Skip to content

C
core
Kaydet (Commit) bef9fe6e authored tarafından Jochen Nitschke's avatar Jochen Nitschke Kaydeden (comit) Stephan Bergmann
Dosyalara gözat
Seçenekler

extend unit test for INetMIME::scanContentType 

This reverts parts of commit 631b6795
and commit abc6071b.

some of the removed fields are usefull,
m_bConverted should be checked by callers

fixed 2 bugs and added test cases:
* extended attributes with more than 2 sections were not parsed
* extended attributes with more than 1 section were not parsed
  if there was an other attribute

Change-Id: I61ab2af7c5151ef1bcd80cc159fa2b99559374a8
Reviewed-on: https://gerrit.libreoffice.org/36913Tested-by: 's avatarJenkins <ci@libreoffice.org>
Reviewed-by: 's avatarStephan Bergmann <sbergman@redhat.com>
üst 925ed700
Hide whitespace changes
Inline Side-by-side
Showing with 128 additions and 17 deletions
include/tools/inetmime.hxx
Dosyayı görüntüle @ bef9fe6e
......@@ -30,6 +30,16 @@
struct INetContentTypeParameter
{
/** The optional character set specification (see RFC 2231), in US-ASCII
encoding and converted to lower case.
*/
OString m_sCharset;
/** The optional language specification (see RFC 2231), in US-ASCII
encoding and converted to lower case.
*/
OString m_sLanguage;
/** The attribute value. If the value is a quoted-string, it is
'unpacked.' If a character set is specified, and the value can be
converted to Unicode, this is done. Also, if no character set is
......@@ -49,9 +59,18 @@ struct INetContentTypeParameter
*/
OUString m_sValue;
/** This is true if the value is successfully converted to Unicode, and
false if the value is a special mixture of ISO-LATIN-1 characters and
characters from Unicode's Private Use Area.
*/
bool m_bConverted;
};
// the key is the m_sAttribute again; all keys are lower case:
/** The key is the name of the attribute, in US-ASCII encoding and converted
to lower case. If a parameter value is split as described in RFC 2231,
there will only be one item for the complete parameter, with the attribute
name lacking any section suffix.
*/
typedef std::unordered_map<OString, INetContentTypeParameter, OStringHash>
INetContentTypeParameterList;
......
tools/qa/cppunit/test_inetmime.cxx
Dosyayı görüntüle @ bef9fe6e
......@@ -35,11 +35,13 @@ namespace
public:
void test_decodeHeaderFieldBody();
void test_scanContentType();
void test_scanContentType_basic();
void test_scanContentType_rfc2231();
CPPUNIT_TEST_SUITE(Test);
CPPUNIT_TEST(test_decodeHeaderFieldBody);
CPPUNIT_TEST(test_scanContentType);
CPPUNIT_TEST(test_scanContentType_basic);
CPPUNIT_TEST(test_scanContentType_rfc2231);
CPPUNIT_TEST_SUITE_END();
};
......@@ -56,17 +58,61 @@ namespace
CPPUNIT_ASSERT(testDecode("=?iso-8859-1?B?QUJD?=", "ABC"));
}
void Test::test_scanContentType()
void Test::test_scanContentType_basic()
{
{
OUString input
= "TEST/subTST; parm1*0*=US-ASCII'En'5%25%20; Parm1*1*=of%2010";
= "TEST/subTST; parm1=Value1; Parm2=\"unpacked value; %20\"";
// Just scan input for valid string:
auto end = INetMIME::scanContentType(input.getStr(), input.getStr()+input.getLength());
CPPUNIT_ASSERT(end != nullptr);
CPPUNIT_ASSERT_EQUAL(OUString(), OUString(end));
// Scan input and parse type, subType and parameters:
