wget/src/css-url.c

/* Collect URLs from CSS source.
   Copyright (C) 1998, 2000, 2001, 2002, 2003 Free Software Foundation, Inc.

This file is part of GNU Wget.

GNU Wget is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
 (at your option) any later version.

GNU Wget is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with Wget; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.

In addition, as a special exception, the Free Software Foundation
gives permission to link the code of its release of Wget with the
OpenSSL project's "OpenSSL" library (or with modified versions of it
that use the same license as the "OpenSSL" library), and distribute
the linked executables.  You must obey the GNU General Public License
in all respects for all of the code used other than "OpenSSL".  If you
modify this file, you may extend this exception to your version of the
file, but you are not obligated to do so.  If you do not wish to do
so, delete this exception statement from your version.  */

/*
  Note that this is not an actual CSS parser, but just a lexical
  scanner with a tiny bit more smarts bolted on top.  A full parser
  is somewhat overkill for this job.  The only things we're interested
  in are @import rules and url() tokens, so it's easy enough to
  grab those without truly understanding the input.  The only downside
  to this is that we might be coerced into downloading files that
  a browser would ignore.  That might merit some more investigation.
 */

#include <wget.h>

#include <stdio.h>
#ifdef HAVE_STRING_H
# include <string.h>
#else
# include <strings.h>
#endif
#include <stdlib.h>
#include <ctype.h>
#include <errno.h>
#include <assert.h>

#include "wget.h"
#include "utils.h"
#include "convert.h"
#include "html-url.h"
#include "css-tokens.h"

/* from lex.yy.c */
extern char *yytext;
extern int yyleng;
typedef struct yy_buffer_state *YY_BUFFER_STATE;
extern YY_BUFFER_STATE yy_scan_bytes (const char *bytes,int len  );
extern int yylex (void);

#if 1
const char *token_names[] = {
  "CSSEOF",
  "S",
  "CDO",
  "CDC",
  "INCLUDES",
  "DASHMATCH",
  "LBRACE",
  "PLUS",
  "GREATER",
  "COMMA",
  "STRING",
  "INVALID",
  "IDENT",
  "HASH",
  "IMPORT_SYM",
  "PAGE_SYM",
  "MEDIA_SYM",
  "CHARSET_SYM",
  "IMPORTANT_SYM",
  "EMS",
  "EXS",
  "LENGTH",
  "ANGLE",
  "TIME",
  "FREQ",
  "DIMENSION",
  "PERCENTAGE",
  "NUMBER",
  "URI",
  "FUNCTION"
};
#endif

/*
  Given a detected URI token, get only the URI specified within.
  Also adjust the starting position and length of the string.

  A URI can be specified with or without quotes, and the quotes
  can be single or double quotes.  In addition there can be
  whitespace after the opening parenthesis and before the closing
  parenthesis.
*/
char *
get_uri_string (const char *at, int *pos, int *length)
{
  char *uri;
  /*char buf[1024];
  strncpy(buf,at + *pos, *length);
  buf[*length] = '\0';
  DEBUGP (("get_uri_string: \"%s\"\n", buf));*/

  if (0 != strncasecmp (at + *pos, "url(", 4))
    return NULL;

  *pos += 4;
  *length -= 5; /* url() */
  /* skip leading space */
  while (isspace (at[*pos]))
    {
    (*pos)++;
    (*length)--;
    }
  /* skip trailing space */
  while (isspace (at[*pos + *length - 1]))
    {
      (*length)--;
    }
  /* trim off quotes */
  if (at[*pos] == '\'' || at[*pos] == '"')
    {
      (*pos)++;
      *length -= 2;
    }

  uri = xmalloc (*length + 1);
  if (uri)
    {
      strncpy (uri, at + *pos, *length);
      uri[*length] = '\0';      
    }

  return uri;
}

void
get_urls_css (struct map_context *ctx, int offset, int buf_length)
{
  int token;
  /*char tmp[2048];*/
  int buffer_pos = 0;
  int pos, length;
  char *uri;

  /*
  strncpy(tmp,ctx->text + offset, buf_length);
  tmp[buf_length] = '\0';
  DEBUGP (("get_urls_css: \"%s\"\n", tmp));
  */

  /* tell flex to scan from this buffer */
  yy_scan_bytes (ctx->text + offset, buf_length);

  while((token = yylex()) != CSSEOF)
    {
      /*DEBUGP (("%s ", token_names[token]));*/
      /* @import "foo.css"
         or @import url(foo.css)
      */
      if(token == IMPORT_SYM)
        {
          do {
            buffer_pos += yyleng;
          } while((token = yylex()) == S);

          /*DEBUGP (("%s ", token_names[token]));*/

          if (token == STRING || token == URI)
            {
              /*DEBUGP (("Got URI "));*/
              pos = buffer_pos + offset;
              length = yyleng;

              if (token == URI)
                {
                  uri = get_uri_string (ctx->text, &pos, &length);
                }
              else
                {
                  /* cut out quote characters */
                  pos++;
                  length -= 2;
                  uri = xmalloc (length + 1);
                  strncpy (uri, yytext + 1, length);
                  uri[length] = '\0';
                }

              if (uri)
                {
                  struct urlpos *up = append_url (uri, pos, length, ctx);
                  DEBUGP (("Found @import: [%s] at %d [%s]\n", yytext, buffer_pos, uri));

                  if (up)
                    {
                      up->link_inline_p = 1;
                      up->link_css_p = 1;
                      up->link_expect_css = 1;
                    }

                  xfree(uri);
                }
            }
        }
      /* background-image: url(foo.png)
         note that we don't care what
         property this is actually on.
      */
      else if(token == URI)
        {
          pos = buffer_pos + offset;
          length = yyleng;
          uri = get_uri_string (ctx->text, &pos, &length);

          if (uri)
            {
              struct urlpos *up = append_url (uri, pos, length, ctx);
              DEBUGP (("Found URI: [%s] at %d [%s]\n", yytext, buffer_pos, uri));
              if (up)
                {
                  up->link_inline_p = 1;
                  up->link_css_p = 1;
                }

              xfree (uri);
            }
        }
      buffer_pos += yyleng;
    }
  DEBUGP (("\n"));
}

struct urlpos *
get_urls_css_file (const char *file, const char *url)
{
  struct file_memory *fm;
  struct map_context ctx;

  /* Load the file. */
  fm = read_file (file);
  if (!fm)
    {
      logprintf (LOG_NOTQUIET, "%s: %s\n", file, strerror (errno));
      return NULL;
    }
  DEBUGP (("Loaded %s (size %s).\n", file, number_to_static_string (fm->length)));

  ctx.text = fm->content;
  ctx.head = ctx.tail = NULL;
  ctx.base = NULL;
  ctx.parent_base = url ? url : opt.base_href;
  ctx.document_file = file;
  ctx.nofollow = 0;

  get_urls_css (&ctx, 0, fm->length);
  read_file_free (fm);
  return ctx.head;
}