sub CollapseWhitespace{@_ or return'';my$T=shift;defined$T or return'';my$L=length($T);$L or return'';my$c;my$N=0;my$P =0;my$U=1;for(my$i=0;$i<$L;$i++){$c=vec($T,$i,8);if($c<33){ $U=0;if($N++==1){vec($T,$P++,8)=32;}}else{$N=0;$U or vec($T ,$P,8)=$c;$P++;}}return$U?$T:substr($T,0,$P);} #### ############################################################## # # This function removes single instances of whitespace and # converts multiple adjacent whitespace characters to a single # space. In this function, "whitespace" is defined as a character # whose ASCII value is less than 33. (This includes many special # characters such as new line characters, nul, bel, etc.) # # Usage: STRING = CollapseWhitespace(STRING) # # Example: # CollapseWhitespace("\n\t abc 123 xxx\n") --> " abc123 xxx" # sub CollapseWhitespace { @_ or return ''; my $T = shift; defined $T or return ''; my $L = length($T); $L or return ''; my $c; my $N = 0; # consecutive whitespace counter my $P = 0; # target pointer to overwrite original str $T my $U = 1; # string length will be left unchanged for (my $i = 0; $i < $L; $i++) { $c = vec($T, $i, 8); if ($c < 33) { $U = 0; if ($N++ == 1) { vec($T, $P++, 8) = 32; } } else { $N = 0; $U or vec($T, $P, 8) = $c; $P++; } } return $U ? $T : substr($T, 0, $P); }