- No longer cutoff nick upon illegal character -- just reject the whole nick. The nick is

still cutoff if the nick is too long. Basically this is the same way as Hybrid does it so it should work ok :). - Added nick character system. This allows you to choose which (additional) characters to allow in nicks via set::allowed-nickchars. See unreal32docs.html -> section 3.16 for a list of available languages and more info on how to use it. Current list: dutch, french, german, italian, spanish, euro-west, chinese-trad, chinese-simp, chinese-ja, chinese. If you wonder why your language is not yet included or why a certain mistake is present, then please understand that we are most likely not experienced (at all) in your language. If you are a native of your language (or know the language well), and your language is not included yet or you have some corrections, then contact syzop@vulnscan.org or report it as a bug on http://bugs.unrealircd.org/
2026-07-05 20:53:12 +02:00 · 2005-02-19 20:47:41 +00:00
parent 6128e121b3
commit 8650c97cd3
12 changed files with 405 additions and 161 deletions
@@ -607,3 +607,16 @@
 - Fixed a small doc bug regarding shun in spamfilter, reported by KnuX (#0002338).
 - Added greek docs, translator: GSF.
 - Some help.conf/005.txt updates, reported by Ron2K (#0002354).
+- No longer cutoff nick upon illegal character -- just reject the whole nick. The nick is
+  still cutoff if the nick is too long. Basically this is the same way as Hybrid does it
+  so it should work ok :).
+- Added nick character system. This allows you to choose which (additional) characters
+  to allow in nicks via set::allowed-nickchars. See unreal32docs.html -> section 3.16
+  for a list of available languages and more info on how to use it.
+  Current list: dutch, french, german, italian, spanish, euro-west, chinese-trad,
+  chinese-simp, chinese-ja, chinese.
+  If you wonder why your language is not yet included or why a certain mistake is present,
+  then please understand that we are most likely not experienced (at all) in your language.
+  If you are a native of your language (or know the language well), and your language
+  is not included yet or you have some corrections, then contact syzop@vulnscan.org or
+  report it as a bug on http://bugs.unrealircd.org/
@@ -69,7 +69,8 @@ English | <a href="unreal32docs.de.html">German</a> |
  -- 3.13. <a href="#feature_bantypes">Ban types</a><br>
  -- 3.14. <a href="#feature_spamfilter">Spamfilter</a><br>
  -- 3.15. <a href="#feature_cidr">CIDR</a><br>
-  -- 3.16. <a href="#feature_other">Other features</a><br>
+  -- 3.16. <a href="#feature_nickchars">Nick Character Sets</a><br>
+  -- 3.17. <a href="#feature_other">Other features</a><br>
  4. <a href="#configuringyourunrealircdconf">Configuring your unrealircd.conf 
  file</a><br>
  ---4.1. <a href="#configurationfileexplained">Configuration file explained</a><br>
@@ -558,7 +559,34 @@ and except tkl::mask (for gzline, gline, and shun). Additionally, CIDR can be us
 127.0.0.0/8 (matches 127.0.0.0 - 127.255.255.255), and fe80:0:0:123::/64 (matches 
 fe80:0:0:123:0:0:0:0 - fe80:0:0:123:ffff:ffff:ffff:ffff).</p></div>

-<p><font size="+2"><b>3.16 - Other features</b></font><a name="feature_other"></a></p><div class="desc">
+<p><font size="+2"><b>3.16 - Nick Character Sets</b></font><a name="feature_nickchars"></a></p><div class="desc">
+<p>UnrealIRCd has now the ability to specify which charsets/languages should be allowed
+in nicknames. You do this in <b>set::allowed-nickchars</b>.<br>
+A table of all possible choices:<br>
+<table border="1">
+<tr><td><b>Name:</b></td><td><b>Description:</b></td><td><b>Character set/encoding:</b></td></tr>
+<tr><td>dutch</td><td>Dutch characters</td><td>latin1</td></tr>
+<tr><td>french</td><td>French characters: accents, ..</td><td>latin1</td></tr>
+<tr><td>german</td><td>German characters: umlauts, eszet, ..</td><td>latin1</td></tr>
+<tr><td>italian</td><td>Italian characters: accents, ..</td><td>latin1</td></tr>
+<tr><td>spanish</td><td>Spanish characters</td><td>latin1</td></tr>
+<tr><td><b>euro-west</b></td><td>dutch, french, german, spanish, italian</td><td>latin1</td></tr>
+<tr><td>chinese-simp</td><td>Simplified Chinese</td><td>Multibyte: GBK/GB2312</td></tr>
+<tr><td>chinese-trad</td><td>Tradditional Chinese</td><td>Multibyte: GBK</td></tr>
+<tr><td>chinese-ja</td><td>Japanese-alike Chinese</td><td>Multibyte: GBK</td></tr>
+<tr><td><b>chinese</b></td><td>chinese-*</td><td>Multibyte: GBK</td></tr>
+</table>
+Please note that some combinations are not allowed (especially multi-region), 
+such as (one of) euro-west and chinese-*, because they can cause display conflicts.
