File: //usr/libexec/oracle-cloud-agent/plugins/osms/charset_normalizer/models.pyc
a
ٓ�fh- � @ s� d dl mZ d dlmZ d dlmZ d dlmZmZm Z m
Z
m Z m Z m
Z
ddlmZ ddlmZmZmZ G dd � d �ZG d
d � d �Ze eef Ze
e ZG d d
� d
�ZdS )� )�aliases)�sha256)�dumps)�Any�Dict�Iterator�List�Optional�Tuple�Union� )�TOO_BIG_SEQUENCE)� iana_name�is_multi_byte_encoding�
unicode_rangec @ s� e Zd Zd8eeeedee d�dd�Ze ed�dd�Z
e ed�d d
�Z e ed �d d
��Z
ed �dd�Zed �dd�Zd dd�dd�Ze ed �dd��Ze ee d �dd��Ze ed �dd��Ze ed �dd��Ze ee d �d d ��Ze ed �d d ��Ze ed �d d!��Ze ed �d"d#��Ze ed �d$d%��Ze ed �d&d'��Ze ed �d(d)��Z e ed d �d*d+��Z e ed �d,d-��Z e ee d �d.d/��Z e ee d �d0d1��Z d9eed3�d4d5�Z!e ed �d6d7��Z"dS ):� CharsetMatchN�CoherenceMatches)�payload�guessed_encoding�mean_mess_ratio�has_sig_or_bom� languages�decoded_payloadc C sF || _ || _|| _|| _|| _d | _g | _d| _d | _d | _ || _
d S )N� ) �_payload� _encoding�_mean_mess_ratio�
_languages�_has_sig_or_bom�_unicode_ranges�_leaves�_mean_coherence_ratio�_output_payload�_output_encoding�_string)�selfr r r r r r � r& �}/sparta/input/_build_configuration/image_build+validate/lib/bmcenv/lib64/python3.9/site-packages/charset_normalizer/models.py�__init__ s zCharsetMatch.__init__)�other�returnc C s> t |t�s&td�t|j�t| j����| j|jko<| j|jkS )Nz&__eq__ cannot be invoked on {} and {}.)�
isinstancer � TypeError�format�str� __class__�encoding� fingerprint�r% r) r& r& r' �__eq__$ s
��zCharsetMatch.__eq__c C s� t |t�st�t| j|j �}t| j|j �}|dk rJ|dkrJ| j|jkS |dk r�|dkr�t| j�tkrt| j|jk S | j |j kS | j|jk S )zQ
Implemented to make sorted available upon CharsetMatches items.
g{�G�z�?g{�G�z�?)
r+ r �
ValueError�abs�chaos� coherence�lenr r
�multi_byte_usage)r% r) �chaos_difference�coherence_differencer& r& r' �__lt__- s
zCharsetMatch.__lt__�r* c C s dt t| ��t | j� S )Ng �?)r8 r. �raw�r% r& r& r' r9 C s z CharsetMatch.multi_byte_usagec C s" | j d u r t| j| jd�| _ | j S )N�strict)r$ r. r r r? r& r& r' �__str__G s
zCharsetMatch.__str__c C s d� | j| j�S )Nz <CharsetMatch '{}' bytes({})>)r- r0 r1 r? r& r& r' �__repr__M s zCharsetMatch.__repr__c C s8 t |t�r|| kr"td�|j���d |_| j�|� d S )Nz;Unable to add instance <{}> as a submatch of a CharsetMatch)r+ r r4 r- r/ r$ r �appendr2 r& r& r' � add_submatchP s ��zCharsetMatch.add_submatchc C s | j S �N)r r? r& r& r' r0 [ s zCharsetMatch.encodingc C sD g }t �� D ]2\}}| j|kr*|�|� q | j|kr |�|� q |S )z�
Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
)r �itemsr0 rC )r% �
also_known_as�u�pr& r& r' �encoding_aliases_ s
z CharsetMatch.encoding_aliasesc C s | j S rE �r r? r& r& r' �boml s zCharsetMatch.bomc C s | j S rE rK r? r& r& r' �byte_order_markp s z CharsetMatch.byte_order_markc C s dd� | j D �S )z�
Return the complete list of possible languages found in decoded sequence.
Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
c S s g | ] }|d �qS )r r& )�.0�er& r& r' �
<listcomp>z � z*CharsetMatch.languages.<locals>.<listcomp>�r r? r& r& r' r t s zCharsetMatch.languagesc C sp | j sbd| jv rdS ddlm}m} t| j�r8|| j�n|| j�}t|�dksVd|v rZdS |d S | j d d S )z�
Most probable language found in decoded sequence. If none were detected or inferred, the property will return
"Unknown".
�ascii�Englishr )�encoding_languages�mb_encoding_languagesz Latin Based�Unknown)r �could_be_from_charset�charset_normalizer.cdrU rV r r0 r8 )r% rU rV r r& r& r' �language| s
� �zCharsetMatch.languagec C s | j S rE )r r? r& r& r' r6 � s zCharsetMatch.chaosc C s | j s
dS | j d d S )Nr r r rR r? r& r& r' r7 � s zCharsetMatch.coherencec C s t | jd dd�S �N�d � )�ndigits)�roundr6 r? r& r& r' �
percent_chaos� s zCharsetMatch.percent_chaosc C s t | jd dd�S r[ )r_ r7 r? r& r& r' �percent_coherence� s z CharsetMatch.percent_coherencec C s | j S )z+
Original untouched bytes.
