Added subject_macro; Tweaked check order; Fixed some warnings

6 files changed, 207 insertions, 47 deletions

diff --git a/doc/INSTRUCTION b/doc/INSTRUCTION
index ef0cdc6..e55fdef 100644
--- a/doc/INSTRUCTION
+++ b/doc/INSTRUCTION
@@ -23,19 +23,21 @@ order:
 
 [trusted settings]
 
+[subject macros]
+
 [domain settings]
 
-Note it is *highly* recommended to set .kbsrc to be only readable by the
-user - this is as passwords are stored in there.
+It is *highly* recommended 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.
 
 Each token is delimited with white space - if the value you want to use
 includes spaces, simple quote them (with either single or double quotes).
 
-Note that 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!
+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!
 
 To see an example kbsrc file, see kbsrc in the src directory.
 
@@ -89,12 +91,13 @@ And understand the following variables:
 			Defaults to off.
 
     blockhtml <on|off>	Whether messages that are pure HTML (content part just
-    			reported as "text/html" are blocked.
+    			reported as "text/html" are blocked.  Also blocks
+			messages with an empty, or missing, content type.
 			Defaults to off.
 
     testmode <on|off>	Whether things will be really deleted, or just
-    			the actions logged.  Note that the log is still
-			filled out as if the deletion occured.
+    			the actions logged.  The log is still filled out as if
+			the deletion occured.
 			Defaults to off, though it is recommended to use this
 			for early runs to ensure your rules are not too harsh
 			(or too easy for that matter).
@@ -119,12 +122,47 @@ other tests.
     }
 
 
+Subject Macros
+==============
+
+This command is simply to ease the writing of regular expressions where you
+want to match expressions where numbers or alternative characters are
+often used to try and fool filters:
+
+    subject_macro <source string> <replacement string>
+
+e.g.
+
+    subject_macro "i" "[i1!l]"	# Common spam spellings for 'i'
+    subject_macro "e" "[e3]"
+    subject_macro "s" "[s5]"
+    ...
+    ...
+    disallow_subject " ?free movies ?"
+
+Subject macros are only expanded one time - if the result of an expansion
+includes another macro, that will not be expanded.  Also remember
+that macros are case sensitive - this allows easy constructions like this
+which would break if the 'i' in the '[]' was expanded:
+
+    set casesense off
+    ...
+    ...
+    subject "i" "[i1!l]"
+    ...
+    ...
+    disallow_subject "i...[I12]"
+
+Even though it's not obvious from the examples above, the source string can
+be any number of characters.
+
+
 Domain settings
 ===============
 
-These define the rules applied to a certain domain.  Note the order these
-appear in is important, as the first match when checking domain names will
-be used.
+These define the rules applied to a certain domain.  The order domains
+appear in is important, as the first match found when checking domain names
+will be used.
 
     domain <regular expression>
     {
@@ -147,9 +185,21 @@ always let through.
 The block_subject means that subjects that match that regular expression are
 always blocked and deleted.
 
-Note that multiple allow_subject and block_subject commands can be in one
-domain.
+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 not matched in a domain command, allow message.
+5. If the subject is allowed for the domain, allow message.
+6. If the username is blocked for the domain, delete message.
+7. If the subject is disallowed for the domain, delete message.
+8. Delete the message if the default is to block.
+
 
 
 -------------------------------------------------------------------------------
-$Id: INSTRUCTION,v 1.3 2003-12-07 01:46:44 ianc Exp $
+$Id: INSTRUCTION,v 1.4 2003-12-08 02:20:14 ianc Exp $
diff --git a/src/Makefile b/src/Makefile
index 481148b..808d8ef 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -18,10 +18,11 @@
 # 
 # -------------------------------------------------------------------------
 # 
-# $Id: Makefile,v 1.3 2003-12-05 19:38:37 ianc Exp $
+# $Id: Makefile,v 1.4 2003-12-08 02:20:14 ianc Exp $
 # 
 
-CFLAGS +=	-g
+# CFLAGS assumes that gcc is being used - simply comment out if required
+CFLAGS	=	-g -Wall -Werror
 
 TARGET	=	kbs
 
@@ -60,8 +61,8 @@ 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 dstring.h
-kbs.o: util.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
@@ -80,12 +81,12 @@ 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
+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: dstring.h config.h rexp.h util.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
diff --git a/src/config.c b/src/config.c
index 616fabf..268198d 100644
--- a/src/config.c
+++ b/src/config.c
@@ -53,6 +53,7 @@ typedef enum {
 		TOK_BlockUser,
 		TOK_AllowSubject,
 		TOK_BlockSubject,
+		TOK_SubjectMacro,
 		TOK_VarHostname,
 		TOK_VarPort,
 		TOK_VarUsername,
@@ -77,10 +78,17 @@ typedef struct Command
     Token	token;
     } Command;
 
