/*****************************************************************************/
/*
                                  HTML.c

Processing associated with reading and composing HTML-format messages.


COPYRIGHT
---------
Copyright (C) 2005-2025 Mark G.Daniel
This program, comes with ABSOLUTELY NO WARRANTY.
This is free software, and you are welcome to redistribute it under the
conditions of the GNU GENERAL PUBLIC LICENSE, version 3, or any later version.


VERSION HISTORY
---------------
01-JUN-2025  MGD  HTML manipulation now performed using JavaScript
25-FEB-2010  MGD  HtmlToPlain() supply charset for UTF-8 deentify
                  HtmlCharacterDeEntify() allow for UTF-8 charset
04-JUL-2006  MGD  bugfix; HtmlSkipTagTo() quotes outside of tags
20-JUN-2006  MGD  HtmlInDisguise() is it really not plain but HTML text?
14-MAR-2006  MGD  refine HtmlNumericDeEntify() and HtmlCharacterDeEntify()
13-MAR-2006  MGD  HtmlSanitise() suppress "background-image"
01-FEB-2005  MGD  initial
*/

/*****************************************************************************/

#ifdef SOYMAIL_VMS_V7
#undef _VMS_V6_SOURCE
#define _VMS_V6_SOURCE
#undef __VMS_VER
#define __VMS_VER 70000000
#undef __CRTL_VER
#define __CRTL_VER 70000000
#endif

#pragma nomember_alignment

/* standard C header files */
#include <ctype.h>
#include <errno.h>
#include <stat.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <types.h>

/* VMS related header files */
#include <descrip.h>
#include <ssdef.h>
#include <stsdef.h>

/* application header file */
#include "soymail.h"
#include "cgilib.h"
#include "config.h"
#include "html.h"
#include "message.h"

#define FI_LI "HTML", __LINE__

/******************/
/* global storage */
/******************/

/********************/
/* external storage */
/********************/

extern BOOL  Debug,
             WatchEnabled;

extern char SoyMailQueryVersion[]; 

extern CONFIG_DATA  SoyMailConfig;

/*****************************************************************************/
/*
The content is already plain.  Just copy it in.
*/

void HtmlIsPlain (char *PlainPtr)

{
   /*********/
   /* begin */
   /*********/

   if (WatchEnabled) WatchThis (FI_LI, "HtmlIsPlain()");

   HtmlByJavaScript (PlainPtr, 1);
}

/*****************************************************************************/
/*
Reduce HTML markup down to a semblance of plain-text.  Relies on the underlying
HTML to provide white-space, indenting, etc.  Essentially just strips the
markup out and adds carriage-control as necessary.  Will format ordered and
unordered lists.
*/

void HtmlToPlain (char *HtmlPtr)

{
   /*********/
   /* begin */
   /*********/

   if (WatchEnabled) WatchThis (FI_LI, "HtmlToPlain()");

   HtmlByJavaScript (HtmlPtr, 2);
}

/*****************************************************************************/
/*
*/

void HtmlSanitise (char *HtmlPtr)

{
   /*********/
   /* begin */
   /*********/

   if (WatchEnabled) WatchThis (FI_LI, "HtmlSanitise()");

   HtmlByJavaScript (HtmlPtr, 3);
}

/*****************************************************************************/
/*
MIXES of fprintf() and fwrite() (the more efficient) seem fraught with
unexpected newlines!!  So fprintf("%*.*s")!
*/

void HtmlByJavaScript
(
char *HtmlPtr,
int mode
)
{
   int  size;
   char  *bptr, *cptr, *sptr, *zptr;

   /*********/
   /* begin */
   /*********/

   if (WatchEnabled) WatchThis (FI_LI, "HtmlByJavaScript() !UL", mode);

   /***
      'protxt' is the compose prologue
      'msgtxt' is the compose/message message text
      'epitxt' is the compose epilogue
   ***/

   if (mode == 1)
   {
      /* plain => plain */
      fprintf (stdout,
"<script>\n\
var txtarea, viatext;\n\
txtarea = document.getElementById(\'compose_text\');\n\
if (!txtarea) viatxt = document.getElementById(\'message_text\');\n\
var msgtxt = (\'");
   }
   else
   if (mode == 2)
   {
      /* HTML => plain */
      fprintf (stdout,
"<script src=\"%stextversion.js%s\"></script>\n\
<script>\n\
var styleConfig = \'\';\n\
var txtarea, viatext;\n\
txtarea = document.getElementById(\'compose_text\');\n\
if (!txtarea) viatxt = document.getElementById(\'message_text\');\n\
var msgtxt = (\'",
            SOY_PATH, SoyMailQueryVersion);
   }
   else
   if (mode == 3)
   {
      /* HTML => HTML */
      fprintf (stdout,
"<script src=\"%sHtmlSanitizer.js%s\"></script>\n\
<div id=\"message_text\"></div>\n\
<script>\n\
var txtarea, viatext;\n\
txtarea = document.getElementById(\'compose_text\');\n\
if (!txtarea) viatxt = document.getElementById(\'message_text\');\n\
var msgtxt = (\'",
            SOY_PATH, SoyMailQueryVersion);
   }

   cptr = HtmlPtr;
   while (*cptr)
   {
      for (sptr = cptr; *sptr &&
           *sptr != '\'' &&
           *sptr != '\"' &&
           *sptr != '\b' &&
           *sptr != '\f' &&
           *sptr != '\n' &&
           *sptr != '\r' &&
           *sptr != '\t' &&
           *sptr != '\v'; sptr++);
      if (!*sptr) break;
      fprintf (stdout, "%*.*s\\x%02x",
               sptr-cptr, sptr-cptr, cptr, (uchar)*sptr);
      cptr = sptr + 1;
   }
   fprintf (stdout, "%*.*s\');\n", sptr-cptr, sptr-cptr, cptr);

