vmime/tests/parser/mailboxTest.cpp

198 lines
6.9 KiB
C++
Raw Normal View History

2004-11-06 10:48:58 +00:00
//
2005-03-18 21:33:11 +00:00
// VMime library (http://www.vmime.org)
2018-09-05 21:54:48 +00:00
// Copyright (C) 2002 Vincent Richard <vincent@vmime.org>
2004-11-06 10:48:58 +00:00
//
// This program 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
2004-11-06 10:48:58 +00:00
// the License, or (at your option) any later version.
//
// This program 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.
//
2005-09-17 10:10:29 +00:00
// You should have received a copy of the GNU General Public License along
// with this program; if not, write to the Free Software Foundation, Inc.,
// 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
//
// Linking this library statically or dynamically with other modules is making
// a combined work based on this library. Thus, the terms and conditions of
// the GNU General Public License cover the whole combination.
2004-11-06 10:48:58 +00:00
//
#include "tests/testUtils.hpp"
2004-11-06 10:48:58 +00:00
2013-03-08 07:19:50 +00:00
VMIME_TEST_SUITE_BEGIN(mailboxTest)
2004-11-06 10:48:58 +00:00
VMIME_TEST_LIST_BEGIN
VMIME_TEST(testParse)
VMIME_TEST(testEmptyEmailAddress)
VMIME_TEST(testSeparatorInComment)
VMIME_TEST(testMalformations)
VMIME_TEST(testExcessiveQuoting)
vmime: prevent loss of a space during text::createFromString (#306) ``` mailbox(text("Test München West", charsets::UTF_8), "a@b.de").generate(); ``` produces ``` =?us-ascii?Q?Test_?= =?utf-8?Q?M=C3=BCnchen?= =?us-ascii?Q?West?= <test@example.com> ``` The first space between ``Test`` and ``München`` is encoded as an underscore along with the first word: ``Test_``. The second space between ``München`` and ``West`` is encoded with neither of the two words and thus lost. Decoding the text results in ``Test MünchenWest`` instead of ``Test München West``. This is caused by how ``vmime::text::createFromString()`` handles transitions between 7-bit and 8-bit words: If an 8-bit word follows a 7-bit word, a space is appended to the previous word. The opposite case of a 7-bit word following an 8-bit word *misses* this behaviour. When one fixes this problem, a follow-up issue appears: ``text::createFromString("a b\xFFc d")`` tokenizes the input into ``m_words={word("a "), word("b\xFFc ", utf8), word("d")}``. This "right-side alignment" nature of the whitespace is a problem for word::generate(): As per RFC 2047, spaces between adjacent encoded words are just separators but not meant to be displayed. A space between an encoded word and a regular ASCII text is not just a separator but also meant to be displayed. When word::generate() outputs the b-word, it would have to strip one space, but only when there is a transition from encoded-word to unencoded word. word::generate() does not know whether d will be encoded or unencoded. The idea now is that we could change the tokenization of ``text::createFromString`` such that whitespace is at the *start* of words rather than at the end. With that, word::generate() need not know anything about the next word, but rather only the *previous* one. Thus, in this patch, 1. The tokenization of ``text::createFromString`` is changed to left-align spaces and the function is fixed to account for the missing space on transition. 2. ``word::generate`` learns how to steal a space character. 3. Testcases are adjusted to account for the shifted position of the space. Fixes: #283, #284 Co-authored-by: Vincent Richard <vincent@vincent-richard.net>
2024-05-21 13:55:06 +00:00
VMIME_TEST(testSpacing)
VMIME_TEST_LIST_END
2004-11-06 10:48:58 +00:00
2018-09-05 21:54:48 +00:00
void testParse() {
static const vmime::string testSuitesParse[] = {
// Test 1
"My (this is a comment)name <me(another \\)comment) @ somewhere(else).com>",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: [[word: charset=us-ascii, buffer=My name]]], email=me@somewhere.com]]]",
2004-11-06 10:48:58 +00:00
// Test 2
