Shell Programming and Scripting

!@#$%2QW5QWERTAB$%^&*

!|@|#|$|%|2QW|5QWERT|A|B|$|%|^|&|*

String   # of A   #of B   # of longer patterns
!@#$%2QW5QWERTABCD$%^&*   1   1   1:QW; 1:QWERT

awk 'BEGIN{OFS="   "; print "String   # of A   #of B   # of longer patterns"}
{
   string=$0
   
   # number of 'A'
   num_A=gsub(/A/,"A",string)
   
   #number of 'B'
   num_B=gsub(/B/,"B",string)
   
   # extract long pattern #1
   num_pattern_1==0   
   match(string, /[0-9]+/)
   length_pattern_1=substr(string, RSTART,RLENGTH)
   pattern_1=substr(string, RSTART+1, length_pattern_1)

   # extract long_pattern #2 (stuck here)
   Is there a way to skip the first digit match?  
   If I use 'split(string, b, "[0-9]+")' I could use a for loop through the different indexes of array b, but I will lose the pattern length.

   # count the number of same pattern
   Since I cannot use 'split' I don't see how I could iterate the count through the different motifs 

   print string, num_A, num_B, num_pattern_1":"pattern_1";"num_pattern_2":"pattern_2"; "num_pattern_X":"pattern-X
}'

$ 
$ cat -n f36.awk
     1	BEGIN {ind=0; str=""}
     2	{
     3	     n = split($0, a, "");
     4	     i = 1;
     5	     while (i <= n) {
     6	         if (a[i] >= 1 && a[i] <= 9) {
     7	             str = a[i];
     8	             for (j=i+1; j<=i+a[i]; j++) {
     9	                 str = str""a[j];
    10	             }
    11	             ind++;
    12	             pattern[ind] = str;
    13	             str = "";
    14	             i = i + a[i] + 1;
    15	         } else if (a[i] >= "A" && a[i] <= "Z") {
    16	             ind++;
    17	             pattern[ind] = a[i];
    18	             i++;
    19	         } else {
    20	             i++;
    21	         }
    22	     }
    23	}
    24	END {
    25	    for (k=1; k<=ind; k++) { printf("pattern[%d] = [%s]\n", k, pattern[k]) }
    26	}
    27	
$ 
$ echo "\!@#$%2QW5QWERTAB$%^&*" | awk -f f36.awk
pattern[1] = [2QW]
pattern[2] = [5QWERT]
pattern[3] = [A]
pattern[4] = [B]
$ 
$ 
$ echo "\!@#$%2QW7QWERTABXY3PQR$%^Z&*LMn#O" | awk -f f36.awk
pattern[1] = [2QW]
pattern[2] = [7QWERTAB]
pattern[3] = [X]
pattern[4] = [Y]
pattern[5] = [3PQR]
pattern[6] = [Z]
pattern[7] = [L]
pattern[8] = [M]
pattern[9] = [O]
$ 
$

!@#$%4AvDf2QWER

3BHuI4RtYU2vGP

$%$6ABcdEf)-2yg*%/LK@~~()

$ 
$ cat -n f36_v1.awk
     1	BEGIN {ind=0; str=""}
     2	{
     3	     n = split($0, a, "");
     4	     i = 1;
     5	     while (i <= n) {
     6	         if (a[i] >= 1 && a[i] <= 9) {
     7	             while (1) {
     8	                 str = str""a[i];
     9	                 if (a[i+1] < 0 || a[i+1] > 9) { break; }
    10	                 else { i++; }
    11	             }
    12	             len = str;
    13	             str = "";
    14	             for (j=i+1; j<=i+len; j++) {
    15	                 str = str""a[j];
    16	             }
    17	             ind++;
    18	             pattern[ind] = str;
    19	             str = "";
    20	             i += len + 1;
    21	         } else if ((a[i] >= "a" && a[i] <= "z") || (a[i] >= "A" && a[i] <= "Z")) {
    22	             ind++;
    23	             pattern[ind] = a[i];
    24	             i++;
    25	         } else {
    26	             i++;
    27	         }
    28	     }
    29	}
    30	END {
    31	    for (k=1; k<=ind; k++) { printf("pattern[%d] = [%s]\n", k, pattern[k]) }
    32	}
    33	
    34	
$ 
$ echo "\!@#$%2QW5QWERTAB$%^&*" | awk -f f36_v1.awk
pattern[1] = [QW]
pattern[2] = [QWERT]
pattern[3] = [A]
pattern[4] = [B]
$ 
$ echo "\!@#$%2QW7QWERTABXY3PQR$%^Z&*LMn#O" | awk -f f36_v1.awk
pattern[1] = [QW]
pattern[2] = [QWERTAB]
pattern[3] = [X]
pattern[4] = [Y]
pattern[5] = [PQR]
pattern[6] = [Z]
pattern[7] = [L]
pattern[8] = [M]
pattern[9] = [n]
pattern[10] = [O]
$ 
$ echo "\$%\$6ABcdEf)-2yg*%/LK@~~()" | awk -f f36_v1.awk
pattern[1] = [ABcdEf]
pattern[2] = [yg]
pattern[3] = [L]
pattern[4] = [K]
$ 
$ echo "3BHuI4RtYU2vGP" | awk -f f36_v1.awk
pattern[1] = [BHu]
pattern[2] = [I]
pattern[3] = [RtYU]
pattern[4] = [vG]
pattern[5] = [P]
$ 
$ echo "\!@#$%4AvDf2QWER" | awk -f f36_v1.awk
pattern[1] = [AvDf]
pattern[2] = [QW]
pattern[3] = [E]
pattern[4] = [R]
$ 
$

!@#$%3ABC$%DE$%4Fghi3ABC^&*D$%^&

pattern[1] = [ABC]
pattern[2] = [D]
pattern[3] = [E]
pattern[4] = [Fghi]
pattern[5] = [ABC]
pattern[6] = [D]

!@#$%3ABC$%DE$%4Fghi3ABC^&*D$%^&|2:D|1:E|2:ABC; 1:Fghi