match index notation of file1 to the index of file2 and pull out matching rows

Question

file1 contains multiple alphabetic sequences:

AETYUIOOILAKSJ
EAYEURIOPOSIDK
RYXURIAJSKDMAO
URITORIEJAHSJD
YWQIAKSJDHFKCM
HAJSUDIDSJSIAJ
AJDHDPFDIXSIBJ
JAQIAUXCNC         


        

Answer 1

Here you go:

awk 'NR==FNR {b[$0]++;next} {for (i in b) {a=match($0,"[A-Z]");n=substr($0,1,(a-1));s=substr($0,a);t=substr(i,n,1);if (t==s) print i}}' file1 file2
AETYUIOOILAKSJ
RYXURIAJSKDMAO
URITORIEJAHSJD
JAQIAUXCNCVUFO

Some more readable:

awk '
NR==FNR {
  b[$0]++;
  next
} 
{
  for (i in b) {
    a=match($0,"[A-Z]");
    n=substr($0,1,(a-1));
    s=substr($0,a);
    t=substr(i,n,1);
    if (t==s) 
      print i
    }
}
' file1 file2

With comments:

awk '
NR==FNR {                 # For the first file
  b[$0]++;                # Store file1 in in array b
  next
} 
{
  for (i in b) {          # Loop trough elements in array b
    a=match($0,"[A-Z]");  # For file2 find where letters starts
    n=substr($0,1,(a-1)); # Store the number part of file2 in n
    s=substr($0,a);       # Store the letters part of file2 in s
    t=substr(i,n,1);      # from file1 find string at position n
    if (t==s)             # test if string found is equal to letter to find s
      print i             # if yes, print the line 
    }
}
' file1 file2