---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006 Python Software Foundation.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # All rights reserved.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # mypy: allow-untyped-defs, allow-untyped-calls
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | """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."""
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | import sys
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | from typing import (
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Callable,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Final,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Iterable,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Iterator,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     List,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Optional,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Pattern,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Set,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Tuple,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Union,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | from blib2to3.pgen2.grammar import Grammar
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | from blib2to3.pgen2.token import (
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     ASYNC,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     AWAIT,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     COMMENT,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     DEDENT,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     ENDMARKER,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     ERRORTOKEN,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     INDENT,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     NAME,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     NEWLINE,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     NL,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     NUMBER,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     OP,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     STRING,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     tok_name,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | __author__ = "Ka-Ping Yee <ping@lfw.org>"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | __credits__ = "GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | import re
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | from codecs import BOM_UTF8, lookup
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | from . import token
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | __all__ = [x for x in dir(token) if x[0] != "_"] + [
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     "tokenize",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     "generate_tokens",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     "untokenize",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | ]
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | del token
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0002 0002 0002 0000 0000 0000 0000 -- 01 001 004 002 004 005 006 0013.93 0006.97 0000.50 | def group(*choices: str) -> str:
0002 0002 0002 0000 0000 0000 0000 -- 01 001 004 002 004 005 006 0013.93 0006.97 0000.50 |     return "(" + "|".join(choices) + ")"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0002 0002 0002 0000 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 | def any(*choices: str) -> str:
0002 0002 0002 0000 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 |     return group(*choices) + "*"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0002 0002 0002 0000 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 | def maybe(*choices: str) -> str:
0002 0002 0002 0000 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 |     return group(*choices) + "?"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0002 0002 0002 0000 0000 0000 0000 -- 04 002 006 003 006 008 009 0027.00 0027.00 0001.00 | def _combinations(*l: str) -> Set[str]:
0002 0002 0002 0000 0000 0000 0000 -- 04 002 006 003 006 008 009 0027.00 0027.00 0001.00 |     return {x + y for x in l for y in l + ("",) if x.casefold() != y.casefold()}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Whitespace = r"[ \f\t]*"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Comment = r"#[^\r\n]*"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Ignore = Whitespace + any(r"\\\r?\n" + Whitespace) + maybe(Comment)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Name = (  # this is invalid but it's fine because Name comes after Number in all groups
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"[^\s#\(\)\[\]\{\}+\-*/!@$%^&=|;:'\",\.<>/?`~\\]+"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Binnumber = r"0[bB]_?[01]+(?:_[01]+)*"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Hexnumber = r"0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Octnumber = r"0[oO]?_?[0-7]+(?:_[0-7]+)*[lL]?"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Decnumber = group(r"[1-9]\d*(?:_\d+)*[lL]?", "0[lL]?")
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Intnumber = group(Binnumber, Hexnumber, Octnumber, Decnumber)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Exponent = r"[eE][-+]?\d+(?:_\d+)*"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Pointfloat = group(r"\d+(?:_\d+)*\.(?:\d+(?:_\d+)*)?", r"\.\d+(?:_\d+)*") + maybe(
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     Exponent
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Expfloat = r"\d+(?:_\d+)*" + Exponent
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Floatnumber = group(Pointfloat, Expfloat)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Imagnumber = group(r"\d+(?:_\d+)*[jJ]", Floatnumber + r"[jJ]")
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Number = group(Imagnumber, Floatnumber, Intnumber)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # Tail end of ' string.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # Tail end of " string.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # Tail end of ''' string.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # Tail end of """ string.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | _litprefix = r"(?:[uUrRbBfF]|[rR][fFbB]|[fFbBuU][rR])?"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Triple = group(_litprefix + "'''", _litprefix + '"""')
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # Single-line ' or " string.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | String = group(
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     _litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     _litprefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*"',
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # Because of leftmost-then-longest match semantics, be sure to put the
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # longest operators first (e.g., if = came before ==, == would get
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # recognized as two instances of =).
