Yf,U T @ s
d Z d Z d Z d d l Z d d l Z d d l m Z m Z d d l Td d l m
Z
d d
e e
D d d d
g Z [
y e
Wn e k
r e Z
Yn Xd d Z d d Z d d Z d Z d Z e e d e e e Z d Z d Z d Z d Z d Z e e e e e Z d Z e d d e e Z d e Z e e e Z e d e d! Z e e e e Z! d" Z" d# Z# d$ Z$ d% Z% e d& d' Z& e d( d) Z' e d* d+ d, d- d. d/ d0 d1 d2 Z( d3 Z) e d4 d5 Z* e e( e) e* Z+ e e! e+ e' e Z, e e, Z- e d6 e d7 d d8 e d9 d Z. e d e e& Z/ e e e/ e! e+ e. e Z0 e1 e2 e j3 e- e0 e$ e% f \ Z4 Z5 Z6 Z7 d7 e j3 e" d9 e j3 e# d: e6 d; e7 d< e6 d= e7 d> e6 d? e7 d@ e6 dA e7 dB e6 dC e7 dD e6 dE e7 dF e6 dG e7 dH e6 dI e7 dJ e6 dK e7 dL e6 dM e7 dN e6 dO e7 dP e6 dQ e7 dR e6 dS e7 dT e6 dU e7 dV e6 dW e7 dX d dY d dZ d d[ d d\ d d] d i& Z8 i Z9 x d D] Z: e: e9 e: <qWi Z; x d D] Z: e: e; e: <qWdz Z< Gd{ d| d| e= Z> Gd} d~ d~ e= Z? d d Z@ e@ d d ZA d d ZB Gd d d ZC e j3 d e jD ZE e j3 d e jD ZF d d ZG d d ZH d d
ZI d d ZJ eK d k r d d lL ZL eM eL jN d k reA eO eL jN d jP n eA eL jQ jP d S)a Tokenization help for Python programs.
generate_tokens(readline) is a generator that breaks a stream of
text into Python tokens. It accepts a readline-like method which is called
repeatedly to get the next line of input (or "" 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
Older entry points
tokenize_loop(readline, tokeneater)
tokenize(readline, tokeneater=printtoken)
are the same, except instead of generating tokens, tokeneater is a callback
function to which the 5 fields described above are passed as 5 arguments,
each time a new token is found.zKa-Ping Yee <ping@lfw.org>z@GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro N)BOM_UTF8lookup)* )tokenc C s& g | ] } | d d k r | q S)r _ ).0xr r ;/opt/alt/python35/lib64/python3.5/lib2to3/pgen2/tokenize.py
<listcomp>% s r tokenizegenerate_tokens
untokenizec G s d d j | d S)N(|))join)choicesr r r group0 s r c G s t | d S)Nr )r )r r r r any1 s r c G s t | d S)N?)r )r r r r maybe2 s r z[ \f\t]*z #[^\r\n]*z\\\r?\nz [a-zA-Z_]\w*z
0[bB][01]*z0[xX][\da-fA-F]*[lL]?z0[oO]?[0-7]*[lL]?z
[1-9]\d*[lL]?z [eE][-+]?\d+z\d+\.\d*z\.\d+z\d+z\d+[jJ]z[jJ]z[^'\\]*(?:\\.[^'\\]*)*'z[^"\\]*(?:\\.[^"\\]*)*"z%[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''z%[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""z[ubUB]?[rR]?'''z[ubUB]?[rR]?"""z&[uU]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*'z&[uU]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*"z\*\*=?z>>=?z<<=?z<>z!=z//=?z->z[+\-*/%&@|^=<>]=?~z[][(){}]z\r?\nz[:;.,`@]z'[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*'z'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*"'''"""r'''r"""u'''u"""b'''b"""ur'''ur"""br'''br"""R'''R"""U'''U"""B'''B"""uR'''uR"""Ur'''Ur"""UR'''UR"""bR'''bR"""Br'''Br"""BR'''BR"""rRuUbBr'r"R'R"u'u"U'U"b'b"B'B"ur'ur"Ur'Ur"uR'uR"UR'UR"br'br"Br'Br"bR'bR"BR'BR" c @ s e Z d Z d S)
TokenErrorN)__name__
__module__ __qualname__r r r r r] s r] c @ s e Z d Z d S)StopTokenizingN)r^ r_ r` r r r r ra s ra c C sF | \ } } | \ } } t d | | | | t | t | f d S)Nz%d,%d-%d,%d: %s %s)printtok_namerepr) typer Zxxx_todo_changemeZxxx_todo_changeme1lineZsrowZscolZerowZecolr r r
printtoken s rg c C s* y t | | Wn t k
r% Yn Xd S)a:
The tokenize() function accepts two parameters: one representing the
input stream, and one providing an output mechanism for tokenize().