+UnrealIRCd will print out an error if you try to do so.<br><br>
+
+Example 1, for people of western europe:<br>
+<pre>set { allowed-nickchars { euro-west; }; };</pre>
+Example 2, if you have mainly chinese users:<br>
+<pre>set { allowed-nickchars { chinese-simp; chinese-trad; }; };</pre>
+</p></div>
+
+<p><font size="+2"><b>3.17 - Other features</b></font><a name="feature_other"></a></p><div class="desc">
 <p>UnrealIRCd has a lot of features so not everything is covered here... You'll find that out by yourself.</p></div>

 <p> </p>
@@ -2152,6 +2180,8 @@ set {
  Specifies the prefix characters for services "in channel commands". Messages starting with 
  any of the specified characters will still be sent even if the client is +d. The default 
  value is "`".</p>
+<p><font class="set">set::allowed-nickchars { &lt;list&gt; };</font><br>
+  Character sets / languages to allow in nicks, see <a href="#feature_nickchars">Nick Character Sets</a>.</p>
 <p><font class="set">set::allow-userhost-change [never|always|not-on-channels|force-rejoin]</font><br>
  Specifies what happens when the user@host changes (+x/-x/chghost/chgident/setident/vhost/etc).<br>
  <i>never</i> disables all the commands, <i>always</i> does always allow it even when in channels 
@@ -184,6 +184,7 @@ extern MODVAR unsigned char char_atribs[];
 #define DIGIT 16
 #define SPACE 32
 #define ALLOW 64
+#define ALLOWN 128

 #ifndef KLINE_TEMP
 #define KLINE_PERM 0
@@ -746,3 +746,7 @@ void cmodej_delentry(aJFlood *e);
 void cmodej_deluserentries(aClient *cptr);
 void cmodej_delchannelentries(aChannel *chptr);
 #endif
+extern void charsys_reset(void);
+extern void charsys_addmultibyterange(char s1, char e1, char s2, char e2);
+extern void charsys_addallowed(char *s);
+extern void charsys_reset(void);
@@ -1636,7 +1636,8 @@ struct liststruct {

 #define	BadPtr(x) (!(x) || (*(x) == '\0'))

-#define	isvalid(c) (((c) >= 'A' && (c) <= '~') || isdigit(c) || (c) == '-')
+/** Is valid character in nick? [not for external usage, use do_check_nickname instead!] */
+#define isvalid(c)   (char_atribs[(u_char)(c)]&ALLOWN)

 /* remote fds are set to -256, else its a local fd (a local fd
 * can get -1 or -2 in case it has been closed). -- Syzop