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Operator = group(
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"\*\*=?",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r">>=?",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"<<=?",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"<>",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"!=",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"//=?",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"->",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"[+\-*/%&@|^=<>:]=?",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     r"~",
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Bracket = "[][(){}]"
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Special = group(r"\r?\n", r"[:;.,`@]")
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Funny = group(Operator, Bracket, Special)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | # First (or only) line of ' or " string.
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | ContStr = group(
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     _litprefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" + group("'", r"\\\r?\n"),
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     _litprefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*' + group('"', r"\\\r?\n"),
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | PseudoExtras = group(r"\\\r?\n", Comment, Triple)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | pseudoprog: Final = re.compile(PseudoToken, re.UNICODE)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | single3prog = re.compile(Single3)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | double3prog = re.compile(Double3)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | _strprefixes = (
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     _combinations("r", "R", "f", "F")
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     | _combinations("r", "R", "b", "B")
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     | {"u", "U", "ur", "uR", "Ur", "UR"}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | endprogs: Final = {
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     "'": re.compile(Single),
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     '"': re.compile(Double),
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     "'''": single3prog,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     '"""': double3prog,
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     **{f"{prefix}'''": single3prog for prefix in _strprefixes},
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     **{f'{prefix}"""': double3prog for prefix in _strprefixes},
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | }
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | triple_quoted: Final = (
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     {"'''", '"""'}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     | {f"{prefix}'''" for prefix in _strprefixes}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     | {f'{prefix}"""' for prefix in _strprefixes}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | single_quoted: Final = (
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     {"'", '"'}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     | {f"{prefix}'" for prefix in _strprefixes}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     | {f'{prefix}"' for prefix in _strprefixes}
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | tabsize = 8
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- 01 -- --- --- --- --- --- --- ------- ------- ------- | class TokenError(Exception):
---- ---- ---- ---- ---- ---- ---- 01 -- --- --- --- --- --- --- ------- ------- ------- |     pass
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- 01 -- --- --- --- --- --- --- ------- ------- ------- | class StopTokenizing(Exception):
---- ---- ---- ---- ---- ---- ---- 01 -- --- --- --- --- --- --- ------- ------- ------- |     pass
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | Coord = Tuple[int, int]
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0008 0004 0008 0001 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 | def printtoken(
0008 0004 0008 0001 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 |     type: int, token: str, srow_col: Coord, erow_col: Coord, line: str
0008 0004 0008 0001 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 | ) -> None:  # for testing
0008 0004 0008 0001 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 |     (srow, scol) = srow_col
0008 0004 0008 0001 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 |     (erow, ecol) = erow_col
0008 0004 0008 0001 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 |     print(
0008 0004 0008 0001 0000 0000 0000 -- 01 001 002 001 002 003 003 0004.75 0002.38 0000.50 |         "%d,%d-%d,%d:\t%s\t%s" % (srow, scol, erow, ecol, tok_name[type], repr(token))
0008 0004 0008 0001 0000 0000 0000 -- -- 001 002 001 002 003 003 0004.75 0002.38 0000.50 |     )
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | TokenEater = Callable[[int, str, Coord, Coord, str], None]
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 | def tokenize(readline: Callable[[], str], tokeneater: TokenEater = printtoken) -> None:
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     """
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     The tokenize() function accepts two parameters: one representing the
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     input stream, and one providing an output mechanism for tokenize().
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 | 
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     The first parameter, readline, must be a callable object which provides
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     the same interface as the readline() method of built-in file objects.
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     Each call to the function should return one line of input as a string.
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 | 
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     The second parameter, tokeneater, must also be a callable object. It is
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     called once for each token, with five arguments, corresponding to the
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     tuples generated by generate_tokens().
