o
    ŀg                     @  s   d Z ddlmZ ddlmZ ddlmZ ddlZddlZddl	m
Z
 e
r,ddlmZmZ dZdddZd ddZd!ddZd"ddZd#ddZdS )$z6
:func:`~pandas.eval` source string parsing functions
    )annotations)StringIO)	iskeywordN)TYPE_CHECKING)HashableIteratord   namestrreturnc                   s   |   r
t| s
| S dd tj D   ddddddd	d
d d fdd| D } d|  } |   s?td|  d| S )a=  
    Create valid Python identifiers from any string.

    Check if name contains any special characters. If it contains any
    special characters, the special characters will be replaced by
    a special string and a prefix is added.

    Raises
    ------
    SyntaxError
        If the returned name is not a Python valid identifier, raise an exception.
        This can happen if there is a hashtag in the name, as the tokenizer will
        than terminate and not find the backtick.
        But also for characters that fall out of the range of (U+0001..U+007F).
    c                 S  s$   i | ]\}}|d t j|  d qS )_)tokentok_name).0chartokval r   S/var/www/html/myenv/lib/python3.10/site-packages/pandas/core/computation/parsing.py
<dictcomp>,   s    z2create_valid_python_identifier.<locals>.<dictcomp>r   _QUESTIONMARK__EXCLAMATIONMARK__DOLLARSIGN_
_EUROSIGN__DEGREESIGN__SINGLEQUOTE__DOUBLEQUOTE_) ?!$u   €   °'" c                   s   g | ]}  ||qS r   )get)r   r   special_characters_replacementsr   r   
<listcomp>@   s    z2create_valid_python_identifier.<locals>.<listcomp>BACKTICK_QUOTED_STRING_zCould not convert 'z' to a valid Python identifier.)isidentifierr   tokenizeEXACT_TOKEN_TYPESitemsupdatejoinSyntaxError)r	   r   r%   r   create_valid_python_identifier   s*   
r0   toktuple[int, str]c                 C  s&   | \}}|t krtjt|fS ||fS )a[  
    Clean up a column name if surrounded by backticks.

    Backtick quoted string are indicated by a certain tokval value. If a string
    is a backtick quoted token it will processed by
    :func:`_create_valid_python_identifier` so that the parser can find this
    string when the query is executed.
    In this case the tok will get the NAME tokval.

    Parameters
    ----------
    tok : tuple of int, str
        ints correspond to the all caps constants in the tokenize module

    Returns
    -------
    tok : Tuple[int, str]
        Either the input or token or the replacement values
    )BACKTICK_QUOTED_STRINGr*   NAMEr0   )r1   toknumr   r   r   r   clean_backtick_quoted_toksI   s   r6   r   c                 C  s>   zt d|  d}t|d }t|W S  ty   |  Y S w )a  
    Function to emulate the cleaning of a backtick quoted name.

    The purpose for this function is to see what happens to the name of
    identifier if it goes to the process of being parsed a Python code
    inside a backtick quoted string and than being cleaned
    (removed of any special characters).

    Parameters
    ----------
    name : hashable
        Name to be cleaned.

    Returns
    -------
    name : hashable
        Returns the name after tokenizing and cleaning.

    Notes
    -----
        For some cases, a name cannot be converted to a valid Python identifier.
        In that case :func:`tokenize_string` raises a SyntaxError.
        In that case, we just return the name unmodified.

        If this name was used in the query string (this makes the query call impossible)
        an error will be raised by :func:`tokenize_backtick_quoted_string` instead,
        which is not caught and propagates to the user level.
    `   )tokenize_stringnextr0   r/   )r	   	tokenizedr   r   r   r   clean_column_namec   s   
r<   token_generatorIterator[tokenize.TokenInfo]sourcestring_startintc                 C  s8   | D ]\}}}}}|dkr|d } nqt ||| fS )a  
    Creates a token from a backtick quoted string.

    Moves the token_generator forwards till right after the next backtick.

    Parameters
    ----------
    token_generator : Iterator[tokenize.TokenInfo]
        The generator that yields the tokens of the source string (Tuple[int, str]).
        The generator is at the first token after the backtick (`)

    source : str
        The Python source code string.

    string_start : int
        This is the start of backtick quoted string inside the source string.

    Returns
    -------
    tok: Tuple[int, str]
        The token that represents the backtick quoted string.
        The integer is equal to BACKTICK_QUOTED_STRING (100).
    r7   r8   )r3   )r=   r?   r@   r   r   start
string_endr   r   r   tokenize_backtick_quoted_string   s   rD   Iterator[tuple[int, str]]c                 c  s    t | j}t|}|D ]4\}}}}}|dkr<zt|| |d d dV  W q ty; } z	td|  d|d}~ww ||fV  qdS )a$  
    Tokenize a Python source code string.

    Parameters
    ----------
    source : str
        The Python source code string.

    Returns
    -------
    tok_generator : Iterator[Tuple[int, str]]
        An iterator yielding all tokens with only toknum and tokval (Tuple[ing, str]).
    r7   r8   )r@   zFailed to parse backticks in 'z'.N)r   readliner*   generate_tokensrD   	Exceptionr/   )r?   line_readerr=   r5   r   rB   r   errr   r   r   r9      s   

r9   )r	   r
   r   r
   )r1   r2   r   r2   )r	   r   r   r   )r=   r>   r?   r
   r@   rA   r   r2   )r?   r
   r   rE   )__doc__
__future__r   ior   keywordr   r   r*   typingr   collections.abcr   r   r3   r0   r6   r<   rD   r9   r   r   r   r   <module>   s    

3

%"