Python tokenize.NL属性代码示例

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def _find_logical(source_lines):
    # Make a variable which is the index of all the starts of lines.
    logical_start = []
    logical_end = []
    last_newline = True
    parens = 0
    for t in generate_tokens(''.join(source_lines)):
        if t[0] in [tokenize.COMMENT, tokenize.DEDENT,
                    tokenize.INDENT, tokenize.NL,
                    tokenize.ENDMARKER]:
            continue
        if not parens and t[0] in [tokenize.NEWLINE, tokenize.SEMI]:
            last_newline = True
            logical_end.append((t[3][0] - 1, t[2][1]))
            continue
        if last_newline and not parens:
            logical_start.append((t[2][0] - 1, t[2][1]))
            last_newline = False
        if t[0] == tokenize.OP:
            if t[1] in '([{':
                parens += 1
            elif t[1] in '}])':
                parens -= 1
    return (logical_start, logical_end) 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def _has_valid_type_annotation(self, tokens, i):
        """Extended check of PEP-484 type hint presence"""
        if not self._inside_brackets("("):
            return False
        # token_info
        # type string start end line
        #  0      1     2    3    4
        bracket_level = 0
        for token in tokens[i - 1 :: -1]:
            if token[1] == ":":
                return True
            if token[1] == "(":
                return False
            if token[1] == "]":
                bracket_level += 1
            elif token[1] == "[":
                bracket_level -= 1
            elif token[1] == ",":
                if not bracket_level:
                    return False
            elif token[1] in (".", "..."):
                continue
            elif token[0] not in (tokenize.NAME, tokenize.STRING, tokenize.NL):
                return False
        return False 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def process_tokens(self, tokens):
        encoding = "ascii"
        for i, (tok_type, token, start, _, line) in enumerate(tokens):
            if tok_type == tokenize.ENCODING:
                # this is always the first token processed
                encoding = token
            elif tok_type == tokenize.STRING:
                # 'token' is the whole un-parsed token; we can look at the start
                # of it to see whether it's a raw or unicode string etc.
                self.process_string_token(token, start[0])
                # We figure the next token, ignoring comments & newlines:
                j = i + 1
                while j < len(tokens) and tokens[j].type in (
                    tokenize.NEWLINE,
                    tokenize.NL,
                    tokenize.COMMENT,
                ):
                    j += 1
                next_token = tokens[j] if j < len(tokens) else None
                if encoding != "ascii":
                    # We convert `tokenize` character count into a byte count,
                    # to match with astroid `.col_offset`
                    start = (start[0], len(line[: start[1]].encode(encoding)))
                self.string_tokens[start] = (str_eval(token), next_token) 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def __waiting(self, ttype, tstring, lineno):
        opts = self.__options
        # Do docstring extractions, if enabled
        if opts.docstrings and not opts.nodocstrings.get(self.__curfile):
            # module docstring?
            if self.__freshmodule:
                if ttype == tokenize.STRING:
                    self.__addentry(safe_eval(tstring), lineno, isdocstring=1)
                    self.__freshmodule = 0
                elif ttype not in (tokenize.COMMENT, tokenize.NL):
                    self.__freshmodule = 0
                return
            # class docstring?
            if ttype == tokenize.NAME and tstring in ('class', 'def'):
                self.__state = self.__suiteseen
                return
        if ttype == tokenize.NAME and tstring in opts.keywords:
            self.__state = self.__keywordseen 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def __openseen(self, ttype, tstring, lineno):
        if ttype == tokenize.OP and tstring == ')':
            # We've seen the last of the translatable strings.  Record the
            # line number of the first line of the strings and update the list
            # of messages seen.  Reset state for the next batch.  If there
            # were no strings inside _(), then just ignore this entry.
            if self.__data:
                self.__addentry(EMPTYSTRING.join(self.__data))
            self.__state = self.__waiting
        elif ttype == tokenize.STRING:
            self.__data.append(safe_eval(tstring))
        elif ttype not in [tokenize.COMMENT, token.INDENT, token.DEDENT,
                           token.NEWLINE, tokenize.NL]:
            # warn if we see anything else than STRING or whitespace
            print >> sys.stderr, _(
                '*** %(file)s:%(lineno)s: Seen unexpected token "%(token)s"'
                ) % {
                'token': tstring,
                'file': self.__curfile,
                'lineno': self.__lineno
                }
            self.__state = self.__waiting 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def remove_docstrings(tokens):
    """
    Removes docstrings from *tokens* which is expected to be a list equivalent
    of `tokenize.generate_tokens()` (so we can update in-place).
    """
    prev_tok_type = None
    for index, tok in enumerate(tokens):
        token_type = tok[0]
        if token_type == tokenize.STRING:
            if prev_tok_type == tokenize.INDENT:
                # Definitely a docstring
                tokens[index][1] = ''  # Remove it
                # Remove the leftover indentation and newline:
                tokens[index - 1][1] = ''
                tokens[index - 2][1] = ''
            elif prev_tok_type == tokenize.NL:
                # This captures whole-module docstrings:
                if tokens[index + 1][0] == tokenize.NEWLINE:
                    tokens[index][1] = ''
                    # Remove the trailing newline:
                    tokens[index + 1][1] = ''
        prev_tok_type = token_type 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def test_tokenizing(self):
    # Test that we produce meaningful tokens on initialization.
    source = "import re  # comment\n\nfoo = 'bar'\n"
    atok = asttokens.ASTTokens(source)
    self.assertEqual(atok.text, source)
    self.assertEqual([str(t) for t in atok.tokens], [
      "NAME:'import'",
      "NAME:'re'",
      "COMMENT:'# comment'",
      "NEWLINE:'\\n'",
      "NL:'\\n'",
      "NAME:'foo'",
      "OP:'='",
      'STRING:"\'bar\'"',
      "NEWLINE:'\\n'",
      "ENDMARKER:''"
    ])

