<!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>[206223] trunk/Source/WebCore</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/206223">206223</a></dd>
<dt>Author</dt> <dd>achristensen@apple.com</dd>
<dt>Date</dt> <dd>2016-09-21 11:33:30 -0700 (Wed, 21 Sep 2016)</dd>
</dl>
<h3>Log Message</h3>
<pre>Optimize URLParser
https://bugs.webkit.org/show_bug.cgi?id=162338
Reviewed by Tim Horton.
No change in behavior. Just a marginal performance improvement.
* platform/URLParser.cpp:
(WebCore::isValidSchemeCharacter):
Added to reduce branches when parsing the scheme of a URL. Now there is a table lookup instead of many range checks.
(WebCore::URLParser::parse):
Use appendVector, which uses memcpy.
(WebCore::URLParser::parseHostAndPort):
If we know that we are parsing the serialized output of a valid URL,
we do not need to convert host characters to lower case.
They are already lower case.</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>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunkSourceWebCoreChangeLog"></a>
<div class="modfile"><h4>Modified: trunk/Source/WebCore/ChangeLog (206222 => 206223)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Source/WebCore/ChangeLog 2016-09-21 18:24:43 UTC (rev 206222)
+++ trunk/Source/WebCore/ChangeLog 2016-09-21 18:33:30 UTC (rev 206223)
</span><span class="lines">@@ -1,3 +1,22 @@
</span><ins>+2016-09-21 Alex Christensen <achristensen@webkit.org>
+
+ Optimize URLParser
+ https://bugs.webkit.org/show_bug.cgi?id=162338
+
+ Reviewed by Tim Horton.
+
+ No change in behavior. Just a marginal performance improvement.
+
+ * platform/URLParser.cpp:
+ (WebCore::isValidSchemeCharacter):
+ Added to reduce branches when parsing the scheme of a URL. Now there is a table lookup instead of many range checks.
+ (WebCore::URLParser::parse):
+ Use appendVector, which uses memcpy.
+ (WebCore::URLParser::parseHostAndPort):
+ If we know that we are parsing the serialized output of a valid URL,
+ we do not need to convert host characters to lower case.
+ They are already lower case.
+
</ins><span class="cx"> 2016-09-21 Keith Miller <keith_miller@apple.com>
</span><span class="cx">
</span><span class="cx"> Fix build for future versions of Clang.
</span></span></pre></div>
<a id="trunkSourceWebCoreplatformURLParsercpp"></a>
<div class="modfile"><h4>Modified: trunk/Source/WebCore/platform/URLParser.cpp (206222 => 206223)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/Source/WebCore/platform/URLParser.cpp 2016-09-21 18:24:43 UTC (rev 206222)
+++ trunk/Source/WebCore/platform/URLParser.cpp 2016-09-21 18:33:30 UTC (rev 206223)
</span><span class="lines">@@ -129,6 +129,7 @@
</span><span class="cx"> InvalidDomain = 0x4,
</span><span class="cx"> QueryPercent = 0x8,
</span><span class="cx"> SlashQuestionOrHash = 0x10,
</span><ins>+ Scheme = 0x20,
</ins><span class="cx"> };
</span><span class="cx">
</span><span class="cx"> static const uint8_t characterClassTable[256] = {
</span><span class="lines">@@ -175,21 +176,21 @@
</span><span class="cx"> 0, // '('
</span><span class="cx"> 0, // ')'
</span><span class="cx"> 0, // '*'
</span><del>- 0, // '+'
</del><ins>+ Scheme, // '+'
</ins><span class="cx"> 0, // ','
</span><del>- 0, // '-'
- 0, // '.'
</del><ins>+ Scheme, // '-'
+ Scheme, // '.'
</ins><span class="cx"> UserInfo | InvalidDomain | SlashQuestionOrHash, // '/'
</span><del>- 0, // '0'
- 0, // '1'
- 0, // '2'
- 0, // '3'
- 0, // '4'
- 0, // '5'
- 0, // '6'
- 0, // '7'
- 0, // '8'
- 0, // '9'
</del><ins>+ Scheme, // '0'
+ Scheme, // '1'
+ Scheme, // '2'
+ Scheme, // '3'
+ Scheme, // '4'
+ Scheme, // '5'
+ Scheme, // '6'
+ Scheme, // '7'
+ Scheme, // '8'
+ Scheme, // '9'
</ins><span class="cx"> UserInfo | InvalidDomain, // ':'
</span><span class="cx"> UserInfo, // ';'
</span><span class="cx"> UserInfo | Default | QueryPercent, // '<'
</span><span class="lines">@@ -197,32 +198,32 @@
</span><span class="cx"> UserInfo | Default | QueryPercent, // '>'
</span><span class="cx"> UserInfo | Default | InvalidDomain | SlashQuestionOrHash, // '?'
