http: Heuristic around rejecting malformed HTTP/0.9 traffic

oss-fuzz generated "HTTP traffic" containing 250k+ sequences of "T<space>\r\r"
which Zeek then logged as individual HTTP requests. Add a heuristic to bail
on such request lines. It's a bit specific to the test case, but should work.

There are more issues around handling HTTP/0.9, e.g. triggering
"not a http reply line" when HTTP/0.9 never had such a thing, but
I don't think that's worth fixing up.

Fixes #119

src/analyzer/protocol/http/HTTP.cc

@@ -1230,6 +1230,18 @@ int HTTP_Analyzer::HTTP_RequestLine(const char* line, const char* end_of_line)
 		return -1;
 		}
 
+	// If we determined HTTP/0.9 (no HTTP/ in the request line), assert that
+	// minimally we have an URI and a 3 character method (HTTP 0.9 only
+	// supports GET). If that doesn't hold, probably not HTTP or very stange.
+	if ( request_version.major == 0 && request_version.minor == 9 )
+		{
+		bool maybe_get_method = (end_of_method - line) >= 3;
+		bool has_uri = request_URI && request_URI->Len() > 0;
+
+		if ( ! maybe_get_method || ! has_uri )
+			goto error;
+		}
+
 	request_method = make_intrusive<StringVal>(end_of_method - line, line);
 
 	Conn()->Match(zeek::detail::Rule::HTTP_REQUEST,

testing/btest/Baseline/scripts.base.protocols.http.curl-http-09/http.log

@@ -0,0 +1,11 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.
+#separator \x09
+#set_separator	,
+#empty_field	(empty)
+#unset_field	-
+#path	http
+#open XXXX-XX-XX-XX-XX-XX
+#fields	ts	uid	id.orig_h	id.orig_p	id.resp_h	id.resp_p	trans_depth	method	host	uri	referrer	version	user_agent	origin	request_body_len	response_body_len	status_code	status_msg	info_code	info_msg	tags	username	password	proxied	orig_fuids	orig_filenames	orig_mime_types	resp_fuids	resp_filenames	resp_mime_types
+#types	time	string	addr	port	addr	port	count	string	string	string	string	string	string	string	count	count	count	string	count	string	set[enum]	string	string	set[string]	vector[string]	vector[string]	vector[string]	vector[string]	vector[string]	vector[string]
+XXXXXXXXXX.XXXXXX	CHhAvVGS1DHFjwGM9	127.0.0.1	49404	127.0.0.1	80	1	GET	localhost	/zeek.html	-	-	curl/7.74.0	-	0	0	-	-	-	-	(empty)	-	-	-	-	-	-	-	-	-
+#close XXXX-XX-XX-XX-XX-XX

testing/btest/Baseline/scripts.base.protocols.http.http-09/http.log

@@ -0,0 +1,12 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.
+#separator \x09
+#set_separator	,
+#empty_field	(empty)
+#unset_field	-
+#path	http
+#open XXXX-XX-XX-XX-XX-XX
+#fields	ts	uid	id.orig_h	id.orig_p	id.resp_h	id.resp_p	trans_depth	method	host	uri	referrer	version	user_agent	origin	request_body_len	response_body_len	status_code	status_msg	info_code	info_msg	tags	username	password	proxied	orig_fuids	orig_filenames	orig_mime_types	resp_fuids	resp_filenames	resp_mime_types
+#types	time	string	addr	port	addr	port	count	string	string	string	string	string	string	string	count	count	count	string	count	string	set[enum]	string	string	set[string]	vector[string]	vector[string]	vector[string]	vector[string]	vector[string]	vector[string]
+XXXXXXXXXX.XXXXXX	CHhAvVGS1DHFjwGM9	127.0.0.1	42960	127.0.0.1	80	1	GET	-	/zeek.html	-	-	-	-	0	0	-	-	-	-	(empty)	-	-	-	-	-	-	-	-	-
+XXXXXXXXXX.XXXXXX	ClEkJM2Vm5giqnMf4h	127.0.0.1	42964	127.0.0.1	80	1	POST	-	/zeek.html	-	-	-	-	0	0	-	-	-	-	(empty)	-	-	-	-	-	-	-	-	-
+#close XXXX-XX-XX-XX-XX-XX

testing/btest/Baseline/scripts.base.protocols.http.http-09/weird.log

@@ -0,0 +1,13 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.
+#separator \x09
+#set_separator	,
+#empty_field	(empty)
+#unset_field	-
+#path	weird
+#open XXXX-XX-XX-XX-XX-XX
+#fields	ts	uid	id.orig_h	id.orig_p	id.resp_h	id.resp_p	name	addl	notice	peer	source
+#types	time	string	addr	port	addr	port	string	string	bool	string	string
+XXXXXXXXXX.XXXXXX	C4J4Th3PJpwUYZZ6gc	127.0.0.1	42968	127.0.0.1	80	bad_HTTP_request	-	F	zeek	HTTP
+XXXXXXXXXX.XXXXXX	CtPZjS20MLrsMUOJi2	127.0.0.1	42970	127.0.0.1	80	bad_HTTP_request	-	F	zeek	HTTP
+XXXXXXXXXX.XXXXXX	CUM0KZ3MLUfNB0cl11	127.0.0.1	42972	127.0.0.1	80	bad_HTTP_request	-	F	zeek	HTTP
+#close XXXX-XX-XX-XX-XX-XX

testing/btest/scripts/base/protocols/http/curl-http-09.zeek

@@ -0,0 +1,7 @@
+# @TEST-DOC: curl --http0.9 to accept the headerless response.
+# @TEST-EXEC: zeek -b -Cr $TRACES/http/curl_http_09.pcap %INPUT
+# @TEST-EXEC: btest-diff http.log
+# @TEST-EXEC: test ! -f weird.log
+
+@load base/frameworks/notice/weird
+@load base/protocols/http

testing/btest/scripts/base/protocols/http/http-09.zeek

@@ -0,0 +1,7 @@
+# @TEST-DOC: Artificially created PCAP with one proper HTTP 0.9 request/response and a few invalid ones.
+# @TEST-EXEC: zeek -b -Cr $TRACES/http/http_09.pcap %INPUT
+# @TEST-EXEC: btest-diff http.log
+# @TEST-EXEC: btest-diff weird.log
+
+@load base/frameworks/notice/weird
+@load base/protocols/http