Django开发:wsgi源码分析

入口

看源码,找到程序的入口是第一步,很简单,我们怎么启动django来着

python manage.py runserver 8000

好了,就它manage.py,我们来看看它里面都干了些啥(读源码不必面面俱到,找到关键代码即可)

#!/usr/bin/env python
import os
import sys

if __name__ == "__main__":
    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "Winston_crm.settings")
    try:
        from django.core.management import execute_from_command_line
    except ImportError:
        # The above import may fail for some other reason. Ensure that the
        # issue is really that Django is missing to avoid masking other
        # exceptions on Python 2.
        try:
            import django
        except ImportError:
            raise ImportError(
                "Couldn't import Django. Are you sure it's installed and "
                "available on your PYTHONPATH environment variable? Did you "
                "forget to activate a virtual environment?"
            )
        raise
    execute_from_command_line(sys.argv)

找到关键代码execute_from_command_line(sys.argv),进入到里面:

def execute_from_command_line(argv=None):
    """Run a ManagementUtility."""
    # 调用当前文件中的类ManagementUtility产生对象,这个类就在该函数的上方,一找就能找到
    utility = ManagementUtility(argv)
    # 调用类ManagementUtility中的方法execute
    utility.execute()

关键代码utility.execute() ,去类ManagementUtility中可以找到,该方法特别长,就不列举了,一连串if条件就是判断参数是否合法

进入到execute()方法中

def execute(self):
    """
    Given the command-line arguments, figure out which subcommand is being
    run, create a parser appropriate to that command, and run it.
    """
    # 获取命令行输入第一个参数,如果没有则为help
    try:
        subcommand = self.argv[1]
    except IndexError:
        subcommand = 'help'  # Display help if no arguments were given.

    # Preprocess options to extract --settings and --pythonpath.
    # These options could affect the commands that are available, so they
    # must be processed early.
    # 添加命令说明
    parser = CommandParser(usage='%(prog)s subcommand [options] [args]', add_help=False, allow_abbrev=False)
    parser.add_argument('--settings')
    parser.add_argument('--pythonpath')
    parser.add_argument('args', nargs='*')  # catch-all
    try:
        # 解析后面的参数,options:Namespace(args=[],pythonpath=None,settings=None)
        options, args = parser.parse_known_args(self.argv[2:])
        # 如果options中的pythonpath或者settings有,则使用传入的路径与文件
        handle_default_options(options)
    except CommandError:
        pass  # Ignore any option errors at this point.
    # 当是django-admin输入时没有配置文件此时会报错,
    # 如果是已经生产的项目则可以导入配置文件中已经配置的应用
    try:
        settings.INSTALLED_APPS
    except ImproperlyConfigured as exc:
        self.settings_exception = exc
    except ImportError as exc:
        self.settings_exception = exc

    if settings.configured:
        # Start the auto-reloading dev server even if the code is broken.
        # The hardcoded condition is a code smell but we can't rely on a
        # flag on the command class because we haven't located it yet.
        # 如果不是runserver并且没有关闭自动重载功能,则执行以下函数
        if subcommand == 'runserver' and '--noreload' not in self.argv:
            try:
                # 调用自动检测文件是否修改如果修改则自动重新启动Django服务
                autoreload.check_errors(django.setup)()
            except Exception:
                # The exception will be raised later in the child process
                # started by the autoreloader. Pretend it didn't happen by
                # loading an empty list of applications.
                apps.all_models = defaultdict(OrderedDict)
                apps.app_configs = OrderedDict()
                apps.apps_ready = apps.models_ready = apps.ready = True

                # Remove options not compatible with the built-in runserver
                # (e.g. options for the contrib.staticfiles' runserver).
                # Changes here require manually testing as described in
                # #27522.
                _parser = self.fetch_command('runserver').create_parser('django', 'runserver')
                _options, _args = _parser.parse_known_args(self.argv[2:])
                for _arg in _args:
                    self.argv.remove(_arg)

