| Server IP : 127.0.0.1 / Your IP : 216.73.216.109 Web Server : Apache/2.4.54 (Win64) OpenSSL/1.1.1q PHP/8.1.10 System : Windows NT DESKTOP-E5T4RUN 10.0 build 19045 (Windows 10) AMD64 User : SERVERWEB ( 0) PHP Version : 8.1.10 Disable Function : NONE MySQL : OFF | cURL : ON | WGET : OFF | Perl : OFF | Python : OFF | Sudo : OFF | Pkexec : OFF Directory : C:/cygwin64/lib/python3.7/site-packages/pip/_internal/index/__pycache__/ |
Upload File : |
B
�N�a~D � @ s d Z ddlZddlZddlZddlZddlZddlZddlZddlZ ddl
Z ddl Z ddl
mZ ddlmZmZmZmZmZmZmZmZ ddlmZmZ ddlm Z ddl m Z m Z ddl m!Z! dd l"m#Z# dd
l$m%Z% dd l&m'Z' dd l(m)Z) dd
l*m+Z+ ddl,m-Z-m.Z. ddl/m0Z0 ddl1m2Z2m3Z3m4Z4 e�5e6�Z7e j8j9j:Z;ee<e<f Z=e<ee< d�dd�Z>G dd� de?�Z@e dd�dd�ZAG dd� de?�ZBe<e'dd �d d �ZCe<e'e d �d d �ZDe=ee< d!�d"d#�ZEe;e<e<d$�d%d&�ZFe<e<d'�d(d)�ZGe<e<d'�d*d+�ZHe�Id,ejJ�ZKe<eLe<d-�d.d/�ZMe<e<d�d0d1�ZNe;e<e<ee# d2�d3d4�ZOG d5d6� d6�ZPed7gee# f ed7gee# f d8�d9d:�ZQeQd7ee# d;�d<d=��ZRG d>d7� d7�ZSdNe#ee<e?f eed? dd@�dAdB�ZTdOe eLeSdD�dEdF�ZUdPe#ee' ed7 dG�dHdI�ZVG dJdK� dKe�ZWG dLdM� dM�ZXdS )QzO
The main purpose of this module is to expose LinkCollector.collect_sources().
� N)�Values)�Callable�Iterable�List�MutableMapping�
NamedTuple�Optional�Sequence�Union)�html5lib�requests)�Response)�
RetryError�SSLError)�NetworkConnectionError)�Link)� SearchScope)�
PipSession)�raise_for_status)�is_archive_file)�pairwise�redact_auth_from_url)�vcs� )�CandidatesFromPage�
LinkSource� build_source)�url�returnc C s6 x0t jD ]&}| �� �|�r| t|� dkr|S qW dS )zgLook for VCS schemes in the URL.
Returns the matched VCS scheme, or None if there's no match.
z+:N)r Zschemes�lower�
startswith�len)r �scheme� r# �A/usr/lib/python3.7/site-packages/pip/_internal/index/collector.py�_match_vcs_scheme0 s r% c s& e Zd Zeedd�� fdd� Z� ZS )�_NotHTMLN)� content_type� request_descr c s t � �||� || _|| _d S )N)�super�__init__r' r( )�selfr' r( )� __class__r# r$ r* < s z_NotHTML.__init__)�__name__�
__module__� __qualname__�strr* �
__classcell__r# r# )r, r$ r& ; s r& )�responser c C s. | j �dd�}|�� �d�s*t|| jj��dS )z�Check the Content-Type header to ensure the response contains HTML.
Raises `_NotHTML` if the content type is not text/html.
z Content-Type� z text/htmlN)�headers�getr r r& �request�method)r2 r' r# r# r$ �_ensure_html_headerB s r8 c @ s e Zd ZdS )�_NotHTTPN)r- r. r/ r# r# r# r$ r9 L s r9 )r �sessionr c C sF t j�| �\}}}}}|dkr$t� �|j| dd�}t|� t|� dS )z�Send a HEAD request to the URL, and ensure the response contains HTML.
Raises `_NotHTTP` if the URL is not available for a HEAD request, or
`_NotHTML` if the content type is not text/html.
