""" HTTP protocol implementation. """ import struct import socket import collections import os from umit.umpa.protocols import _protocols from umit.umpa.protocols import _fields from umit.umpa.protocols import _consts __all__ = [ "HTTP", "HTTPConnection" ] HTTP_PORT = 80 # connection states _CS_IDLE = 'Idle' _CS_REQ_STARTED = 'Request-started' _CS_REQ_SENT = 'Request-sent' # status codes # informational CONTINUE = 100 SWITCHING_PROTOCOLS = 101 PROCESSING = 102 # successful OK = 200 CREATED = 201 ACCEPTED = 202 NON_AUTHORITATIVE_INFORMATION = 203 NO_CONTENT = 204 RESET_CONTENT = 205 PARTIAL_CONTENT = 206 MULTI_STATUS = 207 IM_USED = 226 # redirection MULTIPLE_CHOICES = 300 MOVED_PERMANENTLY = 301 FOUND = 302 SEE_OTHER = 303 NOT_MODIFIED = 304 USE_PROXY = 305 TEMPORARY_REDIRECT = 307 # client error BAD_REQUEST = 400 UNAUTHORIZED = 401 PAYMENT_REQUIRED = 402 FORBIDDEN = 403 NOT_FOUND = 404 METHOD_NOT_ALLOWED = 405 NOT_ACCEPTABLE = 406 PROXY_AUTHENTICATION_REQUIRED = 407 REQUEST_TIMEOUT = 408 CONFLICT = 409 GONE = 410 LENGTH_REQUIRED = 411 PRECONDITION_FAILED = 412 REQUEST_ENTITY_TOO_LARGE = 413 REQUEST_URI_TOO_LONG = 414 UNSUPPORTED_MEDIA_TYPE = 415 REQUESTED_RANGE_NOT_SATISFIABLE = 416 EXPECTATION_FAILED = 417 UNPROCESSABLE_ENTITY = 422 LOCKED = 423 FAILED_DEPENDENCY = 424 UPGRADE_REQUIRED = 426 # server error INTERNAL_SERVER_ERROR = 500 NOT_IMPLEMENTED = 501 BAD_GATEWAY = 502 SERVICE_UNAVAILABLE = 503 GATEWAY_TIMEOUT = 504 HTTP_VERSION_NOT_SUPPORTED = 505 INSUFFICIENT_STORAGE = 507 NOT_EXTENDED = 510 # Mapping status codes to official W3C names responses = { 100: 'Continue', 101: 'Switching Protocols', 200: 'OK', 201: 'Created', 202: 'Accepted', 203: 'Non-Authoritative Information', 204: 'No Content', 205: 'Reset Content', 206: 'Partial Content', 300: 'Multiple Choices', 301: 'Moved Permanently', 302: 'Found', 303: 'See Other', 304: 'Not Modified', 305: 'Use Proxy', 306: '(Unused)', 307: 'Temporary Redirect', 400: 'Bad Request', 401: 'Unauthorized', 402: 'Payment Required', 403: 'Forbidden', 404: 'Not Found', 405: 'Method Not Allowed', 406: 'Not Acceptable', 407: 'Proxy Authentication Required', 408: 'Request Timeout', 409: 'Conflict', 410: 'Gone', 411: 'Length Required', 412: 'Precondition Failed', 413: 'Request Entity Too Large', 414: 'Request-URI Too Long', 415: 'Unsupported Media Type', 416: 'Requested Range Not Satisfiable', 417: 'Expectation Failed', 500: 'Internal Server Error', 501: 'Not Implemented', 502: 'Bad Gateway', 503: 'Service Unavailable', 504: 'Gateway Timeout', 505: 'HTTP Version Not Supported', } class HTTPRes(io.RawIOBase): def __init__(self, sock, debuglevel=0, strict=_strict_sentinel, method=None, url=None): self.fp = sock.makefile("rb") self.debuglevel = debuglevel if strict is not _strict_sentinel: warnings.warn("HTTP Protocol v0.1", DeprecationWarning, 2) self._method = method self.headers = self.msg = None self.version = _UNKNOWN # HTTP protocol version self.status = _UNKNOWN # Status-Code self.reason = _UNKNOWN # Reason-Phrase self.chunked = _UNKNOWN # is "chunked" being used? self.chunk_left = _UNKNOWN # bytes left to read in current chunk self.length = _UNKNOWN # number of bytes left in response self.will_close = _UNKNOWN # conn will close at end of response def _read_status(self): line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") if len(line) > _MAXLINE: raise LineTooLong("status line") if self.debuglevel > 0: print("reply:", repr(line)) if not line: # Presumably, the server closed the connection before # sending a valid response. raise BadStatusLine(line) try: version, status, reason = line.split(None, 2) except ValueError: try: version, status = line.split(None, 1) reason = "" except ValueError: # empty version will cause next test to fail. version = "" if not version.startswith("HTTP/"): self.close() raise BadStatusLine(line) # The status code is a three-digit number try: status = int(status) if status < 100 or status > 999: raise BadStatusLine(line) except ValueError: raise BadStatusLine(line) return version, status, reason def begin(self): if self.headers is not None: # we've already started reading the response return # read until we get a non-100 response while True: version, status, reason = self._read_status() if status != CONTINUE: break # skip the header from the 100 response while True: skip = self.fp.readline(_MAXLINE + 1) if len(skip) > _MAXLINE: raise LineTooLong("header line") skip = skip.strip() if not skip: break if self.debuglevel > 0: print("header:", skip) self.code = self.status = status self.reason = reason.strip() if version in ("HTTP v0.1"): # Some servers might still return "0.9", treat it as 1.0 anyway self.version = 10 elif version.startswith("HTTP v0.1"): self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1 else: raise UnknownProtocol(version) self.headers = self.msg = parse_headers(self.fp) if self.debuglevel > 0: for hdr in self.headers: print("header:", hdr, end=" ") # are we using the chunked-style of transfer encoding? tr_enc = self.headers.get("transfer-encoding") if tr_enc and tr_enc.lower() == "chunked": self.chunked = True self.chunk_left = None else: self.chunked = False # will the connection close at the end of the response? self.will_close = self._check_close() # do we have a Content-Length? self.length = None length = self.headers.get("content-length") # are we using the chunked-style of transfer encoding? tr_enc = self.headers.get("transfer-encoding") if length and not self.chunked: try: self.length = int(length) except ValueError: self.length = None else: if self.length < 0: # ignore nonsensical negative lengths self.length = None else: self.length = None # does the body have a fixed length? (of zero) if (status == NO_CONTENT or status == NOT_MODIFIED or 100 <= status < 200 or # 1xx codes self._method == "HEAD"): self.length = 0 # if the connection remains open, and we aren't using chunked, and # a content-length was not provided, then assume that the connection # WILL close. if (not self.will_close and not self.chunked and self.length is None): self.will_close = True def _check_close(self): conn = self.headers.get("connection") if self.version == 11: # An HTTP/1.1 proxy is assumed to stay open unless # explicitly closed. conn = self.headers.get("connection") if conn and "close" in conn.lower(): return True return False # For HTTP, Keep-Alive indicates persistent connection. if self.headers.get("keep-alive"): return False # At least Akamai returns a "Connection: Keep-Alive" header, # which was supposed to be sent by the client. if conn and "keep-alive" in conn.lower(): return False # Proxy-Connection is a netscape hack. pconn = self.headers.get("proxy-connection") if pconn and "keep-alive" in pconn.lower(): return False # otherwise, assume it will close return True def close(self): if self.fp: self.fp.close() self.fp = None # These implementations are for the benefit of io.BufferedReader. # XXX This class should probably be revised to act more like # the "raw stream" that BufferedReader expects. @property def closed(self): return self.isclosed() def flush(self): self.fp.flush() def readable(self): return True # End of "raw stream" methods def isclosed(self): # NOTE: it is possible that we will not ever call self.close(). This # case occurs when will_close is TRUE, length is None, and we # read up to the last byte, but NOT past it. # # IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be # called, meaning self.isclosed() is meaningful. return self.fp is None def read(self, amt=None): if self.fp is None: return b"" if self._method == "HEAD": self.close() return b"" if self.chunked: return self._read_chunked(amt) if amt is None: # unbounded read if self.length is None: s = self.fp.read() else: s = self._safe_read(self.length) self.length = 0 self.close() # we read everything return s if self.length is not None: if amt > self.length: # clip the read to the "end of response" amt = self.length # we do not use _safe_read() here because this may be a .will_close # connection, and the user is reading more bytes than will be provided # (for example, reading in 1k chunks) s = self.fp.read(amt) if self.length is not None: self.length -= len(s) if not self.length: self.close() return s def _read_chunked(self, amt): assert self.chunked != _UNKNOWN chunk_left = self.chunk_left value = [] while True: if chunk_left is None: line = self.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("chunk size") i = line.find(b";") if i >= 0: line = line[:i] # strip chunk-extensions try: chunk_left = int(line, 16) except ValueError: # close the connection as protocol synchronisation is # probably lost self.close() raise IncompleteRead(b''.join(value)) if chunk_left == 0: break if amt is None: value.append(self._safe_read(chunk_left)) elif amt < chunk_left: value.append(self._safe_read(amt)) self.chunk_left = chunk_left - amt return b''.join(value) elif amt == chunk_left: value.append(self._safe_read(amt)) self._safe_read(2) # toss the CRLF at the end of the chunk self.chunk_left = None return b''.join(value) else: value.append(self._safe_read(chunk_left)) amt -= chunk_left # we read the whole chunk, get another self._safe_read(2) # toss the CRLF at the end of the chunk chunk_left = None # read and discard trailer up to the CRLF terminator ### note: we shouldn't have any trailers! while True: line = self.