# Copyright (c) 2007, Kundan Singh. All rights reserved. See LICENSING for details.
import socket, time class attrs(object): '''A generic class that allows uniformly accessing the attribute and items, and returns None for invalid attribute instead of throwing an acception.''' def __init__(self, **kwargs): for n,v in kwargs.items(): self[n] = v # attribute access: use container if not found def __getattr__(self, name): return self.__getitem__(name) # container access: use key in __dict__ def __getitem__(self, name): return self.__dict__.get(name, None) def __setitem__(self, name, value): self.__dict__[name] = value def __contains__(self, name): return name in self.__dict__ #def __repr__(self): return repr(self.__dict__)
When initiating multimedia teleconferences, voice-over-IP calls, streaming video, or other sessions, there is a requirement to convey media details, transport addresses, and other session description metadata to the participants. SDP provides a standard representation for such information, irrespective of how that information is transported. SDP is purely a format for session description -- it does not incorporate a transport protocol, and it is intended to use different transport protocols as appropriate, including the Session Announcement Protocol [14], Session Initiation Protocol [15], Real Time Streaming Protocol [16], electronic mail using the MIME extensions, and the Hypertext Transport Protocol. SDP is intended to be general purpose so that it can be used in a wide range of network environments and applications. However, it is not intended to support negotiation of session content or media encodings: this is viewed as outside the scope of session description.
class SDP(attrs): '''A SDP packet with dynamic properties. The header names can be accessed as attributes or items. Accessing an unavailable header gives None instead of exception. ''' # header names that can appear multiple times. _multiple = 'tramb' def __init__(self, value=None): if value: self._parse(value)
5.2. Origin ("o=")
o=<username> <sess-id> <sess-version> <nettype> <addrtype>
<unicast-address>
The "o=" field gives the originator of the session (her username and
the address of the user's host) plus a session identifier and version
number:
<username> is the user's login on the originating host, or it is "-"
if the originating host does not support the concept of user IDs.
The <username> MUST NOT contain spaces.
<sess-id> is a numeric string such that the tuple of <username>,
<sess-id>, <nettype>, <addrtype>, and <unicast-address> forms a
globally unique identifier for the session. The method of
<sess-id> allocation is up to the creating tool, but it has been
suggested that a Network Time Protocol (NTP) format timestamp be
used to ensure uniqueness [13].
<sess-version> is a version number for this session description. Its
usage is up to the creating tool, so long as <sess-version> is
increased when a modification is made to the session data. Again,
it is RECOMMENDED that an NTP format timestamp is used.
<nettype> is a text string giving the type of network. Initially
"IN" is defined to have the meaning "Internet", but other values
MAY be registered in the future (see Section 8).
<addrtype> is a text string giving the type of the address that
follows. Initially "IP4" and "IP6" are defined, but other values
MAY be registered in the future (see Section 8).
<unicast-address> is the address of the machine from which the
session was created. For an address type of IP4, this is either
the fully qualified domain name of the machine or the dotted-
decimal representation of the IP version 4 address of the machine.
For an address type of IP6, this is either the fully qualified
domain name of the machine or the compressed textual
representation of the IP version 6 address of the machine. For
both IP4 and IP6, the fully qualified domain name is the form that
SHOULD be given unless this is unavailable, in which case the
globally unique address MAY be substituted. A local IP address
MUST NOT be used in any context where the SDP description might
leave the scope in which the address is meaningful (for example, a
local address MUST NOT be included in an application-level
referral that might leave the scope).
In general, the "o=" field serves as a globally unique identifier for
this version of this session description, and the subfields excepting
the version taken together identify the session irrespective of any
modifications.
For privacy reasons, it is sometimes desirable to obfuscate the
username and IP address of the session originator. If this is a
concern, an arbitrary <username> and private <unicast-address> MAY be
chosen to populate the "o=" field, provided that these are selected
in a manner that does not affect the global uniqueness of the field.
class originator(attrs):
'''Represents a o= line with attributes username (str), sessionid (long),
version (long), nettype (str), addrtype (str), address (str).'''
def __init__(self, value=None):
if value:
self.username, self.sessionid, self.version, self.nettype, self.addrtype, self.address = value.split(' ')
self.sessionid = int(self.sessionid)
self.version = int(self.version)
else:
hostname = socket.gethostname()
self.username, self.sessionid, self.version, self.nettype, self.addrtype, self.address = \
'-', int(time.time()), int(time.time()), 'IN', 'IP4', (hostname.find('.')>0 and hostname or socket.gethostbyname(hostname))
def __repr__(self):
return ' '.join(map(lambda x: str(x), [self.username, self.sessionid, self.version, self.nettype, self.addrtype, self.address]))
c=<nettype> <addrtype> <connection-address>
The "c=" field contains connection data.