        # In all other cases, django.setup() is required to succeed.
        else:
            # 初始化Django环境
            django.setup()
    # 检测是否是自动完成
    self.autocomplete()
    # 如果解析命令为help
    if subcommand == 'help':
        if '--commands' in args:
            # 打印出help命令
            sys.stdout.write(self.main_help_text(commands_only=True) + '\n')
        # 如果输入参数为空
        elif not options.args:
            sys.stdout.write(self.main_help_text() + '\n')
        else:
            # 针对某个命令打印相应命令的帮助信息
            self.fetch_command(options.args[0]).print_help(self.prog_name, options.args[0])
    # Special-cases: We want 'django-admin --version' and
    # 'django-admin --help' to work, for backwards compatibility.
    # 如果输入的命令是打印版本信息
    elif subcommand == 'version' or self.argv[1:] == ['--version']:
        # 则输出当前Django的版本
        sys.stdout.write(django.get_version() + '\n')
    # 如果输入参数中包括了--help -h 则打印帮助信息
    elif self.argv[1:] in (['--help'], ['-h']):
        sys.stdout.write(self.main_help_text() + '\n')
    else:
        # 如果命令行输入单个命令,则寻找该命令,然后执行输入的参数
        self.fetch_command(subcommand).run_from_argv(self.argv)

首先使用命令行工具创建django项目和应用,此时使用的命令为startproject,startapp,该两个命令比较相似,实现的功能都是讲django/conf目录下的project_template和app_template两个模板进行一定数据的渲染后生成一个完整的项目到指定目录下。假如当前执行的参数为django-admin startapp testapp,此时就会执行到self.fetch_command(subcommand).run_from_argv(self.argv),链式调用,我们一点一点来看; 先看fetch_command(subcommand),即fetch_command('runserver'),就在类ManagementUtility中往上翻可以找到该方法,进入其中:

def fetch_command(self, subcommand): # 执行命令行输入的具体命令
    """
    Try to fetch the given subcommand, printing a message with the
    appropriate command called from the command line (usually
    "django-admin" or "manage.py") if it can't be found.
    """
    # Get commands outside of try block to prevent swallowing exceptions
    # get_comands()会返回一个字典
    commands = get_commands() # 获取所有支持的命令
    try:
    # app_name = commands[subcommand]取值操作即app_name='django.core' 
        app_name = commands[subcommand] # 获取命令名称所在的路径或者实例
    except KeyError:
        if os.environ.get('DJANGO_SETTINGS_MODULE'):
            # If `subcommand` is missing due to misconfigured settings, the
            # following line will retrigger an ImproperlyConfigured exception
            # (get_commands() swallows the original one) so the user is
            # informed about it.
            settings.INSTALLED_APPS
        else:
            sys.stderr.write("No Django settings specified.\n")
        possible_matches = get_close_matches(subcommand, commands)
        sys.stderr.write('Unknown command: %r' % subcommand)
        if possible_matches:
            sys.stderr.write('. Did you mean %s?' % possible_matches[0])
        sys.stderr.write("\nType '%s help' for usage.\n" % self.prog_name)
        sys.exit(1)
    if isinstance(app_name, BaseCommand):# 判断app_name是否是基本命令的实例,还是命令的路径
        # If the command is already loaded, use it directly.
        klass = app_name
    else:
    # klass = load_command_class(app_name, subcommand)
    # 即klass = load_command_class('django.core' ,’runserver‘),
    # 自己去看很简单,klass=django.core.management.commands.runserver.Command类
        klass = load_command_class(app_name, subcommand) # 如果是路径则导入该命令
    return klass # 将命令的实例化对象返回

self.fetch_command是利用django内置的命令管理工具去匹配到具体的模块,例如self.fetch_command(subcommand)其实就相当于是self.fetch_command('runserver'),它最终找到了==django.contrib.staticfiles.management.commands.runserver.Command==这个命令工具。
django中的命令工具代码组织采用的是策略模式+接口模式,也就是说django.core.management.commands这个目录下面存在各种命令工具,每个工具下面都有一个Command接口,当匹配到'runserver'时调用'runserver'命令工具的Command接口,当匹配到'migrate'时调用'migrate'命令工具的Command接口。