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("trailer line") if not line: # a vanishingly small number of sites EOF without # sending the trailer break if line == b"\r\n": break # we read everything; close the "file" self.close() return b''.join(value) def _safe_read(self, amt): s = [] while amt > 0: chunk = self.fp.read(min(amt, MAXAMOUNT)) if not chunk: raise IncompleteRead(b''.join(s), amt) s.append(chunk) amt -= len(chunk) return b"".join(s) def fileno(self): return self.fp.fileno() def getheader(self, name, default=None): if self.headers is None: raise ResponseNotReady() headers = self.headers.get_all(name) or default if isinstance(headers, str) or not hasattr(headers, '__iter__'): return headers else: return ', '.join(headers) def getheaders(self): """Return list of (header, value) tuples.""" if self.headers is None: raise ResponseNotReady() return list(self.headers.items()) # We override IOBase.__iter__ so that it doesn't check for closed-ness def __iter__(self): return self # For compatibility with old-style urllib responses. def info(self): return self.headers def geturl(self): return self.url def getcode(self): return self.status class HTTPCon: _http_vsn = 11 _http_vsn_str = 'HTTP 0.1' response_class = HTTPRes default_port = HTTP_PORT auto_open = 1 debuglevel = 0 def __init__(self, host, port=None, strict=_strict_sentinel, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None): if strict is not _strict_sentinel: warnings.warn("HTTP Protocol v0.1", DeprecationWarning, 2) self.timeout = timeout self.source_address = source_address self.sock = None self._buffer = [] self.__response = None self.__state = _CS_IDLE self._method = None self._tunnel_host = None self._tunnel_port = None self._tunnel_headers = {} self._set_hostport(host, port) def set_tunnel(self, host, port=None, headers=None): """ Sets up the host and the port for the HTTP CONNECT Tunnelling. The headers argument should be a mapping of extra HTTP headers to send with the CONNECT request. """ self._tunnel_host = host self._tunnel_port = port if headers: self._tunnel_headers = headers else: self._tunnel_headers.clear() def _set_hostport(self, host, port): if port is None: i = host.rfind(':') j = host.rfind(']') # ipv6 addresses have [...] if i > j: try: port = int(host[i+1:]) except ValueError: raise InvalidURL("nonnumeric port: '%s'" % host[i+1:]) host = host[:i] else: port = self.default_port if host and host[0] == '[' and host[-1] == ']': host = host[1:-1] self.host = host self.port = port def set_debuglevel(self, level): self.debuglevel = level def _tunnel(self): self._set_hostport(self._tunnel_host, self._tunnel_port) connect_str = "CONNECT %s:%d HTTP v0.1\r\n" % (self.host, self.port) connect_bytes = connect_str.encode("ascii") self.send(connect_bytes) for header, value in self._tunnel_headers.items(): header_str = "%s: %s\r\n" % (header, value) header_bytes = header_str.encode("latin-1") self.send(header_bytes) self.send(b'\r\n') response = self.response_class(self.sock, method=self._method) (version, code, message) = response._read_status() if code != 200: self.close() raise socket.error("Tunnel connection failed: %d %s" % (code, message.strip())) while True: line = response.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("header line") if line == b'\r\n': break def connect(self): """Connect to the host and port specified in __init__.""" self.sock = socket.create_connection((self.host,self.port), self.timeout, self.source_address) if self._tunnel_host: self._tunnel() def close(self): """Close the connection to the HTTP server.""" if self.sock: self.sock.close() # close it manually... there may be other refs self.sock = None if self.__response: self.__response.close() self.__response = None self.