← Back
Editing: _url.cpython-38.pyc
U ��\ � - @ s` d Z ddlZddlZddlZddlZddlmZ zddlmZ W n ek rX dZY nX zddl m Z W n ek r� ddl m Z Y nX ddl m ZmZmZ edkr�ddlZG dd� dej�ZejjjZejjjZd d � Zejd d kZed �Z ze W n e k �r e Z Y nX ed�Z d�dd�Z!e!d� Z"Z#e$d�Z%e�&d�Z'e�&d�Z(e�&d�Z)e*dd� ej+D ��Z,e�&d�Z-e$d�Z.e$d�Z/e.e/B Z0e%e/B e1d�B Z2e0e2 Z3e2e1d�B Z4e0e4 Z5e4e1d � Z6e0e6 Z7e%e4B e1d �B Z8e0e8 Z9e%e8e1d � B Z:e0e: Z;e%e:e1d � B Z<e0e< Z=d�d!d"�Z>d#d$� Z?e?e2�Z@e>e3�ZAe?e4�ZBe?e6�ZCe>e5�ZDe?e<�ZEe>e=�ZFe?e:�ZGe>e;�ZHe?e8�ZIe>e9�ZJe?e%�ZKe*d%d� e,�L� D ��ZMe$d&�ZNd�d(d)�ZOd�d*d+�ZPd�d,d-�ZQd�d.d/�ZRd�d0d1�ZSd�d2d3�ZTd�d4d5�ZUd�d6d7�ZVd8d9d:d;dd<d=d>d?d@dAdBdBdCdDdEdFdGdHddIdJdKdLdMdNdOdPdQdRdSdTdUdVdTddWdXdYdZd[d?d@dd\�,ZWe1d]d^d_d`dadbdcdddedfdgdhdig �ZXd�djdk�ZYd�dldm�ZZG dndo� doe[�Z\dpdq� Z]drds� Z^e$� d fdtdu�Z_dvdw� Z`d�dxdy�Zad�dzd{�Zbd�d|d}�Zcd�d~d�Zdd�d�d��Zed�d�d��Zfd d�d d e,fd�d��Zgd�d�� Zhd�d�� Zid�d�� ZjG d�d�� d�ek�ZlelZmG d�d�� d�ek�Znd�d�d��ZodS )�a� Hyperlink provides Pythonic URL parsing, construction, and rendering. Usage is straightforward:: >>> from hyperlink import URL >>> url = URL.from_text(u'http://github.com/mahmoud/hyperlink?utm_source=docs') >>> url.host u'github.com' >>> secure_url = url.replace(scheme=u'https') >>> secure_url.get('utm_source')[0] u'docs' As seen here, the API revolves around the lightweight and immutable :class:`URL` type, documented below. � N)� normalize)� inet_pton)�Mapping)�encode�decode� IDNAErrorc @ s@ e Zd Zdejfdejfdejd fdejd fdejfgZdS ) � _sockaddr� sa_familyZ__pad1� ipv4_addr� � ipv6_addr� Z__pad2N) �__name__� __module__� __qualname__�ctypesZc_shortZc_ushortZc_byteZc_ulongZ_fields_� r r �0/usr/lib/python3/dist-packages/hyperlink/_url.pyr ) s �r c C s� t � }|�d�}| |_t�t�|��}t|| d t�|�t�|��dkrTt� t� � ��| tj krlt� |j d�S | tjkr�t� |jd�S t� d��d S )N�asciir r r zunknown address family)r r r r Zc_intZsizeof�WSAStringToAddressAZbyref�socket�errorZ FormatError�AF_INETZ string_atr �AF_INET6r )Zaddress_familyZ ip_stringZaddrZ addr_sizer r r r 3 s r � � �_MISSINGc s G � �fdd�dt �}|� S )a� Creates and returns a new **instance** of a new class, suitable for usage as a "sentinel", a kind of singleton often used to indicate a value is missing when ``None`` is a valid input. Args: name (str): Name of the Sentinel var_name (str): Set this name to the name of the variable in its respective module enable pickleability. >>> make_sentinel(var_name='_MISSING') _MISSING The most common use cases here in boltons are as default values for optional function arguments, partly because of its less-confusing appearance in automatically generated documentation. Sentinels also function well as placeholders in queues and linked lists. .. note:: By design, additional calls to ``make_sentinel`` with the same values will not produce equivalent objects. >>> make_sentinel('TEST') == make_sentinel('TEST') False >>> type(make_sentinel('TEST')) == type(make_sentinel('TEST')) False c s: e Zd Z� �fdd�Zdd� Z�r*dd� Zdd� ZeZd S ) z make_sentinel.<locals>.Sentinelc s � | _ �| _d S �N��name�var_name��selfr r r �__init__l s z(make_sentinel.<locals>.Sentinel.__init__c S s | j r | j S d| jj| jf S )Nz%s(%r))r � __class__r r r! r r r �__repr__p s z(make_sentinel.<locals>.Sentinel.__repr__c S s | j S r )r r! r r r � __reduce__u s z*make_sentinel.<locals>.Sentinel.__reduce__c S s dS )NFr r! r r r � __nonzero__x s z+make_sentinel.<locals>.Sentinel.__nonzero__N)r r r r# r% r& r' �__bool__r r r r �Sentinelk s r) )�object)r r r) r r r � make_sentinelM s r+ �_UNSETzB~-._0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzz^((?P<scheme>[^:/?#]+):)?((?P<_netloc_sep>//)(?P<authority>[^/?#]*))?(?P<path>[^?#]*)(\?(?P<query>[^#]*))?(#(?P<fragment>.*))?$z^[a-zA-Z0-9+-.]*$z�^(?:(?P<userinfo>[^@/?#]*)@)?(?P<host>(?:\[(?P<ipv6_host>[^[\]/?#]*)\])|(?P<plain_host>[^:/?#[\]]*)|(?P<bad_host>.*?))?(?::(?P<port>.*))?$c C s> g | ]6}t jD ]*}|| �d �tt|| d���d�f�qqS )r r �charmap)�string� hexdigitsr �unichr�int)�.0�a�br r r � <listcomp>� s � �r5 z([ -]+)z:/?#[]@z !$&'()*+,;=�%z:@�:z/?z&+�=Fc C sd t t�}|s t| �tdg�B } | D ]<}d�t|���d�}|�� }|�|� ||kr"|�|� q"|S )Nr6 z{0:02X}r )�dict� _HEX_CHAR_MAP�set�format�ordr �lower�pop)�delimsZ allow_percent�retZdelimZ_hexordZ _hexord_lowerr r r �_make_decode_map� s rB c C s\ i }t td�td��D ]@\}}t|�}|| kr@| ||< ||< qd�|� ||< ||< q|S )N� z%{0:02X})�zip�range�chrr< )Z safe_charsrA �i�v�cr r r �_make_quote_map� s rJ c C s( g | ] \}}|� d d�tkr||f�qS )r �replace)r �_UNRESERVED_CHARS�r2 �krH r r r r5 � s ��)r �r Tc C s< |r(t d| ��d�}d�dd� |D ��S d�dd� | D ��S )z�A very comprehensive percent encoding for encoding all delimiters. Used for arguments to DecodedURL, where a % means a percent sign, and not the character used by URLs for escaping bytes. �NFC�utf8r c S s g | ] }t | �qS r )�_UNRESERVED_QUOTE_MAP�r2 r4 r r r r5 � s z$_encode_reserved.<locals>.<listcomp>c S s g | ]}|t krt| n|�qS r )rL rR �r2 �tr r r r5 � s ��r r �join��text�maximalZbytestrr r r �_encode_reserved� s �r[ c C s< |r(t d| ��d�}d�dd� |D ��S d�dd� | D ��S )z.Percent-encode a single segment of a URL path.rP rQ r c S s g | ] }t | �qS r )�_PATH_PART_QUOTE_MAPrS r r r r5 � s z%_encode_path_part.<locals>.<listcomp>c S s g | ]}|t krt| n|�qS r )� _PATH_DELIMSr\ rT r r r r5 � s �rV rX r r r �_encode_path_part� s �r^ c C s< |r(t d| ��d�}d�dd� |D ��S d�dd� | D ��S )z]Percent-encode the first segment of a URL path for a URL without a scheme specified. rP rQ r c S s g | ] }t | �qS r )� _SCHEMELESS_PATH_PART_QUOTE_MAPrS r r r r5 � s z0_encode_schemeless_path_part.<locals>.