#!/usr/bin/perl
# subsread2.plx
package HTMLMods;
=head1 DESCRIPTION
 Alternative to subread.plx - no control flows, just a 'master' sub which calls
 each sub to perform the HTML tag/attribute stripping/alteration, then
 returning the results.
 This application groups ALL the regexps into a single unit:
 1. The HTML file is opened and inserted into an array (try this with a scalar too!)
 2. A master subroutine is called, which calls other subs to perform HTML reformatting tasks
 3. Each HTML reformatting sub completes its respective operations on the HTML file
 4. Reformatted array is printed in DOS window.
 5. OR write changes back to HTML source file.

 =head2 ALTERNATIVE FILE OPENING CODE
  my $path = "E:/Documents and Settings/Richard Lamb/My Documents/HTML";
  open (INFILE, "$path/test1InLineCSS.html") or die ("$!: Can't open this file");

 =head3 BACKREFS TO REMEDY ENTITY VALUE CHANGE PROBLEM?

=cut

use warnings;
use diagnostics;
use strict;

# Declare and initialise variables.
my @htmlFile;

# Open HTML test file and read into array.
open (INFILE, "E:/Documents and Settings/Richard Lamb/My Documents/HTML/test1InLineCSS.html"), or die ("$!: Can't open this file.\n");
@htmlFile = <INFILE>;
close (INFILE);

sub masterCall
{
  scrapUnderlineTags();
  scrapBoldTags();
  scrapItalicsTags();
  scrapEmphasiseTags();
  changeFontStyle();
  changeFontSize();
  changeFontColour();
  changeBackColour();
  addTextIndent();
  addWordSpacing();
  addLetterSpacing();
  scrapImageTag();
}

masterCall();

# Subroutine defintions
# Removes underline tags in array
sub scrapUnderlineTags
{ # iterates through each element (i.e. HTML line) in array
  foreach my $line (@htmlFile)
  {
    $line =~ s/<\/u>//ig; # case insensitivity and global search for pattern.
    $line =~ s/<u>//ig;
  }
}

# Removes bold tags in array
sub scrapBoldTags
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/<\/?b>//ig;
    $line =~ s/<\/?big>//ig;
    $line =~ s/<\/?strong>//ig;
    $line =~ s/font-weight:\s?bold;?//ig;
  }
}

# Removes italics tags in array
sub scrapItalicsTags
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/<\/?i>//ig;
  }
}

# Remove emphasise tags in array
sub scrapEmphasiseTags
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/<\/?em>//ig;
  }
}

# Change font styles within in-line styles
sub changeFontStyle
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/font-family:\s?Times;/font-family: Arial;/ig;
  }
}

# Change font size within in-line styles
sub changeFontSize
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/font-size:\s?[0-9]{2}pt;?/font-size: 14pt/ig;
  }
}

# Change font colour within in-line styles
sub changeFontColour
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/[^background-]color:\s?#(?:[0-9a-f]{6}|[0-9a-f]{3});?/"color: #000000;/ig;
  }
}

# Changes background colour attributes in array
sub changeBackColour
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/background-color:\s?#(?:[0-9a-f]{6}|[0-9a-f]{3});?/background-color: #FFFFFF/ig;
  }
}

sub addTextIndent
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/(<h[0-6]\sstyle=.*)">/$1; text-indent: 10px">/ig;
    $line =~ s/(<li\sstyle=.*)">/$1; text-indent: 10px">/ig;
    $line =~ s/(<p\s style=.*)">/$1; text-indent: 10px">/ig;
  }
}

# Inserts word spacing entities within in-line styles
sub addWordSpacing
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/(<h[1-6]\sstyle=.*)">/$1; word-spacing: 30px">/ig;
    $line =~ s/(<p\sstyle=.*)">[^<.*?>]/$1; word-spacing: 10px">/ig;
    $line =~ s/(<li\sstyle=.*)">/$1; word-spacing: 10px">/ig;
  }
}