好啦,此时我们得知self.fetch_command(subcommand)得到的是类Command,好多人就在这懵逼了,接下来链式调用应该去找run_from_argv(self.argv)了,但是在Command类中怎么也找不到,傻了吧,去Command的父类BaseCommand里找啊

    def run_from_argv(self, argv):
        """
        Set up any environment changes requested (e.g., Python path
        and Django settings), then run this command. If the
        command raises a ``CommandError``, intercept it and print it sensibly
        to stderr. If the ``--traceback`` option is present or the raised
        ``Exception`` is not ``CommandError``, raise it.
        """
        self._called_from_command_line = True # 从命令行调入标识
        parser = self.create_parser(argv[0], argv[1])# 创建帮助的说明

        options = parser.parse_args(argv[2:])# 解析输入的参数
        cmd_options = vars(options)
        # Move positional args out of options to mimic legacy optparse
        args = cmd_options.pop('args', ())
        handle_default_options(options)# 调用命令行输入的配置文件
        try:
            self.execute(*args, **cmd_options)# 调用execute方法
        except Exception as e:
            if options.traceback or not isinstance(e, CommandError):
                raise

            # SystemCheckError takes care of its own formatting.
            if isinstance(e, SystemCheckError):
                self.stderr.write(str(e), lambda x: x)
            else:
                self.stderr.write('%s: %s' % (e.__class__.__name__, e))
            sys.exit(1)
        finally:
            try:
                connections.close_all()# 关闭所有的数据库连接
            except ImproperlyConfigured:
                # Ignore if connections aren't setup at this point (e.g. no
                # configured settings).
                pass

run_from_argv的作用是初始化中间件、启动服务,也就是拉起wsgi(但实际上并不是由它来直接完成,而是由后续很多其他代码来完成),直观上看它应该是runserver.Command对象的一个方法,但实际上要稍微更复杂一些,因为没有列出关联代码,所以在下一个代码块中进行说明。

关键代码self.execute(*args, **cmd_options),注意了,这个execute应该去Command类里找啊,因为该selfCommand类的对象啊,让我们回到Command类中,找execute

这里有个坑,我找了好久都没找到Command类的入口,原来藏在runserver.py中:

django/core/management/commands/runserver.py # Command类所在文件
class Command(BaseCommand):
    help = "Starts a lightweight Web server for development."

    # Validation is called explicitly each time the server is reloaded.
    requires_system_checks = False
    stealth_options = ('shutdown_message',)

    default_addr = '127.0.0.1'
    default_addr_ipv6 = '::1'
    default_port = '8000'# 默认启动服务监听的端口
    protocol = 'http'
    server_cls = WSGIServer

    def add_arguments(self, parser):  # 创建帮助信息
        parser.add_argument(
            'addrport', nargs='?',
            help='Optional port number, or ipaddr:port'
        )
        parser.add_argument(
            '--ipv6', '-6', action='store_true', dest='use_ipv6',
            help='Tells Django to use an IPv6 address.',
        )
        parser.add_argument(
            '--nothreading', action='store_false', dest='use_threading',
            help='Tells Django to NOT use threading.',
        )
        parser.add_argument(
            '--noreload', action='store_false', dest='use_reloader',
            help='Tells Django to NOT use the auto-reloader.',
        )