<listcomp>c S s g | ]}|t krt| n|�qS r )�_SCHEMELESS_PATH_DELIMSr_ rT r r r r5 � s � rV rX r r r � _encode_schemeless_path_part� s �ra c s| | s|r dS | S |r d| } g }|r8� fdd�| D �}n.t | d �g}|�� fdd�| dd� D �� |rtd �|�S t|�S ) aL Percent-encode a tuple of path parts into a complete path. Setting *maximal* to False percent-encodes only the reserved characters that are syntactically necessary for serialization, preserving any IRI-style textual data. Leaving *maximal* set to its default True percent-encodes everything required to convert a portion of an IRI to a portion of a URI. RFC 3986 3.3: If a URI contains an authority component, then the path component must either be empty or begin with a slash ("/") character. If a URI does not contain an authority component, then the path cannot begin with two slash characters ("//"). In addition, a URI reference (Section 4.1) may be a relative-path reference, in which case the first path segment cannot contain a colon (":") character. r rO c s g | ]}|rt |� d �n|�qS ��rZ �r^ �r2 �partrc r r r5 s �z&_encode_path_parts.<locals>.<listcomp>r c s g | ]}|rt |� d �n|�qS rb rd re rc r r r5 " s �� N�/)ra �extendrW �tuple)Z text_parts�rooted� has_scheme� has_authority�joinedrZ Z encoded_partsr rc r �_encode_path_parts s � � ro c C s< |r(t d| ��d�}d�dd� |D ��S d�dd� | D ��S )�< Percent-encode a single query string key or value. rP rQ r c S s g | ] }t | �qS r )�_QUERY_KEY_QUOTE_MAPrS r r r r5 / s z%_encode_query_key.<locals>.<listcomp>c S s g | ]}|t krt| n|�qS r )�_QUERY_KEY_DELIMSrq rT r r r r5 0 s �rV rX r r r �_encode_query_key) s �rs c C s< |r(t d| ��d�}d�dd� |D ��S d�dd� | D ��S )rp rP rQ r c S s g | ] }t | �qS r )�_QUERY_VALUE_QUOTE_MAPrS r r r r5 : s z'_encode_query_value.<locals>.<listcomp>c S s g | ]}|t krt| n|�qS r )�_QUERY_VALUE_DELIMSrt rT r r r r5 ; s � rV rX r r r �_encode_query_value4 s �rv c C s< |r(t d| ��d�}d�dd� |D ��S d�dd� | D ��S )zyQuote the fragment part of the URL. Fragments don't have subdelimiters, so the whole URL fragment can be passed. rP rQ r c S s g | ] }t | �qS r )�_FRAGMENT_QUOTE_MAPrS r r r r5 E s z)_encode_fragment_part.<locals>.<listcomp>c S s g | ]}|t krt| n|�qS r )�_FRAGMENT_DELIMSrw rT r r r r5 F s �rV rX r r r �_encode_fragment_part? s �ry c C s< |r(t d| ��d�}d�dd� |D ��S d�dd� | D ��S )zXQuote special characters in either the username or password section of the URL. rP rQ r c S s g | ] }t | �qS r )�_USERINFO_PART_QUOTE_MAPrS r r r r5 P s z)_encode_userinfo_part.<locals>.<listcomp>c S s g | ]}|t krt| n|�qS r )�_USERINFO_DELIMSrz rT r r r r5 Q s �rV rX r r r �_encode_userinfo_partJ s �r| i� i$ iD �5 � i�$ �F �P i� � iw �� i) i� i| i� i' i �o �w i3 �n i� i� ii i* iB i� � i� � ij � i� i �� ),ZacapZafpr9 Zdns�fileZftpZgitZgopher�httpZhttpsZimapZippZippsZircZircsZldapZldapsZmmsZmsrpZmsrpsZmtqpZnfsZnntpZnntpsr? ZprosperoZredisZrsyncZrtspZrtspsZrtspuZsftpZsmbZsnmpZsshZsteamZsvnZtelnetZventriloZvncZwaisZwsZwssZxmppZurnZaboutZbitcoinZblob�dataZgeoZmagnetZmailtoZnewsZpkcs11ZsipZsipsZtelc C s� | � � } |dk rDz t|�}W n& ttfk rB td|f ��Y nX |dkrV|t| < n4|dkr~|dk rrtd| ��t�| � n td| ��dS )a Registers new scheme information, resulting in correct port and slash behavior from the URL object. There are dozens of standard schemes preregistered, so this function is mostly meant for proprietary internal customizations or stopgaps on missing standards information. If a scheme seems to be missing, please `file an issue`_! Args: text (unicode): Text representing the scheme. (the 'http' in 'http://hatnote.com') uses_netloc (bool): Does the scheme support specifying a network host? For instance, "http" does, "mailto" does not. Defaults to True. default_port (int): The default port, if any, for netloc-using schemes. .. _file an issue: https://github.com/mahmoud/hyperlink/issues Nz-default_port expected integer or None, not %rTFz>unexpected default port while specifying non-netloc scheme: %rz"uses_netloc expected bool, not: %r)r> r1 � ValueError� TypeError�SCHEME_PORT_MAP�NO_NETLOC_SCHEMES�add)rY � uses_netlocZ default_portr r r �register_schemem s$ � � r� c C sB | sdS | � � } | tkr dS | tkr(dS | �d�d tkr>dS |S )aA Whether or not a URL uses :code:`:` or :code:`://` to separate the scheme from the rest of the URL depends on the scheme's own standard definition. There is no way to infer this behavior from other parts of the URL. A scheme either supports network locations or it does not. The URL type's approach to this is to check for explicitly registered schemes, with common schemes like HTTP preregistered. This is the same approach taken by :mod:`urlparse`. URL adds two additional heuristics if the scheme as a whole is not registered. First, it attempts to check the subpart of the scheme after the last ``+`` character. This adds intuitive behavior for schemes like ``git+ssh``. Second, if a URL with an unrecognized scheme is loaded, it will maintain the separator it sees. FT�+���)r> r� r� �split)�scheme�defaultr r r �scheme_uses_netloc� s r� c @ s e Zd ZdZdS )� URLParseErrorz�Exception inheriting from :exc:`ValueError`, raised when failing to parse a URL. Mostly raised on invalid ports and IPv6 addresses. N)r r r �__doc__r r r r r� � s r� c C s | t kr |S | S d S r )r, )Zargumentr� r r r � _optional� s r� c G s< |s t d��t||�s8tdd�dd� |D ��| |f ��|S )z� Check that the given *value* is one of the given *types*, or raise an exception describing the problem using *name*. z1expected one or more types, maybe use _textcheck?�expected %s for %s, got %rz or c S s g | ] }|j �qS r )r rT r r r r5 � s z _typecheck.<locals>.