The first parameter, readline, 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 a string.
The second parameter, tokeneater, must also be a callable object. It is
called once for each token, with five arguments, corresponding to the
tuples generated by generate_tokens().
N)
tokenize_loopra )readline
tokeneaterr r r r
s
c C s% x t | D] } | | q
Wd S)N)r )ri rj Z
token_infor r r rh s rh c @ s@ e Z d Z d d Z d d Z d d Z d d Z d S)
Untokenizerc C s g | _ d | _ d | _ d S)Nr r )tokensprev_rowprev_col)selfr r r __init__ s zUntokenizer.__init__c C s7 | \ } } | | j } | r3 | j j d | d S)N )rn rl append)ro startrowcol
col_offsetr r r add_whitespace s
zUntokenizer.add_whitespacec C s x | D] } t | d k r0 | j | | P| \ } } } } } | j | | j j | | \ | _ | _ | t t f k r | j d 7_ d | _ q Wd j | j S)N r r )
lencompatrw rl rr rm rn NEWLINENLr )ro iterablettok_typer rs endrf r r r r s
zUntokenizer.untokenizec C s% d } g } | j j } | \ } } | t t f k r@ | d 7} | t t f k rX d } x | D] } | d d \ } } | t t t t f k r | d 7} | t k r | j | q_ nW | t k r | j
q_ n; | t t f k r d } n | r| r| | d d } | | q_ Wd S)NFrq Trx r ) rl rr NAMENUMBERr| r} ASYNCAWAITINDENTDEDENTpop) ro r r~ startlineindents toks_appendtoknumtokvaltokr r r r{ s0
zUntokenizer.compatN)r^ r_ r` rp rw r r{ r r r r rk s rk z&^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)s ^[ \t\f]*(?:[#\r\n]|$)c C sd | d d j j d d } | d k s= | j d rA d S| d
k s\ | j d r` d S| S)z(Imitates get_normal_name in tokenizer.c.N r -zutf-8zutf-8-latin-1
iso-8859-1 iso-latin-1latin-1- iso-8859-1- iso-latin-1-)r r r )r r r )lowerreplace
startswith)orig_encencr r r _get_normal_name s " r c s d d } d } f d d } f d d } | } | j t rj d | d d } d
} | sz | g f S| | } | r | | g f St j | s | | g f S| } | s | | g f S| | } | r | | | g f S| | | g f S) a
The detect_encoding() function is used to detect the encoding that should
be used to decode a Python source file. It requires one argument, readline,
in the same way as the tokenize() generator.
It will call readline a maximum of twice, and return the encoding used
(as a string) and a list of any lines (left as bytes) it has read
in.
It detects the encoding from the presence of a utf-8 bom or an encoding
cookie as specified in pep-0263. If both a bom and a cookie are present, but
disagree, a SyntaxError will be raised. If the encoding cookie is an invalid
charset, raise a SyntaxError. Note that if a utf-8 bom is found,
'utf-8-sig' is returned.
If no encoding is specified, then the default of 'utf-8' will be returned.
FNzutf-8c s+ y SWn t k
r& t SYn Xd S)N)
StopIterationbytesr )ri r r read_or_stop s
z%detect_encoding.<locals>.read_or_stopc s y | j d } Wn t k
r+ d SYn Xt j | } | sE d St | j d } y t | } Wn" t k
r t d | Yn X r | j d k r t d | d 7} | S)Nasciir zunknown encoding: zutf-8zencoding problem: utf-8z-sig)
decodeUnicodeDecodeError cookie_rematchr r r LookupError SyntaxErrorname)rf line_stringr encodingcodec) bom_foundr r find_cookie s"
z$detect_encoding.<locals>.find_cookieT z utf-8-sig)r r blank_rer )ri r defaultr r firstsecondr )r ri r detect_encoding s0
r c C s t } | j | S)a Transform tokens back into Python source code.