    def execute(self, *args, **options):# 调用处理方法
        if options['no_color']:# 检查是否需要更改文字颜色
            # We rely on the environment because it's currently the only
            # way to reach WSGIRequestHandler. This seems an acceptable
            # compromise considering `runserver` runs indefinitely.
            os.environ["DJANGO_COLORS"] = "nocolor"
        # super().execute(*args, **options)会去父类BaseCommand中找到excute方法,
        # 该方法中的关键代码为output = self.handle(*args, **options),
        # 该self是Command类的对象,所以接着去Command类中找到handle方法
        super().execute(*args, **options)# 调用父类的执行方法

    def get_handler(self, *args, **options):
        """Return the default WSGI handler for the runner."""
        return get_internal_wsgi_application()

    def handle(self, *args, **options):# 调用处理方法
        # 检查是否是debug模式,如果不是则ALLOWED_HOSTS不能为空
        if not settings.DEBUG and not settings.ALLOWED_HOSTS:
            raise CommandError('You must set settings.ALLOWED_HOSTS if DEBUG is False.')

        self.use_ipv6 = options['use_ipv6']
        # 检查输入参数中是否是ipv6格式,检查当前python是否支持ipv6
        if self.use_ipv6 and not socket.has_ipv6:
            raise CommandError('Your Python does not support IPv6.')
        self._raw_ipv6 = False
        # 如果输入参数中没有输入端口则使用默认的端口
        if not options['addrport']:
            self.addr = ''
            self.port = self.default_port
        # 检查匹配的ip格式
        else:
            m = re.match(naiveip_re, options['addrport'])
            if m is None:
                raise CommandError('"%s" is not a valid port number '
                                   'or address:port pair.' % options['addrport'])
            # 找出匹配的数据
            self.addr, _ipv4, _ipv6, _fqdn, self.port = m.groups()
            # 检查端口是否为数字
            if not self.port.isdigit():
                raise CommandError("%r is not a valid port number." % self.port)
            # 检查解析出的地址是否合法的ipv6地址
            if self.addr:
                if _ipv6:
                    self.addr = self.addr[1:-1]
                    self.use_ipv6 = True
                    self._raw_ipv6 = True
                elif self.use_ipv6 and not _fqdn:
                    raise CommandError('"%s" is not a valid IPv6 address.' % self.addr)
        # 如果没有输入ip地址则使用默认的地址
        if not self.addr:
            self.addr = self.default_addr_ipv6 if self.use_ipv6 else self.default_addr
            self._raw_ipv6 = self.use_ipv6
        # 运行,调用run方法
        self.run(**options)

    def run(self, **options):
        """Run the server, using the autoreloader if needed."""
        # 根据配置是否自动加载,如果没有输入则default=True  
        use_reloader = options['use_reloader']
        # 当开启了自动加载时,则调用自动启动运行
        if use_reloader:
            autoreload.run_with_reloader(self.inner_run, **options)
        # 如果没有开启文件更新自动重启服务功能则直接运行
        else:
            self.inner_run(None, **options)

    def inner_run(self, *args, **options):
        # If an exception was silenced in ManagementUtility.execute in order
        # to be raised in the child process, raise it now.
        autoreload.raise_last_exception()
        # 是否开启多线程模式,当不传入时则默认为多线程模式运行
        threading = options['use_threading']
        # 'shutdown_message' is a stealth option.
        shutdown_message = options.get('shutdown_message', '')
        # 打印停止服务信息
        quit_command = 'CTRL-BREAK' if sys.platform == 'win32' else 'CONTROL-C'

        self.stdout.write("Performing system checks...\n\n")
        self.check(display_num_errors=True)
        # Need to check migrations here, so can't use the
        # requires_migrations_check attribute.
        # 检查是否migrations是否与数据库一致
        self.check_migrations()
        # 获取当前时间
        now = datetime.now().strftime('%B %d, %Y - %X')
        # 解析当前时间
        self.stdout.write(now)
        # 打印时间等信息
        self.stdout.write((
            "Django version %(version)s, using settings %(settings)r\n"
            "Starting development server at %(protocol)s://%(addr)s:%(port)s/\n"
            "Quit the server with %(quit_command)s.\n"
        ) % {
            "version": self.get_version(),
            "settings": settings.SETTINGS_MODULE,
            "protocol": self.protocol,
            "addr": '[%s]' % self.addr if self._raw_ipv6 else self.addr,
            "port": self.port,
            "quit_command": quit_command,
        })

        try:
            # 获取信息处理的handler,默认返回wsgi
            handler = self.get_handler(*args, **options)
            # 调用run方法
            run(self.addr, int(self.port), handler,
                ipv6=self.use_ipv6, threading=threading, server_cls=self.server_cls)
        except socket.error as e:
            # Use helpful error messages instead of ugly tracebacks.
            ERRORS = {
                errno.EACCES: "You don't have permission to access that port.",
                errno.EADDRINUSE: "That port is already in use.",
                errno.EADDRNOTAVAIL: "That IP address can't be assigned to.",
            }
            try:
                error_text = ERRORS[e.errno]
            except KeyError:
                error_text = e
            self.stderr.write("Error: %s" % error_text)
            # Need to use an OS exit because sys.exit doesn't work in a thread
            os._exit(1)
        except KeyboardInterrupt:
            if shutdown_message:
                self.stdout.write(shutdown_message)
            sys.exit(0)

执行无异常的话,最终都要定位到一个run方法,该方法就在本文件开头位置导入过

from django.core.servers.basehttp import (
    WSGIServer, get_internal_wsgi_application, run,
)

截止到该部分,Command类实际上就是一个初始化过程,全部都为'runserver'服务,虽然很多代码我没有列出来,但是它确实做了一些,例如参数解析、端口指定检测、ipv4检测、ipv6检测、端口是否占用、线程检查、文件改动检测自动重启服务等工作。

接下来我把注意力放在django.core.servers.basehttp下的run函数上,代码如下

# 形参wsgi_handler的值为StaticFilesHandler
# run方法主要是知会各个对象启动wsgi服务
def run(addr, port, wsgi_handler, ipv6=False, threading=False, server_cls=WSGIServer):
    # 服务监听的地址和端口
    server_address = (addr, port)
    # 如果是多线程运行
    if threading:
        # 调用内置元类type创建一个类WSGIServer,该类继承了
        #(socketserver.ThreadingMixIn, WSGIServer),去代码块WSGIServer类中查看它本身只继承
        # wsgiref.simple_server.WSGIServer、object这两个类,通过type重新创建一下是给
        #类WSGIServer强行添加了一个爹socketserver.ThreadingMixIn,这么做的意义是每次调用类
        #WSGIServer的时候都会单独启用一个线程来处理,说完了WSGIServer的第一个基类,
        #我们再来说它的第二个基类WSGIServer完整的继承家族
        """
        django.core.servers.basehttp.WSGIServer
        wsgiref.simple_server.WSGIServer、 socketserver.ThreadingMixIn
        http.server.HTTPServer
        socketserver.TCPServer
        socketserver.BaseServer
        object
        """
        # httpd_cls这个变量被定义完成之后,由于大量的继承关系,它其实已经不单纯的属于django,
        # 它是一个传统意义上的WSGI服务对象了。
        httpd_cls = type('WSGIServer', (socketserver.ThreadingMixIn, server_cls), {})
    else:
        httpd_cls = server_cls
    # 实例化该类,它是WSGI服务器与django之间相互通信的唯一枢纽通道,也就是说,
    # 当WSGI服务对象收到socket请求后,会将这个请求传递给django的WSGIRequestHandler
    httpd = httpd_cls(server_address, WSGIRequestHandler, ipv6=ipv6)
    if threading:
        # ThreadingMixIn.daemon_threads indicates how threads will behave on an
        # abrupt shutdown; like quitting the server by the user or restarting
        # by the auto-reloader. True means the server will not wait for thread
        # termination before it quits. This will make auto-reloader faster
        # and will prevent the need to kill the server manually if a thread
        # isn't terminating correctly.
        # 等到子线程执行完成
        httpd.daemon_threads = True
    # 是将django.contrib.staticfiles.handlers.StaticFilesHandler 传递给
    # WSGIServer当作一个application,当WSGIServer收到网络请求后,可以将数据分发给
    # django.core.servers.basehttp.WSGIRequestHandler,最终由
    # django.core.servers.basehttp.WSGIRequestHandler将数据传递给
    # application(即:django.contrib.staticfiles.handlers.StaticFilesHandler)
    httpd.set_app(wsgi_handler)
    # 启动非堵塞网络监听服务。
    httpd.serve_forever()

