#from chr 2 to right before first space or to the end of $str
#if no space is found
# - ^.{2} = skip past first two characters
# - \S = not whitespace, \s=whitespace
# - (\S*) captures zero or more non-whitespace characters
# - ($str =~ /^.{2}(\S*)\s/) is a list containing one string,
#    i.e. ($1) where $1=what was captured by (\S*)
printf "substr(2, first ' ' or end): %s\n", ($str =~ /^.{2}(\S*)/);

#from chr 2 to lessor of 5 character or first space
#\S = not whitespace, \s=whitespace
printf "substr(2, first ' ' or 5 chars): %s\n"
  , ($str =~ /^.{2}(\S{0,5})/);

#from chr 3 to first X or end of $str
printf "substr(3, first 'X' or end): %s\n"
  , ($str =~ /^.{3}([^X]*)/);

#from chr 3 to lessor of first X or 5 chars
printf "substr(3, first 'X' or 5 chars): %s\n"
  , ($str =~ /^.{3}([^X]{0,5})/);

#from chr 3 to first occurance of two or more A's or to the end if
#no doubled A's are found
printf "substr(3,two or more A's or end): %s\n"
  , ($str =~ /^.{3}(.*?)(AA|$)/);

#from chr 10 to lessor of 5 chars or first of run of 2 or more A's
printf "substr(10,two or more A's or 5 chars): %s\n"
  , ($str =~ /^.{10}((?:[^A]|A(?!A)){0,5})/);

#from chr 10 to lessor of 5 chars or first of run of 2 or more X's
printf "substr(10,two or more X's or 5 chars): %s\n"
  , ($str =~ /^.{10}((?:[^X]|X(?!X)){0,5})/);

#from chr 5 to first occurance of two or more X's or to the end if
#no doubled A's are found
printf "substr(3,two or more X's or end): %s\n"
  , ($str =~ /^.{3}(.*?)(?:XX|$)/);

#outputs
substr(2, first ' ' or end): XCDEFDGHIXTAAGRAAAAAA
substr(2, first ' ' or 5 chars): XCDEF
substr(3, first 'X' or end): CDEFDGHI
substr(3, first 'X' or 5 chars): CDEFD
substr(3,two or more A's or end): CDEFDGHIXT
substr(10,two or more A's or 5 chars): IXT
substr(10,two or more X's or 5 chars): IXTAA
substr(3,two or more X's or end): CDEFDGHIXTAAGRAAAAAA theEnd