<!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>[206198] 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/206198">206198</a></dd>
<dt>Author</dt> <dd>achristensen@apple.com</dd>
<dt>Date</dt> <dd>2016-09-20 23:34:13 -0700 (Tue, 20 Sep 2016)</dd>
</dl>
<h3>Log Message</h3>
<pre>Optimize URLParser
https://bugs.webkit.org/show_bug.cgi?id=162105
Reviewed by Geoffrey Garen.
Source/WebCore:
Covered by new API tests.
This is about a 5% speedup on my URLParser benchmark.
* platform/URLParser.cpp:
(WebCore::percentEncodeByte):
(WebCore::utf8PercentEncode):
(WebCore::utf8QueryEncode):
(WebCore::encodeQuery):
(WebCore::URLParser::parse):
(WebCore::serializeURLEncodedForm):
(WebCore::percentEncode): Deleted.
(WebCore::utf8PercentEncodeQuery): Deleted.
Tools:
* TestWebKitAPI/Tests/WebCore/URLParser.cpp:
(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 (206197 => 206198)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Source/WebCore/ChangeLog        2016-09-21 06:17:13 UTC (rev 206197)
+++ trunk/Source/WebCore/ChangeLog        2016-09-21 06:34:13 UTC (rev 206198)
</span><span class="lines">@@ -1,3 +1,23 @@
</span><ins>+2016-09-20 Alex Christensen <achristensen@webkit.org>
+
+ Optimize URLParser
+ https://bugs.webkit.org/show_bug.cgi?id=162105
+
+ Reviewed by Geoffrey Garen.
+
+ Covered by new API tests.
+ This is about a 5% speedup on my URLParser benchmark.
+
+ * platform/URLParser.cpp:
+ (WebCore::percentEncodeByte):
+ (WebCore::utf8PercentEncode):
+ (WebCore::utf8QueryEncode):
+ (WebCore::encodeQuery):
+ (WebCore::URLParser::parse):
+ (WebCore::serializeURLEncodedForm):
+ (WebCore::percentEncode): Deleted.
+ (WebCore::utf8PercentEncodeQuery): Deleted.
+
</ins><span class="cx"> 2016-09-20 Carlos Garcia Campos <cgarcia@igalia.com>
</span><span class="cx">
</span><span class="cx"> [GTK] Clean up DataObjectGtk handling
</span></span></pre></div>
<a id="trunkSourceWebCoreplatformURLParsercpp"></a>
<div class="modfile"><h4>Modified: trunk/Source/WebCore/platform/URLParser.cpp (206197 => 206198)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Source/WebCore/platform/URLParser.cpp        2016-09-21 06:17:13 UTC (rev 206197)
+++ trunk/Source/WebCore/platform/URLParser.cpp        2016-09-21 06:34:13 UTC (rev 206198)
</span><span class="lines">@@ -457,7 +457,7 @@
</span><span class="cx"> return !isSlashQuestionOrHash(*iterator);
</span><span class="cx"> }
</span><span class="cx">
</span><del>-inline static void percentEncode(uint8_t byte, Vector<LChar>& buffer)
</del><ins>+inline static void percentEncodeByte(uint8_t byte, Vector<LChar>& buffer)
</ins><span class="cx"> {
</span><span class="cx"> buffer.append('%');
</span><span class="cx"> buffer.append(upperNibbleToASCIIHexDigit(byte));
</span><span class="lines">@@ -464,6 +464,9 @@
</span><span class="cx"> buffer.append(lowerNibbleToASCIIHexDigit(byte));
</span><span class="cx"> }
</span><span class="cx">
</span><ins>+const char* replacementCharacterUTF8PercentEncoded = "%EF%BF%BD";
+const size_t replacementCharacterUTF8PercentEncodedLength = 9;
+
</ins><span class="cx"> template<bool serialized>
</span><span class="cx"> inline static void utf8PercentEncode(UChar32 codePoint, Vector<LChar>& destination, bool(*isInCodeSet)(UChar32))
</span><span class="cx"> {
</span><span class="lines">@@ -472,23 +475,30 @@
</span><span class="cx"> ASSERT_WITH_SECURITY_IMPLICATION(!isInCodeSet(codePoint));
</span><span class="cx"> destination.append(codePoint);
</span><span class="cx"> } else {
</span><del>- if (isInCodeSet(codePoint)) {
- uint8_t buffer[U8_MAX_LENGTH];
- int32_t offset = 0;
- UBool error = false;
- U8_APPEND(buffer, offset, U8_MAX_LENGTH, codePoint, error);
- // FIXME: Check error.
