Restore rsmapd support

Following discussions on the exim-user mailinglist it seems that the conclusion
that the interface was nonfunctioning was unwarranted.

6 files changed, 117 insertions, 27 deletions

diff --git a/doc/doc-docbook/spec.xfpt b/doc/doc-docbook/spec.xfpt
index 82e4dfaff..9cddddde5 100644
--- a/doc/doc-docbook/spec.xfpt
+++ b/doc/doc-docbook/spec.xfpt
@@ -32266,14 +32266,20 @@ deny message = This message contains malware ($malware_name)
 .endd
 
 
-.section "Scanning with SpamAssassin" "SECTscanspamass"
+.section "Scanning with SpamAssassin and Rspamd" "SECTscanspamass"
 .cindex "content scanning" "for spam"
 .cindex "spam scanning"
 .cindex "SpamAssassin"
+.cindex "Rspamd"
 The &%spam%& ACL condition calls SpamAssassin's &%spamd%& daemon to get a spam
-score and a report for the message. You can get SpamAssassin at
-&url(http://www.spamassassin.org), or, if you have a working Perl
-installation, you can use CPAN by running:
+score and a report for the message.
+Support is also provided for Rspamd.
+
+For more information about installation and configuration of SpamAssassin or
+Rspamd refer to their respective websites at
+&url(http://spamassassin.apache.org) and &url(http://www.rspamd.com)
+
+SpamAssassin can be installed with CPAN by running:
 .code
 perl -MCPAN -e 'install Mail::SpamAssassin'
 .endd
@@ -32299,6 +32305,14 @@ server (currently defaulting to 120s).  With a lower value the Linux
 connection tracking may consider your half-closed connection as dead too
 soon.
 
+
+To use Rspamd (which by default listens on all local addresses
+on TCP port 11333)
+you should add &%variant=rspamd%& after the address/port pair, for example:
+.code
+spamd_address = 127.0.0.1 11333 variant=rspamd
+.endd
+
 As of version 2.60, &%SpamAssassin%& also supports communication over UNIX
 sockets. If you want to us these, supply &%spamd_address%& with an absolute
 file name instead of an address/port pair:
@@ -32383,7 +32397,8 @@ The right-hand side of the &%spam%& condition specifies a name. This is
 relevant if you have set up multiple SpamAssassin profiles. If you do not want
 to scan using a specific profile, but rather use the SpamAssassin system-wide
 default profile, you can scan for an unknown name, or simply use &"nobody"&.
-However, you must put something on the right-hand side.
+Rspamd does not use this setting. However, you must put something on the
+right-hand side.
 
 The name allows you to use per-domain or per-user antispam profiles in
 principle, but this is not straightforward in practice, because a message may
@@ -32452,8 +32467,10 @@ when running in country-specific locales, which are not legal
 unencoded in headers.
 
 .vitem &$spam_action$&
-Either 'reject' or 'no action' depending on the
+For SpamAssassin either 'reject' or 'no action' depending on the
 spam score versus threshold.
+For Rspamd, the recommended action.
+
 .endlist
 
 The &%spam%& condition caches its results unless expansion in
diff --git a/doc/doc-txt/ChangeLog b/doc/doc-txt/ChangeLog
index 58b82bddd..754f48b15 100644
--- a/doc/doc-txt/ChangeLog
+++ b/doc/doc-txt/ChangeLog
@@ -72,13 +72,10 @@ JH/15 Rework TLS client-side context management.  Stop using a global, and
       explicitly pass a context around.  This enables future use of TLS for
       connections to service-daemons (eg. malware scanning) while a client smtp
       connection is using TLS; with cutthrough connections this is quite likely.
-JH/15 Support for Rspamd, as a variant of the "spam" ACL condition used for
-      connecting to a SpamAssassain "spamd" daemon for content scanning, is
-      removed.  Following changes to the protocol used for communication with
-      Rspamd it was apparently inoperable.
 
 JH/16 Fix ARC verification to do AS checks in reverse order.
-JH/16 Support a "tls" option on the ${readsocket } expansion item.
+
+JH/17 Support a "tls" option on the ${readsocket } expansion item.
 
 
 Exim version 4.91
diff --git a/src/README.UPDATING b/src/README.UPDATING
index 11cd0ba44..2438cc953 100644
--- a/src/README.UPDATING
+++ b/src/README.UPDATING
@@ -34,8 +34,6 @@ Exim version 4.92
    is limited to one retry unless the (new) config option dns_cname_loops
    is changed.
 
