premiere-libtorrent/include/libtorrent/bencode.hpp

442 lines
12 KiB
C++
Raw Normal View History

/*
Copyright (c) 2003-2016, Arvid Norberg
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in
the documentation and/or other materials provided with the distribution.
* Neither the name of the author nor the names of its
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef TORRENT_BENCODE_HPP_INCLUDED
#define TORRENT_BENCODE_HPP_INCLUDED
2013-08-17 04:00:41 +02:00
// OVERVIEW
//
2015-03-14 22:55:26 +01:00
// Bencoding is a common representation in bittorrent used for for dictionary,
// list, int and string hierarchies. It's used to encode .torrent files and
// some messages in the network protocol. libtorrent also uses it to store
// settings, resume data and other state between sessions.
2013-08-17 04:00:41 +02:00
//
2015-03-14 22:55:26 +01:00
// Strings in bencoded structures are not necessarily representing text.
// Strings are raw byte buffers of a certain length. If a string is meant to be
// interpreted as text, it is required to be UTF-8 encoded. See `BEP 3`_.
2013-08-17 04:00:41 +02:00
//
// There are two mechanisms to *decode* bencoded buffers in libtorrent.
2013-08-17 04:00:41 +02:00
//
// The most flexible one is `bdecode() bencode()`_, which returns a structure
// represented by entry. Once a buffer has been decoded with this function, it
2015-03-14 22:55:26 +01:00
// can be discarded. The entry does not contain any references back to it. This
// means that bdecode() copies all the data out of the buffer and into its own
// hierarchy. This makes this function expensive, which might matter if you're
// parsing large amounts of data.
2013-08-17 04:00:41 +02:00
//
// Another consideration is that `bdecode() bencode()`_ is a recursive parser.
2015-03-14 22:55:26 +01:00
// For this reason, in order to avoid DoS attacks by triggering a stack
// overflow, there is a recursion limit. This limit is a sanity check to make
// sure it doesn't run the risk of busting the stack.
2013-08-17 04:00:41 +02:00
//
2015-03-14 22:55:26 +01:00
// The second mechanism is the decode function for bdecode_node. This function
// builds a tree that points back into the original buffer. The returned
// bdecode_node will not be valid once the buffer it was parsed out of is
// discarded.
2013-08-17 04:00:41 +02:00
//
2015-03-14 22:55:26 +01:00
// Not only is this function more efficient because of less memory allocation
// and data copy, the parser is also not recursive, which means it probably
// performs a little bit better and can have a higher recursion limit on the
// structures it's parsing.
#include <string>
#include <iterator> // for distance
#include "libtorrent/config.hpp"
#include "libtorrent/entry.hpp"
2007-09-10 08:12:41 +02:00
#include "libtorrent/assert.hpp"
#include "libtorrent/io.hpp" // for write_string
#include "libtorrent/string_util.hpp" // for is_digit
namespace libtorrent
{
2014-11-29 10:12:44 +01:00
#ifndef TORRENT_NO_DEPRECATE
using invalid_encoding = system_error;
2014-11-29 10:12:44 +01:00
#endif
namespace detail
{
template <class OutIt>
int write_integer(OutIt& out, entry::integer_type val)
{
2005-08-12 14:40:58 +02:00
// the stack allocated buffer for keeping the
// decimal representation of the number can
// not hold number bigger than this:
static_assert(sizeof(entry::integer_type) <= 8, "64 bit integers required");
2005-08-12 14:40:58 +02:00
char buf[21];
int ret = 0;
2005-08-12 14:40:58 +02:00
for (char const* str = integer_to_str(buf, 21, val);
*str != 0; ++str)
{
*out = *str;
++out;
++ret;
2005-08-12 14:40:58 +02:00
}
return ret;
2015-08-08 08:33:54 +02:00
}
template <class OutIt>
void write_char(OutIt& out, char c)
{
*out = c;
++out;
}
template <class InIt>
std::string read_until(InIt& in, InIt end, char end_token, bool& err)
{
std::string ret;
if (in == end)
{
err = true;
return ret;
}
while (*in != end_token)
{
ret += *in;
++in;
if (in == end)
{
err = true;
return ret;
}
}
return ret;
}
template<class InIt>
void read_string(InIt& in, InIt end, int len, std::string& str, bool& err)
{
TORRENT_ASSERT(len >= 0);
for (int i = 0; i < len; ++i)
{
if (in == end)
{
err = true;
return;
}
str += *in;
++in;
}
}
template<class OutIt>
int bencode_recursive(OutIt& out, const entry& e)
{
int ret = 0;
switch(e.type())
{
case entry::int_t:
write_char(out, 'i');
ret += write_integer(out, e.integer());
write_char(out, 'e');
ret += 2;
break;
case entry::string_t:
ret += write_integer(out, e.string().length());
write_char(out, ':');
ret += write_string(e.string(), out);
ret += 1;
break;
case entry::list_t:
write_char(out, 'l');
for (entry::list_type::const_iterator i = e.list().begin(); i != e.list().end(); ++i)
ret += bencode_recursive(out, *i);
write_char(out, 'e');
ret += 2;
break;
case entry::dictionary_t:
write_char(out, 'd');
2004-01-26 11:29:00 +01:00
for (entry::dictionary_type::const_iterator i = e.dict().begin();
i != e.dict().end(); ++i)
{
// write key
ret += write_integer(out, i->first.length());
write_char(out, ':');
ret += write_string(i->first, out);
// write value
ret += bencode_recursive(out, i->second);
ret += 1;
}
write_char(out, 'e');
ret += 2;
break;
case entry::preformatted_t:
std::copy(e.preformatted().begin(), e.preformatted().end(), out);
2016-05-07 07:34:54 +02:00
ret += int(e.preformatted().size());
