B
sa; / @ s d Z dZdZddlmZ ddlmZmZ ddl Z ddl
m Z ddl m
Z
ddl ZddlZddlZdd lT ed
ejZed ejZddlZejd d
ddg Z[eeeeee e e e e e!e"e#e$e%e&e'e(e)e*e+e,e-e.e/e0e1e2e3e4e5e6e7e8e9e:e;ee?e@eAeBeCeDd.ZEG dd de FddZGdd ZHdd ZIdd ZJdZKdZLeKeIdeK eJeL ZMd ZNd ZOd ZPd ZQd ZReHeOePeQeRZSd!ZTeHd"d#eJeT ZUd$eT ZVeHeUeVZWeHd%eWd& ZXeHeXeWeSZYd'd( ZZd)d* Z[eHeZ Z\d+Z]d,Z^d-Z_d.Z`eHe\d/ e\d0 ZaeHe\d1 e\d2 ZbeHd3d4d5d6d7d8d9d:Zcd;ZdeHdZeeHecedeeZfeHeYefebeNZgeMeg ZheHe\d? eHd@d e\dA eHdBd ZieHdCeLeaZjeKeHejeYefeieN Zki Zlx@eZ D ]6Zme]elemd@ < e^elemdB < e_elemd/ < e`elemd0 < qW en Zoen Zpx\eZ D ]RZqx$eqdB eqd@ fD ]Zreoser qW x$eqd0 eqd/ fD ]Zrepser q(W qW dDZtG dEdF dFeuZvG dGdH dHeuZwG dIdJ dJZxdKd ZydLdM ZzdNd
Z{dOdP ZdQd Z|dRdS Z}dTdU Z~dVdW ZedXkre dS )Yao Tokenization help for Python programs.
tokenize(readline) is a generator that breaks a stream of bytes into
Python tokens. It decodes the bytes according to PEP-0263 for
determining source file encoding.
It accepts a readline-like method which is called repeatedly to get the
next line of input (or b"" for EOF). It generates 5-tuples with these
members:
the token type (see token.py)
the token (a string)
the starting (row, column) indices of the token (a 2-tuple of ints)
the ending (row, column) indices of the token (a 2-tuple of ints)
the original line (string)
It is designed to match the working of the Python tokenizer exactly, except
that it produces COMMENT tokens for comments and gives type OP for all
operators. Additionally, all token lists start with an ENCODING token
which tells you which encoding was used to decode the bytes stream.
zKa-Ping Yee zpGvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro, Raymond Hettinger, Trent Nelson, Michael Foord )open)lookupBOM_UTF8N)
TextIOWrapper)chain)*z&^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)s ^[ \t\f]*(?:[#\r\n]|$)tokenizedetect_encoding
untokenize TokenInfo).()[]:,;+-r /|&<>=.%{}z==z!=z<=z>=~^z<>z**z+=z-=z*=z/=z%=z&=z|=z^=z<<=z>>=z**=z//z//=z...z->@z@=c @ s e Zd Zdd Zedd ZdS )r c C s$ d| j t| j f }d| j|d S )Nz%d (%s)z8TokenInfo(type=%s, string=%r, start=%r, end=%r, line=%r))type)r" tok_name_replace)selfannotated_type r' -/opt/alt/python37/lib64/python3.7/tokenize.py__repr___ s zTokenInfo.__repr__c C s( | j tkr | jtkr t| j S | j S d S )N)r" OPstringEXACT_TOKEN_TYPES)r% r' r' r(
exact_typed s
zTokenInfo.exact_typeN)__name__
__module__ __qualname__r) propertyr- r' r' r' r( r ^ s ztype string start end linec G s dd | d S )Nr r r
)join)choicesr' r' r( groupk r4 c G s t | d S )Nr )r4 )r3 r' r' r( anyl r5 r6 c G s t | d S )N?)r4 )r3 r' r' r( maybem r5 r8 z[ \f\t]*z #[^\r\n]*z\\\r?\nz\w+z0[xX](?:_?[0-9a-fA-F])+z0[bB](?:_?[01])+z0[oO](?:_?[0-7])+z (?:0(?:_?0)*|[1-9](?:_?[0-9])*)z[eE][-+]?[0-9](?:_?[0-9])*z)[0-9](?:_?[0-9])*\.(?:[0-9](?:_?[0-9])*)?z\.[0-9](?:_?[0-9])*z[0-9](?:_?[0-9])*z[0-9](?:_?[0-9])*[jJ]z[jJ]c C sj ddddddg} dh}xN| D ]F}x@t |D ]2}x,t jdd |D D ]}|d| qFW q,W q W |S )
Nbrufbrfr c S s g | ]}|| fqS r' )upper).0cr' r' r(
s z(_all_string_prefixes..)
