X-Git-Url: https://git.madduck.net/etc/vim.git/blobdiff_plain/5fa38d4c3bdae68abfe235709b69b1bc8ae75c3a..a73d25883aaaa3fa3a10ea2ddfcb70ac1efd448e:/blib2to3/pgen2/tokenize.py diff --git a/blib2to3/pgen2/tokenize.py b/blib2to3/pgen2/tokenize.py index 6dada47..8c1c4cf 100644 --- a/blib2to3/pgen2/tokenize.py +++ b/blib2to3/pgen2/tokenize.py @@ -25,17 +25,20 @@ 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.""" -__author__ = 'Ka-Ping Yee ' -__credits__ = \ - 'GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro' +__author__ = "Ka-Ping Yee " +__credits__ = "GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro" -import string, re +import regex as re from codecs import BOM_UTF8, lookup from blib2to3.pgen2.token import * from . import token -__all__ = [x for x in dir(token) if x[0] != '_'] + ["tokenize", - "generate_tokens", "untokenize"] + +__all__ = [x for x in dir(token) if x[0] != "_"] + [ + "tokenize", + "generate_tokens", + "untokenize", +] del token try: @@ -45,25 +48,40 @@ except NameError: # valid Python 3 code. bytes = str -def group(*choices): return '(' + '|'.join(choices) + ')' -def any(*choices): return group(*choices) + '*' -def maybe(*choices): return group(*choices) + '?' -Whitespace = r'[ \f\t]*' -Comment = r'#[^\r\n]*' -Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment) -Name = r'[a-zA-Z_]\w*' +def group(*choices): + return "(" + "|".join(choices) + ")" + + +def any(*choices): + return group(*choices) + "*" + + +def maybe(*choices): + return group(*choices) + "?" + + +def _combinations(*l): + return set(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 = r"\w+" # this is invalid but it's fine because Name comes after Number in all groups -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]?') +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 +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]') +Imagnumber = group(r"\d+(?:_\d+)*[jJ]", Floatnumber + r"[jJ]") Number = group(Imagnumber, Floatnumber, Intnumber) # Tail end of ' string. @@ -74,102 +92,94 @@ Double = r'[^"\\]*(?:\\.[^"\\]*)*"' Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''" # Tail end of """ string. Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""' -_litprefix = r"(?:[uUrRbBfF]|[rR][bB]|[bBuU][rR])?" +_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"\\]*)*"') +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'[:;.,`@]') +Operator = group( + r"\*\*=?", + r">>=?", + r"<<=?", + r"<>", + r"!=", + r"//=?", + r"->", + r"[+\-*/%&@|^=<>:]=?", + r"~", +) + +Bracket = "[][(){}]" +Special = group(r"\r?\n", r"[:;.,`@]") Funny = group(Operator, Bracket, Special) PlainToken = group(Number, Funny, String, Name) Token = Ignore + PlainToken # 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) +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) -tokenprog, pseudoprog, single3prog, double3prog = list(map( - re.compile, (Token, PseudoToken, Single3, Double3))) -endprogs = {"'": re.compile(Single), '"': re.compile(Double), - "'''": single3prog, '"""': double3prog, - "r'''": single3prog, 'r"""': double3prog, - "u'''": single3prog, 'u"""': double3prog, - "b'''": single3prog, 'b"""': double3prog, - "f'''": single3prog, 'f"""': double3prog, - "ur'''": single3prog, 'ur"""': double3prog, - "br'''": single3prog, 'br"""': double3prog, - "rb'''": single3prog, 'rb"""': double3prog, - "R'''": single3prog, 'R"""': double3prog, - "U'''": single3prog, 'U"""': double3prog, - "B'''": single3prog, 'B"""': double3prog, - "F'''": single3prog, 'F"""': double3prog, - "uR'''": single3prog, 