1 #include "catch.hpp" 2 #include "internal/catch_xmlwriter.h" 3 4 #include <sstream> 5 encode(std::string const & str,Catch::XmlEncode::ForWhat forWhat=Catch::XmlEncode::ForTextNodes)6inline std::string encode( std::string const& str, Catch::XmlEncode::ForWhat forWhat = Catch::XmlEncode::ForTextNodes ) { 7 std::ostringstream oss; 8 oss << Catch::XmlEncode( str, forWhat ); 9 return oss.str(); 10 } 11 12 TEST_CASE( "XmlEncode", "[XML]" ) { 13 SECTION( "normal string" ) { 14 REQUIRE( encode( "normal string" ) == "normal string" ); 15 } 16 SECTION( "empty string" ) { 17 REQUIRE( encode( "" ) == "" ); 18 } 19 SECTION( "string with ampersand" ) { 20 REQUIRE( encode( "smith & jones" ) == "smith & jones" ); 21 } 22 SECTION( "string with less-than" ) { 23 REQUIRE( encode( "smith < jones" ) == "smith < jones" ); 24 } 25 SECTION( "string with greater-than" ) { 26 REQUIRE( encode( "smith > jones" ) == "smith > jones" ); 27 REQUIRE( encode( "smith ]]> jones" ) == "smith ]]> jones" ); 28 } 29 SECTION( "string with quotes" ) { 30 std::string stringWithQuotes = "don't \"quote\" me on that"; 31 REQUIRE( encode( stringWithQuotes ) == stringWithQuotes ); 32 REQUIRE( encode( stringWithQuotes, Catch::XmlEncode::ForAttributes ) == "don't "quote" me on that" ); 33 } 34 SECTION( "string with control char (1)" ) { 35 REQUIRE( encode( "[\x01]" ) == "[\\x01]" ); 36 } 37 SECTION( "string with control char (x7F)" ) { 38 REQUIRE( encode( "[\x7F]" ) == "[\\x7F]" ); 39 } 40 } 41 42 // Thanks to Peter Bindels (dascandy) for some of the tests 43 TEST_CASE("XmlEncode: UTF-8", "[XML][UTF-8]") { 44 SECTION("Valid utf-8 strings") { 45 CHECK(encode(u8"Here be ��") == u8"Here be ��"); 46 CHECK(encode(u8"šš") == u8"šš"); 47 48 CHECK(encode("\xDF\xBF") == "\xDF\xBF"); // 0x7FF 49 CHECK(encode("\xE0\xA0\x80") == "\xE0\xA0\x80"); // 0x800 50 CHECK(encode("\xED\x9F\xBF") == "\xED\x9F\xBF"); // 0xD7FF 51 CHECK(encode("\xEE\x80\x80") == "\xEE\x80\x80"); // 0xE000 52 CHECK(encode("\xEF\xBF\xBF") == "\xEF\xBF\xBF"); // 0xFFFF 53 CHECK(encode("\xF0\x90\x80\x80") == "\xF0\x90\x80\x80"); // 0x10000 54 CHECK(encode("\xF4\x8F\xBF\xBF") == "\xF4\x8F\xBF\xBF"); // 0x10FFFF 55 } 56 SECTION("Invalid utf-8 strings") { 57 SECTION("Various broken strings") { 58 CHECK(encode("Here \xFF be ��") == u8"Here \\xFF be ��"); 59 CHECK(encode("\xFF") == "\\xFF"); 60 CHECK(encode("\xC5\xC5\xA0") == u8"\\xC5Š"); 61 CHECK(encode("\xF4\x90\x80\x80") == u8"\\xF4\\x90\\x80\\x80"); // 0x110000 -- out of unicode range 62 } 63 64 SECTION("Overlong encodings") { 65 CHECK(encode("\xC0\x80") == u8"\\xC0\\x80"); // \0 66 CHECK(encode("\xF0\x80\x80\x80") == u8"\\xF0\\x80\\x80\\x80"); // Super-over-long \0 67 CHECK(encode("\xC1\xBF") == u8"\\xC1\\xBF"); // ASCII char as UTF-8 (0x7F) 68 CHECK(encode("\xE0\x9F\xBF") == u8"\\xE0\\x9F\\xBF"); // 0x7FF 69 CHECK(encode("\xF0\x8F\xBF\xBF") == u8"\\xF0\\x8F\\xBF\\xBF"); // 0xFFFF 70 } 71 72 // Note that we actually don't modify surrogate pairs, as we do not do strict checking 73 SECTION("Surrogate pairs") { 74 CHECK(encode("\xED\xA0\x80") == "\xED\xA0\x80"); // Invalid surrogate half 0xD800 75 CHECK(encode("\xED\xAF\xBF") == "\xED\xAF\xBF"); // Invalid surrogate half 0xDBFF 76 CHECK(encode("\xED\xB0\x80") == "\xED\xB0\x80"); // Invalid surrogate half 0xDC00 77 CHECK(encode("\xED\xBF\xBF") == "\xED\xBF\xBF"); // Invalid surrogate half 0xDFFF 78 } 79 80 SECTION("Invalid start byte") { 81 CHECK(encode("\x80") == u8"\\x80"); 82 CHECK(encode("\x81") == u8"\\x81"); 83 CHECK(encode("\xBC") == u8"\\xBC"); 84 CHECK(encode("\xBF") == u8"\\xBF"); 85 // Out of range 86 CHECK(encode("\xF5\x80\x80\x80") == u8"\\xF5\\x80\\x80\\x80"); 87 CHECK(encode("\xF6\x80\x80\x80") == u8"\\xF6\\x80\\x80\\x80"); 88 CHECK(encode("\xF7\x80\x80\x80") == u8"\\xF7\\x80\\x80\\x80"); 89 } 90 91 SECTION("Missing continuation byte(s)") { 92 // Missing first continuation byte 93 CHECK(encode("\xDE") == u8"\\xDE"); 94 CHECK(encode("\xDF") == u8"\\xDF"); 95 CHECK(encode("\xE0") == u8"\\xE0"); 96 CHECK(encode("\xEF") == u8"\\xEF"); 97 CHECK(encode("\xF0") == u8"\\xF0"); 98 CHECK(encode("\xF4") == u8"\\xF4"); 99 100 // Missing second continuation byte 101 CHECK(encode("\xE0\x80") == u8"\\xE0\\x80"); 102 CHECK(encode("\xE0\xBF") == u8"\\xE0\\xBF"); 103 CHECK(encode("\xE1\x80") == u8"\\xE1\\x80"); 104 CHECK(encode("\xF0\x80") == u8"\\xF0\\x80"); 105 CHECK(encode("\xF4\x80") == u8"\\xF4\\x80"); 106 107 // Missing third continuation byte 108 CHECK(encode("\xF0\x80\x80") == u8"\\xF0\\x80\\x80"); 109 CHECK(encode("\xF4\x80\x80") == u8"\\xF4\\x80\\x80"); 110 } 111 } 112 } 113