EmbeddedPkg: Extend NvVarStoreFormattedLib LIBRARY_CLASS

[mirror_edk2.git] / AppPkg / Applications / Python / Python-2.7.2 / Lib / test / test_sgmllib.py

import pprint\r
import re\r
import unittest\r
from test import test_support\r
sgmllib = test_support.import_module('sgmllib', deprecated=True)\r
\r
\r
class EventCollector(sgmllib.SGMLParser):\r
\r
    def __init__(self):\r
        self.events = []\r
        self.append = self.events.append\r
        sgmllib.SGMLParser.__init__(self)\r
\r
    def get_events(self):\r
        # Normalize the list of events so that buffer artefacts don't\r
        # separate runs of contiguous characters.\r
        L = []\r
        prevtype = None\r
        for event in self.events:\r
            type = event[0]\r
            if type == prevtype == "data":\r
                L[-1] = ("data", L[-1][1] + event[1])\r
            else:\r
                L.append(event)\r
            prevtype = type\r
        self.events = L\r
        return L\r
\r
    # structure markup\r
\r
    def unknown_starttag(self, tag, attrs):\r
        self.append(("starttag", tag, attrs))\r
\r
    def unknown_endtag(self, tag):\r
        self.append(("endtag", tag))\r
\r
    # all other markup\r
\r
    def handle_comment(self, data):\r
        self.append(("comment", data))\r
\r
    def handle_charref(self, data):\r
        self.append(("charref", data))\r
\r
    def handle_data(self, data):\r
        self.append(("data", data))\r
\r
    def handle_decl(self, decl):\r
        self.append(("decl", decl))\r
\r
    def handle_entityref(self, data):\r
        self.append(("entityref", data))\r
\r
    def handle_pi(self, data):\r
        self.append(("pi", data))\r
\r
    def unknown_decl(self, decl):\r
        self.append(("unknown decl", decl))\r
\r
\r
class CDATAEventCollector(EventCollector):\r
    def start_cdata(self, attrs):\r
        self.append(("starttag", "cdata", attrs))\r
        self.setliteral()\r
\r
\r
class HTMLEntityCollector(EventCollector):\r
\r
    entity_or_charref = re.compile('(?:&([a-zA-Z][-.a-zA-Z0-9]*)'\r
        '|&#(x[0-9a-zA-Z]+|[0-9]+))(;?)')\r
\r
    def convert_charref(self, name):\r
        self.append(("charref", "convert", name))\r
        if name[0] != "x":\r
            return EventCollector.convert_charref(self, name)\r
\r
    def convert_codepoint(self, codepoint):\r
        self.append(("codepoint", "convert", codepoint))\r
        EventCollector.convert_codepoint(self, codepoint)\r
\r
    def convert_entityref(self, name):\r
        self.append(("entityref", "convert", name))\r
        return EventCollector.convert_entityref(self, name)\r
\r
    # These to record that they were called, then pass the call along\r
    # to the default implementation so that it's actions can be\r
    # recorded.\r
\r
    def handle_charref(self, data):\r
        self.append(("charref", data))\r
        sgmllib.SGMLParser.handle_charref(self, data)\r
\r
    def handle_entityref(self, data):\r
        self.append(("entityref", data))\r
        sgmllib.SGMLParser.handle_entityref(self, data)\r
\r
\r
class SGMLParserTestCase(unittest.TestCase):\r
\r
    collector = EventCollector\r
\r
    def get_events(self, source):\r
        parser = self.collector()\r
        try:\r
            for s in source:\r
                parser.feed(s)\r
            parser.close()\r
        except:\r
            #self.events = parser.events\r
            raise\r
        return parser.get_events()\r
\r
    def check_events(self, source, expected_events):\r
        try:\r
            events = self.get_events(source)\r
        except:\r
            #import sys\r
            #print >>sys.stderr, pprint.pformat(self.events)\r
            raise\r
        if events != expected_events:\r
            self.fail("received events did not match expected events\n"\r
                      "Expected:\n" + pprint.pformat(expected_events) +\r
                      "\nReceived:\n" + pprint.pformat(events))\r
\r
    def check_parse_error(self, source):\r
        parser = EventCollector()\r
        try:\r
            parser.feed(source)\r
            parser.close()\r
        except sgmllib.SGMLParseError:\r
            pass\r
        else:\r
            self.fail("expected SGMLParseError for %r\nReceived:\n%s"\r
                      % (source, pprint.pformat(parser.get_events())))\r
\r
    def test_doctype_decl_internal(self):\r
        inside = """\\r
DOCTYPE html PUBLIC '-//W3C//DTD HTML 4.01//EN'\r
             SYSTEM 'http://www.w3.org/TR/html401/strict.dtd' [\r
  <!ELEMENT html - O EMPTY>\r
  <!ATTLIST html\r
      version CDATA #IMPLIED\r
      profile CDATA 'DublinCore'>\r
  <!NOTATION datatype SYSTEM 'http://xml.python.org/notations/python-module'>\r
  <!ENTITY myEntity 'internal parsed entity'>\r
  <!ENTITY anEntity SYSTEM 'http://xml.python.org/entities/something.xml'>\r
  <!ENTITY % paramEntity 'name|name|name'>\r
  %paramEntity;\r
  <!-- comment -->\r
]"""\r
        self.check_events(["<!%s>" % inside], [\r
            ("decl", inside),\r
            ])\r
\r
    def test_doctype_decl_external(self):\r
        inside = "DOCTYPE html PUBLIC '-//W3C//DTD HTML 4.01//EN'"\r
        self.check_events("<!%s>" % inside, [\r
            ("decl", inside),\r
            ])\r
\r
    def test_underscore_in_attrname(self):\r
        # SF bug #436621\r
        """Make sure attribute names with underscores are accepted"""\r
        self.check_events("<a has_under _under>", [\r
            ("starttag", "a", [("has_under", "has_under"),\r
                               ("_under", "_under")]),\r
            ])\r
\r
    def test_underscore_in_tagname(self):\r
        # SF bug #436621\r
        """Make sure tag names with underscores are accepted"""\r
        self.check_events("<has_under></has_under>", [\r
            ("starttag", "has_under", []),\r
            ("endtag", "has_under"),\r
            ])\r
\r
    def test_quotes_in_unquoted_attrs(self):\r
        # SF bug #436621\r
        """Be sure quotes in unquoted attributes are made part of the value"""\r
        self.check_events("<a href=foo'bar\"baz>", [\r
            ("starttag", "a", [("href", "foo'bar\"baz")]),\r
            ])\r
\r
    def test_xhtml_empty_tag(self):\r
        """Handling of XHTML-style empty start tags"""\r
        self.check_events("<br />text<i></i>", [\r
            ("starttag", "br", []),\r
            ("data", "text"),\r
            ("starttag", "i", []),\r
            ("endtag", "i"),\r
            ])\r
\r
    def test_processing_instruction_only(self):\r
        self.check_events("<?processing instruction>", [\r
            ("pi", "processing instruction"),\r
            ])\r
\r
    def test_bad_nesting(self):\r
        self.check_events("<a><b></a></b>", [\r
            ("starttag", "a", []),\r
            ("starttag", "b", []),\r
            ("endtag", "a"),\r
            ("endtag", "b"),\r
            ])\r
\r
    def test_bare_ampersands(self):\r
        self.check_events("this text & contains & ampersands &", [\r
            ("data", "this text & contains & ampersands &"),\r
            ])\r
\r
    def test_bare_pointy_brackets(self):\r
        self.check_events("this < text > contains < bare>pointy< brackets", [\r
            ("data", "this < text > contains < bare>pointy< brackets"),\r
            ])\r
\r
    def test_attr_syntax(self):\r
        output = [\r
          ("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", "e")])\r
          ]\r
        self.check_events("""<a b='v' c="v" d=v e>""", output)\r
        self.check_events("""<a  b = 'v' c = "v" d = v e>""", output)\r
        self.check_events("""<a\nb\n=\n'v'\nc\n=\n"v"\nd\n=\nv\ne>""", output)\r
        self.check_events("""<a\tb\t=\t'v'\tc\t=\t"v"\td\t=\tv\te>""", output)\r
\r
    def test_attr_values(self):\r
        self.check_events("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""",\r
                        [("starttag", "a", [("b", "xxx\n\txxx"),\r
                                            ("c", "yyy\t\nyyy"),\r
                                            ("d", "\txyz\n")])\r
                         ])\r
        self.check_events("""<a b='' c="">""", [\r
            ("starttag", "a", [("b", ""), ("c", "")]),\r
            ])\r
        # URL construction stuff from RFC 1808:\r
        safe = "$-_.+"\r
        extra = "!*'(),"\r
        reserved = ";/?:@&="\r
        url = "http://example.com:8080/path/to/file?%s%s%s" % (\r
            safe, extra, reserved)\r
        self.check_events("""<e a=%s>""" % url, [\r
            ("starttag", "e", [("a", url)]),\r
            ])\r
        # Regression test for SF patch #669683.\r
        self.check_events("<e a=rgb(1,2,3)>", [\r
            ("starttag", "e", [("a", "rgb(1,2,3)")]),\r
            ])\r
\r
    def test_attr_values_entities(self):\r
        """Substitution of entities and charrefs in attribute values"""\r
        # SF bug #1452246\r
        self.check_events("""<a b=&lt; c=&lt;&gt; d=&lt-&gt; e='&lt; '\r
                                f="&xxx;" g='&#32;&#33;' h='&#500;'\r
                                i='x?a=b&c=d;'\r
                                j='&amp;#42;' k='&#38;#42;'>""",\r
            [("starttag", "a", [("b", "<"),\r
                                ("c", "<>"),\r
                                ("d", "&lt->"),\r
                                ("e", "< "),\r
                                ("f", "&xxx;"),\r
                                ("g", " !"),\r
                                ("h", "&#500;"),\r
                                ("i", "x?a=b&c=d;"),\r
                                ("j", "&#42;"),\r
                                ("k", "&#42;"),\r
                                ])])\r
\r
    def test_convert_overrides(self):\r
        # This checks that the character and entity reference\r
        # conversion helpers are called at the documented times.  No\r
        # attempt is made to really change what the parser accepts.\r
        #\r
        self.collector = HTMLEntityCollector\r
        self.check_events(('<a title="&ldquo;test&#x201d;">foo</a>'\r
                           '&foobar;&#42;'), [\r
            ('entityref', 'convert', 'ldquo'),\r
            ('charref', 'convert', 'x201d'),\r
            ('starttag', 'a', [('title', '&ldquo;test&#x201d;')]),\r
            ('data', 'foo'),\r
            ('endtag', 'a'),\r
            ('entityref', 'foobar'),\r
            ('entityref', 'convert', 'foobar'),\r
            ('charref', '42'),\r
            ('charref', 'convert', '42'),\r
            ('codepoint', 'convert', 42),\r
            ])\r
\r
    def test_attr_funky_names(self):\r
        self.check_events("""<a a.b='v' c:d=v e-f=v>""", [\r
            ("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]),\r
            ])\r
\r
    def test_attr_value_ip6_url(self):\r
        # http://www.python.org/sf/853506\r
        self.check_events(("<a href='http://[1080::8:800:200C:417A]/'>"\r
                           "<a href=http://[1080::8:800:200C:417A]/>"), [\r
            ("starttag", "a", [("href", "http://[1080::8:800:200C:417A]/")]),\r
            ("starttag", "a", [("href", "http://[1080::8:800:200C:417A]/")]),\r
            ])\r
\r
    def test_weird_starttags(self):\r
        self.check_events("<a<a>", [\r
            ("starttag", "a", []),\r
            ("starttag", "a", []),\r
            ])\r
        self.check_events("</a<a>", [\r
            ("endtag", "a"),\r
            ("starttag", "a", []),\r
            ])\r
\r
    def test_declaration_junk_chars(self):\r
        self.check_parse_error("<!DOCTYPE foo $ >")\r
\r
    def test_get_starttag_text(self):\r
        s = """<foobar   \n   one="1"\ttwo=2   >"""\r
        self.check_events(s, [\r
            ("starttag", "foobar", [("one", "1"), ("two", "2")]),\r
            ])\r
\r
    def test_cdata_content(self):\r
        s = ("<cdata> <!-- not a comment --> &not-an-entity-ref; </cdata>"\r
             "<notcdata> <!-- comment --> </notcdata>")\r
        self.collector = CDATAEventCollector\r
        self.check_events(s, [\r
            ("starttag", "cdata", []),\r
            ("data", " <!-- not a comment --> &not-an-entity-ref; "),\r
            ("endtag", "cdata"),\r
            ("starttag", "notcdata", []),\r
            ("data", " "),\r
            ("comment", " comment "),\r
            ("data", " "),\r
            ("endtag", "notcdata"),\r
            ])\r
        s = """<cdata> <not a='start tag'> </cdata>"""\r
        self.check_events(s, [\r
            ("starttag", "cdata", []),\r
            ("data", " <not a='start tag'> "),\r
            ("endtag", "cdata"),\r
            ])\r
\r
    def test_illegal_declarations(self):\r
        s = 'abc<!spacer type="block" height="25">def'\r
        self.check_events(s, [\r
            ("data", "abc"),\r
            ("unknown decl", 'spacer type="block" height="25"'),\r
            ("data", "def"),\r
            ])\r
\r
    def test_enumerated_attr_type(self):\r
        s = "<!DOCTYPE doc [<!ATTLIST doc attr (a | b) >]>"\r
        self.check_events(s, [\r
            ('decl', 'DOCTYPE doc [<!ATTLIST doc attr (a | b) >]'),\r
            ])\r
\r
    def test_read_chunks(self):\r
        # SF bug #1541697, this caused sgml parser to hang\r
        # Just verify this code doesn't cause a hang.\r
        CHUNK = 1024  # increasing this to 8212 makes the problem go away\r
\r
        f = open(test_support.findfile('sgml_input.html'))\r
        fp = sgmllib.SGMLParser()\r
        while 1:\r
            data = f.read(CHUNK)\r
            fp.feed(data)\r
            if len(data) != CHUNK:\r
                break\r
\r
    def test_only_decode_ascii(self):\r
        # SF bug #1651995, make sure non-ascii character references are not decoded\r
        s = '<signs exclamation="&#33" copyright="&#169" quoteleft="&#8216;">'\r
        self.check_events(s, [\r
            ('starttag', 'signs',\r
             [('exclamation', '!'), ('copyright', '&#169'),\r
              ('quoteleft', '&#8216;')]),\r
            ])\r
\r
    # XXX These tests have been disabled by prefixing their names with\r
    # an underscore.  The first two exercise outstanding bugs in the\r
    # sgmllib module, and the third exhibits questionable behavior\r
    # that needs to be carefully considered before changing it.\r
\r
    def _test_starttag_end_boundary(self):\r
        self.check_events("<a b='<'>", [("starttag", "a", [("b", "<")])])\r
        self.check_events("<a b='>'>", [("starttag", "a", [("b", ">")])])\r
\r
    def _test_buffer_artefacts(self):\r
        output = [("starttag", "a", [("b", "<")])]\r
        self.check_events(["<a b='<'>"], output)\r
        self.check_events(["<a ", "b='<'>"], output)\r
        self.check_events(["<a b", "='<'>"], output)\r
        self.check_events(["<a b=", "'<'>"], output)\r
        self.check_events(["<a b='<", "'>"], output)\r
        self.check_events(["<a b='<'", ">"], output)\r
\r
        output = [("starttag", "a", [("b", ">")])]\r
        self.check_events(["<a b='>'>"], output)\r
        self.check_events(["<a ", "b='>'>"], output)\r
        self.check_events(["<a b", "='>'>"], output)\r
        self.check_events(["<a b=", "'>'>"], output)\r
        self.check_events(["<a b='>", "'>"], output)\r
        self.check_events(["<a b='>'", ">"], output)\r
\r
        output = [("comment", "abc")]\r
        self.check_events(["", "<!--abc-->"], output)\r
        self.check_events(["<", "!--abc-->"], output)\r
        self.check_events(["<!", "--abc-->"], output)\r
        self.check_events(["<!-", "-abc-->"], output)\r
        self.check_events(["<!--", "abc-->"], output)\r
        self.check_events(["<!--a", "bc-->"], output)\r
        self.check_events(["<!--ab", "c-->"], output)\r
        self.check_events(["<!--abc", "-->"], output)\r
        self.check_events(["<!--abc-", "->"], output)\r
        self.check_events(["<!--abc--", ">"], output)\r
        self.check_events(["<!--abc-->", ""], output)\r
\r
    def _test_starttag_junk_chars(self):\r
        self.check_parse_error("<")\r
        self.check_parse_error("<>")\r
        self.check_parse_error("</$>")\r
        self.check_parse_error("</")\r
        self.check_parse_error("</a")\r
        self.check_parse_error("<$")\r
        self.check_parse_error("<$>")\r
        self.check_parse_error("<!")\r
        self.check_parse_error("<a $>")\r
        self.check_parse_error("<a")\r
        self.check_parse_error("<a foo='bar'")\r
        self.check_parse_error("<a foo='bar")\r
        self.check_parse_error("<a foo='>'")\r
        self.check_parse_error("<a foo='>")\r
        self.check_parse_error("<a foo=>")\r
\r
\r
def test_main():\r
    test_support.run_unittest(SGMLParserTestCase)\r
\r
\r
if __name__ == "__main__":\r
    test_main()\r