cpython/Lib/http/server.py

"""HTTP server classes.

Note: BaseHTTPRequestHandler doesn't implement any HTTP request; see
SimpleHTTPRequestHandler for simple implementations of GET, HEAD and POST,
and CGIHTTPRequestHandler for CGI scripts.

It does, however, optionally implement HTTP/1.1 persistent connections,
as of version 0.3.

Notes on CGIHTTPRequestHandler
------------------------------

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

If the os.fork() function is not present (e.g. on Windows),
subprocess.Popen() is used as a fallback, with slightly altered semantics.

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", "BaseHTTPRequestHandler"]

import cgi
import email.message
import email.parser
import http.client
import io
import mimetypes
import os
import posixpath
import select
import shutil
import socket # For gethostbyaddr()
import socketserver
import sys
import time
import urllib.parse
import copy

# Default error message template
DEFAULT_ERROR_MESSAGE = """\
<head>
<title>Error response</title>
</head>
<body>
<h1>Error response</h1>
<p>Error code %(code)d.
<p>Message: %(message)s.
<p>Error code explanation: %(code)s = %(explain)s.
</body>
"""

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

def _quote_html(html):
    return html.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")

class HTTPServer(socketserver.TCPServer):

    allow_reuse_address = 1    # Seems to make sense in testing environment

    def server_bind(self):
        """Override server_bind to store the server name."""
        socketserver.TCPServer.server_bind(self)
        host, port = self.socket.getsockname()[:2]
        self.server_name = socket.getfqdn(host)
        self.server_port = port


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, an
        error is sent back.

        """
        self.command = None  # set in case of error on the first line
        self.request_version = version = self.default_request_version
        self.close_connection = 1
        requestline = str(self.raw_requestline, 'iso-8859-1')
        if requestline[-2:] == '\r\n':
            requestline = requestline[:-2]
        elif requestline[-1:] == '\n':
            requestline = requestline[:-1]
        self.requestline = requestline
        words = requestline.split()
        if len(words) == 3:
            [command, path, version] = words
            if version[:5] != 'HTTP/':
                self.send_error(400, "Bad request version (%r)" % version)
                return False
            try:
                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
                version_number = int(version_number[0]), int(version_number[1])
            except (ValueError, IndexError):
                self.send_error(400, "Bad request version (%r)" % version)
                return False
            if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1":
                self.close_connection = 0
            if version_number >= (2, 0):
                self.send_error(505,
                          "Invalid HTTP Version (%s)" % base_version_number)
                return False
        elif len(words) == 2:
            [command, path] = words
            self.close_connection = 1
            if command != 'GET':
                self.send_error(400,
                                "Bad HTTP/0.9 request type (%r)" % command)
                return False
        elif not words:
            return False
        else:
            self.send_error(400, "Bad request syntax (%r)" % requestline)
            return False
        self.command, self.path, self.request_version = command, path, version

        # Examine the headers and look for a Connection directive.
        self.headers = http.client.parse_headers(self.rfile,
                                                 _class=self.MessageClass)

        conntype = self.headers.get('Connection', "")
        if conntype.lower() == 'close':
            self.close_connection = 1
        elif (conntype.lower() == 'keep-alive' and
              self.protocol_version >= "HTTP/1.1"):
            self.close_connection = 0
        return True

    def handle_one_request(self):
        """Handle a single HTTP request.

        You normally don't need to override this method; see the class
        __doc__ string for information on how to handle specific HTTP
        commands such as GET and POST.

        """
        self.raw_requestline = self.rfile.readline()
        if not self.raw_requestline:
            self.close_connection = 1
            return
        if not self.parse_request(): # An error code has been sent, just exit
            return
        mname = 'do_' + self.command
        if not hasattr(self, mname):
            self.send_error(501, "Unsupported method (%r)" % self.command)
            return
        method = getattr(self, mname)
        method()

    def handle(self):
        """Handle multiple requests if necessary."""
        self.close_connection = 1

        self.handle_one_request()
        while not self.close_connection:
            self.handle_one_request()

    def send_error(self, code, message=None):
        """Send and log an error reply.

        Arguments are the error code, and a detailed message.
        The detailed message defaults to the short entry matching the
        response code.

        This sends an error response (so it must be called before any
        output has been generated), logs the error, and finally sends
        a piece of HTML explaining the error to the user.