总结:综上所述其实都是在为启动django服务而做准备,大致内容如下

  1. 解析运行 python manage.py 所提供的参数,例如: runserver.
  2. 根据参数 找到相对应的 命令管理工具。
  3. 加载所有的app。
  4. 检查端口、ipv4检测、ipv6检测、端口是否占用、线程检查、orm对象检查(表是否创建)。
  5. 实例化WSGIRequestHandler,并且将它注册到python Lib库中的WSGIServer中。
  6. 最后启动python Lib库中的WSGIServer

httpd.serve_forever调用的是socketserver.BaseServer.serve_forever方法(关于socketserver的源码解析点击这里,下面我直接说流程,原理不再累述)。

  1. socketserver.BaseServer.serve_forever方法采用了selector网络模型进行等待数据,每0.5秒遍历一次文件描述符,当有数据进来时,ready变量会是一个socket请求对象,这时会将后续工作转交给self._handler_request_noblock方法(即:socketserver.BaseServer._handler_request_noblock)去处理。

  2. socketserver.BaseServer._handler_request_noblock方法基本没做什么事情(self.verify_request压根就没有检查任何东西),直接就把后续工作转交给 socketserver.BaseServer.process_request 方法。

  3. socketserver.BaseServer.process_request也没做什么事情,直接就将后续工作转交给socketserver.BaseServer.finish_request方法,只不过在最后加了一条关闭请求的命令。

  4. socketserver.BaseServer.finish_request也没做什么事情,直接就将后续工作转交给socketserver.BaseServer.RequestHandlerClass

  5. socketserver.BaseServer.RequestHandlerClass是由上一节httpd = httpd_cls(server_address, WSGIRequestHandler, ipv6=ipv6)传递过来的参数django.core.servers.basehttp.WSGIRequestHandler。 也就是说当执行self.RequestHandler(request, client_address, self)时等同于执行django.core.servers.basehttp.WSGIRequestHandler(request, client_address, self)

serve_forever就是开启了一个while来无限监听网络层的scoket请求,当一条请求过来时,就层层转交到django.core.servers.basehttp.WSGIRequestHandler代码如下

class WSGIRequestHandler(simple_server.WSGIRequestHandler):
    protocol_version = 'HTTP/1.1'

    def address_string(self):
        # Short-circuit parent method to not call socket.getfqdn
        return self.client_address[0]

    def log_message(self, format, *args):
        extra = {
            'request': self.request,
            'server_time': self.log_date_time_string(),
        }
        if args[1][0] == '4':
            # 0x16 = Handshake, 0x03 = SSL 3.0 or TLS 1.x
            if args[0].startswith('\x16\x03'):
                extra['status_code'] = 500
                logger.error(
                    "You're accessing the development server over HTTPS, but "
                    "it only supports HTTP.\n", extra=extra,
                )
                return

        if args[1].isdigit() and len(args[1]) == 3:
            status_code = int(args[1])
            extra['status_code'] = status_code

            if status_code >= 500:
                level = logger.error
            elif status_code >= 400:
                level = logger.warning
            else:
                level = logger.info
        else:
            level = logger.info

        level(format, *args, extra=extra)

