"""HTTP server classes.

Note: BaseHTTPRequestHandler doesn't implement any HTTP request; see

SimpleHTTPRequestHandler for simple implementations of GET, HEAD and POST,

and (deprecated) CGIHTTPRequestHandler for CGI scripts.

It does, however, optionally implement HTTP/1.1 persistent connections.

Notes on CGIHTTPRequestHandler

------------------------------

This class is deprecated. It implements GET and POST requests to cgi-bin scripts.

If the os.fork() function is not present (Windows), subprocess.Popen() is used,

with slightly altered but never documented semantics. Use from a threaded

process is likely to trigger a warning at os.fork() time.

In all cases, the implementation is intentionally naive -- all

requests are executed synchronously.

SECURITY WARNING: DON'T USE THIS CODE UNLESS YOU ARE INSIDE A FIREWALL

-- it may execute arbitrary Python code or external programs.

Note that status code 200 is sent prior to execution of a CGI script, so

scripts cannot send other status codes such as 302 (redirect).

XXX To do:

- log requests even later (to capture byte count)

- log user-agent header and other interesting goodies

- send error log to separate file

"""

# See also:

#

# HTTP Working Group T. Berners-Lee

# INTERNET-DRAFT R. T. Fielding

# <draft-ietf-http-v10-spec-00.txt> H. Frystyk Nielsen

# Expires September 8, 1995 March 8, 1995

#

# URL: http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt

#

# and

#

# Network Working Group R. Fielding

# Request for Comments: 2616 et al

# Obsoletes: 2068 June 1999

# Category: Standards Track

#

# URL: http://www.faqs.org/rfcs/rfc2616.html

# Log files

# ---------

#

# Here's a quote from the NCSA httpd docs about log file format.

#

# | The logfile format is as follows. Each line consists of:

# |

# | host rfc931 authuser [DD/Mon/YYYY:hh:mm:ss] "request" ddd bbbb

# |

# | host: Either the DNS name or the IP number of the remote client

# | rfc931: Any information returned by identd for this person,

# | - otherwise.

# | authuser: If user sent a userid for authentication, the user name,

# | - otherwise.

# | DD: Day

# | Mon: Month (calendar name)

# | YYYY: Year

# | hh: hour (24-hour format, the machine's timezone)

# | mm: minutes

# | ss: seconds

# | request: The first line of the HTTP request as sent by the client.

# | ddd: the status code returned by the server, - if not available.

# | bbbb: the total number of bytes sent,

# | *not including the HTTP/1.0 header*, - if not available

# |

# | You can determine the name of the file accessed through request.

#

# (Actually, the latter is only true if you know the server configuration

# at the time the request was made!)

__version__ = "0.6"

__all__ = [

"HTTPServer", "ThreadingHTTPServer",

"HTTPSServer", "ThreadingHTTPSServer",

"BaseHTTPRequestHandler", "SimpleHTTPRequestHandler",

"CGIHTTPRequestHandler",

]

import copy

import datetime

import email.utils

import html

import http.client

import io

import itertools

import mimetypes

import os

import posixpath

import select

import shutil

import socket

import socketserver

import sys

import time

import urllib.parse

from http import HTTPStatus

# Default error message template

DEFAULT_ERROR_MESSAGE = """\

<!DOCTYPE HTML>

<html lang="en">

<head>

<meta charset="utf-8">

<style type="text/css">

:root {

color-scheme: light dark;

}

</style>

<title>Error response</title>

</head>

<body>

<h1>Error response</h1>

<p>Error code: %(code)d</p>

<p>Message: %(message)s.</p>

<p>Error code explanation: %(code)s - %(explain)s.</p>

</body>

</html>

"""

DEFAULT_ERROR_CONTENT_TYPE = "text/html;charset=utf-8"

# Data larger than this will be read in chunks, to prevent extreme

# overallocation.

_MIN_READ_BUF_SIZE = 1 << 20

class HTTPServer(socketserver.TCPServer):

allow_reuse_address = True # Seems to make sense in testing environment

allow_reuse_port = False

def server_bind(self):

"""Override server_bind to store the server name."""

socketserver.TCPServer.server_bind(self)

host, port = self.server_address[:2]

self.server_name = socket.getfqdn(host)

self.server_port = port

class ThreadingHTTPServer(socketserver.ThreadingMixIn, HTTPServer):

daemon_threads = True

class HTTPSServer(HTTPServer):

def __init__(self, server_address, RequestHandlerClass,

bind_and_activate=True, *, certfile, keyfile=None,

password=None, alpn_protocols=None):

try:

import ssl

except ImportError:

raise RuntimeError("SSL module is missing; "

"HTTPS support is unavailable")

self.ssl = ssl

self.certfile = certfile

self.keyfile = keyfile

self.password = password

# Support by default HTTP/1.1

self.alpn_protocols = (

["http/1.1"] if alpn_protocols is None else alpn_protocols

)

super().__init__(server_address,

RequestHandlerClass,

bind_and_activate)

def server_activate(self):

"""Wrap the socket in SSLSocket."""

super().server_activate()

context = self._create_context()

self.socket = context.wrap_socket(self.socket, server_side=True)

def _create_context(self):

"""Create a secure SSL context."""

context = self.ssl.create_default_context(self.ssl.Purpose.CLIENT_AUTH)

context.load_cert_chain(self.certfile, self.keyfile, self.password)

context.set_alpn_protocols(self.alpn_protocols)

return context

class ThreadingHTTPSServer(socketserver.ThreadingMixIn, HTTPSServer):

daemon_threads = True

class BaseHTTPRequestHandler(socketserver.StreamRequestHandler):

"""HTTP request handler base class.