"mailbox1 <mailbox@one>,;,,, ,, ,,;group1:mailbox1@group1, mailbox2@group2,,\"mailbox #3\" <mailbox3@group2>;, <mailbox@two>,,,,,,,,=?iso-8859-1?q?mailbox_number_3?= <mailbox@three>, =?abc?Q?mailbox?= =?def?Q?_number_4?= <mailbox@four>",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: [[word: charset=us-ascii, buffer=mailbox1]]], email=mailbox@one],[mailbox-group: name=[text: [[word: charset=us-ascii, buffer=group1]]], list=[[mailbox: name=[text: []], email=mailbox1@group1],[mailbox: name=[text: []], email=mailbox2@group2],[mailbox: name=[text: [[word: charset=us-ascii, buffer=mailbox #3]]], email=mailbox3@group2]]],[mailbox: name=[text: []], email=mailbox@two],[mailbox: name=[text: [[word: charset=iso-8859-1, buffer=mailbox number 3]]], email=mailbox@three],[mailbox: name=[text: [[word: charset=abc, buffer=mailbox],[word: charset=def, buffer= number 4]]], email=mailbox@four]]]",
2004-11-06 10:48:58 +00:00
// Test 3
"John Doe <john.doe@acme.com>",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: [[word: charset=us-ascii, buffer=John Doe]]], email=john.doe@acme.com]]]",
2004-11-06 10:48:58 +00:00
// Test 4
"john.doe@acme.com (John Doe)",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: []], email=john.doe@acme.com]]]",
2004-11-06 10:48:58 +00:00
// Test 5
"John.Doe(ignore)@acme.com (John Doe)",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: []], email=John.Doe@acme.com]]]",
2004-11-06 10:48:58 +00:00
// Test 6
"<john.doe@acme.com>",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: []], email=john.doe@acme.com]]]",
2004-11-06 10:48:58 +00:00
// Test 7
"john.doe@acme.com",
2005-06-17 11:27:26 +00:00
"[address-list: [[mailbox: name=[text: []], email=john.doe@acme.com]]]",
2005-06-17 11:27:26 +00:00
// Test 8
"\"John Doe\" <john.doe@acme.com>",
2005-06-17 11:27:26 +00:00
"[address-list: [[mailbox: name=[text: [[word: charset=us-ascii, buffer=John Doe]]], email=john.doe@acme.com]]]",
2005-06-17 11:27:26 +00:00
// Test 9
"=?us-ascii?q?John?=<john.doe@acme.com>",
2005-06-17 11:27:26 +00:00
"[address-list: [[mailbox: name=[text: [[word: charset=us-ascii, buffer=John]]], email=john.doe@acme.com]]]",
2005-06-17 11:27:26 +00:00
// Test 10
"\"John\"<john.doe@acme.com>",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: [[word: charset=us-ascii, buffer=John]]], email=john.doe@acme.com]]]",
2004-11-06 10:48:58 +00:00
// Test 11
"John<john.doe@acme.com>",
2004-11-06 10:48:58 +00:00
"[address-list: [[mailbox: name=[text: [[word: charset=us-ascii, buffer=John]]], email=john.doe@acme.com]]]"
};
2004-11-06 10:48:58 +00:00
2018-09-05 21:54:48 +00:00
for (unsigned int i = 0 ; i < sizeof(testSuitesParse) / sizeof(testSuitesParse[0]) / 2 ; ++i) {
vmime::string in = testSuitesParse[i * 2];
vmime::string out = testSuitesParse[i * 2 + 1];
2004-11-06 10:48:58 +00:00
std::ostringstream oss;
oss << "Test " << (i + 1);
2004-11-06 10:48:58 +00:00
vmime::addressList addrList;
addrList.parse(in);
2004-11-06 10:48:58 +00:00
std::ostringstream cmp;
cmp << addrList;
2004-11-06 10:48:58 +00:00
VASSERT_EQ(oss.str(), out, cmp.str());
2004-11-06 10:48:58 +00:00
}
}
2004-11-06 10:48:58 +00:00
2018-09-05 21:54:48 +00:00
void testEmptyEmailAddress() {
vmime::addressList addrList;
addrList.parse("\"Full Name\" <>");
VASSERT_EQ("count", 1, addrList.getAddressCount());
VASSERT_EQ("!group", false, addrList.getAddressAt(0)->isGroup());
2013-11-21 21:16:57 +00:00
vmime::shared_ptr <vmime::mailbox> mbox =
vmime::dynamicCast <vmime::mailbox>(addrList.getAddressAt(0));
VASSERT_EQ("name", "Full Name", mbox->getName());
VASSERT_EQ("email", "", mbox->getEmail());
}
2018-09-05 21:54:48 +00:00
void testSeparatorInComment() {
vmime::addressList addrList;
addrList.parse("aaa(comment,comment)@vmime.org, bbb@vmime.org");
VASSERT_EQ("count", 2, addrList.getAddressCount());
2013-11-21 21:16:57 +00:00
vmime::shared_ptr <vmime::mailbox> mbox1 =
vmime::dynamicCast <vmime::mailbox>(addrList.getAddressAt(0));
vmime::shared_ptr <vmime::mailbox> mbox2 =
vmime::dynamicCast <vmime::mailbox>(addrList.getAddressAt(1));
VASSERT_EQ("name1", vmime::text(), mbox1->getName());
VASSERT_EQ("email1", "aaa@vmime.org", mbox1->getEmail());
