Django 精研Django源码分析

django源码分析--02url解析

2017-01-19  本文已影响937人  极光火狐狸

回顾上一章

wsgi通过ServerHandler来执行django的应用程序，第一个落地对象是，django.contrib.staticfiles.handlers.StaticFilesHandler。

class StaticFilesHandler(WSGIHandler):

    def __init__(self, application):
        self.application = application
        super(StaticFilesHandler, self).__init__()
        
    def _should_handle(self, path):
        return path.startswith(self.base_url[2]) and not self.base_url[1]
        
    def get_response(self, request):
        from django.http import Http404
        if self._should_handle(request.path):
            try:
                return self.serve(request)
            except Http404 as e:
                if settings.DEBUG:
                    from django.views import debug
                    return debug.technical_404_response(request, e)
        return super(StaticFilesHandler, self).get_response(request)
        
    def __call__(self, environ, start_response):
        if not self._should_handle(get_path_info(environ)):
            return self.application(environ, start_response)

        return super(StaticFilesHandler, self).__call__(environ, start_response)

django.contrib.staticfiles.handlers.StaticFilesHandler的作用是当请求出现时，先检查url是不是一个静态文件请求，如果是的话则进入静态文件(图片、css样式文件、js脚本文件等等)处理的view，如果不是的话则将该请求提交给Django的handler来进行处理(解析url、执行对应的view代码块、渲染和返回template)。

补充说明
__call__方法中比较有意思的是根据条件进行不同的返回。

 
 

URL解析

django.core.handlers.wsgi.py
class WSGIHandler(base.BaseHandler):
    request_class = WSGIRequest

    def __init__(self, *args, **kwargs):
        super(WSGIHandler, self).__init__(*args, **kwargs)
        self.load_middleware()

    def __call__(self, environ, start_response):
        set_script_prefix(get_script_name(environ))
        signals.request_started.send(sender=self.__class__, environ=environ)
        try:
            request = self.request_class(environ)
        except UnicodeDecodeError:
            logger.warning(
                'Bad Request (UnicodeDecodeError)',
                exc_info=sys.exc_info(),
                extra={
                    'status_code': 400,
                }
            )
            response = http.HttpResponseBadRequest()
        else:
            response = self.get_response(request)

        response._handler_class = self.__class__

        status = '%d %s' % (response.status_code, response.reason_phrase)
        response_headers = [(str(k), str(v)) for k, v in response.items()]
        for c in response.cookies.values():
            response_headers.append((str('Set-Cookie'), str(c.output(header=''))))
        start_response(force_str(status), response_headers)
        if getattr(response, 'file_to_stream', None) is not None and environ.get('wsgi.file_wrapper'):
            response = environ['wsgi.file_wrapper'](response.file_to_stream)
        return response

request = self.request_class(environ)负责初始化 WSGIRequest对象(这个对象有点想wsgi接口中的WSGIRequestHandler对象做的工作，针对environ进行预处理)，在初始化过程中主要是在原本environ中加工处理一些django程序能读得懂的参数(例如header、PATH_INFO、REQUEST_METHOD、charset等等)。
response = self.get_response(request)正如上面的补充说明环节说明一样，针对不同请求执行不同的方法，我主要是跟常规请求而不是静态文件请求，因此这个self.get_response实际上指的是django.core.handlers.base.BaseHandler.get_response。

django.core.handlers.base.py
class BaseHandler(object):

    def __init__(self):
        ...
        self._middleware_chain = None

    def load_middleware(self):
        ...

        if settings.MIDDLEWARE is None:
            ...
        else:
            handler = convert_exception_to_response(self._get_response)
            ...

        self._middleware_chain = handler

        
    def get_response(self, request):
        ...
        response = self._middleware_chain(request)  
        ...
        return response    
        
    def _get_response(self, request):
        response = None

        if hasattr(request, 'urlconf'):
            urlconf = request.urlconf
            set_urlconf(urlconf)
            resolver = get_resolver(urlconf)
        else:
            resolver = get_resolver()           # 初始化RegexURLResolver对象

        resolver_match = resolver.resolve(request.path_info)
        callback, callback_args, callback_kwargs = resolver_match
        request.resolver_match = resolver_match
        ...
        if response is None:
            wrapped_callback = self.make_view_atomic(callback)

            try:
                response = wrapped_callback(request, *callback_args, **callback_kwargs)
            except Exception as e:
                response = self.process_exception_by_middleware(e, request)
        ...
        return response

response = self._middleware_chain(request)，当执行完这行代码时，response变量就是一个html了，也就是说，所有的工作都隐藏在这行代码中。然而self._middleware_chain变量初始化的时候是None，然后在get_response方法中却可以被调用，这表明它是至少是一个方法或函数，也就是说，在调用get_response方法之前，这个self._middleware_chain变量已经被赋值过了，所以我要去找哪里有针对这个self._middleware_chain处理的地方。

django.core.handlers.base.BaseHandler._get_response 负责解析URL和传递参数给view。

小结
流程性的记录了request从初始化到url解析、再到response执行和返回过程。

 
 
