mirror of
https://github.com/qpdf/qpdf.git
synced 2024-11-11 07:30:57 +00:00
cb769c62e5
This comment expands all tabs using an 8-character tab-width. You should ignore this commit when using git blame or use git blame -w. In the early days, I used to use tabs where possible for indentation, since emacs did this automatically. In recent years, I have switched to only using spaces, which means qpdf source code has been a mixture of spaces and tabs. I have avoided cleaning this up because of not wanting gratuitous whitespaces change to cloud the output of git blame, but I changed my mind after discussing with users who view qpdf source code in editors/IDEs that have other tab widths by default and in light of the fact that I am planning to start applying automatic code formatting soon.
318 lines
8.8 KiB
C++
318 lines
8.8 KiB
C++
#include <qpdf/QPDFTokenizer.hh>
|
|
#include <qpdf/QPDFPageDocumentHelper.hh>
|
|
#include <qpdf/QPDFPageObjectHelper.hh>
|
|
#include <qpdf/QUtil.hh>
|
|
#include <qpdf/FileInputSource.hh>
|
|
#include <qpdf/BufferInputSource.hh>
|
|
#include <qpdf/QPDF.hh>
|
|
#include <qpdf/Pl_Buffer.hh>
|
|
#include <qpdf/QIntC.hh>
|
|
#include <stdlib.h>
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
#include <iostream>
|
|
|
|
static char const* whoami = 0;
|
|
|
|
void usage()
|
|
{
|
|
std::cerr << "Usage: " << whoami
|
|
<< " [-maxlen len | -no-ignorable] filename"
|
|
<< std::endl;
|
|
exit(2);
|
|
}
|
|
|
|
class Finder: public InputSource::Finder
|
|
{
|
|
public:
|
|
Finder(PointerHolder<InputSource> is, std::string const& str) :
|
|
is(is),
|
|
str(str)
|
|
{
|
|
}
|
|
virtual ~Finder()
|
|
{
|
|
}
|
|
virtual bool check();
|
|
|
|
private:
|
|
PointerHolder<InputSource> is;
|
|
std::string str;
|
|
};
|
|
|
|
bool
|
|
Finder::check()
|
|
{
|
|
QPDFTokenizer tokenizer;
|
|
QPDFTokenizer::Token t = tokenizer.readToken(is, "finder", true);
|
|
qpdf_offset_t offset = this->is->tell();
|
|
bool result = (t == QPDFTokenizer::Token(QPDFTokenizer::tt_word, str));
|
|
this->is->seek(offset - QIntC::to_offset(this->str.length()), SEEK_SET);
|
|
return result;
|
|
}
|
|
|
|
static char const* tokenTypeName(QPDFTokenizer::token_type_e ttype)
|
|
{
|
|
// Do this is a case statement instead of a lookup so the compiler
|
|
// will warn if we miss any.
|
|
switch (ttype)
|
|
{
|
|
case QPDFTokenizer::tt_bad:
|
|
return "bad";
|
|
case QPDFTokenizer::tt_array_close:
|
|
return "array_close";
|
|
case QPDFTokenizer::tt_array_open:
|
|
return "array_open";
|
|
case QPDFTokenizer::tt_brace_close:
|
|
return "brace_close";
|
|
case QPDFTokenizer::tt_brace_open:
|
|
return "brace_open";
|
|
case QPDFTokenizer::tt_dict_close:
|
|
return "dict_close";
|
|
case QPDFTokenizer::tt_dict_open:
|
|
return "dict_open";
|
|
case QPDFTokenizer::tt_integer:
|
|
return "integer";
|
|
case QPDFTokenizer::tt_name:
|
|
return "name";
|
|
case QPDFTokenizer::tt_real:
|
|
return "real";
|
|
case QPDFTokenizer::tt_string:
|
|
return "string";
|
|
case QPDFTokenizer::tt_null:
|
|