break;
case entry::undefined_t:
// empty string
write_char(out, '0');
write_char(out, ':');
ret += 2;
break;
}
return ret;
}
template<class InIt>
void bdecode_recursive(InIt& in, InIt end, entry& ret, bool& err, int depth)
{
if (depth >= 100)
{
err = true;
return;
}
if (in == end)
{
err = true;
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
switch (*in)
{
// ----------------------------------------------
// integer
case 'i':
{
2015-06-03 07:12:54 +02:00
++in; // 'i'
std::string val = read_until(in, end, 'e', err);
if (err) return;
TORRENT_ASSERT(*in == 'e');
2015-06-03 07:12:54 +02:00
++in; // 'e'
ret = entry(entry::int_t);
char* end_pointer;
ret.integer() = strtoll(val.c_str(), &end_pointer, 10);
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
if (end_pointer == val.c_str())
{
err = true;
return;
}
} break;
// ----------------------------------------------
// list
case 'l':
{
ret = entry(entry::list_t);
++in; // 'l'
while (*in != 'e')
{
2004-03-05 13:04:47 +01:00
ret.list().push_back(entry());
entry& e = ret.list().back();
bdecode_recursive(in, end, e, err, depth + 1);
if (err)
{
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
if (in == end)
{
err = true;
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
}
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
TORRENT_ASSERT(*in == 'e');
++in; // 'e'
} break;
// ----------------------------------------------
// dictionary
case 'd':
{
ret = entry(entry::dictionary_t);
++in; // 'd'
while (*in != 'e')
{
2004-03-05 13:04:47 +01:00
entry key;
bdecode_recursive(in, end, key, err, depth + 1);
if (err || key.type() != entry::string_t)
2015-06-03 07:12:54 +02:00
{
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
2004-03-05 13:04:47 +01:00
entry& e = ret[key.string()];
bdecode_recursive(in, end, e, err, depth + 1);
if (err)
{
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
if (in == end)
{
err = true;
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
}
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
TORRENT_ASSERT(*in == 'e');
++in; // 'e'
} break;
// ----------------------------------------------
// string
default:
if (is_digit(std::uint8_t(*in)))
{
std::string len_s = read_until(in, end, ':', err);
if (err)
{
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
TORRENT_ASSERT(*in == ':');
++in; // ':'
int len = atoi(len_s.c_str());
ret = entry(entry::string_t);
read_string(in, end, len, ret.string(), err);
if (err)
{
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
}
else
{
err = true;
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
return;
}
#if TORRENT_USE_ASSERTS
ret.m_type_queried = false;
#endif
}
}
}
2015-06-03 07:12:54 +02:00
// These functions will encode data to bencoded or decode bencoded data.
2013-08-08 03:03:54 +02:00
//
// If possible, ``bdecode()`` producing a bdecode_node should be preferred
// over this function.
2013-08-08 03:03:54 +02:00
//
// The entry_ class is the internal representation of the bencoded data
// and it can be used to retrieve information, an entry_ can also be build by
// the program and given to ``bencode()`` to encode it into the ``OutIt``
// iterator.
//
// The ``OutIt`` and ``InIt`` are iterators
// (InputIterator_ and OutputIterator_ respectively). They
// are templates and are usually instantiated as ostream_iterator_,
// back_insert_iterator_ or istream_iterator_. These
// functions will assume that the iterator refers to a character
// (``char``). So, if you want to encode entry ``e`` into a buffer
// in memory, you can do it like this::
//
// std::vector<char> buffer;
// bencode(std::back_inserter(buf), e);
//
// .. _InputIterator: http://www.sgi.com/tech/stl/InputIterator.html
// .. _OutputIterator: http://www.sgi.com/tech/stl/OutputIterator.html
// .. _ostream_iterator: http://www.sgi.com/tech/stl/ostream_iterator.html
// .. _back_insert_iterator: http://www.sgi.com/tech/stl/back_insert_iterator.html
// .. _istream_iterator: http://www.sgi.com/tech/stl/istream_iterator.html
//
// If you want to decode a torrent file from a buffer in memory, you can do it like this::
//
// std::vector<char> buffer;
// // ...
// entry e = bdecode(buf.begin(), buf.end());
//
// Or, if you have a raw char buffer::
//
// const char* buf;
// // ...
2013-08-08 03:03:54 +02:00
// entry e = bdecode(buf, buf + data_size);
//
// Now we just need to know how to retrieve information from the entry.
//
// If ``bdecode()`` encounters invalid encoded data in the range given to it
2014-11-29 10:12:44 +01:00
// it will return a default constructed ``entry`` object.
2013-08-12 18:24:37 +02:00
template<class OutIt> int bencode(OutIt out, const entry& e)
{
return detail::bencode_recursive(out, e);
}
2013-08-12 18:24:37 +02:00
template<class InIt> entry bdecode(InIt start, InIt end)
{
entry e;
bool err = false;
detail::bdecode_recursive(start, end, e, err, 0);
TORRENT_ASSERT(e.m_type_queried == false);
2008-06-24 00:00:27 +02:00
if (err) return entry();
return e;
}
2013-08-12 18:24:37 +02:00
template<class InIt> entry bdecode(InIt start, InIt end, int& len)
{
entry e;
bool err = false;
InIt s = start;
detail::bdecode_recursive(start, end, e, err, 0);
len = std::distance(s, start);
TORRENT_ASSERT(len >= 0);
2008-06-24 00:00:27 +02:00
if (err) return entry();
return e;
}
}
#endif // TORRENT_BENCODE_HPP_INCLUDED