comparison mercurial/revsetlang.py @ 37775:03d7f885d5f2

revsetlang: do not pass in non-bytes to parse()

Since parse() isn't a simple function, we shouldn't expect it would raise
TypeError or ValueError for invalid inputs. Before, TypeError was raised
at 'if pos != len(spec)', which was quite late to report an error.

This patch also makes tokenize() detect invalid object before converting
it to a py3-safe bytes.

Spotted while adding the 'revset(...)' hack to _parsewith().

37774:d6970628b95f

    Check that @ is a valid unquoted token character (issue3686):
    >>> list(tokenize(b"@::"))
    [('symbol', '@', 0), ('::', None, 1), ('end', None, 3)]

    '''
    program = pycompat.bytestr(program)
    if syminitletters is None:
        syminitletters = _syminitletters
    if symletters is None:
        symletters = _symletters

    if c == 'd':
        return '%d' % int(arg)
    elif c == 's':
        return _quote(arg)
    elif c == 'r':
        parse(arg) # make sure syntax errors are confined
        return '(%s)' % arg
    elif c == 'n':
        return _quote(node.hex(arg))
    elif c == 'b':

37775:03d7f885d5f2

    Check that @ is a valid unquoted token character (issue3686):
    >>> list(tokenize(b"@::"))
    [('symbol', '@', 0), ('::', None, 1), ('end', None, 3)]

    '''
    if not isinstance(program, bytes):
        raise error.ProgrammingError('revset statement must be bytes, got %r'
                                     % program)
    program = pycompat.bytestr(program)
    if syminitletters is None:
        syminitletters = _syminitletters
    if symletters is None:
        symletters = _symletters

    if c == 'd':
        return '%d' % int(arg)
    elif c == 's':
        return _quote(arg)
    elif c == 'r':
        if not isinstance(arg, bytes):
            raise TypeError
        parse(arg) # make sure syntax errors are confined
        return '(%s)' % arg
    elif c == 'n':
        return _quote(node.hex(arg))
    elif c == 'b':