Remove the htmllib and sgmllib modules as per PEP 3108.

6 files changed, 2 insertions, 1546 deletions

diff --git a/Lib/_markupbase.py b/Lib/_markupbase.py
index b178470..adf6ba2 100644
--- a/Lib/_markupbase.py
+++ b/Lib/_markupbase.py
@@ -1,8 +1,7 @@
 """Shared support for scanning document type declarations in HTML and XHTML.
 
-This module is used as a foundation for the HTMLParser and sgmllib
-modules (indirectly, for htmllib as well).  It has no documented
-public API and should not be used directly.
+This module is used as a foundation for the html.parser module.  It has no
+documented public API and should not be used directly.
 
 """
 
diff --git a/Lib/htmllib.py b/Lib/htmllib.py
deleted file mode 100644
index a580006..0000000
--- a/Lib/htmllib.py
+++ /dev/null
@@ -1,486 +0,0 @@
-"""HTML 2.0 parser.
-
-See the HTML 2.0 specification:
-http://www.w3.org/hypertext/WWW/MarkUp/html-spec/html-spec_toc.html
-"""
-
-import sgmllib
-
-from formatter import AS_IS
-
-__all__ = ["HTMLParser", "HTMLParseError"]
-
-
-class HTMLParseError(sgmllib.SGMLParseError):
-    """Error raised when an HTML document can't be parsed."""
-
-
-class HTMLParser(sgmllib.SGMLParser):
-    """This is the basic HTML parser class.
-
-    It supports all entity names required by the XHTML 1.0 Recommendation.
-    It also defines handlers for all HTML 2.0 and many HTML 3.0 and 3.2
-    elements.
-
-    """
-
-    from html.entities import entitydefs
-
-    def __init__(self, formatter, verbose=0):
-        """Creates an instance of the HTMLParser class.
-
-        The formatter parameter is the formatter instance associated with
-        the parser.
-
-        """
-        sgmllib.SGMLParser.__init__(self, verbose)
-        self.formatter = formatter
-
-    def error(self, message):
-        raise HTMLParseError(message)
-
-    def reset(self):
-        sgmllib.SGMLParser.reset(self)
-        self.savedata = None
-        self.isindex = 0
-        self.title = None
-        self.base = None
-        self.anchor = None
-        self.anchorlist = []
-        self.nofill = 0
-        self.list_stack = []
-
-    # ------ Methods used internally; some may be overridden
-
-    # --- Formatter interface, taking care of 'savedata' mode;
-    # shouldn't need to be overridden
-
-    def handle_data(self, data):
-        if self.savedata is not None:
-            self.savedata = self.savedata + data
-        else:
-            if self.nofill:
-                self.formatter.add_literal_data(data)
-            else:
-                self.formatter.add_flowing_data(data)
-
-    # --- Hooks to save data; shouldn't need to be overridden
-
-    def save_bgn(self):
-        """Begins saving character data in a buffer instead of sending it
-        to the formatter object.
-
-        Retrieve the stored data via the save_end() method.  Use of the
-        save_bgn() / save_end() pair may not be nested.
-
-        """
-        self.savedata = ''
-
-    def save_end(self):
-        """Ends buffering character data and returns all data saved since
-        the preceding call to the save_bgn() method.
-
-        If the nofill flag is false, whitespace is collapsed to single
-        spaces.  A call to this method without a preceding call to the
-        save_bgn() method will raise a TypeError exception.
-
-        """
-        data = self.savedata
-        self.savedata = None
-        if not self.nofill:
-            data = ' '.join(data.split())
-        return data
-
-    # --- Hooks for anchors; should probably be overridden
-
-    def anchor_bgn(self, href, name, type):
-        """This method is called at the start of an anchor region.
-
-        The arguments correspond to the attributes of the <A> tag with
-        the same names.  The default implementation maintains a list of
-        hyperlinks (defined by the HREF attribute for <A> tags) within
-        the document.  The list of hyperlinks is available as the data
-        attribute anchorlist.
-
-        """
-        self.anchor = href
-        if self.anchor:
-            self.anchorlist.append(href)
-
-    def anchor_end(self):
-        """This method is called at the end of an anchor region.
-
-        The default implementation adds a textual footnote marker using an
-        index into the list of hyperlinks created by the anchor_bgn()method.
-
-        """
-        if self.anchor:
-            self.handle_data("[%d]" % len(self.anchorlist))
-            self.anchor = None
-
-    # --- Hook for images; should probably be overridden
-
-    def handle_image(self, src, alt, *args):
-        """This method is called to handle images.
-
-        The default implementation simply passes the alt value to the
-        handle_data() method.