_itertools permutationsproductaddr2 )_valid_string_prefixesresultprefixtr; r' r' r( _all_string_prefixes s
rL c C s t | t jS )N)recompileUNICODE)exprr' r' r( _compile s rQ z[^'\\]*(?:\\.[^'\\]*)*'z[^"\\]*(?:\\.[^"\\]*)*"z%[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''z%[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""z'''z"""z '[^\n'\\]*(?:\\.[^\n'\\]*)*'z "[^\n"\\]*(?:\\.[^\n"\\]*)*"z\*\*=?z>>=?z<<=?z!=z//=?z->z[+\-*/%&@|^=<>]=?r z[][(){}]z\r?\nz\.\.\.z[:;.,@]z'[^\n'\\]*(?:\\.[^\n'\\]*)*'z"[^\n"\\]*(?:\\.[^\n"\\]*)*"z
\\\r?\n|\Z c @ s e Zd ZdS )
TokenErrorN)r. r/ r0 r' r' r' r( rU s rU c @ s e Zd ZdS )StopTokenizingN)r. r/ r0 r' r' r' r( rV s rV c @ s, e Zd Zdd Zdd Zdd Zdd Zd S )
Untokenizerc C s g | _ d| _d| _d | _d S )N r )tokensprev_rowprev_colencoding)r% r' r' r( __init__ s zUntokenizer.__init__c C s |\}}|| j k s&|| j kr>|| jk r>td||| j | j|| j }|rb| jd| d| _|| j }|r| jd| d S )Nz+start ({},{}) precedes previous end ({},{})z\
r )rZ r[
ValueErrorformatrY append)r% startrowcol
row_offset
col_offsetr' r' r( add_whitespace s
zUntokenizer.add_whitespacec C s4 t |}g }d}x|D ]
}t|dkr8| || P |\}}}} }
|tkrV|| _q|tkr`P |tkrv|| qnl|tkr| | \| _
| _ qnL|t t
fkrd}n:|r|r|d } |d t| kr| j| t| | _ d}| | | j| | \| _
| _ |t t
fkr| j
d7 _
d| _ qW d| jS )NF TrX r r? )iterlencompatENCODINGr\ ENDMARKERINDENTra DEDENTpoprZ r[ NEWLINENLrY rg r2 ) r% iterableitindents startlinerK tok_typetokenrb endlineindentr' r' r( r
sF
zUntokenizer.untokenizec
C s g }| j j}|d ttfk}d}xt|g|D ]}|d d \}} |tkrR| | _q.|ttfkrf| d7 } |t kr|rzd| } d}nd}|t
kr|| q.n>|t kr| q.n*|ttfkrd}n|r|r||d d}|| q.W d S )Nr Frh r^ Tri )
rY ra rr rs r rm r\ NAMENUMBERSTRINGro rp rq )
r% ry rt rv toks_appendrw
prevstringtoktoknumtokvalr' r' r( rl s8
zUntokenizer.compatN)r. r/ r0 r] rg r
rl r' r' r' r( rW s
%rW c C s* t }|| }|jdk r&||j}|S )a Transform tokens back into Python source code.
It returns a bytes object, encoded using the ENCODING
token, which is the first token sequence output by tokenize.
Each element returned by the iterable must be a token sequence
with at least two elements, a token number and token value. If
only two tokens are passed, the resulting output is poor.
Round-trip invariant for full input:
Untokenized source will match input source exactly
Round-trip invariant for limited input:
# Output bytes will tokenize back to the input
t1 = [tok[:2] for tok in tokenize(f.readline)]
newcode = untokenize(t1)
readline = BytesIO(newcode).readline
t2 = [tok[:2] for tok in tokenize(readline)]
assert t1 == t2
N)rW r
r\ encode)rt utoutr' r' r( r
8 s
c C sH | dd dd}|dks*|dr.dS |dks@|drDd S | S )
z(Imitates get_normal_name in tokenizer.c.N _r zutf-8zutf-8-)zlatin-1z
iso-8859-1z iso-latin-1)zlatin-1-z iso-8859-1-z iso-latin-1-z
iso-8859-1)lowerreplace
startswith)orig_encencr' r' r( _get_normal_nameS s
r c s y j jW n tk
r$ dY nX d d}d}fdd} fdd}| }|trpd |d d }d
}|s||g fS ||}|r||gfS t|s||gfS | }|s||gfS ||}|r|||gfS |||gfS ) a
The detect_encoding() function is used to detect the encoding that should
be used to decode a Python source file. It requires one argument, readline,
in the same way as the tokenize() generator.
