Added allow_to in domain; Added include; Update docs; Fixed folding header lines

9 files changed, 322 insertions, 45 deletions

diff --git a/doc/INSTRUCTION b/doc/INSTRUCTION
index 40d91b1..1ac9e8e 100644
--- a/doc/INSTRUCTION
+++ b/doc/INSTRUCTION
@@ -2,7 +2,9 @@
 Usage
 =====
 
-    kbs
+    kbs [config-file]
+
+If config-file is not provided, a default of $HOME/.kbsrc is used.
 
 
 Description
@@ -16,11 +18,13 @@ a special keyword in a subject header to be used.
 Config file format
 ==================
 
-The kbs config file is read from $HOME/.kbsrc and has sections in the suggested
-order:
+The kbs config file is read from $HOME/.kbsrc (or the parameter supplied) and
+has sections in the suggested order:
 
 [config settings]
 
+[include]
+
 [trusted settings]
 
 [blacklist settings]
@@ -29,7 +33,7 @@ order:
 
 [domain settings]
 
-It is *highly* recommended to set .kbsrc to be only readable by the user - this
+It is *stringly* suggested to set .kbsrc to be only readable by the user - this
 is as passwords are stored in there.
 
 Blank lines and text proceeded with a hash (#) are ignored.
@@ -39,7 +43,7 @@ includes spaces, simple quote them (with either single or double quotes).
 
 Escapes aren't used (to make regular expression writing easier), so if you want
 to include a quote in a string, simply use the other sort of quote.  If you
-want both, sorry, you're stuck!
+want both, sorry!
 
 To see an example kbsrc file, see kbsrc in the src directory.
 
@@ -98,7 +102,10 @@ And understand the following variables:
 
     blockhtml <on|off>	Whether messages that are pure HTML (content part just
     			reported as "text/html" are blocked.  Also blocks
-			messages with an empty, or missing, content type.
+			messages with an empty, or missing, content type
+			WARNING: this will delete mail sent with old command
+			line mailers as they don't set a content-type - however,
+			plenty of spam has no valid content-type either.
 			Defaults to off.
 
     testmode <on|off>	Whether things will be really deleted, or just
@@ -109,6 +116,33 @@ And understand the following variables:
 			(or too easy for that matter).
 
 
+Include files
+=============
+
+Include files are useful if you want to scan multiple hosts buy using mutiple
+config files, eg.
+
+In file 1:
+
+set host	host1
+set username	user1
+set password	pass1
+
+include "/etc/kbsrc"
+
+
+In file 2:
+
+set host	host2
+set username	user2
+set password	pass2
+
+include "/etc/kbsrc"
+
+
+Then put all your rules as needed in /etc/kbsrc.
+
+
 Trusted settings
 ================
 
@@ -191,6 +225,7 @@ will be used.
     {
 	[default block|allow]
     	[block_user <username>]
+	[allow_to <regular expression>]
     	[allow_subject <regular expression>]
 	[block_subject <regular expression>]
     }
@@ -202,6 +237,13 @@ The block user allows a specific username to be blocked.  For instance, I've
 noticed that spammers have a great love of emailing from your username at
 a different domain.
 
+The allow_to sets a regular expression that the 'To: ' line in the header
+data must match.  This can be handy as for some reason, even though spam may
+be directed to your inbox, the 'To:' line will actually read a nonsense name
+for your host.  Note that it's not recommended to anchor the regular expression
+as if the mail has been sent to multiple recipients it is not guaranteed
+where your name will appear in the list of users.
+
 The allow_subject means that subjects that match that regular expression are
 always let through.
 
