void CFDF_Document::ParseStream(IFX_FileRead *pFile, FX_BOOL bOwnFile)
{
m_pFile = pFile;
m_bOwnFile = bOwnFile;
CPDF_SyntaxParser parser;
parser.InitParser(m_pFile, 0);
while (1) {
FX_BOOL bNumber;
CFX_ByteString word = parser.GetNextWord(bNumber);
if (bNumber) {
FX_DWORD objnum = FXSYS_atoi(word);
word = parser.GetNextWord(bNumber);
if (!bNumber) {
break;
}
word = parser.GetNextWord(bNumber);
if (word != FX_BSTRC("obj")) {
break;
}
CPDF_Object* pObj = parser.GetObject(this, objnum, 0, FALSE);
if (pObj == NULL) {
break;
}
InsertIndirectObject(objnum, pObj);
word = parser.GetNextWord(bNumber);
if (word != FX_BSTRC("endobj")) {
break;
}
} else {
if (word != FX_BSTRC("trailer")) {
break;
}
CPDF_Dictionary* pMainDict = (CPDF_Dictionary*)parser.GetObject(this, 0, 0, 0);
if (pMainDict == NULL || pMainDict->GetType() != PDFOBJ_DICTIONARY) {
break;
}
m_pRootDict = pMainDict->GetDict(FX_BSTRC("Root"));
pMainDict->Release();
break;
}
}
}
void CFDF_Document::ParseStream(IFX_FileRead* pFile, FX_BOOL bOwnFile) {
m_pFile = pFile;
m_bOwnFile = bOwnFile;
CPDF_SyntaxParser parser;
parser.InitParser(m_pFile, 0);
while (1) {
bool bNumber;
CFX_ByteString word = parser.GetNextWord(&bNumber);
if (bNumber) {
FX_DWORD objnum = FXSYS_atoi(word);
word = parser.GetNextWord(&bNumber);
if (!bNumber) {
break;
}
word = parser.GetNextWord(nullptr);
if (word != "obj") {
break;
}
CPDF_Object* pObj = parser.GetObject(this, objnum, 0, true);
if (!pObj) {
break;
}
InsertIndirectObject(objnum, pObj);
word = parser.GetNextWord(nullptr);
if (word != "endobj") {
break;
}
} else {
if (word != "trailer") {
break;
}
if (CPDF_Dictionary* pMainDict =
ToDictionary(parser.GetObject(this, 0, 0, true))) {
m_pRootDict = pMainDict->GetDictBy("Root");
pMainDict->Release();
}
break;
}
}
}
void CFDF_Document::ParseStream(IFX_FileRead* pFile, FX_BOOL bOwnFile) {
m_pFile = pFile;
m_bOwnFile = bOwnFile;
CPDF_SyntaxParser parser;
parser.InitParser(m_pFile, 0);
while (1) {
bool bNumber;
CFX_ByteString word = parser.GetNextWord(&bNumber);
if (bNumber) {
uint32_t objnum = FXSYS_atoui(word.c_str());
word = parser.GetNextWord(&bNumber);
if (!bNumber)
break;
word = parser.GetNextWord(nullptr);
if (word != "obj")
break;
CPDF_Object* pObj = parser.GetObject(this, objnum, 0, true);
if (!pObj)
break;
ReplaceIndirectObjectIfHigherGeneration(objnum, pObj);
word = parser.GetNextWord(nullptr);
if (word != "endobj")
break;
} else {
if (word != "trailer")
break;
if (CPDF_Dictionary* pMainDict =
ToDictionary(parser.GetObject(this, 0, 0, true))) {
m_pRootDict = pMainDict->GetDictFor("Root");
pMainDict->Release();
}
break;
}
}
}
TEST(cpdf_syntax_parser, ReadHexString) {
{
// Empty string.
uint8_t data[] = "";
ScopedFileStream stream(FX_CreateMemoryStream(data, 0, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("", parser.ReadHexString());
EXPECT_EQ(0, parser.SavePos());
}
{
// Blank string.
uint8_t data[] = " ";
ScopedFileStream stream(FX_CreateMemoryStream(data, 2, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("", parser.ReadHexString());
EXPECT_EQ(2, parser.SavePos());
}
{
// Skips unknown characters.
uint8_t data[] = "z12b";
ScopedFileStream stream(FX_CreateMemoryStream(data, 4, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\x12\xb0", parser.ReadHexString());
EXPECT_EQ(4, parser.SavePos());
}
{
// Skips unknown characters.
uint8_t data[] = "*<&*#$^&@1";
ScopedFileStream stream(FX_CreateMemoryStream(data, 10, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\x10", parser.ReadHexString());
EXPECT_EQ(10, parser.SavePos());
}
{
// Skips unknown characters.
uint8_t data[] = "\x80zab";
ScopedFileStream stream(FX_CreateMemoryStream(data, 4, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\xab", parser.ReadHexString());
EXPECT_EQ(4, parser.SavePos());
}
{
// Skips unknown characters.
uint8_t data[] = "\xffzab";
ScopedFileStream stream(FX_CreateMemoryStream(data, 4, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\xab", parser.ReadHexString());
EXPECT_EQ(4, parser.SavePos());
}
{
// Regular conversion.
uint8_t data[] = "1A2b>abcd";
ScopedFileStream stream(FX_CreateMemoryStream(data, 9, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\x1a\x2b", parser.ReadHexString());
EXPECT_EQ(5, parser.SavePos());
}
{
// Position out of bounds.
uint8_t data[] = "12ab>";
ScopedFileStream stream(FX_CreateMemoryStream(data, 5, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
parser.RestorePos(5);
EXPECT_EQ("", parser.ReadHexString());
parser.RestorePos(6);
EXPECT_EQ("", parser.ReadHexString());
parser.RestorePos(-1);
EXPECT_EQ("", parser.ReadHexString());
parser.RestorePos(std::numeric_limits<FX_FILESIZE>::max());
EXPECT_EQ("", parser.ReadHexString());
// Check string still parses when set to 0.
parser.RestorePos(0);
EXPECT_EQ("\x12\xab", parser.ReadHexString());
}
{
// Missing ending >.
uint8_t data[] = "1A2b";
ScopedFileStream stream(FX_CreateMemoryStream(data, 4, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\x1a\x2b", parser.ReadHexString());
EXPECT_EQ(4, parser.SavePos());
}
{
// Missing ending >.
uint8_t data[] = "12abz";
ScopedFileStream stream(FX_CreateMemoryStream(data, 5, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\x12\xab", parser.ReadHexString());
EXPECT_EQ(5, parser.SavePos());
}
{
// Uneven number of bytes.
uint8_t data[] = "1A2>asdf";
ScopedFileStream stream(FX_CreateMemoryStream(data, 8, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\x1a\x20", parser.ReadHexString());
EXPECT_EQ(4, parser.SavePos());
}
{
// Uneven number of bytes.
uint8_t data[] = "1A2zasdf";
ScopedFileStream stream(FX_CreateMemoryStream(data, 8, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("\x1a\x2a\xdf", parser.ReadHexString());
EXPECT_EQ(8, parser.SavePos());
}
{
// Just ending character.
uint8_t data[] = ">";
ScopedFileStream stream(FX_CreateMemoryStream(data, 1, FALSE));
CPDF_SyntaxParser parser;
parser.InitParser(stream.get(), 0);
EXPECT_EQ("", parser.ReadHexString());
EXPECT_EQ(1, parser.SavePos());
}
}