fix(libsinsp): adjust g_invalidchar to allow emojis, cyrillic, chines…

…e etc

Signed-off-by: Melissa Kilby <[email protected]>

userspace/libsinsp/test/sinsp_utils.ut.cpp

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0
 /*
-Copyright (C) 2023 The Falco Authors.
+Copyright (C) 2023 The  Authors.
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
@@ -123,4 +123,19 @@ TEST(sinsp_utils_test, concatenate_paths)
 	path2 = "////app";
 	res = sinsp_utils::concatenate_paths(path1, path2);
 	EXPECT_EQ("/app", res);
+
+	path1 = "/root/";
+	path2 = "../😉";
+	res = sinsp_utils::concatenate_paths(path1, path2);
+	EXPECT_EQ("/😉", res);
+
+	path1 = "/root/";
+	path2 = "../诶比西";
+	res = sinsp_utils::concatenate_paths(path1, path2);
+	EXPECT_EQ("/诶比西", res);
+
+	path1 = "/root/";
+	path2 = "../АБВЙЛж";
+	res = sinsp_utils::concatenate_paths(path1, path2);
+	EXPECT_EQ("/АБВЙЛж", res);
 }

userspace/libsinsp/utils.h

@@ -158,15 +158,12 @@ class sinsp_utils
 
 struct g_invalidchar
 {
-    bool operator()(char c) const
-    {
-	    if(c < -1)
-	    {
-		    return true;
-	    }
-
-	    return !isprint((unsigned)c);
-    }
+	bool operator()(char c) const
+	{
+		// Exclude all non-printable characters and control characters while
+		// including a wide range of languages (emojis, cyrillic, chinese etc)
+		return !(isprint((unsigned)c) || (c < 0));
+	}
 };
 
 inline void sanitize_string(std::string &str)