From 60ad6163440ad67b5e2fa318cc9fd2cdd20d26aa Mon Sep 17 00:00:00 2001 From: adam j hartz Date: Mon, 23 May 2016 01:13:20 -0400 Subject: [PATCH] consolidate tokenizers into a single file --- setup.py | 2 +- xonsh/environ.py | 2 +- .../{tokenize/tokenize_35.py => tokenize.py} | 97 +-- xonsh/tokenize/__init__.py | 6 - xonsh/tokenize/tokenize_34.py | 696 ------------------ 5 files changed, 58 insertions(+), 745 deletions(-) rename xonsh/{tokenize/tokenize_35.py => tokenize.py} (96%) delete mode 100644 xonsh/tokenize/__init__.py delete mode 100644 xonsh/tokenize/tokenize_34.py diff --git a/setup.py b/setup.py index 790e8fc77..fdae19afb 100755 --- a/setup.py +++ b/setup.py @@ -171,7 +171,7 @@ def main(): url='https://github.com/scopatz/xonsh', platforms='Cross Platform', classifiers=['Programming Language :: Python :: 3'], - packages=['xonsh', 'xonsh.ptk', 'xonsh.parsers', 'xonsh.xoreutils', 'xontrib', 'xonsh.tokenize'], + packages=['xonsh', 'xonsh.ptk', 'xonsh.parsers', 'xonsh.xoreutils', 'xontrib'], package_dir={'xonsh': 'xonsh', 'xontrib': 'xontrib'}, package_data={'xonsh': ['*.json'], 'xontrib': ['*.xsh']}, cmdclass=cmdclass diff --git a/xonsh/environ.py b/xonsh/environ.py index c157f66d5..4ae723e48 100644 --- a/xonsh/environ.py +++ b/xonsh/environ.py @@ -213,7 +213,7 @@ DEFAULT_VALUES = { 'XONSH_HISTORY_FILE': os.path.expanduser('~/.xonsh_history.json'), 'XONSH_HISTORY_SIZE': (8128, 'commands'), 'XONSH_LOGIN': False, - 'XONSH_SHOW_TRACEBACK': False, + 'XONSH_SHOW_TRACEBACK': True, 'XONSH_STORE_STDIN': False, 'XONSH_STORE_STDOUT': False, } diff --git a/xonsh/tokenize/tokenize_35.py b/xonsh/tokenize.py similarity index 96% rename from xonsh/tokenize/tokenize_35.py rename to xonsh/tokenize.py index d4d764a60..c792c92b7 100644 --- a/xonsh/tokenize/tokenize_35.py +++ b/xonsh/tokenize.py @@ -1,11 +1,14 @@ """Tokenization help for xonsh programs. -This file is a modified version of tokenize.py form the Python 3.5 standard -library (licensed under the Python Software Foundation License, version 2), -which provides tokenization help for Python programs. +This file is a modified version of tokenize.py form the Python 3.4 and 3.5 +standard libraries (licensed under the Python Software Foundation License, +version 2), which provides tokenization help for Python programs. -It is modified to properly tokenize xonsh's backtick operator and to support -the @$ operator. +It is modified to properly tokenize xonsh code, including backtick regex +path and several xonsh-specific operators. + +A few pieces of this file are specific to the version of Python being used. +To find these pieces, search the PY35. Original file credits: __author__ = 'Ka-Ping Yee ' @@ -23,15 +26,27 @@ import re import sys from token import * +from xonsh.platform import PYTHON_VERSION_INFO + + cookie_re = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)', re.ASCII) blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII) import token __all__ = token.__all__ + ["COMMENT", "tokenize", "detect_encoding", "NL", "untokenize", "ENCODING", "TokenInfo", - "REGEXPATH", "ATDOLLAR", "TokenError"] + "TokenError", 'REGEXPATH', 'ATDOLLAR', 'ATEQUAL', '_tokenize'] del token +PY35 = PYTHON_VERSION_INFO >= (3, 5, 0) +if PY35: + AUGASSIGN_OPS = r"[+\-*/%&@|^=<>]=?" + ADDSPACE_TOKS = (NAME, NUMBER, ASYNC, AWAIT) +else: + AUGASSIGN_OPS = r"[+\-*/%&|^=<>]=?" + ADDSPACE_TOKS = (NAME, NUMBER) + + COMMENT = N_TOKENS tok_name[COMMENT] = 'COMMENT' NL = N_TOKENS + 1 @@ -40,10 +55,13 @@ ENCODING = N_TOKENS + 2 tok_name[ENCODING] = 'ENCODING' N_TOKENS += 3 REGEXPATH = N_TOKENS -tok_name[REGEXPATH] = 'REGEXPATH' +tok_name[N_TOKENS] = 'REGEXPATH' N_TOKENS += 1 ATDOLLAR = N_TOKENS -tok_name[ATDOLLAR] = 'ATDOLLAR' +tok_name[N_TOKENS] = 'ATDOLLAR' +N_TOKENS += 1 +ATEQUAL = N_TOKENS +tok_name[N_TOKENS] = 'ATEQUAL' N_TOKENS += 1 EXACT_TOKEN_TYPES = { '(': LPAR, @@ -152,7 +170,7 @@ RegexPath = r"`[^\n`\\]*(?:\\.[^\n`\\]*)*`" # recognized as two instances of =). Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"!