ferencd@0: //
ferencd@0: // VMime library (http://www.vmime.org)
ferencd@0: // Copyright (C) 2002-2013 Vincent Richard <vincent@vmime.org>
ferencd@0: //
ferencd@0: // This program is free software; you can redistribute it and/or
ferencd@0: // modify it under the terms of the GNU General Public License as
ferencd@0: // published by the Free Software Foundation; either version 3 of
ferencd@0: // the License, or (at your option) any later version.
ferencd@0: //
ferencd@0: // This program is distributed in the hope that it will be useful,
ferencd@0: // but WITHOUT ANY WARRANTY; without even the implied warranty of
ferencd@0: // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
ferencd@0: // General Public License for more details.
ferencd@0: //
ferencd@0: // You should have received a copy of the GNU General Public License along
ferencd@0: // with this program; if not, write to the Free Software Foundation, Inc.,
ferencd@0: // 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
ferencd@0: //
ferencd@0: // Linking this library statically or dynamically with other modules is making
ferencd@0: // a combined work based on this library.  Thus, the terms and conditions of
ferencd@0: // the GNU General Public License cover the whole combination.
ferencd@0: //
ferencd@0: 
ferencd@0: #include "tests/testUtils.hpp"
ferencd@0: 
ferencd@0: #include <locale>
ferencd@0: #include <clocale>
ferencd@0: 
ferencd@0: 
ferencd@0: VMIME_TEST_SUITE_BEGIN(textTest)
ferencd@0: 
ferencd@0: 	VMIME_TEST_LIST_BEGIN
ferencd@0: 		VMIME_TEST(testConstructors)
ferencd@0: 		VMIME_TEST(testCopy)
ferencd@0: 		VMIME_TEST(testNewFromString)
ferencd@0: 		VMIME_TEST(testDisplayForm)
ferencd@0: 		VMIME_TEST(testParse)
ferencd@0: 		VMIME_TEST(testGenerate)
ferencd@0: 
ferencd@0: 		VMIME_TEST(testWordConstructors)
ferencd@0: 		VMIME_TEST(testWordParse)
ferencd@0: 		VMIME_TEST(testWordGenerate)
ferencd@0: 		VMIME_TEST(testWordGenerateSpace)
ferencd@0: 		VMIME_TEST(testWordGenerateSpace2)
ferencd@0: 		VMIME_TEST(testWordGenerateMultiBytes)
ferencd@0: 		VMIME_TEST(testWordGenerateQuote)
ferencd@0: 		VMIME_TEST(testWordGenerateSpecialCharsets)
ferencd@0: 		VMIME_TEST(testWordGenerateSpecials)
ferencd@0: 
ferencd@0: 		VMIME_TEST(testWhitespace)
ferencd@0: 		VMIME_TEST(testWhitespaceMBox)
ferencd@0: 
ferencd@0: 		VMIME_TEST(testFoldingAscii)
ferencd@0: 		VMIME_TEST(testForcedNonEncoding)
ferencd@0: 
ferencd@0: 		VMIME_TEST(testBugFix20110511)
ferencd@0: 
ferencd@0: 		VMIME_TEST(testInternationalizedEmail_specialChars)
ferencd@0: 		VMIME_TEST(testInternationalizedEmail_UTF8)
ferencd@0: 		VMIME_TEST(testInternationalizedEmail_nonUTF8)
ferencd@0: 		VMIME_TEST(testInternationalizedEmail_folding)
ferencd@0: 	VMIME_TEST_LIST_END
ferencd@0: 
ferencd@0: 
ferencd@0: 	static const vmime::string getDisplayText(const vmime::text& t)
ferencd@0: 	{
ferencd@0: 		return t.getWholeBuffer();
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	static const vmime::string cleanGeneratedWords(const std::string& str)
ferencd@0: 	{
ferencd@0: 		std::istringstream iss(str);
ferencd@0: 
ferencd@0: 		std::string res;
ferencd@0: 		std::string x;
ferencd@0: 
ferencd@0: 		while (std::getline(iss, x))
ferencd@0: 			res += vmime::utility::stringUtils::trim(x);
ferencd@0: 
ferencd@0: 		return res;
ferencd@0: 	}
ferencd@0: 
ferencd@0: 
ferencd@0: 	void setUp()
ferencd@0: 	{
ferencd@0: 		// Set the global C and C++ locale to the user-configured locale.
ferencd@0: 		// The locale should use UTF-8 encoding for these tests to run successfully.