A session description MUST contain either at least one "c=" field in
each media description or a single "c=" field at the session level.
It MAY contain a single session-level "c=" field and additional "c="
field(s) per media description, in which case the per-media values
override the session-level settings for the respective media.
The first sub-field ("<nettype>") is the network type, which is a
text string giving the type of network. Initially, "IN" is defined
to have the meaning "Internet", but other values MAY be registered in
the future (see Section 8).
The second sub-field ("<addrtype>") is the address type. This allows
SDP to be used for sessions that are not IP based. This memo only
defines IP4 and IP6, but other values MAY be registered in the future
(see Section 8).
The third sub-field ("<connection-address>") is the connection
address. OPTIONAL sub-fields MAY be added after the connection
address depending on the value of the <addrtype> field.
When the <addrtype> is IP4 and IP6, the connection address is defined
as follows:
o If the session is multicast, the connection address will be an IP
multicast group address. If the session is not multicast, then
the connection address contains the unicast IP address of the
expected data source or data relay or data sink as determined by
additional attribute fields. It is not expected that unicast
addresses will be given in a session description that is
communicated by a multicast announcement, though this is not
prohibited.
o Sessions using an IPv4 multicast connection address MUST also have
a time to live (TTL) value present in addition to the multicast
address. The TTL and the address together define the scope with
which multicast packets sent in this conference will be sent. TTL
values MUST be in the range 0-255. Although the TTL MUST be
specified, its use to scope multicast traffic is deprecated;
applications SHOULD use an administratively scoped address
instead.
The TTL for the session is appended to the address using a slash as a
separator. An example is:
c=IN IP4 224.2.36.42/127
IPv6 multicast does not use TTL scoping, and hence the TTL value MUST
NOT be present for IPv6 multicast. It is expected that IPv6 scoped
addresses will be used to limit the scope of conferences.
Hierarchical or layered encoding schemes are data streams where the
encoding from a single media source is split into a number of layers.
The receiver can choose the desired quality (and hence bandwidth) by
only subscribing to a subset of these layers. Such layered encodings
are normally transmitted in multiple multicast groups to allow
multicast pruning. This technique keeps unwanted traffic from sites
only requiring certain levels of the hierarchy. For applications
requiring multiple multicast groups, we allow the following notation
to be used for the connection address:
<base multicast address>[/<ttl>]/<number of addresses>
If the number of addresses is not given, it is assumed to be one.
Multicast addresses so assigned are contiguously allocated above the
base address, so that, for example:
c=IN IP4 224.2.1.1/127/3
would state that addresses 224.2.1.1, 224.2.1.2, and 224.2.1.3 are to
be used at a TTL of 127. This is semantically identical to including
multiple "c=" lines in a media description:
c=IN IP4 224.2.1.1/127
c=IN IP4 224.2.1.2/127
c=IN IP4 224.2.1.3/127
Similarly, an IPv6 example would be:
c=IN IP6 FF15::101/3
which is semantically equivalent to:
c=IN IP6 FF15::101
c=IN IP6 FF15::102
c=IN IP6 FF15::103
(remembering that the TTL field is not present in IPv6 multicast).
Multiple addresses or "c=" lines MAY be specified on a per-media
basis only if they provide multicast addresses for different layers
in a hierarchical or layered encoding scheme. They MUST NOT be
specified for a session-level "c=" field.
The slash notation for multiple addresses described above MUST NOT be
used for IP unicast addresses.
class connection(attrs):
'''Represents a c= line with attributes nettype (str), addrtype (str), address (str)
and optionally ttl (int) and count (int).'''
def __init__(self, value=None, **kwargs):
if value:
self.nettype, self.addrtype, rest = value.split(' ')
rest = rest.split('/')
if len(rest) == 1: self.address = rest[0]
elif len(rest) == 2: self.address, self.ttl = rest[0], int(rest[1])
else: self.address, self.ttl, self.count = rest[0], int(rest[1]), int(rest[2])
elif 'address' in kwargs:
self.address = kwargs.get('address')
self.nettype = kwargs.get('nettype', 'IN')
self.addrtype = kwargs.get('addrtype', 'IP4')
if 'ttl' in kwargs: self.ttl = int(kwargs.get('ttl'))
if 'count' in kwargs: self.count = int(kwargs.get('count'))
def __repr__(self):
return self.nettype + ' ' + self.addrtype + ' ' + self.address + ('/' + str(self.ttl) if self.ttl else '') + ('/' + str(self.count) if self.count else '')
m=<media> <port> <proto> <fmt> ...