<listcomp>)r� � isinstancer� rW )r �value�typesr r r � _typecheck� s ��r� c C sx t |t�sH|r|d kr|S tr"dnd}|r2|d n|}td|| |f ��|rtt|�t|�@ rttdd�|�| |f ��|S )N�unicode�strz or NoneTyper� z4one or more reserved delimiters %s present in %s: %rr )r� r� �PY2r� r; r� rW )r r� r@ �nullableZstr_nameZexpr r r � _textcheck� s �r� c C s t | t�r| �� } t| �S )z� Iterate over the (key, value) pairs in ``iterable``. This handles dictionaries sensibly, and falls back to assuming the iterable yields (key, value) pairs. This behaviour is similar to what Python's ``dict()`` constructor does. )r� r �items�iter)�iterabler r r � iter_pairs� s r� c C s t | ||td�S �N��normalize_case�encode_stray_percents� _decode_map)�_percent_decode�_UNRESERVED_DECODE_MAP�rY r� r� r r r �_decode_unreserved� s �r� c C s t | ||td�S r� )r� �_USERINFO_DECODE_MAPr� r r r �_decode_userinfo_part� s �r� c C s t | ||td�S )z� >>> _decode_path_part(u'%61%77%2f%7a') u'aw%2fz' >>> _decode_path_part(u'%61%77%2f%7a', normalize_case=True) u'aw%2Fz' r� )r� �_PATH_DECODE_MAPr� r r r �_decode_path_part� s �r� c C s t | ||td�S r� )r� �_QUERY_KEY_DECODE_MAPr� r r r �_decode_query_key s �r� c C s t | ||td�S r� )r� �_QUERY_VALUE_DECODE_MAPr� r r r �_decode_query_value s �r� c C s t | ||td�S r� )r� �_FRAGMENT_DECODE_MAPr� r r r �_decode_fragment_part s �r� �utf-8c C sN z| � |dkrdn|�}W n tk r2 | Y S X |�d�}t|�dkrN| S |d g}|j} |dd� D ]�} | dd� | dd� } } z| || � | | � W qj tk � r� | tk} | s�|s�| d� n| d� |r�| r�| | �� � | | � n| | � Y qjX qjd �|�}|dk�r|S z |� |�W S t k �rH |�r@� | Y S X dS ) a. Convert percent-encoded text characters to their normal, human-readable equivalents. All characters in the input text must be encodable by *subencoding*. All special characters underlying the values in the percent-encoding must be decodable as *subencoding*. If a non-*subencoding*-valid string is passed, the original text is returned with no changes applied. Only called by field-tailored variants, e.g., :func:`_decode_path_part`, as every percent-encodable part of the URL has characters which should not be percent decoded. >>> _percent_decode(u'abc%20def') u'abc def' Args: text (unicode): Text with percent-encoding present. normalize_case (bool): Whether undecoded percent segments, such as encoded delimiters, should be uppercased, per RFC 3986 Section 2.1. See :func:`_decode_path_part` for an example. subencoding (unicode): The name of the encoding underlying the percent-encoding. Pass `False` to get back raw bytes. raise_subencoding_exc (bool): Whether an error in decoding the bytes underlying the percent-decoding should be raised. Returns: unicode: The percent-decoded version of *text*, decoded by *subencoding*, unless `subencoding=False` which returns bytes. Fr� � %rg r Nr s %25� ) r �UnicodeEncodeErrorr� �len�append�KeyErrorr: �upperrW r �UnicodeDecodeError)rY r� Z subencoding�raise_subencoding_excr� r� Z quoted_bytes�bits�resr� �itemZhexpair�restZ pair_is_hexZunquoted_bytesr r r r� s@ " r� c C s^ | sdS z| � d�}W n tk r. | }Y n,X zt|dd�}W n tk rX | }Y nX |S )u� Decode a host from ASCII-encodable text to IDNA-decoded text. If the host text is not ASCII, it is returned unchanged, as it is presumed that it is already IDNA-decoded. Some technical details: _decode_host is built on top of the "idna" package, which has some quirks: Capital letters are not valid IDNA2008. The idna package will raise an exception like this on capital letters: > idna.core.InvalidCodepoint: Codepoint U+004B at position 1 ... not allowed However, if a segment of a host (i.e., something in url.host.split('.')) is already ASCII, idna doesn't perform its usual checks. In fact, for capital letters it automatically lowercases them. This check and some other functionality can be bypassed by passing uts46=True to idna.encode/decode. This allows a more permissive and convenient interface. So far it seems like the balanced approach. Example output (from idna==2.6): >> idna.encode(u'mahmöud.io') 'xn--mahmud-zxa.io' >> idna.encode(u'Mahmöud.io') Traceback (most recent call last): File "<stdin>", line 1, in <module> File "/home/mahmoud/virtualenvs/hyperlink/local/lib/python2.7/site-packages/idna/core.py", line 355, in encode result.append(alabel(label)) File "/home/mahmoud/virtualenvs/hyperlink/local/lib/python2.7/site-packages/idna/core.py", line 276, in alabel check_label(label) File "/home/mahmoud/virtualenvs/hyperlink/local/lib/python2.7/site-packages/idna/core.py", line 253, in check_label raise InvalidCodepoint('Codepoint {0} at position {1} of {2} not allowed'.format(_unot(cp_value), pos+1, repr(label))) idna.core.InvalidCodepoint: Codepoint U+004D at position 1 of u'Mahmöud' not allowed >> idna.encode(u'Mahmoud.io') 'Mahmoud.io' # Similar behavior for decodes below >> idna.decode(u'Mahmoud.io') u'mahmoud.io >> idna.decode(u'Méhmoud.io', uts46=True) u'méhmoud.io' r r T�Zuts46)r r� � idna_decoder� )�hostZ host_bytes� host_textr r r � _decode_hoste s - r� c C sb g }| D ].}|dkrq|dkr,|r6|� � q|�|� qt| dd� �dgdgfkr^|�d� |S )a� Normalize the URL path by resolving segments of '.' and '..'. For more details, see `RFC 3986 section 5.2.4, Remove Dot Segments`_. Args: path (list): path segments in string form Returns: list: a new list of path segments with the '.' and '..' elements removed and resolved. .. _RFC 3986 section 5.2.4, Remove Dot Segments: https://tools.ietf.org/html/rfc3986#section-5.2.4 �.z..r� Nr )r? r� �list)�pathZsegsZsegr r r �_resolve_dot_segments� s r� c C s� | sdS d| krvzt tj| � W nF tjk rT } ztd| |f ��W 5 d}~X Y n" tk rf Y nX tj}|| fS zt tj| � W n tjtfk r� d}Y nX tj}|| fS )a7 Parse the host into a tuple of ``(family, host)``, where family is the appropriate :mod:`socket` module constant when the host is an IP address. Family is ``None`` when the host is not an IP. Will raise :class:`URLParseError` on invalid IPv6 constants. Returns: tuple: family (socket constant or None), host (string) >>> parse_host('googlewebsite.com') == (None, 'googlewebsite.com') True >>> parse_host('::1') == (socket.AF_INET6, '::1') True >>> parse_host('192.168.1.1') == (socket.AF_INET, '192.168.1.1') True )Nr r7 zinvalid IPv6 host: %r (%r)N)r r r r r� r� r )r� ZseZfamilyr r r � parse_host� s" r� c @ s� e Zd ZdZdMdd�ZdNdd �Zed d � �Zed d � �Zedd� �Z edd� �Z edd� �Z edd� �Z edd� �Z edd� �Zedd� �Zed d � �ZdOd d �Zd d!� Zd"d#� Zd$d%� Zed&d'� �Zeeeeeeeeef d(d)�Zed*d+� �ZdPd-d.