ferencd@0: 		try
ferencd@0: 		{
ferencd@0: 			std::locale::global(std::locale(""));
ferencd@0: 		}
ferencd@0: 		catch (std::exception &)
ferencd@0: 		{
ferencd@0: 			std::setlocale(LC_ALL, "");
ferencd@0: 		}
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void tearDown()
ferencd@0: 	{
ferencd@0: 		// Restore default locale
ferencd@0: 		std::locale::global(std::locale("C"));
ferencd@0: 	}
ferencd@0: 
ferencd@0: 
ferencd@0: 	void testConstructors()
ferencd@0: 	{
ferencd@0: 		vmime::text t1;
ferencd@0: 
ferencd@0: 		VASSERT_EQ("1.1", 0, t1.getWordCount());
ferencd@0: 
ferencd@0: 		vmime::text t2("Test\xa9\xc3");
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2.1", 1, t2.getWordCount());
ferencd@0: 		VASSERT_EQ("2.2", "Test\xa9\xc3", t2.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("2.3", vmime::charset::getLocalCharset(), t2.getWordAt(0)->getCharset());
ferencd@0: 
ferencd@0: 		vmime::text t3("Test\xa9\xc3", vmime::charset(vmime::charsets::ISO8859_13));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("3.1", 1, t3.getWordCount());
ferencd@0: 		VASSERT_EQ("3.2", "Test\xa9\xc3", t3.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("3.3", vmime::charset(vmime::charsets::ISO8859_13), t3.getWordAt(0)->getCharset());
ferencd@0: 
ferencd@0: 		vmime::word w1("Test", vmime::charset(vmime::charsets::UTF_8));
ferencd@0: 		vmime::text t4(w1);
ferencd@0: 
ferencd@0: 		VASSERT_EQ("4.1", 1, t4.getWordCount());
ferencd@0: 		VASSERT_EQ("4.2", w1.getBuffer(), t4.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("4.3", w1.getCharset(), t4.getWordAt(0)->getCharset());
ferencd@0: 
ferencd@0: 		vmime::word w2("Other", vmime::charset(vmime::charsets::US_ASCII));
ferencd@0: 		t4.appendWord(vmime::make_shared <vmime::word>(w2));
ferencd@0: 
ferencd@0: 		vmime::text t5(t4);
ferencd@0: 
ferencd@0: 		VASSERT_EQ("5.1", 2, t5.getWordCount());
ferencd@0: 		VASSERT_EQ("5.2", w1.getBuffer(), t5.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("5.3", w1.getCharset(), t5.getWordAt(0)->getCharset());
ferencd@0: 		VASSERT_EQ("5.4", w2.getBuffer(), t5.getWordAt(1)->getBuffer());
ferencd@0: 		VASSERT_EQ("5.5", w2.getCharset(), t5.getWordAt(1)->getCharset());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testCopy()
ferencd@0: 	{
ferencd@0: 		vmime::text t1("Test: \xa9\xc3");
ferencd@0: 
ferencd@0: 		VASSERT("operator==", t1 == t1);
ferencd@0: 		VASSERT("clone", *vmime::clone(t1) == t1);
ferencd@0: 
ferencd@0: 		vmime::text t2;
ferencd@0: 		t2.copyFrom(t1);
ferencd@0: 
ferencd@0: 		VASSERT("copyFrom", t1 == t2);
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testNewFromString()
ferencd@0: 	{
ferencd@0: 		vmime::string s1 = "only ASCII characters";
ferencd@0: 		vmime::charset c1("test");
ferencd@0: 		vmime::text t1;
ferencd@0: 
ferencd@0: 		t1.createFromString(s1, c1);
ferencd@0: 
ferencd@0: 		VASSERT_EQ("1.1", 1, t1.getWordCount());
ferencd@0: 		VASSERT_EQ("1.2", s1, t1.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("1.3", vmime::charset(vmime::charsets::US_ASCII), t1.getWordAt(0)->getCharset());
ferencd@0: 
ferencd@0: 		vmime::string s2_1 = "some ASCII characters and special chars: ";
ferencd@0: 		vmime::string s2_2 = "\xf1\xf2\xf3\xf4 ";
ferencd@0: 		vmime::string s2_3 = "and then more ASCII chars.";
ferencd@0: 		vmime::string s2 = s2_1 + s2_2 + s2_3;
ferencd@0: 		vmime::charset c2("test");
ferencd@0: 		vmime::text t2;
ferencd@0: 
ferencd@0: 		t2.createFromString(s2, c2);
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2.1", 3, t2.getWordCount());
ferencd@0: 		VASSERT_EQ("2.2", "some ASCII characters and special chars: ", t2.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("2.3", vmime::charset(vmime::charsets::US_ASCII), t2.getWordAt(0)->getCharset());
ferencd@0: 		VASSERT_EQ("2.4", "\xf1\xf2\xf3\xf4", t2.getWordAt(1)->getBuffer());
