%!ps

% autoval1.psl
% Attempts to repair most validation errors in an xhtml document
% ===========================================================
% by  Don Lancaster

%  Copyright c 2009 and earlier by Don Lancaster and Synergetics, Box 809,
%  Thatcher Arizona, 5552 (928) 428-4073  don@tinaja.com  support
%  via http://www.tinaja.com  All commercial rights and all electronic
%  media rights **FULLY** reserved. Reposting is expressly forbidden.

%  IMPORTANT NOTE: Don Lancaster's file gonzo.ps is optional for this program.
%  After obvious location mods, uncomment ONE of the following two lines:

  (C:\\gonzo2\\gonzo.ps)run % use internal gonzo  % use internal gonzo
% (A:\\gonzo.ps) run  % use external gonzo

%  NOTE THAT ALL PS FILENAME STRINGS !!!DEMAND!!! DOUBLE REVERSE SLASHES.
%  Gonzo is available as http://www.tinaja.com/post01.asp#gonzo with a
%  tutorial at http://www.tinaja.com/glib/gonzotut.pdf

%%%%%%%%%%%%%

% Newer versions of XHTML are much more strict in their formatting.
% They generally require everything lower case, everything in quotes,
% all ampersands in &amp; format, blockquotes instead of <ul>, etc etc.

% This PostScript utility is a general purpose "search and replace"
% that can read most any uncompressed disk file and make selective
% changes to it. xhtml validation repair is used as an example. The
% utility repairs most but not all validation problems, greatly 
% simplifying and shortening the time required for an update.

% The following algorithm is used: An iccoming file is broken up into
% 40K strings. Each string is search and replaced and then rewritten
% to disk. A command array is forall looped for the individual replacements.
% Additional vm management is used to ease buildups.

% To use, edit as a standard ASCII text file and send to Acrobat
% Distiller. Distiller versions newer than 8.1 default to prohibiting
% file writes and must be activated by a "run acrodist -F from the
% Windows command line.

% At present, input, output, and program files must be in the same folder.

% Note that an "Empty Job - No File Produced" is normal and expected.

% An excerpt from the Gonzo Utilities....

% mergestr merges the two top stack strings into one top stack string

/mergestr {2 copy length exch length add string dup dup 4 3 roll
4 index length exch putinterval 3 1 roll exch 0 exch putinterval} def



% /srpairs is an array of format [ [(oldstr0) (newstr0)] [(oldstr1) (newstr1)]... [(oldstrn) (newstrn)] ]
% this is used to program the corrections to be made...  

% Be sure your actual textual content does not include any similar text strings!!!!

/srpairs [
           [ (<br>)(<br />) ]            % delimit breaks
           [ (<BR>)(<br />) ]

           [ (<ul>)(<blockquote>) ]         % set blockquote
           [ (</ul>)(</blockquote>) ]       % end blockquote
           [ (<UL>)(<blockquote>) ]         % set blockquote
           [ (</UL>)(</blockquote>) ]       % end blockquote


           [ (<name=)(<name=")]             % start name quotes
           [ (<href=h)(<href="h)]           % start href quotes
           [ (<a href=h)(<a href="h)]       % start href quotes
           [ (<A href=h)(<a href="h)]       % start href quotes
           [ ( href=m)( href="m)]
           [ (HREF=) (href=)]

           

           [ ("")(")]                       % eliminate double quotes

           [ (.com>)(.com">) ]              % terminate href quotes
           [ (.com/>)(.com/">) ] 
           [ (.pdf>)(.pdf">) ]          
           [ (.psl>)(.psl">) ]          
           [ (.asp>)(.asp">) ] 
           [ (.net>)(.net">) ]  
           [ (.bmp>)(.bmp">) ]           
           [ (.html>)(.html">) ] 

           [ (<P>)(<p>) ]                   % change case
           [ (</P>)(</p>) ] 
           [ (<B>)(<b>) ] 
           [ (</B>)(</b>) ] 
           [ (<A )(<a ) ] 
           [ (</A>)(</a>) ]

           [ (<IMG SRC) (<img src) ]
           [ (HEIGHT=) (height=) ]
           [ (WIDTH=) (width=)   ]

           [ (<FONT ) (<font ) ]
           [ (</FONT>) (</font>) ]
           [ ( COLOR=) ( color=) ]
           [ (NAME=) (name=) ]

           [ (size=1>)(size="1">) ]   % watch for longer JavaScript sizes!
           [ (size=2>)(size="2">) ]
           [ (size=3>)(size="3">) ]

           [ (size=+1>)(size="+1">) ]   
           [ (size=+2>)(size="+2">) ]
           [ (size=+3>)(size="+3">) ]

           [ (size=-1>)(size="-1">) ]
           [ (size=-2>)(size="-2">) ]
           [ (size=-3>)(size="-3">) ]



