| 1 |
// SPDX-FileCopyrightText: 2008 Dominik Seichter <[email protected]> |
| 2 |
// SPDX-FileCopyrightText: 2021 Francesco Pretto <[email protected]> |
| 3 |
// SPDX-License-Identifier: MIT-0 |
| 4 |
|
| 5 |
#include <PdfTest.h> |
| 6 |
|
| 7 |
#include <ostream> |
| 8 |
#include <iostream> |
| 9 |
|
| 10 |
using namespace std; |
| 11 |
using namespace PoDoFo; |
| 12 |
|
| 13 |
static void outofRangeHelper(PdfEncoding& encoding); |
| 14 |
|
| 15 |
namespace PoDoFo |
| 16 |
{ |
| 17 |
class PdfEncodingTest |
| 18 |
{ |
| 19 |
public: |
| 20 |
static void TestToUnicodeParse(); |
| 21 |
static void TestDifferencesObject(); |
| 22 |
}; |
| 23 |
} |
| 24 |
|
| 25 |
METHOD_AS_TEST_CASE(PdfEncodingTest::TestToUnicodeParse, "TestToUnicodeParse") |
| 26 |
METHOD_AS_TEST_CASE(PdfEncodingTest::TestDifferencesObject, "TestDifferencesObject") |
| 27 |
|
| 28 |
TEST_CASE("TestDifferences") |
| 29 |
{ |
| 30 |
PdfDifferenceMap difference; |
| 31 |
|
| 32 |
// Newly created encoding should be empty |
| 33 |
REQUIRE(difference.GetCount() == 0); |
| 34 |
|
| 35 |
// Adding 0 should work |
| 36 |
difference.AddDifference(0, u'A'); |
| 37 |
REQUIRE(difference.GetCount() == 1); |
| 38 |
|
| 39 |
// Adding 255 should work |
| 40 |
difference.AddDifference(255, u'B'); |
| 41 |
REQUIRE(difference.GetCount() == 2); |
| 42 |
|
| 43 |
// Convert to array |
| 44 |
PdfArray data; |
| 45 |
PdfArray expected; |
| 46 |
expected.Add(static_cast<int64_t>(0)); |
| 47 |
expected.Add(PdfName("A")); |
| 48 |
expected.Add(static_cast<int64_t>(255)); |
| 49 |
expected.Add(PdfName("B")); |
| 50 |
|
| 51 |
difference.ToArray(data); |
| 52 |
|
| 53 |
REQUIRE(expected.GetSize() == data.GetSize()); |
| 54 |
for (unsigned int i = 0; i < data.GetSize(); i++) |
| 55 |
REQUIRE(expected[i] == data[i]); |
| 56 |
|
| 57 |
|
| 58 |
// Test replace |
| 59 |
expected.Clear(); |
| 60 |
expected.Add(static_cast<int64_t>(0)); |
| 61 |
expected.Add(PdfName("A")); |
| 62 |
expected.Add(static_cast<int64_t>(255)); |
| 63 |
expected.Add(PdfName("X")); |
| 64 |
|
| 65 |
difference.AddDifference(255, u'X'); |
| 66 |
|
| 67 |
difference.ToArray(data); |
| 68 |
|
| 69 |
REQUIRE(expected.GetSize() == data.GetSize()); |
| 70 |
for (unsigned int i = 0; i < data.GetSize(); i++) |
| 71 |
REQUIRE(expected[i] == data[i]); |
| 72 |
|
| 73 |
|
| 74 |
// Test more complicated array |
| 75 |
expected.Clear(); |
| 76 |
expected.Add(static_cast<int64_t>(0)); |
| 77 |
expected.Add(PdfName("A")); |
| 78 |
expected.Add(PdfName("B")); |
| 79 |
expected.Add(PdfName("C")); |
| 80 |
expected.Add(static_cast<int64_t>(4)); |
| 81 |
expected.Add(PdfName("D")); |
| 82 |
expected.Add(PdfName("E")); |
| 83 |
expected.Add(static_cast<int64_t>(9)); |
| 84 |
expected.Add(PdfName("F")); |
| 85 |
expected.Add(static_cast<int64_t>(255)); |
| 86 |
expected.Add(PdfName("X")); |
| 87 |
|
| 88 |
difference.AddDifference(1, u'B'); |
| 89 |
difference.AddDifference(2, u'C'); |
| 90 |