ferencd@0: 		VASSERT_EQ("2.5", c2, t2.getWordAt(1)->getCharset());
ferencd@0: 		VASSERT_EQ("2.6", "and then more ASCII chars.", t2.getWordAt(2)->getBuffer());
ferencd@0: 		VASSERT_EQ("2.7", vmime::charset(vmime::charsets::US_ASCII), t2.getWordAt(2)->getCharset());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	static const vmime::string parseText(const vmime::string& buffer)
ferencd@0: 	{
ferencd@0: 		vmime::text t;
ferencd@0: 		t.parse(buffer);
ferencd@0: 
ferencd@0: 		std::ostringstream oss;
ferencd@0: 		oss << t;
ferencd@0: 
ferencd@0: 		return (oss.str());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testParse()
ferencd@0: 	{
ferencd@0: 		// From RFC-2047
ferencd@0: 		VASSERT_EQ("1", "[text: [[word: charset=US-ASCII, buffer=Keith Moore]]]",
ferencd@0: 			parseText("=?US-ASCII?Q?Keith_Moore?="));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2", "[text: [[word: charset=ISO-8859-1, buffer=Keld J\xf8rn Simonsen]]]",
ferencd@0: 			parseText("=?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?="));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("3", "[text: [[word: charset=ISO-8859-1, buffer=Andr\xe9]," \
ferencd@0: 			                 "[word: charset=us-ascii, buffer= Pirard]]]",
ferencd@0: 			parseText("=?ISO-8859-1?Q?Andr=E9?= Pirard"));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("4", "[text: [[word: charset=ISO-8859-1, buffer=If you can read this yo]," \
ferencd@0: 			                 "[word: charset=ISO-8859-2, buffer=u understand the example.]]]",
ferencd@0: 			parseText("=?ISO-8859-1?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?=\r\n " \
ferencd@0: 				"=?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?="));
ferencd@0: 
ferencd@0: 		// Bugfix: in "=?charset?q?=XX=YY?=", the "?=" finish
ferencd@0: 		// sequence was not correctly found (should be the one
ferencd@0: 		// after '=YY' and not the one after '?q').
ferencd@0: 		VASSERT_EQ("5", "[text: [[word: charset=abc, buffer=\xe9\xe9]]]",
ferencd@0: 			parseText("=?abc?q?=E9=E9?="));
ferencd@0: 
ferencd@0: 		// Question marks (?) in the middle of the string
ferencd@0: 		VASSERT_EQ("6", "[text: [[word: charset=iso-8859-1, buffer=Know wh\xe4t? It works!]]]",
ferencd@0: 			parseText("=?iso-8859-1?Q?Know_wh=E4t?_It_works!?="));
ferencd@0: 
ferencd@0: 		// With language specifier
ferencd@0: 		VASSERT_EQ("7", "[text: [[word: charset=US-ASCII, buffer=Keith Moore, lang=EN]]]",
ferencd@0: 			parseText("=?US-ASCII*EN?Q?Keith_Moore?="));
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testGenerate()
ferencd@0: 	{
ferencd@0: 		// TODO
ferencd@0: 
ferencd@0: 		// With language specifier
ferencd@0: 		vmime::word wlang1("Émeline", vmime::charset("UTF-8"), "FR");
ferencd@0: 		VASSERT_EQ("lang1", "=?UTF-8*FR?Q?=C3=89meline?=", wlang1.generate());
ferencd@0: 
ferencd@0: 		vmime::word wlang2("Keith Moore", vmime::charset("US-ASCII"), "EN");
ferencd@0: 		VASSERT_EQ("lang2", "=?US-ASCII*EN?Q?Keith_Moore?=", wlang2.generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testDisplayForm()
ferencd@0: 	{
ferencd@0: #define DISPLAY_FORM(x) getDisplayText(*vmime::text::decodeAndUnfold(x))
ferencd@0: 
ferencd@0: 		// From RFC-2047
ferencd@0: 		VASSERT_EQ("1", "a", DISPLAY_FORM("=?ISO-8859-1?Q?a?="));
ferencd@0: 		VASSERT_EQ("2", "a b", DISPLAY_FORM("=?ISO-8859-1?Q?a?= b"));
ferencd@0: 		VASSERT_EQ("3", "ab", DISPLAY_FORM("=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?="));
ferencd@0: 		VASSERT_EQ("4", "ab", DISPLAY_FORM("=?ISO-8859-1?Q?a?= \t  =?ISO-8859-1?Q?b?="));
ferencd@0: 		VASSERT_EQ("5", "ab", DISPLAY_FORM("=?ISO-8859-1?Q?a?= \r\n  \t =?ISO-8859-1?Q?b?="));
ferencd@0: 		VASSERT_EQ("6", "a b", DISPLAY_FORM("=?ISO-8859-1?Q?a_b?="));
ferencd@0: 		VASSERT_EQ("7", "a b", DISPLAY_FORM("=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?="));
ferencd@0: 
ferencd@0: 		// Some more tests...