</span><span class="cx"> UserInfo | InvalidDomain, // '@'
</span><del>- 0, // 'A'
- 0, // 'B'
- 0, // 'C'
- 0, // 'D'
- 0, // 'E'
- 0, // 'F'
- 0, // 'G'
- 0, // 'H'
- 0, // 'I'
- 0, // 'J'
- 0, // 'K'
- 0, // 'L'
- 0, // 'M'
- 0, // 'N'
- 0, // 'O'
- 0, // 'P'
- 0, // 'Q'
- 0, // 'R'
- 0, // 'S'
- 0, // 'T'
- 0, // 'U'
- 0, // 'V'
- 0, // 'W'
- 0, // 'X'
- 0, // 'Y'
- 0, // 'Z'
</del><ins>+ Scheme, // 'A'
+ Scheme, // 'B'
+ Scheme, // 'C'
+ Scheme, // 'D'
+ Scheme, // 'E'
+ Scheme, // 'F'
+ Scheme, // 'G'
+ Scheme, // 'H'
+ Scheme, // 'I'
+ Scheme, // 'J'
+ Scheme, // 'K'
+ Scheme, // 'L'
+ Scheme, // 'M'
+ Scheme, // 'N'
+ Scheme, // 'O'
+ Scheme, // 'P'
+ Scheme, // 'Q'
+ Scheme, // 'R'
+ Scheme, // 'S'
+ Scheme, // 'T'
+ Scheme, // 'U'
+ Scheme, // 'V'
+ Scheme, // 'W'
+ Scheme, // 'X'
+ Scheme, // 'Y'
+ Scheme, // 'Z'
</ins><span class="cx"> UserInfo | InvalidDomain, // '['
</span><span class="cx"> UserInfo | InvalidDomain | SlashQuestionOrHash, // '\\'
</span><span class="cx"> UserInfo | InvalidDomain, // ']'
</span><span class="lines">@@ -229,32 +230,32 @@
</span><span class="cx"> UserInfo, // '^'
</span><span class="cx"> 0, // '_'
</span><span class="cx"> UserInfo | Default, // '`'
</span><del>- 0, // 'a'
- 0, // 'b'
- 0, // 'c'
- 0, // 'd'
- 0, // 'e'
- 0, // 'f'
- 0, // 'g'
- 0, // 'h'
- 0, // 'i'
- 0, // 'j'
- 0, // 'k'
- 0, // 'l'
- 0, // 'm'
- 0, // 'n'
- 0, // 'o'
- 0, // 'p'
- 0, // 'q'
- 0, // 'r'
- 0, // 's'
- 0, // 't'
- 0, // 'u'
- 0, // 'v'
- 0, // 'w'
- 0, // 'x'
- 0, // 'y'
- 0, // 'z'
</del><ins>+ Scheme, // 'a'
+ Scheme, // 'b'
+ Scheme, // 'c'
+ Scheme, // 'd'
+ Scheme, // 'e'
+ Scheme, // 'f'
+ Scheme, // 'g'
+ Scheme, // 'h'
+ Scheme, // 'i'
+ Scheme, // 'j'
+ Scheme, // 'k'
+ Scheme, // 'l'
+ Scheme, // 'm'
+ Scheme, // 'n'
+ Scheme, // 'o'
+ Scheme, // 'p'
+ Scheme, // 'q'
+ Scheme, // 'r'
+ Scheme, // 's'
+ Scheme, // 't'
+ Scheme, // 'u'
+ Scheme, // 'v'
+ Scheme, // 'w'
+ Scheme, // 'x'
+ Scheme, // 'y'
+ Scheme, // 'z'
</ins><span class="cx"> UserInfo | Default, // '{'
</span><span class="cx"> UserInfo, // '|'
</span><span class="cx"> UserInfo | Default, // '}'
</span><span class="lines">@@ -399,6 +400,7 @@
</span><span class="cx"> template<typename CharacterType> inline static bool isInvalidDomainCharacter(CharacterType character) { return character <= ']' && characterClassTable[character] & InvalidDomain; }
</span><span class="cx"> template<typename CharacterType> inline static bool isPercentOrNonASCII(CharacterType character) { return !isASCII(character) || character == '%'; }
</span><span class="cx"> template<typename CharacterType> inline static bool isSlashQuestionOrHash(CharacterType character) { return character <= '\\' && characterClassTable[character] & SlashQuestionOrHash; }
</span><ins>+template<typename CharacterType> inline static bool isValidSchemeCharacter(CharacterType character) { return character <= 'z' && characterClassTable[character] & Scheme; }
</ins><span class="cx"> static bool shouldPercentEncodeQueryByte(uint8_t byte) { return characterClassTable[byte] & QueryPercent; }
</span><span class="cx">
</span><span class="cx"> template<bool serialized, typename CharacterType>