    self.assertEqual(atok.tokens[5].type, token.NAME)
    self.assertEqual(atok.tokens[5].string, 'foo')
    self.assertEqual(atok.tokens[5].index, 5)
    self.assertEqual(atok.tokens[5].startpos, 22)
    self.assertEqual(atok.tokens[5].endpos, 25) 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def tokeneater(self, type, token, srowcol, erowcol, line):
        if not self.started:
            # look for the first "def", "class" or "lambda"
            if token in ("def", "class", "lambda"):
                if token == "lambda":
                    self.islambda = True
                self.started = True
            self.passline = True    # skip to the end of the line
        elif type == tokenize.NEWLINE:
            self.passline = False   # stop skipping when a NEWLINE is seen
            self.last = srowcol[0]
            if self.islambda:       # lambdas always end at the first NEWLINE
                raise EndOfBlock
        elif self.passline:
            pass
        elif type == tokenize.INDENT:
            self.indent = self.indent + 1
            self.passline = True
        elif type == tokenize.DEDENT:
            self.indent = self.indent - 1
            # the end of matching indent/dedent pairs end a block
            # (note that this only works for "def"/"class" blocks,
            #  not e.g. for "if: else:" or "try: finally:" blocks)
            if self.indent <= 0:
                raise EndOfBlock
        elif self.indent == 0 and type not in (tokenize.COMMENT, tokenize.NL):
            # any other token on the same indentation level end the previous
            # block as well, except the pseudo-tokens COMMENT and NL.
            raise EndOfBlock 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def is_single_token(token_number, tokens):
    '''Is this a single token matching token_number followed by ENDMARKER or NL
    tokens.
    '''
    return (TOKEN_NUMBER(tokens[0]) == token_number and
            all(TOKEN_NUMBER(t) in (tokenize.ENDMARKER, tokenize.NL)
                for t in tokens[1:])) 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def is_trailing_comma(tokens, index):
    """Check if the given token is a trailing comma

