CGIHTTPServer标准库源码学习

class CGIHTTPRequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):

    # 检测运行服务的平台为哪类操作系统 
    have_fork = hasattr(os, 'fork')
    have_popen2 = hasattr(os, 'popen2')
    have_popen3 = hasattr(os, 'popen3')

    # 关闭输入的缓存功能 
    rbufsize = 0

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

    def send_head(self):
        if self.is_cgi():
            return self.run_cgi()
        else:
            return SimpleHTTPServer.SimpleHTTPRequestHandler.send_head(self)

    def is_cgi(self):
        """ 判断请求的路径是否为一个 CGI 脚本 

        如果为一个 CGI 脚本，则更新 self.cgi_info 属性 (dir, rest), 并返回 True，否则返回 False
        """
        collapsed_path = _url_collapse_path(self.path)
        # 下面两行代码可以用一行代码代替 
        # head, _, tail = collapsed_path.partition('/')
        dir_sep = collapsed_path.find('/', 1)
        head, tail = collapsed_path[:dir_sep], collapsed_path[dir_sep+1:]
        # 只允许运行 CGI 脚本存放目录中的脚本 / 程序，
        # 由于 `_url_collapse_path` 已经对请求路径进行压缩过滤，所以这里简单判断即可 
        if head in self.cgi_directories:
            self.cgi_info = head, tail
            return True
        return False

    cgi_directories = ['/cgi-bin', '/htbin'] # CGI 脚本的存放目录 

    def is_executable(self, path):
        return executable(path)

    def is_python(self, path):
        """ 判断某文件是否为 Python 脚本 """
        head, tail = os.path.splitext(path)
        return tail.lower() in (".py", ".pyw") # 其实还有 pyc,pyo... ...

    def run_cgi(self):
        # 这个函数巨长无比 ... ...
        # 解析请求路径 
        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.have_fork or self.have_popen2 or self.have_popen3):
                self.send_error(403, "CGI script is not a Python script (%r)" %
                                scriptname)
                return
            if not self.is_executable(scriptfile):
                self.send_error(403, "CGI script is not executable (%r)" %
                                scriptname)
                return

        # 启动 CGI 脚本所需要的环境变量 
        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.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.getheader("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 = base64.decodestring(authorization[1])
                    except binascii.Error:
                        pass
                    else:
                        authorization = authorization.split(':')
                        if len(authorization) == 2:
                            env['REMOTE_USER'] = authorization[0]
        # XXX REMOTE_IDENT
        if self.headers.typeheader is None:
            env['CONTENT_TYPE'] = self.headers.type
        else:
            env['CONTENT_TYPE'] = self.headers.typeheader
        length = self.headers.getheader('content-length')
        if length:
            env['CONTENT_LENGTH'] = length
        referer = self.headers.getheader('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.getheader('user-agent')
        if ua:
            env['HTTP_USER_AGENT'] = ua
        co = filter(None, self.headers.getheaders('cookie'))
        if co:
            env['HTTP_COOKIE'] = ', '.join(co)
        # 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:
            # 在 Unix 平台上，使用 fork&&exec 形式启动子进程 
            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
                # 将请求内容读取及响应写入文件映射到子进程的标准输入 / 输出接口 
                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:
            # 非 Unix 平台，使用 subprocess 来启动子进程 
            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
                                )
            # 注意：请求及响应的数据，是在父进程处理的 
            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)
            p.stderr.close()
            p.stdout.close()
            status = p.returncode
            if status:
                self.log_error("CGI script exit status %#x", status)
            else:
                self.log_message("CGI script exited OK")