j fyK & @ s6 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 i& e j3 e" d7 6e j3 e# d9 6e6 d: 6e7 d; 6e6 d< 6e7 d= 6e6 d> 6e7 d? 6e6 d@ 6e7 dA 6e6 dB 6e7 dC 6e6 dD 6e7 dE 6e6 dF 6e7 dG 6e6 dH 6e7 dI 6e6 dJ 6e7 dK 6e6 dL 6e7 dM 6e6 dN 6e7 dO 6e6 dP 6e7 dQ 6e6 dR 6e7 dS 6e6 dT 6e7 dU 6e6 dV 6e7 dW 6d dX 6d dY 6d dZ 6d d[ 6d d\ 6d d] 6Z8 i Z9 x d D] Z: e: e9 e: 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 r2d d lL ZL eM eL jN d k r eA eO eL jN d jP q2eA eL jQ jP n 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 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/python34/lib64/python3.4/lib2to3/pgen2/tokenize.py
% 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 sO | \ } } | | j k s! t | | j } | rK | j j d | n d S)N )rm AssertionErrorrn rl append)ro startrowcol
col_offsetr r r add_whitespace s
zUntokenizer.add_whitespacec C s x | D] } t | d k r3 | j | | Pn | \ } } } } } | j | | j j | | \ | _ | _ | t t f k r | j d 7_ d | _ q q Wd j | j S)N r r )
lencompatrx rl rs rm rn NEWLINENLr )ro iterablettok_typer rt endrf r r r r s
zUntokenizer.untokenizec C s+ d } g } | j j } | \ } } | t t f k rC | d 7} n | t t f k r^ d } n x | D] } | d d \ } } | t t f k r | d 7} n | t k r | j | qe nZ | t k r | j qe n> | t t f k r d } n# | r| r| | d d } n | | qe Wd S)NFrq Try r ) rl rs NAMENUMBERr} r~ INDENTDEDENTpop) ro r r startlineindents toks_appendtoknumtokvaltokr r r r| s0
zUntokenizer.compatN)r^ r_ r` rp rx r r| r r r r rk s rk z%^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)s ^[ \t\f]*(?:[#\r\n]|$)c C sd | d d j j d d } | d k s= | j d rA d S| d
k s\ | j d r` d S| S)z(Imitates get_normal_name in tokenizer.c.N r -zutf-8zutf-8-latin-1
iso-8859-1 iso-latin-1latin-1- iso-8859-1- iso-latin-1-)r r r )r r r )lowerreplace
startswith)orig_encencr r r _get_normal_name s " r c s d d } d } f d d } f d d } | } | j t rm d | d d } d
} n | s} | g f S| | } | r | | g f St j | s | | g f S| } | s | | g f S| | } | r | | | g f S| | | g f S) a
The detect_encoding() function is used to detect the encoding that should
be used to decode a Python source file. It requires one argument, readline,
in the same way as the tokenize() generator.
It will call readline a maximum of twice, and return the encoding used
(as a string) and a list of any lines (left as bytes) it has read
in.
It detects the encoding from the presence of a utf-8 bom or an encoding
cookie as specified in pep-0263. If both a bom and a cookie are present, but
disagree, a SyntaxError will be raised. If the encoding cookie is an invalid
charset, raise a SyntaxError. Note that if a utf-8 bom is found,
'utf-8-sig' is returned.
If no encoding is specified, then the default of 'utf-8' will be returned.
FNzutf-8c s+ y SWn t k
r& t SYn Xd S)N)
StopIterationbytesr )ri r r read_or_stop s
z%detect_encoding..read_or_stopc s y | j d } Wn t k
r+ d SYn Xt j | } | sE d St | j d } y t | } Wn" t k
r t d | Yn X r | j d k r t d n | d 7} n | S)Nasciir zunknown encoding: zutf-8zencoding problem: utf-8z-sig)
decodeUnicodeDecodeError cookie_rematchr r r LookupError SyntaxErrorname)rf line_stringr encodingcodec) bom_foundr r find_cookie s"
z$detect_encoding..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 s d } } } t j d d } } d \ } } d } d g } x y
| }
Wn t k
rg d }
Yn X| d } d t |
} } | r|
s t d |
n | j |
} | r | j d } } t | |
d | |
| | f | |
f Vd \ } } d } q | rt|
d d d k rt|
d d d k rtt | |
|
| t |
f | f Vd } d } q@ q | |
} | |
} q@ n~| d k r| r|
sPn d } xv | | k r)|
| d k r| d } n? |
| d
k r| t d t } n |
| d k rd } n P| d } qW| | k r:Pn |
| d k r*|
| d k r|
| d j
d } | t | } t | | | f | | t | f |
f Vt |
| d | | f | t |
f |
f Vq@ t t f |
| d k |
| d | | f | t |
f |
f Vq@ n | | d k rt| j
| t |
d | | d f | | f |
f Vn x | | d k r| | k rt d d | | |
f n | d d } t d | | f | | f |
f VqwWn$ |
st d | d f n d } x9| | k rGt j |
| } | r| j d \ } } | | f | | f | } } } |
| | |
| } } | | k s| d k r| d k rt | | | |
f VqD| d k rt } | d k rt } n | | | | |
f VqD| d k r5| j d s t t | | | |
f VqD| t k rt | } | j |
| } | r| j d } |
| | } t | | | | f |
f Vq| | f }
|
| d } |
} PqD| t k s| d d t k s| d d
t k rw| d! d k r`| | f }
t | p<t | d p<t | d } |
| d d } } |
} Pqt | | | |
f VqD| | k rt | | | |
f VqD| d k rt | | | | f |
f Vd } qD| d k r| d } n | d k r| d } n t | | | |
f Vqt |
| | | f | | d f |
f V| d } qWq@ Wx8 | 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
0123456789rz Nr zEOF in multi-line stringry z\
r z\
rq z#
#z
z3unindent does not match any outer indentation levelz
zEOF in multi-line statement.
\z([{z)]})rz r )rz r r r r r ) stringZ
ascii_lettersr r{ r] r r STRING
ERRORTOKENtabsizerstripCOMMENTr~ rs r IndentationErrorr
pseudoprogspanr r} endswithrr
triple_quotedendprogs
single_quotedr OP ENDMARKER) ri lnumparenlev continuedZ namecharsnumcharscontstrneedcontcontliner rf posmaxstrstartendprogendmatchr column
comment_tokennl_pos pseudomatchrt sposeposr initialnewlineindentr r r r [ s
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.tokenrz 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^ sysr{ argvopenri stdinr r r r s
*#
8 I