- for (int32_t i = 0; i < offset; ++i)
- percentEncode(buffer[i], destination);
- } else {
- ASSERT_WITH_MESSAGE(isASCII(codePoint), "isInCodeSet should always return true for non-ASCII characters");
- destination.append(codePoint);
</del><ins>+ if (isASCII(codePoint)) {
+ if (isInCodeSet(codePoint))
+ percentEncodeByte(codePoint, destination);
+ else
+ destination.append(codePoint);
+ return;
</ins><span class="cx"> }
</span><ins>+ ASSERT_WITH_MESSAGE(isInCodeSet(codePoint), "isInCodeSet should always return true for non-ASCII characters");
+
+ if (!U_IS_UNICODE_CHAR(codePoint)) {
+ destination.append(replacementCharacterUTF8PercentEncoded, replacementCharacterUTF8PercentEncodedLength);
+ return;
+ }
+
+ uint8_t buffer[U8_MAX_LENGTH];
+ int32_t offset = 0;
+ U8_APPEND_UNSAFE(buffer, offset, codePoint);
+ for (int32_t i = 0; i < offset; ++i)
+ percentEncodeByte(buffer[i], destination);
</ins><span class="cx"> }
</span><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> template<bool serialized>
</span><del>-inline static void utf8PercentEncodeQuery(UChar32 codePoint, Vector<LChar>& destination)
</del><ins>+inline static void utf8QueryEncode(UChar32 codePoint, Vector<LChar>& destination)
</ins><span class="cx"> {
</span><span class="cx"> if (serialized) {
</span><span class="cx"> ASSERT_WITH_SECURITY_IMPLICATION(isASCII(codePoint));
</span><span class="lines">@@ -495,16 +505,26 @@
</span><span class="cx"> ASSERT_WITH_SECURITY_IMPLICATION(!shouldPercentEncodeQueryByte(codePoint));
</span><span class="cx"> destination.append(codePoint);
</span><span class="cx"> } else {
</span><ins>+ if (isASCII(codePoint)) {
+ if (shouldPercentEncodeQueryByte(codePoint))
+ percentEncodeByte(codePoint, destination);
+ else
+ destination.append(codePoint);
+ return;
+ }
+
+ if (!U_IS_UNICODE_CHAR(codePoint)) {
+ destination.append(replacementCharacterUTF8PercentEncoded, replacementCharacterUTF8PercentEncodedLength);
+ return;
+ }
+
</ins><span class="cx"> uint8_t buffer[U8_MAX_LENGTH];
</span><span class="cx"> int32_t offset = 0;
</span><del>- UBool error = false;
- U8_APPEND(buffer, offset, U8_MAX_LENGTH, codePoint, error);
- ASSERT_WITH_SECURITY_IMPLICATION(offset <= static_cast<int32_t>(sizeof(buffer)));
- // FIXME: Check error.