It will call readline a maximum of twice, and return the encoding used
(as a string) and a list of any lines (left as bytes) it has read in.
It detects the encoding from the presence of a utf-8 bom or an encoding
cookie as specified in pep-0263. If both a bom and a cookie are present,
but disagree, a SyntaxError will be raised. If the encoding cookie is an
invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found,
'utf-8-sig' is returned.
If no encoding is specified, then the default of 'utf-8' will be returned.
NFzutf-8c s y S t k
r dS X d S )Nr5 )
StopIterationr' )readliner' r( read_or_stopv s z%detect_encoding..read_or_stopc s y| d}W n4 tk
rB d}d k r6d|}t|Y nX t|}|sVd S t|d}y t|}W n: t k
r d krd| }n d|}t|Y nX r|dkr؈d krd}n
d}t||d 7 }|S )
Nzutf-8z'invalid or missing encoding declarationz {} for {!r}rX zunknown encoding: z unknown encoding for {!r}: {}zencoding problem: utf-8z encoding problem for {!r}: utf-8z-sig)
decodeUnicodeDecodeErrorr` SyntaxError cookie_rematchr r4 r LookupError)r{ line_stringmsgr r\ codec) bom_foundfilenamer' r( find_cookie| s6
z$detect_encoding..find_cookieT z utf-8-sig)__self__nameAttributeErrorr r blank_rer )r r\ defaultr r firstsecondr' )r r r r( r ^ s8
&
c C sV t | d}y0t|j\}}|d t||dd}d|_|S | Y nX dS )zXOpen a file in read only mode using the encoding detected by
detect_encoding().
rbr T)line_bufferingr: N)
_builtin_openr r seekr modeclose)r bufferr\ linestextr' r' r( r s
r c C sB ddl m}m} t| \}}t| d}|d}t||||j|S )a
The tokenize() generator requires one argument, readline, which
must be a callable object which provides the same interface as the
readline() method of built-in file objects. Each call to the function
should return one line of input as bytes. Alternatively, readline
can be a callable function terminating with StopIteration:
readline = open(myfile, 'rb').__next__ # Example of alternate readline
The generator produces 5-tuples with these members: the token type; the
token string; a 2-tuple (srow, scol) of ints specifying the row and
column where the token begins in the source; a 2-tuple (erow, ecol) of
ints specifying the row and column where the token ends in the source;
and the line on which the token was found. The line passed is the
logical line; continuation lines are included.
The first token sequence will always be an ENCODING token
which tells you which encoding was used to decode the bytes stream.
