html.c

将HTML转换为TXT文件的程序

/* ------------------------------------------------------------------------- */

/*
 * Copyright (c) 1999
 *      GMRS Software GmbH, Innsbrucker Ring 159, 81669 Munich, Germany.
 *      http://www.gmrs.de
 *      All rights reserved.
 *      Author: Arno Unkrig ([e-mail])
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *      This product includes software developed by GMRS Software GmbH.
 * 4. The name of GMRS Software GmbH may not be used to endorse or promote
 *    products derived from this software without specific prior written
 *    permission.
 *
 * THIS SOFTWARE IS PROVIDED BY GMRS SOFTWARE GMBH ``AS IS'' AND ANY
 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL GMRS SOFTWARE GMBH BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
 * THE POSSIBILITY OF SUCH DAMAGE.
 */

/* ------------------------------------------------------------------------- */

#ident "$Id: html.C,v 1.10 1999/10/27 12:14:16 arno Exp $"

#include <stdlib.h>
#include <stdarg.h>
#include <iostream.h>

#include "html.h"
#include "HTMLParser.h"
#include "cmp_nocase.h"

/* ------------------------------------------------------------------------- */

/*
 * Define some helpers.
 */

#define define_foreach(T, args, action) \
void foreach args { \
  for (T::const_iterator i = l.begin(); i != l.end(); ++i) { \
    action; \
  } \
}

#define pack(T) \
define_foreach(list<auto_ptr<T> >, ( \
  const list<auto_ptr<T> > &l, \
  ostream                  &os, \
  ostream_manipulator      separator \
), (*i)->unparse(os, separator))

static pack(Element)
static pack(TableCell)
static pack(TableRow)
static pack(ListItem)
static pack(Option)
static pack(DefinitionListItem)
static pack(Script)
static pack(Style)

#undef pack

/*
 * Special helper for "const auto_ptr<list<TagAttribute> > &".
 */
static ostream &operator<<(ostream &os, const auto_ptr<list<TagAttribute> > &a)
{
  if (a.get()) {
    const list<TagAttribute> &al(*a);
    list<TagAttribute>::const_iterator i;
    for (i = al.begin(); i != al.end(); ++i) {
      os << " " << (*i).first << "=\"" << (*i).second << "\"";
    }
  }
  return os;
}

/* ------------------------------------------------------------------------- */

/*
 * Brothers of "endl".
 */
static ostream &none(ostream &os) { return os; }

/* ------------------------------------------------------------------------- */

/*
 * Some C++ compilers (e.g. EGCS 2.91.66) have problems if all virtual
 * methods of a class are inline or pure virtual, so we define the virtual
 * "Element::~Element()", which is the only virtual method, non-inline,
 * although it is empty.
 */
Element::~Element()
{
}

/* ------------------------------------------------------------------------- */

void
Document::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<HTML" << attributes << ">" << separator;
  head.unparse(os, separator);
  body.unparse(os, separator);
  os << "</HTML>" << separator;
}

void
Head::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<HEAD>" << separator;
  if (title.get()) {
    os << "<TITLE>" << separator;
    title->unparse(os, separator);
    os << "</TITLE>" << separator;
  }
  if (isindex_attributes.get()) {
    os << "<ISINDEX"<< isindex_attributes << ">" << endl;
  }
  if (base_attributes.get()) os << "<BASE" << base_attributes << ">" << endl;
  foreach(scripts, os, separator);
  foreach(styles, os, separator);
  if (meta_attributes.get()) os << "<META" << meta_attributes << ">" << endl;
  if (link_attributes.get()) os << "<LINK" << link_attributes << ">" << endl;
  os << "</HEAD>" << separator;
}

void
Script::unparse(ostream &os, ostream_manipulator separator) const
{
  os
    << "<SCRIPT" << attributes << ">" << separator
    << text
    << "</SCRIPT>" << separator;
}

void
Style::unparse(ostream &os, ostream_manipulator separator) const
{
  os
    << "<STYLE" << attributes << ">" << separator
    << text
    << "</STYLE>" << separator;
}

void
Body::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<BODY" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</BODY>" << separator;
}

void
PCData::unparse(ostream &os, ostream_manipulator separator) const
{
  for (string::size_type j = 0; j < text.length(); ++j) {
    char c = text[j];
    switch (((int) c) & 255) {
    case LATIN1_nbsp: os << "&nbsp;"; break;
    case '&':         os << "&amp;";  break;
    case '<':         os << "&lt;";   break;
    case '>':         os << "&gt;";   break;
    case '"':         os << "&quot;"; break;
    default:
      if (c & 0x80) {
        os << "&#" << (((int) c) & 255) << ";";
      } else {
        os << c;
      }
      break;
    }
  }

  os << separator;
}

void
Heading::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<H" << level << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</H" << level << ">" << separator;
}

void
Paragraph::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<P" << attributes << ">" << separator;
  if (texts.get()) foreach(*texts, os, separator);
  os << "</P>" << separator;
}

void
Image::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<IMG" << attributes << ">" << separator;
}

void
Applet::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<APPLET" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</APPLET>" << separator;
}

void
Param::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<PARAM" << attributes << ">" << separator;
}

void
Division::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<DIV" << attributes << ">" << separator;
  if (body_content.get()) foreach(*body_content, os, separator);
  os << "</DIV>" << separator;
}

void
Center::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<CENTER>" << separator;
  if (body_content.get()) foreach(*body_content, os, separator);
  os << "</CENTER>" << separator;
}

void
BlockQuote::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<BLOCKQUOTE>" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</BLOCKQUOTE>" << separator;
}

void
Address::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<ADDRESS>" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</ADDRESS>" << separator;
}

void
Form::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<FORM" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</FORM>" << separator;
}

void
Preformatted::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<PRE" << attributes << ">" << separator;
  if (texts.get()) { foreach(*texts, os, none); os << separator; }
  os << "</PRE>" << separator;
}

void
HorizontalRule::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<HR" << attributes << ">" << separator;
}

void
Input::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<INPUT" << attributes << ">" << separator;
}

void
Option::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<OPTION" << attributes << ">" << separator;
  if (pcdata.get()) pcdata->unparse(os, separator);
  os << "</OPTION>" << endl;
}

void
Select::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<SELECT" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</SELECT>" << endl;
}

void
TextArea::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<TEXTAREA" << attributes << ">" << separator;
  if (pcdata.get()) pcdata->unparse(os, separator);
  os << "</TEXTAREA>" << endl;
}

/* ------------------------------------------------------------------------- */