File: //usr/local/lib/python3.10/dist-packages/httpx/__pycache__/_urlparse.cpython-310.pyc
o
���grH �
@ s� d Z ddlmZ ddlZddlZddlZddlZddlmZ dZ dZ
dZ e� d �Z
d
�d d � ed
d�D ��Zd
�dd � ed
d�D ��Zd
�dd � ed
d�D ��Zd
�dd � ed
d�D ��Zd
�dd � ed
d�D ��Zd
�dd � ed
d�D ��Ze� djdddddd��Ze� djdd dd ��Ze� d�e� d�e� d�e� d�e� d�e� d �e� d �e� d�d �Ze� d!�Ze� d"�ZG d#d$� d$ej �Z dFdGd*d+�Z dHd-d.�Z dId3d4�Z dJd:d;�Z!dKd<d=�Z"dLd?d@�Z#dMdBdC�Z$dMdDdE�Z%dS )Na�
An implementation of `urlparse` that provides URL validation and normalization
as described by RFC3986.
We rely on this implementation rather than the one in Python's stdlib, because:
* It provides more complete URL validation.
* It properly differentiates between an empty querystring and an absent querystring,
to distinguish URLs with a trailing '?'.
* It handles scheme, hostname, port, and path normalization.
* It supports IDNA hostnames, normalizing them to their encoded form.
* The API supports passing individual components, as well as the complete URL string.
Previously we relied on the excellent `rfc3986` package to handle URL parsing and
validation, but this module provides a simpler alternative, with less indirection
required.
� )� annotationsN� )�
InvalidURLi zBABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~z !$&'()*+,;=z%[A-Fa-f0-9]{2}� c C � g | ]
}|d vrt |��qS ))� �" �< �> �` ��chr��.0�i� r �:/usr/local/lib/python3.10/dist-packages/httpx/_urlparse.py�
<listcomp>, � r r � c C r ))r r �# r r
r r r r r r 2 r c C r )) r r r r r
�? r �{ �} r r r r r r 8 s
�c C r �)r r r r r
r r r r �/ �: �; �= �@ �[ �\ �] �^ �| r r r r r r C � ��c C r r r r r r r r M r% c C 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 Z r% z�(?:(?P<scheme>{scheme}):)?(?://(?P<authority>{authority}))?(?P<path>{path})(?:\?(?P<query>{query}))?(?:#(?P<fragment>{fragment}))?z([a-zA-Z][a-zA-Z0-9+.-]*)?z[^/?#]*z[^?#]*z[^#]*z.*��scheme� authority�path�query�fragmentzA(?:(?P<userinfo>{userinfo})@)?(?P<host>{host}):?(?P<port>{port})?z(\[.*\]|[^:@]*))�userinfo�host�portz[^@]*z(\[.*\]|[^:]*))r' r( r) r* r+ r, r- r. z ^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$z^\[.*\]$c @ sv e Zd ZU ded< ded< ded< ded< ded< ded < ded
< edd d
��Zeddd��Zddd�Zddd�ZdS )� ParseResult�strr' r, r- �
int | Noner. r) �
str | Noner* r+ �returnc C sV d� | jr | j� d�ndd| jv rd| j� d�n| j| jd ur'd| j� �g�S dg�S )Nr �@�:�[�])�joinr, r- r. ��selfr r r r( � s ����zParseResult.authorityc C sB d� d| jv rd| j� d�n| j| jd ur d| j� �g�S dg�S )Nr r5 r6 r7 )r8 r- r. r9 r r r �netloc� s ����zParseResult.netloc�kwargsc K s: |s| S | j | j| j| j| jd�}|�|� tdi |��S )Nr& r �r )r' r( r) r* r+ �update�urlparse)r: r< �defaultsr r r � copy_with� s �
zParseResult.copy_withc C sl | j }d�| jr| j� d�nd|rd|� �nd| j| jd ur$d| j� �nd| jd ur2d| j� �g�S dg�S )Nr r5 �//�?�#)r( r8 r' r) r* r+ )r: r( r r r �__str__� s ����zParseResult.__str__N)r3 r0 )r< r2 r3 r/ ) �__name__�
__module__� __qualname__�__annotations__�propertyr( r; rA rE r r r r r/ � s
r/ �urlr0 r< r2 r3 c " K s� t | �tkr
td��tdd� | D ��r.tdd� | D ��}| �|�}d|�d|� d�}t|��d|v rC|d }t|t�r?t|�n||d< d |v rZ|� d �pMd
}|�
d �\|d < }|d< d
|v sbd|v r�t |� d
d
�pjd
t d�}t |� dd
�pvd
t
d�} | r�|� d | � �n||d< d|v r�|� d�p�d
}
|
�
d�\|d< } |d< | s�d |d< d |v r�|�d �p�d
} d | v r�| �d�r�| �d�s�d| � d�|d < |�� D ]O\}
}|d u�rt |�tkr�td|
� d���tdd� |D ���rtdd� |D ��}|�|�}d|
� d |�d|� d�}t|��t|
�|��std |
� d ���q�t�| �}|d u�s%J �|�� }|�d |d ��p3d
}|�d |d ��p>d
}|�d|d ��pId
}|�d|d �}|�d!|d! �}t�|�}|d u�sfJ �|�� }|�d|d ��ptd
}|�d |d ��pd
} |�d|d �}|�� }t |td�}t| �}t||�} |d
k} |d
k�p�|d
k�p�| d u} t || | d"� | �s�| �r�t |�}t |t d�} |d u �r�d nt |t d�} |d u �r�d nt |t d�}!t!|||| | | |!�S )#Nz URL too longc s �" � | ] }|� � o |�� V qd S �N��isascii� isprintable�r �charr r r � <genexpr>� � � zurlparse.<locals>.<genexpr>c s �$ � | ]