A session description may contain a number of media descriptions.
Each media description starts with an "m=" field and is terminated by
either the next "m=" field or by the end of the session description.
A media field has several sub-fields:
<media> is the media type. Currently defined media are "audio",
"video", "text", "application", and "message", although this list
may be extended in the future (see Section 8).
<port> is the transport port to which the media stream is sent. The
meaning of the transport port depends on the network being used as
specified in the relevant "c=" field, and on the transport
protocol defined in the <proto> sub-field of the media field.
Other ports used by the media application (such as the RTP Control
Protocol (RTCP) port [19]) MAY be derived algorithmically from the
base media port or MAY be specified in a separate attribute (for
example, "a=rtcp:" as defined in [22]).
If non-contiguous ports are used or if they don't follow the
parity rule of even RTP ports and odd RTCP ports, the "a=rtcp:"
attribute MUST be used. Applications that are requested to send
media to a <port> that is odd and where the "a=rtcp:" is present
MUST NOT subtract 1 from the RTP port: that is, they MUST send the
RTP to the port indicated in <port> and send the RTCP to the port
indicated in the "a=rtcp" attribute.
For applications where hierarchically encoded streams are being
sent to a unicast address, it may be necessary to specify multiple
transport ports. This is done using a similar notation to that
used for IP multicast addresses in the "c=" field:
m=<media> <port>/<number of ports> <proto> <fmt> ...
In such a case, the ports used depend on the transport protocol.
For RTP, the default is that only the even-numbered ports are used
for data with the corresponding one-higher odd ports used for the
RTCP belonging to the RTP session, and the <number of ports>
denoting the number of RTP sessions. For example:
m=video 49170/2 RTP/AVP 31
would specify that ports 49170 and 49171 form one RTP/RTCP pair
and 49172 and 49173 form the second RTP/RTCP pair. RTP/AVP is the
transport protocol and 31 is the format (see below). If non-
contiguous ports are required, they must be signalled using a
separate attribute (for example, "a=rtcp:" as defined in [22]).
If multiple addresses are specified in the "c=" field and multiple
ports are specified in the "m=" field, a one-to-one mapping from
port to the corresponding address is implied. For example:
c=IN IP4 224.2.1.1/127/2
m=video 49170/2 RTP/AVP 31
would imply that address 224.2.1.1 is used with ports 49170 and
49171, and address 224.2.1.2 is used with ports 49172 and 49173.
The semantics of multiple "m=" lines using the same transport
address are undefined. This implies that, unlike limited past
practice, there is no implicit grouping defined by such means and
an explicit grouping framework (for example, [18]) should instead
be used to express the intended semantics.
<proto> is the transport protocol. The meaning of the transport
protocol is dependent on the address type field in the relevant
"c=" field. Thus a "c=" field of IP4 indicates that the transport
protocol runs over IP4. The following transport protocols are
defined, but may be extended through registration of new protocols
with IANA (see Section 8):
* udp: denotes an unspecified protocol running over UDP.
* RTP/AVP: denotes RTP [19] used under the RTP Profile for Audio
and Video Conferences with Minimal Control [20] running over
UDP.
* RTP/SAVP: denotes the Secure Real-time Transport Protocol [23]
running over UDP.
The main reason to specify the transport protocol in addition to
the media format is that the same standard media formats may be
carried over different transport protocols even when the network
protocol is the same -- a historical example is vat Pulse Code
Modulation (PCM) audio and RTP PCM audio; another might be TCP/RTP
PCM audio. In addition, relays and monitoring tools that are
transport-protocol-specific but format-independent are possible.
<fmt> is a media format description. The fourth and any subsequent
sub-fields describe the format of the media. The interpretation
of the media format depends on the value of the <proto> sub-field.
If the <proto> sub-field is "RTP/AVP" or "RTP/SAVP" the <fmt>
sub-fields contain RTP payload type numbers. When a list of
payload type numbers is given, this implies that all of these
payload formats MAY be used in the session, but the first of these
formats SHOULD be used as the default format for the session. For
dynamic payload type assignments the "a=rtpmap:" attribute (see
Section 6) SHOULD be used to map from an RTP payload type number
to a media encoding name that identifies the payload format. The
"a=fmtp:" attribute MAY be used to specify format parameters (see
Section 6).