        """

        try:
            shortmsg, longmsg = self.responses[code]
        except KeyError:
            shortmsg, longmsg = '???', '???'
        if message is None:
            message = shortmsg
        explain = longmsg
        self.log_error("code %d, message %s", code, message)
        # using _quote_html to prevent Cross Site Scripting attacks (see bug #1100201)
        content = (self.error_message_format %
                   {'code': code, 'message': _quote_html(message), 'explain': explain})
        self.send_response(code, message)
        self.send_header("Content-Type", self.error_content_type)
        self.send_header('Connection', 'close')
        self.end_headers()
        if self.command != 'HEAD' and code >= 200 and code not in (204, 304):
            self.wfile.write(content.encode('UTF-8', 'replace'))

    def send_response(self, code, message=None):
        """Send the response header and log the response code.

        Also send two standard headers with the server software
        version and the current date.

        """
        self.log_request(code)
        if message is None:
            if code in self.responses:
                message = self.responses[code][0]
            else:
                message = ''
        if self.request_version != 'HTTP/0.9':
            self.wfile.write(("%s %d %s\r\n" %
                              (self.protocol_version, code, message)).encode('ASCII', 'strict'))
            # print (self.protocol_version, code, message)
        self.send_header('Server', self.version_string())
        self.send_header('Date', self.date_time_string())

    def send_header(self, keyword, value):
        """Send a MIME header."""
        if self.request_version != 'HTTP/0.9':
            self.wfile.write(("%s: %s\r\n" % (keyword, value)).encode('ASCII', 'strict'))

        if keyword.lower() == 'connection':
            if value.lower() == 'close':
                self.close_connection = 1
            elif value.lower() == 'keep-alive':
                self.close_connection = 0

    def end_headers(self):
        """Send the blank line ending the MIME headers."""
        if self.request_version != 'HTTP/0.9':
            self.wfile.write(b"\r\n")

    def log_request(self, code='-', size='-'):
        """Log an accepted request.

        This is called by send_response().

        """

        self.log_message('"%s" %s %s',
                         self.requestline, str(code), str(size))

    def log_error(self, format, *args):
        """Log an error.

        This is called when a request cannot be fulfilled.  By
        default it passes the message on to log_message().

        Arguments are the same as for log_message().

        XXX This should go to the separate error log.

        """

        self.log_message(format, *args)

    def log_message(self, format, *args):
        """Log an arbitrary message.

        This is used by all other logging functions.  Override
        it if you have specific logging wishes.

        The first argument, FORMAT, is a format string for the
        message to be logged.  If the format string contains
        any % escapes requiring parameters, they should be
        specified as subsequent arguments (it's just like
        printf!).

        The client host and current date/time are prefixed to
        every message.

        """

        sys.stderr.write("%s - - [%s] %s\n" %
                         (self.address_string(),
                          self.log_date_time_string(),
                          format%args))

    def version_string(self):
        """Return the server software version string."""
        return self.server_version + ' ' + self.sys_version

    def date_time_string(self, timestamp=None):
        """Return the current date and time formatted for a message header."""
        if timestamp is None:
            timestamp = time.time()
        year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp)
        s = "%s, %02d %3s %4d %02d:%02d:%02d GMT" % (
                self.weekdayname[wd],
                day, self.monthname[month], year,
                hh, mm, ss)
        return s

    def log_date_time_string(self):
        """Return the current time formatted for logging."""
        now = time.time()
        year, month, day, hh, mm, ss, x, y, z = time.localtime(now)
        s = "%02d/%3s/%04d %02d:%02d:%02d" % (
                day, self.monthname[month], year, hh, mm, ss)
        return s

    weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']

    monthname = [None,
                 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
                 '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.

        """

        host, port = self.client_address[:2]
        return socket.getfqdn(host)

    # Essentially static class variables

    # The version of the HTTP protocol we support.
    # Set this to HTTP/1.1 to enable automatic keepalive
    protocol_version = "HTTP/1.0"

    # MessageClass used to parse headers
    MessageClass = http.client.HTTPMessage

    # Table mapping response codes to messages; entries have the
    # form {code: (shortmessage, longmessage)}.
    # See RFC 2616.
    responses = {
        100: ('Continue', 'Request received, please continue'),
        101: ('Switching Protocols',
              'Switching to new protocol; obey Upgrade header'),

        200: ('OK', 'Request fulfilled, document follows'),
        201: ('Created', 'Document created, URL follows'),
        202: ('Accepted',
              'Request accepted, processing continues off-line'),
        203: ('Non-Authoritative Information', 'Request fulfilled from cache'),
        204: ('No Content', 'Request fulfilled, nothing follows'),
        205: ('Reset Content', 'Clear input form for further input.'),
        206: ('Partial Content', 'Partial content follows.'),