    def get_environ(self):
        # Strip all headers with underscores in the name before constructing
        # the WSGI environ. This prevents header-spoofing based on ambiguity
        # between underscores and dashes both normalized to underscores in WSGI
        # env vars. Nginx and Apache 2.4+ both do this as well.
        for k in self.headers:
            if '_' in k:
                del self.headers[k]

        return super().get_environ()

    def handle(self): # 关键代码
        self.close_connection = True
        self.handle_one_request()
        while not self.close_connection:
            self.handle_one_request()
        try:
            self.connection.shutdown(socket.SHUT_WR)
        except (socket.error, AttributeError):
            pass

    def handle_one_request(self):
        """Copy of WSGIRequestHandler.handle() but with different ServerHandler"""
        self.raw_requestline = self.rfile.readline(65537)
        if len(self.raw_requestline) > 65536:
            self.requestline = ''
            self.request_version = ''
            self.command = ''
            self.send_error(414)
            return

        if not self.parse_request():  # An error code has been sent, just exit
            return

        handler = ServerHandler(
            self.rfile, self.wfile, self.get_stderr(), self.get_environ()
        )
        handler.request_handler = self      # backpointer for logging & connection closing
        handler.run(self.server.get_app())

方法handle,至于如何调用到它,需要从WSGIRequestHandler的实例化说起,上面我们提到当执行self.RequestHandler(request, client_address, self)时等同于执行django.core.servers.basehttp.WSGIRequestHandler(request, client_address, self),而WSGIRequestHandler的继承的父类们如下:

1. django.core.servers.basehttp.WSGIRequestHandler
2. wsgiref.simple_server.WSGIRequestHandler
3. http.server.BaseHTTPRequestHandler
4. socketserver.StreamRequestHandler
5. socketserver.BaseRequestHandler
6. object

实例化类WSGIRequestHandler时发现它并没有__init____call__方法,需要去父类中找,最终在socketserver.BaseRequestHandler中找到,它调用了self.hande方法,注意self.handle并不是直接调用BaseRequestHandler中的handle,根据对象属性的查找关系,会去django.core.servers.basehttp.WSGIRequestHandler类中找,找到了handle,其实是相当于回调了handle,代码如下

def handle(self):
    self.close_connection = True
    self.handle_one_request()
    while not self.close_connection:
        self.handle_one_request() # 关键代码
    try:
        self.connection.shutdown(socket.SHUT_WR)
    except (socket.error, AttributeError):
        pass

关键代码:self.handle_one_request()直接在当前类中找到,代码如下

def handle_one_request(self):
    """Copy of WSGIRequestHandler.handle() but with different ServerHandler"""
    self.raw_requestline = self.rfile.readline(65537)
    if len(self.raw_requestline) > 65536:
        self.requestline = ''
        self.request_version = ''
        self.command = ''
        self.send_error(414)
        return

    if not self.parse_request():  # An error code has been sent, just exit
        return
    # 实例化了ServerHandler对象
    handler = ServerHandler(
        self.rfile, self.wfile, self.get_stderr(), self.get_environ()
    )
    # 将django.contrib.staticfiles.handlers.StaticFilesHandler转交给ServerHandler去运行,
    # 而ServerHandler对象并没有run方法,去它的父类们中去找
    handler.request_handler = self      # backpointer for logging & connection closing
    handler.run(self.server.get_app())

run方法位置:

1、django.core.servers.basehttp.ServerHandler
2、wsgiref.simple_server.ServerHandler
3、wsgiref.handlers.SimpleHandler
4、wsgiref.handlers.BaseHandler # 在此处找到run方法
5object

进入run方法:

 def run(self, application):
        """Invoke the application"""
        # Note to self: don't move the close()!  Asynchronous servers shouldn't
        # call close() from finish_response(), so if you close() anywhere but
        # the double-error branch here, you'll break asynchronous servers by
        # prematurely closing.  Async servers must return from 'run()' without
        # closing if there might still be output to iterate over.
        try:
            self.setup_environ()
            self.result = application(self.environ, self.start_response)# 关键代码
            self.finish_response()
        except:
            try:
                self.handle_error()
            except:
                # If we get an error handling an error, just give up already!
                self.close()
                raise   # ...and let the actual server figure it out.

