<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="content-type" content="text/html; charset=utf-8" />
<title>[205521] trunk</title>
</head>
<body>
<style type="text/css"><!--
#msg dl.meta { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dl.meta dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer, #logmsg { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; }
#msg dl a { font-weight: bold}
#msg dl a:link { color:#fc3; }
#msg dl a:active { color:#ff0; }
#msg dl a:visited { color:#cc6; }
h3 { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; font-weight: bold; }
#msg pre { overflow: auto; background: #ffc; border: 1px #fa0 solid; padding: 6px; }
#logmsg { background: #ffc; border: 1px #fa0 solid; padding: 1em 1em 0 1em; }
#logmsg p, #logmsg pre, #logmsg blockquote { margin: 0 0 1em 0; }
#logmsg p, #logmsg li, #logmsg dt, #logmsg dd { line-height: 14pt; }
#logmsg h1, #logmsg h2, #logmsg h3, #logmsg h4, #logmsg h5, #logmsg h6 { margin: .5em 0; }
#logmsg h1:first-child, #logmsg h2:first-child, #logmsg h3:first-child, #logmsg h4:first-child, #logmsg h5:first-child, #logmsg h6:first-child { margin-top: 0; }
#logmsg ul, #logmsg ol { padding: 0; list-style-position: inside; margin: 0 0 0 1em; }
#logmsg ul { text-indent: -1em; padding-left: 1em; }#logmsg ol { text-indent: -1.5em; padding-left: 1.5em; }
#logmsg > ul, #logmsg > ol { margin: 0 0 1em 0; }
#logmsg pre { background: #eee; padding: 1em; }
#logmsg blockquote { border: 1px solid #fa0; border-left-width: 10px; padding: 1em 1em 0 1em; background: white;}
#logmsg dl { margin: 0; }
#logmsg dt { font-weight: bold; }
#logmsg dd { margin: 0; padding: 0 0 0.5em 0; }
#logmsg dd:before { content:'\00bb';}
#logmsg table { border-spacing: 0px; border-collapse: collapse; border-top: 4px solid #fa0; border-bottom: 1px solid #fa0; background: #fff; }
#logmsg table th { text-align: left; font-weight: normal; padding: 0.2em 0.5em; border-top: 1px dotted #fa0; }
#logmsg table td { text-align: right; border-top: 1px dotted #fa0; padding: 0.2em 0.5em; }
#logmsg table thead th { text-align: center; border-bottom: 1px solid #fa0; }
#logmsg table th.Corner { text-align: left; }
#logmsg hr { border: none 0; border-top: 2px dashed #fa0; height: 1px; }
#header, #footer { color: #fff; background: #636; border: 1px #300 solid; padding: 6px; }
#patch { width: 100%; }
#patch h4 {font-family: verdana,arial,helvetica,sans-serif;font-size:10pt;padding:8px;background:#369;color:#fff;margin:0;}
#patch .propset h4, #patch .binary h4 {margin:0;}
#patch pre {padding:0;line-height:1.2em;margin:0;}
#patch .diff {width:100%;background:#eee;padding: 0 0 10px 0;overflow:auto;}
#patch .propset .diff, #patch .binary .diff {padding:10px 0;}
#patch span {display:block;padding:0 10px;}
#patch .modfile, #patch .addfile, #patch .delfile, #patch .propset, #patch .binary, #patch .copfile {border:1px solid #ccc;margin:10px 0;}
#patch ins {background:#dfd;text-decoration:none;display:block;padding:0 10px;}
#patch del {background:#fdd;text-decoration:none;display:block;padding:0 10px;}
#patch .lines, .info {color:#888;background:#fff;}
--></style>
<div id="msg">
<dl class="meta">
<dt>Revision</dt> <dd><a href="http://trac.webkit.org/projects/webkit/changeset/205521">205521</a></dd>
<dt>Author</dt> <dd>achristensen@apple.com</dd>
<dt>Date</dt> <dd>2016-09-06 16:36:36 -0700 (Tue, 06 Sep 2016)</dd>
</dl>
<h3>Log Message</h3>
<pre>Punycode encode non-ascii hosts in URLParser
https://bugs.webkit.org/show_bug.cgi?id=161655
Reviewed by Tim Horton.
Source/WebCore:
Covered by new API tests based on the web platform tests.
