Code:
$
$ cat -n f36
1 !@#$%2QW5QWERTAB$%^&*
2 !@#$%2QW7QWERTABXY3PQR$%^Z&*LMn#O
3 $%$6ABcdEf)-2yg*%/LK@~~()
4 3BHuI4RtYU2vGP
5 !@#$%4AvDf2QWER
6 ##AAAABBBCCD##2RTC##=3XYZ##?4WWWW##3PQaR##=3XYZ#
7 ##AAAA#BBBvCCD##
8 ##AA#Bv#CC#4RSTUV#
9 #?2AA#3XYZvN#4PQrsN#3XYZ=2wq#
10 !^#=3AAAB$$?2CCR^&?2DD*=4EEEEY()
$
$ cat -n f36_v3.awk
1 function fetch_num (s) {
2 # This function returns the number at the start of a string.
3 # If "2ABCD" is passed, then 2 is returned.
4 # If "23XYZW" is passed, then 23 is returned.
5 l = length(s);
6 num = "";
7 i = 0;
8 while (++i <= l && substr(s,i,1) ~ /[2-9]/) {
9 num = num""substr(s,i,1);
10 }
11 return num;
12 }
13 function join (a, kvsep, arrsep) {
14 # This function joins all elements of an associative array with arrsep.
15 # Each key/value pair of the array is joined with kvsep.
16 # a = associative array
17 # kvsep = separator between key/value pairs
18 # arrsep = separator between array elements
19 iter = 1;
20 result = "";
21 for (i in a) {
22 if (iter == 1) { result = a[i] kvsep i; }
23 else { result = result arrsep a[i] kvsep i; }
24 iter++;
25 }
26 return result;
27 }
28 { # There are 4 associative arrays: s, m, q, e
29 # s => to store number of occurrences of single character patterns
30 # m => to store number of occurrences of multi-character patterns
31 # q => to store number of occurrences of patterns that follow "?" character
32 # e => to store number of occurrences of patterns that follow "=" character
33 str = $0;
34 ind = 1;
35 len = length(str);
36 printf("Input : %s\n", str);
37 while (ind <= len) {
38 ch = substr(str, ind, 1);
39 if (ch == "?" && substr(str,ind+1,1) ~ /[2-9]/) { # Pattern following "?"
40 n = fetch_num(substr(str, ind+1));
41 q[substr(str, ind+2, n)]++;
42 ind += n + 2;
43 } else if (ch == "=" && substr(str,ind+1,1) ~ /[2-9]/) { # Pattern following "="
44 n = fetch_num(substr(str, ind+1));
45 e[substr(str, ind+2, n)]++;
46 ind += n + 2;
47 } else if (ch ~ /[2-9]/) { # Multi-character pattern
48 n = fetch_num(substr(str, ind));
49 m[substr(str, ind+1, n)]++;
50 ind += n + 1;
51 } else if (ch ~ /[A-Za-z]/) { # Single-character pattern
52 s[ch]++;
53 ind++;
54 } else {
55 ind++;
56 }
57 }
58 if (join(s,";"," ") != "") { s_str = join(s,";"," "); }
59 if (join(m,";","/") != "") { m_str = join(m,";","/"); }
60 if (join(q,";","|") != "") { q_str = join(q,";","|"); }
61 if (join(e,";","|") != "") { e_str = join(e,";","|"); }
62 printf("Output : %s => %s %s %s %s\n", str, s_str, m_str, q_str, e_str);
63 printf("\n");
64 # Flush all arrays and start over again
65 split("",s);
66 split("",m);
67 split("",q);
68 split("",e);
69 }
70
$
$ awk -f f36_v3.awk f36
Input : !@#$%2QW5QWERTAB$%^&*
Output : !@#$%2QW5QWERTAB$%^&* => 1;A 1;B 1;QWERT/1;QW
Input : !@#$%2QW7QWERTABXY3PQR$%^Z&*LMn#O
Output : !@#$%2QW7QWERTABXY3PQR$%^Z&*LMn#O => 1;O 1;n 1;X 1;L 1;Y 1;M 1;Z 1;QWERTAB/1;PQR/1;QW
Input : $%$6ABcdEf)-2yg*%/LK@~~()
Output : $%$6ABcdEf)-2yg*%/LK@~~() => 1;K 1;L 1;yg/1;ABcdEf
Input : 3BHuI4RtYU2vGP
Output : 3BHuI4RtYU2vGP => 1;P 1;I 1;RtYU/1;vG/1;BHu
Input : !@#$%4AvDf2QWER
Output : !@#$%4AvDf2QWER => 1;R 1;E 1;AvDf/1;QW
Input : ##AAAABBBCCD##2RTC##=3XYZ##?4WWWW##3PQaR##=3XYZ#
Output : ##AAAABBBCCD##2RTC##=3XYZ##?4WWWW##3PQaR##=3XYZ# => 4;A 3;B 3;C 1;D 1;R 1;PQa/1;RT 1;WWWW 2;XYZ
Input : ##AAAA#BBBvCCD##
Output : ##AAAA#BBBvCCD## => 4;A 1;v 3;B 2;C 1;D 1;PQa/1;RT 1;WWWW 2;XYZ
Input : ##AA#Bv#CC#4RSTUV#
Output : ##AA#Bv#CC#4RSTUV# => 2;A 1;v 1;B 2;C 1;V 1;RSTU 1;WWWW 2;XYZ
Input : #?2AA#3XYZvN#4PQrsN#3XYZ=2wq#
Output : #?2AA#3XYZvN#4PQrsN#3XYZ=2wq# => 2;N 1;v 1;PQrs/2;XYZ 1;AA 1;wq
Input : !^#=3AAAB$$?2CCR^&?2DD*=4EEEEY()
Output : !^#=3AAAB$$?2CCR^&?2DD*=4EEEEY() => 1;B 1;R 1;Y 1;PQrs/2;XYZ 1;CC|1;DD 1;AAA|1;EEEE
$
$
12-28-2015