=", r"//=?", r"->", r"@\$", - r"[+\-*/%&@|^=<>]=?", + AUGASSIGN_OPS, r"~") Bracket = '[][(){}]' @@ -292,7 +310,7 @@ class Untokenizer: self.encoding = tokval continue - if toknum in (NAME, NUMBER, ASYNC, AWAIT): + if toknum in ADDSPACE_TOKS: tokval += ' ' # Insert a space between two consecutive strings @@ -464,34 +482,6 @@ def open(filename): raise -def tokenize(readline): - """ - The tokenize() generator requires one argment, readline, which - must be a callable object which provides the same interface as the - readline() method of built-in file objects. Each call to the function - should return one line of input as bytes. Alternately, readline - can be a callable function terminating with StopIteration: - readline = open(myfile, 'rb').__next__ # Example of alternate readline - - The generator produces 5-tuples with these members: the token type; the - token string; a 2-tuple (srow, scol) of ints specifying the row and - column where the token begins in the source; a 2-tuple (erow, ecol) of - ints specifying the row and column where the token ends in the source; - and the line on which the token was found. The line passed is the - logical line; continuation lines are included. - - The first token sequence will always be an ENCODING token - which tells you which encoding was used to decode the bytes stream. - """ - # This import is here to avoid problems when the itertools module is not - # built yet and tokenize is imported. - from itertools import chain, repeat - encoding, consumed = detect_encoding(readline) - rl_gen = iter(readline, b"") - empty = repeat(b"") - return _tokenize(chain(consumed, rl_gen, empty).__next__, encoding) - - def _tokenize(readline, encoding): lnum = parenlev = continued = 0 numchars = '0123456789' @@ -711,6 +701,34 @@ def _tokenize(readline, encoding): yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '') +def tokenize(readline): + """ + The tokenize() generator requires one argment, readline, which + must be a callable object which provides the same interface as the + readline() method of built-in file objects. Each call to the function + should return one line of input as bytes. Alternately, readline + can be a callable function terminating with StopIteration: + readline = open(myfile, 'rb').__next__ # Example of alternate readline + + The generator produces 5-tuples with these members: the token type; the + token string; a 2-tuple (srow, scol) of ints specifying the row and + column where the token begins in the source; a 2-tuple (erow, ecol) of + ints specifying the row and column where the token ends in the source; + and the line on which the token was found. The line passed is the + logical line; continuation lines are included. + + The first token sequence will always be an ENCODING token + which tells you which encoding was used to decode the bytes stream. + """ + # This import is here to avoid problems when the itertools module is not + # built yet and tokenize is imported. + from itertools import chain, repeat + encoding, consumed = detect_encoding(readline) + rl_gen = iter(readline, b"") + empty = repeat(b"") + return _tokenize(chain(consumed, rl_gen, empty).__next__, encoding) + + # An undocumented, backwards compatible, API for all the places in the standard # library that expect to be able to use tokenize with strings def generate_tokens(readline): @@ -775,6 +793,3 @@ def main(): except Exception as err: perror("unexpected error: %s" % err) raise - -if __name__ == "__main__": - main() diff --git a/xonsh/tokenize/__init__.py b/xonsh/tokenize/__init__.py deleted file mode 100644 index 2c5a30940..000000000 --- a/xonsh/tokenize/__init__.py +++ /dev/null @@ -1,6 +0,0 @@ -from xonsh.platform import PYTHON_VERSION_INFO - -if PYTHON_VERSION_INFO >= (3, 5, 0): - from xonsh.tokenize.tokenize_35 import * -else: - from xonsh.tokenize.tokenize_34 import * diff --git a/xonsh/tokenize/tokenize_34.py b/xonsh/tokenize/tokenize_34.py deleted file mode 100644 index cb9a15503..000000000 --- a/xonsh/tokenize/tokenize_34.py +++ /dev/null @@ -1,696 +0,0 @@ -"""Tokenization help for xonsh programs. - -This file is a modified version of tokenize.py form the Python 3.4 standard -library (licensed under the Python Software Foundation License, version 2), -which provides tokenization help for Python programs. - -It is modified to properly tokenize xonsh's backtick operator and to support -the @$ operator. - -Original file credits: - __author__ = 'Ka-Ping Yee ' - __credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, ' - 'Skip Montanaro, Raymond Hettinger, Trent Nelson, ' - 'Michael Foord') -""" - -from codecs import lookup, BOM_UTF8 -import collections -from io import TextIOWrapper -from itertools import chain -import re -import sys -from token import * - -cookie_re = re.compile(r'^[ \t\f]*#.