> �https�httpT)Zallow_redirectsN)�urllib�parseZurlsplitr9 �headr r8 )r r: r" �netloc�pathZqueryZfragment�respr# r# r$ �_ensure_html_responseP s rC c C sR t t| �j�rt| |d� t�dt| �� |j| ddd�d�}t|� t |� |S )a Access an HTML page with GET, and return the response.
This consists of three parts:
1. If the URL looks suspiciously like an archive, send a HEAD first to
check the Content-Type is HTML, to avoid downloading a large file.
Raise `_NotHTTP` if the content type cannot be determined, or
`_NotHTML` if it is not HTML.
2. Actually perform the request. Raise HTTP exceptions on network failures.
3. Check the Content-Type header to make sure we got HTML, and raise
`_NotHTML` otherwise.
)r: zGetting page %sz text/htmlz max-age=0)ZAcceptz
Cache-Control)r4 )
r r �filenamerC �logger�debugr r5 r r8 )r r: rB r# r# r$ �_get_html_response` s
rG )r4 r c C s2 | r.d| kr.t �| d �\}}d|kr.|d S dS )z=Determine if we have any encoding information in our headers.z Content-Type�charsetN)�cgiZ parse_header)r4 r' �paramsr# r# r$ �_get_encoding_from_headers� s
rK )�document�page_urlr c C s. x(| � d�D ]}|�d�}|dk r |S q W |S )a� Determine the HTML document's base URL.
This looks for a ``<base>`` tag in the HTML document. If present, its href
attribute denotes the base URL of anchor tags in the document. If there is
no such tag (or if it does not have a valid href attribute), the HTML
file's URL is used as the base URL.
:param document: An HTML document representation. The current
implementation expects the result of ``html5lib.parse()``.
:param page_url: The URL of the HTML document.
z.//base�hrefN)�findallr5 )rL rM �baserN r# r# r$ �_determine_base_url� s
rQ )�partr c C s t j�t j�| ��S )zP
Clean a "part" of a URL path (i.e. after splitting on "@" characters).
)r= r> ZquoteZunquote)rR r# r# r$ �_clean_url_path_part� s rS c C s t j�t j�| ��S )z�
Clean the first part of a URL path that corresponds to a local
filesystem path (i.e. the first part after splitting on "@" characters).
)r= r6 Z pathname2url� url2pathname)rR r# r# r$ �_clean_file_url_path� s
rU z(@|%2F))rA �
is_local_pathr c C sb |r
t }nt}t�| �}g }x:tt�|dg��D ]$\}}|�||�� |�|�� � q0W d� |�S )z*
Clean the path portion of a URL.
r3 )
rU rS �_reserved_chars_re�splitr � itertools�chain�append�upper�join)rA rV Z
clean_func�partsZ
cleaned_partsZto_cleanZreservedr# r# r$ �_clean_url_path� s
r_ c C s6 t j�| �}|j }t|j|d�}t j�|j|d��S )z�
Make sure a link is fully quoted.
For example, if ' ' occurs in the URL, it will be replaced with "%20",
and without double-quoting other characters.
)rV )rA )r= r> �urlparser@ r_ rA Z
urlunparse�_replace)r �resultrV rA r# r# r$ � _clean_link� s rc )�anchorrM �base_urlr c C sL | � d�}|sdS ttj�||��}| � d�}| � d�}t||||d�}|S )zJ
Convert an anchor element in a simple repository page to a Link.
rN Nzdata-requires-pythonz data-yanked)Z
comes_fromZrequires_python�
yanked_reason)r5 rc r= r> �urljoinr )rd rM re rN r Z pyrequirerf �linkr# r# r$ �_create_link_from_element� s
ri c @ s: e Zd Zddd�dd�Zeed�dd�Zed �d
d �ZdS ) �CacheablePageContent�HTMLPageN)�pager c C s |j s
t�|| _d S )N)�cache_link_parsing�AssertionErrorrl )r+ rl r# r# r$ r* s
z CacheablePageContent.__init__)�otherr c C s t |t| ��o | jj|jjkS )N)�
isinstance�typerl r )r+ ro r# r# r$ �__eq__ s zCacheablePageContent.__eq__)r c C s t | jj�S )N)�hashrl r )r+ r# r# r$ �__hash__ s z CacheablePageContent.__hash__) r- r. r/ r* �object�boolrr �intrt r# r# r# r$ rj s rj rk )�fnr c sL t jdd�ttt d�� fdd� ��t �� �dtt d�� �fdd � �}|S )
z�
Given a function that parses an Iterable[Link] from an HTMLPage, cache the
function's result (keyed by CacheablePageContent), unless the HTMLPage
`page` has `page.cache_link_parsing == False`.