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     """
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     try:
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         tokenize_loop(readline, tokeneater)
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     except StopTokenizing:
0020 0006 0005 0001 0010 0004 0001 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         pass
0020 0006 0005 0001 0010 0004 0001 -- -- --- --- --- --- --- --- ------- ------- ------- | 
0020 0006 0005 0001 0010 0004 0001 -- -- --- --- --- --- --- --- ------- ------- ------- | 
0020 0006 0005 0001 0010 0004 0001 -- -- --- --- --- --- --- --- ------- ------- ------- | # backwards compatible interface
0003 0003 0003 0000 0000 0000 0000 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 | def tokenize_loop(readline: Callable[[], str], tokeneater: TokenEater) -> None:
0003 0003 0003 0000 0000 0000 0000 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     for token_info in generate_tokens(readline):
0003 0003 0003 0000 0000 0000 0000 -- 02 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         tokeneater(*token_info)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | GoodTokenInfo = Tuple[int, str, Coord, Coord, str]
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | TokenInfo = Union[Tuple[int, str], GoodTokenInfo]
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- | class Untokenizer:
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- |     tokens: List[str]
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- |     prev_row: int
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- |     prev_col: int
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- | 
0004 0004 0004 0000 0000 0000 0000 05 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     def __init__(self) -> None:
0004 0004 0004 0000 0000 0000 0000 05 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         self.tokens = []
0004 0004 0004 0000 0000 0000 0000 05 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         self.prev_row = 1
0004 0004 0004 0000 0000 0000 0000 05 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         self.prev_col = 0
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- | 
0006 0006 0006 0000 0000 0000 0000 05 02 003 006 003 006 009 009 0028.53 0042.79 0001.50 |     def add_whitespace(self, start: Coord) -> None:
0006 0006 0006 0000 0000 0000 0000 05 02 003 006 003 006 009 009 0028.53 0042.79 0001.50 |         row, col = start
0006 0006 0006 0000 0000 0000 0000 05 02 003 006 003 006 009 009 0028.53 0042.79 0001.50 |         assert row <= self.prev_row
0006 0006 0006 0000 0000 0000 0000 05 02 003 006 003 006 009 009 0028.53 0042.79 0001.50 |         col_offset = col - self.prev_col
0006 0006 0006 0000 0000 0000 0000 05 02 003 006 003 006 009 009 0028.53 0042.79 0001.50 |         if col_offset:
0006 0006 0006 0000 0000 0000 0000 05 02 003 006 003 006 009 009 0028.53 0042.79 0001.50 |             self.tokens.append(" " * col_offset)
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- | 
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |     def untokenize(self, iterable: Iterable[TokenInfo]) -> str:
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |         for t in iterable:
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |             if len(t) == 2:
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |                 self.compat(t, iterable)
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |                 break
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |             tok_type, token, start, end, line = t
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |             self.add_whitespace(start)
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |             self.tokens.append(token)
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |             self.prev_row, self.prev_col = end
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |             if tok_type in (NEWLINE, NL):
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |                 self.prev_row += 1
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |                 self.prev_col = 0
0013 0013 0013 0000 0000 0000 0000 05 04 003 006 003 006 009 009 0028.53 0042.79 0001.50 |         return "".join(self.tokens)
---- ---- ---- ---- ---- ---- ---- 05 -- --- --- --- --- --- --- ------- ------- ------- | 
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |     def compat(self, token: Tuple[int, str], iterable: Iterable[TokenInfo]) -> None:
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |         startline = False
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |         indents = []
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |         toks_append = self.tokens.append
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |         toknum, tokval = token
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |         if toknum in (NAME, NUMBER):
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             tokval += " "
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |         if toknum in (NEWLINE, NL):
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             startline = True
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |         for tok in iterable:
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             toknum, tokval = tok[:2]
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 | 
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             if toknum in (NAME, NUMBER, ASYNC, AWAIT):
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 tokval += " "
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 | 
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             if toknum == INDENT:
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 indents.append(tokval)
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 continue
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             elif toknum == DEDENT:
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 indents.pop()
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 continue
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             elif toknum in (NEWLINE, NL):
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 startline = True
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             elif startline and indents:
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 toks_append(indents[-1])
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |                 startline = False
0027 0026 0025 0000 0000 0002 0000 05 10 005 012 010 019 017 029 0118.54 0469.21 0003.96 |             toks_append(tokval)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | cookie_re = re.compile(r"^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)", re.ASCII)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | blank_re = re.compile(rb"^[ \t\f]*(?:[#\r\n]|$)", re.ASCII)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 | def _get_normal_name(orig_enc: str) -> str:
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |     """Imitates get_normal_name in tokenizer.c."""