        300: ('Multiple Choices',
              'Object has several resources -- see URI list'),
        301: ('Moved Permanently', 'Object moved permanently -- see URI list'),
        302: ('Found', 'Object moved temporarily -- see URI list'),
        303: ('See Other', 'Object moved -- see Method and URL list'),
        304: ('Not Modified',
              'Document has not changed since given time'),
        305: ('Use Proxy',
              'You must use proxy specified in Location to access this '
              'resource.'),
        307: ('Temporary Redirect',
              'Object moved temporarily -- see URI list'),

        400: ('Bad Request',
              'Bad request syntax or unsupported method'),
        401: ('Unauthorized',
              'No permission -- see authorization schemes'),
        402: ('Payment Required',
              'No payment -- see charging schemes'),
        403: ('Forbidden',
              'Request forbidden -- authorization will not help'),
        404: ('Not Found', 'Nothing matches the given URI'),
        405: ('Method Not Allowed',
              'Specified method is invalid for this resource.'),
        406: ('Not Acceptable', 'URI not available in preferred format.'),
        407: ('Proxy Authentication Required', 'You must authenticate with '
              'this proxy before proceeding.'),
        408: ('Request Timeout', 'Request timed out; try again later.'),
        409: ('Conflict', 'Request conflict.'),
        410: ('Gone',
              'URI no longer exists and has been permanently removed.'),
        411: ('Length Required', 'Client must specify Content-Length.'),
        412: ('Precondition Failed', 'Precondition in headers is false.'),
        413: ('Request Entity Too Large', 'Entity is too large.'),
        414: ('Request-URI Too Long', 'URI is too long.'),
        415: ('Unsupported Media Type', 'Entity body in unsupported format.'),
        416: ('Requested Range Not Satisfiable',
              'Cannot satisfy request range.'),
        417: ('Expectation Failed',
              'Expect condition could not be satisfied.'),

        500: ('Internal Server Error', 'Server got itself in trouble'),
        501: ('Not Implemented',
              'Server does not support this operation'),
        502: ('Bad Gateway', 'Invalid responses from another server/proxy.'),
        503: ('Service Unavailable',
              'The server cannot process the request due to a high load'),
        504: ('Gateway Timeout',
              'The gateway server did not receive a timely response'),
        505: ('HTTP Version Not Supported', 'Cannot fulfill request.'),
        }


class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):

    """Simple HTTP request handler with GET and HEAD commands.

    This serves files from the current directory and any of its
    subdirectories.  The MIME type for files is determined by
    calling the .guess_type() method.

    The GET and HEAD requests are identical except that the HEAD
    request omits the actual contents of the file.

    """

    server_version = "SimpleHTTP/" + __version__

    def do_GET(self):
        """Serve a GET request."""
        f = self.send_head()
        if f:
            self.copyfile(f, self.wfile)
            f.close()

    def do_HEAD(self):
        """Serve a HEAD request."""
        f = self.send_head()
        if f:
            f.close()

    def send_head(self):
        """Common code for GET and HEAD commands.

        This sends the response code and MIME headers.

        Return value is either a file object (which has to be copied
        to the outputfile by the caller unless the command was HEAD,
        and must be closed by the caller under all circumstances), or
        None, in which case the caller has nothing further to do.

        """
        path = self.translate_path(self.path)
        f = None
        if os.path.isdir(path):
            if not self.path.endswith('/'):
                # redirect browser - doing basically what apache does
                self.send_response(301)
                self.send_header("Location", self.path + "/")
                self.end_headers()
                return None
            for index in "index.html", "index.htm":
                index = os.path.join(path, index)
                if os.path.exists(index):
                    path = index
                    break
            else:
                return self.list_directory(path)
        ctype = self.guess_type(path)
        try:
            f = open(path, 'rb')
        except IOError:
            self.send_error(404, "File not found")
            return None
        self.send_response(200)
        self.send_header("Content-type", ctype)
        fs = os.fstat(f.fileno())
        self.send_header("Content-Length", str(fs[6]))
        self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
        self.end_headers()
        return f

    def list_directory(self, path):
        """Helper to produce a directory listing (absent index.html).

        Return value is either a file object, or None (indicating an
        error).  In either case, the headers are sent, making the
        interface the same as for send_head().