</del><ins>+ U8_APPEND_UNSAFE(buffer, offset, codePoint);
</ins><span class="cx"> for (int32_t i = 0; i < offset; ++i) {
</span><span class="cx"> auto byte = buffer[i];
</span><span class="cx"> if (shouldPercentEncodeQueryByte(byte))
</span><del>- percentEncode(byte, destination);
</del><ins>+ percentEncodeByte(byte, destination);
</ins><span class="cx"> else
</span><span class="cx"> destination.append(byte);
</span><span class="cx"> }
</span><span class="lines">@@ -520,7 +540,7 @@
</span><span class="cx"> for (size_t i = 0; i < length; ++i) {
</span><span class="cx"> uint8_t byte = data[i];
</span><span class="cx"> if (shouldPercentEncodeQueryByte(byte))
</span><del>- percentEncode(byte, destination);
</del><ins>+ percentEncodeByte(byte, destination);
</ins><span class="cx"> else
</span><span class="cx"> destination.append(byte);
</span><span class="cx"> }
</span><span class="lines">@@ -1413,7 +1433,7 @@
</span><span class="cx"> break;
</span><span class="cx"> }
</span><span class="cx"> if (isUTF8Encoding)
</span><del>- utf8PercentEncodeQuery<serialized>(*c, m_asciiBuffer);
</del><ins>+ utf8QueryEncode<serialized>(*c, m_asciiBuffer);
</ins><span class="cx"> else
</span><span class="cx"> appendCodePoint(queryBuffer, *c);
</span><span class="cx"> ++c;
</span><span class="lines">@@ -2198,7 +2218,7 @@
</span><span class="cx"> || (byte >= 0x61 && byte <= 0x7A))
</span><span class="cx"> output.append(byte);
</span><span class="cx"> else
</span><del>- percentEncode(byte, output);
</del><ins>+ percentEncodeByte(byte, output);
</ins><span class="cx"> }
</span><span class="cx"> }
</span><span class="cx">
</span></span></pre></div>
<a id="trunkToolsChangeLog"></a>
<div class="modfile"><h4>Modified: trunk/Tools/ChangeLog (206197 => 206198)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Tools/ChangeLog        2016-09-21 06:17:13 UTC (rev 206197)
+++ trunk/Tools/ChangeLog        2016-09-21 06:34:13 UTC (rev 206198)
</span><span class="lines">@@ -1,3 +1,13 @@
</span><ins>+2016-09-20 Alex Christensen <achristensen@webkit.org>
+
+ Optimize URLParser
+ https://bugs.webkit.org/show_bug.cgi?id=162105
+
+ Reviewed by Geoffrey Garen.
+
+ * TestWebKitAPI/Tests/WebCore/URLParser.cpp:
+ (TestWebKitAPI::TEST_F):
+
</ins><span class="cx"> 2016-09-20 Aakash Jain <aakash_jain@apple.com>
</span><span class="cx">
</span><span class="cx"> enable remote_api (for debugging) in flakiness dashboard app
</span></span></pre></div>
<a id="trunkToolsTestWebKitAPITestsWebCoreURLParsercpp"></a>
<div class="modfile"><h4>Modified: trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp (206197 => 206198)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp        2016-09-21 06:17:13 UTC (rev 206197)
+++ trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp        2016-09-21 06:34:13 UTC (rev 206198)
</span><span class="lines">@@ -215,7 +215,6 @@
</span><span class="cx"> checkURL("http://123.256/", {"http", "", "", "123.256", 0, "/", "", "", "http://123.256/"});
</span><span class="cx"> checkURL("notspecial:/a", {"notspecial", "", "", "", 0, "/a", "", "", "notspecial:/a"});
</span><span class="cx"> checkURL("notspecial:", {"notspecial", "", "", "", 0, "", "", "", "notspecial:"});
</span><del>- // FIXME: Fix and add a test with an invalid surrogate pair at the end with a space as the second code unit.
</del><span class="cx">
</span><span class="cx"> // This disagrees with the web platform test for http://:@www.example.com but agrees with Chrome and URL::parse,
</span><span class="cx"> // and Firefox fails the web platform test differently. Maybe the web platform test ought to be changed.