-
-        """
-        self.handle_data(alt)
-
-    # --------- Top level elememts
-
-    def start_html(self, attrs): pass
-    def end_html(self): pass
-
-    def start_head(self, attrs): pass
-    def end_head(self): pass
-
-    def start_body(self, attrs): pass
-    def end_body(self): pass
-
-    # ------ Head elements
-
-    def start_title(self, attrs):
-        self.save_bgn()
-
-    def end_title(self):
-        self.title = self.save_end()
-
-    def do_base(self, attrs):
-        for a, v in attrs:
-            if a == 'href':
-                self.base = v
-
-    def do_isindex(self, attrs):
-        self.isindex = 1
-
-    def do_link(self, attrs):
-        pass
-
-    def do_meta(self, attrs):
-        pass
-
-    def do_nextid(self, attrs): # Deprecated
-        pass
-
-    # ------ Body elements
-
-    # --- Headings
-
-    def start_h1(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_font(('h1', 0, 1, 0))
-
-    def end_h1(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_font()
-
-    def start_h2(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_font(('h2', 0, 1, 0))
-
-    def end_h2(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_font()
-
-    def start_h3(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_font(('h3', 0, 1, 0))
-
-    def end_h3(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_font()
-
-    def start_h4(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_font(('h4', 0, 1, 0))
-
-    def end_h4(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_font()
-
-    def start_h5(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_font(('h5', 0, 1, 0))
-
-    def end_h5(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_font()
-
-    def start_h6(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_font(('h6', 0, 1, 0))
-
-    def end_h6(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_font()
-
-    # --- Block Structuring Elements
-
-    def do_p(self, attrs):
-        self.formatter.end_paragraph(1)
-
-    def start_pre(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_font((AS_IS, AS_IS, AS_IS, 1))
-        self.nofill = self.nofill + 1
-
-    def end_pre(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_font()
-        self.nofill = max(0, self.nofill - 1)
-
-    def start_xmp(self, attrs):
-        self.start_pre(attrs)
-        self.setliteral('xmp') # Tell SGML parser
-
-    def end_xmp(self):
-        self.end_pre()
-
-    def start_listing(self, attrs):
-        self.start_pre(attrs)
-        self.setliteral('listing') # Tell SGML parser
-
-    def end_listing(self):
-        self.end_pre()
-
-    def start_address(self, attrs):
-        self.formatter.end_paragraph(0)
-        self.formatter.push_font((AS_IS, 1, AS_IS, AS_IS))
-
-    def end_address(self):
-        self.formatter.end_paragraph(0)
-        self.formatter.pop_font()
-
-    def start_blockquote(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.formatter.push_margin('blockquote')
-
-    def end_blockquote(self):
-        self.formatter.end_paragraph(1)
-        self.formatter.pop_margin()
-
-    # --- List Elements
-
-    def start_ul(self, attrs):
-        self.formatter.end_paragraph(not self.list_stack)
-        self.formatter.push_margin('ul')
-        self.list_stack.append(['ul', '*', 0])
-
-    def end_ul(self):
-        if self.list_stack: del self.list_stack[-1]
-        self.formatter.end_paragraph(not self.list_stack)
-        self.formatter.pop_margin()
-
-    def do_li(self, attrs):
-        self.formatter.end_paragraph(0)
-        if self.list_stack:
-            [dummy, label, counter] = top = self.list_stack[-1]
-            top[2] = counter = counter+1
-        else:
-            label, counter = '*', 0
-        self.formatter.add_label_data(label, counter)
-
-    def start_ol(self, attrs):
-        self.formatter.end_paragraph(not self.list_stack)
-        self.formatter.push_margin('ol')
-        label = '1.'
-        for a, v in attrs:
-            if a == 'type':
-                if len(v) == 1: v = v + '.'
-                label = v
-        self.list_stack.append(['ol', label, 0])
-
-    def end_ol(self):
-        if self.list_stack: del self.list_stack[-1]
-        self.formatter.end_paragraph(not self.list_stack)
-        self.formatter.pop_margin()
-
-    def start_menu(self, attrs):
-        self.start_ul(attrs)
-
-    def end_menu(self):
-        self.end_ul()
-
-    def start_dir(self, attrs):
-        self.start_ul(attrs)
-
-    def end_dir(self):
-        self.end_ul()
-
-    def start_dl(self, attrs):
-        self.formatter.end_paragraph(1)
-        self.list_stack.append(['dl', '', 0])
-
-    def end_dl(self):
-        self.ddpop(1)
-        if self.list_stack: del self.list_stack[-1]
-
-    def do_dt(self, attrs):
-        self.ddpop()
-
-    def do_dd(self, attrs):
-        self.ddpop()
-        self.formatter.push_margin('dd')
-        self.list_stack.append(['dd', '', 0])
-
-    def ddpop(self, bl=0):
-        self.formatter.end_paragraph(bl)
-        if self.list_stack:
-            if self.list_stack[-1][0] == 'dd':
-                del self.list_stack[-1]
-                self.formatter.pop_margin()
-
-    # --- Phrase Markup
-
-    # Idiomatic Elements
-
-    def start_cite(self, attrs): self.start_i(attrs)
-    def end_cite(self): self.end_i()
-
-    def start_code(self, attrs): self.start_tt(attrs)
-    def end_code(self): self.end_tt()
-
-    def start_em(self, attrs): self.start_i(attrs)
-    def end_em(self): self.end_i()
-
-    def start_kbd(self, attrs): self.start_tt(attrs)
-    def end_kbd(self): self.end_tt()
-
-    def start_samp(self, attrs): self.start_tt(attrs)
-    def end_samp(self): self.end_tt()
-
-    def start_strong(self, attrs): self.start_b(attrs)
-    def end_strong(self): self.end_b()
-
-    def start_var(self, attrs): self.start_i(attrs)
-    def end_var(self): self.end_i()
-
-    # Typographic Elements
-
-    def start_i(self, attrs):
-        self.formatter.push_font((AS_IS, 1, AS_IS, AS_IS))
-    def end_i(self):
-        self.formatter.pop_font()
-
-    def start_b(self, attrs):
-        self.formatter.push_font((AS_IS, AS_IS, 1, AS_IS))
-    def end_b(self):
-        self.formatter.pop_font()
-
-    def start_tt(self, attrs):
-        self.formatter.push_font((AS_IS, AS_IS, AS_IS, 1))
-    def end_tt(self):
-        self.formatter.pop_font()
-
-    def start_a(self, attrs):
-        href = ''
-        name = ''
-        type = ''
-        for attrname, value in attrs:
-            value = value.strip()
-            if attrname == 'href':
-                href = value
-            if attrname == 'name':
-                name = value
-            if attrname == 'type':
-                type = value.lower()
-        self.anchor_bgn(href, name, type)
-
-    def end_a(self):
-        self.anchor_end()
-
-    # --- Line Break
-
-    def do_br(self, attrs):
-        self.formatter.add_line_break()
-
-    # --- Horizontal Rule
-
-    def do_hr(self, attrs):
-        self.formatter.add_hor_rule()
-
-    # --- Image
-
-    def do_img(self, attrs):
-        align = ''
-        alt = '(image)'
-        ismap = ''
-        src = ''
-        width = 0
-        height = 0
-        for attrname, value in attrs:
-            if attrname == 'align':
-                align = value
-            if attrname == 'alt':
-                alt = value
-            if attrname == 'ismap':
-                ismap = value
-            if attrname == 'src':
-                src = value
-            if attrname == 'width':
-                try: width = int(value)
-                except ValueError: pass
-            if attrname == 'height':
-                try: height = int(value)
-                except ValueError: pass
-        self.handle_image(src, alt, ismap, align, width, height)
-
-    # --- Really Old Unofficial Deprecated Stuff
-
-    def do_plaintext(self, attrs):
-        self.start_pre(attrs)
-        self.setnomoretags() # Tell SGML parser
-
-    # --- Unhandled tags
-
-    def unknown_starttag(self, tag, attrs):
-        pass
-
-    def unknown_endtag(self, tag):
-        pass
-
-
-def test(args = None):
-    import sys, formatter
-
-    if not args:
-        args = sys.argv[1:]
-
-    silent = args and args[0] == '-s'
-    if silent:
-        del args[0]
-
-    if args:
-        file = args[0]
-    else:
-        file = 'test.html'
-
-    if file == '-':
-        f = sys.stdin
-    else:
-        try:
-            f = open(file, 'r')
-        except IOError as msg:
-            print(file, ":", msg)
-            sys.exit(1)
-
-    data = f.read()
-
-    if f is not sys.stdin:
-        f.close()
-
-    if silent:
-        f = formatter.NullFormatter()
-    else:
-        f = formatter.AbstractFormatter(formatter.DumbWriter())
-
-    p = HTMLParser(f)
-    p.feed(data)
-    p.close()
-
-
-if __name__ == '__main__':
-    test()
diff --git a/Lib/sgmllib.py b/Lib/sgmllib.py
deleted file mode 100644
index 7eca9de..0000000
--- a/Lib/sgmllib.py
+++ /dev/null
@@ -1,548 +0,0 @@
-"""A parser for SGML, using the derived class as a static DTD."""