 

深入理解URL解析

上一节有提及到resolver = get_resolver()、resolver_match = resolver.resolve(request.path_info)这两行代码，它就是理解URL解析的入口，另外一个理解URL解析的入口在项目文件的urls.py文件中(也就是我当前HelloWorld项目的HelloWorld.urls.py)。

HelloWorld.urls.py
from django.conf.urls import url    # 这里是重点
from django.contrib import admin

urlpatterns = [
    url(r'^admin/', admin.site.urls),
]

url(r'^admin/', admin.site.urls)这里采用了url()函数对正则表达式的url和视图进行包裹，反过来看就是将正则表达式url和视图当作参数传递给url()函数。
备注： admin.site.urls是一个tuple，里面包含一个url集合(另外一组urlpatterns)。

 

django.conf.urls.__init__.py
from django.urls import (
    LocaleRegexURLResolver, RegexURLPattern, RegexURLResolver,
)

def url(regex, view, kwargs=None, name=None):
    if isinstance(view, (list, tuple)):
        # For include(...) processing.
        urlconf_module, app_name, namespace = view
        return RegexURLResolver(regex, urlconf_module, kwargs, app_name=app_name, namespace=namespace)
    elif callable(view):
        return RegexURLPattern(regex, view, kwargs, name)
    else:
        raise TypeError('view must be a callable or a list/tuple in the case of include().')

通过查看url()函数的定义，regex参数可以看作是r'^admin/'， view参数可以看作是admin.site.urls。接下来是根据view参数的对象类型来调用不同的对象进行解析，因此这里临时插入一段代码来看看admin.site.urls。

django.contrib.admin.sites.py
class AdminSite(object):

    def __init__(self, name='admin'):
       self.name = name
        
    @property
    def urls(self):
        return self.get_urls(), 'admin', self.name

    def get_urls(self):
        from django.conf.urls import url, include

        def wrap(view, cacheable=False):
            def wrapper(*args, **kwargs):
                return self.admin_view(view, cacheable)(*args, **kwargs)
            wrapper.admin_site = self
            return update_wrapper(wrapper, view)

        urlpatterns = [
            url(r'^$', wrap(self.index), name='index'),
            url(r'^login/$', self.login, name='login'),
            url(r'^logout/$', wrap(self.logout), name='logout'),
            url(r'^password_change/$', wrap(self.password_change, cacheable=True), name='password_change'),
            url(r'^password_change/done/$', wrap(self.password_change_done, cacheable=True), name='password_change_done'),
            url(r'^jsi18n/$', wrap(self.i18n_javascript, cacheable=True), name='jsi18n'),
            url(r'^r/(?P<content_type_id>\d+)/(?P<object_id>.+)/$', wrap(contenttype_views.shortcut), name='view_on_site'),
        ]

        valid_app_labels = []
        for model, model_admin in self._registry.items():
            urlpatterns += [
                url(r'^%s/%s/' % (model._meta.app_label, model._meta.model_name), include(model_admin.urls)),
            ]
            if model._meta.app_label not in valid_app_labels:
                valid_app_labels.append(model._meta.app_label)

        if valid_app_labels:
            regex = r'^(?P<app_label>' + '|'.join(valid_app_labels) + ')/$'
            urlpatterns += [
                url(regex, wrap(self.app_index), name='app_list'),
            ]
        return urlpatterns

site = AdminSite()

透过这个代码片段可以清晰的看到admin.site.urls 实际上是一个元祖(tuple)对象，因此会匹配到if isinstance(view, (list, tuple))条件，并执行该条件下的代码块(返回RegexURLResolver初始化后的对象)。

urlconf_module, app_name, namespace = view这里将view拆分成了三个变量(对象)。

  • urlconf_module = self.get_urls() = 整个admin的所有定义的urls.
  • app_name = 'admin' = 常量变量'admin'字符串
  • namespace = self.name = 'admin' = 常量变量'admin'字符串，由于site = AdminSite()初始化过程中并没有提供任何参数，因此采用了默认的def __init__(self, name='admin')。

另外一个情况是当view是单个函数时，则会匹配到elif callable(view)并执行该条件下的代码块(返回RegexURLPattern初始化后的对象)。

小结
上面三个代码片段主要是为了接下来的django.urls.resolvers.RegexURLResolver对象的原理理解做一个铺垫，因此下面我会言归正传，接着django.core.handlers.base.BaseHandler._get_response往下走。