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |     # Only care about the first 12 characters.
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |     enc = orig_enc[:12].lower().replace("_", "-")
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |     if enc == "utf-8" or enc.startswith("utf-8-"):
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |         return "utf-8"
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |     if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or enc.startswith(
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |         ("latin-1-", "iso-8859-1-", "iso-latin-1-")
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |     ):
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |         return "iso-8859-1"
0011 0009 0009 0001 0000 0000 0002 -- 05 003 007 004 008 010 012 0039.86 0068.34 0001.71 |     return orig_enc
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | def detect_encoding(readline: Callable[[], bytes]) -> Tuple[str, List[bytes]]:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     """
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     The detect_encoding() function is used to detect the encoding that should
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     be used to decode a Python source file. It requires one argument, readline,
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     in the same way as the tokenize() generator.
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     It will call readline a maximum of twice, and return the encoding used
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     (as a string) and a list of any lines (left as bytes) it has read
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     in.
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     It detects the encoding from the presence of a utf-8 bom or an encoding
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     cookie as specified in pep-0263. If both a bom and a cookie are present, but
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     disagree, a SyntaxError will be raised. If the encoding cookie is an invalid
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     charset, raise a SyntaxError.  Note that if a utf-8 bom is found,
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     'utf-8-sig' is returned.
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     If no encoding is specified, then the default of 'utf-8' will be returned.
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     """
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     bom_found = False
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     encoding = None
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     default = "utf-8"
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     def read_or_stop() -> bytes:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         try:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             return readline()
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         except StopIteration:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             return b""
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     def find_cookie(line: bytes) -> Optional[str]:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         try:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             line_string = line.decode("ascii")
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         except UnicodeDecodeError:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             return None
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         match = cookie_re.match(line_string)
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         if not match:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             return None
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         encoding = _get_normal_name(match.group(1))
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         try:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             codec = lookup(encoding)
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         except LookupError:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             # This behaviour mimics the Python interpreter
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             raise SyntaxError("unknown encoding: " + encoding)
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         if bom_found:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             if codec.name != "utf-8":
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |                 # This behaviour mimics the Python interpreter
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |                 raise SyntaxError("encoding problem: utf-8")
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |             encoding += "-sig"
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         return encoding
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     first = read_or_stop()
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     if first.startswith(BOM_UTF8):
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         bom_found = True
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         first = first[3:]
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         default = "utf-8-sig"
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     if not first:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         return default, []
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     encoding = find_cookie(first)
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     if encoding:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         return encoding, [first]
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     if not blank_re.match(first):
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         return default, [first]
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     second = read_or_stop()
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     if not second:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         return default, [first]
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     encoding = find_cookie(second)
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     if encoding:
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |         return encoding, [first, second]
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 | 
0073 0048 0046 0002 0014 0011 0002 -- 07 003 009 007 010 012 017 0060.94 0101.57 0001.67 |     return default, [first, second]
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 | def untokenize(iterable: Iterable[TokenInfo]) -> str:
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     """Transform tokens back into Python source code.
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 | 
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     Each element returned by the iterable must be a token sequence
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     with at least two elements, a token number and token value.  If
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     only two tokens are passed, the resulting output is poor.