If the <proto> sub-field is "udp" the <fmt> sub-fields MUST
reference a media type describing the format under the "audio",
"video", "text", "application", or "message" top-level media
types. The media type registration SHOULD define the packet
format for use with UDP transport.
For media using other transport protocols, the <fmt> field is
protocol specific. Rules for interpretation of the <fmt> sub-
field MUST be defined when registering new protocols (see Section
8.2.2).
class media(attrs):
'''Represents a m= line and all subsequent lines until next m= or end.
It has attributes such as media (str), port (int), proto (str), fmt (list).'''
def __init__(self, value=None, **kwargs):
if value:
self.media, self.port, self.proto, rest = value.split(' ', 3)
self.port = int(self.port)
self.fmt = []
for f in rest.split(' '):
a = attrs(); a.pt = f; self.fmt.append(a)
elif 'media' in kwargs:
self.media = kwargs.get('media')
self.port = int(kwargs.get('port', 0))
self.proto = kwargs.get('proto', 'RTP/AVP')
self.fmt = kwargs.get('fmt', [])
def __repr__(self):
result = self.media + ' ' + str(self.port) + ' ' + self.proto + ' ' + ' '.join(map(lambda x: str(x.pt), self.fmt))
for k in filter(lambda x: x in self, 'icbka'): # order is important
if k not in SDP._multiple: # single header
result += '\r\n' + k + '=' + str(self[k])
else:
for v in self[k]:
result += '\r\n' + k + '=' + str(v)
for f in self.fmt:
if f.name:
result += '\r\n' + 'a=rtpmap:' + str(f.pt) + ' ' + f.name + '/' + str(f.rate) + (f.params and ('/'+f.params) or '')
return result
An SDP session description consists of a number of lines of text of
the form:
<type>=<value>
where <type> MUST be exactly one case-significant character and
<value> is structured text whose format depends on <type>. In
general, <value> is either a number of fields delimited by a single
space character or a free format string, and is case-significant
unless a specific field defines otherwise. Whitespace MUST NOT be
used on either side of the "=" sign.
An SDP session description consists of a session-level section
followed by zero or more media-level sections. The session-level
part starts with a "v=" line and continues to the first media-level
section. Each media-level section starts with an "m=" line and
continues to the next media-level section or end of the whole session
description. In general, session-level values are the default for
all media unless overridden by an equivalent media-level value.
Some lines in each description are REQUIRED and some are OPTIONAL,
but all MUST appear in exactly the order given here (the fixed order
greatly enhances error detection and allows for a simple parser).
OPTIONAL items are marked with a "*".
Session description
v= (protocol version)
o= (originator and session identifier)
s= (session name)
i=* (session information)
u=* (URI of description)
e=* (email address)
p=* (phone number)
c=* (connection information -- not required if included in
all media)
b=* (zero or more bandwidth information lines)
One or more time descriptions ("t=" and "r=" lines; see below)
z=* (time zone adjustments)
k=* (encryption key)
a=* (zero or more session attribute lines)
Zero or more media descriptions
Time description
t= (time the session is active)
r=* (zero or more repeat times)
Media description, if present
m= (media name and transport address)
i=* (media title)
c=* (connection information -- optional if included at
session level)
b=* (zero or more bandwidth information lines)
k=* (encryption key)
a=* (zero or more media attribute lines)
The set of type letters is deliberately small and not intended to be
extensible -- an SDP parser MUST completely ignore any session
description that contains a type letter that it does not understand.
The attribute mechanism ("a=" described below) is the primary means
for extending SDP and tailoring it to particular applications or
media. Some attributes (the ones listed in Section 6 of this memo)
have a defined meaning, but others may be added on an application-,
media-, or session-specific basis. An SDP parser MUST ignore any
attribute it doesn't understand.
An SDP session description may contain URIs that reference external
content in the "u=", "k=", and "a=" lines. These URIs may be
dereferenced in some cases, making the session description non-self-
contained.
The connection ("c=") and attribute ("a=") information in the
session-level section applies to all the media of that session unless
overridden by connection information or an attribute of the same name
in the media description. For instance, in the example below, each
media behaves as if it were given a "recvonly" attribute.
def _parse(self, text):
g = True # whether we are in global line or per media line?
for line in text.replace('\r\n', '\n').split('\n'):
k, sep, v = line.partition('=')
if k == 'o': v = SDP.originator(v)
elif k == 'c': v = SDP.connection(v)
elif k == 'm': v = SDP.media(v)
if k == 'm': # new m= line
if not self['m']:
self['m'] = []
self['m'].append(v)
obj = self['m'][-1]
elif self['m']: # not in global
obj = self['m'][-1]
a=rtpmap:<payload type> <encoding name>/<clock rate> [/<encoding
parameters>]
This attribute maps from an RTP payload type number (as used in
an "m=" line) to an encoding name denoting the payload format
to be used. It also provides information on the clock rate and
encoding parameters. It is a media-level attribute that is not
dependent on charset.