-
-# XXX This only supports those SGML features used by HTML.
-
-# XXX There should be a way to distinguish between PCDATA (parsed
-# character data -- the normal case), RCDATA (replaceable character
-# data -- only char and entity references and end tags are special)
-# and CDATA (character data -- only end tags are special).  RCDATA is
-# not supported at all.
-
-
-import _markupbase
-import re
-
-__all__ = ["SGMLParser", "SGMLParseError"]
-
-# Regular expressions used for parsing
-
-interesting = re.compile('[&<]')
-incomplete = re.compile('&([a-zA-Z][a-zA-Z0-9]*|#[0-9]*)?|'
-                           '<([a-zA-Z][^<>]*|'
-                              '/([a-zA-Z][^<>]*)?|'
-                              '![^<>]*)?')
-
-entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
-charref = re.compile('&#([0-9]+)[^0-9]')
-
-starttagopen = re.compile('<[>a-zA-Z]')
-shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
-shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
-piclose = re.compile('>')
-endbracket = re.compile('[<>]')
-tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*')
-attrfind = re.compile(
-    r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
-    r'(\'[^\']*\'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*))?')
-
-
-class SGMLParseError(RuntimeError):
-    """Exception raised for all parse errors."""
-    pass
-
-
-# SGML parser base class -- find tags and call handler functions.
-# Usage: p = SGMLParser(); p.feed(data); ...; p.close().
-# The dtd is defined by deriving a class which defines methods
-# with special names to handle tags: start_foo and end_foo to handle
-# <foo> and </foo>, respectively, or do_foo to handle <foo> by itself.
-# (Tags are converted to lower case for this purpose.)  The data
-# between tags is passed to the parser by calling self.handle_data()
-# with some data as argument (the data may be split up in arbitrary
-# chunks).  Entity references are passed by calling
-# self.handle_entityref() with the entity reference as argument.
-
-class SGMLParser(_markupbase.ParserBase):
-    # Definition of entities -- derived classes may override
-    entity_or_charref = re.compile('&(?:'
-      '([a-zA-Z][-.a-zA-Z0-9]*)|#([0-9]+)'
-      ')(;?)')
-
-    def __init__(self, verbose=0):
-        """Initialize and reset this instance."""
-        self.verbose = verbose
-        self.reset()
-
-    def reset(self):
-        """Reset this instance. Loses all unprocessed data."""
-        self.__starttag_text = None
-        self.rawdata = ''
-        self.stack = []
-        self.lasttag = '???'
-        self.nomoretags = 0
-        self.literal = 0
-        _markupbase.ParserBase.reset(self)
-
-    def setnomoretags(self):
-        """Enter literal mode (CDATA) till EOF.
-
-        Intended for derived classes only.
-        """
-        self.nomoretags = self.literal = 1
-
-    def setliteral(self, *args):
-        """Enter literal mode (CDATA).
-
-        Intended for derived classes only.
-        """
-        self.literal = 1
-
-    def feed(self, data):
-        """Feed some data to the parser.
-
-        Call this as often as you want, with as little or as much text
-        as you want (may include '\n').  (This just saves the text,
-        all the processing is done by goahead().)
-        """
-
-        self.rawdata = self.rawdata + data
-        self.goahead(0)
-
-    def close(self):
-        """Handle the remaining data."""
-        self.goahead(1)
-
-    def error(self, message):
-        raise SGMLParseError(message)
-
-    # Internal -- handle data as far as reasonable.  May leave state
-    # and data to be processed by a subsequent call.  If 'end' is
-    # true, force handling all data as if followed by EOF marker.
-    def goahead(self, end):
-        rawdata = self.rawdata
-        i = 0
-        n = len(rawdata)
-        while i < n:
-            if self.nomoretags:
-                self.handle_data(rawdata[i:n])
-                i = n
-                break
-            match = interesting.search(rawdata, i)
-            if match: j = match.start()
-            else: j = n
-            if i < j:
-                self.handle_data(rawdata[i:j])
-            i = j
-            if i == n: break
-            if rawdata[i] == '<':
-                if starttagopen.match(rawdata, i):
-                    if self.literal:
-                        self.handle_data(rawdata[i])
-                        i = i+1
-                        continue
-                    k = self.parse_starttag(i)
-                    if k < 0: break
-                    i = k
-                    continue
-                if rawdata.startswith("</", i):
-                    k = self.parse_endtag(i)
-                    if k < 0: break
-                    i = k
-                    self.literal = 0
-                    continue
-                if self.literal:
-                    if n > (i + 1):
-                        self.handle_data("<")
-                        i = i+1
-                    else:
-                        # incomplete
-                        break
-                    continue
-                if rawdata.startswith("<!--", i):
-                        # Strictly speaking, a comment is --.*--
-                        # within a declaration tag <!...>.
-                        # This should be removed,
-                        # and comments handled only in parse_declaration.