</span><span class="lines">@@ -945,9 +947,9 @@
</span><span class="cx"> {
</span><span class="cx"> LOG(URLParser, "Parsing URL <%s> base <%s>", String(input, length).utf8().data(), base.string().utf8().data());
</span><span class="cx"> m_url = { };
</span><del>- m_asciiBuffer.clear();
- m_unicodeFragmentBuffer.clear();
- m_asciiBuffer.reserveCapacity(length);
</del><ins>+ ASSERT(m_asciiBuffer.isEmpty());
+ ASSERT(m_unicodeFragmentBuffer.isEmpty());
+ m_asciiBuffer.reserveInitialCapacity(length);
</ins><span class="cx">
</span><span class="cx"> bool isUTF8Encoding = encoding == UTF8Encoding();
</span><span class="cx"> Vector<UChar> queryBuffer;
</span><span class="lines">@@ -1010,7 +1012,7 @@
</span><span class="cx"> break;
</span><span class="cx"> case State::Scheme:
</span><span class="cx"> LOG_STATE("Scheme");
</span><del>- if (isASCIIAlphanumeric(*c) || *c == '+' || *c == '-' || *c == '.')
</del><ins>+ if (isValidSchemeCharacter(*c))
</ins><span class="cx"> m_asciiBuffer.append(toASCIILower(*c));
</span><span class="cx"> else if (*c == ':') {
</span><span class="cx"> m_url.m_schemeEnd = m_asciiBuffer.size();
</span><span class="lines">@@ -1631,13 +1633,11 @@
</span><span class="cx"> if (m_unicodeFragmentBuffer.isEmpty())
</span><span class="cx"> m_url.m_string = String::adopt(WTFMove(m_asciiBuffer));
</span><span class="cx"> else {
</span><del>- // FIXME: This should use a Vector<UChar> and adopt it.
- StringBuilder builder;
- builder.reserveCapacity(m_asciiBuffer.size() + m_unicodeFragmentBuffer.size());
- builder.append(m_asciiBuffer.data(), m_asciiBuffer.size());
- for (size_t i = 0; i < m_unicodeFragmentBuffer.size(); ++i)
- builder.append(m_unicodeFragmentBuffer[i]);
- m_url.m_string = builder.toString();
</del><ins>+ Vector<UChar> buffer;
+ buffer.reserveInitialCapacity(m_asciiBuffer.size() + m_unicodeFragmentBuffer.size());
+ buffer.appendVector(m_asciiBuffer);
+ buffer.appendVector(m_unicodeFragmentBuffer);
+ m_url.m_string = String::adopt(WTFMove(buffer));
</ins><span class="cx"> }
</span><span class="cx"> m_url.m_isValid = true;
</span><span class="cx"> LOG(URLParser, "Parsed URL <%s>", m_url.m_string.utf8().data());
</span><span class="lines">@@ -2103,6 +2103,7 @@
</span><span class="cx"> }
</span><span class="cx"> }
</span><span class="cx">
</span><ins>+ ASSERT(!serialized || m_hostHasPercentOrNonASCII);
</ins><span class="cx"> if (!m_hostHasPercentOrNonASCII) {
</span><span class="cx"> auto hostIterator = iterator;
</span><span class="cx"> for (; !iterator.atEnd(); ++iterator) {
</span><span class="lines">@@ -2124,7 +2125,10 @@
</span><span class="cx"> return parsePort<serialized>(iterator);
</span><span class="cx"> }
</span><span class="cx"> for (; hostIterator != iterator; ++hostIterator) {
</span><del>- if (serialized || !isTabOrNewline(*hostIterator))
</del><ins>+ if (serialized) {
+ ASSERT(!isASCIIUpper(*hostIterator));
+ m_asciiBuffer.append(*hostIterator);
+ } else if (!isTabOrNewline(*hostIterator))
</ins><span class="cx"> m_asciiBuffer.append(toASCIILower(*hostIterator));
</span><span class="cx"> }
</span><span class="cx"> m_url.m_hostEnd = m_asciiBuffer.size();
</span></span></pre>
</div>
</div>
</body>
</html>