* platform/URLParser.cpp:
(WebCore::URLParser::parse):
(WebCore::containsOnlyASCII):
(WebCore::domainToASCII):
Tools:
* TestWebKitAPI/Tests/WebCore/URLParser.cpp:
(TestWebKitAPI::wideString):
(TestWebKitAPI::TEST_F):</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunkSourceWebCoreChangeLog">trunk/Source/WebCore/ChangeLog</a></li>
<li><a href="#trunkSourceWebCoreplatformURLParsercpp">trunk/Source/WebCore/platform/URLParser.cpp</a></li>
<li><a href="#trunkToolsChangeLog">trunk/Tools/ChangeLog</a></li>
<li><a href="#trunkToolsTestWebKitAPITestsWebCoreURLParsercpp">trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunkSourceWebCoreChangeLog"></a>
<div class="modfile"><h4>Modified: trunk/Source/WebCore/ChangeLog (205520 => 205521)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Source/WebCore/ChangeLog 2016-09-06 23:22:01 UTC (rev 205520)
+++ trunk/Source/WebCore/ChangeLog 2016-09-06 23:36:36 UTC (rev 205521)
</span><span class="lines">@@ -1,3 +1,17 @@
</span><ins>+2016-09-06 Alex Christensen <achristensen@webkit.org>
+
+ Punycode encode non-ascii hosts in URLParser
+ https://bugs.webkit.org/show_bug.cgi?id=161655
+
+ Reviewed by Tim Horton.
+
+ Covered by new API tests based on the web platform tests.
+
+ * platform/URLParser.cpp:
+ (WebCore::URLParser::parse):
+ (WebCore::containsOnlyASCII):
+ (WebCore::domainToASCII):
+
</ins><span class="cx"> 2016-09-06 Saam Barati <sbarati@apple.com>
</span><span class="cx">
</span><span class="cx"> Make JSMap and JSSet faster
</span></span></pre></div>
<a id="trunkSourceWebCoreplatformURLParsercpp"></a>
<div class="modfile"><h4>Modified: trunk/Source/WebCore/platform/URLParser.cpp (205520 => 205521)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Source/WebCore/platform/URLParser.cpp 2016-09-06 23:22:01 UTC (rev 205520)
+++ trunk/Source/WebCore/platform/URLParser.cpp 2016-09-06 23:36:36 UTC (rev 205521)
</span><span class="lines">@@ -28,6 +28,7 @@
</span><span class="cx">
</span><span class="cx"> #include "Logging.h"
</span><span class="cx"> #include <array>
</span><ins>+#include <unicode/uidna.h>
</ins><span class="cx"> #include <wtf/HashMap.h>
</span><span class="cx"> #include <wtf/NeverDestroyed.h>
</span><span class="cx"> #include <wtf/text/StringBuilder.h>
</span><span class="lines">@@ -450,7 +451,8 @@
</span><span class="cx"> case State::SchemeEndCheckForSlashes:
</span><span class="cx"> LOG_STATE("SchemeEndCheckForSlashes");
</span><span class="cx"> if (*c == '/') {
</span><del>- m_buffer.append('/');
</del><ins>+ m_buffer.append("//");
+ m_url.m_userStart = m_buffer.length();
</ins><span class="cx"> state = State::PathOrAuthority;
</span><span class="cx"> ++c;
</span><span class="cx"> } else {
</span><span class="lines">@@ -1269,11 +1271,44 @@
</span><span class="cx"> return output.toStringPreserveCapacity();
</span><span class="cx"> }
</span><span class="cx">
</span><ins>+static bool containsOnlyASCII(const String& string)
+{
+ if (string.is8Bit())
+ return charactersAreAllASCII(string.characters8(), string.length());
+ return charactersAreAllASCII(string.characters16(), string.length());
+}
+
</ins><span class="cx"> static Optional<String> domainToASCII(const String& domain)
</span><span class="cx"> {
</span><del>- // FIXME: Implement correctly
- CString utf8 = domain.utf8();
- return String(utf8.data(), utf8.length());
</del><ins>+ const unsigned hostnameBufferLength = 2048;
+
+ if (containsOnlyASCII(domain)) {
+ if (domain.is8Bit())
+ return domain;
+ Vector<LChar, hostnameBufferLength> buffer;
+ size_t length = domain.length();
+ buffer.reserveInitialCapacity(length);
+ for (size_t i = 0; i < length; ++i)
+ buffer.append(domain[i]);
+ return String(buffer.data(), length);
+ }
+
+ UChar hostnameBuffer[hostnameBufferLength];
+ UErrorCode error = U_ZERO_ERROR;
+
+ int32_t numCharactersConverted = uidna_IDNToASCII(StringView(domain).upconvertedCharacters(), domain.length(), hostnameBuffer, hostnameBufferLength, UIDNA_ALLOW_UNASSIGNED, nullptr, &error);
+
+ if (error == U_ZERO_ERROR) {
+ LChar buffer[hostnameBufferLength];
+ for (int32_t i = 0; i < numCharactersConverted; ++i) {
+ ASSERT(isASCII(hostnameBuffer[i]));
+ buffer[i] = hostnameBuffer[i];
+ }
+ return String(buffer, numCharactersConverted);
+ }
+
+ // FIXME: Check for U_BUFFER_OVERFLOW_ERROR and retry with an allocated buffer.
