diff options
Diffstat (limited to 'parser/html/java/htmlparser/ruby-gcj/test')
4 files changed, 28 insertions, 0 deletions
diff --git a/parser/html/java/htmlparser/ruby-gcj/test/domencoding.rb b/parser/html/java/htmlparser/ruby-gcj/test/domencoding.rb new file mode 100644 index 000000000..1beb94c10 --- /dev/null +++ b/parser/html/java/htmlparser/ruby-gcj/test/domencoding.rb @@ -0,0 +1,5 @@ +require 'nu/validator' + +ARGV.each do |arg| + puts Nu::Validator::parse(open(arg)).root.name +end diff --git a/parser/html/java/htmlparser/ruby-gcj/test/fonts.rb b/parser/html/java/htmlparser/ruby-gcj/test/fonts.rb new file mode 100644 index 000000000..595e3ae06 --- /dev/null +++ b/parser/html/java/htmlparser/ruby-gcj/test/fonts.rb @@ -0,0 +1,11 @@ +require 'nu/validator' +require 'open-uri' + +ARGV.each do |arg| + doc = Nu::Validator::parse(open(arg)) + doc.xpath("//*[local-name()='font']").each do |font| + font.attributes.each do |name, attr| + puts "#{name} => #{attr.value}" + end + end +end diff --git a/parser/html/java/htmlparser/ruby-gcj/test/google.html b/parser/html/java/htmlparser/ruby-gcj/test/google.html new file mode 100644 index 000000000..8d2183b29 --- /dev/null +++ b/parser/html/java/htmlparser/ruby-gcj/test/google.html @@ -0,0 +1,10 @@ +<!doctype html><html><head><meta http-equiv="content-type" content="text/html; charset=ISO-8859-1"><title>Google</title><script>window.google={kEI:"vLhASujeGpTU9QT2iOnWAQ",kEXPI:"17259",kCSIE:"17259",kHL:"en"}; +window.google.sn="webhp";window.google.timers={load:{t:{start:(new Date).getTime()}}};try{window.google.pt=window.gtbExternal&&window.gtbExternal.pageT()||window.external&&window.external.pageT}catch(b){} +window.google.jsrt_kill=1; +var _gjwl=location;function _gjuc(){var e=_gjwl.href.indexOf("#");if(e>=0){var a=_gjwl.href.substring(e);if(a.indexOf("&q=")>0||a.indexOf("#q=")>=0){a=a.substring(1);if(a.indexOf("#")==-1){for(var c=0;c<a.length;){var d=c;if(a.charAt(d)=="&")++d;var b=a.indexOf("&",d);if(b==-1)b=a.length;var f=a.substring(d,b);if(f.indexOf("fp=")==0){a=a.substring(0,c)+a.substring(b,a.length);b=c}else if(f=="cad=h")return 0;c=b}_gjwl.href="/search?"+a+"&cad=h";return 1}}}return 0}function _gjp(){!(window._gjwl.hash&& +window._gjuc())&&setTimeout(_gjp,500)}; +window._gjp && _gjp();</script><style>td{line-height:.8em;}.gac_c{line-height:normal;}form{margin-bottom:20px;}body,td,a,p,.h{font-family:arial,sans-serif}.h{color:#36c;font-size:20px}.q{color:#00c}.ts td{padding:0}.ts{border-collapse:collapse}#gbar{height:22px;padding-left:0px}.gbh,.gbd{border-top:1px solid #c9d7f1;font-size:1px}.gbh{height:0;position:absolute;top:24px;width:100%}#guser{padding-bottom:7px !important;text-align:right}#gbar,#guser{font-size:13px;padding-top:1px !important}@media all{.gb1,.gb3{height:22px;margin-right:.5em;vertical-align:top}#gbar{float:left}}a.gb1,a.gb3{color:#00c !important}.gb3{text-decoration:none}</style><script>google.y={};google.x=function(e,g){google.y[e.id]=[e,g];return false};</script></head><body bgcolor=#ffffff text=#000000 link=#0000cc vlink=#551a8b alink=#ff0000 onload="document.f.q.focus();if(document.images)new Image().src='/images/nav_logo4.png'" topmargin=3 marginheight=3><textarea id=csi style=display:none></textarea><iframe name=wgjf style="display:none"></iframe><div id=gbar><nobr><b class=gb1>Web</b> <a