return "null";
|
|
case QPDFTokenizer::tt_bool:
|
|
return "bool";
|
|
case QPDFTokenizer::tt_word:
|
|
return "word";
|
|
case QPDFTokenizer::tt_eof:
|
|
return "eof";
|
|
case QPDFTokenizer::tt_space:
|
|
return "space";
|
|
case QPDFTokenizer::tt_comment:
|
|
return "comment";
|
|
case QPDFTokenizer::tt_inline_image:
|
|
return "inline-image";
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static std::string
|
|
sanitize(std::string const& value)
|
|
{
|
|
std::string result;
|
|
for (std::string::const_iterator iter = value.begin(); iter != value.end();
|
|
++iter)
|
|
{
|
|
if ((*iter >= 32) && (*iter <= 126))
|
|
{
|
|
result.append(1, *iter);
|
|
}
|
|
else
|
|
{
|
|
result += "\\x" + QUtil::int_to_string_base(
|
|
static_cast<unsigned char>(*iter), 16, 2);
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
static void
|
|
try_skipping(QPDFTokenizer& tokenizer, PointerHolder<InputSource> is,
|
|
size_t max_len, char const* what, Finder& f)
|
|
{
|
|
std::cout << "skipping to " << what << std::endl;
|
|
qpdf_offset_t offset = is->tell();
|
|
if (! is->findFirst(what, offset, 0, f))
|
|
{
|
|
std::cout << what << " not found" << std::endl;
|
|
is->seek(offset, SEEK_SET);
|
|
}
|
|
}
|
|
|
|
static void
|
|
dump_tokens(PointerHolder<InputSource> is, std::string const& label,
|
|
size_t max_len, bool include_ignorable,
|
|
bool skip_streams, bool skip_inline_images)
|
|
{
|
|
Finder f1(is, "endstream");
|
|
std::cout << "--- BEGIN " << label << " ---" << std::endl;
|
|
bool done = false;
|
|
QPDFTokenizer tokenizer;
|
|
tokenizer.allowEOF();
|
|
if (include_ignorable)
|
|
{
|
|
tokenizer.includeIgnorable();
|
|
}
|
|
qpdf_offset_t inline_image_offset = 0;
|
|
while (! done)
|
|
{
|
|
QPDFTokenizer::Token token =
|
|
tokenizer.readToken(is, "test", true,
|
|
inline_image_offset ? 0 : max_len);
|
|
if (inline_image_offset && (token.getType() == QPDFTokenizer::tt_bad))
|
|
{
|
|
std::cout << "EI not found; resuming normal scanning" << std::endl;
|
|
is->seek(inline_image_offset, SEEK_SET);
|
|
inline_image_offset = 0;
|
|
continue;
|
|
}
|
|
inline_image_offset = 0;
|
|
|
|
qpdf_offset_t offset = is->getLastOffset();
|
|
std::cout << offset << ": "
|
|
<< tokenTypeName(token.getType());
|
|
if (token.getType() != QPDFTokenizer::tt_eof)
|
|
{
|
|
std::cout << ": "
|
|
<< sanitize(token.getValue());
|
|
if (token.getValue() != token.getRawValue())
|
|
{
|
|
std::cout << " (raw: " << sanitize(token.getRawValue()) << ")";
|
|
}
|
|
}
|
|
if (! token.getErrorMessage().empty())
|
|
{
|
|
std::cout << " (" << token.getErrorMessage() << ")";
|
|
}
|
|
std::cout << std::endl;
|
|
if (skip_streams &&
|
|
(token == QPDFTokenizer::Token(QPDFTokenizer::tt_word, "stream")))
|
|
{
|
|
try_skipping(tokenizer, is, max_len, "endstream", f1);
|
|
}
|
|
else if (skip_inline_images &&
|
|
(token == QPDFTokenizer::Token(QPDFTokenizer::tt_word, "ID")))
|
|
{
|
|
char ch;
|
|
is->read(&ch, 1);
|
|
tokenizer.expectInlineImage(is);
|
|
inline_image_offset = is->tell();
|
|
}
|
|
