diff options
Diffstat (limited to 'Lib/http')
| -rw-r--r-- | Lib/http/client.py | 176 | ||||
| -rw-r--r-- | Lib/http/cookiejar.py | 8 | ||||
| -rw-r--r-- | Lib/http/cookies.py | 2 | ||||
| -rw-r--r-- | Lib/http/server.py | 97 |
4 files changed, 190 insertions, 93 deletions
diff --git a/Lib/http/client.py b/Lib/http/client.py index 4d93b93..6a4496f 100644 --- a/Lib/http/client.py +++ b/Lib/http/client.py @@ -141,6 +141,9 @@ UNPROCESSABLE_ENTITY = 422 LOCKED = 423 FAILED_DEPENDENCY = 424 UPGRADE_REQUIRED = 426 +PRECONDITION_REQUIRED = 428 +TOO_MANY_REQUESTS = 429 +REQUEST_HEADER_FIELDS_TOO_LARGE = 431 # server error INTERNAL_SERVER_ERROR = 500 @@ -151,6 +154,7 @@ GATEWAY_TIMEOUT = 504 HTTP_VERSION_NOT_SUPPORTED = 505 INSUFFICIENT_STORAGE = 507 NOT_EXTENDED = 510 +NETWORK_AUTHENTICATION_REQUIRED = 511 # Mapping status codes to official W3C names responses = { @@ -192,6 +196,9 @@ responses = { 415: 'Unsupported Media Type', 416: 'Requested Range Not Satisfiable', 417: 'Expectation Failed', + 428: 'Precondition Required', + 429: 'Too Many Requests', + 431: 'Request Header Fields Too Large', 500: 'Internal Server Error', 501: 'Not Implemented', @@ -199,6 +206,7 @@ responses = { 503: 'Service Unavailable', 504: 'Gateway Timeout', 505: 'HTTP Version Not Supported', + 511: 'Network Authentication Required', } # maximal amount of data to read at one time in _safe_read @@ -485,11 +493,17 @@ class HTTPResponse(io.RawIOBase): self.close() return b"" - if self.chunked: - return self._read_chunked(amt) + if amt is not None: + # Amount is given, so call base class version + # (which is implemented in terms of self.readinto) + return super(HTTPResponse, self).read(amt) + else: + # Amount is not given (unbounded read) so we must check self.length + # and self.chunked + + if self.chunked: + return self._readall_chunked() - if amt is None: - # unbounded read if self.length is None: s = self.fp.read() else: @@ -498,82 +512,130 @@ class HTTPResponse(io.RawIOBase): self.close() # we read everything return s + def readinto(self, b): + if self.fp is None: + return 0 + + if self._method == "HEAD": + self.close() + return 0 + + if self.chunked: + return self._readinto_chunked(b) + if self.length is not None: - if amt > self.length: + if len(b) > self.length: # clip the read to the "end of response" - amt = self.length + b = memoryview(b)[0: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) + n = self.fp.readinto(b) if self.length is not None: - self.length -= len(s) + self.length -= n if not self.length: self.close() else: - if not s: + if not n: self.close() + return n - return s + def _read_next_chunk_size(self): + # Read the next chunk size from the file + 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: + return int(line, 16) + except ValueError: + # close the connection as protocol synchronisation is + # probably lost + self.close() + raise - def _read_chunked(self, amt): + def _read_and_discard_trailer(self): + # 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 in (b'\r\n', b'\n', b''): + break + + def _readall_chunked(self): 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) + chunk_left = self._read_next_chunk_size() + if chunk_left == 0: + break 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)) + value.append(self._safe_read(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 + + self._read_and_discard_trailer() + + # we read everything; close the "file" + self.close() + + return b''.join(value) + + def _readinto_chunked(self, b): + assert self.chunked != _UNKNOWN + chunk_left = self.chunk_left + + total_bytes = 0 + mvb = memoryview(b) + while True: + if chunk_left is None: + try: + chunk_left = self._read_next_chunk_size() + if chunk_left == 0: + break + except ValueError: + raise IncompleteRead(bytes(b[0:total_bytes])) + + if len(mvb) < chunk_left: + n = self._safe_readinto(mvb) + self.chunk_left = chunk_left - n + return total_bytes + n + elif len(mvb) == chunk_left: + n = self._safe_readinto(mvb) self._safe_read(2) # toss the CRLF at the end of the chunk self.chunk_left = None - return b''.join(value) + return total_bytes + n else: - value.append(self._safe_read(chunk_left)) - amt -= chunk_left + temp_mvb = mvb[0:chunk_left] + n = self._safe_readinto(temp_mvb) + mvb = mvb[n:] + total_bytes += n # 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 in (b'\r\n', b'\n', b''): - break + self._read_and_discard_trailer() # we read everything; close the "file" self.close() - return b''.join(value) + return total_bytes def _safe_read(self, amt): """Read the number of bytes requested, compensating for partial reads. @@ -598,6 +660,22 @@ class HTTPResponse(io.RawIOBase): amt -= len(chunk) return b"".join(s) + def _safe_readinto(self, b): + """Same as _safe_read, but for reading into a buffer.""" + total_bytes = 0 + mvb = memoryview(b) + while total_bytes < len(b): + if MAXAMOUNT < len(mvb): + temp_mvb = mvb[0:MAXAMOUNT] + n = self.fp.readinto(temp_mvb) + else: + n = self.fp.readinto(mvb) + if not n: + raise IncompleteRead(bytes(mvb[0:total_bytes]), len(b)) + mvb = mvb[n:] + total_bytes += n + return total_bytes + def fileno(self): return self.fp.fileno() @@ -704,7 +782,7 @@ class HTTPConnection: 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("latin1") + header_bytes = header_str.encode("latin-1") self.send(header_bytes) self.send(b'\r\n') @@ -947,7 +1025,7 @@ class HTTPConnection: values = list(values) for i, one_value in enumerate(values): if hasattr(one_value, 'encode'): - values[i] = one_value.encode('latin1') + 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) diff --git a/Lib/http/cookiejar.py b/Lib/http/cookiejar.py index b6cfc35..901e762 100644 --- a/Lib/http/cookiejar.py +++ b/Lib/http/cookiejar.py @@ -625,7 +625,7 @@ def request_path(request): return path def request_port(request): - host = request.get_host() + host = request.host i = host.find(':') if i >= 0: port = host[i+1:] @@ -949,7 +949,7 @@ class DefaultCookiePolicy(CookiePolicy): return True def set_ok_verifiability(self, cookie, request): - if request.is_unverifiable() and is_third_party(request): + if request.unverifiable and is_third_party(request): if cookie.version > 0 and self.strict_rfc2965_unverifiable: _debug(" third-party RFC 2965 cookie during " "unverifiable transaction") @@ -1088,7 +1088,7 @@ class DefaultCookiePolicy(CookiePolicy): return True def return_ok_verifiability(self, cookie, request): - if request.is_unverifiable() and is_third_party(request): + if request.unverifiable and is_third_party(request): if cookie.version > 0 and self.strict_rfc2965_unverifiable: _debug(" third-party RFC 2965 cookie during unverifiable " "transaction") @@ -1100,7 +1100,7 @@ class DefaultCookiePolicy(CookiePolicy): return True def return_ok_secure(self, cookie, request): - if cookie.secure and request.get_type() != "https": + if cookie.secure and request.type != "https": _debug(" secure cookie with non-secure request") return False return True diff --git a/Lib/http/cookies.py b/Lib/http/cookies.py index ddbcbf8..d291678 100644 --- a/Lib/http/cookies.py +++ b/Lib/http/cookies.py @@ -159,7 +159,7 @@ class CookieError(Exception): # _LegalChars is the list of chars which don't require "'s # _Translator hash-table for fast quoting # -_LegalChars = string.ascii_letters + string.digits + "!#$%&'*+-.^_`|~" +_LegalChars = string.ascii_letters + string.digits + "!#$%&'*+-.