r )r repeatr5 ) itertoolsr r r rj _tokenize__next__)r r r r\ consumedrl_genemptyr' r' r( r s
c c s d } }}d}d\}}d }dg} |d k rH|dkr6d}t t|dddV d}
d} xy| }
| } W n tk
rz d} Y nX |d k r| |} |d 7 }dt| } }
|rt| std
||| }|r
|d } }t t|| d | |||f|| V d\}}d }nf|r^| d d d kr^| d
d dkr^t t || ||t| f|V d}d }qTn|| }|| }qTn|dkr |s | sP d}xf| |
k r| | dkr|d 7 }n6| | dkr|t
d t
}n| | dkrd}nP | d 7 } qW | |
krP | | dkr| | dkr`| | d d}t t ||| f|| t| f| V | t|7 } t t
| | d || f|t| f| V qT|| d kr| | t t| d | |df|| f| V xp|| d k r|| krtdd|| | f| d d } t td|| f|| f| V qW n| s0td|dfd}x| |
k rtt| | }|r|d \}}||f||f| }}} ||krq8| || | | }}||ks|dkr|dkr|dkrt t|||| V q|dkr |dkrt t
|||| V nt t|||| V q|dkr>t t |||| V q|tkrtt| }|| | }|r|d} | || }t t|||| f| V n||f}| |d }| }P q|tks|d d tks|d d tkrR|d d kr>||f}tt|p t|d p t|d }| |d d }}| }P nt t|||| V nf| rpt t |||| V nH|d krd }n8|d kr|d 7 }n|d kr|d 8 }t t |||| V n*t t | | || f|| d f| V | d 7 } q8W qTW |
r0|
d dkr0t td|d t|
f|d t|
d fdV x0| d d D ] }t td|df|dfdV q>W t t d|df|dfdV d S )!Nr
0123456789)r? r z utf-8-sigzutf-8)r r r? r5 rX zEOF in multi-line stringz\
z\
r^ z#
#z
ri z3unindent does not match any outer indentation levelz
zEOF in multi-line statementr z...rh r
\z([{z)]}) r rm r r rk rU r rz r
ERRORTOKENtabsizerstripCOMMENTrs ra ro IndentationErrorrp rQ PseudoTokenspanr~ rr
triple_quotedendpats
single_quotedget isidentifierr} r* rn )r r\ lnumparenlev continuednumcharscontstrneedcontcontlinerv last_liner{ posmaxstrstartendprogendmatchrz column
comment_token pseudomatchrb sposeposry initialr| r' r' r( r s
*
"
"
. r c C s
t | d S )N)r )r r' r' r( generate_tokens s r c
s( dd l } dd d fdd }| jdd}|jdd d
d d |jd
ddddd | }y|jr|j}t|d}tt|j}W d Q R X nd}t t
j jd }xF|D ]>}|j }|j
r|j}d|j|j } td| t| |jf qW W n8 tk
r: }
z0|
jd dd \} } ||
jd || | f W d d }
~
X Y n tk
r }
z(|
jd \} } ||
jd || | f W d d }
~
X Y n tk
r }
z||
| W d d }
~
X Y nx tk
r }
z ||
W d d }
~
X Y nN tk
r td Y n2 tk
r" }
z d|
W d d }
~
X Y nX d S ) Nr c S s t | tjd d S )N)file)printsysstderr)messager' r' r( perror s zmain..perrorc sR |r"|f| | f } d| n"|r8 d|| f n d| t d d S )Nz%s:%d:%d: error: %sz
%s: error: %sz error: %srX )r exit)r r locationargs)r r' r( error s zmain..errorzpython -m tokenize)progr r7 z filename.pyz'the file to tokenize; defaults to stdin)destnargsmetavarhelpz-ez--exactexact
store_truez(display token names using the exact type)r actionr r zz %d,%d-%d,%d:z%-20s%-15s%-15rrX r z interrupted
zunexpected error: %s)NN)argparseArgumentParser add_argument
parse_argsr r listr r r r stdinr" r r- rb rz r r# r+ r r rU r OSErrorKeyboardInterrupt Exception)
r r parserr r r< rY ry
token_type token_rangeerrr{ r r' )r r( main sN
&& r __main__)__doc__
__author__ __credits__builtinsr r codecsr r collectionsior r r rD rM r ry rN ASCIIr r __all__LPARRPARLSQBRSQBCOLONCOMMASEMIPLUSMINUSSTARSLASHVBARAMPERLESSGREATEREQUALDOTPERCENTLBRACERBRACEEQEQUALNOTEQUAL LESSEQUAL GREATEREQUALTILDE
CIRCUMFLEX LEFTSHIFT
RIGHTSHIFT
DOUBLESTAR PLUSEQUALMINEQUAL STAREQUAL
SLASHEQUAL PERCENTEQUAL
AMPEREQUAL VBAREQUALCIRCUMFLEXEQUALLEFTSHIFTEQUALRIGHTSHIFTEQUALDOUBLESTAREQUAL DOUBLESLASHDOUBLESLASHEQUALELLIPSISRARROWATATEQUALr,
namedtupler r4 r6 r8
WhitespaceCommentIgnoreName Hexnumber Binnumber Octnumber Decnumber IntnumberExponent
PointfloatExpfloat Floatnumber
ImagnumberNumberrL rQ StringPrefixSingleDoubleSingle3Double3TripleStringOperatorBracketSpecialFunny
PlainTokenTokenContStr PseudoExtrasr r _prefixsetr r rK r; rG r r rU rV rW r
r r r r r r r. r' r' r' r( s
_ ] :<