strings.c

VLC Player Source Code

/*****************************************************************************
 * strings.c: String related functions
 *****************************************************************************
 * Copyright (C) 2006 the VideoLAN team
 * $Id: 5d1395782375435cf10a18dedb84537c235b7578 $
 *
 * Authors: Antoine Cellerier <dionoea at videolan dot org>
 *          Daniel Stranger <vlc at schmaller dot de>
 *          Rémi Denis-Courmont <rem # videolan org>
 *
 * This program 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.
 *
 * This program 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 this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301, USA.
 *****************************************************************************/

/*****************************************************************************
 * Preamble
 *****************************************************************************/
#ifdef HAVE_CONFIG_H
# include "config.h"
#endif

#include <vlc_common.h>
#include <assert.h>

/* Needed by str_format_time */
#include <time.h>

/* Needed by str_format_meta */
#include <vlc_input.h>
#include <vlc_meta.h>
#include <vlc_playlist.h>
#include <vlc_aout.h>

#include <vlc_strings.h>
#include <vlc_url.h>
#include <vlc_charset.h>

/**
 * Unescape URI encoded string
 * \return decoded duplicated string
 */
char *unescape_URI_duplicate( const char *psz )
{
    char *psz_dup = strdup( psz );
    unescape_URI( psz_dup );
    return psz_dup;
}

/**
 * Unescape URI encoded string in place
 * \return nothing
 */
void unescape_URI( char *psz )
{
    unsigned char *in = (unsigned char *)psz, *out = in, c;
    if( psz == NULL )
        return;

    while( ( c = *in++ ) != '\0' )
    {
        switch( c )
        {
            case '%':
            {
                char val[5], *pval = val;
                unsigned long cp;

                switch( c = *in++ )
                {
                    case '\0':
                        return;

                    case 'u':
                    case 'U':
                        if( ( *pval++ = *in++ ) == '\0' )
                            return;
                        if( ( *pval++ = *in++ ) == '\0' )
                            return;
                        c = *in++;

                    default:
                        *pval++ = c;
                        if( ( *pval++ = *in++ ) == '\0' )
                            return;
                        *pval = '\0';
                }

                cp = strtoul( val, NULL, 0x10 );
                if( cp < 0x80 )
                    *out++ = cp;
                else
                if( cp < 0x800 )
                {
                    *out++ = (( cp >>  6)         | 0xc0);
                    *out++ = (( cp        & 0x3f) | 0x80);
                }
                else
                {
                    assert( cp < 0x10000 );
                    *out++ = (( cp >> 12)         | 0xe0);
                    *out++ = (((cp >>  6) & 0x3f) | 0x80);
                    *out++ = (( cp        & 0x3f) | 0x80);
                }
                break;
            }

            /* + is not a special case - it means plus, not space. */

            default:
                /* Inserting non-ASCII or non-printable characters is unsafe,
                 * and no sane browser will send these unencoded */
                if( ( c < 32 ) || ( c > 127 ) )
                    *out++ = '?';
                else
                    *out++ = c;
        }
    }
    *out = '\0';
}

/**
 * Decode encoded URI string
 * \return decoded duplicated string
 */
char *decode_URI_duplicate( const char *psz )
{
    char *psz_dup = strdup( psz );
    decode_URI( psz_dup );
    return psz_dup;
}

/**
 * Decode encoded URI string in place
 * \return nothing
 */
void decode_URI( char *psz )
{
    unsigned char *in = (unsigned char *)psz, *out = in, c;
    if( psz == NULL )
        return;

    while( ( c = *in++ ) != '\0' )
    {
        switch( c )
        {
            case '%':
            {
                char hex[3];

                if( ( ( hex[0] = *in++ ) == 0 )
                 || ( ( hex[1] = *in++ ) == 0 ) )
                    return;

                hex[2] = '\0';
                *out++ = (unsigned char)strtoul( hex, NULL, 0x10 );
                break;
            }

            case '+':
                *out++ = ' ';
                break;

            default:
                /* Inserting non-ASCII or non-printable characters is unsafe,
                 * and no sane browser will send these unencoded */
                if( ( c < 32 ) || ( c > 127 ) )
                    *out++ = '?';
                else
                    *out++ = c;
        }
    }
    *out = '\0';
    EnsureUTF8( psz );
}