@@ -133,7 +133,7 @@ EXP_OBJ_FILES=SRC/CHANNEL.OBJ SRC/SEND.OBJ SRC/SOCKET.OBJ \
 SRC/HELP.OBJ SRC/S_MISC.OBJ SRC/MATCH.OBJ SRC/CRULE.OBJ \
 SRC/S_DEBUG.OBJ  SRC/SUPPORT.OBJ SRC/LIST.OBJ \
 SRC/S_ERR.OBJ SRC/PACKET.OBJ SRC/S_BSD.OBJ \
- SRC/S_SERV.OBJ SRC/S_USER.OBJ \
+ SRC/S_SERV.OBJ SRC/S_USER.OBJ SRC/CHARSYS.OBJ \
 SRC/VERSION.OBJ SRC/RES_INIT.OBJ SRC/RES_COMP.OBJ SRC/RES_MKQUERY.OBJ SRC/RES_SKIPNAME.OBJ \
 SRC/S_KLINE.OBJ SRC/S_EXTRA.OBJ SRC/IRCSPRINTF.OBJ SRC/LUSERS.OBJ \
 SRC/SCACHE.OBJ SRC/ALN.OBJ SRC/BADWORDS.OBJ SRC/WEBTV.OBJ SRC/RES.OBJ SRC/MODULES.OBJ \
@@ -352,6 +352,10 @@ src/s_user.obj: src/s_user.c $(INCLUDES) ./include/dbuf.h \
                ./include/channel.h ./include/whowas.h
        $(CC) $(CFLAGS) src/s_user.c

+src/charsys.obj: src/charsys.c $(INCLUDES) ./include/dbuf.h \
+                ./include/channel.h ./include/whowas.h
+        $(CC) $(CFLAGS) src/charsys.c
+
 src/s_extra.obj: src/s_extra.c $(INCLUDES) ./include/dbuf.h \
                ./include/channel.h ./include/whowas.h
        $(CC) $(CFLAGS) src/s_extra.c
@@ -27,7 +27,7 @@ OBJS=auth.o aln.o badwords.o channel.o cloak.o crule.o dbuf.o \
 	res_init.o res_comp.o res_mkquery.o res_skipname.o s_auth.o \
 	s_bsd.o s_conf.o s_debug.o s_err.o s_extra.o s_kline.o \
 	s_misc.o s_numeric.o s_serv.o s_svs.o $(STRTOUL) socket.o \
-	ssl.o s_user.o scache.o send.o support.o umodes.o \
+	ssl.o s_user.o charsys.o scache.o send.o support.o umodes.o \
 	version.o webtv.o whowas.o zip.o cidr.o random.o extcmodes.o \
 	extbans.o md5.o api-isupport.o api-command.o $(URL)

@@ -211,6 +211,10 @@ s_user.o: s_user.c $(INCLUDES) \
 	  ../include/dbuf.h ../include/channel.h ../include/whowas.h
 	$(CC) $(CFLAGS) -c s_user.c

+charsys.o: charsys.c $(INCLUDES) \
+	  ../include/dbuf.h ../include/channel.h ../include/whowas.h
+	$(CC) $(CFLAGS) -c charsys.c
+
 s_extra.o: s_extra.c $(INCLUDES) \
 	  s_numeric.c ../include/dbuf.h ../include/channel.h ../include/whowas.h
 	$(CC) $(CFLAGS) -c s_extra.c
@@ -0,0 +1,306 @@
+/*
+ * Unreal Internet Relay Chat Daemon, src/charsys.c
+ * (C) Copyright 2005 Bram Matthys and The UnrealIRCd Team.
+ *
+ * Character system: This subsystem deals with finding out wheter a
+ * character should be allowed or not in nicks (nicks only for now).
