def parse_request_line(self, line_bytes):
bits = [bytes_to_str(bit) for bit in line_bytes.split(None, 2)]
if len(bits) != 3:
raise InvalidRequestLine(bytes_to_str(line_bytes))
# Method
if not METH_RE.match(bits[0]):
raise InvalidRequestMethod(bits[0])
self.method = bits[0].upper()
# URI
self.uri = bits[1]
try:
parts = split_request_uri(self.uri)
except ValueError:
raise InvalidRequestLine(bytes_to_str(line_bytes))
self.path = parts.path or ""
self.query = parts.query or ""
self.fragment = parts.fragment or ""
# Version
match = VERSION_RE.match(bits[2])
if match is None:
raise InvalidHTTPVersion(bits[2])
self.version = (int(match.group(1)), int(match.group(2)))
def parse_request_line(self, line_bytes):
bits = [bytes_to_str(bit) for bit in line_bytes.split(None, 2)]
if len(bits) != 3:
raise InvalidRequestLine(bytes_to_str(line_bytes))
# Method
if not METH_RE.match(bits[0]):
raise InvalidRequestMethod(bits[0])
self.method = bits[0].upper()
# URI
self.uri = bits[1]
try:
parts = split_request_uri(self.uri)
except ValueError:
raise InvalidRequestLine(bytes_to_str(line_bytes))
self.path = parts.path or ""
self.query = parts.query or ""
self.fragment = parts.fragment or ""
# Version
match = VERSION_RE.match(bits[2])
if match is None:
raise InvalidHTTPVersion(bits[2])
self.version = (int(match.group(1)), int(match.group(2)))
def parse(self, unreader):
buf = io.BytesIO()
self.get_data(unreader, buf, stop=True)
# get request line, rbuf: 一行 \r\n 后面多余的数据
line, rbuf = self.read_line(unreader, buf, self.limit_request_line)
# todo: proxy protocol
if self.proxy_protocol(bytes_to_str(line)):
# get next request line
buf = io.BytesIO()
buf.write(rbuf)
line, rbuf = self.read_line(unreader, buf, self.limit_request_line)
# 处理请求行, 如: b'GET /test-db/1 HTTP/1.1'
self.parse_request_line(line)
buf = io.BytesIO()
buf.write(rbuf)
# data 如: b'Host: localhost:8000\r\nAccept: */*\r\n\r\na=1&b=2'
# 既包括请求头, 也包括请求体(a=1&b=2)
data = buf.getvalue()
idx = data.find(b"\r\n\r\n")
done = data[:2] == b"\r\n"
while True:
idx = data.find(b"\r\n\r\n")
# todo: 什么时候data的前两位会是\r\n呢?
done = data[:2] == b"\r\n"
if idx < 0 and not done:
self.get_data(unreader, buf)
data = buf.getvalue()
if len(data) > self.max_buffer_headers:
raise LimitRequestHeaders("max buffer headers")
else: # idx >= 0 or done
break
if done:
self.unreader.unread(data[2:])
return b""
# 请求头
self.headers = self.parse_headers(data[:idx])
# 请求体
ret = data[idx + 4:]
buf = None
return ret
def parse(self, unreader):
buf = io.BytesIO()
self.get_data(unreader, buf, stop=True)
# get request line
line, rbuf = self.read_line(unreader, buf, self.limit_request_line)
# proxy protocol
if self.proxy_protocol(bytes_to_str(line)):
# get next request line
buf = io.BytesIO()
buf.write(rbuf)
line, rbuf = self.read_line(unreader, buf, self.limit_request_line)
self.parse_request_line(line)
buf = io.BytesIO()
buf.write(rbuf)
# Headers
data = buf.getvalue()
idx = data.find(b"\r\n\r\n")
done = data[:2] == b"\r\n"
while True:
idx = data.find(b"\r\n\r\n")
done = data[:2] == b"\r\n"
if idx < 0 and not done:
self.get_data(unreader, buf)
data = buf.getvalue()
if len(data) > self.max_buffer_headers:
raise LimitRequestHeaders("max buffer headers")
else:
break
if done:
self.unreader.unread(data[2:])
return b""
self.headers = self.parse_headers(data[:idx])
ret = data[idx + 4:]
buf = None
return ret
def parse(self, unreader):
buf = io.BytesIO()
self.get_data(unreader, buf, stop=True)
# get request line
line, rbuf = self.read_line(unreader, buf, self.limit_request_line)
# proxy protocol
if self.proxy_protocol(bytes_to_str(line)):
# get next request line
buf = io.BytesIO()
buf.write(rbuf)
line, rbuf = self.read_line(unreader, buf, self.limit_request_line)
self.parse_request_line(line)
buf = io.BytesIO()
buf.write(rbuf)
# Headers
data = buf.getvalue()
idx = data.find(b"\r\n\r\n")
done = data[:2] == b"\r\n"
while True:
idx = data.find(b"\r\n\r\n")
done = data[:2] == b"\r\n"
if idx < 0 and not done:
self.get_data(unreader, buf)
data = buf.getvalue()
if len(data) > self.max_buffer_headers:
raise LimitRequestHeaders("max buffer headers")
else:
break
if done:
self.unreader.unread(data[2:])
return b""
self.headers = self.parse_headers(data[:idx])
ret = data[idx + 4:]
buf = None
return ret
def parse_headers(self, data):
cfg = self.cfg
headers = []
# Split lines on \r\n keeping the \r\n on each line
lines = [bytes_to_str(line) + "\r\n" for line in data.split(b"\r\n")]
# handle scheme headers
scheme_header = False
secure_scheme_headers = {}
if '*' in cfg.forwarded_allow_ips:
secure_scheme_headers = cfg.secure_scheme_headers
elif isinstance(self.unreader, SocketUnreader):
remote_addr = self.unreader.sock.getpeername()
if self.unreader.sock.family in (socket.AF_INET, socket.AF_INET6):
remote_host = remote_addr[0]
if remote_host in cfg.forwarded_allow_ips:
secure_scheme_headers = cfg.secure_scheme_headers
elif self.unreader.sock.family == socket.AF_UNIX:
secure_scheme_headers = cfg.secure_scheme_headers
# Parse headers into key/value pairs paying attention
# to continuation lines.
while lines:
if len(headers) >= self.limit_request_fields:
raise LimitRequestHeaders("limit request headers fields")
# Parse initial header name : value pair.
curr = lines.pop(0)
header_length = len(curr)
if curr.find(":") < 0:
raise InvalidHeader(curr.strip())
name, value = curr.split(":", 1)
name = name.rstrip(" \t").upper()
if HEADER_RE.search(name):
raise InvalidHeaderName(name)
name, value = name.strip(), [value.lstrip()]
# Consume value continuation lines
while lines and lines[0].startswith((" ", "\t")):
curr = lines.pop(0)
header_length += len(curr)
if header_length > self.limit_request_field_size > 0:
raise LimitRequestHeaders("limit request headers " +
"fields size")
value.append(curr)
value = ''.join(value).rstrip()
if header_length > self.limit_request_field_size > 0:
raise LimitRequestHeaders("limit request headers fields size")
if name in secure_scheme_headers:
secure = value == secure_scheme_headers[name]
scheme = "https" if secure else "http"
if scheme_header:
if scheme != self.scheme:
raise InvalidSchemeHeaders()
else:
scheme_header = True
self.scheme = scheme
headers.append((name, value))
return headers
def parse_headers(self, data):
cfg = self.cfg
headers = []
# Split lines on \r\n keeping the \r\n on each line
lines = [bytes_to_str(line) + "\r\n" for line in data.split(b"\r\n")]
# handle scheme headers
scheme_header = False
secure_scheme_headers = {}
if '*' in cfg.forwarded_allow_ips:
secure_scheme_headers = cfg.secure_scheme_headers
elif isinstance(self.unreader, SocketUnreader):
remote_addr = self.unreader.sock.getpeername()
if self.unreader.sock.family in (socket.AF_INET, socket.AF_INET6):
remote_host = remote_addr[0]
if remote_host in cfg.forwarded_allow_ips:
secure_scheme_headers = cfg.secure_scheme_headers
elif self.unreader.sock.family == socket.AF_UNIX:
secure_scheme_headers = cfg.secure_scheme_headers
# Parse headers into key/value pairs paying attention
# to continuation lines.
while lines:
if len(headers) >= self.limit_request_fields:
raise LimitRequestHeaders("limit request headers fields")
# Parse initial header name : value pair.
curr = lines.pop(0)
header_length = len(curr)
if curr.find(":") < 0:
raise InvalidHeader(curr.strip())
name, value = curr.split(":", 1)
name = name.rstrip(" \t").upper()
if HEADER_RE.search(name):
raise InvalidHeaderName(name)
name, value = name.strip(), [value.lstrip()]
# Consume value continuation lines
while lines and lines[0].startswith((" ", "\t")):
curr = lines.pop(0)
header_length += len(curr)
if header_length > self.limit_request_field_size > 0:
raise LimitRequestHeaders("limit request headers "
+ "fields size")
value.append(curr)
value = ''.join(value).rstrip()
if header_length > self.limit_request_field_size > 0:
raise LimitRequestHeaders("limit request headers fields size")
if name in secure_scheme_headers:
secure = value == secure_scheme_headers[name]
scheme = "https" if secure else "http"
if scheme_header:
if scheme != self.scheme:
raise InvalidSchemeHeaders()
else:
scheme_header = True
self.scheme = scheme
headers.append((name, value))
return headers
