htmlparser.c

一个小的RTOS具有UIP网络功能

/*
 * Copyright (c) 2002, Adam Dunkels.
 * All rights reserved. 
 *
 * 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 Adam Dunkels. 
 * 4. The name of the author may not be used to endorse or promote
 *    products derived from this software without specific prior
 *    written permission.  
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 THE AUTHOR 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.  
 *
 * This file is part of the Contiki desktop environment 
 *
 * $Id: htmlparser.c,v 1.4 2003/09/04 19:33:05 adamdunkels Exp $
 *
 */

/* htmlparser.c:
 *
 * Implements a very simplistic HTML parser. It recognizes HTML links
 * (<a href>-tags), HTML img alt tags, a few text flow break tags
G * (<br>, <p>, <h>), the <li> tag (but does not even try to
 * distinguish between <ol> or <ul>) as well as HTML comment tags
 * (<!-- -->).
 *
 * To save memory, the HTML parser is state machine driver, which
 * means that it will shave off one character from the HTML page,
 * process that character, and return to the next. Another way of
 * doing it would be to buffer a number of characters and process them
 * together.
 *
 * The main function in this file is the htmlparser_parse() function
 * which takes a htmlparser_state structur and a part of an HTML file
 * as an argument. The htmlparser_parse() function will call the
 * helper functions parse_char() and parse_tag(). Those functions will
 * in turn call the two callback functions htmlparser_char() and
 * htmlparser_tag(). Those functions must be implemented by the using
 * module (e.g., a web browser program).
 *
 * htmlparser_char() will be called for every non-tag character.
 *
 * htmlparser_tag() will be called whenever a full tag has been found.
 *
 */


#include "htmlparser.h"
#include "html-strings.h"
#include "www-conf.h"
#include "cc.h"

#if 1
#define PRINTF(x)
#else
#include <stdio.h>
#define PRINTF(x) printf x
#endif


/*-----------------------------------------------------------------------------------*/
#define ISO_A     0x41
#define ISO_B     0x42
#define ISO_E     0x45
#define ISO_F     0x46
#define ISO_G     0x47
#define ISO_H     0x48
#define ISO_I     0x49
#define ISO_L     0x4c
#define ISO_M     0x4d
#define ISO_P     0x50
#define ISO_R     0x52
#define ISO_T     0x54

#define ISO_a     (ISO_A | 0x20)
#define ISO_b     (ISO_B | 0x20)
#define ISO_e     (ISO_E | 0x20)
#define ISO_f     (ISO_F | 0x20)
#define ISO_g     (ISO_G | 0x20)
#define ISO_h     (ISO_H | 0x20)
#define ISO_i     (ISO_I | 0x20)
#define ISO_l     (ISO_L | 0x20)
#define ISO_m     (ISO_M | 0x20)
#define ISO_p     (ISO_P | 0x20)
#define ISO_r     (ISO_R | 0x20)
#define ISO_t     (ISO_T | 0x20)

#define ISO_ht    0x09
#define ISO_nl    0x0a
#define ISO_cr    0x0d
#define ISO_space 0x20
#define ISO_bang  0x21
#define ISO_citation 0x22
#define ISO_ampersand 0x26
#define ISO_citation2 0x27
#define ISO_asterisk 0x2a
#define ISO_dash  0x2d
#define ISO_slash 0x2f
#define ISO_semicolon  0x3b
#define ISO_lt    0x3c
#define ISO_eq    0x3d
#define ISO_gt    0x3e

#define ISO_rbrack 0x5b
#define ISO_lbrack 0x5d

#define MINORSTATE_NONE           0
#define MINORSTATE_TEXT           1 /* Parse normal text */
#define MINORSTATE_EXTCHAR        2 /* Check for semi-colon */
#define MINORSTATE_TAG            3 /* Check for name of tag. */
#define MINORSTATE_TAGEND         4 /* Scan for end of tag. */
#define MINORSTATE_TAGATTR        5 /* Parse tag attr. */
#define MINORSTATE_TAGATTRSPACE   6 /* Parse optional space after tag
				       attr. */
#define MINORSTATE_TAGATTRPARAM   7 /* Parse tag attr parameter. */
#define MINORSTATE_TAGATTRPARAMNQ 8 /* Parse tag attr parameter without
				  quotation marks. */
#define MINORSTATE_HTMLCOMMENT    9 /* Scan for HTML comment end */

