[urls.py设置技巧]URLconf处理其二：URL分解器

        注：以下内容转载自 现代魔法学院 网站的 URLconf处理其二：URL分解器 一文，仅供学习使用。

        通常一个 URL 分解器对应一个 URL 配置模块，它可以包含多个 URL 模式，也可以包含多个其他 URL 分解器。通过这种包含结构设计，实现 Django 对 URL 的层级解析。

        URL 分解器是 Django 实现 app 与项目解耦的关键。通常由 include 方法操作的 URL 配置模块，最终会被解释成为 URL 分解器。

        每个 URL 分解器都需要指定如下几个内容：

• 一个正则表达式字符串。URL 开始部分是否匹配正则表达式，如匹配，去除成功匹配部分后余下部分匹配包含的 URL 模式和 URL 分解器。
  
• URL 配置模块名或 URL 配置模块的引用。
  
• 可选的关键参数(字典形式)。
  
• 可选的 App 名称。
  
• 可选的名称空间名字。

        可以看看 Django 里 URL 分解器的实现，类 django.core.urlresolvers.RegexURLResolver 用来表示 URL 分解器。

class RegexURLResolver(object):
    def __init__(self, regex, urlconf_name, default_kwargs=None, app_name=None, namespace=None):
        # regex is a string representing a regular expression.
        # urlconf_name is a string representing the module containing URLconfs.
        self.regex = re.compile(regex, re.UNICODE)
        self.urlconf_name = urlconf_name
        if not isinstance(urlconf_name, basestring):
            self._urlconf_module = self.urlconf_name
        self.callback = None
        self.default_kwargs = default_kwargs or {}
        self.namespace = namespace
        self.app_name = app_name
        self._reverse_dict = None
        self._namespace_dict = None
        self._app_dict = None
 
    def __repr__(self):
        return '<%s %s (%s:%s) %s>' % (self.__class__.__name__, self.urlconf_name, self.app_name, self.namespace, self.regex.pattern)
 
    def _populate(self):
        lookups = MultiValueDict()
        namespaces = {}
        apps = {}
        for pattern in reversed(self.url_patterns):
            p_pattern = pattern.regex.pattern
            if p_pattern.startswith('^'):
                p_pattern = p_pattern[1:]
            if isinstance(pattern, RegexURLResolver):
                if pattern.namespace:
                    namespaces[pattern.namespace] = (p_pattern, pattern)
                    if pattern.app_name:
                        apps.setdefault(pattern.app_name, []).append(pattern.namespace)
                else:
                    parent = normalize(pattern.regex.pattern)
                    for name in pattern.reverse_dict:
                        for matches, pat in pattern.reverse_dict.getlist(name):
                            new_matches = []
                            for piece, p_args in parent:
                                new_matches.extend([(piece + suffix, p_args + args) for (suffix, args) in matches])
                            lookups.appendlist(name, (new_matches, p_pattern + pat))
                    for namespace, (prefix, sub_pattern) in pattern.namespace_dict.items():
                        namespaces[namespace] = (p_pattern + prefix, sub_pattern)
                    for app_name, namespace_list in pattern.app_dict.items():
                        apps.setdefault(app_name, []).extend(namespace_list)
            else:
                bits = normalize(p_pattern)
                lookups.appendlist(pattern.callback, (bits, p_pattern))
                if pattern.name is not None:
                    lookups.appendlist(pattern.name, (bits, p_pattern))
        self._reverse_dict = lookups
        self._namespace_dict = namespaces
        self._app_dict = apps
 
    def _get_reverse_dict(self):
        if self._reverse_dict is None:
            self._populate()
        return self._reverse_dict
    reverse_dict = property(_get_reverse_dict)
 
    def _get_namespace_dict(self):
        if self._namespace_dict is None:
            self._populate()
        return self._namespace_dict
    namespace_dict = property(_get_namespace_dict)
 
    def _get_app_dict(self):
        if self._app_dict is None:
            self._populate()
        return self._app_dict
    app_dict = property(_get_app_dict)
 
    def resolve(self, path):
        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, 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([(smart_str(k), v) for k, v in match.groupdict().items()])
                        sub_match_dict.update(self.default_kwargs)
                        for k, v in sub_match.kwargs.iteritems():
                            sub_match_dict[smart_str(k)] = v
                        return ResolverMatch(sub_match.func, sub_match.args, sub_match_dict, sub_match.url_name, self.app_name or sub_match.app_name, [self.namespace] + sub_match.namespaces)
                    tried.append([pattern])
            raise Resolver404({'tried': tried, 'path': new_path})
        raise Resolver404({'path' : path})
 
    def _get_urlconf_module(self):
        try:
            return self._urlconf_module
        except AttributeError:
            self._urlconf_module = import_module(self.urlconf_name)
            return self._urlconf_module
    urlconf_module = property(_get_urlconf_module)
 
    def _get_url_patterns(self):
        patterns = getattr(self.urlconf_module, "urlpatterns", self.urlconf_module)
        try:
            iter(patterns)
        except TypeError:
            raise ImproperlyConfigured("The included urlconf %s doesn't have any patterns in it" % self.urlconf_name)
        return patterns
    url_patterns = property(_get_url_patterns)
 
    def _resolve_special(self, view_type):
        callback = getattr(self.urlconf_module, 'handler%s' % view_type, None)
        if not callback:
            # No handler specified in file; use default
            # Lazy import, since urls.defaults imports this file
            from django.conf.urls import defaults
            callback = getattr(defaults, 'handler%s' % view_type)
        try:
            return get_callable(callback), {}
        except (ImportError, AttributeError), e:
            raise ViewDoesNotExist("Tried %s. Error was: %s" % (callback, str(e)))
 
    def resolve404(self):
        return self._resolve_special('404')
 
    def resolve500(self):
        return self._resolve_special('500')
 
    def reverse(self, lookup_view, *args, **kwargs):
        if args and kwargs:
            raise ValueError("Don't mix *args and **kwargs in call to reverse()!")
        try:
            lookup_view = get_callable(lookup_view, True)
        except (ImportError, AttributeError), e:
            raise NoReverseMatch("Error importing '%s': %s." % (lookup_view, e))
        possibilities = self.reverse_dict.getlist(lookup_view)
        for possibility, pattern in possibilities:
            for result, params in possibility:
                if args:
                    if len(args) != len(params):
                        continue
                    unicode_args = [force_unicode(val) for val in args]
                    candidate =  result % dict(zip(params, unicode_args))
                else:
                    if set(kwargs.keys()) != set(params):
                        continue
                    unicode_kwargs = dict([(k, force_unicode(v)) for (k, v) in kwargs.items()])
                    candidate = result % unicode_kwargs
                if re.search(u'^%s' % pattern, candidate, re.UNICODE):
                    return candidate
        # lookup_view can be URL label, or dotted path, or callable, Any of
        # these can be passed in at the top, but callables are not friendly in
        # error messages.
        m = getattr(lookup_view, '__module__', None)
        n = getattr(lookup_view, '__name__', None)
        if m is not None and n is not None:
            lookup_view_s = "%s.%s" % (m, n)
        else:
            lookup_view_s = lookup_view
        raise NoReverseMatch("Reverse for '%s' with arguments '%s' and keyword "
                "arguments '%s' not found." % (lookup_view_s, args, kwargs))