}|� � r|�� s|V qd S rM rN rQ r r r rS � s �" z.Invalid non-printable ASCII character in URL, z
at position �.r. r; r r5 r- �username�password��safer, �raw_pathrC r) r* r6 r7 zURL component 'z
' too longc s rL rM rN rQ r r r rS rT c s rU rM rN rQ r r r rS s � ��
�z-Invalid non-printable ASCII character in URL z component, zInvalid URL component '�'r' r( r+ )�
has_scheme�
has_authority)"�len�MAX_URL_LENGTHr �any�next�find�
isinstance�intr0 �pop� partition�quote�
USERNAME_SAFE�
PASSWORD_SAFE�get�
startswith�endswith�items�COMPONENT_REGEX� fullmatch� URL_REGEX�match� groupdict�AUTHORITY_REGEX�lower�
USERINFO_SAFE� encode_host�normalize_port�
validate_path�normalize_path� PATH_SAFE�
QUERY_SAFE� FRAG_SAFEr/ )"rK r< rR �idx�errorr. r; �_rW rX r[ � seperatorr- �key�value� url_match�url_dictr' r( r) r* �frag�authority_match�authority_dictr, �
parsed_scheme�parsed_userinfo� parsed_host� parsed_portr] r^ � parsed_path� parsed_query� parsed_fragr r r r? � s�
�
�
����
� �r? r- c C s� | sdS t �| �r!zt�| � W | S tjy td| ����w t�| �rGz t�| dd� � W n tjy@ td| ����w | dd� S | �� rWd}t | �
� t | d�S z t �
| �
� ��d�W S t jyq td | ����w )
Nr zInvalid IPv4 address: r ���zInvalid IPv6 address: z"`{}%|\rY �asciizInvalid IDNA hostname: )�IPv4_STYLE_HOSTNAMErr � ipaddress� IPv4Address�AddressValueErrorr �IPv6_STYLE_HOSTNAME� IPv6AddressrO rh ru �
SUB_DELIMS�idna�encode�decode� IDNAError)r- � WHATWG_SAFEr r r rw \ s0
��
� �rw r. �str | int | Noner' r1 c C sd | d u s| dkr
d S zt | �}W n ty td| ����w dddddd��|�}||kr0d S |S )Nr zInvalid port: � �P i� )�ftp�http�https�ws�wss)re �
ValueErrorr rk )r. r' � port_as_int� default_portr r r rx � s
��rx r) r] �boolr^ �Nonec C sR |r
| r
| � d�s
td��|s#|s%| � d�rtd��| � d�r'td��dS dS dS )z�
Path validation rules that depend on if the URL contains
a scheme or authority component.
See https://datatracker.ietf.org/doc/html/rfc3986.html#section-3.3
�/z7For absolute URLs, path must be empty or begin with '/'rB z3Relative URLs cannot have a path starting with '//'r5 z2Relative URLs cannot have a path starting with ':'N)rl r )r) r] r^ r r r ry � s
�ry c C sv d| vr| S | � d�}d|vrd|vr| S g }|D ] }|dkr q|dkr0|r/|dgkr/|�� q|�|� qd�|�S )z�
Drop "." and ".." segments from a URL path.
For example:
normalize_path("/path/./to/somewhere/..") == "/path/to"
rV r� z..r )�splitrf �appendr8 )r) �
components�output� componentr r r rz � s
�
rz �stringc C s d� dd� | �d�D ��S )Nr c S s g | ]}d |d���qS )�%�02Xr )r �byter r r r � s zPERCENT.<locals>.<listcomp>zutf-8)r8 r� )r� r r r �PERCENT� s r� rZ c s. t | � | �� �s | S d�� fdd�| D ��S )z1
Use percent-encoding to quote a string.
r c s g | ] }|� v r
|nt |��qS r )r� rQ ��NON_ESCAPED_CHARSr r r � s z#percent_encoded.<locals>.<listcomp>)�UNRESERVED_CHARACTERS�rstripr8 )r� rZ r r� r �percent_encoded� s
�r� c
C s� g }d}t �t| �D ]*}|�� |�� }}|�d�}||kr-| ||� }|�t||d�� |�|� |}q
|t| �krJ| |d� } |�t| |d�� d� |�S )a�
Use percent-encoding to quote a string, omitting existing '%xx' escape sequences.
See: https://www.rfc-editor.org/rfc/rfc3986#section-2.1
* `string`: The string to be percent-escaped.
* `safe`: A string containing characters that may be treated as safe, and do not
need to be escaped. Unreserved characters are always treated as safe.
See: https://www.rfc-editor.org/rfc/rfc3986#section-2.3
r rY Nr )
�re�finditer�PERCENT_ENCODED_REGEX�start�end�groupr� r� r_ r8 )
r� rZ �parts�current_positionrr �start_position� end_position� matched_text� leading_text�
trailing_textr r r rh � s
rh r= )rK r0 r< r2 r3 r/ )r- r0 r3 r0 )r. r� r' r0 r3 r1 )r) r0 r] r� r^ r� r3 r� )r) r0 r3 r0 )r� r0 r3 r0 )r� r0 rZ r0 r3 r0 )&�__doc__�
__future__r r� r� �typingr� � _exceptionsr r` r� r� �compiler� r8 �ranger} r| r{ ri rj rv �formatrq rt ro r� r� �
NamedTupler/ r? rw rx ry rz r� r� rh r r r r �<module> s� �
���� ��
��
�������
7
/