^_`|~:" _Translator = { '\000' : '\\000', '\001' : '\\001', '\002' : '\\002', '\003' : '\\003', '\004' : '\\004', '\005' : '\\005', diff --git a/Lib/http/server.py b/Lib/http/server.py index 5569037..c4ac703 100644 --- a/Lib/http/server.py +++ b/Lib/http/server.py @@ -100,11 +100,14 @@ import sys import time import urllib.parse import copy +import argparse + # Default error message template DEFAULT_ERROR_MESSAGE = """\ <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"> +<html> <head> <meta http-equiv="Content-Type" content="text/html;charset=utf-8"> <title>Error response</title> @@ -352,6 +355,7 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): """ self.send_response_only(100) + self.flush_headers() return True def handle_one_request(self): @@ -429,7 +433,8 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): self.wfile.write(content.encode('UTF-8', 'replace')) def send_response(self, code, message=None): - """Send the response header and log the response code. + """Add the response header to the headers buffer and log the + response code. Also send two standard headers with the server software version and the current date. @@ -448,16 +453,19 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): else: message = '' if self.request_version != 'HTTP/0.9': - self.wfile.write(("%s %d %s\r\n" % - (self.protocol_version, code, message)).encode('latin1', 'strict')) + if not hasattr(self, '_headers_buffer'): + self._headers_buffer = [] + self._headers_buffer.append(("%s %d %s\r\n" % + (self.protocol_version, code, message)).encode( + 'latin-1', 'strict')) def send_header(self, keyword, value): - """Send a MIME header.""" + """Send a MIME header to the headers buffer.""" if self.request_version != 'HTTP/0.9': if not hasattr(self, '_headers_buffer'): self._headers_buffer = [] self._headers_buffer.append( - ("%s: %s\r\n" % (keyword, value)).encode('latin1', 'strict')) + ("%s: %s\r\n" % (keyword, value)).encode('latin-1', 'strict')) if keyword.lower() == 'connection': if value.lower() == 'close': @@ -469,6 +477,10 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): """Send the blank line ending the MIME headers.""" if self.request_version != 'HTTP/0.9': self._headers_buffer.append(b"\r\n") + self.flush_headers() + + def flush_headers(self): + if hasattr(self, '_headers_buffer'): self.wfile.write(b"".join(self._headers_buffer)) self._headers_buffer = [] @@ -514,7 +526,7 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): """ sys.stderr.write("%s - - [%s] %s\n" % - (self.client_address[0], + (self.address_string(), self.log_date_time_string(), format%args)) @@ -548,15 +560,9 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] def address_string(self): - """Return the client address formatted for logging. - - This version looks up the full hostname using gethostbyaddr(), - and tries to find a name that contains at least one dot. - - """ + """Return the client address.""" - host, port = self.client_address[:2] - return socket.getfqdn(host) + return self.client_address[0] # Essentially static class variables @@ -569,7 +575,7 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): # Table mapping response codes to messages; entries have the # form {code: (shortmessage, longmessage)}. - # See RFC 2616. + # See RFC 2616 and 6585. responses = { 100: ('Continue', 'Request received, please continue'), 101: ('Switching Protocols', @@ -624,6 +630,12 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): 'Cannot satisfy request range.'), 417: ('Expectation Failed', 'Expect condition could not be satisfied.'), + 428: ('Precondition Required', + 'The origin server requires the request to be conditional.'), + 429: ('Too Many Requests', 'The user has sent too many requests ' + 'in a given amount of time ("rate limiting").'), + 431: ('Request Header Fields Too Large', 'The server is unwilling to ' + 'process the request because its header fields are too large.'), 500: ('Internal Server Error', 'Server got itself in trouble'), 501: ('Not Implemented', @@ -634,6 +646,8 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): 504: ('Gateway Timeout', 'The gateway server did not receive a timely response'), 505: ('HTTP Version Not Supported', 