webencode

#!/usr/bin/env perl
use strict;
use warnings;
use Data::Dump qw( dump );

while (<>) {
    chomp;
    print urlenc($_), "\n";
}

sub webparams
{
  my $query=shift()||$ENV{QUERY_STRING};
  if(! $query && $ENV{REQUEST_METHOD} eq "POST"){
    read(STDIN,$query , $ENV{CONTENT_LENGTH});
    $ENV{QUERY_STRING}=$query;
  }
  my %R;
  for(split("&",$query)){
    next if !length($_);
    my($nkl,$verdi)=map urldec($_),split("=",$_,2);
    $R{$nkl}=exists$R{$nkl}?"$R{$nkl},$verdi":$verdi;
  }
  return %R;
}

=head2 urlenc

Input: a string

Output: the same string URL encoded so it can be sent in URLs or POST requests.

In URLs (web addresses) certain characters are illegal. For instance I<space> and I<newline>.
And certain other chars have special meaning, such as C<+>, C<%>, C<=>, C<?>, C<&>.

These illegal and special chars needs to be encoded to be sent in
URLs.  This is done by sending them as C<%> and two hex-digits. All
chars can be URL encodes this way, but it's necessary just on some.

Example:

 $search="Østdal, Åge";
 use LWP::Simple;
 my $url="http://machine.somewhere.com/cgi-bin/script?s=".urlenc($search);
 print $url;
 my $html = get($url);

Prints C<< http://soda.uio.no/cgi/DB/person?id=%D8stdal%2C+%C5ge >>

=cut

sub urlenc
{
  my $str=shift;
  $str=~s/([^\w\-\.\,\[\]])/sprintf("%%%02x",ord($1))/eg; #more chars is probably legal...
  return $str;
}

=head2 urldec

Opposite of L</urlenc>.

Example, this returns 'C< ø>'. That is space and C<< ø >>.

 urldec('+%C3')

=cut

sub urldec{
  my $str=shift;
#  $str=~y/+/ /;
  $str=~s/\+/ /gs;
  $str=~s/%([a-f\d]{2})/pack("C", hex($1))/egi;
  return $str;
}