        """
        try:
            list = os.listdir(path)
        except os.error:
            self.send_error(404, "No permission to list directory")
            return None
        list.sort(key=lambda a: a.lower())
        r = []
        displaypath = cgi.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")
        for name in list:
            fullname = os.path.join(path, name)
            displayname = linkname = name
            # Append / for directories or @ for symbolic links
            if os.path.isdir(fullname):
                displayname = name + "/"
                linkname = name + "/"
            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'
                    % (urllib.parse.quote(linkname), cgi.escape(displayname)))
        r.append("</ul>\n<hr>\n</body>\n</html>\n")
        enc = sys.getfilesystemencoding()
        encoded = ''.join(r).encode(enc)
        f = io.BytesIO()
        f.write(encoded)
        f.seek(0)
        self.send_response(200)
        self.send_header("Content-type", "text/html; charset=%s" % enc)
        self.send_header("Content-Length", str(len(encoded)))
        self.end_headers()
        return f

    def translate_path(self, path):
        """Translate a /-separated PATH to the local filename syntax.

        Components that mean special things to the local file system
        (e.g. drive or directory names) are ignored.  (XXX They should
        probably be diagnosed.)

        """
        # abandon query parameters
        path = path.split('?',1)[0]
        path = path.split('#',1)[0]
        path = posixpath.normpath(urllib.parse.unquote(path))
        words = path.split('/')
        words = filter(None, words)
        path = os.getcwd()
        for word in words:
            drive, word = os.path.splitdrive(word)
            head, word = os.path.split(word)
            if word in (os.curdir, os.pardir): continue
            path = os.path.join(path, word)
        return path

    def copyfile(self, source, outputfile):
        """Copy all data between two file objects.

        The SOURCE argument is a file object open for reading
        (or anything with a read() method) and the DESTINATION
        argument is a file object open for writing (or
        anything with a write() method).

        The only reason for overriding this would be to change
        the block size or perhaps to replace newlines by CRLF
        -- note however that this the default server uses this
        to copy binary data as well.

        """
        shutil.copyfileobj(source, outputfile)

    def guess_type(self, path):
        """Guess the type of a file.

        Argument is a PATH (a filename).

        Return value is a string of the form type/subtype,
        usable for a MIME Content-type header.

        The default implementation looks the file's extension
        up in the table self.extensions_map, using application/octet-stream
        as a default; however it would be permissible (if
        slow) to look inside the data to make a better guess.

        """

        base, ext = posixpath.splitext(path)
        if ext in self.extensions_map:
            return self.extensions_map[ext]
        ext = ext.lower()
        if ext in self.extensions_map:
            return self.extensions_map[ext]
        else:
            return self.extensions_map['']

    if not mimetypes.inited:
        mimetypes.init() # try to read system mime.types
    extensions_map = mimetypes.types_map.copy()
    extensions_map.update({
        '': 'application/octet-stream', # Default
        '.py': 'text/plain',
        '.c': 'text/plain',
        '.h': 'text/plain',
        })


# Utilities for CGIHTTPRequestHandler

# TODO(gregory.p.smith): Move this into an appropriate library.
def _url_collapse_path_split(path):
    """
    Given a URL path, remove extra '/'s and '.' path elements and collapse
    any '..' references.

    Implements something akin to RFC-2396 5.2 step 6 to parse relative paths.

    Returns: A tuple of (head, tail) where tail is everything after the final /
    and head is everything before it.  Head will always start with a '/' and,
    if it contains anything else, never have a trailing '/'.

    Raises: IndexError if too many '..' occur within the path.
    """
    # Similar to os.path.split(os.path.normpath(path)) but specific to URL
    # path semantics rather than local operating system semantics.
    path_parts = []
    for part in path.split('/'):
        if part == '.':
            path_parts.append('')
        else:
            path_parts.append(part)
    # Filter out blank non trailing parts before consuming the '..'.
    path_parts = [part for part in path_parts[:-1] if part] + path_parts[-1:]
    if path_parts:
        tail_part = path_parts.pop()
    else:
        tail_part = ''
    head_parts = []
    for part in path_parts:
        if part == '..':
            head_parts.pop()
        else:
            head_parts.append(part)
    if tail_part and tail_part == '..':
        head_parts.pop()
        tail_part = ''
    return ('/' + '/'.join(head_parts), tail_part)


nobody = None

def nobody_uid():
    """Internal routine to get nobody's uid"""
    global nobody
    if nobody:
        return nobody
    try:
        import pwd
    except ImportError:
        return -1
    try:
        nobody = pwd.getpwnam('nobody')[2]
    except KeyError:
        nobody = 1 + max(map(lambda x: x[2], pwd.getpwall()))
    return nobody


def executable(path):
    """Test for executable file."""
    try:
        st = os.stat(path)
    except os.error:
        return False
    return st.st_mode & 0o111 != 0


class CGIHTTPRequestHandler(SimpleHTTPRequestHandler):

    """Complete HTTP server with GET, HEAD and POST commands.