-                    k = self.parse_comment(i)
-                    if k < 0: break
-                    i = k
-                    continue
-                if rawdata.startswith("<?", i):
-                    k = self.parse_pi(i)
-                    if k < 0: break
-                    i = i+k
-                    continue
-                if rawdata.startswith("<!", i):
-                    # This is some sort of declaration; in "HTML as
-                    # deployed," this should only be the document type
-                    # declaration ("<!DOCTYPE html...>").
-                    k = self.parse_declaration(i)
-                    if k < 0: break
-                    i = k
-                    continue
-            elif rawdata[i] == '&':
-                if self.literal:
-                    self.handle_data(rawdata[i])
-                    i = i+1
-                    continue
-                match = charref.match(rawdata, i)
-                if match:
-                    name = match.group(1)
-                    self.handle_charref(name)
-                    i = match.end(0)
-                    if rawdata[i-1] != ';': i = i-1
-                    continue
-                match = entityref.match(rawdata, i)
-                if match:
-                    name = match.group(1)
-                    self.handle_entityref(name)
-                    i = match.end(0)
-                    if rawdata[i-1] != ';': i = i-1
-                    continue
-            else:
-                self.error('neither < nor & ??')
-            # We get here only if incomplete matches but
-            # nothing else
-            match = incomplete.match(rawdata, i)
-            if not match:
-                self.handle_data(rawdata[i])
-                i = i+1
-                continue
-            j = match.end(0)
-            if j == n:
-                break # Really incomplete
-            self.handle_data(rawdata[i:j])
-            i = j
-        # end while
-        if end and i < n:
-            self.handle_data(rawdata[i:n])
-            i = n
-        self.rawdata = rawdata[i:]
-        # XXX if end: check for empty stack
-
-    # Extensions for the DOCTYPE scanner:
-    _decl_otherchars = '='
-
-    # Internal -- parse processing instr, return length or -1 if not terminated
-    def parse_pi(self, i):
-        rawdata = self.rawdata
-        if rawdata[i:i+2] != '<?':
-            self.error('unexpected call to parse_pi()')
-        match = piclose.search(rawdata, i+2)
-        if not match:
-            return -1
-        j = match.start(0)
-        self.handle_pi(rawdata[i+2: j])
-        j = match.end(0)
-        return j-i
-
-    def get_starttag_text(self):
-        return self.__starttag_text
-
-    # Internal -- handle starttag, return length or -1 if not terminated
-    def parse_starttag(self, i):
-        self.__starttag_text = None
-        start_pos = i
-        rawdata = self.rawdata
-        if shorttagopen.match(rawdata, i):
-            # SGML shorthand: <tag/data/ == <tag>data</tag>
-            # XXX Can data contain &... (entity or char refs)?
-            # XXX Can data contain < or > (tag characters)?
-            # XXX Can there be whitespace before the first /?
-            match = shorttag.match(rawdata, i)
-            if not match:
-                return -1
-            tag, data = match.group(1, 2)
-            self.__starttag_text = '<%s/' % tag
-            tag = tag.lower()
-            k = match.end(0)
-            self.finish_shorttag(tag, data)
-            self.__starttag_text = rawdata[start_pos:match.end(1) + 1]
-            return k
-        # XXX The following should skip matching quotes (' or ")
-        # As a shortcut way to exit, this isn't so bad, but shouldn't
-        # be used to locate the actual end of the start tag since the
-        # < or > characters may be embedded in an attribute value.
-        match = endbracket.search(rawdata, i+1)
-        if not match:
-            return -1
-        j = match.start(0)
-        # Now parse the data between i+1 and j into a tag and attrs
-        attrs = []
-        if rawdata[i:i+2] == '<>':
-            # SGML shorthand: <> == <last open tag seen>
-            k = j
-            tag = self.lasttag
-        else:
-            match = tagfind.match(rawdata, i+1)
-            if not match:
-                self.error('unexpected call to parse_starttag')
-            k = match.end(0)
-            tag = rawdata[i+1:k].lower()
-            self.lasttag = tag
-        while k < j:
-            match = attrfind.match(rawdata, k)
-            if not match: break
-            attrname, rest, attrvalue = match.group(1, 2, 3)
-            if not rest:
-                attrvalue = attrname
-            else:
-                if (attrvalue[:1] == "'" == attrvalue[-1:] or
-                    attrvalue[:1] == '"' == attrvalue[-1:]):
-                    # strip quotes
-                    attrvalue = attrvalue[1:-1]
-                attrvalue = self.entity_or_charref.sub(
-                    self._convert_ref, attrvalue)
-            attrs.append((attrname.lower(), attrvalue))
-            k = match.end(0)
-        if rawdata[j] == '>':
-            j = j+1
-        self.__starttag_text = rawdata[start_pos:j]
-        self.finish_starttag(tag, attrs)
-        return j
-
-    # Internal -- convert entity or character reference
-    def _convert_ref(self, match):
-        if match.group(2):
-            return self.convert_charref(match.group(2)) or \
-                '&#%s%s' % match.groups()[1:]
-        elif match.group(3):
-            return self.convert_entityref(match.group(1)) or \
-                '&%s;' % match.group(1)
-        else:
-            return '&%s' % match.group(1)
-
-    # Internal -- parse endtag
-    def parse_endtag(self, i):
-        rawdata = self.rawdata
-        match = endbracket.search(rawdata, i+1)
-        if not match:
-            return -1
-        j = match.start(0)
-        tag = rawdata[i+2:j].strip().lower()
-        if rawdata[j] == '>':
-            j = j+1
-        self.finish_endtag(tag)
-        return j
-
-    # Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
-    def finish_shorttag(self, tag, data):
-        self.finish_starttag(tag, [])
-        self.handle_data(data)
-        self.finish_endtag(tag)
-
-    # Internal -- finish processing of start tag
-    # Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
-    def finish_starttag(self, tag, attrs):
-        try:
-            method = getattr(self, 'start_' + tag)
-        except AttributeError:
-            try:
-                method = getattr(self, 'do_' + tag)
-            except AttributeError:
-                self.unknown_starttag(tag, attrs)
-                return -1
-            else:
-                self.handle_starttag(tag, method, attrs)
-                return 0
-        else:
-            self.stack.append(tag)
-            self.handle_starttag(tag, method, attrs)
-            return 1
-
-    # Internal -- finish processing of end tag
-    def finish_endtag(self, tag):
-        if not tag:
-            found = len(self.stack) - 1
-            if found < 0:
-                self.unknown_endtag(tag)
-                return
-        else:
-            if tag not in self.stack:
-                try:
-                    method = getattr(self, 'end_' + tag)
-                except AttributeError:
-                    self.unknown_endtag(tag)
-                else:
-                    self.report_unbalanced(tag)
-                return
-            found = len(self.stack)
-            for i in range(found):
-                if self.stack[i] == tag: found = i
-        while len(self.stack) > found:
-            tag = self.stack[-1]
-            try:
-                method = getattr(self, 'end_' + tag)
-            except AttributeError:
-                method = None
-            if method:
-                self.handle_endtag(tag, method)
-            else:
-                self.unknown_endtag(tag)
-            del self.stack[-1]
-
-    # Overridable -- handle start tag
-    def handle_starttag(self, tag, method, attrs):
-        method(attrs)
-
-    # Overridable -- handle end tag
-    def handle_endtag(self, tag, method):
-        method()
-
-    # Example -- report an unbalanced </...> tag.