# Inserts letter spacing entities within in-line styles
sub addLetterSpacing
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/(<h[1-6]\s+style=.*)">/$1; letter-spacing: 3px">/ig;
    $line =~ s/(<li\sstyle=.*)">/$1; letter-spacing: 2px">/ig;
    $line =~ s/(<p\sstyle=.*)">/$1; letter-spacing: 2px">/ig;
  }
}

# Removes image tag in array
sub scrapImageTag
{
  foreach my $line (@htmlFile)
  {
    $line =~ s/<IMG\s+(.*)>//ig;
  }
}

# Print array to DOS window
sub printHTML
{
  for my $i (0..@htmlFile-1)
  {
    print $htmlFile[$i];
  }
}

# Replacing original file with reformatted file!
open (OUTFILE, ">E:/Documents and Settings/Richard Lamb/My Documents/HTML/test1InLineCSS.html") or die("$1: Can't rewrite the HTML file.\n");
print (OUTFILE @htmlFile);
close (OUTFILE);

# printHTML();              # sub called to print array in DOS window

##</code><code>##

<!DOCTYPE html
PUBLIC "-//W3C//DTD html 4.01 Transitional//EN"
"http://www.w3.org/TR/html4/loose.dtd">

<html lang="en">

 <head>
   <title>My First Page</title>
   <meta http-equiv="content-type" content="text/html; charset=iso-8859-1"/>
 </head>

    <body style="background-color: #8DCB41">
      <h1 style="color: #648DC7; text-align: center; font-family: Times; font-weight: bold">
        <i>Hello folks...This is my <big>first</big> page!</i>
      </h1>

      <h4 style="color: #648DC7; font-family: Times">
        <form>
          <u>Username:</u> <input type="text" name="user">
          <br>
          <u>Password:</u> <input type="password" name="password">
        </form>
      </h4>

      <p style="font-family: Times; font-size: 10pt">Note that when you type characters in a password field, the browser displays asterisks or bullets instead of the characters.</p>

      <img src="images/dicky.jpg" height="350" width="350" title="Dickybloke!" style="text-align: center">
      <hr>

      <h4 style="color: #648DC7; font-family: Times">My kinda places...</h4>

      <ul type="square">
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://www.bbc.co.uk/manchester/"><i>Manchester</i></a></li>
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://www.bbc.co.uk/leeds/"><i>Leeds</i></a></li>
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://www.bbc.co.uk/london/"><i>London</i></a></li>
      </ul><hr>

      <h2 style="color: #2D73B9; text-align: center; font-family: Times">Ferocious Felines!</h2>
      <img src="images/pissedkitty.jpg" height="300" width="300" alt="A picture of a &quot;very&quot; upset kitten!">
      <img src="images/pissedkitty.jpg" height="300" width="300" alt="A picture of a &quot;very&quot; upset kitten!">
      <img src="images/pissedkitty.jpg" height="300" width="300" alt="A picture of a &quot;very&quot; upset kitten!">
      <hr>

      <h4 style="color: #497FBF; font-family: Times">Places to visit and go back to...</h4>

      <ul type="square">
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://english.firenze.net/"><em>Florence</em></a></li>
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://www.timeout.com/prague/"><em>Prague</em></a></li>
	    <li style="font-family: Times; font-size: 10pt">
	      <a href="http://www.canada.com/vancouver/"><em>Vancouver</em></a></li>
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://metromix.chicagotribune.com/"><em>Chicago</em></a></li>
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://www.sanfrancisco.com/"><em>San Fransisco</em></a></li>
        <li style="font-family: Times; font-size: 10pt">
          <a href="http://www.ny.com/"><em>New York</em></a></li>
      </ul>


