aboutsummaryrefslogtreecommitdiffstats
path: root/lib/url.c
blob: e4deac7810ea8d9a94f538eea3f294b1ff640cb9 (plain) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107

  /********************************************************************\
  * BitlBee -- An IRC to other IM-networks gateway                     *
  *                                                                    *
  * Copyright 2001-2005 Wilmer van der Gaast and others                *
  \********************************************************************/

/* URL/mirror stuff - Stolen from Axel                                  */

/*
  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 with
  the Debian GNU/Linux distribution in /usr/share/common-licenses/GPL;
  if not, write to the Free Software Foundation, Inc., 59 Temple Place,
  Suite 330, Boston, MA  02111-1307  USA
*/

#include "url.h"

/* Convert an URL to a url_t structure					*/
int url_set( url_t *url, char *set_url )
{
	char s[MAX_STRING];
	char *i;
	
	/* protocol://							*/
	if( ( i = strstr( set_url, "://" ) ) == NULL )
	{
		url->proto = PROTO_DEFAULT;
		strncpy( s, set_url, MAX_STRING );
	}
	else
	{
		if( g_strncasecmp( set_url, "http", i - set_url ) == 0 )
			url->proto = PROTO_HTTP;
		else if( g_strncasecmp( set_url, "https", i - set_url ) == 0 )
			url->proto = PROTO_HTTPS;
		else if( g_strncasecmp( set_url, "socks4", i - set_url ) == 0 )
			url->proto = PROTO_SOCKS4;
		else if( g_strncasecmp( set_url, "socks5", i - set_url ) == 0 )
			url->proto = PROTO_SOCKS5;
		else
		{
			return( 0 );
		}
		strncpy( s, i + 3, MAX_STRING );
	}
	
	/* Split							*/
	if( ( i = strchr( s, '/' ) ) == NULL )
	{
		strcpy( url->file, "/" );
	}
	else
	{
		strncpy( url->file, i, MAX_STRING );
		*i = 0;
	}
	strncpy( url->host, s, MAX_STRING );
	
	/* Check for username in host field				*/
	if( strrchr( url->host, '@' ) != NULL )
	pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */
.highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */
.highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */
.highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */
.highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */
.highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */
.highlight .vc { color: #336699 } /* Name.Variable.Class */
.highlight .vg { color: #dd7700 } /* Name.Variable.Global */
.highlight .vi { color: #3333bb } /* Name.Variable.Instance */
.highlight .vm { color: #336699 } /* Name.Variable.Magic */
.highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */
  /********************************************************************\
  * BitlBee -- An IRC to other IM-networks gateway                     *
  *                                                                    *
  * Copyright 2002-2006 Wilmer van der Gaast and others                *
  \********************************************************************/

/*
 * Various utility functions. Some are copied from Gaim to support the
 * IM-modules, most are from BitlBee.
 *
 * Copyright (C) 1998-1999, Mark Spencer <markster@marko.net>
 *                          (and possibly other members of the Gaim team)
 * Copyright 2002-2006 Wilmer van der Gaast <wilmer@gaast.net>
 */

/*
  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 with
  the Debian GNU/Linux distribution in /usr/share/common-licenses/GPL;
  if not, write to the Free Software Foundation, Inc., 59 Temple Place,
  Suite 330, Boston, MA  02111-1307  USA
*/

