U c@sdZddlmZddlmZddlmZddlZddlZddl m Z m Z dZ ddd d d Z d d d ddZddd ddZdddd dddZdddddZdS)z6 :func:`~pandas.eval` source string parsing functions ) annotations)StringIO) iskeywordN)HashableIteratordstr)namereturnc s|rt|s|SddtjDddddddd d d d fd d|D}d|}|s|td|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). cSs$i|]\}}|dtj|dqS)_)tokentok_name).0chartokvalrC/tmp/pip-unpacked-wheel-g7fro6k3/pandas/core/computation/parsing.py )sz2create_valid_python_identifier..r Z_QUESTIONMARK_Z_EXCLAMATIONMARK_Z _DOLLARSIGN_Z _EUROSIGN_Z _DEGREESIGN_Z _SINGLEQUOTE_Z _DOUBLEQUOTE_) ?!$u€°'"csg|]}||qSr)get)rrZspecial_characters_replacementsrr =sz2create_valid_python_identifier..ZBACKTICK_QUOTED_STRING_zCould not convert 'z' to a valid Python identifier.) isidentifierrtokenizeEXACT_TOKEN_TYPESitemsupdatejoin SyntaxError)r rrrcreate_valid_python_identifiers*r&ztuple[int, str])tokr cCs&|\}}|tkrtjt|fS||fS)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 NAMEr&)r'toknumrrrrclean_backtick_quoted_toksFsr+rcCsDz&td|d}t|d}t|WStk r>|YSXdS)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. `N)tokenize_stringnextr&r%)r Z tokenizedrrrrclean_column_name`s   r0zIterator[tokenize.TokenInfo]int)token_generatorsource string_startr cCs8|D]"\}}}}}|dkr|d}q(qt|||fS)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). r,r-)r()r2r3r4r rstartZ string_endrrrtokenize_backtick_quoted_strings r6zIterator[tuple[int, str]])r3r c cst|j}t|}|D]t\}}}}}|dkrzt|||dddVWqtk r~}ztd|d|W5d}~XYqXq||fVqdS)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]). r,r-)r4zFailed to parse backticks in 'z'.N)rreadliner generate_tokensr6 Exceptionr%)r3Z line_readerr2r*rr5r errrrrr.s   &r.)__doc__ __future__riorkeywordrr r typingrrr(r&r+r0r6r.rrrrs   3%"