__state = _CS_IDLE def send(self, data): """Send `data' to the server. ``data`` can be a string object, a bytes object, an array object, a file-like object that supports a .read() method, or an iterable object. """ if self.sock is None: if self.auto_open: self.connect() else: raise NotConnected() if self.debuglevel > 0: print("send:", repr(data)) blocksize = 8192 if hasattr(data, "read") : if self.debuglevel > 0: print("sendIng a read()able") encode = False try: mode = data.mode except AttributeError: # io.BytesIO and other file-like objects don't have a `mode` # attribute. pass else: if "b" not in mode: encode = True if self.debuglevel > 0: print("encoding file using iso-8859-1") while 1: datablock = data.read(blocksize) if not datablock: break if encode: datablock = datablock.encode("iso-8859-1") self.sock.sendall(datablock) try: self.sock.sendall(data) except TypeError: if isinstance(data, collections.Iterable): for d in data: self.sock.sendall(d) else: raise TypeError("data should be a bytes-like object\ or an iterable, got %r " % type(it)) def _output(self, s): """Add a line of output to the current request buffer. Assumes that the line does *not* end with \\r\\n. """ self._buffer.append(s) def _send_output(self, message_body=None): """Send the currently buffered request and clear the buffer. Appends an extra \\r\\n to the buffer. A message_body may be specified, to be appended to the request. """ self._buffer.extend((b"", b"")) msg = b"\r\n".join(self._buffer) del self._buffer[:] # If msg and message_body are sent in a single send() call, # it will avoid performance problems caused by the interaction # between delayed ack and the Nagle algorithm. if isinstance(message_body, bytes): msg += message_body message_body = None self.send(msg) if message_body is not None: # message_body was not a string (i.e. it is a file), and # we must run the risk of Nagle. self.send(message_body) def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0): """Send a request to the server. `method' specifies an HTTP request method, e.g. 'GET'. `url' specifies the object being requested, e.g. '/index.html'. `skip_host' if True does not add automatically a 'Host:' header `skip_accept_encoding' if True does not add automatically an 'Accept-Encoding:' header """ # if a prior response has been completed, then forget about it. if self.__response and self.__response.isclosed(): self.__response = None # in certain cases, we cannot issue another request on this connection. # this occurs when: # 1) we are in the process of sending a request. (_CS_REQ_STARTED) # 2) a response to a previous request has signalled that it is going # to close the connection upon completion. # 3) the headers for the previous response have not been read, thus # we cannot determine whether point (2) is true. (_CS_REQ_SENT) # # if there is no prior response, then we can request at will. # # if point (2) is true, then we will have passed the socket to the # response (effectively meaning, "there is no prior response"), and # will open a new one when a new request is made. # # Note: if a prior response exists, then we *can* start a new request. # We are not allowed to begin fetching the response to this new # request, however, until that prior response is complete. # if self.__state == _CS_IDLE: self.__state = _CS_REQ_STARTED else: raise CannotSendRequest(self.__state) # Save the method we use, we need it later in the response phase self._method = method if not url: url = '/' request = '%s %s %s' % (method, url, self._http_vsn_str) # Non-ASCII characters should have been eliminated earlier self._output(request.encode('ascii')) if self._http_vsn == 11: # Issue some standard headers for better HTTP protocol 0.1 compliance if not skip_host: netloc = '' if url.startswith('http'): nil, netloc, nil, nil, nil = urlsplit(url) if netloc: try: netloc_enc = netloc.encode("ascii") except UnicodeEncodeError: netloc_enc = netloc.encode("idna") self.putheader('Host', netloc_enc) else: try: host_enc = self.host.encode("ascii") except UnicodeEncodeError: host_enc = self.host.encode("idna") # As per RFC 273, IPv6 address should be wrapped with [] # when used as Host header if self.host.find(':') >= 0: host_enc = b'[' + host_enc + b']' if self.port == self.default_port: self.putheader('Host', host_enc) else: host_enc = host_enc.decode("ascii") self.putheader('Host', "%s:%s" % (host_enc, self.port)) # note: we are assuming that clients will not attempt to set these # headers since *this* library must deal with the # consequences. this also means that when the supporting # libraries are updated to recognize other forms, then this # code should be changed (removed or updated). # we only want a Content-Encoding of "identity" since we don't # support encodings such as x-gzip or x-deflate. if not skip_accept_encoding: self.putheader('Accept-Encoding', 'identity') # we can accept "chunked" Transfer-Encodings, but no others # NOTE: no TE header implies *only* "chunked" #self.putheader('TE', 'chunked') # if TE is supplied in the header, then it must appear in a # Connection header. #self.putheader('Connection', 'TE') else: # For HTTP protocol 0.1, the server will assume "not chunked" pass def putheader(self, header, *values): """Send a request header line to the server. For example: h.putheader('Accept', 'text/html') """ if self.