�Zd/d0� Zd1d2� Z dQd3d4�Z d5d6� Z d7d8� Z dRd9d:�Z d;d<� Z!d=d>� Z"e#�rLe"Z$e Z%ne"Z&e Z$e Z'e Z(ed?d@� �Z)dSdAdB�Z*dCdD� Z+dTdEdF�Z,dUdGdH�Z-dIdJ� Z.edfdKdL�Z/dS )V�URLa� From blogs to billboards, URLs are so common, that it's easy to overlook their complexity and power. With hyperlink's :class:`URL` type, working with URLs doesn't have to be hard. URLs are made of many parts. Most of these parts are officially named in `RFC 3986`_ and this diagram may prove handy in identifying them:: foo://user:pass@example.com:8042/over/there?name=ferret#nose \_/ \_______/ \_________/ \__/\_________/ \_________/ \__/ | | | | | | | scheme userinfo host port path query fragment While :meth:`~URL.from_text` is used for parsing whole URLs, the :class:`URL` constructor builds a URL from the individual components, like so:: >>> from hyperlink import URL >>> url = URL(scheme=u'https', host=u'example.com', path=[u'hello', u'world']) >>> print(url.to_text()) https://example.com/hello/world The constructor runs basic type checks. All strings are expected to be decoded (:class:`unicode` in Python 2). All arguments are optional, defaulting to appropriately empty values. A full list of constructor arguments is below. Args: scheme (unicode): The text name of the scheme. host (unicode): The host portion of the network location port (int): The port part of the network location. If ``None`` or no port is passed, the port will default to the default port of the scheme, if it is known. See the ``SCHEME_PORT_MAP`` and :func:`register_default_port` for more info. path (tuple): A tuple of strings representing the slash-separated parts of the path. query (tuple): The query parameters, as a dictionary or as an iterable of key-value pairs. fragment (unicode): The fragment part of the URL. rooted (bool): Whether or not the path begins with a slash. userinfo (unicode): The username or colon-separated username:password pair. uses_netloc (bool): Indicates whether two slashes appear between the scheme and the host (``http://eg.com`` vs ``mailto:e@g.com``). Set automatically based on scheme. All of these parts are also exposed as read-only attributes of URL instances, along with several useful methods. .. _RFC 3986: https://tools.ietf.org/html/rfc3986 .. _RFC 3987: https://tools.ietf.org/html/rfc3987 Nr r c C sD |d k r|d krd}|d kr&t �|�}|r6|r6|s6d}|d krBd}|d krNd}|d kr^t|�}td|�| _| jr�t�| j�s�td| j| jj f ��t td|d��\} | _ t |t �r�td|f ��td d � |D ��| _td d � t|�D ��| _td |�| _td |tt�| _td|t�| _td|d�| _t| j| �} td| tt�| _d S )Nr� rO r r� zginvalid scheme: %r. Only alphanumeric, "+", "-", and "." allowed. Did you meant to call %s.from_text()?r� z/?#@z+expected iterable of text for path, not: %rc s s | ]}t d |d�V qdS )� path segmentz/?#N�r� �r2 �segmentr r r � <genexpr>A s �z URL.__init__.<locals>.<genexpr>c s s. | ]&\}}t d |d�t d|ddd�fV qdS )zquery parameter namez&=#zquery parameter valuez&#T)r� Nr� rM r r r r� C s � ��fragment�portrk �userinfor� ) r� �get�boolr� �_scheme� _SCHEME_RE�matchr� r$ r r� �_hostr� r� r� rj �_pathr� �_query� _fragmentr� r1 �NoneType�_port�_rooted� _userinfor� � _uses_netloc) r" r� r� r� �queryr� r� rk r� r� �_r r r r# sP � �� � �z URL.__init__Fc C s2 z| j W S tk r* t| |d�| _ Y nX | j S �N��lazy)Z _decoded_url�AttributeError� DecodedURL)r" r� r r r �get_decoded_urlR s zURL.get_decoded_urlc C s | j S )aM The scheme is a string, and the first part of an absolute URL, the part before the first colon, and the part which defines the semantics of the rest of the URL. Examples include "http", "https", "ssh", "file", "mailto", and many others. See :func:`~hyperlink.register_scheme()` for more info. )r� r! r r r r� Y s z URL.schemec C s | j S )a The host is a string, and the second standard part of an absolute URL. When present, a valid host must be a domain name, or an IP (v4 or v6). It occurs before the first slash, or the second colon, if a :attr:`~hyperlink.URL.port` is provided. )r� r! r r r r� c s zURL.hostc C s | j S )a� The port is an integer that is commonly used in connecting to the :attr:`host`, and almost never appears without it. When not present in the original URL, this attribute defaults to the scheme's default port. If the scheme's default port is not known, and the port is not provided, this attribute will be set to None. >>> URL.from_text(u'http://example.com/pa/th').port 80 >>> URL.from_text(u'foo://example.com/pa/th').port >>> URL.from_text(u'foo://example.com:8042/pa/th').port 8042 .. note:: Per the standard, when the port is the same as the schemes default port, it will be omitted in the text URL. )r� r! r r r r� l s zURL.portc C s | j S )z�A tuple of strings, created by splitting the slash-separated hierarchical path. Started by the first slash after the host, terminated by a "?", which indicates the start of the :attr:`~hyperlink.URL.query` string. )r� r! r r r r� � s zURL.pathc C s | j S )a� Tuple of pairs, created by splitting the ampersand-separated mapping of keys and optional values representing non-hierarchical data used to identify the resource. Keys are always strings. Values are strings when present, or None when missing. For more operations on the mapping, see :meth:`~hyperlink.URL.get()`, :meth:`~hyperlink.URL.add()`, :meth:`~hyperlink.URL.set()`, and :meth:`~hyperlink.URL.delete()`. )r� r! r r r r� � s z URL.queryc C s | j S )a A string, the last part of the URL, indicated by the first "#" after the :attr:`~hyperlink.URL.path` or :attr:`~hyperlink.URL.query`. Enables indirect identification of a secondary resource, like an anchor within an HTML page. )r� r! r r r r� � s z URL.fragmentc C s | j S )ax Whether or not the path starts with a forward slash (``/``). This is taken from the terminology in the BNF grammar, specifically the "path-rootless", rule, since "absolute path" and "absolute URI" are somewhat ambiguous. :attr:`path` does not contain the implicit prefixed ``"/"`` since that is somewhat awkward to work with. )r� r! r r r rk � s z URL.rootedc C s | j S )zVThe colon-separated string forming the username-password combination. )r� r! r r r r� � s z URL.userinfoc C s | j S )z )r� r! r r r r� � s zURL.uses_netlocc C s | j �d�d S )zF The user portion of :attr:`~hyperlink.URL.userinfo`. r7 r )r� r� r! r r r �user� s zURL.userc K s� |� d|�}|r td|�� ��| j}d|kr>d| d g}n| jg}| jt�| j�krh|�t | j�� g }| j r�| j }|s�d|kr�|d|� d�d � }|�|� |�d� |�� d� |�S ) aV Compute and return the appropriate host/port/userinfo combination. >>> url = URL.from_text(u'http://user:pass@localhost:8080/a/b?x=y') >>> url.authority() u'user:@localhost:8080' >>> url.authority(with_password=True) u'user:pass@localhost:8080' Args: with_password (bool): Whether the return value of this method include the password in the URL, if it is set. Defaults to False. Returns: str: The authority (network location and user information) portion of the URL. �includeSecretsz$got unexpected keyword arguments: %rr7 �[�]Nrg �@) r? r� �keysr� r� r� r� r� r� r� r� �indexrW )r" � with_password�kwr� Zhostport� authorityr� r r r r� � s" z URL.authorityc C s\ t || j�stS dD ] }t| |�t||�kr dS q| j|jksT| jtkrX|jtkrXdS dS )N)r� r� r� r� r� r� r� FT)r� r$ �NotImplemented�getattrr� � _ROOT_PATHS)r" �other�attrr r r �__eq__� s �z URL.