    GET and HEAD also support running CGI scripts.

    The POST command is *only* implemented for CGI scripts.

    """

    # Determine platform specifics
    have_fork = hasattr(os, 'fork')

    # Make rfile unbuffered -- we need to read one line and then pass
    # the rest to a subprocess, so we can't use buffered input.
    rbufsize = 0

    def do_POST(self):
        """Serve a POST request.

        This is only implemented for CGI scripts.

        """

        if self.is_cgi():
            self.run_cgi()
        else:
            self.send_error(501, "Can only POST to CGI scripts")

    def send_head(self):
        """Version of send_head that support CGI scripts"""
        if self.is_cgi():
            return self.run_cgi()
        else:
            return SimpleHTTPRequestHandler.send_head(self)

    def is_cgi(self):
        """Test whether self.path corresponds to a CGI script.

        Returns True and updates the cgi_info attribute to the tuple
        (dir, rest) if self.path requires running a CGI script.
        Returns False otherwise.

        If any exception is raised, the caller should assume that
        self.path was rejected as invalid and act accordingly.

        The default implementation tests whether the normalized url
        path begins with one of the strings in self.cgi_directories
        (and the next character is a '/' or the end of the string).

        """

        splitpath = _url_collapse_path_split(self.path)
        if splitpath[0] in self.cgi_directories:
            self.cgi_info = splitpath
            return True
        return False

    cgi_directories = ['/cgi-bin', '/htbin']

    def is_executable(self, path):
        """Test whether argument path is an executable file."""
        return executable(path)

    def is_python(self, path):
        """Test whether argument path is a Python script."""
        head, tail = os.path.splitext(path)
        return tail.lower() in (".py", ".pyw")

    def run_cgi(self):
        """Execute a CGI script."""
        path = self.path
        dir, rest = self.cgi_info

        i = path.find('/', len(dir) + 1)
        while i >= 0:
            nextdir = path[:i]
            nextrest = path[i+1:]

            scriptdir = self.translate_path(nextdir)
            if os.path.isdir(scriptdir):
                dir, rest = nextdir, nextrest
                i = path.find('/', len(dir) + 1)
            else:
                break

        # find an explicit query string, if present.
        i = rest.rfind('?')
        if i >= 0:
            rest, query = rest[:i], rest[i+1:]
        else:
            query = ''

        # dissect the part after the directory name into a script name &
        # a possible additional path, to be stored in PATH_INFO.
        i = rest.find('/')
        if i >= 0:
            script, rest = rest[:i], rest[i:]
        else:
            script, rest = rest, ''

        scriptname = dir + '/' + script
        scriptfile = self.translate_path(scriptname)
        if not os.path.exists(scriptfile):
            self.send_error(404, "No such CGI script (%r)" % scriptname)
            return
        if not os.path.isfile(scriptfile):
            self.send_error(403, "CGI script is not a plain file (%r)" %
                            scriptname)
            return
        ispy = self.is_python(scriptname)
        if not ispy:
            if not self.is_executable(scriptfile):
                self.send_error(403, "CGI script is not executable (%r)" %
                                scriptname)
                return