-    def report_unbalanced(self, tag):
-        if self.verbose:
-            print('*** Unbalanced </' + tag + '>')
-            print('*** Stack:', self.stack)
-
-    def convert_charref(self, name):
-        """Convert character reference, may be overridden."""
-        try:
-            n = int(name)
-        except ValueError:
-            return
-        if not 0 <= n <= 255:
-            return
-        return self.convert_codepoint(n)
-
-    def convert_codepoint(self, codepoint):
-        return chr(codepoint)
-
-    def handle_charref(self, name):
-        """Handle character reference, no need to override."""
-        replacement = self.convert_charref(name)
-        if replacement is None:
-            self.unknown_charref(name)
-        else:
-            self.handle_data(replacement)
-
-    # Definition of entities -- derived classes may override
-    entitydefs = \
-            {'lt': '<', 'gt': '>', 'amp': '&', 'quot': '"', 'apos': '\''}
-
-    def convert_entityref(self, name):
-        """Convert entity references.
-
-        As an alternative to overriding this method; one can tailor the
-        results by setting up the self.entitydefs mapping appropriately.
-        """
-        table = self.entitydefs
-        if name in table:
-            return table[name]
-        else:
-            return
-
-    def handle_entityref(self, name):
-        """Handle entity references, no need to override."""
-        replacement = self.convert_entityref(name)
-        if replacement is None:
-            self.unknown_entityref(name)
-        else:
-            self.handle_data(replacement)
-
-    # Example -- handle data, should be overridden
-    def handle_data(self, data):
-        pass
-
-    # Example -- handle comment, could be overridden
-    def handle_comment(self, data):
-        pass
-
-    # Example -- handle declaration, could be overridden
-    def handle_decl(self, decl):
-        pass
-
-    # Example -- handle processing instruction, could be overridden
-    def handle_pi(self, data):
-        pass
-
-    # To be overridden -- handlers for unknown objects
-    def unknown_starttag(self, tag, attrs): pass
-    def unknown_endtag(self, tag): pass
-    def unknown_charref(self, ref): pass
-    def unknown_entityref(self, ref): pass
-
-
-class TestSGMLParser(SGMLParser):
-
-    def __init__(self, verbose=0):
-        self.testdata = ""
-        SGMLParser.__init__(self, verbose)
-
-    def handle_data(self, data):
-        self.testdata = self.testdata + data
-        if len(repr(self.testdata)) >= 70:
-            self.flush()
-
-    def flush(self):
-        data = self.testdata
-        if data:
-            self.testdata = ""
-            print('data:', repr(data))
-
-    def handle_comment(self, data):
-        self.flush()
-        r = repr(data)
-        if len(r) > 68:
-            r = r[:32] + '...' + r[-32:]
-        print('comment:', r)
-
-    def unknown_starttag(self, tag, attrs):
-        self.flush()
-        if not attrs:
-            print('start tag: <' + tag + '>')
-        else:
-            print('start tag: <' + tag, end=' ')
-            for name, value in attrs:
-                print(name + '=' + '"' + value + '"', end=' ')
-            print('>')
-
-    def unknown_endtag(self, tag):
-        self.flush()
-        print('end tag: </' + tag + '>')
-
-    def unknown_entityref(self, ref):
-        self.flush()
-        print('*** unknown entity ref: &' + ref + ';')
-
-    def unknown_charref(self, ref):
-        self.flush()
-        print('*** unknown char ref: &#' + ref + ';')
-
-    def unknown_decl(self, data):
-        self.flush()
-        print('*** unknown decl: [' + data + ']')
-
-    def close(self):
-        SGMLParser.close(self)
-        self.flush()
-
-
-def test(args = None):
-    import sys
-
-    if args is None:
-        args = sys.argv[1:]
-
-    if args and args[0] == '-s':
-        args = args[1:]
-        klass = SGMLParser
-    else:
-        klass = TestSGMLParser
-
-    if args:
-        file = args[0]
-    else:
-        file = 'test.html'
-
-    if file == '-':
-        f = sys.stdin
-    else:
-        try:
-            f = open(file, 'r')
-        except IOError as msg:
-            print(file, ":", msg)
-            sys.exit(1)
-
-    data = f.read()
-    if f is not sys.stdin:
-        f.close()
-
-    x = klass()
-    for c in data:
-        x.feed(c)
-    x.close()
-
-
-if __name__ == '__main__':
-    test()
diff --git a/Lib/test/test___all__.py b/Lib/test/test___all__.py
index e33c54a..491f159 100644
--- a/Lib/test/test___all__.py
+++ b/Lib/test/test___all__.py
@@ -73,7 +73,6 @@ class AllTest(unittest.TestCase):
         self.check_all("glob")
         self.check_all("gzip")
         self.check_all("heapq")
-        self.check_all("htmllib")
         self.check_all("http.client")
         self.check_all("ihooks")
         self.check_all("imaplib")
@@ -116,7 +115,6 @@ class AllTest(unittest.TestCase):
         self.check_all("rlcompleter")
         self.check_all("robotparser")
         self.check_all("sched")
-        self.check_all("sgmllib")
         self.check_all("shelve")
         self.check_all("shlex")
         self.check_all("shutil")
diff --git a/Lib/test/test_htmllib.py b/Lib/test/test_htmllib.py
deleted file mode 100644
index 61f3a13..0000000
--- a/Lib/test/test_htmllib.py
+++ /dev/null
@@ -1,69 +0,0 @@
-import formatter
-import htmllib
-import unittest
-
-from test import support
-
-
-class AnchorCollector(htmllib.HTMLParser):
-    def __init__(self, *args, **kw):
-        self.__anchors = []
-        htmllib.HTMLParser.__init__(self, *args, **kw)
-
-    def get_anchor_info(self):
-        return self.__anchors
-
-    def anchor_bgn(self, *args):
-        self.__anchors.append(args)
-
-class DeclCollector(htmllib.HTMLParser):
-    def __init__(self, *args, **kw):
-        self.__decls = []
-        htmllib.HTMLParser.__init__(self, *args, **kw)
-
-    def get_decl_info(self):
-        return self.__decls
-
-    def unknown_decl(self, data):
-        self.__decls.append(data)
-
-
-class HTMLParserTestCase(unittest.TestCase):
-    def test_anchor_collection(self):
-        # See SF bug #467059.