VASSERT_EQ("name2", vmime::text(), mbox2->getName());
VASSERT_EQ("email2", "bbb@vmime.org", mbox2->getEmail());
}
void testMalformations() {
2018-03-12 19:33:27 +00:00
vmime::mailbox mbox;
mbox.parse("a@b.c <e@f.g>");
2018-03-12 19:33:27 +00:00
VASSERT_EQ("name", vmime::text("a@b.c"), mbox.getName());
VASSERT_EQ("email", "e@f.g", mbox.getEmail());
mbox.parse("a@b.c e@f.g <h@i.j>");
VASSERT_EQ("name", vmime::text("a@b.c e@f.g"), mbox.getName());
VASSERT_EQ("email", "h@i.j", mbox.getEmail());
mbox.parse("Foo <bar<baz@quux.com>");
VASSERT_EQ("name", vmime::text("Foo <bar"), mbox.getName());
VASSERT_EQ("email", "baz@quux.com", mbox.getEmail());
mbox.parse("Foo <foo@x.com> <bar@x.com>");
VASSERT_EQ("name", vmime::text("Foo <foo@x.com>"), mbox.getName());
VASSERT_EQ("email", "bar@x.com", mbox.getEmail());
mbox.parse("Foo <foo@x.com> Bar <bar@y.com>");
VASSERT_EQ("name", vmime::text("Foo <foo@x.com> Bar"), mbox.getName());
VASSERT_EQ("email", "bar@y.com", mbox.getEmail());
2018-03-12 19:33:27 +00:00
}
void testExcessiveQuoting() {
using namespace vmime;
// Check that ASCII display names are not encoded more than necessary
emailAddress e("a@b.com");
auto a = make_shared<mailbox>(text(word("Foo B@r", charsets::US_ASCII)), e);
VASSERT_EQ("generate", "\"Foo B@r\" <a@b.com>", a->generate());
VASSERT_NEQ("generate", "=?utf-8?Q?Foo_B=40r?= <a@b.com>", a->generate());
a = make_shared<mailbox>(text(word("Foo B@r", charsets::UTF_8)), e);
VASSERT_EQ("generate", "=?utf-8?Q?Foo_B=40r?= <a@b.com>", a->generate());
}
vmime: prevent loss of a space during text::createFromString (#306) ``` mailbox(text("Test München West", charsets::UTF_8), "a@b.de").generate(); ``` produces ``` =?us-ascii?Q?Test_?= =?utf-8?Q?M=C3=BCnchen?= =?us-ascii?Q?West?= <test@example.com> ``` The first space between ``Test`` and ``München`` is encoded as an underscore along with the first word: ``Test_``. The second space between ``München`` and ``West`` is encoded with neither of the two words and thus lost. Decoding the text results in ``Test MünchenWest`` instead of ``Test München West``. This is caused by how ``vmime::text::createFromString()`` handles transitions between 7-bit and 8-bit words: If an 8-bit word follows a 7-bit word, a space is appended to the previous word. The opposite case of a 7-bit word following an 8-bit word *misses* this behaviour. When one fixes this problem, a follow-up issue appears: ``text::createFromString("a b\xFFc d")`` tokenizes the input into ``m_words={word("a "), word("b\xFFc ", utf8), word("d")}``. This "right-side alignment" nature of the whitespace is a problem for word::generate(): As per RFC 2047, spaces between adjacent encoded words are just separators but not meant to be displayed. A space between an encoded word and a regular ASCII text is not just a separator but also meant to be displayed. When word::generate() outputs the b-word, it would have to strip one space, but only when there is a transition from encoded-word to unencoded word. word::generate() does not know whether d will be encoded or unencoded. The idea now is that we could change the tokenization of ``text::createFromString`` such that whitespace is at the *start* of words rather than at the end. With that, word::generate() need not know anything about the next word, but rather only the *previous* one. Thus, in this patch, 1. The tokenization of ``text::createFromString`` is changed to left-align spaces and the function is fixed to account for the missing space on transition. 2. ``word::generate`` learns how to steal a space character. 3. Testcases are adjusted to account for the shifted position of the space. Fixes: #283, #284 Co-authored-by: Vincent Richard <vincent@vincent-richard.net>
2024-05-21 13:55:06 +00:00
void testSpacing() {
vmime::text t("Foo B\xc3\xa4renstark Baz", vmime::charsets::UTF_8);
vmime::mailbox m(t, "a@b.de");
VASSERT_EQ("1", "Foo =?utf-8?Q?B=C3=A4renstark?= Baz", t.generate());
VASSERT_EQ("2", "=?us-ascii?Q?Foo?= =?utf-8?Q?_B=C3=A4renstark?= =?us-ascii?Q?_Baz?= <a@b.de>", m.generate());
}
VMIME_TEST_SUITE_END