ferencd@0: 		VASSERT_EQ("8", "a b", DISPLAY_FORM(" a =?ISO-8859-1?Q?b?=  "));
ferencd@0: 		VASSERT_EQ("9", "a b  ", DISPLAY_FORM(" \t  =?ISO-8859-1?Q?a?= b  "));
ferencd@0: 		VASSERT_EQ("10", "a b", DISPLAY_FORM("  a\r\n\t  b"));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("11", "a b c", DISPLAY_FORM("a =?ISO-8859-1?Q?b?= c"));
ferencd@0: 		VASSERT_EQ("12", "a b c ", DISPLAY_FORM("a =?ISO-8859-1?Q?b?= c "));
ferencd@0: 		VASSERT_EQ("13", "a b c ", DISPLAY_FORM(" a =?ISO-8859-1?Q?b?= c "));
ferencd@0: 		VASSERT_EQ("14", "a b c d", DISPLAY_FORM("a =?ISO-8859-1?Q?b?= c =?ISO-8859-1?Q?d?= "));
ferencd@0: 		VASSERT_EQ("15", "a b c d e", DISPLAY_FORM("a =?ISO-8859-1?Q?b?= c =?ISO-8859-1?Q?d?= e"));
ferencd@0: 
ferencd@0: 		// Whitespaces and multiline
ferencd@0: 		VASSERT_EQ("16", "a b c d e", DISPLAY_FORM("=?ISO-8859-1?Q?a_b_?=c\n\t=?ISO-8859-1?Q?d_?=e"));
ferencd@0: 
ferencd@0: #undef DISPLAY_FORM
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordConstructors()
ferencd@0: 	{
ferencd@0: 		VASSERT_EQ("1.1", vmime::charset::getLocalCharset(), vmime::word().getCharset());
ferencd@0: 		VASSERT_EQ("1.2", "", vmime::word().getBuffer());
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2.1", vmime::charset::getLocalCharset(), vmime::word("foo").getCharset());
ferencd@0: 		VASSERT_EQ("2.2", "foo", vmime::word("foo").getBuffer());
ferencd@0: 
ferencd@0: 		VASSERT_EQ("3.1", "bar", vmime::word("foo", vmime::charset("bar")).getCharset().getName());
ferencd@0: 		VASSERT_EQ("3.2", "foo", vmime::word("foo", vmime::charset("bar")).getBuffer());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordParse()
ferencd@0: 	{
ferencd@0: 		// Simple encoded word
ferencd@0: 		vmime::word w1;
ferencd@0: 		w1.parse("=?foo?q?bar=E9 baz?=");
ferencd@0: 
ferencd@0: 		VASSERT_EQ("1.1", "foo", w1.getCharset().getName());
ferencd@0: 		VASSERT_EQ("1.2", "bar\xe9 baz", w1.getBuffer());
ferencd@0: 
ferencd@0: 		// Unencoded text
ferencd@0: 		vmime::word w2;
ferencd@0: 		w2.parse("  foo bar \tbaz...");
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2.1", vmime::charset(vmime::charsets::US_ASCII), w2.getCharset());
ferencd@0: 		VASSERT_EQ("2.2", "  foo bar \tbaz...", w2.getBuffer());
ferencd@0: 
ferencd@0: 		// Malformed word
ferencd@0: 		vmime::word w3;
ferencd@0: 		w3.parse("=?foo bar");
ferencd@0: 
ferencd@0: 		VASSERT_EQ("3.1", vmime::charset(vmime::charsets::US_ASCII), w3.getCharset());
ferencd@0: 		VASSERT_EQ("3.2", "=?foo bar", w3.getBuffer());
ferencd@0: 
ferencd@0: 		// Unknown encoding
ferencd@0: 		vmime::word w4;
ferencd@0: 		w4.parse("=?whatever?not_q_or_b?whatever?=");
ferencd@0: 
ferencd@0: 		VASSERT_EQ("4.1", vmime::charset(vmime::charsets::US_ASCII), w4.getCharset());
ferencd@0: 		VASSERT_EQ("4.2", "=?whatever?not_q_or_b?whatever?=", w4.getBuffer());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordGenerate()
ferencd@0: 	{
ferencd@0: 		VASSERT_EQ("1", "=?foo?Q?bar=E9_baz?=",
ferencd@0: 			vmime::word("bar\xe9 baz", vmime::charset("foo")).generate());
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2", "=?foo?B?8fLz9PU=?=",
ferencd@0: 			vmime::word("\xf1\xf2\xf3\xf4\xf5", vmime::charset("foo")).generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordGenerateSpace()