-        parser = AnchorCollector(formatter.NullFormatter(), verbose=1)
-        parser.feed(
-            """<a href='http://foo.org/' name='splat'> </a>
-            <a href='http://www.python.org/'> </a>
-            <a name='frob'> </a>
-            """)
-        parser.close()
-        self.assertEquals(parser.get_anchor_info(),
-                          [('http://foo.org/', 'splat', ''),
-                           ('http://www.python.org/', '', ''),
-                           ('', 'frob', ''),
-                           ])
-
-    def test_decl_collection(self):
-        # See SF patch #545300
-        parser = DeclCollector(formatter.NullFormatter(), verbose=1)
-        parser.feed(
-            """<html>
-            <body>
-            hallo
-            <![if !supportEmptyParas]>&nbsp;<![endif]>
-            </body>
-            </html>
-            """)
-        parser.close()
-        self.assertEquals(parser.get_decl_info(),
-                          ["if !supportEmptyParas",
-                           "endif"
-                           ])
-
-def test_main():
-    support.run_unittest(HTMLParserTestCase)
-
-
-if __name__ == "__main__":
-    test_main()
diff --git a/Lib/test/test_sgmllib.py b/Lib/test/test_sgmllib.py
deleted file mode 100644
index 6015878..0000000
--- a/Lib/test/test_sgmllib.py
+++ /dev/null
@@ -1,438 +0,0 @@
-import pprint
-import re
-import sgmllib
-import unittest
-from test import support
-
-
-class EventCollector(sgmllib.SGMLParser):
-
-    def __init__(self):
-        self.events = []
-        self.append = self.events.append
-        sgmllib.SGMLParser.__init__(self)
-
-    def get_events(self):
-        # Normalize the list of events so that buffer artefacts don't
-        # separate runs of contiguous characters.
-        L = []
-        prevtype = None
-        for event in self.events:
-            type = event[0]
-            if type == prevtype == "data":
-                L[-1] = ("data", L[-1][1] + event[1])
-            else:
-                L.append(event)
-            prevtype = type
-        self.events = L
-        return L
-
-    # structure markup
-
-    def unknown_starttag(self, tag, attrs):
-        self.append(("starttag", tag, attrs))
-
-    def unknown_endtag(self, tag):
-        self.append(("endtag", tag))
-
-    # all other markup
-
-    def handle_comment(self, data):
-        self.append(("comment", data))
-
-    def handle_charref(self, data):
-        self.append(("charref", data))
-
-    def handle_data(self, data):
-        self.append(("data", data))
-
-    def handle_decl(self, decl):
-        self.append(("decl", decl))
-
-    def handle_entityref(self, data):
-        self.append(("entityref", data))
-
-    def handle_pi(self, data):
-        self.append(("pi", data))
-
-    def unknown_decl(self, decl):
-        self.append(("unknown decl", decl))
-
-
-class CDATAEventCollector(EventCollector):
-    def start_cdata(self, attrs):
-        self.append(("starttag", "cdata", attrs))
-        self.setliteral()
-
-
-class HTMLEntityCollector(EventCollector):
-
-    entity_or_charref = re.compile('(?:&([a-zA-Z][-.a-zA-Z0-9]*)'
-        '|&#(x[0-9a-zA-Z]+|[0-9]+))(;?)')
-
-    def convert_charref(self, name):
-        self.append(("charref", "convert", name))
-        if name[0] != "x":
-            return EventCollector.convert_charref(self, name)
-
-    def convert_codepoint(self, codepoint):
-        self.append(("codepoint", "convert", codepoint))
-        EventCollector.convert_codepoint(self, codepoint)
-
-    def convert_entityref(self, name):
-        self.append(("entityref", "convert", name))
-        return EventCollector.convert_entityref(self, name)
-
-    # These to record that they were called, then pass the call along
-    # to the default implementation so that it's actions can be
-    # recorded.