static inline int isurlsafe( int c )
{
    return ( (unsigned char)( c - 'a' ) < 26 )
            || ( (unsigned char)( c - 'A' ) < 26 )
            || ( (unsigned char)( c - '0' ) < 10 )
        /* Hmm, we should not encode character that are allowed in URLs
         * (even if they are not URL-safe), nor URL-safe characters.
         * We still encode some of them because of Microsoft's crap browser.
         */
            || ( strchr( "-_.", c ) != NULL );
}

static inline char url_hexchar( int c )
{
    return ( c < 10 ) ? c + '0' : c + 'A' - 10;
}

/**
 * encode_URI_component
 * Encodes an URI component.
 *
 * @param psz_url nul-terminated UTF-8 representation of the component.
 * Obviously, you can't pass an URI containing a nul character, but you don't
 * want to do that, do you?
 *
 * @return encoded string (must be free()'d)
 */
char *encode_URI_component( const char *psz_url )
{
    char psz_enc[3 * strlen( psz_url ) + 1], *out = psz_enc;
    const uint8_t *in;

    for( in = (const uint8_t *)psz_url; *in; in++ )
    {
        uint8_t c = *in;

        if( isurlsafe( c ) )
            *out++ = (char)c;
        else
        if ( c == ' ')
            *out++ = '+';
        else
        {
            *out++ = '%';
            *out++ = url_hexchar( c >> 4 );
            *out++ = url_hexchar( c & 0xf );
        }
    }
    *out++ = '\0';

    return strdup( psz_enc );
}

/**
 * Converts "&lt;", "&gt;" and "&amp;" to "<", ">" and "&"
 * \param string to convert
 */
void resolve_xml_special_chars( char *psz_value )
{
    char *p_pos = psz_value;