ferencd@0: 	{
ferencd@0: 		// No white-space between an unencoded word and a encoded one
ferencd@0: 		VASSERT_EQ("1", "Bonjour =?utf-8?Q?Fran=C3=A7ois?=",
ferencd@0: 			vmime::text::newFromString("Bonjour Fran\xc3\xa7ois",
ferencd@0: 				vmime::charset("utf-8"))->generate());
ferencd@0: 
ferencd@0: 		// White-space between two encoded words
ferencd@0: 		vmime::text txt;
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>("\xc3\x89t\xc3\xa9", "utf-8"));
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>("Fran\xc3\xa7ois", "utf-8"));
ferencd@0: 
ferencd@0: 		const vmime::string decoded = "\xc3\x89t\xc3\xa9""Fran\xc3\xa7ois";
ferencd@0: 		const vmime::string encoded = "=?utf-8?B?w4l0w6k=?= =?utf-8?Q?Fran=C3=A7ois?=";
ferencd@0: 
ferencd@0: 		// -- test encoding
ferencd@0: 		VASSERT_EQ("2", encoded, txt.generate());
ferencd@0: 
ferencd@0: 		// -- ensure no space is added when decoding
ferencd@0: 		vmime::text txt2;
ferencd@0: 		txt2.parse(encoded, 0, encoded.length());
ferencd@0: 
ferencd@0: 		VASSERT_EQ("3", decoded, txt2.getWholeBuffer());
ferencd@0: 
ferencd@0: 		// -- test rencoding
ferencd@0: 		VASSERT_EQ("4", encoded, txt2.generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordGenerateSpace2()
ferencd@0: 	{
ferencd@0: 		// White-space between two encoded words (#2)
ferencd@0: 		vmime::text txt;
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>("Facture ", "utf-8"));
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>("\xc3\xa0", "utf-8"));
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>(" envoyer ", "utf-8"));
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>("\xc3\xa0", "utf-8"));
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>(" Martine", "utf-8"));
ferencd@0: 
ferencd@0: 		const vmime::string decoded = "Facture ""\xc3\xa0"" envoyer ""\xc3\xa0"" Martine";
ferencd@0: 		const vmime::string encoded = "Facture =?utf-8?B?w6A=?= envoyer =?utf-8?B?w6A=?= Martine";
ferencd@0: 
ferencd@0: 		// -- test encoding
ferencd@0: 		VASSERT_EQ("1", encoded, txt.generate());
ferencd@0: 
ferencd@0: 		// -- ensure no space is added when decoding
ferencd@0: 		vmime::text txt2;
ferencd@0: 		txt2.parse(encoded, 0, encoded.length());
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2", decoded, txt2.getWholeBuffer());
ferencd@0: 
ferencd@0: 		// -- test rencoding
ferencd@0: 		VASSERT_EQ("3", encoded, txt2.generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordGenerateMultiBytes()
ferencd@0: 	{
ferencd@0: 		// Ensure we don't encode a non-integral number of characters
ferencd@0: 		VASSERT_EQ("1", "=?utf-8?Q?aaa?==?utf-8?Q?=C3=A9?==?utf-8?Q?zzz?=",
ferencd@0: 			cleanGeneratedWords(vmime::word("aaa\xc3\xa9zzz", vmime::charset("utf-8")).generate(16)));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2", "=?utf-8?Q?aaa=C3=A9?==?utf-8?Q?zzz?=",
ferencd@0: 			cleanGeneratedWords(vmime::word("aaa\xc3\xa9zzz", vmime::charset("utf-8")).generate(17)));
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordGenerateQuote()
ferencd@0: 	{
ferencd@0: 		std::string str;
ferencd@0: 		vmime::utility::outputStreamStringAdapter os(str);
