see Re: Count Quoted Words, Re: Help required in find command. (read parse file tokenize m//gc), Re^2: Help with regular expression ( m/\G/gc ), perlfaq6#What good is \G in a regular expression? , Re^2: POD style regex for inline HTML elements 

#!/usr/bin/perl --
use strict;
use warnings;

use Data::Dump qw/ dd /;
sub TRACE; sub DEBUG;
*TRACE = *DEBUG = sub { print STDERR @_,"\n" };

my $data =<<'END';
# yo
x = 10;
y = 12;
z = 100;
junk
END

my $matches = dadata( \$data );
dd( $matches );
while( @$matches ){
    my $ma = shift @$matches ;
    dd( $ma );
}
exit( 0 );
sub dadata {
    my( $dataref ) = @_;
    my @matches;
    pos( $$dataref ) = 0;
    while( length( $$dataref ) > pos( $$dataref ) ){
        $$dataref =~ m{\G^(#.*$)}gcm and do {
            push @matches, [ "COMMENT", $1 ];
            TRACE "# COMMENT $1";
            next;
        };;
        $$dataref =~ m{\G^\s*(\w+)\s*=\s*(\d+)\s*;\s*$}gcmx and do {
            push @matches, [ "KV",  $1 , $2 ];
            TRACE "# K($1)=V($2)";
            next;
        };;
        $$dataref =~ m{\G(\s+)}gcxs and do {
            push @matches, [ "SPACE", $1 ];
            next;
        };;
        $$dataref =~ m{\G(\S)}gcxs and do {
            push @matches, [ "INCH", $1 ];
            TRACE "# INCH($1)";
            next;
        };;
    }
    return \@matches;
}
__END__
# COMMENT # yo
# K(x)=V(10)
# K(y)=V(12)
# K(z)=V(100)
# INCH(j)
# INCH(u)
# INCH(n)
# INCH(k)
[
  ["COMMENT", "# yo"],
  ["SPACE", "\n"],
  ["KV", "x", 10],
  ["SPACE", "\n"],
  ["KV", "y", 12],
  ["SPACE", "\n"],
  ["KV", "z", 100],
  ["SPACE", "\n"],
  ["INCH", "j"],
  ["INCH", "u"],
  ["INCH", "n"],
  ["INCH", "k"],
  ["SPACE", "\n"],
]
["COMMENT", "# yo"]
["SPACE", "\n"]
["KV", "x", 10]
["SPACE", "\n"]
["KV", "y", 12]
["SPACE", "\n"]
["KV", "z", 100]
["SPACE", "\n"]
["INCH", "j"]
["INCH", "u"]
["INCH", "n"]
["INCH", "k"]
["SPACE", "\n"]

[download]

In reply to Re: Perl regex \G /g and /gc by Anonymous Monk
in thread Perl regex \G /g and /gc by tj_thompson

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.