 

django.urls.resolvers.py
class ResolverMatch(object):
    def __init__(self, func, args, kwargs, url_name=None, app_names=None, namespaces=None):
        self.func = func
        self.args = args
        self.kwargs = kwargs
        self.url_name = url_name

        self.app_names = [x for x in app_names if x] if app_names else []
        self.app_name = ':'.join(self.app_names)
        self.namespaces = [x for x in namespaces if x] if namespaces else []
        self.namespace = ':'.join(self.namespaces)

        if not hasattr(func, '__name__'):
            self._func_path = '.'.join([func.__class__.__module__, func.__class__.__name__])
        else:
            self._func_path = '.'.join([func.__module__, func.__name__])

        view_path = url_name or self._func_path
        self.view_name = ':'.join(self.namespaces + [view_path])

    def __getitem__(self, index):
        return (self.func, self.args, self.kwargs)[index]

    def __repr__(self):
        return "ResolverMatch(func=%s, args=%s, kwargs=%s, url_name=%s, app_names=%s, namespaces=%s)" % (
            self._func_path, self.args, self.kwargs, self.url_name,
            self.app_names, self.namespaces,
        )


@lru_cache.lru_cache(maxsize=None)
def get_resolver(urlconf=None):
    if urlconf is None:
        from django.conf import settings
        urlconf = settings.ROOT_URLCONF
    return RegexURLResolver(r'^/', urlconf)


class LocaleRegexProvider(object):

    def __init__(self, regex):
        self._regex = regex
        self._regex_dict = {}

    @property
    def regex(self):
        language_code = get_language()
        if language_code not in self._regex_dict:
            regex = self._regex if isinstance(self._regex, six.string_types) else force_text(self._regex)
            try:
                compiled_regex = re.compile(regex, re.UNICODE)              # initially regex -> '^/'
            except re.error as e:
                raise ImproperlyConfigured(
                    '"%s" is not a valid regular expression: %s' %
                    (regex, six.text_type(e))
                )
            self._regex_dict[language_code] = compiled_regex
        return self._regex_dict[language_code]


class RegexURLResolver(LocaleRegexProvider):
    def __init__(self, regex, urlconf_name, default_kwargs=None, app_name=None, namespace=None):
        LocaleRegexProvider.__init__(self, regex)
        self.urlconf_name = urlconf_name
        self.callback = None
        self.default_kwargs = default_kwargs or {}
        self.namespace = namespace
        self.app_name = app_name
        self._reverse_dict = {}
        self._namespace_dict = {}
        self._app_dict = {}
        self._callback_strs = set()
        self._populated = False
        self._local = threading.local()
        
    def resolve(self, path):
        path = force_text(path)  # path may be a reverse_lazy object
        tried = []
        match = self.regex.search(path)
        if match:
            new_path = path[match.end():]
            for pattern in self.url_patterns:
                try:
                    sub_match = pattern.resolve(new_path)
                except Resolver404 as e:
                    sub_tried = e.args[0].get('tried')
                    if sub_tried is not None:
                        tried.extend([pattern] + t for t in sub_tried)
                    else:
                        tried.append([pattern])
                else:
                    if sub_match:
                        sub_match_dict = dict(match.groupdict(), **self.default_kwargs)
                        sub_match_dict.update(sub_match.kwargs)
                        sub_match_args = sub_match.args
                        if not sub_match_dict:
                            sub_match_args = match.groups() + sub_match.args

                        return ResolverMatch(
                            sub_match.func,
                            sub_match_args,
                            sub_match_dict,
                            sub_match.url_name,
                            [self.app_name] + sub_match.app_names,
                            [self.namespace] + sub_match.namespaces,
                        )
                    tried.append([pattern])
            raise Resolver404({'tried': tried, 'path': new_path})
        raise Resolver404({'path': path})

    @cached_property
    def urlconf_module(self):
        if isinstance(self.urlconf_name, six.string_types):
            return import_module(self.urlconf_name)
        else:
            return self.urlconf_name

    @cached_property
    def url_patterns(self):
        patterns = getattr(self.urlconf_module, "urlpatterns", self.urlconf_module)
        try:
            iter(patterns)
        except TypeError:
            msg = (
                "The included URLconf '{name}' does not appear to have any "
                "patterns in it. If you see valid patterns in the file then "
                "the issue is probably caused by a circular import."
            )
            raise ImproperlyConfigured(msg.format(name=self.urlconf_name))
        return patterns

django.core.handlers.base.BaseHandler._get_response方法中通过resolver = get_resolver()来初始化RegexURLResolver对象，它调用了当前代码片段中的get_resolver，返回值是RegexURLResolver(r'^/', urlconf)相当于RegexURLResolver(r'^/', 'HelloWorld.urls')。

django.core.handlers.base.BaseHandler._get_response 方法中通过resolver_match = resolver.resolve(request.path_info)来返回url解析结果，该url解析结果包含了对应的view、该view执行需要用到的args和该view执行需要用到的kwargs。resolver.resolve(request.path_info)相当于是RegexURLResolver(r'^/', 'HelloWorld.urls').resolve(request.path_info)。

上一篇 下一篇

猜你喜欢

热点阅读