-
-    def handle_charref(self, data):
-        self.append(("charref", data))
-        sgmllib.SGMLParser.handle_charref(self, data)
-
-    def handle_entityref(self, data):
-        self.append(("entityref", data))
-        sgmllib.SGMLParser.handle_entityref(self, data)
-
-
-class SGMLParserTestCase(unittest.TestCase):
-
-    collector = EventCollector
-
-    def get_events(self, source):
-        parser = self.collector()
-        try:
-            for s in source:
-                parser.feed(s)
-            parser.close()
-        except:
-            #self.events = parser.events
-            raise
-        return parser.get_events()
-
-    def check_events(self, source, expected_events):
-        try:
-            events = self.get_events(source)
-        except:
-            #import sys
-            #print >>sys.stderr, pprint.pformat(self.events)
-            raise
-        if events != expected_events:
-            self.fail("received events did not match expected events\n"
-                      "Expected:\n" + pprint.pformat(expected_events) +
-                      "\nReceived:\n" + pprint.pformat(events))
-
-    def check_parse_error(self, source):
-        parser = EventCollector()
-        try:
-            parser.feed(source)
-            parser.close()
-        except sgmllib.SGMLParseError:
-            pass
-        else:
-            self.fail("expected SGMLParseError for %r\nReceived:\n%s"
-                      % (source, pprint.pformat(parser.get_events())))
-
-    def test_doctype_decl_internal(self):
-        inside = """\
-DOCTYPE html PUBLIC '-//W3C//DTD HTML 4.01//EN'
-             SYSTEM 'http://www.w3.org/TR/html401/strict.dtd' [
-  <!ELEMENT html - O EMPTY>
-  <!ATTLIST html
-      version CDATA #IMPLIED
-      profile CDATA 'DublinCore'>
-  <!NOTATION datatype SYSTEM 'http://xml.python.org/notations/python-module'>
-  <!ENTITY myEntity 'internal parsed entity'>
-  <!ENTITY anEntity SYSTEM 'http://xml.python.org/entities/something.xml'>
-  <!ENTITY % paramEntity 'name|name|name'>
-  %paramEntity;
-  <!-- comment -->
-]"""
-        self.check_events(["<!%s>" % inside], [
-            ("decl", inside),
-            ])
-
-    def test_doctype_decl_external(self):
-        inside = "DOCTYPE html PUBLIC '-//W3C//DTD HTML 4.01//EN'"
-        self.check_events("<!%s>" % inside, [
-            ("decl", inside),
-            ])
-
-    def test_underscore_in_attrname(self):
-        # SF bug #436621
-        """Make sure attribute names with underscores are accepted"""
-        self.check_events("<a has_under _under>", [
-            ("starttag", "a", [("has_under", "has_under"),
-                               ("_under", "_under")]),
-            ])
-
-    def test_underscore_in_tagname(self):
-        # SF bug #436621
-        """Make sure tag names with underscores are accepted"""
-        self.check_events("<has_under></has_under>", [
-            ("starttag", "has_under", []),
-            ("endtag", "has_under"),
-            ])
-
-    def test_quotes_in_unquoted_attrs(self):
-        # SF bug #436621
-        """Be sure quotes in unquoted attributes are made part of the value"""
-        self.check_events("<a href=foo'bar\"baz>", [
-            ("starttag", "a", [("href", "foo'bar\"baz")]),
-            ])
-
-    def test_xhtml_empty_tag(self):
-        """Handling of XHTML-style empty start tags"""
-        self.check_events("<br />text<i></i>", [
-            ("starttag", "br", []),
-            ("data", "text"),
-            ("starttag", "i", []),
-            ("endtag", "i"),
-            ])
-
-    def test_processing_instruction_only(self):
-        self.check_events("<?processing instruction>", [
-            ("pi", "processing instruction"),
-            ])
-
-    def test_bad_nesting(self):
-        self.check_events("<a><b></a></b>", [
-            ("starttag", "a", []),
-            ("starttag", "b", []),
-            ("endtag", "a"),
-            ("endtag", "b"),
-            ])
-
-    def test_bare_ampersands(self):
-        self.check_events("this text & contains & ampersands &", [
-            ("data", "this text & contains & ampersands &"),
-            ])
-
-    def test_bare_pointy_brackets(self):
-        self.check_events("this < text > contains < bare>pointy< brackets", [
-            ("data", "this < text > contains < bare>pointy< brackets"),
-            ])
-
-    def test_attr_syntax(self):
-        output = [
-          ("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", "e")])
-          ]
-        self.check_events("""<a b='v' c="v" d=v e>""", output)
-        self.check_events("""<a  b = 'v' c = "v" d = v e>""", output)
-        self.check_events("""<a\nb\n=\n'v'\nc\n=\n"v"\nd\n=\nv\ne>""", output)
-        self.check_events("""<a\tb\t=\t'v'\tc\t=\t"v"\td\t=\tv\te>""", output)
-
-    def test_attr_values(self):
-        self.check_events("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""",
-                        [("starttag", "a", [("b", "xxx\n\txxx"),
-                                            ("c", "yyy\t\nyyy"),
-                                            ("d", "\txyz\n")])
-                         ])
-        self.check_events("""<a b='' c="">""", [
-            ("starttag", "a", [("b", ""), ("c", "")]),
-            ])
-        # URL construction stuff from RFC 1808:
-        safe = "$-_.+"
-        extra = "!*'(),"
-        reserved = ";/?:@&="
-        url = "http://example.com:8080/path/to/file?%s%s%s" % (
-            safe, extra, reserved)
-        self.check_events("""<e a=%s>""" % url, [
-            ("starttag", "e", [("a", url)]),
-            ])
-        # Regression test for SF patch #669683.
-        self.check_events("<e a=rgb(1,2,3)>", [
-            ("starttag", "e", [("a", "rgb(1,2,3)")]),
-            ])
-
-    def test_attr_values_entities(self):
-        """Substitution of entities and charrefs in attribute values"""
-        # SF bug #1452246
-        self.check_events("""<a b=&lt; c=&lt;&gt; d=&lt-&gt; e='&lt; '
-                                f="&xxx;" g='&#32;&#33;' h='&#500;'
-                                i='x?a=b&c=d;'
-                                j='&amp;#42;' k='&#38;#42;'>""",
-            [("starttag", "a", [("b", "<"),
-                                ("c", "<>"),
-                                ("d", "&lt->"),
-                                ("e", "< "),
-                                ("f", "&xxx;"),
-                                ("g", " !"),
-                                ("h", "&#500;"),
-                                ("i", "x?a=b&c=d;"),
-                                ("j", "&#42;"),
-                                ("k", "&#42;"),
-                                ])])
-
-    def test_convert_overrides(self):
-        # This checks that the character and entity reference
-        # conversion helpers are called at the documented times.  No
-        # attempt is made to really change what the parser accepts.