*coding[:=][ \t]*([-\w.]+)', re.ASCII) -blank_re = re.compile(br'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII) - -import token -__all__ = token.__all__ + ["COMMENT", "tokenize", "detect_encoding", - "NL", "untokenize", "ENCODING", "TokenInfo", - "REGEXPATH", "ATDOLLAR", "TokenError"] -del token - -COMMENT = N_TOKENS -tok_name[COMMENT] = 'COMMENT' -NL = N_TOKENS + 1 -tok_name[NL] = 'NL' -ENCODING = N_TOKENS + 2 -tok_name[ENCODING] = 'ENCODING' -N_TOKENS += 3 -REGEXPATH = N_TOKENS -tok_name[REGEXPATH] = 'REGEXPATH' -N_TOKENS += 1 -ATDOLLAR = N_TOKENS -tok_name[ATDOLLAR] = 'ATDOLLAR' -N_TOKENS += 1 -EXACT_TOKEN_TYPES = { - '(': LPAR, - ')': RPAR, - '[': LSQB, - ']': RSQB, - ':': COLON, - ',': COMMA, - ';': SEMI, - '+': PLUS, - '-': MINUS, - '*': STAR, - '/': SLASH, - '|': VBAR, - '&': AMPER, - '<': LESS, - '>': GREATER, - '=': EQUAL, - '.': DOT, - '%': PERCENT, - '{': LBRACE, - '}': RBRACE, - '==': EQEQUAL, - '!=': NOTEQUAL, - '<=': LESSEQUAL, - '>=': GREATEREQUAL, - '~': TILDE, - '^': CIRCUMFLEX, - '<<': LEFTSHIFT, - '>>': RIGHTSHIFT, - '**': DOUBLESTAR, - '+=': PLUSEQUAL, - '-=': MINEQUAL, - '*=': STAREQUAL, - '/=': SLASHEQUAL, - '%=': PERCENTEQUAL, - '&=': AMPEREQUAL, - '|=': VBAREQUAL, - '^=': CIRCUMFLEXEQUAL, - '<<=': LEFTSHIFTEQUAL, - '>>=': RIGHTSHIFTEQUAL, - '**=': DOUBLESTAREQUAL, - '//': DOUBLESLASH, - '//=': DOUBLESLASHEQUAL, - '@': AT, - '@$': ATDOLLAR, -} - -class TokenInfo(collections.namedtuple('TokenInfo', 'type string start end line')): - def __repr__(self): - annotated_type = '%d (%s)' % (self.type, tok_name[self.type]) - return ('TokenInfo(type=%s, string=%r, start=%r, end=%r, line=%r)' % - self._replace(type=annotated_type)) - - @property - def exact_type(self): - if self.type == OP and self.string in EXACT_TOKEN_TYPES: - return EXACT_TOKEN_TYPES[self.string] - else: - return self.type - -def group(*choices): return '(' + '|'.join(choices) + ')' -def any(*choices): return group(*choices) + '*' -def maybe(*choices): return group(*choices) + '?' - -# Note: we use unicode matching for names ("\w") but ascii matching for -# number literals. -Whitespace = r'[ \f\t]*' -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]*)' -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 -Floatnumber = group(Pointfloat, Expfloat) -Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]') -Number = group(Imagnumber, Floatnumber, Intnumber) - -StringPrefix = r'(?:[bB][rR]?|[rR][bB]?|[uU])?' - -# Tail end of ' string. -Single = r"[^'\\]*(?:\\.[^'\\]*)*'" -# Tail end of " string. -Double = r'[^"\\]*(?:\\.[^"\\]*)*"' -# Tail end of ''' string. -Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''" -# Tail end of """ string. -Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""' -Triple = group(StringPrefix + "'''", StringPrefix + '"""') -# Single-line ' or " string. -String = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'", - StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*"') - -# Xonsh-specific Regular Expression Glob Syntax -RegexPath = 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'\.\.\.', r'[:;.,@]') -Funny = group(Operator, Bracket, Special) - -PlainToken = group(Number, Funny, String, Name, RegexPath) -Token = Ignore + PlainToken - -# First (or only) line of ' or " string. -ContStr = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" + - group("'", r'\\\r?\n'), - StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*' + - group('"', r'\\\r?\n')) -PseudoExtras = group(r'\\\r?