Although an RTP profile may make static assignments of payload
type numbers to payload formats, it is more common for that
assignment to be done dynamically using "a=rtpmap:" attributes.
As an example of a static payload type, consider u-law PCM
coded single-channel audio sampled at 8 kHz. This is
completely defined in the RTP Audio/Video profile as payload
type 0, so there is no need for an "a=rtpmap:" attribute, and
the media for such a stream sent to UDP port 49232 can be
specified as:
m=audio 49232 RTP/AVP 0
An example of a dynamic payload type is 16-bit linear encoded
stereo audio sampled at 16 kHz. If we wish to use the dynamic
RTP/AVP payload type 98 for this stream, additional information
is required to decode it:
m=audio 49232 RTP/AVP 98
a=rtpmap:98 L16/16000/2
Up to one rtpmap attribute can be defined for each media format
specified. Thus, we might have the following:
m=audio 49230 RTP/AVP 96 97 98
a=rtpmap:96 L8/8000
a=rtpmap:97 L16/8000
a=rtpmap:98 L16/11025/2
RTP profiles that specify the use of dynamic payload types MUST
define the set of valid encoding names and/or a means to
register encoding names if that profile is to be used with SDP.
The "RTP/AVP" and "RTP/SAVP" profiles use media subtypes for
encoding names, under the top-level media type denoted in the
"m=" line. In the example above, the media types are
"audio/l8" and "audio/l16".
For audio streams, <encoding parameters> indicates the number
of audio channels. This parameter is OPTIONAL and may be
omitted if the number of channels is one, provided that no
additional parameters are needed.
For video streams, no encoding parameters are currently
specified.
Additional encoding parameters MAY be defined in the future,
but codec-specific parameters SHOULD NOT be added. Parameters
added to an "a=rtpmap:" attribute SHOULD only be those required
for a session directory to make the choice of appropriate media
to participate in a session. Codec-specific parameters should
be added in other attributes (for example, "a=fmtp:").
Note: RTP audio formats typically do not include information
about the number of samples per packet. If a non-default (as
defined in the RTP Audio/Video Profile) packetisation is
required, the "ptime" attribute is used as given above.
if k == 'a' and v.startswith('rtpmap:'):
pt, rest = v[7:].split(' ', 1)
name, sep, rest = rest.partition('/')
rate, sep, params = rest.partition('/')
for f in filter(lambda x: x.pt == pt, obj.fmt):
f.name = name; f.rate = int(rate); f.params = params or None
else:
obj[k] = (k in SDP._multiple and ((k in obj) and (obj[k]+v) or [v])) or v
else: # global
obj = self
obj[k] = ((k in SDP._multiple) and ((k in obj) and (obj[k]+v) or [v])) or v
def __repr__(self):
result = ''
for k in filter(lambda x: x in self, 'vosiuepcbtam'): # order is important
if k not in SDP._multiple: # single header
result += k + '=' + str(self[k]) + '\r\n'
else:
for v in self[k]:
result += k + '=' + str(v) + '\r\n'
return result
#--------------------------- Testing --------------------------------------
An example SDP description is:
v=0
o=jdoe 2890844526 2890842807 IN IP4 10.47.16.5
s=SDP Seminar
i=A Seminar on the session description protocol
u=http://www.example.com/seminars/sdp.pdf
e=j.doe@example.com (Jane Doe)
c=IN IP4 224.2.17.12/127
t=2873397496 2873404696
a=recvonly
m=audio 49170 RTP/AVP 0
m=video 51372 RTP/AVP 99
a=rtpmap:99 h263-1998/90000
def testSDP(): s = '''v=0\r o=jdoe 2890844526 2890842807 IN IP4 10.47.16.5\r s=SDP Seminar\r i=A Seminar on the session description protocol\r u=http://www.example.com/seminars/sdp.pdf\r e=j.doe@example.com (Jane Doe)\r c=IN IP4 224.2.17.12/127\r t=2873397496 2873404696\r a=recvonly\r m=audio 49170 RTP/AVP 0\r m=video 51372 RTP/AVP 99\r a=rtpmap:99 h263-1998/90000\r ''' sdp = SDP(s) assert str(sdp) == s if __name__ == '__main__': import doctest doctest.testmod() testSDP()