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 | 
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     Round-trip invariant for full input:
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         Untokenized source will match input source exactly
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 | 
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     Round-trip invariant for limited input:
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         # Output text will tokenize the back to the input
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         t1 = [tok[:2] for tok in generate_tokens(f.readline)]
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         newcode = untokenize(t1)
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         readline = iter(newcode.splitlines(1)).next
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         t2 = [tok[:2] for tokin generate_tokens(readline)]
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |         assert t1 == t2
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     """
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     ut = Untokenizer()
0020 0004 0003 0000 0014 0003 0000 -- 01 000 000 000 000 000 000 0000.00 0000.00 0000.00 |     return ut.untokenize(iterable)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | def generate_tokens(
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     readline: Callable[[], str], grammar: Optional[Grammar] = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | ) -> Iterator[GoodTokenInfo]:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     """
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     The generate_tokens() generator requires one argument, readline, which
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     must be a callable object which provides the same interface as the
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     readline() method of built-in file objects. Each call to the function
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     should return one line of input as a string.  Alternately, readline
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     can be a callable function terminating with StopIteration:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         readline = open(myfile).next    # Example of alternate readline
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     The generator produces 5-tuples with these members: the token type; the
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     token string; a 2-tuple (srow, scol) of ints specifying the row and
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     column where the token begins in the source; a 2-tuple (erow, ecol) of
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     ints specifying the row and column where the token ends in the source;
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     and the line on which the token was found. The line passed is the
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     logical line; continuation lines are included.
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     """
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     lnum = parenlev = continued = 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     numchars: Final[str] = "0123456789"
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     contstr, needcont = "", 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     contline: Optional[str] = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     indents = [0]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     # If we know we're parsing 3.7+, we can unconditionally parse `async` and
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     # `await` as keywords.
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     async_keywords = False if grammar is None else grammar.async_keywords
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     # 'stashed' and 'async_*' are used for async/await parsing
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     stashed: Optional[GoodTokenInfo] = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     async_def = False
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     async_def_indent = 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     async_def_nl = False
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     strstart: Tuple[int, int]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     endprog: Pattern[str]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     while 1:  # loop over lines in stream
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         try:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             line = readline()
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         except StopIteration:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             line = ""
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         lnum += 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         pos, max = 0, len(line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         if contstr:  # continued string
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             assert contline is not None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if not line:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 raise TokenError("EOF in multi-line string", strstart)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             endmatch = endprog.match(line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if endmatch:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 pos = end = endmatch.end(0)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     STRING,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     contstr + line[:end],
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     strstart,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     (lnum, end),
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     contline + line,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 )
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 contstr, needcont = "", 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 contline = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             elif needcont and line[-2:] != "\\\n" and line[-3:] != "\\\r\n":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     ERRORTOKEN,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     contstr + line,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     strstart,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     (lnum, len(line)),
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     contline,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 )
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 contstr = ""
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 contline = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 continue
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             else:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 contstr = contstr + line
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 contline = contline + line
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 continue
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         elif parenlev == 0 and not continued:  # new statement
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if not line:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 break
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             column = 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             while pos < max:  # measure leading whitespace
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 if line[pos] == " ":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     column += 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif line[pos] == "\t":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     column = (column // tabsize + 1) * tabsize
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif line[pos] == "\f":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     column = 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 else:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     break
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 pos += 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if pos == max:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 break
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if line[pos] in "\r\n":  # skip blank lines
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (NL, line[pos:], (lnum, pos), (lnum, len(line)), line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 continue
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if line[pos] == "#":  # skip comments
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 comment_token = line[pos:].rstrip("\r\n")
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 nl_pos = pos + len(comment_token)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     COMMENT,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     comment_token,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     (lnum, pos),
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     (lnum, nl_pos),
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     line,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 )
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (NL, line[nl_pos:], (lnum, nl_pos), (lnum, len(line)), line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 continue
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if column > indents[-1]:  # count indents
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 indents.append(column)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             while column < indents[-1]:  # count dedents
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 if column not in indents:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     raise IndentationError(
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         "unindent does not match any outer indentation level",
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         ("<tokenize>", lnum, pos, line),
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     )
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 indents = indents[:-1]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 if async_def and async_def_indent >= indents[-1]:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     async_def = False
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     async_def_nl = False
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     async_def_indent = 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (DEDENT, "", (lnum, pos), (lnum, pos), line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if async_def and async_def_nl and async_def_indent >= indents[-1]:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 async_def = False
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 async_def_nl = False
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 async_def_indent = 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         else:  # continued statement
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if not line:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 raise TokenError("EOF in multi-line statement", (lnum, 0))
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             continued = 0
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         while pos < max:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             pseudomatch = pseudoprog.match(line, pos)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             if pseudomatch:  # scan for tokens
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 start, end = pseudomatch.span(1)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 spos, epos, pos = (lnum, start), (lnum, end), end
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 token, initial = line[start:end], line[start]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 if initial in numchars or (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     initial == "." and token != "."