+ *
+ * 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 1, 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include "config.h"
+#include "struct.h"
+#include "common.h"
+#include "sys.h"
+#include "macros.h"
+#include "numeric.h"
+#include "msg.h"
+#include "channel.h"
+#include <time.h>
+#include <sys/stat.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#ifdef _WIN32
+#include <io.h>
+#endif
+#include <fcntl.h>
+#include "h.h"
+#include "proto.h"
+#ifdef STRIPBADWORDS
+#include "badwords.h"
+#endif
+
+#ifdef _WIN32
+#include "version.h"
+#endif
+
+/* NOTE: it is guaranteed that char is unsigned by compiling options
+ *       (-funsigned-char @ gcc, /J @ MSVC)
+ * NOTE2: Original credit for supplying the correct chinese
+ *        coderanges goes to: RexHsu, Mr.WebBar and Xuefer
+ */
+
+/** Our multibyte structure */
+typedef struct _mblist MBList;
+struct _mblist
+{
+	MBList *next;
+	char s1, e1, s2, e2;
+};
+MBList *mblist = NULL, *mblist_tail = NULL;
+
+static int do_nick_name_multibyte(char *nick);
+static int do_nick_name_standard(char *nick);
+
+/* Use this to prevent mixing of certain combinations
+ * (such as GBK & high-ascii, etc)
+ */
+static int langav;
+/* bitmasks: */
+#define LANGAV_ASCII	1 /* 8 bit ascii */
+#define LANGAV_GBK		2 /* (Chinese) GBK encoding */
+
+/** Called on boot and just before config run */
+void charsys_reset(void)
+{
+int i;
+MBList *m, *m_next;
+
+	/* First, reset everything */
+	for (i=0; i < 256; i++)
+		char_atribs[i] &= ~ALLOWN;
+	for (m=mblist; m; m=m_next)
+	{
+		m_next = m->next;
+		MyFree(m);
+	}
+	mblist=mblist_tail=NULL;
+	/* Then add the default which will always be allowed */
+	charsys_addallowed("0123456789-ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyzy{|}");
+	langav = 0;
+}
+
+void charsys_reset_pretest(void)
+{
+	langav = 0;
+}
+
+/** Add a character range to the multibyte list.
+ * @param s1 Start of highest byte
+ * @param e1 End of highest byte
+ * @param s2 Start of lowest byte
+ * @param e2 End of lowest byte
+ * @example charsys_addmultibyterange(0xaa, 0xbb, 0x00, 0xff) for 0xaa00-0xbbff
+ */
+void charsys_addmultibyterange(char s1, char e1, char s2, char e2)
+{
+MBList *m = MyMallocEx(sizeof(m));
+
+	m->s1 = s1;
+	m->e1 = e1;
+	m->s2 = s2;
+	m->e2 = e2;
+
+	if (mblist_tail)
+		mblist_tail->next = m;
+	else
+		mblist = m;
+	mblist_tail = m;
+}
+
+/** Adds all characters in the specified string to the allowed list. */
+void charsys_addallowed(char *s)
+{
+	for (; *s; s++)
+		char_atribs[(unsigned int)*s] |= ALLOWN;
+}
+
+int do_nick_name(char *nick)
+{
+	if (mblist)
+		return do_nick_name_multibyte(nick);
+	else
+		return do_nick_name_standard(nick);
+}
+
+static int do_nick_name_standard(char *nick)
+{
+int len;
+char *ch;
+
+	if ((*nick == '-') || isdigit(*nick))
+		return 0;
+
+	for (ch=nick,len=0; *ch && len <= NICKLEN; ch++, len++)
+		if (!isvalid(*ch))
+			return 0; /* reject the full nick */
+	*ch = '\0';
+	return len;
+}
+
+static int isvalidmbyte(unsigned char c1, unsigned char c2)
+{
+MBList *m;
+
+	for (m=mblist; m; m=m->next)
+	{
+		if ((c1 >= m->s1) && (c1 <= m->e1) &&
+		    (c2 >= m->s2) && (c2 <= m->e2))
+		    return 1;
+	}
+	return 0;
+}
+
+/* hmmm.. there must be some problems with multibyte &
+ * other high ascii characters I think (such as german etc).
+ * Not sure if this can be solved? I don't think so... -- Syzop.
+ */
+static int do_nick_name_multibyte(char *nick)
+{
+int len;
+char *ch;
+MBList *m;
+int firstmbchar = 0;
+
+	if ((*nick == '-') || isdigit(*nick))
+		return 0;
+
+	for (ch=nick,len=0; *ch && len <= NICKLEN; ch++, len++)
+	{
+		if (firstmbchar)
+		{
+			if (!isvalidmbyte(ch[-1], *ch))
+				return 0;
+			firstmbchar = 0;
+		} else if ((*ch) & 0x80)
+			firstmbchar = 1;
+		else if (!isvalid(*ch))
+			return 0;
+	}
+	if (firstmbchar)
+		ch--;
+	*ch = '\0';
+	return len;
+}
+
+/** Check if the specified charsets during the TESTING phase can be
+ * premitted without getting into problems.