ferencd@0: 
ferencd@0: 		vmime::generationContext ctx;
ferencd@0: 		ctx.setMaxLineLength(1000);
ferencd@0: 
ferencd@0: 		// ASCII-only text is quotable
ferencd@0: 		str.clear();
ferencd@0: 		vmime::word("Quoted text").generate(ctx, os, 0, NULL, vmime::text::QUOTE_IF_POSSIBLE, NULL);
ferencd@0: 		VASSERT_EQ("1", "\"Quoted text\"", cleanGeneratedWords(str));
ferencd@0: 
ferencd@0: 		// Text with CR/LF is not quotable
ferencd@0: 		str.clear();
ferencd@0: 		vmime::word("Non-quotable\ntext", "us-ascii").generate(ctx, os, 0, NULL, vmime::text::QUOTE_IF_POSSIBLE, NULL);
ferencd@0: 		VASSERT_EQ("2", "=?us-ascii?Q?Non-quotable=0Atext?=", cleanGeneratedWords(str));
ferencd@0: 
ferencd@0: 		// Text with non-ASCII chars is not quotable
ferencd@0: 		str.clear();
ferencd@0: 		vmime::word("Non-quotable text \xc3\xa9").generate(ctx, os, 0, NULL, vmime::text::QUOTE_IF_POSSIBLE, NULL);
ferencd@0: 		VASSERT_EQ("3", "=?UTF-8?Q?Non-quotable_text_=C3=A9?=", cleanGeneratedWords(str));
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordGenerateSpecialCharsets()
ferencd@0: 	{
ferencd@0: 		// ISO-2022-JP only uses 7-bit chars but should be encoded in Base64
ferencd@0: 		VASSERT_EQ("1", "=?iso-2022-jp?B?XlskQiVRITwlPSVKJWshJiU9JVUlSCUmJSclIl5bKEI=?=",
ferencd@0: 			cleanGeneratedWords(vmime::word("^[$B%Q!<%=%J%k!&%=%U%H%&%'%\"^[(B",
ferencd@0: 				vmime::charset("iso-2022-jp")).generate(100)));
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWordGenerateSpecials()
ferencd@0: 	{
ferencd@0: 		// In RFC-2047, quotation marks (ASCII 22h) should be encoded
ferencd@0: 		VASSERT_EQ("1", "=?UTF-8?Q?=22=C3=9Cml=C3=A4ute=22?=",
ferencd@0: 			vmime::word("\x22\xC3\x9Cml\xC3\xA4ute\x22", vmime::charset("UTF-8")).generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWhitespace()
ferencd@0: 	{
ferencd@0: 		// Create
ferencd@0: 		vmime::text text;
ferencd@0: 		text.createFromString("Achim Br\xc3\xa4ndt", vmime::charsets::UTF_8);
ferencd@0: 
ferencd@0: 		VASSERT_EQ("1", 2, text.getWordCount());
ferencd@0: 		VASSERT_EQ("2", "Achim ", text.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("3", "us-ascii", text.getWordAt(0)->getCharset());
ferencd@0: 		VASSERT_EQ("4", "Br\xc3\xa4ndt", text.getWordAt(1)->getBuffer());
ferencd@0: 		VASSERT_EQ("5", "utf-8", text.getWordAt(1)->getCharset());
ferencd@0: 
ferencd@0: 		// Generate
ferencd@0: 		VASSERT_EQ("6", "Achim =?utf-8?Q?Br=C3=A4ndt?=", text.generate());
ferencd@0: 
ferencd@0: 		// Parse
ferencd@0: 		text.parse("=?us-ascii?Q?Achim_?= =?utf-8?Q?Br=C3=A4ndt?=");
ferencd@0: 
ferencd@0: 		VASSERT_EQ("7", 2, text.getWordCount());
ferencd@0: 		VASSERT_EQ("8", "Achim ", text.getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("9", "us-ascii", text.getWordAt(0)->getCharset());
ferencd@0: 		VASSERT_EQ("10", "Br\xc3\xa4ndt", text.getWordAt(1)->getBuffer());
ferencd@0: 		VASSERT_EQ("11", "utf-8", text.getWordAt(1)->getCharset());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testWhitespaceMBox()
ferencd@0: 	{
ferencd@0: 		// Space MUST be encoded inside a word
ferencd@0: 		vmime::mailbox mbox(vmime::text("Achim Br\xc3\xa4ndt", vmime::charsets::UTF_8), "me@vmime.org");