-        #
-        self.collector = HTMLEntityCollector
-        self.check_events(('<a title="&ldquo;test&#x201d;">foo</a>'
-                           '&foobar;&#42;'), [
-            ('entityref', 'convert', 'ldquo'),
-            ('charref', 'convert', 'x201d'),
-            ('starttag', 'a', [('title', '&ldquo;test&#x201d;')]),
-            ('data', 'foo'),
-            ('endtag', 'a'),
-            ('entityref', 'foobar'),
-            ('entityref', 'convert', 'foobar'),
-            ('charref', '42'),
-            ('charref', 'convert', '42'),
-            ('codepoint', 'convert', 42),
-            ])
-
-    def test_attr_funky_names(self):
-        self.check_events("""<a a.b='v' c:d=v e-f=v>""", [
-            ("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]),
-            ])
-
-    def test_attr_value_ip6_url(self):
-        # http://www.python.org/sf/853506
-        self.check_events(("<a href='http://[1080::8:800:200C:417A]/'>"
-                           "<a href=http://[1080::8:800:200C:417A]/>"), [
-            ("starttag", "a", [("href", "http://[1080::8:800:200C:417A]/")]),
-            ("starttag", "a", [("href", "http://[1080::8:800:200C:417A]/")]),
-            ])
-
-    def test_illegal_declarations(self):
-        s = 'abc<!spacer type="block" height="25">def'
-        self.check_events(s, [
-            ("data", "abc"),
-            ("unknown decl", 'spacer type="block" height="25"'),
-            ("data", "def"),
-            ])
-
-    def test_weird_starttags(self):
-        self.check_events("<a<a>", [
-            ("starttag", "a", []),
-            ("starttag", "a", []),
-            ])
-        self.check_events("</a<a>", [
-            ("endtag", "a"),
-            ("starttag", "a", []),
-            ])
-
-    def test_declaration_junk_chars(self):
-        self.check_parse_error("<!DOCTYPE foo $ >")
-
-    def test_get_starttag_text(self):
-        s = """<foobar   \n   one="1"\ttwo=2   >"""
-        self.check_events(s, [
-            ("starttag", "foobar", [("one", "1"), ("two", "2")]),
-            ])
-
-    def test_cdata_content(self):
-        s = ("<cdata> <!-- not a comment --> &not-an-entity-ref; </cdata>"
-             "<notcdata> <!-- comment --> </notcdata>")
-        self.collector = CDATAEventCollector
-        self.check_events(s, [
-            ("starttag", "cdata", []),
-            ("data", " <!-- not a comment --> &not-an-entity-ref; "),
-            ("endtag", "cdata"),
-            ("starttag", "notcdata", []),
-            ("data", " "),
-            ("comment", " comment "),
-            ("data", " "),
-            ("endtag", "notcdata"),
-            ])
-        s = """<cdata> <not a='start tag'> </cdata>"""
-        self.check_events(s, [
-            ("starttag", "cdata", []),
-            ("data", " <not a='start tag'> "),
-            ("endtag", "cdata"),
-            ])
-
-    def test_illegal_declarations(self):
-        s = 'abc<!spacer type="block" height="25">def'
-        self.check_events(s, [
-            ("data", "abc"),
-            ("unknown decl", 'spacer type="block" height="25"'),
-            ("data", "def"),
-            ])
-
-    def test_enumerated_attr_type(self):
-        s = "<!DOCTYPE doc [<!ATTLIST doc attr (a | b) >]>"
-        self.check_events(s, [
-            ('decl', 'DOCTYPE doc [<!ATTLIST doc attr (a | b) >]'),
-            ])
-
-    def test_read_chunks(self):
-        # SF bug #1541697, this caused sgml parser to hang
-        # Just verify this code doesn't cause a hang.
-        CHUNK = 1024  # increasing this to 8212 makes the problem go away
-
-        f = open(support.findfile('sgml_input.html'), encoding="latin-1")
-        fp = sgmllib.SGMLParser()
-        while 1:
-            data = f.read(CHUNK)
-            fp.feed(data)
-            if len(data) != CHUNK:
-                break
-
-    # XXX These tests have been disabled by prefixing their names with
-    # an underscore.  The first two exercise outstanding bugs in the
-    # sgmllib module, and the third exhibits questionable behavior
-    # that needs to be carefully considered before changing it.
-
-    def _test_starttag_end_boundary(self):
-        self.check_events("<a b='<'>", [("starttag", "a", [("b", "<")])])
-        self.check_events("<a b='>'>", [("starttag", "a", [("b", ">")])])
-
-    def _test_buffer_artefacts(self):
-        output = [("starttag", "a", [("b", "<")])]
-        self.check_events(["<a b='<'>"], output)
-        self.check_events(["<a ", "b='<'>"], output)
-        self.check_events(["<a b", "='<'>"], output)
-        self.check_events(["<a b=", "'<'>"], output)
-        self.check_events(["<a b='<", "'>"], output)
-        self.check_events(["<a b='<'", ">"], output)
-
-        output = [("starttag", "a", [("b", ">")])]
-        self.check_events(["<a b='>'>"], output)
-        self.check_events(["<a ", "b='>'>"], output)
-        self.check_events(["<a b", "='>'>"], output)
-        self.check_events(["<a b=", "'>'>"], output)
-        self.check_events(["<a b='>", "'>"], output)
-        self.check_events(["<a b='>'", ">"], output)
-
-        output = [("comment", "abc")]
-        self.check_events(["", "<!--abc-->"], output)
-        self.check_events(["<", "!--abc-->"], output)
-        self.check_events(["<!", "--abc-->"], output)
-        self.check_events(["<!-", "-abc-->"], output)
-        self.check_events(["<!--", "abc-->"], output)
-        self.check_events(["<!--a", "bc-->"], output)
-        self.check_events(["<!--ab", "c-->"], output)
-        self.check_events(["<!--abc", "-->"], output)
-        self.check_events(["<!--abc-", "->"], output)
-        self.check_events(["<!--abc--", ">"], output)
-        self.check_events(["<!--abc-->", ""], output)
-
-    def _test_starttag_junk_chars(self):
-        self.check_parse_error("<")
-        self.check_parse_error("<>")
-        self.check_parse_error("</$>")
-        self.check_parse_error("</")
-        self.check_parse_error("</a")
-        self.check_parse_error("<$")
-        self.check_parse_error("<$>")
-        self.check_parse_error("<!")
-        self.check_parse_error("<a $>")
-        self.check_parse_error("<a")
-        self.check_parse_error("<a foo='bar'")
-        self.check_parse_error("<a foo='bar")
-        self.check_parse_error("<a foo='>'")
-        self.check_parse_error("<a foo='>")
-        self.check_parse_error("<a foo=>")
-
-
-def test_main():
-    support.run_unittest(SGMLParserTestCase)
-
-
-if __name__ == "__main__":
-    test_main()