#define MAJORSTATE_NONE       0
#define MAJORSTATE_BODY       1
#define MAJORSTATE_LINK       2
#define MAJORSTATE_FORM       3
#define MAJORSTATE_DISCARD    4


struct htmlparser_state {
  unsigned char minorstate;
  char tag[20];
  unsigned char tagptr;
  char tagattr[20];
  unsigned char tagattrptr;
  char tagattrparam[WWW_CONF_MAX_URLLEN];
  unsigned char tagattrparamptr;
  unsigned char lastchar, quotechar;
  unsigned char majorstate, lastmajorstate;
  char linkurl[WWW_CONF_MAX_URLLEN];
  char linktext[40];
  unsigned char linktextptr;
#if WWW_CONF_FORMS
  char formaction[WWW_CONF_MAX_FORMACTIONLEN];
  char formname[WWW_CONF_MAX_FORMNAMELEN];
  unsigned char inputtype;
  char inputname[WWW_CONF_MAX_INPUTNAMELEN];
  char inputvalue[WWW_CONF_MAX_INPUTVALUELEN];
  unsigned char inputvaluesize;
#endif /* WWW_CONF_FORMS */
};

static struct htmlparser_state s;

/*-----------------------------------------------------------------------------------*/
static char last[1] = {0xff};

static const char *tags[] = {
#define TAG_FIRST       0
#define TAG_SLASHA      0
  html_slasha,
#define TAG_SLASHCENTER 1
  html_slashcenter,
#define TAG_SLASHFORM   2
  html_slashform,
#define TAG_SLASHH      3
  html_slashh,
#define TAG_SLASHSCRIPT 4
  html_slashscript,
#define TAG_SLASHSELECT 5
  html_slashselect,
#define TAG_SLASHSTYLE  6
  html_slashstyle,
#define TAG_A           7
  html_a,
#define TAG_BODY        8
  html_body,
#define TAG_BR          9
  html_br,
#define TAG_CENTER     10 
  html_center,
#define TAG_FORM       11
  html_form,
#define TAG_FRAME      12    
  html_frame,
#define TAG_H1         13  
  html_h1,
#define TAG_H2         14
  html_h2,
#define TAG_H3         15  
  html_h3,
#define TAG_H4         16  
  html_h4,
#define TAG_IMG        17  
  html_img,
#define TAG_INPUT      18  
  html_input,
#define TAG_LI         19
  html_li,
#define TAG_P          20
  html_p,
#define TAG_SCRIPT     21
  html_script, 
#define TAG_SELECT     22
  html_select,
#define TAG_STYLE      23
  html_style,
#define TAG_TR         24   
  html_tr,
#define TAG_LAST       25
  last,
};

/*-----------------------------------------------------------------------------------*/
static unsigned char CC_FASTCALL
iswhitespace(char c)
{
  return (c == ISO_space ||
	  c == ISO_nl ||
	  c == ISO_cr ||
	  c == ISO_ht);
}
/*-----------------------------------------------------------------------------------*/
static unsigned char CC_FASTCALL
find_tag(char *tag)
{
  static unsigned char first, last, i, tabi;
  static char tagc;
  
  tabi = first = TAG_FIRST;
  last = TAG_LAST;
  i = 0;
  
  do {
    tagc = tag[i];

    if(tagc == 0 &&
       tags[first][i] == 0) {
      return first;
    }
    
    /* First, find first matching tag from table. */
    while(tagc > (tags[tabi])[i] &&
	  tabi < last) {
      ++tabi;
    }
    first = tabi;
    
    /* Second, find last matching tag from table. */
    while(tagc == (tags[tabi])[i] &&
	  tabi < last) {
      ++tabi;
    }
    last = tabi;
    