N)�maxsize)�cacheable_pager c s t � | j��S )N)�listrl )rz )rx r# r$ �wrapper s z'with_cached_html_pages.<locals>.wrapperrk )rl r c s | j r�t| ��S t� | ��S )N)rm rj r{ )rl )rx r| r# r$ �wrapper_wrapper s z/with_cached_html_pages.<locals>.wrapper_wrapper)� functools� lru_cacherj r r �wraps)rx r} r# )rx r| r$ �with_cached_html_pages s
r� )rl r c c sZ t j| j| jdd�}| j}t||�}x0|�d�D ]"}t|||d�}|dkrLq0|V q0W dS )zP
Parse an HTML document, and yield its anchor elements as Link objects.
F)Ztransport_encodingZnamespaceHTMLElementsz.//a)rM re N)r r> �content�encodingr rQ rO ri )rl rL r re rd rh r# r# r$ � parse_links( s
r� c @ s: e Zd ZdZd
eee eedd�dd�Zed�dd �Z dS ) rk z'Represents one page, along with its URLTN)r� r� r rm r c C s || _ || _|| _|| _dS )am
:param encoding: the encoding to decode the given content.
:param url: the URL from which the HTML was downloaded.
:param cache_link_parsing: whether links parsed from this page's url
should be cached. PyPI index urls should
have this set to False, for example.
N)r� r� r rm )r+ r� r� r rm r# r# r$ r* C s zHTMLPage.__init__)r c C s
t | j�S )N)r r )r+ r# r# r$ �__str__V s zHTMLPage.__str__)T)
r- r. r/ �__doc__�bytesr r0 rv r* r� r# r# r# r$ rk @ s
).N)rh �reason�methr c C s |d krt j}|d| |� d S )Nz%Could not fetch URL %s: %s - skipping)rE rF )rh r� r� r# r# r$ �_handle_get_page_failZ s r� T)r2 rm r c C s t | j�}t| j|| j|d�S )N)r� r rm )rK r4 rk r� r )r2 rm r� r# r# r$ �_make_html_paged s
r� )rh r: r c
C s |d krt d��| j�dd�d }t|�}|r@t�d|| � d S tj�|�\}}}}}}|dkr�t j
� tj �
|��r�|�d�s�|d7 }tj�|d�}t�d |� yt||d
�}W �nF tk
r� t�d | � Y �n4 tk
�r
} zt�d | |j|j� W d d }~X Y n� tk
�r6 } zt| |� W d d }~X Y n� tk
�rb } zt| |� W d d }~X Y n� tk
�r� } z$d
} | t|�7 } t| | tjd� W d d }~X Y nd t j k
�r� } zt| d|� �� W d d }~X Y n0 t j k
�r� t| d� Y nX t || j d�S d S )Nz?_get_html_page() missing 1 required keyword argument: 'session'�#r r zICannot look at %s URL %s because it does not support lookup as web pages.�file�/z
index.htmlz# file: URL is directory, getting %s)r: z`Skipping page %s because it looks like an archive, and cannot be checked by a HTTP HEAD request.ziSkipping page %s because the %s request got Content-Type: %s.The only supported Content-Type is text/htmlz4There was a problem confirming the ssl certificate: )r� zconnection error: z timed out)rm )!� TypeErrorr rX r% rE Zwarningr= r> r` �osrA �isdirr6 rT �endswithrg rF rG r9 r& r( r' r r� r r r0 �infor �ConnectionErrorZTimeoutr� rm )
rh r: r Z
vcs_schemer" �_rA rB �excr� r# r# r$ �_get_html_pagen sV
r� c @ s. e Zd ZU eee ed< eee ed< dS )�CollectedSources�
find_links�
index_urlsN)r- r. r/ r r r �__annotations__r# r# r# r$ r� � s
r� c @ sx e Zd ZdZeedd�dd�Zedeee d d�dd ��Z
e e e
d
�d d ��Zeee d
�dd�Ze
eed�dd�ZdS )�
LinkCollectorz�
Responsible for collecting Link objects from all configured locations,
making network requests as needed.