+ * RETURNS: -1 in case of failure, 1 if ok
+ */
+int charsys_postconftest(void)
+{
+	if ((langav & LANGAV_ASCII) && (langav & LANGAV_GBK))
+	{
+		config_error("ERROR: set::accept-language specifies incorrect combination "
+		             "of languages: high-ascii languages (such as german, french, etc) "
+		             "cannot be mixed with chinese/..");
+		return -1;
+	}
+	return 1;
+}
+
+/** Check if language is available. */
+int charsys_test_language(char *name)
+{
+	if (!strcmp(name, "euro-west") ||
+	    !strcmp(name, "german") || !strcmp(name, "dutch") ||
+	    !strcmp(name, "french") || !strcmp(name, "spanish"))
+	{
+		langav |= LANGAV_ASCII;
+		return 1;
+	}
+	if (!strcmp(name, "chinese") || !strcmp(name, "chinese-trad") ||
+	    !strcmp(name, "chinese-simp") || !strcmp(name, "chinese-ja"))
+	{
+		langav |= LANGAV_GBK;
+		return 1;
+	}
+	return 0;
+}
+
+void charsys_add_language(char *name)
+{
+char euro_west=0, chinese=0;
+
+	/** Note: there could well be some characters missing in the lists below.
+	 *        While I've seen other altnernatives that just allow pretty much
+	 *        every accent that exists even for dutch (where we rarely use
+	 *        accents except for like 3 types), I rather prefer to use a bit more
+	 *        reasonable aproach ;). That said, anyone is welcome to make
+	 *        suggestions about characters that should be added (or removed)
+	 *        of course. -- Syzop
+	 */
+
+	/* GROUPS */
+	if (!strcmp(name, "euro-west"))
+		euro_west = 1;
+	if (!strcmp(name, "chinese"))
+		chinese = 1;
+	
+	/* INDIVIDUAL CHARSETS */
+
+	if (euro_west || !strcmp(name, "german"))
+	{
+		/* a", A", e', o", O", u", U" and es-zett */
+		charsys_addallowed("äÄéöÖüÜß");
+	}
+	if (euro_west || !strcmp(name, "dutch"))
+	{
+		/* Ok, even though I'm Dutch myself, I've trouble getting
+		 * a proper list of this ;). I think I got them all now, but
+		 * I did not include "borrow-words" like words we use in Dutch
+		 * that are literal French. So if you really want to use them all,
+		 * I suggest you to use just euro-west :P.
+		 */
+		/* e', e", o", i", u", e`. */
+		charsys_addallowed("éëöïüè");
+	}
+	if (euro_west || !strcmp(name, "french"))
+	{
+		/* A`, A^, a`, a^, weird-C, weird-c, E`, E', E^, E", e`, e', e^, e",
+		 * I^, I", i^, i", O^, o^, U`, U^, U", u`, u", u`, y" [not in that order, sry]
+		 * Hmm.. there might be more, but I'm not sure how common they are
+		 * and I don't think they are always displayed correctly (?).