    /* If first and last matching tags are equal, we have a match and
       return. Else we continue with the next character. */
    ++i;
    tabi = first;
  } while(last != first);
  return TAG_LAST;
}
/*-----------------------------------------------------------------------------------*/
static void CC_FASTCALL
parse_char(unsigned char c)
{
  if(c < 0x80) {
    if(s.majorstate == MAJORSTATE_LINK) {
      if(s.linktextptr < sizeof(s.linktext)) {
	if(iswhitespace(c)) {
	  c = ISO_space;
	}
	s.linktext[s.linktextptr] = c;
	++s.linktextptr;
      }
    } else if(s.majorstate != MAJORSTATE_DISCARD) {
      htmlparser_char(c);
    } 
  }
}
/*-----------------------------------------------------------------------------------*/
static void CC_FASTCALL
switch_majorstate(unsigned char newstate)
{
  if(s.majorstate != newstate) {
    PRINTF(("Switching state from %d to %d (%d)\n", s.majorstate, newstate, s.lastmajorstate));
    s.lastmajorstate = s.majorstate;
    s.majorstate = newstate;
  }
}
/*-----------------------------------------------------------------------------------*/
static void
parse_tag(void)
{
  static char *tagattrparam;
  static unsigned char size, i;
  
  PRINTF(("Parsing tag '%s' '%s' '%s'\n",
	  s.tag, s.tagattr, s.tagattrparam));

  switch(find_tag(s.tag)) {
  case TAG_P:
  case TAG_H1:
  case TAG_H2:
  case TAG_H3:
  case TAG_H4:
    parse_char(ISO_nl);
    /* FALLTHROUGH */
  case TAG_BR:
  case TAG_TR:
  case TAG_SLASHH:
    parse_char(ISO_nl);
    break;
  case TAG_LI:
    parse_char(ISO_nl);
    parse_char(ISO_asterisk);
    parse_char(ISO_space);
    break;
  case TAG_SCRIPT:
  case TAG_STYLE:
  case TAG_SELECT:
    switch_majorstate(MAJORSTATE_DISCARD);
    break;
  case TAG_SLASHSCRIPT:
  case TAG_SLASHSTYLE:
  case TAG_SLASHSELECT:
    switch_majorstate(s.lastmajorstate);
    break;
  case TAG_BODY:
    s.majorstate = s.lastmajorstate = MAJORSTATE_BODY;
    break;
  case TAG_FRAME:
    if(strncmp(s.tagattr, html_src, sizeof(html_src)) == 0 &&
       s.tagattrparam[0] != 0) {
      switch_majorstate(MAJORSTATE_BODY);
      parse_char(ISO_nl);
      parse_char(ISO_rbrack);
      parse_char(ISO_space);
      htmlparser_link((char *)html_frame, s.tagattrparam);
      PRINTF(("Frame [%s]\n", s.tagattrparam));
      parse_char(ISO_space);
      parse_char(ISO_lbrack);
      parse_char(ISO_nl);
    }
    break;
  case TAG_IMG:
    if(strncmp(s.tagattr, html_alt, sizeof(html_alt)) == 0 &&
       s.tagattrparam[0] != 0) {
      parse_char(ISO_lt);
      tagattrparam = &s.tagattrparam[0];
      while(*tagattrparam) {
	parse_char(*tagattrparam);
	++tagattrparam;
      }
      parse_char(ISO_gt);
    }
    break;
  case TAG_A:
    PRINTF(("A %s %s\n", s.tagattr, s.tagattrparam));
    if(strncmp(s.tagattr, html_href, sizeof(html_href)) == 0 &&
       s.tagattrparam[0] != 0) {
      strcpy(s.linkurl, s.tagattrparam);
      switch_majorstate(MAJORSTATE_LINK);
      s.linktextptr = 0;
    }
    break;
  case TAG_SLASHA:
    if(s.majorstate == MAJORSTATE_LINK) {
      switch_majorstate(s.lastmajorstate);
      s.linktext[s.linktextptr] = 0;
      htmlparser_link(s.linktext, s.linkurl);
      PRINTF(("Link '%s' [%s]\n", s.linktext, s.linkurl));