   if (mode == 1)
      fprintf (stdout,
"if (txtarea)\n\
   txtarea.value = protxt + plainToText(msgtxt) + epitxt;\n\
else\n\
   viatxt.innerHTML = protxt + plainToText(msgtxt) + epitxt;\n");
   else
   if (mode == 2)
      fprintf (stdout,
"if (txtarea)\n\
   txtarea.value = protxt + htmlToPlainText(msgtxt) + epitxt;\n\
else\n\
   viatxt.innerHTML = protxt + htmlToPlainText(msgtxt) + epitxt;\n");
   else
   if (mode == 3)
      fprintf (stdout,
"if (txtarea)\n\
   txtarea.value = protxt + HtmlSanitizer.SanitizeHtml(msgtxt) + epitxt;\n\
else\n\
   viatxt.innerHTML = protxt + HtmlSanitizer.SanitizeHtml(msgtxt) + epitxt;\n");

   fwrite ("</script>\n", 10, 1, stdout);
}

/*****************************************************************************/
/*
Elementary UTF-8 encoding for characters > 127.
*/

char* HtmlUtf8Encode (char *TextPtr)

{
   int  ch, cnt;
   uchar  *cptr, *sptr, *tptr;

   /*********/
   /* begin */
   /*********/

   if (Debug) fprintf (stdout, "HtmlUtf8Encode() |%s|\n", TextPtr);

   for (cptr = (uchar*)TextPtr; *cptr && *cptr <= 127; cptr++);
   if (!*cptr) return (TextPtr);

   cnt = cptr - (uchar*)TextPtr;
   /* worst case for UTF-8 is plus 3 chars */
   for (cptr = (uchar*)TextPtr; *cptr && *cptr > 127; cptr++) cnt += 3;
   tptr =  CgiLibVeeMemCalloc (cnt+4);
   if (!tptr) ErrorExit (vaxc$errno, FI_LI);

   sptr = tptr;
   cptr = (uchar*)TextPtr;
   for (cptr = (uchar*)TextPtr; *cptr; cptr++)
   {
      if (*cptr <= 127)
         *sptr++ = *cptr;
      else
         sptr += HtmlUtf8EncodeChar (sptr, (uint)*cptr);
   }
   *sptr = '\0';

   if (Debug) fprintf (stdout, "|%s|\n", tptr);
   return ((char*)tptr);
}

/*****************************************************************************/
/*
UTF-8 encode a single character.  Return the number of chars generated.
*/

int HtmlUtf8EncodeChar (uchar *out, uint utf)

{
   /*********/
   /* begin */
   /*********/

   if (utf <= 0x7F)
   {
      /* plain ASCII */
      out[0] = (char) utf;
      out[1] = 0;
      return (1);
   }
   else
   if (utf <= 0x07FF)
   {
      /* 2-byte unicode */
      out[0] = (char) (((utf >> 6) & 0x1F) | 0xC0);
      out[1] = (char) (((utf >> 0) & 0x3F) | 0x80);
      out[2] = 0;
      return (2);
   }
   else
   if (utf <= 0xFFFF)
   {
      /* 3-byte unicode */
      out[0] = (char) (((utf >> 12) & 0x0F) | 0xE0);
      out[1] = (char) (((utf >>  6) & 0x3F) | 0x80);
      out[2] = (char) (((utf >>  0) & 0x3F) | 0x80);
      out[3] = 0;
      return (3);
   }
   else
   if (utf <= 0x10FFFF)
   {
     /* 4-byte unicode */
     out[0] = (char) (((utf >> 18) & 0x07) | 0xF0);
     out[1] = (char) (((utf >> 12) & 0x3F) | 0x80);
     out[2] = (char) (((utf >>  6) & 0x3F) | 0x80);
     out[3] = (char) (((utf >>  0) & 0x3F) | 0x80);
     out[4] = 0;
     return (4);
   }
   else
   { 
      /* error - use replacement character */
      out[0] = (char) 0xEF;  
      out[1] = (char) 0xBF;
      out[2] = (char) 0xBD;
      out[3] = 0;
      return (0);
   }
}

/*****************************************************************************/
/*
Check the leading text for what looks like a common HTML tag.
*/

BOOL HtmlInDisguise (char *TextPtr)

{
   char  *cptr;

   /*********/
   /* begin */
   /*********/

   if (Debug) fprintf (stdout, "HtmlInDisguise()\n");

   if (!TextPtr) return (FALSE);
   for (cptr = TextPtr; *cptr && isspace(*cptr); cptr++);
   if (WatchEnabled) WatchThis (FI_LI, "!8AZ", cptr);
   if (*cptr != '<') return (FALSE);
   if (!memcmp (cptr, "<!--", 4)) return (TRUE);
   if (strsame (cptr, "<!DOCTYPE", 9)) return (TRUE);
   if (strsame (cptr, "<html", 5)) return (TRUE);
   if (strsame (cptr, "<head", 5)) return (TRUE);
   if (strsame (cptr, "<body", 5)) return (TRUE);
   if (strsame (cptr, "<table", 6)) return (TRUE);
   if (strsame (cptr, "<font", 5)) return (TRUE);
   return (FALSE);
}

/*****************************************************************************/