ferencd@0: 		VASSERT_EQ("generate1", "=?us-ascii?Q?Achim_?= =?utf-8?Q?Br=C3=A4ndt?= <me@vmime.org>", mbox.generate());
ferencd@0: 
ferencd@0: 		vmime::text txt;
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>("Achim ", "us-ascii"));
ferencd@0: 		txt.appendWord(vmime::make_shared <vmime::word>("Br\xc3\xa4ndt", "utf-8"));
ferencd@0: 		mbox = vmime::mailbox(txt, "me@vmime.org");
ferencd@0: 		VASSERT_EQ("generate2", "=?us-ascii?Q?Achim_?= =?utf-8?Q?Br=C3=A4ndt?= <me@vmime.org>", mbox.generate());
ferencd@0: 
ferencd@0: 		mbox.parse("=?us-ascii?Q?Achim?= =?utf-8?Q?Br=C3=A4ndt?= <me@vmime.org>");
ferencd@0: 		VASSERT_EQ("parse.name.count", 2, mbox.getName().getWordCount());
ferencd@0: 		VASSERT_EQ("parse.name.word1.buffer", "Achim", mbox.getName().getWordAt(0)->getBuffer());
ferencd@0: 		VASSERT_EQ("parse.name.word1.charset", "us-ascii", mbox.getName().getWordAt(0)->getCharset());
ferencd@0: 		VASSERT_EQ("parse.name.word2.buffer", "Br\xc3\xa4ndt", mbox.getName().getWordAt(1)->getBuffer());
ferencd@0: 		VASSERT_EQ("parse.name.word2.charset", "utf-8", mbox.getName().getWordAt(1)->getCharset());
ferencd@0: 
ferencd@0: 		VASSERT_EQ("parse.email", "me@vmime.org", mbox.getEmail());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testFoldingAscii()
ferencd@0: 	{
ferencd@0: 		// In this test, no encoding is needed, but line should be folded anyway
ferencd@0: 		vmime::word w("01234567890123456789012345678901234567890123456789"
ferencd@0: 		              "01234567890123456789012345678901234567890123456789", vmime::charset("us-ascii"));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("fold.ascii",
ferencd@0: 			"=?us-ascii?Q?01234567890123456789012345678901234?=\r\n"
ferencd@0: 			" =?us-ascii?Q?5678901234567890123456789012345678?=\r\n"
ferencd@0: 			" =?us-ascii?Q?9012345678901234567890123456789?=", w.generate(50));
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testForcedNonEncoding()
ferencd@0: 	{
ferencd@0: 		// Testing long unbreakable and unencodable header
ferencd@0: 		vmime::relay r;
ferencd@0: 		r.parse(" from User (Ee9GMqZQ8t7IQwftfAFHd2KyScCYRrFSJ50tKEoXv2bVCG4HcPU80GGWiFabAvG77FekpGgF1h@[127.0.0.1]) by servername.hostname.com\n\t"
ferencd@0: 				"with esmtp id 1NGTS9-2C0sqG0; Fri, 4 Dec 2009 09:23:49 +0100");
ferencd@0: 
ferencd@0: 		VASSERT_EQ("received.long", "from User\r\n (Ee9GMqZQ8t7IQwftfAFHd2KyScCYRrFSJ50tKEoXv2bVCG4HcPU80GGWiFabAvG77FekpGgF1h@[127.0.0.1])\r\n by servername.hostname.com with esmtp id 1NGTS9-2C0sqG0; Fri, 4 Dec 2009\r\n 09:23:49 +0100", r.generate(78));
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testBugFix20110511()
ferencd@0: 	{
ferencd@0: 		/*
ferencd@0: 
ferencd@0: 		 Using the latest version of vmime (0.9.1), encoding the following string: Jean
ferencd@0: 		 Gwenaël Dutourd will result in:
ferencd@0: 		 Jean =?utf-8?Q?Gwena=C3=ABl_?= Dutourd
ferencd@0: 		 However, decoding this will result in Jean Gwenaël  Dutourd (notice two spaces
ferencd@0: 		 between the last 2 words).  The encoder adds a _ after the second word, but
ferencd@0: 		 since the last word is not encoded, the space between them is not ignored, and
ferencd@0: 		 is decoded into an additional space.