else if (token.getType() == QPDFTokenizer::tt_eof)
|
|
{
|
|
done = true;
|
|
}
|
|
}
|
|
std::cout << "--- END " << label << " ---" << std::endl;
|
|
}
|
|
|
|
static void process(char const* filename, bool include_ignorable,
|
|
size_t max_len)
|
|
{
|
|
PointerHolder<InputSource> is;
|
|
|
|
// Tokenize file, skipping streams
|
|
FileInputSource* fis = new FileInputSource();
|
|
fis->setFilename(filename);
|
|
is = PointerHolder<InputSource>(fis);
|
|
dump_tokens(is, "FILE", max_len, include_ignorable, true, false);
|
|
|
|
// Tokenize content streams, skipping inline images
|
|
QPDF qpdf;
|
|
qpdf.processFile(filename);
|
|
std::vector<QPDFPageObjectHelper> pages =
|
|
QPDFPageDocumentHelper(qpdf).getAllPages();
|
|
int pageno = 0;
|
|
for (std::vector<QPDFPageObjectHelper>::iterator iter = pages.begin();
|
|
iter != pages.end(); ++iter)
|
|
{
|
|
++pageno;
|
|
Pl_Buffer plb("buffer");
|
|
(*iter).pipeContents(&plb);
|
|
auto content_data = plb.getBufferSharedPointer();
|
|
BufferInputSource* bis = new BufferInputSource(
|
|
"content data", content_data.get());
|
|
is = PointerHolder<InputSource>(bis);
|
|
dump_tokens(is, "PAGE " + QUtil::int_to_string(pageno),
|
|
max_len, include_ignorable, false, true);
|
|
}
|
|
|
|
// Tokenize object streams
|
|
std::vector<QPDFObjectHandle> all = qpdf.getAllObjects();
|
|
for (std::vector<QPDFObjectHandle>::iterator iter = all.begin();
|
|
iter != all.end(); ++iter)
|
|
{
|
|
if ((*iter).isStream() &&
|
|
(*iter).getDict().getKey("/Type").isName() &&
|
|
(*iter).getDict().getKey("/Type").getName() == "/ObjStm")
|
|
{
|
|
PointerHolder<Buffer> b =
|
|
(*iter).getStreamData(qpdf_dl_specialized);
|
|
BufferInputSource* bis = new BufferInputSource(
|
|
"object stream data", b.get());
|
|
is = PointerHolder<InputSource>(bis);
|
|
dump_tokens(is, "OBJECT STREAM " +
|
|
QUtil::int_to_string((*iter).getObjectID()),
|
|
max_len, include_ignorable, false, false);
|
|
}
|
|
}
|
|
}
|
|
|
|
int main(int argc, char* argv[])
|
|
{
|
|
QUtil::setLineBuf(stdout);
|
|
if ((whoami = strrchr(argv[0], '/')) == NULL)
|
|
{
|
|
whoami = argv[0];
|
|
}
|
|
else
|
|
{
|
|
++whoami;
|
|
}
|
|
// For libtool's sake....
|
|
if (strncmp(whoami, "lt-", 3) == 0)
|
|
{
|
|
whoami += 3;
|
|
}
|
|
|
|
char const* filename = 0;
|
|
size_t max_len = 0;
|
|
bool include_ignorable = true;
|
|
for (int i = 1; i < argc; ++i)
|
|
{
|
|
if (argv[i][0] == '-')
|
|
{
|
|
if (strcmp(argv[i], "-maxlen") == 0)
|
|
{
|
|
if (++i >= argc)
|
|
{
|
|
usage();
|
|
}
|
|
max_len = QUtil::string_to_uint(argv[i]);
|
|
}
|
|
else if (strcmp(argv[i], "-no-ignorable") == 0)
|
|
{
|
|
include_ignorable = false;
|
|
}
|
|
else
|
|
{
|
|
usage();
|
|
}
|
|
}
|
|
else if (filename)
|
|
{
|
|
usage();
|
|
}
|
|
else
|
|
{
|
|
filename = argv[i];
|
|
}
|
|
}
|
|
if (filename == 0)
|
|
{
|
|
usage();
|
|
}
|
|
|
|
try
|
|
{
|
|
process(filename, include_ignorable, max_len);
|
|
}
|
|
catch (std::exception& e)
|
|
{
|
|
std::cerr << whoami << ": exception: " << e.what();
|
|
exit(2);
|
|
}
|
|
return 0;
|
|
}
|