- * Support for Rspamd has been removed.
-
 Exim version 4.91
 -----------------
 
diff --git a/src/src/spam.c b/src/src/spam.c
index db6cf8495..9384bfa0d 100644
--- a/src/src/spam.c
+++ b/src/src/spam.c
@@ -16,7 +16,7 @@
 uschar spam_score_buffer[16];
 uschar spam_score_int_buffer[16];
 uschar spam_bar_buffer[128];
-uschar * spam_action_buffer;
+uschar spam_action_buffer[32];
 uschar spam_report_buffer[32600];
 uschar prev_user_name[128] = "";
 int spam_ok = 0;
@@ -30,6 +30,7 @@ static int
 spamd_param_init(spamd_address_container *spamd)
 {
 /* default spamd server weight, time and priority value */
+spamd->is_rspamd = FALSE;
 spamd->is_failed = FALSE;
 spamd->weight = SPAMD_WEIGHT;
 spamd->timeout = SPAMD_TIMEOUT;
@@ -94,6 +95,12 @@ if (Ustrncmp(param, "time=", 5) == 0)
   return 0; /* OK */
   }
 
+if (Ustrcmp(param, "variant=rspamd") == 0)
+  {
+  spamd->is_rspamd = TRUE;
+  return 0;
+  }
+
 if (Ustrncmp(param, "tmo=", 4) == 0)
   {
   int sec = readconf_readtime((s = param+4), '\0', FALSE);
@@ -361,15 +368,42 @@ start = time(NULL);
   }
 
 (void)fcntl(spamd_cctx.sock, F_SETFL, O_NONBLOCK);
-/* now we are connected to spamd on spamd_sock */
-
-(void)string_format(spamd_buffer,
-	sizeof(spamd_buffer),
-	"REPORT SPAMC/1.2\r\nUser: %s\r\nContent-length: %ld\r\n\r\n",
-	user_name,
-	mbox_size);
-/* send our request */
-wrote = send(spamd_cctx.sock, spamd_buffer, Ustrlen(spamd_buffer), 0);
+/* now we are connected to spamd on spamd_cctx.sock */
+if (sd->is_rspamd)
+  {
+  gstring * req_str;
+  const uschar * s;
+
+  req_str = string_append(NULL, 8,
+    "CHECK RSPAMC/1.3\r\nContent-length: ", string_sprintf("%lu\r\n", mbox_size),
+    "Queue-Id: ", message_id,
+    "\r\nFrom: <", sender_address,
+    ">\r\nRecipient-Number: ", string_sprintf("%d\r\n", recipients_count));
+
+  for (i = 0; i < recipients_count; i ++)
+    req_str = string_append(req_str, 3,
+      "Rcpt: <", recipients_list[i].address, ">\r\n");
+  if ((s = expand_string(US"$sender_helo_name")) && *s)
+    req_str = string_append(req_str, 3, "Helo: ", s, "\r\n");
+  if ((s = expand_string(US"$sender_host_name")) && *s)
+    req_str = string_append(req_str, 3, "Hostname: ", s, "\r\n");
+  if (sender_host_address)
+    req_str = string_append(req_str, 3, "IP: ", sender_host_address, "\r\n");
+  if ((s = expand_string(US"$authenticated_id")) && *s)
+    req_str = string_append(req_str, 3, "User: ", s, "\r\n");
+  req_str = string_catn(req_str, US"\r\n", 2);
+  wrote = send(spamd_cctx.sock, req_str->s, req_str->ptr, 0);
+  }
+else
+  {				/* spamassassin variant */
+  (void)string_format(spamd_buffer,
+	  sizeof(spamd_buffer),
+	  "REPORT SPAMC/1.2\r\nUser: %s\r\nContent-length: %ld\r\n\r\n",
+	  user_name,
+	  mbox_size);
+  /* send our request */
+  wrote = send(spamd_cctx.sock, spamd_buffer, Ustrlen(spamd_buffer), 0);
+  }
 
 if (wrote == -1)
   {
@@ -393,6 +427,7 @@ if (wrote == -1)
 pollfd.fd = spamd_cctx.sock;
 pollfd.events = POLLOUT;
 #endif
+(void)fcntl(spamd_cctx.sock, F_SETFL, O_NONBLOCK);
 do
   {
   read = fread(spamd_buffer,1,sizeof(spamd_buffer),mbox_file);
@@ -459,7 +494,8 @@ if (ferror(mbox_file))
 (void)fclose(mbox_file);
 
 /* we're done sending, close socket for writing */
-shutdown(spamd_cctx.sock, SHUT_WR);
+if (!sd->is_rspamd)
+  shutdown(spamd_cctx.sock,SHUT_WR);
 