The following explanation of HTTP serves to guide you through the

code as well as to expose any misunderstandings I may have about

HTTP (so you don't need to read the code to figure out I'm wrong

:-).

HTTP (HyperText Transfer Protocol) is an extensible protocol on

top of a reliable stream transport (e.g. TCP/IP). The protocol

recognizes three parts to a request:

1. One line identifying the request type and path

2. An optional set of RFC-822-style headers

3. An optional data part

The headers and data are separated by a blank line.

The first line of the request has the form

<command> <path> <version>

where <command> is a (case-sensitive) keyword such as GET or POST,

<path> is a string containing path information for the request,

and <version> should be the string "HTTP/1.0" or "HTTP/1.1".

<path> is encoded using the URL encoding scheme (using %xx to signify

the ASCII character with hex code xx).

The specification specifies that lines are separated by CRLF but

for compatibility with the widest range of clients recommends

servers also handle LF. Similarly, whitespace in the request line

is treated sensibly (allowing multiple spaces between components

and allowing trailing whitespace).

Similarly, for output, lines ought to be separated by CRLF pairs

but most clients grok LF characters just fine.

If the first line of the request has the form

<command> <path>

(i.e. <version> is left out) then this is assumed to be an HTTP

0.9 request; this form has no optional headers and data part and

the reply consists of just the data.

The reply form of the HTTP 1.x protocol again has three parts:

1. One line giving the response code

2. An optional set of RFC-822-style headers

3. The data

Again, the headers and data are separated by a blank line.

The response code line has the form

<version> <responsecode> <responsestring>

where <version> is the protocol version ("HTTP/1.0" or "HTTP/1.1"),

<responsecode> is a 3-digit response code indicating success or

failure of the request, and <responsestring> is an optional

human-readable string explaining what the response code means.

This server parses the request and the headers, and then calls a

function specific to the request type (<command>). Specifically,

a request SPAM will be handled by a method do_SPAM(). If no

such method exists the server sends an error response to the

client. If it exists, it is called with no arguments:

do_SPAM()

Note that the request name is case sensitive (i.e. SPAM and spam

are different requests).

The various request details are stored in instance variables:

- client_address is the client IP address in the form (host,

port);

- command, path and version are the broken-down request line;

- headers is an instance of email.message.Message (or a derived

class) containing the header information;

- rfile is a file object open for reading positioned at the

start of the optional input data part;

- wfile is a file object open for writing.

IT IS IMPORTANT TO ADHERE TO THE PROTOCOL FOR WRITING!

The first thing to be written must be the response line. Then

follow 0 or more header lines, then a blank line, and then the

actual data (if any). The meaning of the header lines depends on

the command executed by the server; in most cases, when data is

returned, there should be at least one header line of the form

Content-type: <type>/<subtype>

where <type> and <subtype> should be registered MIME types,

e.g. "text/html" or "text/plain".

"""

# The Python system version, truncated to its first component.

sys_version = "Python/" + sys.version.split()[0]

# The server software version. You may want to override this.

# The format is multiple whitespace-separated strings,

# where each string is of the form name[/version].

server_version = "BaseHTTP/" + __version__

error_message_format = DEFAULT_ERROR_MESSAGE

error_content_type = DEFAULT_ERROR_CONTENT_TYPE

# The default request version. This only affects responses up until

# the point where the request line is parsed, so it mainly decides what

# the client gets back when sending a malformed request line.

# Most web servers default to HTTP 0.9, i.e. don't send a status line.

default_request_version = "HTTP/0.9"

def parse_request(self):

"""Parse a request (internal).

The request should be stored in self.raw_requestline; the results

are in self.command, self.path, self.request_version and

self.headers.

Return True for success, False for failure; on failure, any relevant

error response has already been sent back.

"""

is_http_0_9 = False

self.command = None # set in case of error on the first line

self.request_version = version = self.default_request_version

self.close_connection = True

requestline = str(self.raw_requestline, 'iso-8859-1')

requestline = requestline.rstrip('\r\n')

self.requestline = requestline

words = requestline.split()

if len(words) == 0:

return False

if len(words) >= 3: # Enough to determine protocol version

version = words[-1]

try:

if not version.startswith('HTTP/'):

raise ValueError

base_version_number = version.split('/', 1)[1]

version_number = base_version_number.split(".")

# RFC 2145 section 3.1 says there can be only one "." and

# - major and minor numbers MUST be treated as

# separate integers;

# - HTTP/2.4 is a lower version than HTTP/2.13, which in

# turn is lower than HTTP/12.3;

# - Leading zeros MUST be ignored by recipients.

if len(version_number) != 2:

raise ValueError

if any(not component.isdigit() for component in version_number):

raise ValueError("non digit in http version")

if any(len(component) > 10 for component in version_number):

raise ValueError("unreasonable length http version")

version_number = int(version_number[0]), int(version_number[1])

except (ValueError, IndexError):

# Send the error response with a status line and headers.

self.request_version = ''

self.send_error(

HTTPStatus.BAD_REQUEST,

"Bad request version (%r)" % version)

return False

self.request_version = version

if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1":

self.close_connection = False

if version_number >= (2, 0