difference.AddDifference(4, u'D'); |
| 91 |
difference.AddDifference(5, u'E'); |
| 92 |
difference.AddDifference(9, u'F'); |
| 93 |
|
| 94 |
difference.ToArray(data); |
| 95 |
|
| 96 |
REQUIRE(expected.GetSize() == data.GetSize()); |
| 97 |
for (unsigned int i = 0; i < data.GetSize(); i++) |
| 98 |
REQUIRE(expected[i] == data[i]); |
| 99 |
|
| 100 |
// Test if contains works correctly |
| 101 |
const PdfName* name; |
| 102 |
CodePointSpan codepoints; |
| 103 |
REQUIRE(difference.TryGetMappedName(0, name, codepoints)); |
| 104 |
REQUIRE(*name == "A"); |
| 105 |
REQUIRE(static_cast<int>(*codepoints) == 0x41); |
| 106 |
|
| 107 |
REQUIRE(difference.TryGetMappedName(9, name, codepoints)); |
| 108 |
REQUIRE(*name == "F"); |
| 109 |
REQUIRE(static_cast<int>(*codepoints) == 0x46); |
| 110 |
|
| 111 |
REQUIRE(difference.TryGetMappedName(255, name, codepoints)); |
| 112 |
REQUIRE(*name == "X"); |
| 113 |
REQUIRE(static_cast<int>(*codepoints) == 0x58); |
| 114 |
|
| 115 |
REQUIRE(!difference.TryGetMappedName(100, name, codepoints)); |
| 116 |
} |
| 117 |
|
| 118 |
void PdfEncodingTest::TestDifferencesObject() |
| 119 |
{ |
| 120 |
PdfDifferenceMap differences; |
| 121 |
differences.AddDifference(1, 'B'); |
| 122 |
differences.AddDifference(2, 'C'); |
| 123 |
differences.AddDifference(4, 'D'); |
| 124 |
differences.AddDifference(5, 'E'); |
| 125 |
differences.AddDifference(9, 'F'); |
| 126 |
|
| 127 |
PdfDifferenceEncoding encoding(PdfEncodingMapFactory::GetMacRomanEncodingInstancePtr(), std::move(differences)); |
| 128 |
|
| 129 |
// Check for encoding key |
| 130 |
PdfMemDocument doc; |
| 131 |
PdfName name; |
| 132 |
PdfObject* encodingObj; |
| 133 |
REQUIRE(encoding.TryGetExportObject(doc.GetObjects(), name, encodingObj)); |
| 134 |
REQUIRE(encodingObj != nullptr); |
| 135 |
|
| 136 |
// Test BaseEncoding |
| 137 |
PdfObject* baseObj = encodingObj->GetDictionary().GetKey("BaseEncoding"); |
| 138 |
REQUIRE(baseObj->GetName() == "MacRomanEncoding"); |
| 139 |
|
| 140 |
// Test differences |
| 141 |
PdfObject* diff = encodingObj->GetDictionary().GetKey("Differences"); |
| 142 |
PdfArray expected; |
| 143 |
|
| 144 |
expected.Add(static_cast<int64_t>(1)); |
| 145 |
expected.Add(PdfName("B")); |
| 146 |
expected.Add(PdfName("C")); |
| 147 |
expected.Add(static_cast<int64_t>(4)); |
| 148 |
expected.Add(PdfName("D")); |
| 149 |
expected.Add(PdfName("E")); |
| 150 |
expected.Add(static_cast<int64_t>(9)); |
| 151 |
expected.Add(PdfName("F")); |
| 152 |
|
| 153 |
const PdfArray& data = diff->GetArray(); |
| 154 |
REQUIRE(expected.GetSize() == data.GetSize()); |
| 155 |
for (unsigned int i = 0; i < data.GetSize(); i++) |
| 156 |
REQUIRE(expected[i] == data[i]); |
| 157 |
} |
| 158 |
|
| 159 |
TEST_CASE("TestDifferencesEncoding") |
| 160 |
{ |
| 161 |
// Create a differences encoding where A and B are exchanged |
| 162 |
PdfDifferenceMap differences; |
| 163 |
differences.AddDifference((unsigned char)'A', 'B'); |
