Class DocTestParser

Lib/doctest.py:603–831

A class used to parse strings containing doctest examples.

######################################################################

class DocTestParser:
    """
    A class used to parse strings containing doctest examples.
    """
    # This regular expression is used to find doctest examples in a
    # string.  It defines three groups: `source` is the source code
    # (including leading indentation and prompts); `indent` is the
    # indentation of the first (PS1) line of the source code; and
    # `want` is the expected output (including leading indentation).
    _EXAMPLE_RE = re.compile(r'''
        # Source consists of a PS1 line followed by zero or more PS2 lines.
        (?P<source>
            (?:^(?P<indent> [ ]*) >>>    .*)    # PS1 line
            (?:\n           [ ]*  \.\.\. .*)*)  # PS2 lines
        \n?
        # Want consists of any non-blank lines that do not start with PS1.
        (?P<want> (?:(?![ ]*$)    # Not a blank line
                     (?![ ]*>>>)  # Not a line starting with PS1
                     .+$\n?       # But any other line
                  )*)
        ''&#x27;, re.MULTILINE | re.VERBOSE)

    # A regular expression for handling `want` strings that contain
    # expected exceptions.  It divides `want` into three pieces:
    #    - the traceback header line (`hdr`)
    #    - the traceback stack (`stack`)
    #    - the exception message (`msg`), as generated by
    #      traceback.format_exception_only()
    # `msg` may have multiple lines.  We assume/require that the
    # exception message is the first non-indented line starting with a word
    # character following the traceback header line.
    _EXCEPTION_RE = re.compile(r"""
        # Grab the traceback header.  Different versions of Python have
        # said different things on the first traceback line.
        ^(?P<hdr> Traceback\ \(
            (?: most\ recent\ call\ last
            |   innermost\ last
            ) \) :
        )
        \s* $                # toss trailing whitespace on the header.
        (?P<stack> .*?)      # don't blink: absorb stuff until...
        ^ (?P<msg> \w+ .*)   #     a line *starts* with alphanum.
        """, re.VERBOSE | re.MULTILINE | re.DOTALL)

    # A callable returning a true value iff its argument is a blank line
    # or contains a single comment.
    _IS_BLANK_OR_COMMENT = re.compile(r'^[ ]*(#.*)?$').match

    def parse(self, string, name='<string>'):
        """
        Divide the given string into examples and intervening text,
        and return them as a list of alternating Examples and strings.
        Line numbers for the Examples are 0-based.  The optional
        argument `name` is a name identifying this string, and is only
        used for error messages.
        """
        string = string.expandtabs()
        # If all lines begin with the same indentation, then strip it.