'Cannot fulfill request.'), + 511: ('Network Authentication Required', + 'The client needs to authenticate to gain network access.'), } @@ -722,10 +736,16 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): list.sort(key=lambda a: a.lower()) r = [] displaypath = html.escape(urllib.parse.unquote(self.path)) - r.append('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">') - r.append("<html>\n<title>Directory listing for %s</title>\n" % displaypath) - r.append("<body>\n<h2>Directory listing for %s</h2>\n" % displaypath) - r.append("<hr>\n<ul>\n") + enc = sys.getfilesystemencoding() + title = 'Directory listing for %s' % displaypath + r.append('<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" ' + '"http://www.w3.org/TR/html4/strict.dtd">') + r.append('<html>\n<head>') + r.append('<meta http-equiv="Content-Type" ' + 'content="text/html; charset=%s">' % enc) + r.append('<title>%s</title>\n</head>' % title) + r.append('<body>\n<h1>%s</h1>' % title) + r.append('<hr>\n<ul>') for name in list: fullname = os.path.join(path, name) displayname = linkname = name @@ -736,11 +756,10 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): if os.path.islink(fullname): displayname = name + "@" # Note: a link to a directory displays with @ and links with / - r.append('<li><a href="%s">%s</a>\n' + r.append('<li><a href="%s">%s</a></li>' % (urllib.parse.quote(linkname), html.escape(displayname))) - r.append("</ul>\n<hr>\n</body>\n</html>\n") - enc = sys.getfilesystemencoding() - encoded = ''.join(r).encode(enc) + r.append('</ul>\n<hr>\n</body>\n</html>\n') + encoded = '\n'.join(r).encode(enc) f = io.BytesIO() f.write(encoded) f.seek(0) @@ -888,11 +907,7 @@ def nobody_uid(): def executable(path): """Test for executable file.""" - try: - st = os.stat(path) - except os.error: - return False - return st.st_mode & 0o111 != 0 + return os.access(path, os.X_OK) class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): @@ -1008,7 +1023,7 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): scriptname) return ispy = self.is_python(scriptname) - if not ispy: + if self.have_fork or not ispy: if not self.is_executable(scriptfile): self.send_error(403, "CGI script is not executable (%r)" % scriptname) @@ -1029,9 +1044,6 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): env['SCRIPT_NAME'] = scriptname if query: env['QUERY_STRING'] = query - host = self.address_string() - if host != self.client_address[0]: - env['REMOTE_HOST'] = host env['REMOTE_ADDR'] = self.client_address[0] authorization = self.headers.get("authorization") if authorization: @@ -1083,6 +1095,7 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): env.setdefault(k, "") self.send_response(200, "Script output follows") + self.flush_headers() decoded_query = query.replace('+', ' ') @@ -1162,18 +1175,13 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): def test(HandlerClass = BaseHTTPRequestHandler, - ServerClass = HTTPServer, protocol="HTTP/1.0"): + ServerClass = HTTPServer, protocol="HTTP/1.0", port=8000): """Test the HTTP request handler class. This runs an HTTP server on port 8000 (or the first command line argument). """ - - if sys.argv[1:]: - port = int(sys.argv[1]) - else: - port = 8000 server_address = ('', port) HandlerClass.protocol_version = protocol @@ -1189,4 +1197,15 @@ def test(HandlerClass = BaseHTTPRequestHandler, sys.exit(0) if __name__ == '__main__': - test(HandlerClass=SimpleHTTPRequestHandler) + parser = argparse.ArgumentParser() + parser.add_argument('--cgi', action='store_true', + help='Run as CGI Server') + parser.add_argument('port', action='store', + default=8000, type=int, + nargs='?', + help='Specify alternate port [default: 8000]') + args = parser.parse_args() + if args.cgi: + test(HandlerClass=CGIHTTPRequestHandler, port=args.port) + else: + test(HandlerClass=SimpleHTTPRequestHandler, port=args.port) |