 /* read spamd response using what's left of the timeout.  */
 memset(spamd_buffer, 0, sizeof(spamd_buffer));
@@ -483,6 +519,33 @@ if (i <= 0 && errno != 0)
 /* reading done */
 (void)close(spamd_cctx.sock);
 
+if (sd->is_rspamd)
+  {				/* rspamd variant of reply */
+  int r;
+  if (  (r = sscanf(CS spamd_buffer,
+	  "RSPAMD/%7s 0 EX_OK\r\nMetric: default; %7s %lf / %lf / %lf\r\n%n",
+	  spamd_version, spamd_short_result, &spamd_score, &spamd_threshold,
+	  &spamd_reject_score, &spamd_report_offset)) != 5
+     || spamd_report_offset >= offset		/* verify within buffer */
+     )
+    {
+    log_write(0, LOG_MAIN|LOG_PANIC,
+	      "%s cannot parse spamd %s, output: %d", loglabel, callout_address, r);
+    return DEFER;
+    }
+  /* now parse action */
+  p = &spamd_buffer[spamd_report_offset];
+
+  if (Ustrncmp(p, "Action: ", sizeof("Action: ") - 1) == 0)
+    {
+    p += sizeof("Action: ") - 1;
+    q = &spam_action_buffer[0];
+    while (*p && *p != '\r' && (q - spam_action_buffer) < sizeof(spam_action_buffer) - 1)
+      *q++ = *p++;
+    *q = '\0';
+    }
+  }
+else
   {				/* spamassassin */
   /* dig in the spamd output and put the report in a multiline header,
   if requested */
@@ -501,7 +564,8 @@ if (i <= 0 && errno != 0)
 	}
     }
 
-  spam_action_buffer = spamd_score >= spamd_threshold ? US"reject" : US"no action";
+  Ustrcpy(spam_action_buffer,
+    spamd_score >= spamd_threshold ? "reject" : "no action");
   }
 
 /* Create report. Since this is a multiline string,
diff --git a/src/src/spam.h b/src/src/spam.h
index 9f6b749cc..2fe73809e 100644
--- a/src/src/spam.h
+++ b/src/src/spam.h
@@ -27,6 +27,7 @@
 typedef struct spamd_address_container
 {
   uschar * hostspec;
+  int is_rspamd:1;
   int is_failed:1;
   unsigned int weight;
   unsigned int timeout;
diff --git a/test/src/server.c b/test/src/server.c
index 719350c15..d433ebe0e 100644
--- a/test/src/server.c
+++ b/test/src/server.c
@@ -519,6 +519,11 @@ s = script;
 
 for (count = 0; count < connection_count; count++)
   {
+  struct {
+    int left;
+    BOOL in_use;
+  } content_length = { 0, FALSE };
+
   alarm(timeout);
   if (port <= 0)
     {
@@ -729,6 +734,7 @@ for (count = 0; count < connection_count; count++)
 
 	alarm(timeout);
 	n = read(dup_accept_socket, CS buffer+offset, s->len - offset);
+	if (content_length.in_use) content_length.left -= n;
 	if (n == 0)
 	  {
 	  printf("%sxpected EOF read from client\n",
@@ -746,8 +752,9 @@ for (count = 0; count < connection_count; count++)
 	if (data) do
 	  {
 	  n = (read(dup_accept_socket, &c, 1) == 1 && c == '.');
+	  if (content_length.in_use) content_length.left--;
 	  while (c != '\n' && read(dup_accept_socket, &c, 1) == 1)
-	    ;
+            if (content_length.in_use) content_length.left--;
 	  } while (!n);
 	else if (memcmp(ss, buffer, n) != 0)
 	  {
@@ -770,7 +777,8 @@ for (count = 0; count < connection_count; count++)
 	    goto END_OFF;
 	    }
 	  alarm(0);
-	  n = (int)strlen(CS buffer);
+	  n = strlen(CS buffer);
+	  if (content_length.in_use) content_length.left -= (n - offset);
 	  while (n > 0 && isspace(buffer[n-1])) n--;
 	  buffer[n] = 0;
 	  printf("%s\n", buffer);
@@ -784,6 +792,11 @@ for (count = 0; count < connection_count; count++)
 	  break;
 	  }
 	}
+
+	if (sscanf(CCS buffer, "<Content-length: %d", &content_length.left))
+       	  content_length.in_use = TRUE;
+	if (content_length.in_use && content_length.left <= 0)
+	  shutdown(dup_accept_socket, SHUT_RD);
       }
     }