        # Reference: http://hoohoo.ncsa.uiuc.edu/cgi/env.html
        # XXX Much of the following could be prepared ahead of time!
        env = copy.deepcopy(os.environ)
        env['SERVER_SOFTWARE'] = self.version_string()
        env['SERVER_NAME'] = self.server.server_name
        env['GATEWAY_INTERFACE'] = 'CGI/1.1'
        env['SERVER_PROTOCOL'] = self.protocol_version
        env['SERVER_PORT'] = str(self.server.server_port)
        env['REQUEST_METHOD'] = self.command
        uqrest = urllib.parse.unquote(rest)
        env['PATH_INFO'] = uqrest
        env['PATH_TRANSLATED'] = self.translate_path(uqrest)
        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:
            authorization = authorization.split()
            if len(authorization) == 2:
                import base64, binascii
                env['AUTH_TYPE'] = authorization[0]
                if authorization[0].lower() == "basic":
                    try:
                        authorization = authorization[1].encode('ascii')
                        authorization = base64.decodebytes(authorization).\
                                        decode('ascii')
                    except (binascii.Error, UnicodeError):
                        pass
                    else:
                        authorization = authorization.split(':')
                        if len(authorization) == 2:
                            env['REMOTE_USER'] = authorization[0]
        # XXX REMOTE_IDENT
        if self.headers.get('content-type') is None:
            env['CONTENT_TYPE'] = self.headers.get_content_type()
        else:
            env['CONTENT_TYPE'] = self.headers['content-type']
        length = self.headers.get('content-length')
        if length:
            env['CONTENT_LENGTH'] = length
        referer = self.headers.get('referer')
        if referer:
            env['HTTP_REFERER'] = referer
        accept = []
        for line in self.headers.getallmatchingheaders('accept'):
            if line[:1] in "\t\n\r ":
                accept.append(line.strip())
            else:
                accept = accept + line[7:].split(',')
        env['HTTP_ACCEPT'] = ','.join(accept)
        ua = self.headers.get('user-agent')
        if ua:
            env['HTTP_USER_AGENT'] = ua
        co = filter(None, self.headers.get_all('cookie', []))
        cookie_str = ', '.join(co)
        if cookie_str:
            env['HTTP_COOKIE'] = cookie_str
        # XXX Other HTTP_* headers
        # Since we're setting the env in the parent, provide empty
        # values to override previously set values
        for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH',
                  'HTTP_USER_AGENT', 'HTTP_COOKIE', 'HTTP_REFERER'):
            env.setdefault(k, "")

        self.send_response(200, "Script output follows")

        decoded_query = query.replace('+', ' ')

        if self.have_fork:
            # Unix -- fork as we should
            args = [script]
            if '=' not in decoded_query:
                args.append(decoded_query)
            nobody = nobody_uid()
            self.wfile.flush() # Always flush before forking
            pid = os.fork()
            if pid != 0:
                # Parent
                pid, sts = os.waitpid(pid, 0)
                # throw away additional data [see bug #427345]
                while select.select([self.rfile], [], [], 0)[0]:
                    if not self.rfile.read(1):
                        break
                if sts:
                    self.log_error("CGI script exit status %#x", sts)
                return
            # Child
            try:
                try:
                    os.setuid(nobody)
                except os.error:
                    pass
                os.dup2(self.rfile.fileno(), 0)
                os.dup2(self.wfile.fileno(), 1)
                os.execve(scriptfile, args, env)
            except:
                self.server.handle_error(self.request, self.client_address)
                os._exit(127)

        else:
            # Non-Unix -- use subprocess
            import subprocess
            cmdline = [scriptfile]
            if self.is_python(scriptfile):
                interp = sys.executable
                if interp.lower().endswith("w.exe"):
                    # On Windows, use python.exe, not pythonw.exe
                    interp = interp[:-5] + interp[-4:]
                cmdline = [interp, '-u'] + cmdline
            if '=' not in query:
                cmdline.append(query)
            self.log_message("command: %s", subprocess.list2cmdline(cmdline))
            try:
                nbytes = int(length)
            except (TypeError, ValueError):
                nbytes = 0
            p = subprocess.Popen(cmdline,
                                 stdin=subprocess.PIPE,
                                 stdout=subprocess.PIPE,
                                 stderr=subprocess.PIPE,
                                 env = env
                                 )
            if self.command.lower() == "post" and nbytes > 0:
                data = self.rfile.read(nbytes)
            else:
                data = None
            # throw away additional data [see bug #427345]
            while select.select([self.rfile._sock], [], [], 0)[0]:
                if not self.rfile._sock.recv(1):
                    break
            stdout, stderr = p.communicate(data)
            self.wfile.write(stdout)
            if stderr:
                self.log_error('%s', stderr)
            status = p.returncode
            if status:
                self.log_error("CGI script exit status %#x", status)
            else:
                self.log_message("CGI script exited OK")


def test(HandlerClass = BaseHTTPRequestHandler,
         ServerClass = HTTPServer, protocol="HTTP/1.0"):
    """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
    httpd = ServerClass(server_address, HandlerClass)

    sa = httpd.socket.getsockname()
    print("Serving HTTP on", sa[0], "port", sa[1], "...")
    try:
        httpd.serve_forever()
    except KeyboardInterrupt:
        print("\nKeyboard interrupt received, exiting.")
        httpd.server_close()
        sys.exit(0)

if __name__ == '__main__':
    test(HandlerClass=SimpleHTTPRequestHandler)