1 /*

     2  * nohtml.c     -- (X)HTML helper functions

     3  *

     4  * Copyright (C) 2008 Mikael Berthe <mikael@lilotux.net>

     5  * Some portions come from the jabberd project, see below.

     6  *

     7  * This program is free software; you can redistribute it and/or modify

     8  * it under the terms of the GNU General Public License as published by

     9  * the Free Software Foundation; either version 2 of the License, or (at

    10  * your option) any later version.

    11  *

    12  * This program is distributed in the hope that it will be useful, but

    13  * WITHOUT ANY WARRANTY; without even the implied warranty of

    14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU

    15  * General Public License for more details.

    16  *

    17  * You should have received a copy of the GNU General Public License

    18  * along with this program; if not, write to the Free Software

    19  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307

    20  * USA

    21  *

    22  *

    23  * Some parts come from libjabber/str.c:

    24  * Copyright (c) 1999-2002 Jabber.com, Inc.  All Rights Reserved.  Contact

    25  * information for Jabber.com, Inc. is available at http://www.jabber.com/.

    26  * Portions Copyright (c) 1998-1999 Jeremie Miller.

    27  */

    28 

    29 #include <string.h>

    30 #include <glib.h>

    31 #include <config.h>

    32 

    33 

    34 /*  html_strip(htmlbuf)

    35  * Remove html entities from htmlbuf and try to convert it to plain text.

    36  * The caller must g_free the string after use.

    37  * Code mostly derived from strunescape(), in libjabber.

    38  */

    39 char *html_strip(const char *htmlbuf)

    40 {

    41   int i, j=0;

    42   char *nohtml;

    43 

    44   if (!htmlbuf) return(NULL);

    45 

    46   nohtml = g_strdup(htmlbuf);

    47 

    48   if (!strchr(htmlbuf, '&') && !strchr(htmlbuf, '<'))

    49     return(nohtml);

    50 

    51   for (i = 0; i < (int)strlen(htmlbuf); i++) {

    52     if (htmlbuf[i] == '&') {

    53       if (!strncmp(&htmlbuf[i],"&",5)) {

    54         nohtml[j] = '&';

    55         i += 4;

    56       } else if (!strncmp(&htmlbuf[i],""", 6)) {

    57         nohtml[j] = '\"';

    58         i += 5;

    59       } else if (!strncmp(&htmlbuf[i],"'", 6)) {

    60         nohtml[j] = '\'';

    61         i += 5;

    62       } else if (!strncmp(&htmlbuf[i],"<", 4)) {

    63         nohtml[j] = '<';

    64         i += 3;

    65       } else if (!strncmp(&htmlbuf[i],">", 4)) {

    66         nohtml[j] = '>';

    67         i += 3;

    68       }

    69     } else if (!strncmp(&htmlbuf[i],"<br>", 4) ||

    70                !strncmp(&htmlbuf[i],"<br/>", 5)) {

    71       nohtml[j] = '\n';

    72       i += (htmlbuf[i+3] == '/' ? 4 : 3);

    73     } else if (htmlbuf[i] == '<') {

    74       /* Let's strip all unknown tags */

    75       j--;

    76       while (htmlbuf[++i] != '>');

    77     } else

    78       nohtml[j] = htmlbuf[i];

    79     j++;

    80   }

    81   nohtml[j] = '\0';

    82   return nohtml;

    83 }

    84 

    85 /*  html_escape(text)

    86  * Add (x)html entities to the text.

    87  * The caller must g_free the string after use.

    88  * Code mostly derived from strescape(), in libjabber.

    89  */

    90 char *html_escape(const char *text)

    91 {

    92   int i, j;

    93   int oldlen, newlen;

    94   char *html;

    95 

    96   if (!text) return(NULL);

    97 

    98   oldlen = newlen = strlen(text);

    99 

   100   for (i = 0; i < oldlen; i++) {

   101     switch(text[i])

   102     {

   103       case '&':

   104           newlen += 5;

   105           break;

   106       case '\'':

   107           newlen += 6;

   108           break;

   109           case '\"':

   110               newlen += 6;

   111           break;

   112       case '<':

   113           newlen += 4;

   114           break;

   115       case '>':

   116           newlen += 4;

   117           break;

   118       case '\n':

   119           newlen += 5;

   120     }

   121   }

   122 

   123   if (oldlen == newlen)

   124     return g_strdup(text);

   125 

   126   html = g_new0(char, newlen+1);

   127 

   128   for (i = j = 0; i < oldlen; i++) {

   129     switch(text[i])

   130     {

   131       case '&':

   132           memcpy(&html[j], "&", 5);

   133           j += 5;

   134           break;

   135       case '\'':

   136           memcpy(&html[j], "'", 6);

   137           j += 6;

   138           break;

   139       case '\"':

   140           memcpy(&html[j], """, 6);

   141           j += 6;

   142           break;

   143       case '<':

   144           memcpy(&html[j], "<", 4);

   145           j += 4;

   146           break;

   147       case '>':

   148           memcpy(&html[j], ">", 4);

   149           j += 4;

   150           break;

   151       case '\n':

   152           memcpy(&html[j], "<br/>", 5);

   153           j += 5;

   154           break;

   155       default:

   156           html[j++] = text[i];

   157     }

   158   }

   159   return html;

   160 }

   161 

   162 /* vim: set expandtab cindent cinoptions=>2\:2(0:  For Vim users... */