+		 */
+		charsys_addallowed("ÀÂàâÇçÈÉÊËèéêëÎÏîïÔôÙÛÜùûüÿ");
+	}
+	if (euro_west || !strcmp(name, "spanish"))
+	{
+		/* a', A', e', E', i', I', o', O', u', U', u", U", n~, N~ */
+		charsys_addallowed("áÁéÉíÍóÓúÚüÜñÑ");
+	}
+	if (euro_west || !strcmp(name, "italian"))
+	{
+		/* A`, E`, E', I`, I', O`, O', U`, U', a`, e`, e', i`, i', o`, o', u`, u' */
+		charsys_addallowed("ÀÈÉÌÍÒÓÙÚàèéìíòóùú");
+	}
+	if (chinese || !strcmp(name, "chinese-ja"))
+	{
+		charsys_addmultibyterange(0xa4, 0xa4, 0xa1, 0xf3); /* JIS_PIN */
+		charsys_addmultibyterange(0xa5, 0xa5, 0xa1, 0xf6); /* JIS_PIN */
+	}
+	if (chinese || !strcmp(name, "chinese-simp"))
+	{
+		charsys_addmultibyterange(0xb0, 0xd6, 0xa1, 0xfe); /* GBK/2 BC with GB2312 */
+		charsys_addmultibyterange(0xd7, 0xd7, 0xa1, 0xf9); /* GBK/2 BC with GB2312 */
+		charsys_addmultibyterange(0xd8, 0xf7, 0xa1, 0xfe); /* GBK/2 BC with GB2312 */
+	}
+	if (chinese || !strcmp(name, "chinese-trad"))
+	{
+		charsys_addmultibyterange(0x81, 0xa0, 0x40, 0xfe); /* GBK/3 */
+		charsys_addmultibyterange(0xaa, 0xfe, 0x40, 0xa0); /* GBK/4 */
+	}
+}
@@ -1006,6 +1006,7 @@ int InitwIRCD(int argc, char *argv[])
 	bzero((char *)&me, sizeof(me));
 	bzero(&StatsZ, sizeof(StatsZ));
 	setup_signals();
+	charsys_reset();
 	init_ircstats();
 #ifdef USE_LIBCURL
 	url_init();
@@ -378,8 +378,8 @@ u_char char_atribs[] = {
 	PRINT | ALPHA | ALLOW,
 /* VWX */ PRINT | ALPHA | ALLOW, PRINT | ALPHA | ALLOW,
 	PRINT | ALPHA | ALLOW,
-/* YZ[ */ PRINT | ALPHA | ALLOW, PRINT | ALPHA | ALLOW, PRINT | ALPHA,
-/* \]^ */ PRINT | ALPHA, PRINT | ALPHA, PRINT | ALPHA,
+/* YZ[ */ PRINT | ALPHA | ALLOW, PRINT | ALPHA | ALLOW, PRINT,
+/* \]^ */ PRINT, PRINT, PRINT,
 /* _`  */ PRINT | ALLOW, PRINT,
 /* abc */ PRINT | ALPHA | ALLOW, PRINT | ALPHA | ALLOW,
 	PRINT | ALPHA | ALLOW,
@@ -397,8 +397,8 @@ u_char char_atribs[] = {
 	PRINT | ALPHA | ALLOW,
 /* vwx */ PRINT | ALPHA | ALLOW, PRINT | ALPHA | ALLOW,
 	PRINT | ALPHA | ALLOW,
-/* yz{ */ PRINT | ALPHA | ALLOW, PRINT | ALPHA | ALLOW, PRINT | ALPHA,
-/* |}~ */ PRINT | ALPHA, PRINT | ALPHA, PRINT | ALPHA,
+/* yz{ */ PRINT | ALPHA | ALLOW, PRINT | ALPHA | ALLOW, PRINT,
+/* |}~ */ PRINT, PRINT, PRINT,
 /* del */ 0,
 /* 80-8f */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 /* 90-9f */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -331,6 +331,11 @@ extern void add_entropy_configfile(struct stat st, char *buf);
 extern void unload_all_unused_snomasks();
 extern void unload_all_unused_umodes();

+extern int charsys_test_language(char *name);
+extern void charsys_add_language(char *name);
+extern void charsys_reset_pretest(void);
+int charsys_postconftest(void);
+
 /* Stuff we only need here for spamfilter, so not in h.h... */
 extern aTKline *tklines[TKLISTLEN];
 extern inline int tkl_hash(char c);
@@ -1595,7 +1600,9 @@ int	init_conf(char *rootconf, int rehash)
 	config_setdefaultsettings(&tempiConf);
 	if (load_conf(rootconf) > 0)
 	{
-		if ((config_test() < 0) || (callbacks_check() < 0) || (efunctions_check() < 0))
+		charsys_reset_pretest();
+		if ((config_test() < 0) || (callbacks_check() < 0) || (efunctions_check() < 0) ||
+		    (charsys_postconftest() < 0))
 		{