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 intput:
# Output text will tokenize the back to the input
t1 = [tok[:2] for tok in generate_tokens(f.readline)]
newcode = untokenize(t1)
readline = iter(newcode.splitlines(1)).next
t2 = [tok[:2] for tokin generate_tokens(readline)]
assert t1 == t2
)rk r )r~ utr r r r F s c ! c sY d } } } t j d d } } d \ } } d } d g } d }
d } d } d }
xy
| } Wn t k
r d } Yn X| d } d t | } } | r| s t d | | j | } | r!| j d } } t | | d | | | | f | | f Vd! \ } } d } qv| r| d" d d
k r| d# d d k rt | | | | t | f | f Vd } d } qX qv| | } | | } qX n| d k rU| rU| sPd } xv | | k r;| | d
k r| d } n? | | d k r| t d t } n | | d k r-d } n P| d } qW| | k rIP|
rZ|
Vd }
| | d k rG| | d k r | | d j
d } | t | } t | | | f | | t | f | f Vt | | d | | f | t | f | f VqX t t f | | d k | | d | | f | t | f | f VqX | | d$ k r| j
| t | d | | d f | | f | f Vx | | d% k r#| | k rt d d | | | f | d d& } | r | | d' k r d } d }
d } t d | | f | | f | f VqW| rv|
rv| | d( k rvd } d }
d } n! | spt d | d f d } xl| | k rt j | | } | r| j d \ } } | | f | | f | } } } | | | | | } } | | k s| d k r(| d k r(t | | | | f Vq| d k rt } | d k rOt } n | r[d }
|
rl|
Vd }
| | | | | f Vq| d k r|
r|
Vd }
t | | | | f Vq| t k rXt | } | j | | } | r2| j d } | | | } |
r|
Vd }
t | | | | f | f Vq| | f } | | d } | } Pq| t k s| d d t k s| d d t k r| d) d k r| | f } t | pt | d pt | d } | | d d } } | } Pq|
r|
Vd }
t | | | | f Vq| | k r| d* k rb| rb| d k rKt n t | | | | f Vqyt | | | | f } | d k r|
r| }
qy| d k r|
r|
d t k r|
d d k rd } | d+ } t |
d |
d |
d |
d f Vd }
|
r|
Vd }
| Vq| d k rX|
r5|
Vd }
t | | | | f | f Vd } q| d k rq| d } n | d k r| d } |
r|
Vd }
t | | | | f Vqyt | | | | f | | d f | f V| d } qyWqX W|
r|
Vd }
x8 | d d D]& } t d | d f | d f d f Vq Wt d | d f | d f d f Vd S),aT
The generate_tokens() 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 a string. Alternately, readline
can be a callable function terminating with StopIteration:
readline = open(myfile).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.
r r
0123456789ry NFr zEOF in multi-line stringrx z\
r z\
rq z#
#z
z3unindent does not match any outer indentation levelz
<tokenize>zEOF in multi-line statement.T
asyncawaitdef \z([{z)]})ry r )ry r r r r r r r )r r r ) stringZ
ascii_lettersr rz r] r r STRING
ERRORTOKENtabsizerstripCOMMENTr} rr r IndentationErrorr
pseudoprogspanr r|
triple_quotedendprogs
single_quotedr r r OP ENDMARKER)!ri lnumparenlev continuedZ namecharsnumcharscontstrneedcontcontliner stashed async_defasync_def_indent async_def_nlrf posmaxstrstartendprogendmatchr column
comment_tokennl_pos pseudomatchrs sposeposr initialnewliner indentr r r r [ sp
2
$#$
* $
$__main__) r r r r r( r) r r! r* r+ r" r# r, r- r$ r% r0 r1 r. r/ r2 r3 r& r' r6 r7 r4 r5 r8 r9 ) r r r@ rA rB rC rD rE rF rG rH rI rJ rK rL rM rN rO rP rQ rR rS rT rU rV rW rX rY rZ r[ )R__doc__
__author__ __credits__r recodecsr r Zlib2to3.pgen2.tokenry r dir__all__r NameErrorstrr r r
WhitespaceCommentIgnoreName Binnumber Hexnumber Octnumber Decnumber IntnumberExponent
PointfloatExpfloat Floatnumber
ImagnumberNumberSingleDoubleSingle3Double3TripleStringOperatorBracketSpecialFunny
PlainTokenTokenContStr PseudoExtras PseudoTokenlistmapcompileZ tokenprogr Z single3progZ double3progr r r r r Exceptionr] ra rg r
rh rk ASCIIr r r r r r r^ sysrz argvopenri stdinr r r r <module> s
*
8 I