__eq__c C s t || j�stS | �|� S r �r� r$ r� r �r" r r r r �__ne__� s z URL.__ne__c C s0 t | j| j| j| j| j| j| j| j| j | j f �S r � �hashr$ r� r� r� r� r� r� r� rk r� r! r r r �__hash__� s �z URL.__hash__c C s t | jo | j�S )ao Whether or not the URL is "absolute". Absolute URLs are complete enough to resolve to a network resource without being relative to a base URI. >>> URL.from_text(u'http://wikipedia.org/').absolute True >>> URL.from_text(u'?a=b&c=d').absolute False Absolute URLs must have both a scheme and a host set. )r� r� r� r! r r r �absolute s z URL.absolutec C sd | j t|| j�t|| j�t|| j�t|| j�t|| j�t|| j�t|| j�t|| j �t| | j �d� S )ar :class:`URL` objects are immutable, which means that attributes are designed to be set only once, at construction. Instead of modifying an existing URL, one simply creates a copy with the desired changes. If any of the following arguments is omitted, it defaults to the value on the current URL. Args: scheme (unicode): The text name of the scheme. host (unicode): The host portion of the network location port (int): The port part of the network location. path (tuple): A tuple of strings representing the slash-separated parts of the path. query (tuple): The query parameters, as a tuple of key-value pairs. query (tuple): The query parameters, as a dictionary or as an iterable of key-value pairs. fragment (unicode): The fragment part of the URL. rooted (bool): Whether or not the path begins with a slash. userinfo (unicode): The username or colon-separated username:password pair. uses_netloc (bool): Indicates whether two slashes appear between the scheme and the host (``http://eg.com`` vs ``mailto:e@g.com``) Returns: URL: a copy of the current :class:`URL`, with new values for parameters passed. � r� r� r� r� r� r� rk r� r� ) r$ r� r� r� r� r� r� r� rk r� r� ) r" r� r� r� r� r� r� rk r� r� r r r rK s " �z URL.replacec C s� t �td|��}z |�� }W n tk r< td| ��Y nX |d pHd}t�|�}z |�� }W n$ tk r� td||f ��Y nX |d r�td|d |f ��|d p�d}|d p�|d }|d } | d k �rz t| �} W n2 tk �r | s�td | ��td| ��Y nX |d �p d} |d �p*d} t |d �} |d �rp|d � d�} | d �sj| � d� d}nd}n d} t |�}|d �r�dd� |d � d�D �}nd}| | || || | ||| � S ) aM Whereas the :class:`URL` constructor is useful for constructing URLs from parts, :meth:`~URL.from_text` supports parsing whole URLs from their string form:: >>> URL.from_text(u'http://example.com') URL.from_text(u'http://example.com') >>> URL.from_text(u'?a=b&x=y') URL.from_text(u'?a=b&x=y') As you can see above, it's also used as the :func:`repr` of :class:`URL` objects. The natural counterpart to :func:`~URL.to_text()`. This method only accepts *text*, so be sure to decode those bytestrings. Args: text (unicode): A valid URL string. Returns: URL: The structured object version of the parsed string. .. note:: Somewhat unexpectedly, URLs are a far more permissive format than most would assume. Many strings which don't look like URLs are still valid URLs. As a result, this method only raises :class:`URLParseError` on invalid port and IPv6 values in the host portion of the URL. rY zcould not parse url: %rr� r z invalid authority %r in url: %rZbad_hostzinvalid host %r in url: %rr� Z ipv6_hostZ plain_hostr� Nzport must not be empty: %rz!expected integer for port, not %rr� r� Z _netloc_sepr� rh r TFr r� c s s* | ]"}d |kr|� d d�n|dfV qdS )r8 rg N)r� )r2 Zqer r r r� � s �z URL.from_text.<locals>.<genexpr>�&) �_URL_REr� r� � groupdictr� r� � _AUTHORITY_REr1 r� r� r� r? )�clsrY ZumZgsZau_textZau_mZau_gsr� r� r� r� r� r� r� rk r� r r r � from_text@ s` � � � �z URL.from_textTc s� i }|r| j �� |d< |r(| j�� |d< �fdd�� |rd| jr\� fdd�t| j�D �|d< nd|d< |r�� fd d�| jD �|d < |r�� | j�|d < |r�d �� fd d�| j� d d�D ��|d< | j f |�S )aM Return a new URL object with several standard normalizations applied: * Decode unreserved characters (`RFC 3986 2.3`_) * Uppercase remaining percent-encoded octets (`RFC 3986 2.1`_) * Convert scheme and host casing to lowercase (`RFC 3986 3.2.2`_) * Resolve any "." and ".." references in the path (`RFC 3986 6.2.2.3`_) * Ensure an ending slash on URLs with an empty path (`RFC 3986 6.2.3`_) * Encode any stray percent signs (`%`) in percent-encoded fields (path, query, fragment, userinfo) (`RFC 3986 2.4`_) All are applied by default, but normalizations can be disabled per-part by passing `False` for that part's corresponding name. Args: scheme (bool): Convert the scheme to lowercase host (bool): Convert the host to lowercase path (bool): Normalize the path (see above for details) query (bool): Normalize the query string fragment (bool): Normalize the fragment userinfo (bool): Normalize the userinfo percents (bool): Encode isolated percent signs for any percent-encoded fields which are being normalized (defaults to True). >>> url = URL.from_text(u'Http://example.COM/a/../b/./c%2f?%61%') >>> print(url.normalize().to_text()) http://example.com/b/c%2F?a%25 .. _RFC 3986 3.2.2: https://tools.ietf.org/html/rfc3986#section-3.2.2 .. _RFC 3986 2.3: https://tools.ietf.org/html/rfc3986#section-2.3 .. _RFC 3986 2.1: https://tools.ietf.org/html/rfc3986#section-2.1 .. _RFC 3986 6.2.2.3: https://tools.ietf.org/html/rfc3986#section-6.2.2.3 .. _RFC 3986 6.2.3: https://tools.ietf.org/html/rfc3986#section-6.2.3 .. _RFC 3986 2.4: https://tools.ietf.org/html/rfc3986#section-2.4 r� r� c s t | d� d�S )NT)r� r� )r� )�target)�percentsr r � _dec_unres� s �z!URL.normalize.