Merge remote-tracking branch 'origin/topic/timw/636-config-commas'

* origin/topic/timw/636-config-commas:
  GH-636: Fix regex to handle commas at the end of config parser lines
  Convert config framework to use std::regex

CHANGES

@@ -1,3 +1,9 @@
+5.1.0-dev.265 | 2022-07-18 08:54:30 -0700
+
+  * GH-636: Fix regex to handle commas at the end of config parser lines (Tim Wojtulewicz, Corelight)
+
+  * Convert config framework to use std::regex (Tim Wojtulewicz, Corelight)
+
 5.1.0-dev.261 | 2022-07-14 15:46:29 -0700
 
   * Management framework: fix an agent boot-time race condition plus minor tweaks (Christian Kreibich, Corelight)

VERSION

@@ -1 +1 @@
-5.1.0-dev.261
+5.1.0-dev.265

src/input/readers/config/Config.cc

@@ -2,11 +2,11 @@
 
 #include "zeek/input/readers/config/Config.h"
 
-#include <regex.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <cerrno>
+#include <regex>
 #include <sstream>
 #include <unordered_set>
 
@@ -181,28 +181,34 @@ bool Config::DoUpdate()
 		unseen_options.insert(i.first);
 		}
 
-	regex_t re;
-	if ( regcomp(&re, "^([^[:blank:]]+)[[:blank:]]+([^[:blank:]](.*[^[:blank:]])?)?[[:blank:]]*$",
-	             REG_EXTENDED) )
+	std::regex re;
+	try
 		{
-		Error(Fmt("Failed to compile regex."));
+		std::string re_str = util::fmt(
+			"^([^[:blank:]]+)[[:blank:]]+([^[:blank:]](.*[^[:blank:]%c])?)?[[:blank:]%c]*$",
+			set_separator[0], set_separator[0]);
+		re.assign(re_str, std::regex::extended);
+		}
+	catch ( const std::regex_error& e )
+		{
+		Error(Fmt("Failed to compile regex: %s", e.what()));
 		return true;
 		}
 
 	while ( GetLine(line) )
 		{
-		regmatch_t match[3];
-		if ( regexec(&re, line.c_str(), 3, match, 0) )
+		std::smatch match;
+		if ( ! std::regex_match(line, match, re) )
 			{
 			Warning(
 				Fmt("Could not parse '%s'; line has invalid format. Ignoring line.", line.c_str()));
 			continue;
 			}
 
-		std::string key = line.substr(match[1].rm_so, match[1].rm_eo - match[1].rm_so);
+		std::string key = match[1].str();
 		std::string value;
-		if ( match[2].rm_so > 0 )
-			value = line.substr(match[2].rm_so, match[2].rm_eo - match[2].rm_so);
+		if ( match.size() > 2 )
+			value = match[2].str();
 
 		auto typeit = option_types.find(key);
 		if ( typeit == option_types.end() )
@@ -283,8 +289,6 @@ bool Config::DoUpdate()
 			}
 		}
 
-	regfree(&re);
-
 	if ( Info().mode != MODE_STREAM )
 		EndCurrentSend();
 

testing/btest/Baseline/scripts.base.frameworks.config.basic/zeek.config.log

@@ -23,7 +23,8 @@ XXXXXXXXXX.XXXXXX	testsub	2607:f8b0:4001::/48	2607:f8b0:4002::/48	../configfile
 XXXXXXXXXX.XXXXXX	testinterval	1.0 sec	1.0 min	../configfile
 XXXXXXXXXX.XXXXXX	testtime	0.0	XXXXXXXXXX.XXXXXX	../configfile
 XXXXXXXXXX.XXXXXX	test_set	(empty)	a,d,b,c,erdbeerschnitzel	../configfile
+XXXXXXXXXX.XXXXXX	test_set	a,d,b,c,erdbeerschnitzel	a,c,b	../configfile
 XXXXXXXXXX.XXXXXX	test_vector	(empty)	1,2,3,4,5,6	../configfile
-XXXXXXXXXX.XXXXXX	test_set	a,d,b,c,erdbeerschnitzel	(empty)	../configfile
+XXXXXXXXXX.XXXXXX	test_set	a,c,b	(empty)	../configfile
 XXXXXXXXXX.XXXXXX	test_set	(empty)	\x2d	../configfile
 #close XXXX-XX-XX-XX-XX-XX

testing/btest/scripts/base/frameworks/config/basic.zeek

@@ -27,6 +27,7 @@ testsub [2607:f8b0:4002:801::]/48
 testinterval 60
 testtime 1507321987
 test_set a,b,c,d,erdbeerschnitzel
+test_set a,b,c,
 test_vector 1,2,3,4,5,6
 test_set 
 test_set -