#define BITLBEE_CORE
#include "nogaim.h"
#include "base64.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <
generated by cgit v1.2.3 (git 2.25.1) at 2025-11-01 09:32:58 +0000
/span> #include <resolv.h> #endif #include "ssl_client.h" void strip_linefeed(gchar *text) { int i, j; gchar *text2 = g_malloc(strlen(text) + 1); for (i = 0, j = 0; text[i]; i++) if (text[i] != '\r') text2[j++] = text[i]; text2[j] = '\0'; strcpy(text, text2); g_free(text2); } time_t get_time(int year, int month, int day, int hour, int min, int sec) { struct tm tm; memset(&tm, 0, sizeof(struct tm)); tm.tm_year = year - 1900; tm.tm_mon = month - 1; tm.tm_mday = day; tm.tm_hour = hour; tm.tm_min = min; tm.tm_sec = sec >= 0 ? sec : time(NULL) % 60; return mktime(&tm); } typedef struct htmlentity { char code[7]; char is[3]; } htmlentity_t; static const htmlentity_t ent[] = { { "lt", "<" }, { "gt", ">" }, { "amp", "&" }, { "quot", "\"" }, { "aacute", "á" }, { "eacute", "é" }, { "iacute", "é" }, { "oacute", "ó" }, { "uacute", "ú" }, { "agrave", "à" }, { "egrave", "è" }, { "igrave", "ì" }, { "ograve", "ò" }, { "ugrave", "ù" }, { "acirc", "â" }, { "ecirc", "ê" }, { "icirc", "î" }, { "ocirc", "ô" }, { "ucirc", "û" }, { "auml", "ä" }, { "euml", "ë" }, { "iuml", "ï" }, { "ouml", "ö" }, { "uuml", "ü" }, { "nbsp", " " }, { "", "" } }; void strip_html( char *in ) { char *start = in; char *out = g_malloc( strlen( in ) + 1 ); char *s = out, *cs; int i, matched; memset( out, 0, strlen( in ) + 1 ); while( *in ) { if( *in == '<' && ( isalpha( *(in+1) ) || *(in+1) == '/' ) ) { /* If in points at a < and in+1 points at a letter or a slash, this is probably a HTML-tag. Try to find a closing > and continue there. If the > can't be found, assume that it wasn't a HTML-tag after all. */ cs = in; while( *in && *in != '>' ) in ++; if( *in ) { if( g_strncasecmp( cs+1, "br", 2) == 0 ) *(s++) = '\n'; in ++; } else { in = cs; *(s++) = *(in++); } } else if( *in == '&' ) { cs = ++in; while( *in && isalpha( *in ) ) in ++; if( *in == ';' ) in ++; matched = 0; for( i = 0; *ent[i].code; i ++ ) if( g_strncasecmp( ent[i].code, cs, strlen( ent[i].code ) ) == 0 ) { int j; for( j = 0; ent[i].is[j]; j ++ ) *(s++) = ent[i].is[j]; matched = 1; break; } /* None of the entities were matched, so return the string */ if( !matched ) { in = cs - 1; *(s++) = *(in++); } } else { *(s++) = *(in++); } } strcpy( start, out ); g_free( out ); } char *escape_html( const char *html ) { const char *c = html; GString *ret; char *str; if( html == NULL ) return( NULL ); ret = g_string_new( "" ); while( *c ) { switch( *c ) { case '&': ret = g_string_append( ret, "&amp;" ); break; case '<': ret = g_string_append( ret, "&lt;" ); break; case '>': ret = g_string_append( ret, "&gt;" ); break; case '"': ret = g_string_append( ret, "&quot;" ); break; default: ret = g_string_append_c( ret, *c ); } c ++; } str = ret->str; g_string_free( ret, FALSE ); return( str ); } /* Decode%20a%20file%20name */ void http_decode( char *s ) { char *t; int i, j, k; t = g_new( char, strlen( s ) + 1 ); for( i = j = 0; s[i]; i ++, j ++ ) { if( s[i] == '%' ) { if( sscanf( s + i + 1, "%2x", &k ) ) { t[j] = k; i += 2; } else { *t = 0; break; } } else { t[j] = s[i]; } } t[j] = 0; strcpy( s, t ); g_free( t ); } /* Warning: This one explodes the string. Worst-cases can make the string 3x its original size! */ /* This fuction is safe, but make sure you call it safely as well! */ void http_encode( char *s ) { char *t; int i, j; t = g_strdup( s ); for( i = j = 0; t[i]; i ++, j ++ ) { /* if( t[i] <= ' ' || ((unsigned char *)t)[i] >= 128 || t[i] == '%' ) */ if( !isalnum( t[i] ) ) { sprintf( s + j, "%%%02X", ((unsigned char*)t)[i] ); j += 2; } else { s[j] = t[i]; } } s[j] = 0; g_free( t ); } /* Strip newlines from a string. Modifies the string passed to it. */ char *strip_newlines( char *source ) { int i; for( i = 0; source[i] != '\0'; i ++ ) if( source[i] == '\n' || source[i] == '\r' ) source[i] = ' '; return source; } /* Wrap an IPv4 address into IPv6 space. Not thread-safe... */ char *ipv6_wrap( char *src ) { static char dst[64]; int i; for( i = 0; src[i]; i ++ ) if( ( src[i] < '0' || src[i] > '9' ) && src[i] != '.' ) break; /* Hmm, it's not even an IP... */ if( src[i] ) return src; g_snprintf( dst, sizeof( dst ), "::ffff:%s", src ); return dst; } /* Unwrap an IPv4 address into IPv6 space. Thread-safe, because it's very simple. :-) */ char *ipv6_unwrap( char *src ) { int i; if( g_strncasecmp( src, "::ffff:", 7 ) != 0 ) return src; for( i = 7; src[i]; i ++ ) if( ( src[i] < '0' || src[i] > '9' ) && src[i] != '.' ) break; /* Hmm, it's not even an IP... */ if( src[i] ) return src; return ( src + 7 ); } /* Convert from one charset to another. from_cs, to_cs: Source and destination charsets src, dst: Source and destination strings size: Size if src. 0 == use strlen(). strlen() is not reliable for UNICODE/UTF16 strings though. maxbuf: Maximum number of bytes to write to dst Returns the number of bytes written to maxbuf or -1 on an error. */ signed int do_iconv( char *from_cs, char *to_cs, char *src, char *dst, size_t size, size_t maxbuf ) { GIConv cd; size_t res; size_t inbytesleft, outbytesleft; char *inbuf = src; char *outbuf = dst; cd = g_iconv_open( to_cs, from_cs ); if( cd == (GIConv) -1 ) return( -1 ); inbytesleft = size ? size : strlen( src ); outbytesleft = maxbuf - 1; res = g_iconv( cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft ); *outbuf = '\0'; g_iconv_close( cd ); if( res == (size_t) -1 ) return( -1 ); else return( outbuf - dst ); } /* A pretty reliable random number generator. Tries to use the /dev/random devices first, and falls back to the random number generator from libc when it fails. Opens randomizer devices with O_NONBLOCK to make sure a lack of entropy won't halt BitlBee. */ void random_bytes( unsigned char *buf, int count ) { static int use_dev = -1; /* Actually this probing code isn't really necessary, is it? */ if( use_dev == -1 ) { if( access( "/dev/random", R_OK ) == 0 || access( "/dev/urandom", R_OK ) == 0 ) use_dev = 1; else { use_dev = 0; srand( ( getpid() << 16 ) ^ time( NULL ) ); } } if( use_dev ) { int fd; /* At least on Linux, /dev/random can block if there's not enough entropy. We really don't want that, so if it can't give anything, use /dev/urandom instead. */ if( ( fd = open( "/dev/random", O_RDONLY | O_NONBLOCK ) ) >= 0 ) if( read( fd, buf, count ) == count ) { close( fd ); return; } close( fd ); /* urandom isn't supposed to block at all, but just to be sure. If it blocks, we'll disable use_dev and use the libc randomizer instead. */ if( ( fd = open( "/dev/urandom", O_RDONLY | O_NONBLOCK ) ) >= 0 ) if( read( fd, buf, count ) == count ) { close( fd ); return; } close( fd ); /* If /dev/random blocks once, we'll still try to use it again next time. If /dev/urandom also fails for some reason, stick with libc during this session. */ use_dev = 0; srand( ( getpid() << 16 ) ^ time( NULL ) ); } if( !use_dev ) { int i; /* Possibly the LSB of rand() isn't very random on some platforms. Seems okay on at least Linux and OSX though. */ for( i = 0; i < count; i ++ ) buf[i] = rand() & 0xff; } } int is_bool( char *value ) { if( *value == 0 ) return 0; if( ( g_strcasecmp( value, "true" ) == 0 ) || ( g_strcasecmp( value, "yes" ) == 0 ) || ( g_strcasecmp( value, "on" ) == 0 ) ) return 1; if( ( g_strcasecmp( value, "false" ) == 0 ) || ( g_strcasecmp( value, "no" ) == 0 ) || ( g_strcasecmp( value, "off" ) == 0 ) ) return 1; while( *value ) if( !isdigit( *value ) ) return 0; else value ++; return 1; } int bool2int( char *value ) { int i; if( ( g_strcasecmp( value, "true" ) == 0 ) || ( g_strcasecmp( value, "yes" ) == 0 ) || ( g_strcasecmp( value, "on" ) == 0 ) ) return 1; if( ( g_strcasecmp( value, "false" ) == 0 ) || ( g_strcasecmp( value, "no" ) == 0 ) || ( g_strcasecmp( value, "off" ) == 0 ) ) return 0; if( sscanf( value, "%d", &i ) == 1 ) return i; return 0; } struct ns_srv_reply *srv_lookup( char *service, char *protocol, char *domain ) { struct ns_srv_reply *reply = NULL; #ifdef HAVE_RESOLV_A char name[1024]; unsigned char querybuf[1024]; const unsigned char *buf; ns_msg nsh; ns_rr rr; int i, len, size; g_snprintf( name, sizeof( name ), "_%s._%s.%s", service, protocol, domain ); if( ( size = res_query( name, ns_c_in, ns_t_srv, querybuf, sizeof( querybuf ) ) ) <= 0 ) return NULL; if( ns_initparse( querybuf, size, &nsh ) != 0 ) return NULL; if( ns_parserr( &nsh, ns_s_an, 0, &rr ) != 0 ) return NULL; size = ns_rr_rdlen( rr ); buf = ns_rr_rdata( rr ); len = 0; for( i = 6; i < size && buf[i]; i += buf[i] + 1 ) len += buf[i] + 1; if( i > size ) return NULL; reply = g_malloc( sizeof( struct ns_srv_reply ) + len ); memcpy( reply->name, buf + 7, len ); for( i = buf[6]; i < len && buf[7+i]; i += buf[7+i] + 1 ) reply->name[i] = '.'; if( i > len ) { g_free( reply ); return NULL; } reply->prio = ( buf[0] << 8 ) | buf[1]; reply->weight = ( buf[2] << 8 ) | buf[3]; reply->port = ( buf[4] << 8 ) | buf[5]; #endif return reply; } /* Word wrapping. Yes, I know this isn't UTF-8 clean. I'm willing to take the risk. */ char *word_wrap( char *msg, int line_len ) { GString *ret = g_string_sized_new( strlen( msg ) + 16 ); while( strlen( msg ) > line_len ) { int i; /* First try to find out if there's a newline already. Don't want to add more splits than necessary. */ for( i = line_len; i > 0 && msg[i] != '\n'; i -- ); if( msg[i] == '\n' ) { g_string_append_len( ret, msg, i + 1 ); msg += i + 1; continue; } for( i = line_len; i > 0; i -- ) { if( msg[i] == '-' ) { g_string_append_len( ret, msg, i + 1 ); g_string_append_c( ret, '\n' ); msg += i + 1; break; } else if( msg[i] == ' ' ) { g_string_append_len( ret, msg, i ); g_string_append_c( ret, '\n' ); msg += i + 1; break; } } if( i == 0 ) { g_string_append_len( ret, msg, line_len ); g_string_append_c( ret, '\n' ); msg += line_len; } } g_string_append( ret, msg ); return g_string_free( ret, FALSE ); } gboolean ssl_sockerr_again( void *ssl ) { if( ssl ) return ssl_errno == SSL_AGAIN; else return sockerr_again(); } /* Returns values: -1 == Failure (base64-decoded to something unexpected) 0 == Okay 1 == Password doesn't match the hash. */ int md5_verify_password( char *password, char *hash ) { md5_byte_t *pass_dec = NULL; md5_byte_t pass_md5[16]; md5_state_t md5_state; int ret, i; if( base64_decode( hash, &pass_dec ) != 21 ) { ret = -1; } else { md5_init( &md5_state ); md5_append( &md5_state, (md5_byte_t*) password, strlen( password ) ); md5_append( &md5_state, (md5_byte_t*) pass_dec + 16, 5 ); /* Hmmm, salt! */ md5_finish( &md5_state, pass_md5 ); for( i = 0; i < 16; i ++ ) { if( pass_dec[i] != pass_md5[i] ) { ret = 1; break; } } /* If we reached the end of the loop, it was a match! */ if( i == 16 ) ret = 0; } g_free( pass_dec ); return ret; }