The class's main method is its collect_sources() method.
N)r: � search_scoper c C s || _ || _d S )N)r� r: )r+ r: r� r# r# r$ r* � s zLinkCollector.__init__F)r: �options�suppress_no_indexr c C s` |j g|j }|jr8|s8t�dd�dd� |D ��� g }|jp@g }tj||d�}t ||d�}|S )z�
:param session: The Session to use to make requests.
:param suppress_no_index: Whether to ignore the --no-index option
when constructing the SearchScope object.
zIgnoring indexes: %s�,c s s | ]}t |�V qd S )N)r )�.0r r# r# r$ � <genexpr>� s z'LinkCollector.create.<locals>.<genexpr>)r� r� )r: r� )
Z index_urlZextra_index_urlsZno_indexrE rF r] r� r �creater� )�clsr: r� r� r� r� r� Zlink_collectorr# r# r$ r� � s
zLinkCollector.create)r c C s | j jS )N)r� r� )r+ r# r# r$ r� � s zLinkCollector.find_links)�locationr c C s t || jd�S )z>
Fetch an HTML page containing package links.
)r: )r� r: )r+ r� r# r# r$ �
fetch_page� s zLinkCollector.fetch_page)� project_name�candidates_from_pager c s� t �� �fdd��j�|�D ���� }t �� �fdd��jD ���� }t�tj �r�dd� t
� ||�D �}t |�� d|� d�g| }t�
d�|�� tt|�t|�d �S )
Nc 3 s$ | ] }t |� �jjd d d�V qdS )F)r� �page_validator�
expand_dirrm N)r r: �is_secure_origin)r� �loc)r� r+ r# r$ r� � s z0LinkCollector.collect_sources.<locals>.<genexpr>c 3 s$ | ] }t |� �jjd d d�V qdS )T)r� r� r� rm N)r r: r� )r� r� )r� r+ r# r$ r� � s c S s* g | ]"}|d k r|j d k rd|j � ��qS )Nz* )rh )r� �sr# r# r$ �
<listcomp> s z1LinkCollector.collect_sources.<locals>.<listcomp>z' location(s) to search for versions of �:�
)r� r� )� collections� OrderedDictr� Zget_index_urls_locations�valuesr� rE Z isEnabledFor�logging�DEBUGrY rZ r! rF r] r� r{ )r+ r� r� Zindex_url_sourcesZfind_links_sources�linesr# )r� r+ r$ �collect_sources� s z LinkCollector.collect_sources)F)r- r. r/ r� r r r* � classmethodr rv r� �propertyr r0 r� r r rk r� r r� r� r# r# r# r$ r� � s r� )N)T)N)Yr� rI r� r~ rY r� r� �reZ urllib.parser= Zurllib.requestZxml.etree.ElementTreeZxmlZoptparser �typingr r r r r r r r
Z pip._vendorr r Zpip._vendor.requestsr
Z pip._vendor.requests.exceptionsr r Zpip._internal.exceptionsr Zpip._internal.models.linkr Z!pip._internal.models.search_scoper Z pip._internal.network.sessionr Zpip._internal.network.utilsr Z pip._internal.utils.filetypesr Zpip._internal.utils.miscr r Zpip._internal.vcsr Zsourcesr r r Z getLoggerr- rE ZetreeZ ElementTreeZElementZ HTMLElementr0 ZResponseHeadersr% � Exceptionr& r8 r9 rC rG rK rQ rS rU �compile�
IGNORECASErW rv r_ rc ri rj r� r� rk r� r� r� r� r� r# r# r# r$ �<module> sr (
2
=