summaryrefslogtreecommitdiffstats
path: root/tests
diff options
context:
space:
mode:
authorThiago Macieira <thiago.macieira@intel.com>2018-09-16 09:05:47 -0700
committerThiago Macieira <thiago.macieira@intel.com>2018-09-25 22:14:07 +0000
commit7e1a0c07390ed18de074ce5450b272838a3b8ac8 (patch)
treee9acf3de8ba572b12efac0122d865802408e2069 /tests
parent4d40f09a45202dff901d4f970a6a7e939797138b (diff)
Add tests for decoding too-short UTF-8 sequences
We were handling this properly, but not testing them. I guess we weren't testing because the condition is a valid intermediate state, so hasFailure() is correct it returning false. Testing inspired by the bug reported in https://github.com/intel/tinycbor/issues/137 Change-Id: Ib47c56818178458a88b4fffd1554ecfdd0af637e Reviewed-by: Lars Knoll <lars.knoll@qt.io>
Diffstat (limited to 'tests')
-rw-r--r--tests/auto/corelib/codecs/utf8/tst_utf8.cpp15
-rw-r--r--tests/auto/corelib/codecs/utf8/utf8data.cpp30
2 files changed, 32 insertions, 13 deletions
diff --git a/tests/auto/corelib/codecs/utf8/tst_utf8.cpp b/tests/auto/corelib/codecs/utf8/tst_utf8.cpp
index 8f78aa937c..9ce1748e72 100644
--- a/tests/auto/corelib/codecs/utf8/tst_utf8.cpp
+++ b/tests/auto/corelib/codecs/utf8/tst_utf8.cpp
@@ -1,7 +1,7 @@
/****************************************************************************
**
-** Copyright (C) 2016 The Qt Company Ltd.
-** Copyright (C) 2016 Intel Corporation.
+** Copyright (C) 2018 The Qt Company Ltd.
+** Copyright (C) 2018 Intel Corporation.
** Contact: https://www.qt.io/licensing/
**
** This file is part of the test suite of the Qt Toolkit.
@@ -71,7 +71,7 @@ void tst_Utf8::initTestCase()
// is the locale UTF-8?
if (QString(QChar(QChar::ReplacementCharacter)).toLocal8Bit() == "\xEF\xBF\xBD") {
QTest::newRow("localecodec") << true;
- qDebug() << "locale is utf8";
+ qInfo() << "locale is utf8";
}
}
@@ -227,6 +227,15 @@ void tst_Utf8::invalidUtf8()
// GNU libc's iconv is known to accept U+FFFF and U+FFFE encoded as UTF-8
// OS X's iconv is known to accept those, plus surrogates and codepoints above U+10FFFF
if (!useLocale)
+ QVERIFY(decoder->hasFailure() || decoder->needsMoreData());
+ else if (!decoder->hasFailure() && !decoder->needsMoreData())
+ qWarning("System codec does not report failure when it should. Should report bug upstream.");
+
+ // add a continuation character and test that we don't accidentally use it
+ // (buffer overrun)
+ utf8 += char(0x80 | 0x3f);
+ decoder->toUnicode(utf8.constData(), utf8.size() - 1);
+ if (!useLocale)
QVERIFY(decoder->hasFailure());
else if (!decoder->hasFailure())
qWarning("System codec does not report failure when it should. Should report bug upstream.");
diff --git a/tests/auto/corelib/codecs/utf8/utf8data.cpp b/tests/auto/corelib/codecs/utf8/utf8data.cpp
index 2267dc8514..221e1d5579 100644
--- a/tests/auto/corelib/codecs/utf8/utf8data.cpp
+++ b/tests/auto/corelib/codecs/utf8/utf8data.cpp
@@ -1,6 +1,7 @@
/****************************************************************************
**
-** Copyright (C) 2016 The Qt Company Ltd.
+** Copyright (C) 2018 The Qt Company Ltd.
+** Copyright (C) 2018 Intel Corporation.
** Contact: https://www.qt.io/licensing/
**
** This file is part of the test suite of the Qt Toolkit.
@@ -29,15 +30,24 @@
void loadInvalidUtf8Rows()
{
- QTest::newRow("1char") << QByteArray("\x80");
- QTest::newRow("2chars-1") << QByteArray("\xC2\xC0");
- QTest::newRow("2chars-2") << QByteArray("\xC3\xDF");
- QTest::newRow("2chars-3") << QByteArray("\xC7\xF0");
- QTest::newRow("3chars-1") << QByteArray("\xE0\xA0\xC0");
- QTest::newRow("3chars-2") << QByteArray("\xE0\xC0\xA0");
- QTest::newRow("4chars-1") << QByteArray("\xF0\x90\x80\xC0");
- QTest::newRow("4chars-2") << QByteArray("\xF0\x90\xC0\x80");
- QTest::newRow("4chars-3") << QByteArray("\xF0\xC0\x80\x80");
+ // Wrong continuations
+ QTest::newRow("bad-continuation-1char") << QByteArray("\x80");
+ QTest::newRow("bad-continuation-2chars-1") << QByteArray("\xC2\xC0");
+ QTest::newRow("bad-continuation-2chars-2") << QByteArray("\xC3\xDF");
+ QTest::newRow("bad-continuation-2chars-3") << QByteArray("\xC7\xF0");
+ QTest::newRow("bad-continuation-3chars-1") << QByteArray("\xE0\xA0\xC0");
+ QTest::newRow("bad-continuation-3chars-2") << QByteArray("\xE0\xC0\xA0");
+ QTest::newRow("bad-continuation-4chars-1") << QByteArray("\xF0\x90\x80\xC0");
+ QTest::newRow("bad-continuation-4chars-2") << QByteArray("\xF0\x90\xC0\x80");
+ QTest::newRow("bad-continuation-4chars-3") << QByteArray("\xF0\xC0\x80\x80");
+
+ // Too short
+ QTest::newRow("too-short-2chars") << QByteArray("\xC2");
+ QTest::newRow("too-short-3chars-1") << QByteArray("\xE0");
+ QTest::newRow("too-short-3chars-2") << QByteArray("\xE0\xA0");
+ QTest::newRow("too-short-4chars-1") << QByteArray("\xF0");
+ QTest::newRow("too-short-4chars-2") << QByteArray("\xF0\x90");
+ QTest::newRow("too-short-4chars-3") << QByteArray("\xF0\x90\x80");
// Surrogate pairs must now be present either
// U+D800: 1101 10 0000 00 0000