+ return Nullopt;
</ins><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> static bool hasInvalidDomainCharacter(const String& asciiDomain)
</span></span></pre></div>
<a id="trunkToolsChangeLog"></a>
<div class="modfile"><h4>Modified: trunk/Tools/ChangeLog (205520 => 205521)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Tools/ChangeLog 2016-09-06 23:22:01 UTC (rev 205520)
+++ trunk/Tools/ChangeLog 2016-09-06 23:36:36 UTC (rev 205521)
</span><span class="lines">@@ -1,3 +1,14 @@
</span><ins>+2016-09-06 Alex Christensen <achristensen@webkit.org>
+
+ Punycode encode non-ascii hosts in URLParser
+ https://bugs.webkit.org/show_bug.cgi?id=161655
+
+ Reviewed by Tim Horton.
+
+ * TestWebKitAPI/Tests/WebCore/URLParser.cpp:
+ (TestWebKitAPI::wideString):
+ (TestWebKitAPI::TEST_F):
+
</ins><span class="cx"> 2016-09-05 Alex Christensen <achristensen@webkit.org>
</span><span class="cx">
</span><span class="cx"> Implement relative file urls and begin implementing character encoding in URLParser
</span></span></pre></div>
<a id="trunkToolsTestWebKitAPITestsWebCoreURLParsercpp"></a>
<div class="modfile"><h4>Modified: trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp (205520 => 205521)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp 2016-09-06 23:22:01 UTC (rev 205520)
+++ trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp 2016-09-06 23:36:36 UTC (rev 205521)
</span><span class="lines">@@ -84,6 +84,16 @@
</span><span class="cx"> EXPECT_TRUE(URLParser::allValuesEqual(url, oldURL));
</span><span class="cx"> }
</span><span class="cx">
</span><ins>+template<size_t length>
+static String wideString(const wchar_t (&url)[length])
+{
+ StringBuilder builder;
+ builder.reserveCapacity(length - 1);
+ for (size_t i = 0; i < length - 1; ++i)
+ builder.append(url[i]);
+ return builder.toString();
+}
+
</ins><span class="cx"> TEST_F(URLParserTest, Basic)
</span><span class="cx"> {
</span><span class="cx"> checkURL("http://user:pass@webkit.org:123/path?query#fragment", {"http", "user", "pass", "webkit.org", 123, "/path", "query", "fragment", "http://user:pass@webkit.org:123/path?query#fragment"});
</span><span class="lines">@@ -209,6 +219,8 @@
</span><span class="cx"> checkRelativeURL("//whatwg.org/index.html", "https://www.webkit.org/path", {"https", "", "", "whatwg.org", 0, "/index.html", "", "", "https://whatwg.org/index.html"});
</span><span class="cx"> checkRelativeURL("http://example\t.\norg", "http://example.org/foo/bar", {"http", "", "", "example.org", 0, "/", "", "", "http://example.org/"});
</span><span class="cx"> checkRelativeURL("test", "file:///path1/path2", {"file", "", "", "", 0, "/path1/test", "", "", "file:///path1/test"});
</span><ins>+ checkRelativeURL(wideString(L"http://www.foo。bar.com"), "http://other.com/", {"http", "", "", "www.foo.bar.com", 0, "/", "", "", "http://www.foo.bar.com/"});
+ checkRelativeURL(wideString(L"sc://ñ.test/"), "about:blank", {"sc", "", "", "xn--ida.test", 0, "/", "", "", "sc://xn--ida.test/"});
</ins><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> static void checkURLDifferences(const String& urlString, const ExpectedParts& partsNew, const ExpectedParts& partsOld)
</span><span class="lines">@@ -351,6 +363,9 @@
</span><span class="cx"> {"http", "", "", "host%73", 0, "/", "", "", "http://host%73/"});
</span><span class="cx">
</span><span class="cx"> // URLParser matches Chrome and the spec, but not URL::parse or Firefox.
</span><ins>+ checkURLDifferences(wideString(L"http://０Ｘｃ０．０２５０．０１"),
+ {"http", "", "", "192.168.0.1", 0, "/", "", "", "http://192.168.0.1/"},
+ {"http", "", "", "0xc0.0250.01", 0, "/", "", "", "http://0xc0.0250.01/"});
</ins><span class="cx"> checkURLDifferences("http://host/path%2e.%2E",
</span><span class="cx"> {"http", "", "", "host", 0, "/path...", "", "", "http://host/path..."},
</span><span class="cx"> {"http", "", "", "host", 0, "/path%2e.%2E", "", "", "http://host/path%2e.%2E"});
</span></span></pre>
</div>
</div>
</body>
</html>