)r r? r& r& r' r> � s zCharsetMatch.rawc C s | j S rE )r r? r& r& r' �submatch� s zCharsetMatch.submatchc C s t | j�dkS �Nr )r8 r r? r& r& r' � has_submatch� s zCharsetMatch.has_submatchc C s@ | j d ur| j S dd� t| �D �}ttdd� |D ���| _ | j S )Nc S s g | ] }t |��qS r& )r )rN �charr& r& r' rP � s z*CharsetMatch.alphabets.<locals>.<listcomp>c S s h | ] }|r|�qS r& r& )rN �rr& r& r' � <setcomp>� rQ z)CharsetMatch.alphabets.<locals>.<setcomp>)r r. �sorted�list)r% �detected_rangesr& r& r' � alphabets� s
�zCharsetMatch.alphabetsc C s | j gdd� | jD � S )z�
The complete list of encoding that output the exact SAME str result and therefore could be the originating
encoding.
This list does include the encoding available in property 'encoding'.
c S s g | ]
}|j �qS r& )r0 )rN �mr& r& r' rP � rQ z6CharsetMatch.could_be_from_charset.<locals>.<listcomp>)r r r? r& r& r' rX � s z"CharsetMatch.could_be_from_charset�utf_8)r0 r* c C s2 | j du s| j |kr,|| _ t| ��|d�| _| jS )z�
Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
Any errors will be simply ignored by the encoder NOT replaced.
N�replace)r# r. �encoder" )r% r0 r& r& r' �output� s zCharsetMatch.outputc C s t | �� ��� S )zw
Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
)r rp � hexdigestr? r& r& r' r1 � s zCharsetMatch.fingerprint)N)rm )#�__name__�
__module__� __qualname__�bytesr. �float�boolr r( �objectr3 r< �propertyr9 rA rB rD r0 r rJ rL rM r rZ r6 r7 r` ra r> rb rd rk rX rp r1 r& r& r& r' r
sb �� r c @ s� e Zd ZdZdeee d�dd�Zee d�dd�Z e
e e f ed �d
d �Z
e d�d d
�Zed�dd�Zedd �dd�Zed d�dd�Zed d�dd�ZdS )�CharsetMatchesz�
Container with every CharsetMatch items ordered by default from most probable to the less one.
Act like a list(iterable) but does not implements all related methods.
N)�resultsc C s |r t |�ng | _d S rE )rh �_results)r% r{ r& r& r' r( � s zCharsetMatches.__init__r= c c s | j E d H d S rE �r| r? r& r& r' �__iter__� s zCharsetMatches.__iter__)�itemr* c C sN t |t�r| j| S t |t�rFt|d�}| jD ]}||jv r.| S q.t�dS )z�
Retrieve a single item either by its position or encoding name (alias may be used here).
Raise KeyError upon invalid index or encoding not present in results.
FN)r+ �intr| r. r rX �KeyError)r% r �resultr& r& r' � __getitem__� s
zCharsetMatches.__getitem__c C s
t | j�S rE �r8 r| r? r& r& r' �__len__� s zCharsetMatches.__len__c C s t | j�dkS rc r� r? r& r& r' �__bool__� s zCharsetMatches.__bool__c C s| t |t�s td�t|j����t|j�tkr`| j D ],}|j
|j
kr2|j |j kr2|� |� dS q2| j �
|� t| j �| _ dS )z~
Insert a single match. Will be inserted accordingly to preserve sort.
Can be inserted as a submatch.
z-Cannot append instance '{}' to CharsetMatchesN)r+ r r4 r- r. r/ r8 r> r
r| r1 r6 rD rC rh )r% r �matchr& r& r' rC s
��
zCharsetMatches.appendr c C s | j s
dS | j d S )zQ
Simply return the first match. Strict equivalent to matches[0].
Nr r} r? r& r& r' �best s zCharsetMatches.bestc C s | � � S )zP
Redundant method, call the method best(). Kept for BC reasons.
)r� r? r& r& r' �first s zCharsetMatches.first)N)rr rs rt �__doc__r r r r( r r~ r r� r. r� r� rw r� rC r� r� r& r& r& r' rz � s rz c @ sj e Zd Zeee ee ee eee eeeee ed� dd�Ze e
ee f d�dd��Z ed�dd�Z
d S )
�CliDetectionResult� �pathr0 rJ �alternative_encodingsrZ rk r r6 r7 � unicode_path� is_preferredc C sF || _ |
| _|| _|| _|| _|| _|| _|| _|| _| | _ | | _
d S rE ) r� r� r0 rJ r� rZ rk r r6 r7 r� ) r% r� r0 rJ r� rZ rk r r6 r7 r� r� r& r& r' r( ) s zCliDetectionResult.__init__r= c C s2 | j | j| j| j| j| j| j| j| j| j | j
d� S )Nr� r� r? r& r& r' �__dict__C s �zCliDetectionResult.__dict__c C s t | jddd�S )NT� )� ensure_ascii�indent)r r� r? r& r& r' �to_jsonS s zCliDetectionResult.to_jsonN)rr rs rt r. r r rw rv r( ry r r r� r� r& r& r& r' r� ( s � r� N)�encodings.aliasesr �hashlibr �jsonr �typingr r r r r r
r �constantr
�utilsr r r r rz r. rv �CoherenceMatchr r� r& r& r& r' �<module> s $ XC