@@ -213,17 +255,19 @@ Multiple allow and block commands can be in one domain.
 The commands inside a domain can appear in any order, but the checks are always
 done in this order:
 
-1. If a trusted domain, allow message.
-2. If a trusted user, allow message.
-3. If an HTML message and these are blocked, delete message.
-4. If the domain is blacklisted, delete message.
-5. If the domain is not matched in a domain command, allow message.
-6. If the subject is allowed for the domain, allow message.
-7. If the username is blocked for the domain, delete message.
-8. If the subject is disallowed for the domain, delete message.
-9. Delete the message if the default is to block, otherwise allow.
+ 1. If a trusted domain, allow message.
+ 2. If a trusted user, allow message.
+ 3. If an HTML message and these are blocked, delete message.
+ 4. If the domain is blacklisted, delete message.
+ 5. If the domain is not matched in a domain command, allow message.
+ 6. If the subject is allowed for the domain, allow message.
+ 7. If an allow_to has been set for the domain, and it doesn't match,
+    delete message.
+ 8. If the username is blocked for the domain, delete message.
+ 9. If the subject is disallowed for the domain, delete message.
+10. Delete the message if the default is to block, otherwise allow.
 
 
 
 -------------------------------------------------------------------------------
-$Id: INSTRUCTION,v 1.6 2004-01-01 01:25:04 ianc Exp $
+$Id: INSTRUCTION,v 1.7 2004-01-26 02:01:49 ianc Exp $
diff --git a/src/Makefile b/src/Makefile
index e1ef0ce..15b4775 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -18,7 +18,7 @@
 # 
 # -------------------------------------------------------------------------
 # 
-# $Id: Makefile,v 1.6 2003-12-12 01:15:38 ianc Exp $
+# $Id: Makefile,v 1.7 2004-01-26 02:01:49 ianc Exp $
 # 
 
 # CFLAGS assumes that gcc is being used - simply comment out if required
@@ -54,3 +54,52 @@ depend:
 	if test -e Makefile ; then rm -f Makefile.bak ; fi
 
