states.py

Requirement =====================================================================================

        if text.startswith('pep-'):
            pepnum = int(match.group('pepnum1'))
        elif text.startswith('PEP'):
            pepnum = int(match.group('pepnum2'))
        else:
            raise MarkupMismatch
        ref = self.document.settings.pep_base_url + self.pep_url % pepnum
        unescaped = unescape(text, 0)
        return [nodes.reference(unescape(text, 1), unescaped, refuri=ref)]

    rfc_url = 'rfc%d.html'

    def rfc_reference(self, match, lineno):
        text = match.group(0)
        if text.startswith('RFC'):
            rfcnum = int(match.group('rfcnum'))
            ref = self.document.settings.rfc_base_url + self.rfc_url % rfcnum
        else:
            raise MarkupMismatch
        unescaped = unescape(text, 0)
        return [nodes.reference(unescape(text, 1), unescaped, refuri=ref)]

    def implicit_inline(self, text, lineno):
        """
        Check each of the patterns in `self.implicit_dispatch` for a match,
        and dispatch to the stored method for the pattern.  Recursively check
        the text before and after the match.  Return a list of `nodes.Text`
        and inline element nodes.
        """
        if not text:
            return []
        for pattern, method in self.implicit_dispatch:
            match = pattern.search(text)
            if match:
                try:
                    # Must recurse on strings before *and* after the match;
                    # there may be multiple patterns.
                    return (self.implicit_inline(text[:match.start()], lineno)
                            + method(match, lineno) +
                            self.implicit_inline(text[match.end():], lineno))
                except MarkupMismatch:
                    pass
        return [nodes.Text(unescape(text), rawsource=unescape(text, 1))]

    dispatch = {'*': emphasis,
                '**': strong,
                '`': interpreted_or_phrase_ref,
                '``': literal,
                '_`': inline_internal_target,
                ']_': footnote_reference,
                '|': substitution_reference,
                '_': reference,
                '__': anonymous_reference}


def _loweralpha_to_int(s, _zero=(ord('a')-1)):
    return ord(s) - _zero

def _upperalpha_to_int(s, _zero=(ord('A')-1)):
    return ord(s) - _zero

def _lowerroman_to_int(s):
    return roman.fromRoman(s.upper())


class Body(RSTState):

    """
    Generic classifier of the first line of a block.
    """

    double_width_pad_char = tableparser.TableParser.double_width_pad_char
    """Padding character for East Asian double-width text."""

    enum = Struct()
    """Enumerated list parsing information."""

    enum.formatinfo = {
          'parens': Struct(prefix='(', suffix=')', start=1, end=-1),
          'rparen': Struct(prefix='', suffix=')', start=0, end=-1),
          'period': Struct(prefix='', suffix='.', start=0, end=-1)}
    enum.formats = enum.formatinfo.keys()
    enum.sequences = ['arabic', 'loweralpha', 'upperalpha',
                      'lowerroman', 'upperroman'] # ORDERED!
    enum.sequencepats = {'arabic': '[0-9]+',
                         'loweralpha': '[a-z]',
                         'upperalpha': '[A-Z]',
                         'lowerroman': '[ivxlcdm]+',
                         'upperroman': '[IVXLCDM]+',}
    enum.converters = {'arabic': int,
                       'loweralpha': _loweralpha_to_int,
                       'upperalpha': _upperalpha_to_int,
                       'lowerroman': _lowerroman_to_int,
                       'upperroman': roman.fromRoman}

    enum.sequenceregexps = {}
    for sequence in enum.sequences:
        enum.sequenceregexps[sequence] = re.compile(
              enum.sequencepats[sequence] + '$')

    grid_table_top_pat = re.compile(r'\+-[-+]+-\+ *$')
    """Matches the top (& bottom) of a full table)."""

    simple_table_top_pat = re.compile('=+( +=+)+ *$')
    """Matches the top of a simple table."""

    simple_table_border_pat = re.compile('=+[ =]*$')
    """Matches the bottom & header bottom of a simple table."""

    pats = {}
    """Fragments of patterns used by transitions."""