           [ (size=1 )(size="1" ) ]   % watch for longer JavaScript sizes!
           [ (size=2 )(size="2" ) ]
           [ (size=3 )(size="3" ) ]

           [ (size=+1 )(size="+1" ) ]   
           [ (size=+2 )(size="+2" ) ]
           [ (size=+3 )(size="+3" ) ]

           [ (size=-1 )(size="-1" ) ]
           [ (size=-2 )(size="-2" ) ]
           [ (size=-3 )(size="-3" ) ]

           [ (nowrap ) (nowrap="nowrap" ) ]


           [ (<TABLE ) (<table ) ]
           [ (</TABLE ) (</table ) ]
           [ (<TR>) (<tr>) ]
           [ (<TR ) (<tr ) ]
           [ (</TR>) (</tr>) ]   
           [ (<TD>) (<td>) ]
           [ (<TD ) (<td ) ]
           [ (</TD>) (</td>) ]
           [ (COLSPAN=) (colspan=)]

           [ (<TD BGCOLOR=) (<td bgcolor=) ]
           [ (<TD BGCOLOR =) (<td bgcolor=) ]

           [ (SIZE=)(size=)]
           [ (size=+2) (size="+2") ]
           [ (size=+1) (size="+1") ]
           [ (size=-1) (size="-1") ]
           [ (size=-2) (size="-2") ]


           [ (align=CENTER) (align="center") ]
           [ ( ALIGN=CENTER ) ( align="center" ) ]
           [ ( VALIGN=CENTER ) ( valign="middle" ) ]
           [ (valign="center") (valign="middle") ]
           [ (valign=middle) (valign="middle") ]

           [ (BORDER=) (border=) ]
           [ (CELLSPACING=) (cellspacing=) ]
           [ (CELLPADDING=) (cellpadding=) ]
        
           [ (border=1) (border="1") ]
           [ (border=2) (border="2") ]
           [ (border=3) (border="3") ]

           [ (cellpadding=1) (cellpadding="1") ]
           [ (cellspacing=2) (cellpadding="2") ]
           [ (cellspacing=3) (cellpadding="3") ]

           [ (cellspacing=1) (cellspacing="1") ]
           [ (cellspacing=2) (cellspacing="2") ]
           [ (cellspacing=3) (cellspacing="3") ]

           [ ( BGCOLOR=) ( bgcolor=) ]
           [ ( BGCOLOR =) ( bgcolor=) ]

           [ (<INPUT ) (<input ) ]

           [ ( ID=) ( id=) ]

% These are highly site specific -- modify as needed...

           [ (color=#FF9966) (color="#FF9966") ]   
           [ (color=#00CC99) (color="#00CC99") ]

           [ (width=100) (width="100") ]         % watch for longer exclusions!!!!
           [ (height=62) (height="62") ] 

           [ (value=0.000 ) (value="0.000" ) ]
           [ (value=999.9 ) (value="999.9" ) ]

           [ (size=12) (size="12") ]
           [ (size=14) (size="14") ]

         ] def





% /searchandreplace makes the corrections to the substring


/searchandreplace {  


/blowcount 0 store


                /curstring exch store


 

            srpairs { dup 1 get /wilby exch store     % new text to be replaced
                          0 get /wuz exch store       % old text to be replaced

                   

                    {   curstring wuz search not {exit} if


                        exch pop wilby mergestr
                        exch mergestr



 /blowcount blowcount 1 add store

       
          blowcount 30000 eq {
                                                    writefile2 exch writestring  asdfasdf  } if   % hang trapper



                          /curstring exch store

(.) print flush


                    } loop 





                   } forall

                  curstring                     % return with latest string 

                  } store



% /searchandreplace {} store % temp





% /autovalidate is the high level code. It separates the input into 40K files, 
% modifies through subprocs, and writes to a new file.


/autovalidate {

        /readfilename fileheader infilename mergestr store
        /readfile readfilename (r) file store


        /writefilename fileheader outfilename mergestr store
        /writefile writefilename (w+) file store


        /writefilename2 fileheader diagfilename mergestr store
        /writefile2 writefilename2 (w+) file store


        /curstring 40000 string store


        {readfile curstring readstring     % for all earlier strings
            not{exit}if
            searchandreplace
            writefile exch writestring
             } loop 

            searchandreplace                % for final short string
            writefile exch writestring


            readfile closefile
            writefile closefile

             } bind def












%%%%%%%%%%%%%%%%%% demo - remove or alter before reuse

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 
%
  /fileheader (C:\\Documents and Settings\\don\\Desktop\\validate\\autoval\\mc hybrid\\)def      
  /infilename (mctemp01.asp) def 
  /outfilename (mctemp01a.asp) def

  /diagfilename (dmctemp01.txt) def
%    
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%


stopwatchon
autovalidate    % this does it
stopwatchoff

% EOF