<locals>._dec_unresc s g | ] }� |��qS r r �r2 �p�r r r r5 � s z!URL.normalize.<locals>.<listcomp>r� rO c s( g | ] \}}� |�|r � |�n|f�qS r r rM r r r r5 � s �r� r� r7 c s g | ] }� |��qS r r r r r r r5 � s �rg r� ) r� r> r� r� r� r� r� rW r� r� rK ) r" r� r� r� r� r� r� r r� r )r r r r � s* ( � � z URL.normalizec G sZ |s| S dd� |D �}t |ddd�}| jd| jrB| jd dkrBdnd� | }| j|d�S ) a� Make a new :class:`URL` where the given path segments are a child of this URL, preserving other parts of the URL, including the query string and fragment. For example:: >>> url = URL.from_text(u'http://localhost/a/b?x=y') >>> child_url = url.child(u"c", u"d") >>> child_url.to_text() u'http://localhost/a/b/c/d?x=y' Args: segments (unicode): Additional parts to be joined and added to the path, like :func:`os.path.join`. Special characters in segments will be percent encoded. Returns: URL: A copy of the current URL with the extra path segments. c S s g | ]}t d |��qS )r� r� �r2 �sr r r r5 � s z URL.child.<locals>.<listcomp>F)rn rZ Nr� r �r� )ro r� rK )r" �segments�new_segs�new_pathr r r �child� s ��z URL.childc C s. t d|� | jdd� t|�f }| j|d�S )ar Make a new :class:`URL` with a single path segment that is a sibling of this URL path. Args: segment (unicode): A single path segment. Returns: URL: A copy of the current URL with the last path segment replaced by *segment*. Special characters such as ``/?#`` will be percent encoded. r� Nr� r )r� r� r^ rK )r" r� r r r r �sibling� s z URL.siblingc C s� |r4t |t�r|}ntd|� t�|�}|jr8|S n| }|j}|jrZ|jsZtd|f ��n:|jrh|j }n,|j r�| j dd� |j }n| j }|s�| j}| j |jp�| j|j p�| j |j p�| j t |�||jd�S )a9 Resolve the given URL relative to this URL. The resulting URI should match what a web browser would generate if you visited the current URL and clicked on *href*. >>> url = URL.from_text(u'http://blog.hatnote.com/') >>> url.click(u'/post/155074058790').to_text() u'http://blog.hatnote.com/post/155074058790' >>> url = URL.from_text(u'http://localhost/a/b/c/') >>> url.click(u'../d/./e').to_text() u'http://localhost/a/b/d/e' Args: href (unicode): A string representing a clicked URL. Return: URL: A copy of the current URL with navigation logic applied. For more information, see `RFC 3986 section 5`_. .. _RFC 3986 section 5: https://tools.ietf.org/html/rfc3986#section-5 z relative URLz#absolute URI with rootless path: %rNr� )r� r� r� r� r� r� )r� r� r� r r r� r� rk �NotImplementedErrorr� rK r� r� r� r� )r" �hrefZclickedr� r� r r r �click s6 � �z URL.clickc C s� d� dd� | j�dd�D ��}t| jt| j�dddd�}| jsD| jnt| jdd�� d �}| j |||t d d� | j D ��t | jdd �d �S ) u< Make a new :class:`URL` instance with all non-ASCII characters appropriately percent-encoded. This is useful to do in preparation for sending a :class:`URL` over a network protocol. For example:: >>> URL.from_text(u'https://ايران.com/foo⇧bar/').to_uri() URL.from_text(u'https://xn--mgba3a4fra.com/foo%E2%87%A7bar/') Returns: URL: A new instance with its path segments, query parameters, and hostname encoded, so that they are all in the standard US-ASCII range. r7 c S s g | ] }t |��qS r )r| r r r r r5 L s z URL.to_uri.<locals>.<listcomp>rg FT)rl rk rn rZ r� r c S s4 g | ],\}}t |d d�|dk r*t|d d�ndf�qS )Trc N)rs rv rM r r r r5 U s � ��rc �r� r� r� r� r� )rW r� r� ro r� r� r� r� � idna_encoder rK rj r� ry r� )r" � new_userinfor Znew_hostr r r �to_uri= s$ � � � �z URL.to_uric C sZ d� dd� | j�dd�D ��}t| j�}| j||dd� | jD �dd� | jD �t| j �d�S )u� Make a new :class:`URL` instance with all but a few reserved characters decoded into human-readable format. Percent-encoded Unicode and IDNA-encoded hostnames are decoded, like so:: >>> url = URL.from_text(u'https://xn--mgba3a4fra.example.com/foo%E2%87%A7bar/') >>> print(url.to_iri().to_text()) https://ايران.example.com/foo⇧bar/ .. note:: As a general Python issue, "narrow" (UCS-2) builds of Python may not be able to fully decode certain URLs, and the in those cases, this method will return a best-effort, partially-decoded, URL which is still valid. This issue does not affect any Python builds 3.4+. Returns: URL: A new instance with its path segments, query parameters, and hostname decoded for display purposes. r7 c S s g | ] }t |��qS r )r� r r r r r5 s s z URL.to_iri.<locals>.<listcomp>rg c S s g | ] }t |��qS r )r� r� r r r r5 y s �c S s, g | ]$\}}t |�|d k r"t|�nd f�qS r )r� r� rM r r r r5 { s �� �r$ ) rW r� r� r� r� rK r� r� r� r� )r" r& r� r r r �to_iri\ s � ���z URL.to_iric C sR | j }| �|�}t| j| jt|�t|�dd�}g }| jD ]H\}}|dkr\|�t|dd�� q8|�d� t|dd�t |dd�f�� q8d� |�}| j } g } | j} |r�| |� | d� |r�| d� | |� n"|r�|dd � dkr�| j r�| d� |�r |�r|�r|dd � d k�r| d � | |� |�r2| d � | |� | �rH| d � | | � d� | �S )a� Render this URL to its textual representation. By default, the URL text will *not* include a password, if one is set. RFC 3986 considers using URLs to represent such sensitive information as deprecated. Quoting from RFC 3986, `section 3.2.1`: "Applications should not render as clear text any data after the first colon (":") character found within a userinfo subcomponent unless the data after the colon is the empty string (indicating no password)." Args: with_password (bool): Whether or not to include the password in the URL text. Defaults to False. Returns: str: The serialized textual representation of this URL, such as ``u"http://example.com/some/path?some=query"``. The natural counterpart to :class:`URL.from_text()`. .. _section 3.2.1: https://tools.ietf.org/html/rfc3986#section-3.2.1 F)rk rl rm rZ Nrc r8 r r7 z//r rg rh �?�#r ) r� r� ro r� rk r� r� r� rs rW rv r� r� ) r" r� r� r� r� Z query_partsrN rH Z query_stringr� �partsZ_addr r r �to_text� sL � � z URL.to_textc C s d| j j| �� f S )z�Convert this URL to an representation that shows all of its constituent parts, as well as being a valid argument to :func:`eval`. z%s.from_text(%r))r$ r r, r! r r r r% � s z URL.