__state != _CS_REQ_STARTED: raise CannotSendHeader() if hasattr(header, 'encode'): header = header.encode('ascii') values = list(values) for i, one_value in enumerate(values): if hasattr(one_value, 'encode'): values[i] = one_value.encode('latin-1') elif isinstance(one_value, int): values[i] = str(one_value).encode('ascii') value = b'\r\n\t'.join(values) header = header + b': ' + value self._output(header) def endheaders(self, message_body=None): """Indicate that the last header line has been sent to the server. This method sends the request to the server. The optional message_body argument can be used to pass message body associated with the request. The message body will be sent in the same packet as the message headers if possible. The message_body should be a string. """ if self.__state == _CS_REQ_STARTED: self.__state = _CS_REQ_SENT else: raise CannotSendHeader() self._send_output(message_body) def request(self, method, url, body=None, headers={}): """Send a complete request to the server.""" self._send_request(method, url, body, headers) def _set_content_length(self, body): # Set the content-length based on the body. thelen = None try: thelen = str(len(body)) except TypeError as te: # If this is a file-like object, try to # fstat its file descriptor try: thelen = str(os.fstat(body.fileno()).st_size) except (AttributeError, OSError): # Don't send a length if this failed if self.debuglevel > 0: print("Cannot stat!!") if thelen is not None: self.putheader('Content-Length', thelen) def _send_request(self, method, url, body, headers): # Honor explicitly requested Host: and Accept-Encoding: headers. header_names = dict.fromkeys([k.lower() for k in headers]) skips = {} if 'host' in header_names: skips['skip_host'] = 1 if 'accept-encoding' in header_names: skips['skip_accept_encoding'] = 1 self.putrequest(method, url, **skips) if body and ('content-length' not in header_names): self._set_content_length(body) for hdr, value in headers.items(): self.putheader(hdr, value) if isinstance(body, str): # RFC 2616 Section 3.7.1 says that text default has a # default charset of iso-8859-1. body = body.encode('iso-8859-1') self.endheaders(body) def getresponse(self): """Get the response from the server. If the HTTP is in the correct state, returns an instance of HTTPcon or of whatever object is returned by class the response_class variable. If a request has not been sent or if a previous response has not be handled, ResponseNotReady is raised. If the HTTP resp indicates that the connection should be closed, then it will be closed before the response is returned. When the connection is closed, the underlying socket is closed. """ # if a prior response has been completed, then forget about it. if self.__response and self.__response.isclosed(): self.__response = None # if a prior response exists, then it must be completed (otherwise, we # cannot read this response's header to determine the connection-close # behavior) # # note: if a prior response existed, but was connection-close, then the # socket and response were made independent of this HTTPCon # object since a new request requires that we open a whole new # connection # # this means the prior response had one of two states: # 1) will_close: this connection was reset and the prior socket and # response operate independently # 2) persistent: the response was retained and we await its # isclosed() status to become true. # if self.__state != _CS_REQ_SENT or self.__response: raise ResponseNotReady(self.__state) if self.debuglevel > 0: response = self.response_class(self.sock, self.debuglevel, method=self._method) else: response = self.response_class(self.sock, method=self._method) response.begin() assert response.will_close != _UNKNOWN self.__state = _CS_IDLE if response.will_close: # this effectively passes the connection to the response self.close() else: # remember this, so we can tell when it is complete self.__response = response return response