SCORE 4 track 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
(可以改寫成next語句：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:6 track name=STRINGENT_LT_332KB:0 track name=STRINGENT_HIGH_SCORE:5 track name=STRINGENT_LOW_SCORE:3
awk '{if(/^t/){if(NR>1)print s;s=$0}}' f8 track name=STRINGENT_LT_1KB track name=STRINGENT_HIGH_SCORE track name=STRINGENT_LT_332KB
awk '{if(/^t/){if(NR>1)print s;s=$0;print s}}' f8 track name=STRINGENT_LT_1KB track name=STRINGENT_LT_1KB track name=STRINGENT_HIGH_SCORE track name=STRINGENT_HIGH_SCORE track name=STRINGENT_LT_332KB track name=STRINGENT_LT_332KB track name=STRINGENT_LOW_SCORE
5.
http://bbs.chinaunix.net/thread-4155608-2-1.html
echo "a b|c"|awk -F' |\|' '{print NF}' 3 echo "a b|c"|awk -F' ||' '{print NF}' awk: 警告: 轉義序列「|」被當作單純的「|」 2 echo "a b|c"|awk -F'[ |]' '{print NF}' 3
awk -v RS='...'
這種寫法是可以用少寫一個，但不"規範"吧。可以少一個的原因是，最 後落單的那個，經過 awk 的字元串解釋後還是，與\的解釋結果是一樣的。
awk 'BEGIN{RS="...";}
寫法就必須寫夠，一個也不能少。
$ 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"]"}' 出錯
cat file：
123 123 {
123 123 123 { 1af ewfwf af
怎麼才能用awk以{為行分隔符來分割得到每一段的內容想要得到第一段 123 123
awk -vRS='{\\' 'NR==1'
6.
http://bbs.chinaunix.net/thread-3679733-1-1.html
字元串 'aaabcccaaabbbccc'，連續的字母作為一個子字元串，從左往右，去重複後，變為 'aaabcccbbb' ， awk或sed實現，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 1 2 3 4 5 6 7 8 9 如何得到以下結果: 1 2 3 2 3 4 3 4 5 4 5 6 5 6 7 6 7 8 7 8 9 8 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=$1}END{print a,b}'
8.
http://bbs.chinaunix.net/thread-4154751-1-1.html
[root@localhost ~]# a=1 [root@localhost ~]# while read num ; do a=$num ; done < <(seq 5) ; echo $a 5 [root@localhost ~]# for num in $(seq 5) ; do a=$num ; done ; echo $a 5
seq 5 | while ... 這樣的方式是產生一個了shell子進程,自然子進程里的東西不能改變父進程的值
9.
http://bbs.chinaunix.net/thread-4154600-1-1.html
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.
http://bbs.chinaunix.net/thread-4154603-1-1.html
實現這樣 （a=1且b=1）或者（c=1且d=1）成立時 echo pass 這樣能用if實現么？ 如何來嵌套？
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 && $d = 1) ]];then echo True else echo False fi
11.
http://bbs.chinaunix.net/thread-4154531-3-1.html
awk 'm~/==/&&/^s*$/{print m}{m=$0}'
12.
http://bbs.chinaunix.net/thread-4154504-1-1.html
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}' B Now|We|ment)
13.
http://bbs.chinaunix.net/thread-4154469-1-1.html
二維數組
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沒有的行
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.
http://bbs.chinaunix.net/thread-4153934-1-1.html
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.
http://bbs.chinaunix.net/thread-4150372-1-1.html
1代表你前面第一個( )裡面的內容 2代表第二個，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.
http://bbs.chinaunix.net/thread-4150043-1-1.html
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 s 2 f 5 g 7 j 4 t 9 r 6 w 8 l
根據第一行排序第二行
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 125 ddd 123 bbb 128 ccc 120
$ awk '{a[$2]=$0}END{for(i=1;i<=asort(a);i++)print a[i]}' file aaa 125 bbb 128 ccc 120 ddd 123
$ awk '{a[$2]=$0}END{for(i=1;i<=asorti(a,b);i++)print a[b[i]]}' file ccc 120 ddd 123 aaa 125 bbb 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 8 2 11111 9 3 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($0,a," ");for(i=1;i<=asort(a,c);i++)print i,a[2],c[2]}' 1 11111 9 2 11111 9 3 11111 9
17.
http://bbs.chinaunix.net/thread-4149019-1-1.html
var="'(]\{}$""
18.
http://bbs.chinaunix.net/thread-1393874-1-1.html
#! /bin/sh A=B echo $A echo $A
19.
http://bbs.chinaunix.net/thread-4148647-1-1.html
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.
http://blog.chinaunix.net/uid-20778583-id-4247874.html
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.
http://bbs.chinaunix.net/thread-3620300-1-1.html
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}'
http://bbs.chinaunix.net/forum.php?mod=viewthread&tid=4156330&page=1#pid24396455
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.
http://bbs.chinaunix.net/thread-4119434-1-1.html 練習題（排序合併）
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 apple apple cat 107 apple apple cat 108 apple apple cat 109 apple apple cat 123 apple apple cat 125 apple pear dog 11 pear pear dog 101 pear pear dog 103 pear pear dog 104 pear pear dog 105 pear pear mouse 106 pear pear mouse 107 pear pear mouse 108 pear pear mouse 109 pear pear mouse 123 pear pear 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 "%sn%s: ",s,a[d[i]];s=""}}}'
23.
http://bbs.chinaunix.net/forum.php?mod=viewthread&tid=4147474
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.
http://bbs.chinaunix.net/thread-4145403-1-1.html
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"}' f5 awk '/^..4/{print $0>"g"}/^..5/{print$0>"h"}' f5 awk '{m=substr($0,3,1);if(m==4)print $0>"c";else{print $0>"d"}}' f5 awk '{print >substr($0,3,1)".txt"}'