| 164 |
differences.AddDifference((unsigned char)'B', 'A'); |
| 165 |
differences.AddDifference((unsigned char)'C', 'D'); |
| 166 |
|
| 167 |
PdfMemDocument doc; |
| 168 |
|
| 169 |
PdfFontCreateParams params; |
| 170 |
params.Encoding = PdfEncoding(std::make_shared<PdfDifferenceEncoding>(PdfEncodingMapFactory::GetWinAnsiEncodingInstancePtr(), std::move(differences))); |
| 171 |
auto& font = doc.GetFonts().GetStandard14Font(PdfStandard14FontType::Helvetica, params); |
| 172 |
|
| 173 |
charbuff encoded; |
| 174 |
INFO("'C' in \"BAABC\" is already reserved for mapping in 'D'"); |
| 175 |
REQUIRE(!font.GetEncoding().TryConvertToEncoded("BAABC", encoded)); |
| 176 |
encoded = font.GetEncoding().ConvertToEncoded("BAABI"); |
| 177 |
REQUIRE(encoded == "ABBAI"); |
| 178 |
auto unicode = params.Encoding.ConvertToUtf8(PdfString::FromRaw(encoded)); |
| 179 |
REQUIRE(unicode == "BAABI"); |
| 180 |
} |
| 181 |
|
| 182 |
TEST_CASE("TestGetCharCode") |
| 183 |
{ |
| 184 |
auto winAnsiEncoding = PdfEncodingFactory::CreateWinAnsiEncoding(); |
| 185 |
INFO("WinAnsiEncoding"); |
| 186 |
outofRangeHelper(winAnsiEncoding); |
| 187 |
|
| 188 |
auto macRomanEncoding = PdfEncodingFactory::CreateMacRomanEncoding(); |
| 189 |
INFO("MacRomanEncoding"); |
| 190 |
outofRangeHelper(macRomanEncoding); |
| 191 |
|
| 192 |
PdfDifferenceMap differences; |
| 193 |
differences.AddDifference((unsigned char)'A', 'B'); |
| 194 |
differences.AddDifference((unsigned char)'B', 'A'); |
| 195 |
PdfEncoding differenceEncoding(std::make_shared<PdfDifferenceEncoding>(PdfEncodingMapFactory::GetWinAnsiEncodingInstancePtr(), std::move(differences))); |
| 196 |
outofRangeHelper(differenceEncoding); |
| 197 |
} |
| 198 |
|
| 199 |
TEST_CASE("CMapIdentityTest") |
| 200 |
{ |
| 201 |
constexpr string_view OneByteIdentity = R"( |
| 202 |
/CIDInit /ProcSet findresource begin |
| 203 |
12 dict begin |
| 204 |
begincmap |
| 205 |
/CIDSystemInfo 3 dict dup begin |
| 206 |
/Registry (Adobe) def |
| 207 |
/Ordering (Identity) def |
| 208 |
/Supplement 0 def |
| 209 |
end def |
| 210 |
/CMapName /OneByteIdentityH def |
| 211 |
/CMapVersion 1.000 def |
| 212 |
/CMapType 1 def |
| 213 |
/UIDOffset 0 def |
| 214 |
/XUID [1 10 25404 9999] def |
| 215 |
/WMode 0 def |
| 216 |
1 begincodespacerange |
| 217 |
<00> <FF> |
| 218 |
endcodespacerange |
| 219 |
1 begincidrange |
| 220 |
<00> <FF> 0 |
| 221 |
endcidrange |
| 222 |
endcmap |
| 223 |
CMapName currentdict /CMap defineresource pop |
| 224 |
end |
| 225 |
end |
| 226 |
)"; |
| 227 |
|
| 228 |
SpanStreamDevice device(OneByteIdentity); |
| 229 |
auto map = PdfCMapEncoding::Parse(device); |
| 230 |
REQUIRE(map.GetCharMap().IsTrivialIdentity()); |
| 231 |
} |
| 232 |
|
| 233 |
void PdfEncodingTest::TestToUnicodeParse() |
| 234 |
{ |
| 235 |
string_view toUnicode = |
| 236 |
"3 beginbfrange\n" |
| 237 |
"<0001> <0004> <1001>\n" |
| 238 |
"<0005> <000A> [<000A> <0009> <0008> <0007> <0006> <0005>]\n" |