    :param tokens: Sequence of modules tokens
    :type tokens: list[tokenize.TokenInfo]
    :param int index: Index of token under check in tokens
    :returns: True if the token is a comma which trails an expression
    :rtype: bool
    """
    token = tokens[index]
    if token.exact_type != tokenize.COMMA:
        return False
    # Must have remaining tokens on the same line such as NEWLINE
    left_tokens = itertools.islice(tokens, index + 1, None)
    same_line_remaining_tokens = list(itertools.takewhile(
        lambda other_token, _token=token: other_token.start[0] == _token.start[0],
        left_tokens
    ))
    # Note: If the newline is tokenize.NEWLINE and not tokenize.NL
    # then the newline denotes the end of expression
    is_last_element = all(
        other_token.type in (tokenize.NEWLINE, tokenize.COMMENT)
        for other_token in same_line_remaining_tokens
    )
    if not same_line_remaining_tokens or not is_last_element:
        return False
    def get_curline_index_start():
        """Get the index denoting the start of the current line"""
        for subindex, token in enumerate(reversed(tokens[:index])):
            # See Lib/tokenize.py and Lib/token.py in cpython for more info
            if token.type in (tokenize.NEWLINE, tokenize.NL):
                return index - subindex
        return 0
    curline_start = get_curline_index_start()
    for prevtoken in tokens[curline_start:index]:
        if '=' in prevtoken.string:
            return True
    return False 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def _token_followed_by_eol(tokens, position):
    return (tokens.type(position+1) == tokenize.NL or
            tokens.type(position+1) == tokenize.COMMENT and
            tokens.type(position+2) == tokenize.NL) 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def next_physical_line(self):
        """Prepares the tracker for a new physical line (NL)."""
        self._line_start = -1
        self._is_block_opener = False 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def parse_docstring(self):
        """Parse a single docstring and return its value."""
        self.log.debug("parsing docstring, token is %r (%s)",
                       self.current.kind, self.current.value)
        while self.current.kind in (tk.COMMENT, tk.NEWLINE, tk.NL):
            self.stream.move()
            self.log.debug("parsing docstring, token is %r (%s)",
                           self.current.kind, self.current.value)
        if self.current.kind == tk.STRING:
            docstring = self.current.value
            self.stream.move()
            return docstring
        return None 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def parse_all(self):
        """Parse the __all__ definition in a module."""
        assert self.current.value == '__all__'
        self.consume(tk.NAME)
        if self.current.value != '=':
            raise AllError('Could not evaluate contents of __all__. ')
        self.consume(tk.OP)
        if self.current.value not in '([':
            raise AllError('Could not evaluate contents of __all__. ')
        self.consume(tk.OP)

        self.all = []
        all_content = "("
        while self.current.kind != tk.OP or self.current.value not in ")]":
            if self.current.kind in (tk.NL, tk.COMMENT):
                pass
            elif (self.current.kind == tk.STRING or
                    self.current.value == ','):
                all_content += self.current.value
            else:
                raise AllError('Unexpected token kind in  __all__: {!r}. '
                               .format(self.current.kind))
            self.stream.move()
        self.consume(tk.OP)
        all_content += ")"
        try:
            self.all = eval(all_content, {})
        except BaseException as e:
            raise AllError('Could not evaluate contents of __all__.'
                           '\bThe value was {}. The exception was:\n{}'
                           .format(all_content, e)) 

# 需要导入模块: import tokenize [as 别名]
# 或者: from tokenize import NL [as 别名]
def whitespace_before_comment(logical_line, tokens):
    r"""Separate inline comments by at least two spaces.

    An inline comment is a comment on the same line as a statement.  Inline
    comments should be separated by at least two spaces from the statement.
    They should start with a # and a single space.

    Each line of a block comment starts with a # and a single space
    (unless it is indented text inside the comment).

    Okay: x = x + 1  # Increment x
    Okay: x = x + 1    # Increment x
    Okay: # Block comment
    E261: x = x + 1 # Increment x
    E262: x = x + 1  #Increment x
    E262: x = x + 1  #  Increment x
    E265: #Block comment
    E266: ### Block comment
    """
    prev_end = (0, 0)
    for token_type, text, start, end, line in tokens:
        if token_type == tokenize.COMMENT:
            inline_comment = line[:start[1]].strip()
            if inline_comment:
                if prev_end[0] == start[0] and start[1] < prev_end[1] + 2:
                    yield (prev_end,
                           "E261 at least two spaces before inline comment")
            symbol, sp, comment = text.partition(' ')
            bad_prefix = symbol not in '#:' and (symbol.lstrip('#')[:1] or '#')
            if inline_comment:
                if bad_prefix or comment[:1] in WHITESPACE:
                    yield start, "E262 inline comment should start with '# '"
            elif bad_prefix and (bad_prefix != '!' or start[0] > 1):
                if bad_prefix != '#':
                    yield start, "E265 block comment should start with '# '"
                elif comment:
                    yield start, "E266 too many leading '#' for block comment"
        elif token_type != tokenize.NL:
            prev_end = end