 # DO NOT DELETE THIS LINE -- make depend depends on it
+
+kbs.o: /usr/include/stdlib.h /usr/include/sys/cdefs.h
+kbs.o: /usr/include/sys/_types.h /usr/include/machine/_types.h
+kbs.o: /usr/include/limits.h /usr/include/sys/limits.h
+kbs.o: /usr/include/machine/_limits.h /usr/include/sys/syslimits.h
+kbs.o: /usr/include/stdio.h /usr/include/string.h /usr/include/strings.h
+kbs.o: /usr/include/stdarg.h /usr/include/time.h /usr/include/sys/timespec.h
+kbs.o: /usr/include/errno.h global.h config.h pop3.h msg.h dbase.h rexp.h
+kbs.o: dstring.h util.h
+pop3.o: /usr/include/stdlib.h /usr/include/sys/cdefs.h
+pop3.o: /usr/include/sys/_types.h /usr/include/machine/_types.h
+pop3.o: /usr/include/string.h /usr/include/strings.h /usr/include/stdio.h
+pop3.o: /usr/include/stdarg.h /usr/include/ctype.h /usr/include/runetype.h
+pop3.o: /usr/include/unistd.h /usr/include/sys/types.h
+pop3.o: /usr/include/machine/endian.h /usr/include/sys/select.h
+pop3.o: /usr/include/sys/_sigset.h /usr/include/sys/_timeval.h
+pop3.o: /usr/include/sys/timespec.h /usr/include/sys/unistd.h
+pop3.o: /usr/include/sys/socket.h /usr/include/sys/_iovec.h
+pop3.o: /usr/include/machine/param.h /usr/include/netinet/in.h
+pop3.o: /usr/include/netinet6/in6.h /usr/include/netinet/tcp.h
+pop3.o: /usr/include/netdb.h global.h pop3.h msg.h dstring.h util.h
+config.o: /usr/include/stdlib.h /usr/include/sys/cdefs.h
+config.o: /usr/include/sys/_types.h /usr/include/machine/_types.h
+config.o: /usr/include/string.h /usr/include/strings.h /usr/include/stdio.h
+config.o: /usr/include/errno.h /usr/include/ctype.h /usr/include/runetype.h
+config.o: global.h config.h dstring.h dbase.h msg.h rexp.h util.h
+rexp.o: /usr/include/stdlib.h /usr/include/sys/cdefs.h
+rexp.o: /usr/include/sys/_types.h /usr/include/machine/_types.h
+rexp.o: /usr/include/regex.h global.h rexp.h config.h util.h
+dbase.o: /usr/include/stdlib.h /usr/include/sys/cdefs.h
+dbase.o: /usr/include/sys/_types.h /usr/include/machine/_types.h
+dbase.o: /usr/include/string.h /usr/include/strings.h /usr/include/stdio.h
+dbase.o: /usr/include/ctype.h /usr/include/runetype.h global.h dbase.h msg.h
+dbase.o: rexp.h dstring.h config.h util.h
+dstring.o: /usr/include/stdlib.h /usr/include/sys/cdefs.h
+dstring.o: /usr/include/sys/_types.h /usr/include/machine/_types.h
+dstring.o: /usr/include/string.h /usr/include/strings.h /usr/include/stdio.h
+dstring.o: /usr/include/stdarg.h /usr/include/ctype.h /usr/include/runetype.h
+dstring.o: /usr/include/sys/types.h /usr/include/machine/endian.h
+dstring.o: /usr/include/sys/select.h /usr/include/sys/_sigset.h
+dstring.o: /usr/include/sys/_timeval.h /usr/include/sys/timespec.h
+dstring.o: /usr/include/sys/socket.h /usr/include/sys/_iovec.h
+dstring.o: /usr/include/machine/param.h /usr/include/netinet/in.h
+dstring.o: /usr/include/netinet6/in6.h /usr/include/netinet/tcp.h
+dstring.o: /usr/include/netdb.h global.h dstring.h util.h
+util.o: /usr/include/stdlib.h /usr/include/sys/cdefs.h
+util.o: /usr/include/sys/_types.h /usr/include/machine/_types.h
+util.o: /usr/include/string.h /usr/include/strings.h /usr/include/stdio.h
+util.o: global.h util.h
diff --git a/src/config.c b/src/config.c
index 1c10591..66ea944 100644
--- a/src/config.c
+++ b/src/config.c
@@ -57,6 +57,8 @@ typedef enum {
 		TOK_BlockSubject,
 		TOK_SubjectMacro,
 		TOK_Blacklist,
+		TOK_Include,
+		TOK_AllowTo,
 		TOK_VarHostname,
 		TOK_VarPort,
 		TOK_VarUsername,
@@ -128,6 +130,8 @@ static const Command cmd_table[]=
 	    {"block_subject",	TOK_BlockSubject},
 	    {"subject_macro",	TOK_SubjectMacro},
 	    {"blacklist",	TOK_Blacklist},
+	    {"include",		TOK_Include},
+	    {"allow_to",	TOK_AllowTo},
 
 	    /* Variables
 	    */
@@ -160,6 +164,7 @@ static const Command cmd_table[]=
 /* ---------------------------------------- REQUIRED PROTOS
 */
 static Token	GetToken(FILE *fp, DString *ret);
+static int	Parse(FILE *fp);
 
 
 /* ---------------------------------------- COMMAND HANDLER UTILS
@@ -417,6 +422,22 @@ static int DoDomain(FILE *fp)
 		DBBlockSubject(domain,re);
 	    	break;
 
+	    case TOK_AllowTo:
+		GetToken(fp,&ds);
+
+		ds=ExpandRE(ds);
+
+		if (!(re=RECompile(ds->text)))
+		{
+		    DSAddCP(error,"Bad regular expression: ");
+		    DSAddDS(error,ds);
+		    DSFree(ds);
+		    return FALSE;
+		}
+
+		DBAllowTo(domain,re);
+	    	break;
+
 	    default:
 		DSAddCP(error,"Unexpected string in domain command: ");
 		DSAddDS(error,ds);
@@ -576,6 +597,42 @@ static int DoBlacklist(FILE *fp)
 }
 