+typedef struct
+    {
+    char	*macro;
+    char	*expansion;
+    } Macro;
+
 
 /* ---------------------------------------- GLOBALS
 */
 static DString	error;
+
 static char	*hostname=NULL;
 static char	*username=NULL;
 static char	*password=NULL;
@@ -93,6 +101,9 @@ static int	testmode=FALSE;
 static int	blockhtml=FALSE;
 static int	verbose=TRUE;
 
+static int	no_macro=0;
+static Macro	*macro=NULL;
+
 
 /* ---------------------------------------- COMMAND TABLE
 */
@@ -110,6 +121,7 @@ static const Command cmd_table[]=
 	    {"block_user",	TOK_BlockUser},
 	    {"allow_subject",	TOK_AllowSubject},
 	    {"block_subject",	TOK_BlockSubject},
+	    {"subject_macro",	TOK_SubjectMacro},
 
 	    /* Variables
 	    */
@@ -143,6 +155,48 @@ static const Command cmd_table[]=
 static Token	GetToken(FILE *fp, DString *ret);
 
 
+/* ---------------------------------------- COMMAND HANDLER UTILS
+*/
+static DString	ExpandRE(DString re)
+{
+    DString new;
+    Macro *m;
+    char *p;
+    int f;
+
+    new=DSInit();
+
+    p=re->text;
+
+    while(*p)
+    {
+	m=NULL;
+
+    	for(f=0;f<no_macro && !m;f++)
+	{
+	    if (strncmp(p,macro[f].macro,strlen(macro[f].macro))==0)
+	    {
+	    	m=macro+f;
+	    }
+	}
+
+	if (!m)
+	{
+	    DSAddChar(new,*p);
+	    p++;
+	}
+	else
+	{
+	    DSAddCP(new,m->expansion);
+	    p+=strlen(m->macro);
+	}
+    }
+
+    DSFree(re);
+    return new;
+}
+
+
 /* ---------------------------------------- COMMAND HANDLERS
 */
 static int DoSet(FILE *fp)
@@ -252,7 +306,6 @@ static int DoDomain(FILE *fp)
 {
     DString ds;
     Token tok;
-    int status=TRUE;
     Domain *domain;
     RE_Expression re;
 
@@ -327,6 +380,8 @@ static int DoDomain(FILE *fp)
 	    case TOK_AllowSubject:
 		GetToken(fp,&ds);
 
+		ds=ExpandRE(ds);
+
 		if (!(re=RECompile(ds->text)))
 		{
 		    DSAddCP(error,"Bad regular expression: ");
@@ -341,6 +396,8 @@ static int DoDomain(FILE *fp)
 	    case TOK_BlockSubject:
 		GetToken(fp,&ds);
 
+		ds=ExpandRE(ds);
+
 		if (!(re=RECompile(ds->text)))
 		{
 		    DSAddCP(error,"Bad regular expression: ");
@@ -371,7 +428,6 @@ static int DoTrustedUsers(FILE *fp)
 {
     DString ds;
     Token tok;
-    int status=TRUE;
 
     ds=DSInit();
 
@@ -406,7 +462,6 @@ static int DoTrustedDomains(FILE *fp)
 {
     DString ds;
     Token tok;
-    int status=TRUE;
 
     ds=DSInit();
 
@@ -433,6 +488,42 @@ static int DoTrustedDomains(FILE *fp)
 }
 
 
+static int DoSubjectMacro(FILE *fp)
+{
+    DString arg[2];
+    int f;
+
+    for(f=0;f<2;f++)
+    {
+    	arg[f]=DSInit();
+
+	if (GetToken(fp,&arg[f])==TOK_EOF)
+	{
+	    DSAddCP(error,"Unexpected EOF in subject_macro");
+	    return FALSE;
+	}
+    }
+
+    if (arg[0]->len==0 || arg[1]->len==0)
+    {
+	DSAddCP(error,"Can't use zero length strings in subject_macro");
+	return FALSE;
+    }
+
+    no_macro++;
+
+    macro=Realloc(macro,sizeof *macro * no_macro);
+
+    macro[no_macro-1].macro=CopyStr(arg[0]->text);
+    macro[no_macro-1].expansion=CopyStr(arg[1]->text);
+
+    for(f=0;f<2;f++)
+    	DSFree(arg[f]);
+
+    return TRUE;
+}
+
+
 /* ---------------------------------------- PRVIVATE FUNCTIONS
 */
 static int Getc(FILE *fp)
@@ -570,7 +661,6 @@ static int Parse(FILE *fp)
 {
     DString txt;
     Token tok;
-    char *p;
 
     txt=DSInit();
 