OUString type;
OUString subType;
INetContentTypeParameterList parameters;
end = INetMIME::scanContentType(input.getStr(), input.getStr() + input.getLength(),
&type, &subType, &parameters);
CPPUNIT_ASSERT(end != nullptr);
CPPUNIT_ASSERT_EQUAL(OUString(), OUString(end));
CPPUNIT_ASSERT_EQUAL(OUString("test"), type);
CPPUNIT_ASSERT_EQUAL(OUString("subtst"), subType);
CPPUNIT_ASSERT_EQUAL(
INetContentTypeParameterList::size_type(2), parameters.size());
auto i = parameters.find("parm1");
CPPUNIT_ASSERT(i != parameters.end());
CPPUNIT_ASSERT_EQUAL(OString(), i->second.m_sCharset);
CPPUNIT_ASSERT_EQUAL(OString(), i->second.m_sLanguage);
CPPUNIT_ASSERT_EQUAL(OUString("Value1"), i->second.m_sValue);
CPPUNIT_ASSERT(i->second.m_bConverted);
i = parameters.find("parm2");
CPPUNIT_ASSERT(i != parameters.end());
CPPUNIT_ASSERT_EQUAL(OString(), i->second.m_sCharset);
CPPUNIT_ASSERT_EQUAL(OString(), i->second.m_sLanguage);
CPPUNIT_ASSERT_EQUAL(OUString("unpacked value; %20"), i->second.m_sValue);
CPPUNIT_ASSERT(i->second.m_bConverted);
}
}
void Test::test_scanContentType_rfc2231()
{
{
// Test extended parameter with value split in 3 sections:
OUString input
= "TEST/subTST; "
"parm1*0*=US-ASCII'En'5%25%20; "
"Parm1*1*=of%2010;\t"
"parm1*2*=%20%3d%200.5";
// Just scan input for valid string:
auto end = INetMIME::scanContentType(input.getStr(), input.getStr()+input.getLength());
CPPUNIT_ASSERT(end != nullptr);
CPPUNIT_ASSERT_EQUAL(OUString(), OUString(end));
// Scan input and parse type, subType and parameters:
OUString type;
OUString subType;
INetContentTypeParameterList parameters;
auto end = INetMIME::scanContentType(
input.getStr(), input.getStr() + input.getLength(), &type,
&subType, &parameters);
end = INetMIME::scanContentType(input.getStr(), input.getStr() + input.getLength(),
&type, &subType, &parameters);
CPPUNIT_ASSERT(end != nullptr);
CPPUNIT_ASSERT_EQUAL(OUString(), OUString(end));
CPPUNIT_ASSERT_EQUAL(OUString("test"), type);
......@@ -75,7 +121,48 @@ namespace
INetContentTypeParameterList::size_type(1), parameters.size());
auto i = parameters.find("parm1");
CPPUNIT_ASSERT(i != parameters.end());
CPPUNIT_ASSERT_EQUAL(OUString("5% of 10"), i->second.m_sValue);
CPPUNIT_ASSERT_EQUAL(OString("us-ascii"), i->second.m_sCharset);
CPPUNIT_ASSERT_EQUAL(OString("en"), i->second.m_sLanguage);
CPPUNIT_ASSERT_EQUAL(OUString("5% of 10 = 0.5"), i->second.m_sValue);
CPPUNIT_ASSERT(i->second.m_bConverted);
// Test extended parameters with different value charsets:
input = "TEST/subTST;"
"parm1*0*=us-ascii'en'value;PARM1*1*=1;"
"parm2*0*=WINDOWS-1250'en-GB'value2%20%80;"
"parm3*0*=UNKNOWN'EN'value3";
// Just scan input for valid string:
end = INetMIME::scanContentType(input.getStr(), input.getStr()+input.getLength());
CPPUNIT_ASSERT(end != nullptr);
CPPUNIT_ASSERT_EQUAL(OUString(), OUString(end));
// Scan input and parse type, subType and parameters:
end = INetMIME::scanContentType(input.getStr(), input.getStr() + input.getLength(),
&type, &subType, &parameters);
CPPUNIT_ASSERT(end != nullptr);
CPPUNIT_ASSERT_EQUAL(OUString(), OUString(end));
CPPUNIT_ASSERT_EQUAL(OUString("test"), type);
CPPUNIT_ASSERT_EQUAL(OUString("subtst"), subType);
CPPUNIT_ASSERT_EQUAL(