 
+static int DoInclude(FILE *fp)
+{
+    FILE *inc;
+    DString ds;
+    Token tok;
+    int ret;
+
+    ds=DSInit();
+
+    tok=GetToken(fp,&ds);
+
+    if (tok==TOK_EOF)
+    {
+	DSAddCP(error,"Unexpected EOF in include command");
+	DSFree(ds);
+	return FALSE;
+    }
+
+    if (!(inc=fopen(ds->text,"r")))
+    {
+	DSAddCP(error,"Couldn't open include file ");
+	DSAddDS(error,ds);
+	DSFree(ds);
+	return FALSE;
+    }
+
+    DSFree(ds);
+
+    ret=Parse(inc);
+
+    fclose(inc);
+
+    return ret;
+}
+
+
 /* ---------------------------------------- PRVIVATE FUNCTIONS
 */
 static int Getc(FILE *fp)
@@ -752,6 +809,11 @@ static int Parse(FILE *fp)
 		    ok=FALSE;
 		break;
 
+	    case TOK_Include:
+		if (!DoInclude(fp))
+		    ok=FALSE;
+		break;
+
 	    case TOK_Expression:
 		DSAddCP(error,"Unknown command in config file: ");
 		DSAddDS(error,txt);
@@ -780,7 +842,7 @@ static int Parse(FILE *fp)
 /* ---------------------------------------- INTERFACES
 */
 
-int ConfigLoad(void)
+int ConfigLoad(const char *path)
 {
     DString ds;
     FILE *fp;
@@ -793,14 +855,19 @@ int ConfigLoad(void)
     password=CopyStr("");
     log=CopyStr("");
 
-    if (!getenv("HOME"))
-    	return FALSE;
-
     ds=DSInit();
 
-    DSAddCP(ds,getenv("HOME"));
-    DSAddChar(ds,'/');
-    DSAddCP(ds,".kbsrc");
+    if (path)
+    	DSAddCP(ds,path);
+    else
+    {
+	if (!getenv("HOME"))
+	    return FALSE;
+
+	DSAddCP(ds,getenv("HOME"));
+	DSAddChar(ds,'/');
+	DSAddCP(ds,".kbsrc");
+    }
 
     if ((fp=fopen(ds->text,"r")))
     	ret=Parse(fp);
diff --git a/src/config.h b/src/config.h
index 7f48a70..d545531 100644
--- a/src/config.h
+++ b/src/config.h
@@ -61,9 +61,10 @@ typedef enum
 /* ---------------------------------------- INTERFACES
 */
 
-/* Loads in config file.  Returns FALSE for problems.
+/* Loads in config file (the default name if path is NULL).  Returns FALSE
+   for problems.
 */
-int		ConfigLoad(void);
+int		ConfigLoad(const char *path);
 
 
 /* Returns a reason for config load failure
diff --git a/src/dbase.c b/src/dbase.c
index c3e83b7..e1caa04 100644
--- a/src/dbase.c
+++ b/src/dbase.c
@@ -49,9 +49,11 @@ struct Domain
     int			no_user;
     int			no_block;
     int			no_allow;
+    int			no_allow_to;
     char		**user;
     RE_Expression	*block;
     RE_Expression	*allow;
+    RE_Expression	*allow_to;
     Domain		*next;
     Domain		*prev;
     };
@@ -165,6 +167,7 @@ Domain *DBNewDomain(RE_Expression name)
     dom->user=NULL;
     dom->block=NULL;
     dom->allow=NULL;
+    dom->allow_to=NULL;
 
     if (tail)
     	tail->next=dom;
@@ -208,6 +211,15 @@ void DBBlockSubject(Domain *domain, RE_Expression re)
 }
 
 
+void DBAllowTo(Domain *domain, RE_Expression re)
+{
+    domain->no_allow_to++;
+    domain->allow_to=Realloc(domain->allow_to,
+			     sizeof(RE_Expression)*domain->no_allow_to);
+    domain->allow_to[domain->no_allow_to-1]=re;
+}
+
+
 void DBTrustedUser(const char *username)
 {
     no_trusted_users++;
@@ -254,7 +266,7 @@ int DBBlockMessage(const POP3Message *msg)
 	(strncmp(msg->content_type,html,strlen(html))==0 ||
 	 strcmp(msg->content_type,"UNKNOWN")==0))
     {
-	DSAddCP(reason,"HTML message");
+	DSAddCP(reason,"HTML message or unknown content type");
     	return TRUE;
     }
 