    while ( *psz_value )
    {
        if( *psz_value == '&' )
        {
#define TRY_CHAR( src, len, dst )                   \
            if( !strncmp( psz_value, src, len ) )   \
            {                                       \
                *p_pos = dst;                       \
                psz_value += len;                   \
            }
#define TRY_LONGCHAR( src, len, dst )                   \
            if( !strncmp( psz_value, src, len ) )       \
            {                                           \
                strncpy( p_pos, dst, strlen( dst ) );   \
                p_pos += strlen( dst ) - 1;             \
                psz_value += len;                       \
            }
            TRY_CHAR( "&lt;", 4, '<' )
            else TRY_CHAR( "&gt;", 4, '>' )
            else TRY_CHAR( "&amp;", 5, '&' )
            else TRY_CHAR( "&quot;", 6, '"' )
            else TRY_CHAR( "&apos;", 6, '\'' )
            else if( psz_value[1] == '#' )
            {
                char *psz_end;
                int i = strtol( psz_value+2, &psz_end, 10 );
                if( *psz_end == ';' )
                {
                    if( i >= 32 && i <= 126 )
                    {
                        *p_pos = (char)i;
                        psz_value = psz_end+1;
                    }
                    else
                    {
                        /* Unhandled code, FIXME */
                        *p_pos = *psz_value;
                        psz_value++;
                    }
                }
                else
                {
                    /* Invalid entity number */
                    *p_pos = *psz_value;
                    psz_value++;
                }
            }
            else TRY_LONGCHAR( "&Agrave;", 8, "À" )
            else TRY_LONGCHAR( "&Aacute;", 8, "Á" )
            else TRY_LONGCHAR( "&Acirc;", 7, "Â" )
            else TRY_LONGCHAR( "&Atilde;", 8, "Ã" )
            else TRY_LONGCHAR( "&Auml;", 6, "Ä" )
            else TRY_LONGCHAR( "&Aring;", 7, "Å" )
            else TRY_LONGCHAR( "&AElig;", 7, "Æ" )
            else TRY_LONGCHAR( "&Ccedil;", 8, "Ç" )
            else TRY_LONGCHAR( "&Egrave;", 8, "È" )
            else TRY_LONGCHAR( "&Eacute;", 8, "É" )
            else TRY_LONGCHAR( "&Ecirc;", 7, "Ê" )
            else TRY_LONGCHAR( "&Euml;", 6, "Ë" )
            else TRY_LONGCHAR( "&Igrave;", 8, "Ì" )
            else TRY_LONGCHAR( "&Iacute;", 8, "Í" )
            else TRY_LONGCHAR( "&Icirc;", 7, "Î" )
            else TRY_LONGCHAR( "&Iuml;", 6, "Ï" )
            else TRY_LONGCHAR( "&ETH;", 5, "Ð" )
            else TRY_LONGCHAR( "&Ntilde;", 8, "Ñ" )
            else TRY_LONGCHAR( "&Ograve;", 8, "Ò" )
            else TRY_LONGCHAR( "&Oacute;", 8, "Ó" )
            else TRY_LONGCHAR( "&Ocirc;", 7, "Ô" )
            else TRY_LONGCHAR( "&Otilde;", 8, "Õ" )
            else TRY_LONGCHAR( "&Ouml;", 6, "Ö" )
            else TRY_LONGCHAR( "&Oslash;", 8, "Ø" )
            else TRY_LONGCHAR( "&Ugrave;", 8, "Ù" )
            else TRY_LONGCHAR( "&Uacute;", 8, "Ú" )
            else TRY_LONGCHAR( "&Ucirc;", 7, "Û" )
            else TRY_LONGCHAR( "&Uuml;", 6, "Ü" )
            else TRY_LONGCHAR( "&Yacute;", 8, "Ý" )
            else TRY_LONGCHAR( "&THORN;", 7, "Þ" )
            else TRY_LONGCHAR( "&szlig;", 7, "ß" )
            else TRY_LONGCHAR( "&agrave;", 8, "à" )
            else TRY_LONGCHAR( "&aacute;", 8, "á" )
            else TRY_LONGCHAR( "&acirc;", 7, "â" )
            else TRY_LONGCHAR( "&atilde;", 8, "ã" )
            else TRY_LONGCHAR( "&auml;", 6, "ä" )
            else TRY_LONGCHAR( "&aring;", 7, "å" )
            else TRY_LONGCHAR( "&aelig;", 7, "æ" )
            else TRY_LONGCHAR( "&ccedil;", 8, "ç" )
            else TRY_LONGCHAR( "&egrave;", 8, "è" )
            else TRY_LONGCHAR( "&eacute;", 8, "é" )
            else TRY_LONGCHAR( "&ecirc;", 7, "ê" )
            else TRY_LONGCHAR( "&euml;", 6, "ë" )
            else TRY_LONGCHAR( "&igrave;", 8, "ì" )
            else TRY_LONGCHAR( "&iacute;", 8, "í" )
            else TRY_LONGCHAR( "&icirc;", 7, "î" )
            else TRY_LONGCHAR( "&iuml;", 6, "ï" )
            else TRY_LONGCHAR( "&eth;", 5, "ð" )
            else TRY_LONGCHAR( "&ntilde;", 8, "ñ" )
            else TRY_LONGCHAR( "&ograve;", 8, "ò" )
            else TRY_LONGCHAR( "&oacute;", 8, "ó" )
            else TRY_LONGCHAR( "&ocirc;", 7, "ô" )
            else TRY_LONGCHAR( "&otilde;", 8, "õ" )
            else TRY_LONGCHAR( "&ouml;", 6, "ö" )
            else TRY_LONGCHAR( "&oslash;", 8, "ø" )
            else TRY_LONGCHAR( "&ugrave;", 8, "ù" )
            else TRY_LONGCHAR( "&uacute;", 8, "ú" )
            else TRY_LONGCHAR( "&ucirc;", 7, "û" )
            else TRY_LONGCHAR( "&uuml;", 6, "ü" )
            else TRY_LONGCHAR( "&yacute;", 8, "ý" )
            else TRY_LONGCHAR( "&thorn;", 7, "þ" )
            else TRY_LONGCHAR( "&yuml;", 6, "ÿ" )
            else TRY_LONGCHAR( "&iexcl;", 7, "¡" )
            else TRY_LONGCHAR( "&curren;", 8, "¤" )
            else TRY_LONGCHAR( "&cent;", 6, "¢" )
            else TRY_LONGCHAR( "&pound;", 7, "£" )