@@ -600,6 +690,11 @@ static int Parse(FILE *fp)
 		    ok=FALSE;
 		break;
 
+	    case TOK_SubjectMacro:
+		if (!DoSubjectMacro(fp))
+		    ok=FALSE;
+		break;
+
 	    case TOK_Expression:
 		DSAddCP(error,"Unknown command in config file: ");
 		DSAddDS(error,txt);
@@ -725,6 +820,16 @@ int ConfigInt(ConfigIntVar var)
 
 void ConfigClose(void)
 {
+    int f;
+
+    for(f=0;f<no_macro;f++)
+    {
+    	free(macro[f].macro);
+    	free(macro[f].expansion);
+    }
+    
+    free(macro);
+
     DSFree(error);
     free(hostname);
     free(username);
diff --git a/src/dbase.c b/src/dbase.c
index aed142d..43fe0b5 100644
--- a/src/dbase.c
+++ b/src/dbase.c
@@ -236,7 +236,8 @@ int DBBlockMessage(const POP3Message *msg)
     	return FALSE;
 
     if (ConfigInt(CONFIG_BLOCKHTML) &&
-	    strncmp(msg->content_type,html,strlen(html))==0)
+	(strncmp(msg->content_type,html,strlen(html))==0 ||
+	 strcmp(msg->content_type,"UNKNOWN")==0))
     {
 	reason="HTML message";
     	return TRUE;
@@ -245,22 +246,6 @@ int DBBlockMessage(const POP3Message *msg)
     if (!(dom=GetDomain(msg->from_domain)))
 	return FALSE;
 
-    for(f=0;f<dom->no_user;f++)
-    {
-	int res;
-
-	if (ConfigInt(CONFIG_CASESENSE))
-	    res=strcmp(dom->user[f],msg->from_uname);
-	else
-	    res=strcasecmp(dom->user[f],msg->from_uname);
-
-	if (res==0)
-	{
-	    reason="disallowed name";
-	    return TRUE;
-	}
-    }
-
     ds=DSInit();
 
     if (ConfigInt(CONFIG_DEJUNK))
@@ -277,6 +262,23 @@ int DBBlockMessage(const POP3Message *msg)
 	}
     }
 
+    for(f=0;f<dom->no_user;f++)
+    {
+	int res;
+
+	if (ConfigInt(CONFIG_CASESENSE))
+	    res=strcmp(dom->user[f],msg->from_uname);
+	else
+	    res=strcasecmp(dom->user[f],msg->from_uname);
+
+	if (res==0)
+	{
+	    DSFree(ds);
+	    reason="disallowed name";
+	    return TRUE;
+	}
+    }
+
     for(f=0;f<dom->no_block;f++)
     {
     	if (RESearch(dom->block[f],ds->text))
diff --git a/src/dstring.c b/src/dstring.c
index e614e83..7e13067 100644
--- a/src/dstring.c
+++ b/src/dstring.c
@@ -87,6 +87,8 @@ DString DSAddChar(DString to, char c)
 
     to->text[to->len++]=c;
     to->text[to->len]=0;
+
+    return to;
 }
 
 
@@ -96,15 +98,16 @@ DString DSAddCP(DString to, const char *from)
     to->text=Realloc(to->text,(((to->len+1)/BLOCKSIZE)+1)*BLOCKSIZE);
 
     strcat(to->text,from);
+
+    return to;
 }
 
 
 DString DSAddDS(DString to, const DString from)
 {
-    to->len+=from->len;
-    to->text=Realloc(to->text,(((to->len+1)/BLOCKSIZE)+1)*BLOCKSIZE);
+    DSAddCP(to,from->text);
 
-    strcat(to->text,from->text);
+    return to;
 }
 
 
diff --git a/src/pop3.c b/src/pop3.c
index 660283e..d9fab19 100644
--- a/src/pop3.c
+++ b/src/pop3.c
@@ -31,6 +31,7 @@ static const char id[]="$Id$";
 #include <stdarg.h>
 #include <ctype.h>
 
+#include <unistd.h>
 #include <sys/types.h>
 #include <sys/select.h>
 #include <sys/socket.h>
@@ -183,7 +184,6 @@ static int GetChar(void)
     static char buff[BLOCKSIZE];
     static ssize_t len=0;
     static int ptr=0;
-    int ch;
 
     if (len==0 || ptr==len)
     {
@@ -214,10 +214,9 @@ static int GetChar(void)
 
 static int GetLine(DString t)
 {
-    size_t size;
     int done;
-    int ch;
     int last;
+    int ch;
 
     done=FALSE;