__repr__c C s | � � �� �d�S )z� Allows for direct usage of URL objects with libraries like requests, which automatically stringify URL parameters. See issue #49. r )r' r, r r! r r r � _to_bytes� s z URL._to_bytesc C s | � |�S r �r )r r r r r �fromText� s z URL.fromTextc C s | j |d�S �N)r� �r, �r" r� r r r �asText� s z URL.asTextc C s\ zt �| �}W n, tk r: t| j�t| j�� � }Y nX tt |�t ddddg� �}|S �Nr/ �asURI�asIRIr3 � r* �__dir__r� �dirr$ r� �__dict__r� �sortedr; �r" rA r r r r8 � s z URL.__dir__c C s | j | j||ff d�S )a Make a new :class:`URL` instance with a given query argument, *name*, added to it with the value *value*, like so:: >>> URL.from_text(u'https://example.com/?x=y').add(u'x') URL.from_text(u'https://example.com/?x=y&x') >>> URL.from_text(u'https://example.com/?x=y').add(u'x', u'z') URL.from_text(u'https://example.com/?x=y&x=z') Args: name (unicode): The name of the query parameter to add. The part before the ``=``. value (unicode): The value of the query parameter to add. The part after the ``=``. Defaults to ``None``, meaning no value. Returns: URL: A new :class:`URL` instance with the parameter added. �r� �rK r� �r" r r� r r r r� � s zURL.addc sP � fdd�| j D �}t� fdd�t| j �D �d�}� |fg|||�< | j|d�S )a/ Make a new :class:`URL` instance with the query parameter *name* set to *value*. All existing occurences, if any are replaced by the single name-value pair. >>> URL.from_text(u'https://example.com/?x=y').set(u'x') URL.from_text(u'https://example.com/?x') >>> URL.from_text(u'https://example.com/?x=y').set(u'x', u'z') URL.from_text(u'https://example.com/?x=z') Args: name (unicode): The name of the query parameter to set. The part before the ``=``. value (unicode): The value of the query parameter to set. The part after the ``=``. Defaults to ``None``, meaning no value. Returns: URL: A new :class:`URL` instance with the parameter set. c s g | ]\}}|� kr||f�qS r r rM �r r r r5 s zURL.set.<locals>.<listcomp>c 3 s" | ]\}\}}|� kr|V qd S r r �r2 rG rN rH r@ r r r� s �zURL.set.<locals>.<genexpr>r� r= �r� �next� enumeraterK )r" r r� �q�idxr r@ r r; s �zURL.setc s � fdd�| j D �S )a0 Get a list of values for the given query parameter, *name*:: >>> url = URL.from_text(u'?x=1&x=2') >>> url.get('x') [u'1', u'2'] >>> url.get('y') [] If the given *name* is not set, an empty list is returned. A list is always returned, and this method raises no exceptions. Args: name (unicode): The name of the query parameter to get. Returns: list: A list of all the values associated with the key, in string form. c s g | ]\}}� |kr|�qS r r )r2 �keyr� r@ r r r5 2 s zURL.get.<locals>.<listcomp>r= �r" r r r@ r r� s zURL.getc s� |dkr>�t kr&� fdd�| jD �}q�� �fdd�| jD �}nRg d }}| jD ]@\}}|� kr��t ksn|�kr�||k r�|d7 }qN|�||f� qN| j|d�S )a� Make a new :class:`URL` instance with occurrences of the query parameter *name* removed, or, if *value* is set, parameters matching *name* and *value*. No exception is raised if the parameter is not already set. Args: name (unicode): The name of the query parameter to remove. value (unicode): Optional value to additionally filter on. Setting this removes query parameters which match both name and value. limit (int): Optional maximum number of parameters to remove. Returns: URL: A new :class:`URL` instance with the parameter removed. Nc s g | ]\}}|� kr||f�qS r r rM r@ r r r5 F s z URL.remove.<locals>.<listcomp>c s( g | ] \}}|� kr |�ks||f�qS r r rM �r r� r r r5 H s r rg r= �r, r� r� rK �r" r r� �limitZnqZ removed_countrN rH r rI r �remove4 s z URL.remove) NNr r r NNr N)F)F)TTTTTTT)r )F)F)N)N)0r r r r� r# r� �propertyr� r� r� r� r� r� rk r� r� r� r� r r r r r, rK � classmethodr r r r r# r' r( r, r% r- r� �__str__Z __unicode__� __bytes__r5 r6 r/ r3 r8 r� r; r� rM r r r r r� � s� 6 � 3 & � . Q � @ < % A r� c @ s� e Zd ZdZdIdd�ZedJdd��Zedd� �Zd d � Z d d � Z d d� Z dKdd�Z dd� Z dd� Zdd� Zedd� �Zedd� �Zed d � �Zed d � �Zed d!� �Zed"d#� �Zed$d%� �Zed&d'� �Zed(d)� �Zed*d+� �Zed,d-� �Zeeeeeeeeef d.d/�Z d0d1� Z dLd3d4�Z dMd5d6�Z ed2fd7d8�Z d9d:� Z!d;d<� Z"d=d>� Z#d?d@� Z$dAdB� Z%e Z&e Z'edNdCdD��Z(dOdEdF�Z)dGdH� Z*d2S )Pr� ap DecodedURL is a type meant to act as a higher-level interface to the URL. It is the `unicode` to URL's `bytes`. `DecodedURL` has almost exactly the same API as `URL`, but everything going in and out is in its maximally decoded state. All percent decoding is handled automatically. Where applicable, a UTF-8 encoding is presumed. Be advised that some interactions can raise :exc:`UnicodeEncodeErrors` and :exc:`UnicodeDecodeErrors`, just like when working with bytestrings. Examples of such interactions include handling query strings encoding binary data, and paths containing segments with special characters encoded with codecs other than UTF-8. Args: url (URL): A :class:`URL` object to wrap. lazy (bool): Set to True to avoid pre-decode all parts of the URL to check for validity. Defaults to False. Fc C s& || _ |s"| j| j| j| j| jf d S r )�_urlr� r� r� r� r� )r" �urlr� r r r r# l s zDecodedURL.__init__c C s t �|�}| ||d�S )a Make a `DecodedURL` instance from any text string containing a URL. Args: text (unicode): Text containing the URL lazy (bool): Whether to pre-decode all parts of the URL to check for validity. Defaults to True. r� )r� r )r rY r� rR r r r r t s zDecodedURL.from_textc C s | j S )zeAccess the underlying :class:`URL` object, which has any special characters encoded. )rR r! r r r � encoded_url� s zDecodedURL.encoded_urlc O s | j j||�S )z/Passthrough to :meth:`~hyperlink.URL.to_text()`)rR r, �r" r3 r� r r r r, � s zDecodedURL.to_textc O s | j j||�S )z.Passthrough to :meth:`~hyperlink.URL.to_uri()`)rR r' rU r r r r' � s zDecodedURL.to_uric O s | j j||�S )z.Passthrough to :meth:`~hyperlink.URL.to_iri()`)rR r( rU r r r r( � s zDecodedURL.to_irir c C s$ t |t�r|j}| �| jj|d��S )zMReturn a new DecodedURL wrapping the result of :meth:`~hyperlink.URL.click()`)r" )r� r� rR r$ r# )r" r" r r r r# � s zDecodedURL.clickc C s | � | j�t|���S )z�Automatically encode any reserved characters in *segment* and return a new `DecodedURL` wrapping the result of :meth:`~hyperlink.URL.sibling()` )r$ rR r r[ )r" r� r r r r � s zDecodedURL.siblingc G s( |s| S dd� |D �}| � | jj|� �S )z�Automatically encode any reserved characters in *segments* and return a new `DecodedURL` wrapping the result of :meth:`~hyperlink.URL.child()`. c S s g | ] }t |��qS r �r[ r r r r r5 � s z$DecodedURL.child.