 			config_error("IRCd configuration failed to pass testing");
 #ifdef _WIN32
@@ -1647,6 +1654,7 @@ int	init_conf(char *rootconf, int rehash)
 			l_commands_Init(&ModCoreInfo);
 		}
 #endif
+		charsys_reset();
 		if (config_run() < 0)
 		{
 			config_error("Bad case of config errors. Server will now die. This really shouldn't happen");
@@ -6400,6 +6408,10 @@ int	_conf_set(ConfigFile *conf, ConfigEntry *ce)
 			else
 				tempiConf.userhost_allowed = UHALLOW_REJOIN;
 		}
+		else if (!strcmp(cep->ce_varname, "allowed-nickchars")) {
+			for (cepp = cep->ce_entries; cepp; cepp=cepp->ce_next)
+				charsys_add_language(cepp->ce_varname);
+		}
 		else if (!strcmp(cep->ce_varname, "channel-command-prefix")) {
 			ircstrdup(tempiConf.channel_command_prefix, cep->ce_vardata);
 		}
@@ -6914,6 +6926,25 @@ int	_test_set(ConfigFile *conf, ConfigEntry *ce)
 				continue;
 			}
 		}
+		else if (!strcmp(cep->ce_varname, "allowed-nickchars")) {
+			if (cep->ce_vardata)
+			{
+				config_error("%s:%i: set::allow-nickchars: please use 'allowed-nickchars { name; };' "
+				             "and not 'allowed-nickchars name;'",
+				             cep->ce_fileptr->cf_filename, cep->ce_varlinenum);
+				errors++;
+				continue;
+			}
+			for (cepp = cep->ce_entries; cepp; cepp=cepp->ce_next)
+			{
+				if (!charsys_test_language(cepp->ce_varname))
+				{
+					config_error("%s:%i: set::allow-nickchars: Unknown (sub)language '%s'",
+						cep->ce_fileptr->cf_filename, cep->ce_varlinenum, cepp->ce_varname);
+					errors++;
+				}
+			}
+		}
 		else if (!strcmp(cep->ce_varname, "anti-spam-quit-message-time")) {
 			CheckNull(cep);
 			CheckDuplicate(cep, anti_spam_quit_message_time, "anti-spam-quit-message-time");
@@ -657,157 +657,6 @@ int  check_for_target_limit(aClient *sptr, void *target, const char *name)
 	return 0;
 }

-
-
-
-/*
-** 'do_nick_name' ensures that the given parameter (nick) is
-** really a proper string for a nickname (note, the 'nick'
-** may be modified in the process...)
-**
-**	RETURNS the length of the final NICKNAME (0, if
-**	nickname is illegal)
-**
-**  Nickname characters are in range
-**	'A'..'}', '_', '-', '0'..'9'
-**  anything outside the above set will terminate nickname.
-**  In addition, the first character cannot be '-'
-**  or a Digit.
-**
-**  Note:
-**	'~'-character should be allowed, but
-**	a change should be global, some confusion would
-**	result if only few servers allowed it...
-*/
-
-#if defined(NICK_GB2312) || defined(NICK_GBK) || defined(NICK_GBK_JAP)
-#define NICK_MULTIBYTE
-#endif
-
-#ifdef NICK_MULTIBYTE
-/* Chinese Nick Verification Code - Added by RexHsu on 08/09/00 (beta2)
- * Now Support All GBK Words,Thanks to Mr.WebBar <climb@guomai.sh.cn>!
- * Special Char Bugs Fixed by RexHsu 09/01/00 I dont know whether it is
- * okay now?May I am right ;p
- * Thanks dilly for providing me Japanese code range!
- * Now I am meeting a nickname conflicting problem....
- *
- * GBK Libary Reference:
- * 1. GBK2312非汉字符号区(A1A1----A9FE)
- * 2. GBK2312汉字区(B0A1----F7FE)
- * 3. GBK扩充汉字区(8140----A0FE)
- * 4. GBK扩充汉字区(AA40----FEA0)
- * 5. GBK扩充非汉字区(A840----A9A0)
- * 6. 日文平假名编码区(a4a1-a4f3) -->work correctly?maybe...