关键代码:application(self.environ, self.start_response)也就相当于是django.contrib.staticfiles.handlers.StaticFilesHandler.__call__(self.environ, lf.start_response)

进入到StaticFilesHandler类中:

class StaticFilesHandler(WSGIHandler): # django专门用来处理静态文件的类
    """
    WSGI middleware that intercepts calls to the static files directory, as
    defined by the STATIC_URL setting, and serves those files.
    """
    # May be used to differentiate between handler types (e.g. in a
    # request_finished signal)
    handles_files = True

    def __init__(self, application):
        self.application = application
        # 解析配置的静态文件路径
        self.base_url = urlparse(self.get_base_url())
        super().__init__()

    def load_middleware(self):
        # Middleware are already loaded for self.application; no need to reload
        # them for self.
        pass

    def get_base_url(self):
        # 检查静态文件相关配置是否正确
        utils.check_settings()
        # 返回配置中的静态文件
        return settings.STATIC_URL

    def _should_handle(self, path):
        """
        Check if the path should be handled. Ignore the path if:
        * the host is provided as part of the base_url
        * the request's path isn't under the media path (or equal)
        """
        # 路径是否以静态路径开头,并且配置文件没有给出静态文件的Host
        return path.startswith(self.base_url[2]) and not self.base_url[1]

    def file_path(self, url):
        """
        Return the relative path to the media file on disk for the given URL.
        """
        # 获取文件的相对路径
        relative_url = url[len(self.base_url[2]):]
        return url2pathname(relative_url)

    def serve(self, request):
        """Serve the request path."""
        # 启动server处理静态文件
        return serve(request, self.file_path(request.path), insecure=True)

    def get_response(self, request):
        from django.http import Http404
        # 如果是静态文件路径则使用server处理
        if self._should_handle(request.path):
            try:
                return self.serve(request)
            except Http404 as e:
                return response_for_exception(request, e)
        return super().get_response(request)

    def __call__(self, environ, start_response):
        # 先判断请求url是否是静态文件路径
        if not self._should_handle(get_path_info(environ)):
            # 如果不是静态文件路径,则正常处理
            return self.application(environ, start_response) # 关键代码
        # 如果是静态文件路径则调用父方法处理
        return super().__call__(environ, start_response)

self.application(environ, start_response) ,先说self.application是个啥呢,可以看到在该类的__init__方法中执行了一个self.application = application,那它的值到底是啥呢?

读源码的窍门在于读一点记录一点,遇到看不懂的变量打印一下值看一下即可,最好不要重复回头,那样只会让你更晕,例如我们用管理用户(修改django源码需要权限)修改文件django.contrib.staticfiles.handlers.StaticFilesHandler加一行打印代码

def __init__(self, application):
    self.application = application
    print('django源码打印--->self.application值为',self.application) # 打印
    self.base_url = urlparse(self.get_base_url())
    super().__init__()

然后重启django可以看到self.application的值为<django.core.handlers.wsgi.WSGIHandler object at 0x106cf0278>,去查看类django.core.handlers.wsgi.WSGIHandler 的实例化发现加载了中间件self.load_middleware(),至此我们完成分析如何从wsgi服务到将url请求信息转交给django,剩下的就是django的内部流程啦,我们有机会再继续剖析吧

另外补充:可以用同样的手法查看envion变量,该变量非常重要,http协议的请求信息都被放入了environ变量中。我们分析流程中的WSGIServer类主要用于处理socket请求和对接WSGIRequestHandlerWSGIRequestHandler类主要针对environ进行预处理和对接WSGIServerHandler,而ServerHandler类则主要用于执行应用程序(application)和返回响应给WSGIServer

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章