diff options
Diffstat (limited to 'Lib/http')
| -rw-r--r-- | Lib/http/client.py | 167 | ||||
| -rw-r--r-- | Lib/http/cookies.py | 2 | ||||
| -rw-r--r-- | Lib/http/server.py | 50 |
3 files changed, 151 insertions, 68 deletions
diff --git a/Lib/http/client.py b/Lib/http/client.py index d226f63..9c110d5 100644 --- a/Lib/http/client.py +++ b/Lib/http/client.py @@ -485,11 +485,17 @@ 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: @@ -498,78 +504,127 @@ 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() - return s + return n + + 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. @@ -594,6 +649,22 @@ 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() @@ -700,7 +771,7 @@ 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') @@ -943,7 +1014,7 @@ 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/cookies.py b/Lib/http/cookies.py index 93da627..d73f79a 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 80f58e6..18313cf 100644 --- a/Lib/http/server.py +++ b/Lib/http/server.py @@ -105,6 +105,7 @@ import copy 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 +353,7 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): """ self.send_response_only(100) + self.flush_headers() return True def handle_one_request(self): @@ -429,7 +431,8 @@ 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 +451,19 @@ 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 +475,10 @@ 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 = [] @@ -722,10 +732,16 @@ 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 +752,10 @@ 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 +903,7 @@ 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 +1019,7 @@ 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) @@ -1083,6 +1094,7 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): env.setdefault(k, "") self.send_response(200, "Script output follows") + self.flush_headers() decoded_query = query.replace('+', ' ') |