href="http://images.google.com/imghp?hl=en&tab=wi" class=gb1>Images</a> <a href="http://video.google.com/?hl=en&tab=wv" class=gb1>Video</a> <a href="http://maps.google.com/maps?hl=en&tab=wl" class=gb1>Maps</a> <a href="http://news.google.com/nwshp?hl=en&tab=wn" class=gb1>News</a> <a href="http://www.google.com/prdhp?hl=en&tab=wf" class=gb1>Shopping</a> <a href="http://mail.google.com/mail/?hl=en&tab=wm" class=gb1>Gmail</a> <a href="http://www.google.com/intl/en/options/" class=gb3><u>more</u> »</a></nobr></div><div id=guser width=100%><nobr><a href="/url?sa=p&pref=ig&pval=3&q=http://www.google.com/ig%3Fhl%3Den%26source%3Diglk&usg=AFQjCNFA18XPfgb7dKnXfKz7x7g1GDH1tg">iGoogle</a> | <a href="https://www.google.com/accounts/Login?hl=en&continue=http://www.google.com/">Sign in</a></nobr></div><div class=gbh style=left:0></div><div class=gbh style=right:0></div><center><br clear=all id=lgpd><img alt="Google" height=110 src="/intl/en_ALL/images/logo.gif" width=276 id=logo onload="window.lol&&lol()"><br><br><form action="/search" name=f><table cellpadding=0 cellspacing=0><tr valign=top><td width=25%> </td><td align=center nowrap><input name=hl type=hidden value=en><input type=hidden name=ie value="ISO-8859-1"><input autocomplete="off" maxlength=2048 name=q size=55 title="Google Search" value=""><br><input name=btnG type=submit value="Google Search"><input name=btnI type=submit value="I'm Feeling Lucky"></td><td nowrap width=25% align=left><font size=-2> <a href=/advanced_search?hl=en>Advanced Search</a><br> <a href=/preferences?hl=en>Preferences</a><br> <a href=/language_tools?hl=en>Language Tools</a></font></td></tr></table></form><br><font size=-1><a href="/aclk?sa=L&ai=CqVchLbNASrv7IZa68gS13KTwAc3__IMB29PoogzB2ZzZExABIMFUUK_O0JX______wFgyQaqBAlP0BcDOBRYhqw&num=1&sig=AGiWqty21CD7ixNXZILwCnH7c_3n9v2-tg&q=http://www.allforgood.org#source=hpp">Find an opportunity to volunteer</a> in your community today.</font><br><br><br><font size=-1><a href="/intl/en/ads/">Advertising Programs</a> - <a href="/services/">Business Solutions</a> - <a href="/intl/en/about.html">About Google</a></font><p><font size=-2>©2009 - <a href="/intl/en/privacy.html">Privacy</a></font></p></center><div id=xjsd></div><div id=xjsi><script>if(google.y)google.y.first=[];if(google.y)google.y.first=[];google.dstr=[];google.rein=[];window.setTimeout(function(){var a=document.createElement("script");a.src="/extern_js/f/CgJlbhICdXMgACswCjggQAgsKzAOOAUsKzAYOAQsKzAlOMmIASwrMCY4BCwrMCc4ACw/1t0T7hspHT4.js";(document.getElementById("xjsd")||document.body).appendChild(a)},0); +;google.y.first.push(function(){google.ac.i(document.f,document.f.q,'','')});google.xjs&&google.j&&google.j.xi&&google.j.xi()</script></div><script>(function(){ +function a(){google.timers.load.t.ol=(new Date).getTime();google.report&&google.report(google.timers.load,{ei:google.kEI,e:google.kCSIE})}if(window.addEventListener)window.addEventListener("load",a,false);else if(window.attachEvent)window.attachEvent("onload",a);google.timers.load.t.prt=(new Date).getTime(); +})(); +</script>
\ No newline at end of file diff --git a/parser/html/java/htmlparser/ruby-gcj/test/greek.xml b/parser/html/java/htmlparser/ruby-gcj/test/greek.xml new file mode 100644 index 000000000..a14d23eb1 --- /dev/null +++ b/parser/html/java/htmlparser/ruby-gcj/test/greek.xml @@ -0,0 +1,2 @@ +<?xml version='1.0' encoding='iso-8859-7'?> +<root/> |