'uR"""': double3prog, - "Ur'''": single3prog, 'Ur"""': double3prog, - "UR'''": single3prog, 'UR"""': double3prog, - "bR'''": single3prog, 'bR"""': double3prog, - "Br'''": single3prog, 'Br"""': double3prog, - "BR'''": single3prog, 'BR"""': double3prog, - "rB'''": single3prog, 'rB"""': double3prog, - "Rb'''": single3prog, 'Rb"""': double3prog, - "RB'''": single3prog, 'RB"""': double3prog, - 'r': None, 'R': None, - 'u': None, 'U': None, - 'f': None, 'F': None, - 'b': None, 'B': None} - -triple_quoted = {} -for t in ("'''", '"""', - "r'''", 'r"""', "R'''", 'R"""', - "u'''", 'u"""', "U'''", 'U"""', - "b'''", 'b"""', "B'''", 'B"""', - "f'''", 'f"""', "F'''", 'F"""', - "ur'''", 'ur"""', "Ur'''", 'Ur"""', - "uR'''", 'uR"""', "UR'''", 'UR"""', - "br'''", 'br"""', "Br'''", 'Br"""', - "bR'''", 'bR"""', "BR'''", 'BR"""', - "rb'''", 'rb"""', "Rb'''", 'Rb"""', - "rB'''", 'rB"""', "RB'''", 'RB"""',): - triple_quoted[t] = t -single_quoted = {} -for t in ("'", '"', - "r'", 'r"', "R'", 'R"', - "u'", 'u"', "U'", 'U"', - "b'", 'b"', "B'", 'B"', - "f'", 'f"', "F'", 'F"', - "ur'", 'ur"', "Ur'", 'Ur"', - "uR'", 'uR"', "UR'", 'UR"', - "br'", 'br"', "Br'", 'Br"', - "bR'", 'bR"', "BR'", 'BR"', - "rb'", 'rb"', "Rb'", 'Rb"', - "rB'", 'rB"', "RB'", 'RB"',): - single_quoted[t] = t +tokenprog = re.compile(Token, re.UNICODE) +pseudoprog = 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 = { + "'": re.compile(Single), + '"': re.compile(Double), + "'''": single3prog, + '"""': double3prog, + **{f"{prefix}'''": single3prog for prefix in _strprefixes}, + **{f'{prefix}"""': double3prog for prefix in _strprefixes}, + **{prefix: None for prefix in _strprefixes}, +} + +triple_quoted = ( + {"'''", '"""'} + | {f"{prefix}'''" for prefix in _strprefixes} + | {f'{prefix}"""' for prefix in _strprefixes} +) +single_quoted = ( + {"'", '"'} + | {f"{prefix}'" for prefix in _strprefixes} + | {f'{prefix}"' for prefix in _strprefixes} +) tabsize = 8 -class TokenError(Exception): pass -class StopTokenizing(Exception): pass +class TokenError(Exception): + pass + + +class StopTokenizing(Exception): + pass + -def printtoken(type, token, xxx_todo_changeme, xxx_todo_changeme1, line): # for testing +def printtoken(type, token, xxx_todo_changeme, xxx_todo_changeme1, line): # for testing (srow, scol) = xxx_todo_changeme (erow, ecol) = xxx_todo_changeme1 - print("%d,%d-%d,%d:\t%s\t%s" % \ - (srow, scol, erow, ecol, tok_name[type], repr(token))) + print( + "%d,%d-%d,%d:\t%s\t%s" % (srow, scol, erow, ecol, tok_name[type], repr(token)) + ) + def tokenize(readline, tokeneater=printtoken): """ @@ -189,13 +199,14 @@ def tokenize(readline, tokeneater=printtoken): except StopTokenizing: pass + # backwards compatible interface def tokenize_loop(readline, tokeneater): for token_info in generate_tokens(readline): tokeneater(*token_info) -class Untokenizer: +class Untokenizer: def __init__(self): self.tokens = [] self.prev_row = 1 @@ -228,14 +239,14 @@ class Untokenizer: toks_append = self.tokens.append toknum, tokval = token if toknum in (NAME, NUMBER): - tokval += ' ' + tokval += " " if toknum in (NEWLINE, NL): startline = True for tok in iterable: toknum, tokval = tok[:2] if toknum in (NAME, NUMBER, ASYNC, AWAIT): - tokval += ' ' + tokval += " " if toknum == INDENT: indents.append(tokval) @@ -250,8 +261,10 @@ class Untokenizer: startline = False toks_append(tokval) -cookie_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII) -blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII) + +cookie_re = re.compile(r"^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)", re.ASCII) +blank_re = re.compile(br"^[ \t\f]*(?:[#\r\n]|$)", re.ASCII) + def _get_normal_name(orig_enc): """Imitates get_normal_name in tokenizer.c.""" @@ -259,11 +272,13 @@ def _get_normal_name(orig_enc): enc = orig_enc[:12].lower().replace("_", "-") if enc == "utf-8" or enc.startswith("utf-8-"): return "utf-8" - if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \ - enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")): + if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or enc.startswith( + ("latin-1-", "iso-8859-1-", "iso-latin-1-") + ): return "iso-8859-1" return orig_enc + def detect_encoding(readline): """ The detect_encoding() function is used to detect the encoding that should @@ -284,7 +299,8 @@ def detect_encoding(readline): """ bom_found = False encoding = None - default = 'utf-8' + default = "utf-8" + def read_or_stop(): try: return readline() @@ -293,7 +309,7 @@ def detect_encoding(readline): def find_cookie(line): try: - line_string = line.decode('ascii') + line_string = line.decode("ascii") except UnicodeDecodeError: return None match = cookie_re.match(line_string) @@ -307,17 +323,17 @@ def detect_encoding(readline): raise SyntaxError("unknown encoding: " + encoding) if bom_found: - if codec.name != 'utf-8': + if codec.name != "utf-8": # This behaviour mimics the Python interpreter - raise SyntaxError('encoding problem: utf-8') - encoding += '-sig' + raise SyntaxError("encoding problem: utf-8") + encoding += "-sig" return encoding first = read_or_stop() if first.startswith(BOM_UTF8): bom_found = True first = first[3:] - default = 'utf-8-sig' + default = "utf-8-sig" if not first: return default, [] @@ -337,6 +353,7 @@ def detect_encoding(readline): return default, [first, second] + def untokenize(iterable): """Transform tokens back into Python source code. @@ -358,7 +375,8 @@ def untokenize(iterable): ut = Untokenizer() return ut.untokenize(iterable) -def generate_tokens(readline): + +def generate_tokens(readline, grammar=None): """ The generate_tokens() generator requires one argument, readline, which must be a callable object which provides the same interface as the @@ -375,39 +393,52 @@ def generate_tokens(readline): logical line; continuation lines are included. """ lnum = parenlev = continued = 0 - namechars, numchars = string.ascii_letters + '_', '0123456789' - contstr, needcont = '', 0 + numchars = "0123456789" + contstr, needcont = "", 0 contline = None indents = [0] + # If we know we're parsing 3.7+, we can unconditionally parse `async` and + # `await` as keywords. + async_keywords = False if grammar is None else grammar.async_keywords # 'stashed' and 'async_*' are used for async/await parsing stashed = None async_def = False async_def_indent = 0 async_def_nl = False - while 1: # loop over lines in stream + while 1: # loop over lines in stream try: line = readline() except StopIteration: - line = '' + line = "" lnum = lnum + 1 pos, max = 0, len(line) - if contstr: # continued string + if contstr: # continued string if not line: raise TokenError("EOF in multi-line string", strstart) endmatch = endprog.match(line) if endmatch: pos = end = endmatch.end(0) - yield (STRING, contstr + line[:end], - strstart, (lnum, end), contline + line) - contstr, needcont = '', 0 + yield ( + STRING, + contstr + line[:end], + strstart, + (lnum, end), + contline + line, + ) + contstr, needcont = "", 0 contline = None - elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n': - yield (ERRORTOKEN, contstr + line, - strstart, (lnum, len(line)), contline) - contstr = '' + elif needcont and line[-2:] != "\\\n" and line[-3:] != "\\\r\n": + yield ( + ERRORTOKEN, + contstr + line, + strstart, + (lnum, len(line)), + contline, + ) + contstr = "" contline = None continue else: @@ -416,41 +447,53 @@ def generate_tokens(readline): continue elif parenlev == 0 and not continued: # new statement - if not line: break + if not line: + break column = 0 - while pos < max: # measure leading whitespace - if line[pos] == ' ': column = column + 1 - elif line[pos] == '\t': column = (column//tabsize + 1)*tabsize - elif line[pos] == '\f': column = 0 - else: break + while pos < max: # measure leading whitespace + if line[pos] == " ": + column = column + 1 + elif line[pos] == "\t": + column = (column // tabsize + 1) * tabsize + elif line[pos] == "\f": + column = 0 + else: + break pos = pos + 1 - if pos == max: break + if pos == max: + break if stashed: yield stashed stashed = None - if line[pos] in '#\r\n': # skip comments or blank lines - if line[pos] == '#': - comment_token = line[pos:].rstrip('\r\n') - nl_pos = pos + len(comment_token) - yield (COMMENT, comment_token, - (lnum, pos), (lnum, pos + len(comment_token)), line) - yield (NL, line[nl_pos:], - (lnum, nl_pos), (lnum, len(line)), line) - else: - yield ((NL, COMMENT)[line[pos] == '#'], line[pos:], - (lnum, pos), (lnum, len(line)), line) + if line[pos] in "\r\n": # skip blank lines + yield (NL, line[pos:], (lnum, pos), (lnum, len(line)), line) + continue + + if line[pos] == "#": # skip comments + comment_token = line[pos:].rstrip("\r\n") + nl_pos = pos + len(comment_token) + yield ( + COMMENT, + comment_token, + (lnum, pos), + (lnum, pos + len(comment_token)), + line, + ) + yield (NL, line[nl_pos:], (lnum, nl_pos), (lnum, len(line)), line) continue - if column > indents[-1]: # count indents or dedents + if column > indents[-1]: # count indents indents.append(column) yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line) - while column < indents[-1]: + + while column < indents[-1]: # count dedents if column not in indents: raise IndentationError( "unindent does not match any outer indentation level", - ("", lnum, pos, line)) + ("", lnum, pos, line), + ) indents = indents[:-1] if async_def and async_def_indent >= indents[-1]: @@ -458,29 +501,30 @@ def generate_tokens(readline): async_def_nl = False async_def_indent = 0 - yield (DEDENT, '', (lnum, pos), (lnum, pos), line) + yield (DEDENT, "", (lnum, pos), (lnum, pos), line) if async_def and async_def_nl and async_def_indent >= indents[-1]: async_def = False async_def_nl = False async_def_indent = 0 - else: # continued statement + else: # continued statement if not line: raise TokenError("EOF in multi-line statement", (lnum, 0)) continued = 0 while pos < max: pseudomatch = pseudoprog.match(line, pos) - if pseudomatch: # scan for tokens + if pseudomatch: # scan for tokens start, end = pseudomatch.span(1) spos, epos, pos = (lnum, start), (lnum, end), end token, initial = line[start:end], line[start] - if initial in numchars or \ - (initial == '.' and token != '.'): # ordinary number + if initial in numchars or ( + initial == "." and token != "." + ): # ordinary number yield (NUMBER, token, spos, epos, line) - elif initial in '\r\n': + elif initial in "\r\n": newline = NEWLINE if parenlev > 0: newline = NL @@ -491,7 +535,7 @@ def generate_tokens(readline): stashed = None yield (newline, token, spos, epos, line) - elif initial == '#': + elif initial == "#": assert not token.endswith("\n") if