<locals>.<listcomp>)r$ rR r )r" r r r r r r � s zDecodedURL.childc O s | � | jj||��S )zSReturn a new `DecodedURL` wrapping the result of :meth:`~hyperlink.URL.normalize()`)r$ rR r rU r r r r � s zDecodedURL.normalizec C s | j jS r )rR r r! r r r r � s zDecodedURL.absolutec C s | j jS r )rR r� r! r r r r� � s zDecodedURL.schemec C s t | jj�S r )r� rR r� r! r r r r� � s zDecodedURL.hostc C s | j jS r )rR r� r! r r r r� � s zDecodedURL.portc C s | j jS r )rR rk r! r r r rk � s zDecodedURL.rootedc C s< z| j W S tk r Y nX tdd� | jjD ��| _ | j S )Nc S s g | ]}t |d d��qS �T�r� �r� r r r r r5 � s �z#DecodedURL.path.<locals>.<listcomp>)r� r� rj rR r� r! r r r r� � s � zDecodedURL.pathc C s@ z| j W S tk r Y nX dd� | jjD �}t|�| _ | j S )Nc S s& g | ] \}}t d d� ||fD ���qS )c s s& | ] }|d k rt |dd�nd V qd S �NTrX rY �r2 �xr r r r� � s ��z.DecodedURL.query.<locals>.<listcomp>.<genexpr>)rj rM r r r r5 � s ��z$DecodedURL.query.<locals>.<listcomp>)r� r� rR r� rj )r" Z_qr r r r� � s � zDecodedURL.queryc C s: z| j W S tk r Y nX | jj}t|dd�| _ | j S rZ )r� r� rR r� r� )r" Zfragr r r r� � s zDecodedURL.fragmentc C sD z| j W S tk r Y nX tdd� | jj�dd�D ��| _ | j S )Nc S s g | ]}t |d d��qS rW rY r r r r r5 � s �z'DecodedURL.userinfo.<locals>.<listcomp>r7 rg )r� r� rj rR r� r� r! r r r r� � s � zDecodedURL.userinfoc C s | j d S )Nr )r� r! r r r r� � s zDecodedURL.userc C s | j jS r )rR r� r! r r r r� � s zDecodedURL.uses_netlocc C s� |t k rdd� |D �}|t k r0dd� t|�D �}|t k rdt|�dkrPtd| ��d�dd� |D ��}| jj||||||||| d� } | j| d �S ) a� While the signature is the same, this `replace()` differs a little from URL.replace. For instance, it accepts userinfo as a tuple, not as a string, handling the case of having a username containing a `:`. As with the rest of the methods on DecodedURL, if you pass a reserved character, it will be automatically encoded instead of an error being raised. c S s g | ] }t |��qS r rV r r r r r5 s z&DecodedURL.replace.<locals>.<listcomp>c S s" g | ]\}}d d� ||fD ��qS )c S s g | ]}|d k rt |�nd �qS r rV r[ r r r r5 s �� z1DecodedURL.replace.<locals>.<listcomp>.<listcomp>r rM r r r r5 s ��r zFuserinfo expected sequence of ["user"] or ["user", "password"], got %rr7 c S s g | ] }t |��qS r rV r r r r r5 s r )rS )r, r� r� r� rW rR rK r$ ) r" r� r� r� r� r� r� rk r� r� Znew_urlr r r rK � s. � �� zDecodedURL.replacec s � fdd�| j D �S )z?Get the value of all query parameters whose name matches *name*c s g | ]\}}� |kr|�qS r r rM r@ r r r5 s z"DecodedURL.get.<locals>.<listcomp>r= rH r r@ r r� s zDecodedURL.getNc C s | j | j||ff d�S )zJReturn a new DecodedURL with the query parameter *name* and *value* added.r= r> r? r r r r� s zDecodedURL.addc sR | j }� fdd�|D �}t� fdd�t|�D �d�}� |fg|||�< | j|d�S )zBReturn a new DecodedURL with query parameter *name* set to *value*c s g | ]\}}|� kr||f�qS r r rM r@ r r r5 # s z"DecodedURL.set.<locals>.<listcomp>c 3 s" | ]\}\}}|� kr|V qd S r r rA r@ r r r� $ s z!DecodedURL.set.<locals>.<genexpr>r� r= rB )r" r r� r� rE rF r r@ r r; s zDecodedURL.setc s� |dkr>�t kr&� fdd�| jD �}q�� �fdd�| jD �}nRg d }}| jD ]@\}}|� kr��t ksn|�kr�||k r�|d7 }qN|�||f� qN| j|d�S )z�Return a new DecodedURL with query parameter *name* removed. Optionally also filter for *value*, as well as cap the number of parameters removed with *limit*. Nc s g | ]\}}|� kr||f�qS r r rM r@ r r r5 0 s z%DecodedURL.remove.<locals>.<listcomp>c s( g | ] \}}|� kr |�ks||f�qS r r rM rI r r r5 2 s r rg r= rJ rK r rI r rM ( s zDecodedURL.removec C s | j j}d|| jf S )Nz %s(url=%r))r$ r rR )r" Zcnr r r r% = s zDecodedURL.__repr__c C s t | j�S r )r� rR r! r r r rP A s zDecodedURL.__str__c C s( t || j�stS | �� �� |�� �� kS r )r� r$ r� r r' r r r r r F s zDecodedURL.__eq__c C s t || j�stS | �|� S r r r r r r r K s zDecodedURL.__ne__c C s0 t | j| j| j| j| j| j| j| j| j | j f �S r r r! r r r r P s �zDecodedURL.__hash__c C s | j ||d�S r� r. )r r r� r r r r/ Y s zDecodedURL.fromTextc C s | j |d�S r0 r1 r2 r r r r3 ] s zDecodedURL.asTextc C s\ zt �| �}W n, tk r: t| j�t| j�� � }Y nX tt |�t ddddg� �}|S r4 r7 r< r r r r8 ` s zDecodedURL.__dir__)F)F)r )N)N)F)F)+r r r r� r# rO r rN rT r, r' r( r# r r r r r� r� r� rk r� r� r� r� r� r� r, rK r� r� r; rM r% rP r r r r5 r6 r/ r3 r8 r r r r r� X sr � " r� c C s" t �| �}|s|S t||d�}|S )a� Automatically turn text into a structured URL object. Args: decoded (bool): Whether or not to return a :class:`DecodedURL`, which automatically handles all encoding/decoding/quoting/unquoting for all the various accessors of parts of the URL, or an :class:`EncodedURL`, which has the same API, but requires handling of special characters for different parts of the URL. lazy (bool): In the case of `decoded=True`, this controls whether the URL is decoded immediately or as accessed. The default, `lazy=False`, checks all encoded parts of the URL for decodability. r� )� EncodedURLr r� )rS Zdecodedr� Zenc_urlZdec_urlr r r �parsel s r^ )r N)F)T)T)T)FTTTT)T)T)T)T)TN)N)FF)FF)FF)FF)FF)FF)TF)pr� �re�sysr. r � unicodedatar r � ImportErrorZcollections.abcr � collectionsZidnar r% r r� r r Z Structurer ZwindllZws2_32r ZWSAAddressToStringA� version_infor� �typer� r0 � NameErrorrF r� r+ Z _unspecifiedr, � frozensetrL �compiler r� r r9 r/ r: Z _ASCII_REZ _GEN_DELIMSZ _SUB_DELIMSZ _ALL_DELIMSr; Z_USERINFO_SAFEr{ Z _PATH_SAFEr] Z_SCHEMELESS_PATH_SAFEr` Z_FRAGMENT_SAFErx Z_QUERY_VALUE_SAFEru Z_QUERY_KEY_SAFErr rB rJ rz r� r\ r_ r� rq r� rt r� rw r� rR r� r� r r[ r^ ra ro rs rv ry r| r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r* r� r] r� r^ r r r r �<module> sH 3 � � ) � � ) � O? & s
Save File
Cancel