Add unit test for utf8 sanitization.

test/unit/CMakeLists.txt

@@ -1,23 +1,32 @@
-project(tawashi_unittest CXX)
+project(tawashi_unittest CXX C)
+
+find_package(GLIB 2.20 REQUIRED)
 
 set(CMAKE_CXX_STANDARD 14)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 
+set(CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG} -Wall -Wpedantic -Wconversion -Werror")
+set(CMAKE_C_FLAGS_RELEASE "${CMAKE_C_FLAGS_DEBUG} -Wall -Wpedantic -Wconversion -Werror")
+
 add_executable(${PROJECT_NAME}
 	check.cpp
 	fake_cgi_env.cpp
 	test_ini_file.cpp
 	test_settings_bag.cpp
 	test_index_response.cpp
+	test_invalid_utf8_post.cpp
+	../data/UTF-8-test.txt.c
 )
 
 target_include_directories(${PROJECT_NAME}
 	PRIVATE ${TAWASHI_SOURCE_ROOT}/lib/Catch/single_include
 	PRIVATE ${TAWASHI_GEN_INCLUDE_DIR}
+	PRIVATE ${GLIB_INCLUDE_DIRS}
 )
 target_link_libraries(${PROJECT_NAME}
 	PRIVATE tawashi_implem
 	PRIVATE duckhandy
+	PRIVATE ${GLIB_LIBRARIES}
 )
 
 add_test(

test/unit/test_invalid_utf8_post.cpp

@@ -0,0 +1,72 @@
+/* Copyright 2017, Michele Santullo
+ * This file is part of "tawashi".
+ *
+ * "tawashi" is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * "tawashi" is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with "tawashi".  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "catch.hpp"
+#include "cgi_post.hpp"
+#include "cgi_env.hpp"
+#include "sanitized_utf8.hpp"
+#include <vector>
+#include <string>
+#include <sstream>
+#include <utility>
+#include <iterator>
+#include <fstream>
+#include <ciso646>
+#include <glib.h>
+
+extern "C" {
+	extern const unsigned char UTF_8_test_txt[];
+	extern const unsigned int UTF_8_test_txt_len;
+} //extern C
+
+TEST_CASE ("Retrieve and sanitize invalid an invalid utf-8 text", "[utf8][security]") {
+	using tawashi::cgi::PostMapType;
+
+	auto content_length = std::string("CONTENT_LENGTH=") + std::to_string(UTF_8_test_txt_len);
+	const std::string invalid_text_prefix("invalid_text=");
+	std::string invalid_text;
+	invalid_text.reserve(invalid_text_prefix.size() + UTF_8_test_txt_len);
+	invalid_text = "invalid_text=";
+	std::copy(reinterpret_cast<const char*>(UTF_8_test_txt), reinterpret_cast<const char*>(UTF_8_test_txt) + UTF_8_test_txt_len, std::back_inserter(invalid_text));
+
+	std::istringstream iss;
+	iss >> std::noskipws;
+	iss.str(std::move(invalid_text));
+
+	const char* const fake_env[] = {
+		content_length.c_str(),
+		nullptr
+	};
+
+	tawashi::cgi::Env env(fake_env);
+	const PostMapType& post_data = read_post(iss, env);
+
+	CHECK(g_utf8_validate(post_data.at("invalid_text").data(), post_data.at("invalid_text").size(), nullptr));
+
+	//std::istringstream iss_expected;
+	//iss_expected >> std::noskipws;
+	//iss_expected.str(std::string(reinterpret_cast<const char*>(libreoffice_UTF_8_test_txt), libreoffice_UTF_8_test_txt_len));
+	//std::string expected_line;
+	//std::istringstream iss_obtained;
+	//iss_obtained >> std::noskipws;
+	//iss_obtained.str(post_data.at("invalid_text"));
+	//for (std::string line; std::getline(iss_obtained, line); ) {
+	//	std::getline(iss_expected, expected_line);
+	//	std::cout << '"' << line << "\n\"" << expected_line << "\"\n";
+	//	REQUIRE(line == expected_line);
+	//}
+}