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 ):  # ordinary number
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     yield (NUMBER, token, spos, epos, line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif initial in "\r\n":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     newline = NEWLINE
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if parenlev > 0:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         newline = NL
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     elif async_def:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         async_def_nl = True
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     yield (newline, token, spos, epos, line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif initial == "#":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     assert not token.endswith("\n")
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     yield (COMMENT, token, spos, epos, line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif token in triple_quoted:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     endprog = endprogs[token]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     endmatch = endprog.match(line, pos)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if endmatch:  # all on one line
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         pos = endmatch.end(0)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         token = line[start:pos]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         yield (STRING, token, spos, (lnum, pos), line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     else:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         strstart = (lnum, start)  # multiple lines
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         contstr = line[start:]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         contline = line
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         break
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     initial in single_quoted
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     or token[:2] in single_quoted
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     or token[:3] in single_quoted
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 ):
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if token[-1] == "\n":  # continued string
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         strstart = (lnum, start)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         maybe_endprog = (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             endprogs.get(initial)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             or endprogs.get(token[1])
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             or endprogs.get(token[2])
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         )
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         assert (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             maybe_endprog is not None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         ), f"endprog not found for {token}"
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         endprog = maybe_endprog
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         contstr, needcont = line[start:], 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         contline = line
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         break
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     else:  # ordinary string
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         yield (STRING, token, spos, epos, line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif initial.isidentifier():  # ordinary name
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if token in ("async", "await"):
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         if async_keywords or async_def:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             yield (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 ASYNC if token == "async" else AWAIT,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 token,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 spos,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 epos,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 line,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             )
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             continue
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     tok = (NAME, token, spos, epos, line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if token == "async" and not stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         stashed = tok
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         continue
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if token in ("def", "for"):
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         if stashed and stashed[0] == NAME and stashed[1] == "async":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             if token == "def":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 async_def = True
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 async_def_indent = indents[-1]
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             yield (
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 ASYNC,
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 stashed[1],
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 stashed[2],
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 stashed[3],
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                                 stashed[4],
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             )
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                             stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     yield tok
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 elif initial == "\\":  # continued stmt
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     # This yield is new; needed for better idempotency:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     yield (NL, token, spos, (lnum, pos), line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     continued = 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 else:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if initial in "([{":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         parenlev += 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     elif initial in ")]}":
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         parenlev -= 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                         stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                     yield (OP, token, spos, epos, line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |             else:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 yield (ERRORTOKEN, line[pos], (lnum, pos), (lnum, pos + 1), line)
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |                 pos += 1
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     if stashed:
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         yield stashed
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         stashed = None
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 | 
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     for _indent in indents[1:]:  # pop remaining indent levels
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |         yield (DEDENT, "", (lnum, 0), (lnum, 0), "")
0274 0200 0231 0022 0014 0025 0004 -- 71 017 087 082 154 104 236 1581.30 23792.26 0015.05 |     yield (ENDMARKER, "", (lnum, 0), (lnum, 0), "")
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | 
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- | if __name__ == "__main__":  # testing
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     if len(sys.argv) > 1:
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |         tokenize(open(sys.argv[1]).readline)
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |     else:
---- ---- ---- ---- ---- ---- ---- -- -- --- --- --- --- --- --- ------- ------- ------- |         tokenize(sys.stdin.readline)