| 239 |
"<000B> <000F> <100B>\n" |
| 240 |
"endbfrange\n"; |
| 241 |
charbuff encodedStr("\x00\x01\x00\x02\x00\x03\x00\x04\x00\x05\x00\x06\x00\x07\x00\x08\x00\x09\x00\x0A\x00\x0B\x00\x0C\x00\x0D\x00\x0E\x00\x0F"sv); |
| 242 |
string expected("\xE1\x80\x81\xE1\x80\x82\xE1\x80\x83\xE1\x80\x84\x0A\x09\x08\x07\x06\x05\xE1\x80\x8B\xE1\x80\x8C\xE1\x80\x8D\xE1\x80\x8E\xE1\x80\x8F"sv); |
| 243 |
|
| 244 |
PdfMemDocument doc; |
| 245 |
auto& toUnicodeObj = doc.GetObjects().CreateDictionaryObject(); |
| 246 |
toUnicodeObj.GetOrCreateStream().SetData(toUnicode); |
| 247 |
|
| 248 |
PdfEncoding encoding(PdfEncodingMapConstPtr(new PdfIdentityEncoding(PdfEncodingMapType::Indeterminate, 2)), PdfEncodingMapFactory::ParseCMapEncoding(toUnicodeObj)); |
| 249 |
|
| 250 |
auto utf8str = encoding.ConvertToUtf8(PdfString::FromRaw(encodedStr)); |
| 251 |
REQUIRE(utf8str == expected); |
| 252 |
|
| 253 |
const char* toUnicodeInvalidTests[] = |
| 254 |
{ |
| 255 |
// missing object numbers |
| 256 |
"beginbfrange\n", |
| 257 |
"beginbfchar\n", |
| 258 |
|
| 259 |
// invalid hex digits |
| 260 |
"2 beginbfrange <WXYZ> endbfrange\n", |
| 261 |
"2 beginbfrange <-123> endbfrange\n", |
| 262 |
"2 beginbfrange <<00>> endbfrange\n", |
| 263 |
|
| 264 |
// missing hex digits |
| 265 |
"2 beginbfrange <> endbfrange\n", |
| 266 |
|
| 267 |
// empty array |
| 268 |
"2 beginbfrange [] endbfrange\n", |
| 269 |
|
| 270 |
nullptr |
| 271 |
}; |
| 272 |
|
| 273 |
for (size_t i = 0; toUnicodeInvalidTests[i] != nullptr; i++) |
| 274 |
{ |
| 275 |
try |
| 276 |
{ |
| 277 |
PdfIndirectObjectList invalidList; |
| 278 |
auto& invalidObject = invalidList.CreateDictionaryObject(); |
| 279 |
invalidObject.GetOrCreateStream().SetData(bufferview(toUnicodeInvalidTests[i], char_traits<char>::length(toUnicodeInvalidTests[i]))); |
| 280 |
|
| 281 |
PdfEncoding encodingTestInvalid(PdfEncodingMapConstPtr(new PdfIdentityEncoding(PdfEncodingMapType::Indeterminate, 2)), PdfEncodingMapFactory::ParseCMapEncoding(invalidObject)); |
| 282 |
|
| 283 |
auto unicodeStringTestInvalid = encodingTestInvalid.ConvertToUtf8(PdfString::FromRaw(encodedStr)); |
| 284 |
|
| 285 |
// exception not thrown - should never get here |
| 286 |
// TODO not all invalid input throws an exception (e.g. no hex digits in <WXYZ>) |
| 287 |
FAIL(); |
| 288 |
} |
| 289 |
catch (PdfError&) |
| 290 |
{ |
| 291 |
// parsing every invalid test string should throw an exception |
| 292 |
} |
| 293 |
catch (exception&) |
| 294 |
{ |
| 295 |
FAIL("Unexpected exception type"); |
| 296 |
} |
| 297 |
} |
| 298 |
} |
| 299 |
|
| 300 |
void outofRangeHelper(PdfEncoding& encoding) |
| 301 |
{ |
| 302 |
(void)encoding.GetCodePoint(encoding.GetFirstChar()); |
| 303 |
REQUIRE(encoding.GetCodePoint(encoding.GetFirstChar().Code - 1) == U'\0'); |
| 304 |
(void)encoding.GetCodePoint(encoding.GetLastChar()); |
| 305 |
REQUIRE(encoding.GetCodePoint(encoding.GetLastChar().Code + 1) == U'\0'); |
| 306 |
} |