@@ -293,6 +305,30 @@ int DBBlockMessage(const POP3Message *msg)
 	}
     }
 
+    if (dom->no_allow_to)
+    {
+    	int found=FALSE;
+	int f;
+
+	for(f=0;f<dom->no_allow_to && !found;f++)
+	    if (RESearch(dom->allow_to[f],msg->to))
+	    	found=TRUE;
+
+	if (!found)
+	{
+	    if (show)
+	    {
+	    	DSAddCP(reason,"disallowed to address - ");
+		DSAddCP(reason,msg->to);
+	    }
+	    else
+	    	DSAddCP(reason,"disallowed to address");
+
+	    DSFree(ds);
+	    return TRUE;
+	}
+    }
+
     for(f=0;f<dom->no_user;f++)
     {
 	int res;
@@ -392,6 +428,11 @@ void DBClose(void)
 
 	free(t->allow);
 
+	for(f=0;f<t->no_allow;f++)
+	    REFree(t->allow_to[f]);
+
+	free(t->allow_to);
+
 	free(t);
     }
 
diff --git a/src/dbase.h b/src/dbase.h
index 3c771af..1b3dfa6 100644
--- a/src/dbase.h
+++ b/src/dbase.h
@@ -70,6 +70,12 @@ void		DBAllowSubject(Domain *domain, RE_Expression re);
 void		DBBlockSubject(Domain *domain, RE_Expression re);
 
 
+/* Sets the allowed 'To:' name for a domain.
+   re will be freed by the database when closed.
+*/
+void		DBAllowTo(Domain *domain, RE_Expression re);
+
+
 /* Adds a trusted username
 */
 void		DBTrustedUser(const char *username);
diff --git a/src/kbs.c b/src/kbs.c
index c951a63..8cdf8be 100644
--- a/src/kbs.c
+++ b/src/kbs.c
@@ -60,7 +60,7 @@ int main(int argc, char *argv[])
     else
 	name=argv[0];
 
-    if (!ConfigLoad())
+    if (!ConfigLoad(argv[1]))
     {
 	fprintf(stderr,"%s: %s\n",name,ConfigError());
 	exit(EXIT_FAILURE);
diff --git a/src/kbsrc b/src/kbsrc
index 5361dd3..27031df 100644
--- a/src/kbsrc
+++ b/src/kbsrc
@@ -69,6 +69,12 @@ domain "."
     #
     block_user emailname
 
+
+    # Only allow emails legitimately directed to us:
+    #
+    allow_to emailname@myisp.co.uk
+
+
     # Obviously, things like "credit card" will not be blocked from the bank
     # as that's in the trusted_domains.
     #
@@ -94,9 +100,10 @@ domain "."
     block_subject ".* ?naked ?.*"
     block_subject ".* ?nigeria ?.*"
 
+
     # Why would anyone sane want to use my username in a subject?
     # I know who I am!  Note it's capitilised so nothing bizarre gets
     # done by the subject macros.
     #
-    block_subject "EMAILNAME@MY-ISP.CO.UK"
+    block_subject "EMAILNAME@MYISP.CO.UK"
 }
diff --git a/src/pop3.c b/src/pop3.c
index c6b6fe1..bfd9e6c 100644
--- a/src/pop3.c
+++ b/src/pop3.c
@@ -57,6 +57,7 @@ static const char message_id[]=KBS_MSG_H;
 #define HDR_FROM		1
 #define HDR_TO			2
 #define HDR_CONTENT_TYPE	3
+#define HDR_DEBUG		4
 
 /* ---------------------------------------- TYPES
 */
@@ -71,6 +72,7 @@ static int	connected=FALSE;
 
 /* ---------------------------------------- PRIVATE FUNCTIONS
 */
+/*
 static void Chomp(char *p)
 {
     size_t l;
@@ -87,6 +89,7 @@ static void Chomp(char *p)
     	p[--l]=0;
     }
 }
+*/
 
 
 static char *ChompQuotesWS(char *p)
@@ -182,13 +185,14 @@ static int Send(const char *cmd, ...)
 }
 
