diff options
Diffstat (limited to 'Lib/tokenize.py')
| -rw-r--r-- | Lib/tokenize.py | 135 |
1 files changed, 76 insertions, 59 deletions
diff --git a/Lib/tokenize.py b/Lib/tokenize.py index b1d0c83263..825aa90646 100644 --- a/Lib/tokenize.py +++ b/Lib/tokenize.py @@ -29,6 +29,7 @@ from codecs import lookup, BOM_UTF8 import collections from io import TextIOWrapper from itertools import chain +import itertools as _itertools import re import sys from token import * @@ -119,19 +120,41 @@ Comment = r'#[^\r\n]*' Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment) Name = r'\w+' -Hexnumber = r'0[xX][0-9a-fA-F]+' -Binnumber = r'0[bB][01]+' -Octnumber = r'0[oO][0-7]+' -Decnumber = r'(?:0+|[1-9][0-9]*)' +Hexnumber = r'0[xX](?:_?[0-9a-fA-F])+' +Binnumber = r'0[bB](?:_?[01])+' +Octnumber = r'0[oO](?:_?[0-7])+' +Decnumber = r'(?:0(?:_?0)*|[1-9](?:_?[0-9])*)' Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber) -Exponent = r'[eE][-+]?[0-9]+' -Pointfloat = group(r'[0-9]+\.[0-9]*', r'\.[0-9]+') + maybe(Exponent) -Expfloat = r'[0-9]+' + Exponent +Exponent = r'[eE][-+]?[0-9](?:_?[0-9])*' +Pointfloat = group(r'[0-9](?:_?[0-9])*\.(?:[0-9](?:_?[0-9])*)?', + r'\.[0-9](?:_?[0-9])*') + maybe(Exponent) +Expfloat = r'[0-9](?:_?[0-9])*' + Exponent Floatnumber = group(Pointfloat, Expfloat) -Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]') +Imagnumber = group(r'[0-9](?:_?[0-9])*[jJ]', Floatnumber + r'[jJ]') Number = group(Imagnumber, Floatnumber, Intnumber) -StringPrefix = r'(?:[bB][rR]?|[rR][bB]?|[uU])?' +# Return the empty string, plus all of the valid string prefixes. +def _all_string_prefixes(): + # The valid string prefixes. Only contain the lower case versions, + # and don't contain any permuations (include 'fr', but not + # 'rf'). The various permutations will be generated. + _valid_string_prefixes = ['b', 'r', 'u', 'f', 'br', 'fr'] + # if we add binary f-strings, add: ['fb', 'fbr'] + result = set(['']) + for prefix in _valid_string_prefixes: + for t in _itertools.permutations(prefix): + # create a list with upper and lower versions of each + # character + for u in _itertools.product(*[(c, c.upper()) for c in t]): + result.add(''.join(u)) + return result + +def _compile(expr): + return re.compile(expr, re.UNICODE) + +# Note that since _all_string_prefixes includes the empty string, +# StringPrefix can be the empty string (making it optional). +StringPrefix = group(*_all_string_prefixes()) # Tail end of ' string. Single = r"[^'\\]*(?:\\.[^'\\]*)*'" @@ -169,50 +192,25 @@ ContStr = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" + PseudoExtras = group(r'\\\r?\n|\Z', Comment, Triple) PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name) -def _compile(expr): - return re.compile(expr, re.UNICODE) - -endpats = {"'": Single, '"': Double, - "'''": Single3, '"""': Double3, - "r'''": Single3, 'r"""': Double3, - "b'''": Single3, 'b"""': Double3, - "R'''": Single3, 'R"""': Double3, - "B'''": Single3, 'B"""': Double3, - "br'''": Single3, 'br"""': Double3, - "bR'''": Single3, 'bR"""': Double3, - "Br'''": Single3, 'Br"""': Double3, - "BR'''": Single3, 'BR"""': Double3, - "rb'''": Single3, 'rb"""': Double3, - "Rb'''": Single3, 'Rb"""': Double3, - "rB'''": Single3, 'rB"""': Double3, - "RB'''": Single3, 'RB"""': Double3, - "u'''": Single3, 'u"""': Double3, - "U'''": Single3, 'U"""': Double3, - 'r': None, 'R': None, 'b': None, 'B': None, - 'u': None, 'U': None} - -triple_quoted = {} -for t in ("'''", '"""', - "r'''", 'r"""', "R'''", 'R"""', - "b'''", 'b"""', "B'''", 'B"""', - "br'''", 'br"""', "Br'''", 'Br"""', - "bR'''", 'bR"""', "BR'''", 'BR"""', - "rb'''", 'rb"""', "rB'''", 'rB"""', - "Rb'''", 'Rb"""', "RB'''", 'RB"""', - "u'''", 'u"""', "U'''", 'U"""', - ): - triple_quoted[t] = t -single_quoted = {} -for t in ("'", '"', - "r'", 'r"', "R'", 'R"', - "b'", 'b"', "B'", 'B"', - "br'", 'br"', "Br'", 'Br"', - "bR'", 'bR"', "BR'", 'BR"' , - "rb'", 'rb"', "rB'", 'rB"', - "Rb'", 'Rb"', "RB'", 'RB"' , - "u'", 'u"', "U'", 'U"', - ): - single_quoted[t] = t +# For a given string prefix plus quotes, endpats maps it to a regex +# to match the remainder of that string. _prefix can be empty, for +# a normal single or triple quoted string (with no prefix). +endpats = {} +for _prefix in _all_string_prefixes(): + endpats[_prefix + "'"] = Single + endpats[_prefix + '"'] = Double + endpats[_prefix + "'''"] = Single3 + endpats[_prefix + '"""'] = Double3 + +# A set of all of the single and triple quoted string prefixes, +# including the opening quotes. +single_quoted = set() +triple_quoted = set() +for t in _all_string_prefixes(): + for u in (t + '"', t + "'"): + single_quoted.add(u) + for u in (t + '"""', t + "'''"): + triple_quoted.add(u) tabsize = 8 @@ -626,6 +624,7 @@ def _tokenize(readline, encoding): yield stashed stashed = None yield TokenInfo(COMMENT, token, spos, epos, line) + elif token in triple_quoted: endprog = _compile(endpats[token]) endmatch = endprog.match(line, pos) @@ -638,19 +637,37 @@ def _tokenize(readline, encoding): contstr = line[start:] contline = line break - elif initial in single_quoted or \ - token[:2] in single_quoted or \ - token[:3] in single_quoted: + + # Check up to the first 3 chars of the token to see if + # they're in the single_quoted set. If so, they start + # a string. + # We're using the first 3, because we're looking for + # "rb'" (for example) at the start of the token. If + # we switch to longer prefixes, this needs to be + # adjusted. + # Note that initial == token[:1]. + # Also note that single quote checking must come after + # triple quote checking (above). + elif (initial in single_quoted or + token[:2] in single_quoted or + token[:3] in single_quoted): if token[-1] == '\n': # continued string strstart = (lnum, start) - endprog = _compile(endpats[initial] or - endpats[token[1]] or - endpats[token[2]]) + # Again, using the first 3 chars of the + # token. This is looking for the matching end + # regex for the correct type of quote + # character. So it's really looking for + # endpats["'"] or endpats['"'], by trying to + # skip string prefix characters, if any. + endprog = _compile(endpats.get(initial) or + endpats.get(token[1]) or + endpats.get(token[2])) contstr, needcont = line[start:], 1 contline = line break else: # ordinary string yield TokenInfo(STRING, token, spos, epos, line) + elif initial.isidentifier(): # ordinary name if token in ('async', 'await'): if async_def: |