- * 7. 日文片假名编码区(a5a1-a5f7) -->work correctly?maybe...
- * 8. 韩文编码区(xxxx-yyyy)
- *
- * isvalidChinese() rewritten by Xuefer (2004-10-10),
- * this will probably be the last time we do it this way,
- * in 3.2.3 we are gonna try a more generic aproach. -- Syzop
- */
-
-int isvalidChinese(const unsigned char c1, const unsigned char c2)
-{
-    unsigned int w = (((unsigned int)c1) << 8) | c2;
-
-/* rang of w/c1/c2 (rw never used) */
-#define rw(s, e) (w >= ((unsigned int )s) && w <= ((unsigned int )e))
-#define r1(s, e) (c1 >= ((unsigned char)s) && c1 <= ((unsigned char)e))
-#define r2(s, e) (c2 >= ((unsigned char)s) && c2 <= ((unsigned char)e))
-#define e1(e) (c1 == (unsigned char)e)
-
-#ifdef NICK_GBK_JAP
-    /* GBK/1 */
-    /* JIS_PIN part 1 */
-    if (e1(0xA4) && r2(0xA1, 0xF3)) return 1;
-    /* JIS_PIN part 2 */
-    if (e1(0xA5) && r2(0xA1, 0xF6)) return 1;
-#endif
-#if defined(NICK_GB2312) || defined(NICK_GBK)
-    /* GBK/2 BC with GB2312 */
-    if (r2(0xA1, 0xFE))
-    {
-        /* Block 16-55, ordered by Chinese Spelling(PinYin) 3755 chars */
-        if (r1(0xB0, 0xD6)) return 1;
-        /* Block 55 is NOT full (w <= 0xd7f9) */
-        if (e1(0xD7) && c2 <= (unsigned char)0xF9 /* r2(0xA1, 0xF9)*/) return 1;
-        /* Block 56-87 is level 2 chars, ordered by writing 3008 chars */
-        if (r1(0xD8, 0xF7)) return 1;
-    }
-#endif
-
-#ifdef NICK_GBK
-    /* GBK/3 */
-    if (r1(0x81, 0xA0) && r2(0x40, 0xFE)) return 1;
-    /* GBK/4 */
-    if (r2(0x40, 0xA0) && r1(0xAA, 0xFE)) return 1;
-#endif
-
-    /* all failed */
-    return 0;
-
-#undef rw
-#undef r1
-#undef r2
-#undef e1
-}
-
-/* Chinese Nick Supporting Code (Switch Mode) - Modified by RexHsu on 08/09/00 */
-int  do_nick_name(char *pnick)
-{
-	unsigned char *ch;
-	unsigned char *nick = pnick;
-	int  firstChineseChar = 0;
-	char lastChar;
-
-	if (*nick == '-' || isdigit(*nick))	/* first character in [0..9-] */
-		return 0;
-
-	for (ch = nick; *ch && (ch - nick) < NICKLEN; ch++)
-	{
-		if ((!isvalid(*ch) && !((*ch) & 0x80)) || isspace(*ch)
-		    || (*ch) == '@' || (*ch) == '!' || (*ch) == ':'
-		    || (*ch) == ' ')
-			break;
-		if (firstChineseChar)
-		{
-			if (!isvalidChinese(lastChar, *ch))
-				break;
-			firstChineseChar = 0;
-		}
-		else if ((*ch) & 0x80)
-			firstChineseChar = 1;
-		lastChar = *ch;
-	}
-
-	if (firstChineseChar)
-		ch--;
-
-	*ch = '\0';
-
-	return (ch - nick);
-}
-
-
-#else
-int  do_nick_name(char *nick)
-{
-	char *ch;
-
-	if (*nick == '-' || isdigit(*nick))	/* first character in [0..9-] */
-		return 0;
-
-	for (ch = nick; *ch && (ch - nick) < NICKLEN; ch++)
-		if (!isvalid(*ch) || isspace(*ch))
-			break;
-
-	*ch = '\0';
-
-	return (ch - nick);
-}
-#endif
-
 /*
 ** canonize
 **