\n|\Z', Comment, Triple, RegexPath) -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, - "R'''": Single3, 'R"""': 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 - -tabsize = 8 - -class TokenError(Exception): pass - -class StopTokenizing(Exception): pass - - -class Untokenizer: - - def __init__(self): - self.tokens = [] - self.prev_row = 1 - self.prev_col = 0 - self.encoding = None - - def add_whitespace(self, start): - row, col = start - if row < self.prev_row or row == self.prev_row and col < self.prev_col: - raise ValueError("start ({},{}) precedes previous end ({},{})" - .format(row, col, self.prev_row, self.prev_col)) - row_offset = row - self.prev_row - if row_offset: - self.tokens.append("\\\n" * row_offset) - self.prev_col = 0 - col_offset = col - self.prev_col - if col_offset: - self.tokens.append(" " * col_offset) - - def untokenize(self, iterable): - it = iter(iterable) - for t in it: - if len(t) == 2: - self.compat(t, it) - break - tok_type, token, start, end, line = t - if tok_type == ENCODING: - self.encoding = token - continue - if tok_type == ENDMARKER: - break - self.add_whitespace(start) - self.tokens.append(token) - self.prev_row, self.prev_col = end - if tok_type in (NEWLINE, NL): - self.prev_row += 1 - self.prev_col = 0 - return "".join(self.tokens) - - def compat(self, token, iterable): - indents = [] - toks_append = self.tokens.append - startline = token[0] in (NEWLINE, NL) - prevstring = False - - for tok in chain([token], iterable): - toknum, tokval = tok[:2] - if toknum == ENCODING: - self.encoding = tokval - continue - - if toknum in (NAME, NUMBER): - tokval += ' ' - - # Insert a space between two consecutive strings - if toknum == STRING: - if prevstring: - tokval = ' ' + tokval - prevstring = True - else: - prevstring = False - - if toknum == INDENT: - indents.append(tokval) - continue - elif toknum == DEDENT: - indents.pop() - continue - elif toknum in (NEWLINE, NL): - startline = True - elif startline and indents: - toks_append(indents[-1]) - startline = False - toks_append(tokval) - - -def untokenize(iterable): - """Transform tokens back into Python source code. - It returns a bytes object, encoded using the ENCODING - token, which is the first token sequence output by tokenize. - - Each element returned by the iterable must be a token sequence - with at least two elements, a token number and token value. If - only two tokens are passed, the resulting output is poor. - - Round-trip invariant for full input: - Untokenized source will match input source exactly - - Round-trip invariant for limited intput: - # Output bytes will tokenize the back to the input - t1 = [tok[:2] for tok in tokenize(f.readline)] - newcode = untokenize(t1) - readline = BytesIO(newcode).readline - t2 = [tok[:2] for tok in tokenize(readline)] - assert t1 == t2 - """ - ut = Untokenizer() - out = ut.untokenize(iterable) - if ut.encoding is not None: - out = out.encode(ut.encoding) - return out - - -def _get_normal_name(orig_enc): - """Imitates get_normal_name in tokenizer.c.""" - # Only care about the first 12 characters. - 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-")): - return "iso-8859-1" - return orig_enc - -def detect_encoding(readline): - """ - The detect_encoding() function is used to detect the encoding that should - be used to decode a Python source file. It requires one argument, readline, - in the same way as the tokenize() generator. - - It will call readline a maximum of twice, and return the encoding used - (as a string) and a list of any lines (left as bytes) it has read in. - - It detects the encoding from the presence of a utf-8 bom or an encoding - cookie as specified in pep-0263. If both a bom and a cookie are present, - but disagree, a SyntaxError will be raised. If the encoding cookie is an - invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found, - 'utf-8-sig' is returned. - - If no encoding is specified, then the default of 'utf-8' will be returned. - """ - try: - filename = readline.__self__.name - except AttributeError: - filename = None - bom_found = False - encoding = None - default = 'utf-8' - def read_or_stop(): - try: - return readline() - except StopIteration: - return b'' - - def find_cookie(line): - try: - # Decode as UTF-8. Either the line is an encoding declaration, - # in which case it should be pure ASCII, or it must be UTF-8 - # per default encoding. - line_string = line.decode('utf-8') - except UnicodeDecodeError: - msg = "invalid or missing encoding declaration" - if filename is not None: - msg = '{} for {!r}'.format(msg, filename) - raise SyntaxError(msg) - - match = cookie_re.match(line_string) - if not match: - return None - encoding = _get_normal_name(match.group(1)) - try: - codec = lookup(encoding) - except LookupError: - # This behaviour mimics the Python interpreter - if filename is None: - msg = "unknown encoding: " + encoding - else: - msg = "unknown encoding for {!r}: {}".format(filename, - encoding) - raise SyntaxError(msg) - - if bom_found: - if encoding != 'utf-8': - # This behaviour mimics the Python interpreter - if filename is None: - msg = 'encoding problem: utf-8' - else: - msg = 'encoding problem for {!r}: utf-8'.format(filename) - raise SyntaxError(msg) - encoding += '-sig' - return encoding - - first = read_or_stop() - if first.startswith(BOM_UTF8): - bom_found = True - first = first[3:] - default = 'utf-8-sig' - if not first: - return default, [] - - encoding = find_cookie(first) - if encoding: - return encoding, [first] - if not blank_re.match(first): - return default, [first] - - second = read_or_stop() - if not second: - return default, [first] - - encoding = find_cookie(second) - if encoding: - return encoding, [first, second] - - return default, [first, second] - - -_builtin_open = open - -def open(filename): - """Open a file in read only mode using the encoding detected by - detect_encoding(). - """ - buffer = _builtin_open(filename, 'rb') - encoding, lines = detect_encoding(buffer.readline) - buffer.seek(0) - text = TextIOWrapper(buffer, encoding, line_buffering=True) - text.mode = 'r' - return text - - -def tokenize(readline): - """ - The tokenize() generator requires one argment, readline, which - must be a callable object which provides the same interface as the - readline() method of built-in file objects. Each call to the function - should return one line of input as bytes. Alternately, readline - can be a callable function terminating with StopIteration: - readline = open(myfile, 'rb').__next__ # Example of alternate readline - - The generator produces 5-tuples with these members: the token type; the - token string; a 2-tuple (srow, scol) of ints specifying the row and - column where the token begins in the source; a 2-tuple (erow, ecol) of - ints specifying the row and column where the token ends in the source; - and the line on which the token was found. The line passed is the - logical line; continuation lines are included. - - The first token sequence will always be an ENCODING token - which tells you which encoding was used to decode the bytes stream. - """ - # This import is here to avoid problems when the itertools module is not - # built yet and tokenize is imported. - from itertools import chain, repeat - encoding, consumed = detect_encoding(readline) - rl_gen = iter(readline, b"") - empty = repeat(b"") - return _tokenize(chain(consumed, rl_gen, empty).__next__, encoding) - - -def _tokenize(readline, encoding): - lnum = parenlev = continued = 0 - numchars = '0123456789' - contstr, needcont = '', 0 - contline = None - indents = [0] - - if encoding is not None: - if encoding == "utf-8-sig": - # BOM will already have been stripped. - encoding = "utf-8" - yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '') - while True: # loop over lines in stream - try: - line = readline() - except StopIteration: - line = b'' - - if encoding is not None: - line = line.decode(encoding) - lnum += 1 - pos, max = 0, len(line) - - 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 TokenInfo(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 TokenInfo(ERRORTOKEN, contstr + line, - strstart, (lnum, len(line)), contline) - contstr = '' - contline = None - continue - else: - contstr = contstr + line - contline = contline + line - continue - - elif parenlev == 0 and not continued: # new statement - if not line: break - column = 0 - while pos < max: # measure leading whitespace - if line[pos] == ' ': - column += 1 - elif line[pos] == '\t': - column = (column//tabsize + 1)*tabsize - elif line[pos] == '\f': - column = 0 - else: - break - pos += 1 - if pos == max: - break - - 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 TokenInfo(COMMENT, comment_token, - (lnum, pos), (lnum, pos + len(comment_token)), line) - yield TokenInfo(NL, line[nl_pos:], - (lnum, nl_pos), (lnum, len(line)), line) - else: - yield TokenInfo((NL, COMMENT)[line[pos] == '#'], line[pos:], - (lnum, pos), (lnum, len(line)), line) - continue - - if column > indents[-1]: # count indents or dedents - indents.append(column) - yield TokenInfo(INDENT, line[:pos], (lnum, 0), (lnum, pos), line) - while column < indents[-1]: - if column not in indents: - raise IndentationError( - "unindent does not match any outer indentation level", - ("", lnum, pos, line)) - indents = indents[:-1] - yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line) - - else: # continued statement - if not line: - raise TokenError("EOF in multi-line statement", (lnum, 0)) - continued = 0 - - while pos < max: - pseudomatch = _compile(PseudoToken).match(line, pos) - if pseudomatch: # scan for tokens - start, end = pseudomatch.span(1) - spos, epos, pos = (lnum, start), (lnum, end), end - if start == end: - continue - token, initial = line[start:end], line[start] - - if (initial in numchars or # ordinary number - (initial == '.' and token != '.' and token != '...')): - yield TokenInfo(NUMBER, token, spos, epos, line) - elif initial in '\r\n': - yield TokenInfo(NL if parenlev > 0 else NEWLINE, - token, spos, epos, line) - elif initial == '#': - assert not token.endswith("\n") - yield TokenInfo(COMMENT, token, spos, epos, line) - elif initial == '`': - # Xonsh-specific Regex Globbing - yield TokenInfo(REGEXPATH, token, spos, epos, line) - elif token in triple_quoted: - endprog = _compile(endpats[token]) - endmatch = endprog.match(line, pos) - if endmatch: # all on one line - pos = endmatch.end(0) - token = line[start:pos] - yield TokenInfo(STRING, token, spos, (lnum, pos), line) - else: - 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 - strstart = (lnum, start) - endprog = _compile(endpats[initial] or - endpats[token[1]] or - endpats[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 - yield TokenInfo(NAME, token, spos, epos, line) - elif initial == '\\': # continued stmt - continued = 1 - else: - if initial in '([{': - parenlev += 1 - elif initial in ')]}': - parenlev -= 1 - yield TokenInfo(OP, token, spos, epos, line) - else: - yield TokenInfo(ERRORTOKEN, line[pos], - (lnum, pos), (lnum, pos+1), line) - pos += 1 - - for indent in indents[1:]: # pop remaining indent levels - yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '') - yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '') - - -# An undocumented, backwards compatible, API for all the places in the standard -# library that expect to be able to use tokenize with strings -def generate_tokens(readline): - return _tokenize(readline, None) - -def main(): - import argparse - - # Helper error handling routines - def perror(message): - print(message, file=sys.stderr) - - def error(message, filename=None, location=None): - if location: - args = (filename,) + location + (message,) - perror("%s:%d:%d: error: %s" % args) - elif filename: - perror("%s: error: %s" % (filename, message)) - else: - perror("error: %s" % message) - sys.exit(1) - - # Parse the arguments and options - parser = argparse.ArgumentParser(prog='python -m tokenize') - parser.add_argument(dest='filename', nargs='?', - metavar='filename.py', - help='the file to tokenize; defaults to stdin') - parser.add_argument('-e', '--exact', dest='exact', action='store_true', - help='display token names using the exact type') - args = parser.parse_args() - - try: - # Tokenize the input - if args.filename: - filename = args.filename - with _builtin_open(filename, 'rb') as f: - tokens = list(tokenize(f.readline)) - else: - filename = "" - tokens = _tokenize(sys.stdin.readline, None) - - # Output the tokenization - for token in tokens: - token_type = token.type - if args.exact: - token_type = token.exact_type - token_range = "%d,%d-%d,%d:" % (token.start + token.end) - print("%-20s%-15s%-15r" % - (token_range, tok_name[token_type], token.string)) - except IndentationError as err: - line, column = err.args[1][1:3] - error(err.args[0], filename, (line, column)) - except TokenError as err: - line, column = err.args[1] - error(err.args[0], filename, (line, column)) - except SyntaxError as err: - error(err, filename) - except OSError as err: - error(err) - except KeyboardInterrupt: - print("interrupted\n") - except Exception as err: - perror("unexpected error: %s" % err) - raise - -if __name__ == "__main__": - main()