stashed: yield stashed @@ -500,7 +544,7 @@ def generate_tokens(readline): elif token in triple_quoted: endprog = endprogs[token] endmatch = endprog.match(line, pos) - if endmatch: # all on one line + if endmatch: # all on one line pos = endmatch.end(0) token = line[start:pos] if stashed: @@ -508,48 +552,61 @@ def generate_tokens(readline): stashed = None yield (STRING, token, spos, (lnum, pos), line) else: - strstart = (lnum, start) # multiple lines + strstart = (lnum, start) # multiple lines contstr = line[start:] contline = line break - elif initial in single_quoted or \ - token[:2] in single_quoted or \ - token[:3] in single_quoted: - if token[-1] == '\n': # continued string + 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 = (endprogs[initial] or endprogs[token[1]] or - endprogs[token[2]]) + endprog = ( + endprogs[initial] + or endprogs[token[1]] + or endprogs[token[2]] + ) contstr, needcont = line[start:], 1 contline = line break - else: # ordinary string + else: # ordinary string if stashed: yield stashed stashed = None yield (STRING, token, spos, epos, line) - elif initial in namechars: # ordinary name - if token in ('async', 'await'): - if async_def: - yield (ASYNC if token == 'async' else AWAIT, - token, spos, epos, line) + elif initial.isidentifier(): # ordinary name + if token in ("async", "await"): + if async_keywords or async_def: + yield ( + ASYNC if token == "async" else AWAIT, + token, + spos, + epos, + line, + ) continue tok = (NAME, token, spos, epos, line) - if token == 'async' and not stashed: + if token == "async" and not stashed: stashed = tok continue - if token == 'def': - if (stashed - and stashed[0] == NAME - and stashed[1] == 'async'): + if token in ("def", "for"): + if stashed and stashed[0] == NAME and stashed[1] == "async": - async_def = True - async_def_indent = indents[-1] + if token == "def": + async_def = True + async_def_indent = indents[-1] - yield (ASYNC, stashed[1], - stashed[2], stashed[3], - stashed[4]) + yield ( + ASYNC, + stashed[1], + stashed[2], + stashed[3], + stashed[4], + ) stashed = None if stashed: @@ -557,7 +614,7 @@ def generate_tokens(readline): stashed = None yield tok - elif initial == '\\': # continued stmt + elif initial == "\\": # continued stmt # This yield is new; needed for better idempotency: if stashed: yield stashed @@ -565,26 +622,31 @@ def generate_tokens(readline): yield (NL, token, spos, (lnum, pos), line) continued = 1 else: - if initial in '([{': parenlev = parenlev + 1 - elif initial in ')]}': parenlev = parenlev - 1 + if initial in "([{": + parenlev = parenlev + 1 + elif initial in ")]}": + parenlev = parenlev - 1 if stashed: yield stashed stashed = None yield (OP, token, spos, epos, line) else: - yield (ERRORTOKEN, line[pos], - (lnum, pos), (lnum, pos+1), line) + yield (ERRORTOKEN, line[pos], (lnum, pos), (lnum, pos + 1), line) pos = pos + 1 if stashed: yield stashed stashed = None - for indent in indents[1:]: # pop remaining indent levels - yield (DEDENT, '', (lnum, 0), (lnum, 0), '') - yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '') + for indent in indents[1:]: # pop remaining indent levels + yield (DEDENT, "", (lnum, 0), (lnum, 0), "") + yield (ENDMARKER, "", (lnum, 0), (lnum, 0), "") -if __name__ == '__main__': # testing + +if __name__ == "__main__": # testing import sys - if len(sys.argv) > 1: tokenize(open(sys.argv[1]).readline) - else: tokenize(sys.stdin.readline) + + if len(sys.argv) > 1: + tokenize(open(sys.argv[1]).readline) + else: + tokenize(sys.stdin.readline)