    pats['nonalphanum7bit'] = '[!-/:-@[-`{-~]'
    pats['alpha'] = '[a-zA-Z]'
    pats['alphanum'] = '[a-zA-Z0-9]'
    pats['alphanumplus'] = '[a-zA-Z0-9_-]'
    pats['enum'] = ('(%(arabic)s|%(loweralpha)s|%(upperalpha)s|%(lowerroman)s'
                    '|%(upperroman)s|#)' % enum.sequencepats)
    pats['optname'] = '%(alphanum)s%(alphanumplus)s*' % pats
    # @@@ Loosen up the pattern?  Allow Unicode?
    pats['optarg'] = '(%(alpha)s%(alphanumplus)s*|<[^<>]+>)' % pats
    pats['shortopt'] = r'(-|\+)%(alphanum)s( ?%(optarg)s)?' % pats
    pats['longopt'] = r'(--|/)%(optname)s([ =]%(optarg)s)?' % pats
    pats['option'] = r'(%(shortopt)s|%(longopt)s)' % pats

    for format in enum.formats:
        pats[format] = '(?P<%s>%s%s%s)' % (
              format, re.escape(enum.formatinfo[format].prefix),
              pats['enum'], re.escape(enum.formatinfo[format].suffix))

    patterns = {
          'bullet': r'[-+*]( +|$)',
          'enumerator': r'(%(parens)s|%(rparen)s|%(period)s)( +|$)' % pats,
          'field_marker': r':(?![: ])([^:\\]|\\.)*(?<! ):( +|$)',
          'option_marker': r'%(option)s(, %(option)s)*(  +| ?$)' % pats,
          'doctest': r'>>>( +|$)',
          'line_block': r'\|( +|$)',
          'grid_table_top': grid_table_top_pat,
          'simple_table_top': simple_table_top_pat,
          'explicit_markup': r'\.\.( +|$)',
          'anonymous': r'__( +|$)',
          'line': r'(%(nonalphanum7bit)s)\1* *$' % pats,
          'text': r''}
    initial_transitions = (
          'bullet',
          'enumerator',
          'field_marker',
          'option_marker',
          'doctest',
          'line_block',
          'grid_table_top',
          'simple_table_top',
          'explicit_markup',
          'anonymous',
          'line',
          'text')

    def indent(self, match, context, next_state):
        """Block quote."""
        indented, indent, line_offset, blank_finish = \
              self.state_machine.get_indented()
        blockquote, messages = self.block_quote(indented, line_offset)
        self.parent += blockquote
        self.parent += messages
        if not blank_finish:
            self.parent += self.unindent_warning('Block quote')
        return context, next_state, []

    def block_quote(self, indented, line_offset):
        blockquote_lines, attribution_lines, attribution_offset = \
              self.check_attribution(indented, line_offset)
        blockquote = nodes.block_quote()
        self.nested_parse(blockquote_lines, line_offset, blockquote)
        messages = []
        if attribution_lines:
            attribution, messages = self.parse_attribution(attribution_lines,
                                                           attribution_offset)
            blockquote += attribution
        return blockquote, messages

    # u'\u2014' is an em-dash:
    attribution_pattern = re.compile(ur'(---?(?!-)|\u2014) *(?=[^ \n])')

    def check_attribution(self, indented, line_offset):
        """
        Check for an attribution in the last contiguous block of `indented`.

        * First line after last blank line must begin with "--" (etc.).
        * Every line after that must have consistent indentation.

        Return a 3-tuple: (block quote lines, attribution lines,
        attribution offset).
        """
        #import pdb ; pdb.set_trace()
        blank = None
        nonblank_seen = None
        indent = 0
        for i in range(len(indented) - 1, 0, -1): # don't check first line
            this_line_blank = not indented[i].strip()
            if nonblank_seen and this_line_blank:
                match = self.attribution_pattern.match(indented[i + 1])
                if match:
                    blank = i
                break
            elif not this_line_blank:
                nonblank_seen = 1
        if blank and len(indented) - blank > 2: # multi-line attribution
            indent = (len(indented[blank + 2])
                      - len(indented[blank + 2].lstrip()))
            for j in range(blank + 3, len(indented)):
                if ( indented[j]        # may be blank last line
                     and indent != (len(indented[j])
                                    - len(indented[j].lstrip()))):
                    # bad shape
                    blank = None
                    break
        if blank:
            a_lines = indented[blank + 1:]
            a_lines.trim_left(match.end(), end=1)
            a_lines.trim_left(indent, start=1)
            return (indented[:blank], a_lines, line_offset + blank + 1)
        else:
            return (indented, None, None)

    def parse_attribution(self, indented, line_offset):
        text = '\n'.join(indented).rstrip()
        lineno = self.state_machine.abs_line_number() + line_offset
        textnodes, messages = self.inline_text(text, lineno)
        node = nodes.attribution(text, '', *textnodes)
        node.line = lineno
        return node, messages

    def bullet(self, match, context, next_state):
        """Bullet list item."""
        bulletlist = nodes.bullet_list()
        self.parent += bulletlist
        bulletlist['bullet'] = match.string[0]
        i, blank_finish = self.list_item(match.end())
        bulletlist += i
        offset = self.state_machine.line_offset + 1   # next line
        new_line_offset, blank_finish = self.nested_list_parse(
              self.state_machine.input_lines[offset:],
              input_offset=self.state_machine.abs_line_offset() + 1,
              node=bulletlist, initial_state='BulletList',
              blank_finish=blank_finish)
        self.goto_line(new_line_offset)
        if not blank_finish:
            self.parent += self.unindent_warning('Bullet list')
        return [], next_state, []

    def list_item(self, indent):
        if self.state_machine.line[indent:]:
            indented, line_offset, blank_finish = (
                self.state_machine.get_known_indented(indent))
        else:
            indented, indent, line_offset, blank_finish = (
                self.state_machine.get_first_known_indented(indent))
        listitem = nodes.list_item('\n'.join(indented))
        if indented:
            self.nested_parse(indented, input_offset=line_offset,
                              node=listitem)
        return listitem, blank_finish

    def enumerator(self, match, context, next_state):
        """Enumerated List Item"""
        format, sequence, text, ordinal = self.parse_enumerator(match)
        if not self.is_enumerated_list_item(ordinal, sequence, format):
            raise statemachine.TransitionCorrection('text')
        enumlist = nodes.enumerated_list()
        self.parent += enumlist
        if sequence == '#':
            enumlist['enumtype'] = 'arabic'
        else:
            enumlist['enumtype'] = sequence
        enumlist['prefix'] = self.enum.formatinfo[format].prefix
        enumlist['suffix'] = self.enum.formatinfo[format].suffix
        if ordinal != 1:
            enumlist['start'] = ordinal
            msg = self.reporter.info(
                'Enumerated list start value not ordinal-1: "%s" (ordinal %s)'
                % (text, ordinal), line=self.state_machine.abs_line_number())
            self.parent += msg
        listitem, blank_finish = self.list_item(match.end())
        enumlist += listitem
        offset = self.state_machine.line_offset + 1   # next line
        newline_offset, blank_finish = self.nested_list_parse(
              self.state_machine.input_lines[offset:],
              input_offset=self.state_machine.abs_line_offset() + 1,
              node=enumlist, initial_state='EnumeratedList',
              blank_finish=blank_finish,
              extra_settings={'lastordinal': ordinal,
                              'format': format,
                              'auto': sequence == '#'})
        self.goto_line(newline_offset)
        if not blank_finish:
            self.parent += self.unindent_warning('Enumerated list')
        return [], next_state, []

    def parse_enumerator(self, match, expected_sequence=None):
        """
        Analyze an enumerator and return the results.

        :Return:
            - the enumerator format ('period', 'parens', or 'rparen'),
            - the sequence used ('arabic', 'loweralpha', 'upperroman', etc.),
            - the text of the enumerator, stripped of formatting, and
            - the ordinal value of the enumerator ('a' -> 1, 'ii' -> 2, etc.;