Add unicode_count() crule, e.g. unicode_count('Emoticons')

This will return the number of characters that are in the unicode block
with that name.

spamfilter {
	rule "unicode_count('Emoticons')>2";
	target { private; channel; private-notice; channel-notice; }
	action block;
	reason "Too much emotion";
}

In this commit we also make it so we pass the ClientContext (including
clictx->textanalysis) in crule_context.

include/struct.h

@@ -1116,6 +1116,7 @@ struct crule_context
 	Client *client;			/**< Client that is being processed (can be NULL) */
 	const char *text;		/**< The input string, if any (can be NULL) */
 	const char *destination;	/**< Destination of the message, like '#xyz' for spamfilter (can be NULL, eg for 'u') */
+	ClientContext *clictx;		/**< Client context (can be NULL)  */
 };
 
 /** Evaluation function for a connection rule. */

src/modules/crule.c

@@ -144,6 +144,7 @@ static int crule_match_country(crule_context *, int, void **);
 static int crule_match_asn(crule_context *, int, void **);
 static int crule_match_certfp(crule_context *, int, void **);
 static int crule_match_realname(crule_context *, int, void **);
+static int crule_unicode_count(crule_context *, int, void **);
 
 /* parsing function prototypes - local! */
 static int crule_gettoken(crule_token *next_tokp, const char **str);
@@ -204,6 +205,7 @@ struct crule_funclistent crule_funclist[] = {
 	{"match_asn", 1, crule_match_asn},
 	{"match_certfp", 1, crule_match_certfp},
 	{"match_realname", 1, crule_match_realname},
+	{"unicode_count", 1, crule_unicode_count},
 	{"", 0, NULL} /* this must be here to mark end of list */
 };
 
@@ -550,6 +552,20 @@ static int crule_match_realname(crule_context *context, int numargs, void *crule
 	return 0;
 }
 
+static int crule_unicode_count(crule_context *context, int numargs, void *crulearg[])
+{
+	const char *arg = (char *)crulearg[0];
+
+	if (context && context->clictx && context->clictx->textanalysis)
+	{
+		int i = utf8_get_block_number(arg);
+		if (i < 0)
+			return -1; /* Block name not found */
+		return context->clictx->textanalysis->unicode_blockmap[i];
+	}
+	return 0;
+}
+
 /** Evaluate a connection rule.
  * @param[in] rule Rule to evalute.
  * @return Non-zero if the rule allows the connection, zero otherwise.

src/modules/tkl.c

@@ -5516,6 +5516,7 @@ int _match_spamfilter(Client *client, const char *str_in, int target, const char
 	context.client = client;
 	context.text = str_in;
 	context.destination = destination;
+	context.clictx = clictx;
 
 	/* Client exempt from spamfilter checking?
 	 * Let's check that early: going through elines is likely faster than running the regex(es).
@@ -5678,6 +5679,7 @@ int _match_spamfilter(Client *client, const char *str_in, int target, const char
 			context.client = client;
 			context.text = str_in;
 			context.destination = destination;
+			context.clictx = clictx;
 			if (!crule_eval(&context, tkl->ptr.spamfilter->rule))
 				continue;