 
+static char	gc_buff[BLOCKSIZE];
+static ssize_t	gc_len=0;
+static int	gc_ptr=0;
+
+
 static int GetChar(void)
 {
-    static char buff[BLOCKSIZE];
-    static ssize_t len=0;
-    static int ptr=0;
-
-    if (len==0 || ptr==len)
+    if (gc_len==0 || gc_ptr==gc_len)
     {
     	struct timeval tv;
 	fd_set set;
@@ -205,13 +209,20 @@ static int GetChar(void)
 	if (!FD_ISSET(sock,&set))
 	    return -1;
 
-	if ((len=read(sock,buff,sizeof buff))<1)
+	if ((gc_len=read(sock,gc_buff,sizeof gc_buff))<1)
 	    return -1;
 
-	ptr=0;
+	gc_ptr=0;
     }
 
-    return buff[ptr++];
+    return gc_buff[gc_ptr++];
+}
+
+
+static void UnGetChar(int c)
+{
+    if (gc_ptr)
+    	gc_buff[--gc_ptr]=c;
 }
 
 
@@ -225,7 +236,8 @@ static int GetLine(DString t)
 
     while(!done && (ch=GetChar())!=-1)
     {
-	DSAddChar(t,ch);
+	if (ch!='\015' && ch!='\012')
+	    DSAddChar(t,ch);
 
 	if (last=='\015' && ch=='\012')
 	    done=TRUE;
@@ -236,8 +248,6 @@ static int GetLine(DString t)
     if (ch==-1)
     	return FALSE;
 
-    Chomp(t->text);
-
     return TRUE;
 }
 
@@ -263,14 +273,59 @@ static int GetResponse(DString ret)
 }
 
 
+static int IsHeader(const DString line)
+{
+    const char *p;
+
+    p=line->text;
+
+    while(*p && !isspace(*p))
+    {
+    	if (*p==':')
+	    return TRUE;
+
+	p++;
+    }
+
+    return FALSE;
+}
+
+
 static int GetMultiLine(DString ret)
 {
-    int flag;
+    int done=FALSE;
+    int flag=TRUE;
 
-    if (GetLine(ret))
-    	flag=TRUE;
-    else
-    	flag=FALSE;
+    while (!done)
+    {
+    	if (GetLine(ret))
+	{
+	    if (IsHeader(ret))
+	    {
+		int ch;
+
+		if ((ch=GetChar())!=-1)
+		{
+		    if (ch!=' ' && ch!='\t')
+		    	done=TRUE;
+
+		    UnGetChar(ch);
+		}
+		else
+		{
+		    flag=FALSE;
+		    done=TRUE;
+		}
+	    }
+	    else
+	    	done=TRUE;
+	}
+	else
+	{
+	    flag=FALSE;
+	    done=TRUE;
+	}
+    }
 
     return flag;
 }
@@ -289,15 +344,18 @@ static void ParseHeader(POP3Message *msg, char *line)
 	    	{"To: ",		HDR_TO},
 	    	{"Content-type: ",	HDR_CONTENT_TYPE},
 	    	{"Content-Type: ",	HDR_CONTENT_TYPE},
+	    	/* {"Received: ",	HDR_DEBUG}, */
 	    	{NULL,			HDR_UNKNOWN}
 	    };
 
+    const char *name;
     int f;
     int type=HDR_UNKNOWN;
 
     for(f=0;type==HDR_UNKNOWN && field[f].text;f++)
     	if (strncmp(field[f].text,line,strlen(field[f].text))==0)
 	{
+	    name=field[f].text;
 	    type=field[f].type;
 	    line+=strlen(field[f].text);
 	}
@@ -341,6 +399,10 @@ static void ParseHeader(POP3Message *msg, char *line)
 	    msg->content_type=CopyStr(line);
 	    break;
 
+	case HDR_DEBUG:
+	    printf("%s = '%s'\n",name,line);
+	    break;
+
     	default:
 	    break;
     }