INetContentTypeParameterList::size_type(3), parameters.size());
i = parameters.find("parm1");
CPPUNIT_ASSERT(i != parameters.end());
CPPUNIT_ASSERT_EQUAL(OString("us-ascii"), i->second.m_sCharset);
CPPUNIT_ASSERT_EQUAL(OString("en"), i->second.m_sLanguage);
CPPUNIT_ASSERT_EQUAL(OUString("value1"), i->second.m_sValue);
CPPUNIT_ASSERT(i->second.m_bConverted);
i = parameters.find("parm2");
CPPUNIT_ASSERT(i != parameters.end());
CPPUNIT_ASSERT_EQUAL(OString("windows-1250"), i->second.m_sCharset);
CPPUNIT_ASSERT_EQUAL(OString("en-gb"), i->second.m_sLanguage);
// Euro currency sign, windows-1250 x80 is converted to unicode u20AC:
CPPUNIT_ASSERT_EQUAL(OUString(u"value2 \u20AC"), i->second.m_sValue);
CPPUNIT_ASSERT(i->second.m_bConverted);
i = parameters.find("parm3");
CPPUNIT_ASSERT(i != parameters.end());
CPPUNIT_ASSERT_EQUAL(OString("unknown"), i->second.m_sCharset);
CPPUNIT_ASSERT_EQUAL(OString("en"), i->second.m_sLanguage);
// Convertion fails for unknown charsets:
CPPUNIT_ASSERT(!i->second.m_bConverted);
}
}
......
tools/source/inet/inetmime.cxx
Dosyayı görüntüle @ bef9fe6e
......@@ -369,12 +369,14 @@ struct Parameter
Parameter * m_pNext;
OString m_aAttribute;
OString m_aCharset;
OString m_aLanguage;
OString m_aValue;
sal_uInt32 m_nSection;
bool m_bExtended;
inline Parameter(Parameter * pTheNext, const OString& rTheAttribute,
const OString& rTheCharset,
const OString& rTheLanguage,
const OString& rTheValue, sal_uInt32 nTheSection,
bool bTheExtended);
};
......@@ -382,11 +384,13 @@ struct Parameter
inline Parameter::Parameter(Parameter * pTheNext,
const OString& rTheAttribute,
const OString& rTheCharset,
const OString& rTheLanguage,
const OString& rTheValue,
sal_uInt32 nTheSection, bool bTheExtended):
m_pNext(pTheNext),
m_aAttribute(rTheAttribute),
m_aCharset(rTheCharset),
m_aLanguage(rTheLanguage),
m_aValue(rTheValue),
m_nSection(nTheSection),
m_bExtended(bTheExtended)
......@@ -439,16 +443,16 @@ Parameter ** ParameterList::find(const OString& rAttribute,
for (; *p; p = &(*p)->m_pNext)
{
sal_Int32 nCompare = rAttribute.compareTo((*p)->m_aAttribute);
if (nCompare > 0)
return &(*p)->m_pNext;
if (nCompare < 0)
break;
else if (nCompare == 0)
{
if (nSection > (*p)->m_nSection)
return &(*p)->m_pNext;
if (nSection < (*p)->m_nSection)
break;
else if (nSection == (*p)->m_nSection)
{
rPresent = true;
return p;
break;
}
}
}
......@@ -537,8 +541,9 @@ bool parseParameters(ParameterList const & rInput,
break;
};
}
INetContentTypeParameter x {aValue}; // workaround ICE in VisualStudio2013
auto const ret = pOutput->insert({p->m_aAttribute, x });
auto const ret = pOutput->insert(
{p->m_aAttribute,
{p->m_aCharset, p->m_aLanguage, aValue, !bBadEncoding}});
SAL_INFO_IF(!ret.second, "tools",
"INetMIME: dropping duplicate parameter: " << p->m_aAttribute);
p = pNext;
......@@ -877,7 +882,7 @@ sal_Unicode const * scanParameters(sal_Unicode const * pBegin,
RTL_TEXTENCODING_UTF8);
}
*pPos = new Parameter(*pPos, aAttribute, aCharset, aValue,
*pPos = new Parameter(*pPos, aAttribute, aCharset, aLanguage, aValue,
nSection, bExtended);
}
return parseParameters(aList, pParameters) ? pParameterBegin : pBegin;
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment