XHTML results from the CPAN

XHTML
Erlang-Parser
view release on metacpan or search on metacpan
             (CC =:= $c orelse CC =:= $C) andalso
             (RR =:= $r orelse RR =:= $R) andalso
             (II =:= $i orelse II =:= $I) andalso
             (PP =:= $p orelse PP =:= $P) andalso
             (TT=:= $t orelse TT =:= $T) andalso
             ?PROBABLE_CLOSE(ZZ) ->
            Len = O - Start,
            <<_:Start/binary, Raw:Len/binary, _/binary>> = Bin,
            {{data, Raw, false}, S};
        <<_:O/binary, C, _/binary>> ->
            tokenize_script(Bin, ?INC_CHAR(S, C), Start);
        <<_:Start/binary, Raw/binary>> ->
            {{data, Raw, false}, S}
    end.

tokenize_textarea(Bin, S=#decoder{offset=O}) ->
    tokenize_textarea(Bin, S, O).

tokenize_textarea(Bin, S=#decoder{offset=O}, Start) ->
    case Bin of
        %% Just a look-ahead, we want the end_tag separately
        <<_:O/binary, $<, $/, TT, EE, XX, TT2, AA, RR, EE2, AA2, ZZ, _/binary>>
        when (TT =:= $t orelse TT =:= $T) andalso
             (EE =:= $e orelse EE =:= $E) andalso
             (XX =:= $x orelse XX =:= $X) andalso
             (TT2 =:= $t orelse TT2 =:= $T) andalso
             (AA =:= $a orelse AA =:= $A) andalso
             (RR =:= $r orelse RR =:= $R) andalso
             (EE2 =:= $e orelse EE2 =:= $E) andalso
             (AA2 =:= $a orelse AA2 =:= $A) andalso
             ?PROBABLE_CLOSE(ZZ) ->
            Len = O - Start,
            <<_:Start/binary, Raw:Len/binary, _/binary>> = Bin,
            {{data, Raw, false}, S};
        <<_:O/binary, C, _/binary>> ->
            tokenize_textarea(Bin, ?INC_CHAR(S, C), Start);
        <<_:Start/binary, Raw/binary>> ->
            {{data, Raw, false}, S}
    end.


%%
%% Tests
%%
-ifdef(TEST).
-include_lib("eunit/include/eunit.hrl").

to_html_test() ->
    ?assertEqual(
       <<"<html><head><title>hey!</title></head><body><p class=\"foo\">what's up<br /></p><div>sucka</div>RAW!<!-- comment! --></body></html>">>,
       iolist_to_binary(
         to_html({html, [],
                  [{<<"head">>, [],
                    [{title, <<"hey!">>}]},
                   {body, [],
                    [{p, [{class, foo}], [<<"what's">>, <<" up">>, {br}]},
                     {'div', <<"sucka">>},
                     {'=', <<"RAW!">>},
                     {comment, <<" comment! ">>}]}]}))),
    ?assertEqual(
       <<"<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">">>,
       iolist_to_binary(
         to_html({doctype,
                  [<<"html">>, <<"PUBLIC">>,
                   <<"-//W3C//DTD XHTML 1.0 Transitional//EN">>,
                   <<"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">>]}))),
    ?assertEqual(
       <<"<html><?xml:namespace prefix=\"o\" ns=\"urn:schemas-microsoft-com:office:office\"?></html>">>,
       iolist_to_binary(
         to_html({<<"html">>,[],
                  [{pi, <<"xml:namespace">>,
                    [{<<"prefix">>,<<"o">>},
                     {<<"ns">>,<<"urn:schemas-microsoft-com:office:office">>}]}]}))),
    ok.

escape_test() ->
    ?assertEqual(
       <<"&amp;quot;\"word &gt;&lt;&lt;up!&amp;quot;">>,
       escape(<<"&quot;\"word ><<up!&quot;">>)),
    ?assertEqual(
       <<"&amp;quot;\"word &gt;&lt;&lt;up!&amp;quot;">>,
       escape("&quot;\"word ><<up!&quot;")),
    ?assertEqual(
       <<"&amp;quot;\"word &gt;&lt;&lt;up!&amp;quot;">>,
       escape('&quot;\"word ><<up!&quot;')),
    ok.

escape_attr_test() ->
    ?assertEqual(
       <<"&amp;quot;&quot;word &gt;&lt;&lt;up!&amp;quot;">>,
       escape_attr(<<"&quot;\"word ><<up!&quot;">>)),
    ?assertEqual(
       <<"&amp;quot;&quot;word &gt;&lt;&lt;up!&amp;quot;">>,
       escape_attr("&quot;\"word ><<up!&quot;")),
    ?assertEqual(
       <<"&amp;quot;&quot;word &gt;&lt;&lt;up!&amp;quot;">>,
       escape_attr('&quot;\"word ><<up!&quot;')),
    ?assertEqual(
       <<"12345">>,
       escape_attr(12345)),
    ?assertEqual(
       <<"1.5">>,
       escape_attr(1.5)),
    ok.

tokens_test() ->
    ?assertEqual(
       [{start_tag, <<"foo">>, [{<<"bar">>, <<"baz">>},
                                {<<"wibble">>, <<"wibble">>},
                                {<<"alice">>, <<"bob">>}], true}],
       tokens(<<"<foo bar=baz wibble='wibble' alice=\"bob\"/>">>)),
    ?assertEqual(
       [{start_tag, <<"foo">>, [{<<"bar">>, <<"baz">>},
                                {<<"wibble">>, <<"wibble">>},
                                {<<"alice">>, <<"bob">>}], true}],
       tokens(<<"<foo bar=baz wibble='wibble' alice=bob/>">>)),
    ?assertEqual(
       [{comment, <<"[if lt IE 7]>\n<style type=\"text/css\">\n.no_ie { display: none; }\n</style>\n<![endif]">>}],
       tokens(<<"<!--[if lt IE 7]>\n<style type=\"text/css\">\n.no_ie { display: none; }\n</style>\n<![endif]-->">>)),
    ?assertEqual(
       [{start_tag, <<"script">>, [{<<"type">>, <<"text/javascript">>}], false},
        {data, <<" A= B <= C ">>, false},
        {end_tag, <<"script">>}],
       tokens(<<"<script type=\"text/javascript\"> A= B <= C </script>">>)),
    ?assertEqual(
( run in 0.674 second using v1.01-cache-2.11-cpan-98d9bbf8dc8 )