      <hr>
      <h2 style="color: #497FBF; text-align: center; font-family: Times"><u><b>A Brief History to the Future summary:</b></u></h2>
          <p style="color: #648DC7; font-family: Times; font-size: 10pt">The <b><u>Internet</u></b> is the most <strong>remarkable</strong> achievement of humankind since the pyramids.  The millennium from now, historians will
             look back at it and marvelled at the people equipped with such conduct tools succeeded in creating such a leviathan.
             Yet even as the Net pervades our lives, we begin to take it for granted.  Many have lost the capacity for wonder.
             Most of us have no idea where the Interet came from, how it works, or who created it and why.  And even fewer have any
             idea what it means for society and future.</p>

          <p style="color: #648DC7; font-family: Times; font-size: 10pt"><i>John Naughton</i> has written a warm and passionate book whose heroes and the visionaries laid the foundations of postmodern world.
             A Brief History of the Future celebrates the engineers and scientists who implemented their dreams in hardware and software
             and explains the values and ideas that drove them.  Although its subject seems technical, the book in fact is a highly personal
             account.  The author writes about the Net and way Nick Hornby writes about soccer-as part of life, and as a key influence on his
             own voyage from solitary child to establish academic and writer.</p>

          <p style="color: #497FBF; font-family: Times; font-size: 10pt"><i><u>A Brief History of the Future</u></i> is an intimate celebration of vision and al truism, ingenuity and determination, and above all
             of the power of ideas transform the world.</p>

          <p style="color: #497FBF; font-family: Times;  font-size: 10pt">John Naughton is an academic and a journalit.  He teaches at the Open University and has written an award-winning weekly column
             for the Observer for more than ten years.  He lives in Cambridge, England, and is a fellow of Wolfson College at the University of Cambridge.</p>
          <br>

      <h4 style="color: #497FBF; font-family: Times">Link</h4>

        <ul type="square">
          <li style="font-size: 10pt; font-family: Times">
            <a href="http://www.briefhistory.com/pages/bh-index.htm">A Brief History of the Future</a></li>
        </ul>
      <hr>

      <h2 style="color: #497FBF; font-family: Times; text-align: center">Rockerfellers - NOT!</h2>


      <img src="images/oldgrooves.jpg" height="450" width="450" alt="Old-time groovers!" style="text-align: center; border: 3px">


      <p style="font-family: Times; font-size: 10pt">
        <a href="http://www.bbc.co.uk/">This text<a/> will take you to the BBC!!
      </p>

      <p style="font-family: Times; font-size: 10pt">
        <a href="http://www.programmersheaven.com/">This text</a> is a link to a developer's page.This text is a link to a developer's page.
      </p>

      <p style="font-family: Times; font-size: 10pt">
        You can also use an image as a link:
        <a href="http://www.google.com/">
        <img src="images/thankyou.gif" height="75" width="75" alt="Google search">
        </a>
      </p>

      <p style="font-family: Times; font-size: 10pt">
        <a href="mailto:dikymintos@hotmail.com subject="Hello%20to%20me!">Send mail to Mintosville</a>
      </p>

      <h4 style="color: #497FBF; font-family: Times">Table headers:</h4>
        <table style="margin-left:50px; border: 4px; border-color: #000000">
          <tr>
            <th>Name</th>
            <th>Telephone</th>
            <th>Address</th>
          </tr>
          <tr>
            <td>Dicky Mintos</td>
            <td>0161 2363736</td>
            <td>Flat 23, Lockes Yard, Manchester</td>
          </tr>
        </table>
       <br><br>

       <form action="mailto:dickymintos@hotmail.com" method="post" enctype="text/plain">
       <h3 style="color: #6F559D; font-family: Times">This form sends an e-mail to Trixter...</h3>
         Name:<br>
         <input type="text" name="name" value="yourname" size="20">
         <br>
         Mail:<br>
         <input type="text" name="mail" value="yourmail" size="20">
         <br>
         Comment:<br>
         <input type="text" name="comment" value="yourcomment" size="40">
         <br><br>
         <input type="submit" value="Send">
         <input type="reset" vale="Reset">
       </form>


    </body>
    </html>