</span><span class="lines">@@ -656,7 +655,9 @@
</span><span class="cx"> checkURLDifferences("http://%48OsT",
</span><span class="cx"> {"http", "", "", "host", 0, "/", "", "", "http://host/"},
</span><span class="cx"> {"http", "", "", "%48ost", 0, "/", "", "", "http://%48ost/"});
</span><del>-
</del><ins>+ checkURLDifferences("http://host/`",
+ {"http", "", "", "host", 0, "/%60", "", "", "http://host/%60"},
+ {"http", "", "", "host", 0, "/`", "", "", "http://host/`"});
</ins><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> static void shouldFail(const String& urlString)
</span><span class="lines">@@ -719,6 +720,29 @@
</span><span class="cx"> {"ws", "", "", "", 0, "", "", "", "ws:"},
</span><span class="cx"> {"ws", "", "", "", 0, "s:", "", "", "ws:s:"});
</span><span class="cx"> checkRelativeURL("notspecial:", "http://example.org/foo/bar", {"notspecial", "", "", "", 0, "", "", "", "notspecial:"});
</span><ins>+
+ const wchar_t surrogateBegin = 0xD800;
+ const wchar_t validSurrogateEnd = 0xDD55;
+ const wchar_t invalidSurrogateEnd = 'A';
+ checkURL(wideString<12>({'h', 't', 't', 'p', ':', '/', '/', 'w', '/', surrogateBegin, validSurrogateEnd, '\0'}),
+ {"http", "", "", "w", 0, "/%F0%90%85%95", "", "", "http://w/%F0%90%85%95"});
+
+ // URLParser matches Chrome and Firefox but not URL::parse.
+ checkURLDifferences(wideString<12>({'h', 't', 't', 'p', ':', '/', '/', 'w', '/', surrogateBegin, invalidSurrogateEnd}),
+ {"http", "", "", "w", 0, "/%EF%BF%BDA", "", "", "http://w/%EF%BF%BDA"},
+ {"http", "", "", "w", 0, "/%ED%A0%80A", "", "", "http://w/%ED%A0%80A"});
+ checkURLDifferences(wideString<13>({'h', 't', 't', 'p', ':', '/', '/', 'w', '/', '?', surrogateBegin, invalidSurrogateEnd, '\0'}),
+ {"http", "", "", "w", 0, "/", "%EF%BF%BDA", "", "http://w/?%EF%BF%BDA"},
+ {"http", "", "", "w", 0, "/", "%ED%A0%80A", "", "http://w/?%ED%A0%80A"});
+ checkURLDifferences(wideString<11>({'h', 't', 't', 'p', ':', '/', '/', 'w', '/', surrogateBegin, '\0'}),
+ {"http", "", "", "w", 0, "/%EF%BF%BD", "", "", "http://w/%EF%BF%BD"},
+ {"http", "", "", "w", 0, "/%ED%A0%80", "", "", "http://w/%ED%A0%80"});
+ checkURLDifferences(wideString<12>({'h', 't', 't', 'p', ':', '/', '/', 'w', '/', '?', surrogateBegin, '\0'}),
+ {"http", "", "", "w", 0, "/", "%EF%BF%BD", "", "http://w/?%EF%BF%BD"},
+ {"http", "", "", "w", 0, "/", "%ED%A0%80", "", "http://w/?%ED%A0%80"});
+ checkURLDifferences(wideString<13>({'h', 't', 't', 'p', ':', '/', '/', 'w', '/', '?', surrogateBegin, ' ', '\0'}),
+ {"http", "", "", "w", 0, "/", "%EF%BF%BD", "", "http://w/?%EF%BF%BD"},
+ {"http", "", "", "w", 0, "/", "%ED%A0%80", "", "http://w/?%ED%A0%80"});
</ins><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> static void checkURL(const String& urlString, const TextEncoding& encoding, const ExpectedParts& parts)
</span></span></pre>
</div>
</div>
</body>
</html>