ferencd@0: 
ferencd@0: 		 See: http://sourceforge.net/projects/vmime/forums/forum/237357/topic/4531365
ferencd@0: 
ferencd@0: 		*/
ferencd@0: 
ferencd@0: 		const std::string DECODED_TEXT = "Jean Gwenaël Dutourd";
ferencd@0: 		const std::string ENCODED_TEXT = "Jean =?utf-8?Q?Gwena=C3=ABl?= Dutourd";
ferencd@0: 
ferencd@0: 		// Encode
ferencd@0: 		VASSERT_EQ("encode", ENCODED_TEXT,
ferencd@0: 			vmime::text::newFromString(DECODED_TEXT, vmime::charset("utf-8"))->generate());
ferencd@0: 
ferencd@0: 		// Decode
ferencd@0: 		vmime::text t;
ferencd@0: 		t.parse(ENCODED_TEXT);
ferencd@0: 
ferencd@0: 		// -- words
ferencd@0: 		std::ostringstream oss; oss << t;
ferencd@0: 		VASSERT_EQ("decode1",
ferencd@0: 			"[text: [[word: charset=us-ascii, buffer=Jean ],"
ferencd@0: 			        "[word: charset=utf-8, buffer=Gwenaël],"
ferencd@0: 				  "[word: charset=us-ascii, buffer= Dutourd]]]", oss.str());
ferencd@0: 
ferencd@0: 		// -- getWholeBuffer
ferencd@0: 		VASSERT_EQ("decode2", DECODED_TEXT, t.getWholeBuffer());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testInternationalizedEmail_specialChars()
ferencd@0: 	{
ferencd@0: 		vmime::generationContext ctx(vmime::generationContext::getDefaultContext());
ferencd@0: 		ctx.setInternationalizedEmailSupport(true);
ferencd@0: 
ferencd@0: 		vmime::generationContext::switcher <vmime::generationContext> contextSwitcher(ctx);
ferencd@0: 
ferencd@0: 		// Special sequence/chars should still be encoded
ferencd@0: 		VASSERT_EQ("1", "=?us-ascii?Q?Test=3D=3Frfc2047_sequence?=",
ferencd@0: 			vmime::word("Test=?rfc2047 sequence", vmime::charset("us-ascii")).generate());
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2", "=?us-ascii?Q?Line_One=0ALine_Two?=",
ferencd@0: 			vmime::word("Line One\nLine Two", vmime::charset("us-ascii")).generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testInternationalizedEmail_UTF8()
ferencd@0: 	{
ferencd@0: 		vmime::generationContext ctx(vmime::generationContext::getDefaultContext());
ferencd@0: 		ctx.setInternationalizedEmailSupport(true);
ferencd@0: 
ferencd@0: 		vmime::generationContext::switcher <vmime::generationContext> contextSwitcher(ctx);
ferencd@0: 
ferencd@0: 		// Already UTF-8 encoded text should be left as is
ferencd@0: 		VASSERT_EQ("1", "Achim Br\xc3\xa4ndt",
ferencd@0: 			vmime::word("Achim Br\xc3\xa4ndt", vmime::charset("utf-8")).generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testInternationalizedEmail_nonUTF8()
ferencd@0: 	{
ferencd@0: 		vmime::generationContext ctx(vmime::generationContext::getDefaultContext());
ferencd@0: 		ctx.setInternationalizedEmailSupport(true);
ferencd@0: 
ferencd@0: 		vmime::generationContext::switcher <vmime::generationContext> contextSwitcher(ctx);
ferencd@0: 
ferencd@0: 		// Non UTF-8 encoded text should first be converted to UTF-8
ferencd@0: 		VASSERT_EQ("1", "Achim Br\xc3\xa4ndt",
ferencd@0: 			vmime::word("Achim Br\xe4ndt", vmime::charset("iso-8859-1")).generate());
ferencd@0: 	}
ferencd@0: 
ferencd@0: 	void testInternationalizedEmail_folding()
ferencd@0: 	{
ferencd@0: 		vmime::generationContext ctx(vmime::generationContext::getDefaultContext());
ferencd@0: 		ctx.setInternationalizedEmailSupport(true);
ferencd@0: 
ferencd@0: 		vmime::generationContext::switcher <vmime::generationContext> contextSwitcher(ctx);
ferencd@0: 
ferencd@0: 		// RFC-2047 encoding must be performed, as line folding is needed
ferencd@0: 		vmime::word w1("01234567890123456789\xc3\xa0x012345678901234567890123456789"
ferencd@0: 		               "01234567890123456789\xc3\xa0x012345678901234567890123456789", vmime::charset("utf-8"));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("1",
ferencd@0: 			"=?utf-8?Q?01234567890123456789=C3=A0x01234567890?=\r\n"
ferencd@0: 			" =?utf-8?Q?1234567890123456789012345678901234567?=\r\n"
ferencd@0: 			" =?utf-8?Q?89=C3=A0x0123456789012345678901234567?=\r\n"
ferencd@0: 			" =?utf-8?Q?89?=", w1.generate(50));
ferencd@0: 
ferencd@0: 		// RFC-2047 encoding will not be forced, as words can be wrapped in a new line
ferencd@0: 		vmime::word w2("bla bla bla This is some '\xc3\xa0\xc3\xa7' UTF-8 encoded text", vmime::charset("utf-8"));
ferencd@0: 
ferencd@0: 		VASSERT_EQ("2",
ferencd@0: 			"bla bla bla This is\r\n"
ferencd@0: 			" some '\xc3\xa0\xc3\xa7' UTF-8\r\n"
ferencd@0: 			" encoded text", w2.generate(20));
ferencd@0: 	}
ferencd@0: 
ferencd@0: VMIME_TEST_SUITE_END
ferencd@0: