Attachment 357550 Details for Bug 174816 – Patch

[patch] Patch

a (text/plain), 109.52 KB, created by Ms2ger (he/him; ⌚ UTC+1/+2) on 2018-12-18 01:04:04 PST

(hide)

Description:

Filename:

MIME Type:

Creator: Ms2ger (he/him; ⌚ UTC+1/+2)

Created: 2018-12-18 01:04:04 PST

Size: 109.52 KB

patch

obsolete

>diff --git a/LayoutTests/ChangeLog b/LayoutTests/ChangeLog
>index fc660cd3292..0a268db198d 100644
>--- a/LayoutTests/ChangeLog
>+++ b/LayoutTests/ChangeLog
>@@ -1,3 +1,12 @@
>+2018-12-14  Ms2ger  <Ms2ger@igalia.com>
>+
>+        [GTK][WPE] Need a function to convert internal URI to display ("pretty") URI
>+        https://bugs.webkit.org/show_bug.cgi?id=174816
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        * TestExpectations: Enable fast/url/user-visible/.
>+
> 2018-12-13  Eric Carlson  <eric.carlson@apple.com>
> 
>         [MediaStream] Calculate width or height when constraints contain only the other
>diff --git a/LayoutTests/TestExpectations b/LayoutTests/TestExpectations
>index d75b0e97913..7db777f7206 100644
>--- a/LayoutTests/TestExpectations
>+++ b/LayoutTests/TestExpectations
>@@ -68,7 +68,6 @@ fast/forms/search/search-padding-cancel-results-buttons.html [ Skip ]
> fast/forms/search/search-results-hidden-crash.html [ Skip ]
> 
> # These tests don't have to be platform-specific, but they are only implemented on Mac now.
>-fast/url/user-visible [ Skip ]
> fast/images/eps-as-image.html [ Skip ]
> 
> # Only Mac supports Dashboard widgets.
>diff --git a/Source/WTF/ChangeLog b/Source/WTF/ChangeLog
>index 10a64b64d26..e8835930033 100644
>--- a/Source/WTF/ChangeLog
>+++ b/Source/WTF/ChangeLog
>@@ -1,3 +1,43 @@
>+2018-12-14  Ms2ger  <Ms2ger@igalia.com>
>+
>+        [GTK][WPE] Need a function to convert internal URI to display ("pretty") URI
>+        https://bugs.webkit.org/show_bug.cgi?id=174816
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        Translate userVisibleString and dependent code into platform-neutral C++
>+        in wtf/URLHelpers.{h,cpp}.
>+
>+        * WTF.xcodeproj/project.pbxproj:
>+        * wtf/CMakeLists.txt:
>+        * wtf/URLHelpers.cpp: Added.
>+        (WTF::URLHelpers::loadIDNScriptWhiteList):
>+        (WTF::URLHelpers::isArmenianLookalikeCharacter):
>+        (WTF::URLHelpers::isArmenianScriptCharacter):
>+        (WTF::URLHelpers::isASCIIDigitOrValidHostCharacter):
>+        (WTF::URLHelpers::isLookalikeCharacter):
>+        (WTF::URLHelpers::whiteListIDNScript):
>+        (WTF::URLHelpers::initializeDefaultIDNScriptWhiteList):
>+        (WTF::URLHelpers::allCharactersInIDNScriptWhiteList):
>+        (WTF::URLHelpers::isSecondLevelDomainNameAllowedByTLDRules):
>+        (WTF::URLHelpers::isRussianDomainNameCharacter):
>+        (WTF::URLHelpers::allCharactersAllowedByTLDRules):
>+        (WTF::URLHelpers::mapHostName):
>+        (WTF::URLHelpers::collectRangesThatNeedMapping):
>+        (WTF::URLHelpers::applyHostNameFunctionToMailToURLString):
>+        (WTF::URLHelpers::applyHostNameFunctionToURLString):
>+        (WTF::URLHelpers::mapHostNames):
>+        (WTF::URLHelpers::createStringWithEscapedUnsafeCharacters):
>+        (WTF::URLHelpers::userVisibleURL):
>+        * wtf/URLHelpers.h: Added.
>+        * wtf/cocoa/NSURLExtras.mm:
>+        (WTF::URLHelpers::loadIDNScriptWhiteList):
>+        (WTF::decodePercentEscapes):
>+        (WTF::decodeHostName):
>+        (WTF::encodeHostName):
>+        (WTF::URLWithUserTypedString):
>+        (WTF::userVisibleString):
>+
> 2018-12-12  Alex Christensen  <achristensen@webkit.org>
> 
>         Implement safe browsing in WebKit on WatchOS
>diff --git a/Source/WTF/WTF.xcodeproj/project.pbxproj b/Source/WTF/WTF.xcodeproj/project.pbxproj
>index a2239490d11..8082cbdba81 100644
>--- a/Source/WTF/WTF.xcodeproj/project.pbxproj
>+++ b/Source/WTF/WTF.xcodeproj/project.pbxproj
>@@ -78,6 +78,7 @@
> 		5CC0EE7621629F1900A1A842 /* URL.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 5CC0EE7421629F1900A1A842 /* URL.cpp */; };
> 		5CC0EE892162BC2200A1A842 /* URLCocoa.mm in Sources */ = {isa = PBXBuildFile; fileRef = 5CC0EE862162BC2200A1A842 /* URLCocoa.mm */; };
> 		5CC0EE8A2162BC2200A1A842 /* NSURLExtras.mm in Sources */ = {isa = PBXBuildFile; fileRef = 5CC0EE882162BC2200A1A842 /* NSURLExtras.mm */; };
>+		5FAD3AE221B9636600BEE178 /* URLHelpers.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 5FAD3AE121B9636600BEE178 /* URLHelpers.cpp */; };
> 		70A993FE1AD7151300FA615B /* SymbolRegistry.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 70A993FC1AD7151300FA615B /* SymbolRegistry.cpp */; };
> 		70ECA60D1B02426800449739 /* AtomicStringImpl.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 70ECA60A1B02426800449739 /* AtomicStringImpl.cpp */; };
> 		7A05093F1FB9DCC500B33FB8 /* JSONValues.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 7A05093E1FB9DCC500B33FB8 /* JSONValues.cpp */; };
>@@ -382,6 +383,8 @@
> 		5D247B6E14689C4700E78B76 /* Base.xcconfig */ = {isa = PBXFileReference; lastKnownFileType = text.xcconfig; path = Base.xcconfig; sourceTree = "<group>"; };
> 		5D247B7014689C4700E78B76 /* DebugRelease.xcconfig */ = {isa = PBXFileReference; lastKnownFileType = text.xcconfig; path = DebugRelease.xcconfig; sourceTree = "<group>"; };
> 		5D247B7314689C4700E78B76 /* WTF.xcconfig */ = {isa = PBXFileReference; lastKnownFileType = text.xcconfig; path = WTF.xcconfig; sourceTree = "<group>"; };
>+		5FAD3AE021B9636600BEE178 /* URLHelpers.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = URLHelpers.h; sourceTree = "<group>"; };
>+		5FAD3AE121B9636600BEE178 /* URLHelpers.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = URLHelpers.cpp; sourceTree = "<group>"; };
> 		6541CAF41630DB26006D0DEC /* CopyWTFHeaders.xcconfig */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = text.xcconfig; path = CopyWTFHeaders.xcconfig; sourceTree = "<group>"; };
> 		70A993FC1AD7151300FA615B /* SymbolRegistry.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = SymbolRegistry.cpp; sourceTree = "<group>"; };
> 		70A993FD1AD7151300FA615B /* SymbolRegistry.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = SymbolRegistry.h; sourceTree = "<group>"; };
>@@ -980,6 +983,8 @@
> 				A8A472CE151A825B004123FF /* MetaAllocator.h */,
> 				A8A472CF151A825B004123FF /* MetaAllocatorHandle.h */,
> 				FE7497ED209163060003565B /* MetaAllocatorPtr.h */,
>+				5FAD3AE121B9636600BEE178 /* URLHelpers.cpp */,
>+				5FAD3AE021B9636600BEE178 /* URLHelpers.h */,
> 				0F66B2821DC97BAB004A1D3F /* MonotonicTime.cpp */,
> 				0F66B2831DC97BAB004A1D3F /* MonotonicTime.h */,
> 				FE8225301B2A1E5B00BA68FD /* NakedPtr.h */,
>@@ -1502,6 +1507,7 @@
> 				0F66B28C1DC97BAB004A1D3F /* MonotonicTime.cpp in Sources */,
> 				5CC0EE8A2162BC2200A1A842 /* NSURLExtras.mm in Sources */,
> 				A8A473F4151A825B004123FF /* NumberOfCores.cpp in Sources */,
>+				5FAD3AE221B9636600BEE178 /* URLHelpers.cpp in Sources */,
> 				A8A473F7151A825B004123FF /* OSAllocatorPosix.cpp in Sources */,
> 				A8A473F9151A825B004123FF /* OSRandomSource.cpp in Sources */,
> 				A8A47402151A825B004123FF /* PageBlock.cpp in Sources */,
>diff --git a/Source/WTF/wtf/CMakeLists.txt b/Source/WTF/wtf/CMakeLists.txt
>index cee1cce1e57..109c2727704 100644
>--- a/Source/WTF/wtf/CMakeLists.txt
>+++ b/Source/WTF/wtf/CMakeLists.txt
>@@ -241,6 +241,7 @@ set(WTF_PUBLIC_HEADERS
>     TriState.h
>     TypeCasts.h
>     URL.h
>+    URLHelpers.h
>     URLHash.h
>     URLParser.h
>     UUID.h
>@@ -398,6 +399,7 @@ set(WTF_SOURCES
>     TimeWithDynamicClockType.cpp
>     TimingScope.cpp
>     URL.cpp
>+    URLHelpers.cpp
>     URLParser.cpp
>     UUID.cpp
>     WTFAssertions.cpp
>diff --git a/Source/WTF/wtf/URLHelpers.cpp b/Source/WTF/wtf/URLHelpers.cpp
>new file mode 100644
>index 00000000000..4795673627a
>--- /dev/null
>+++ b/Source/WTF/wtf/URLHelpers.cpp
>@@ -0,0 +1,867 @@
>+/*
>+ * Copyright (C) 2005, 2007, 2014 Apple Inc. All rights reserved.
>+ * Copyright (C) 2018 Igalia S.L.
>+ *
>+ * Redistribution and use in source and binary forms, with or without
>+ * modification, are permitted provided that the following conditions
>+ * are met:
>+ *
>+ * 1.  Redistributions of source code must retain the above copyright
>+ *     notice, this list of conditions and the following disclaimer.
>+ * 2.  Redistributions in binary form must reproduce the above copyright
>+ *     notice, this list of conditions and the following disclaimer in the
>+ *     documentation and/or other materials provided with the distribution.
>+ * 3.  Neither the name of Apple Inc. ("Apple") nor the names of
>+ *     its contributors may be used to endorse or promote products derived
>+ *     from this software without specific prior written permission.
>+ *
>+ * THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY
>+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
>+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
>+ * DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY
>+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
>+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
>+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
>+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
>+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
>+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
>+ */
>+
>+#include "config.h"
>+#include "URLHelpers.h"
>+
>+#include "URLParser.h"
>+#include <mutex>
>+#include <unicode/uidna.h>
>+#include <unicode/unorm.h>
>+#include <unicode/uscript.h>
>+
>+namespace WTF {
>+namespace URLHelpers {
>+
>+// Needs to be big enough to hold an IDN-encoded name.
>+// For host names bigger than this, we won't do IDN encoding, which is almost certainly OK.
>+const unsigned hostNameBufferLength = 2048;
>+const unsigned urlBytesBufferLength = 2048;
>+
>+static uint32_t IDNScriptWhiteList[(USCRIPT_CODE_LIMIT + 31) / 32];
>+
>+#if !PLATFORM(COCOA)
>+
>+// Cocoa has an implementation that uses a whitelist in /Library or ~/Library,
>+// if it exists.
>+void loadIDNScriptWhiteList()
>+{
>+    static std::once_flag flag;
>+    std::call_once(flag, initializeDefaultIDNScriptWhiteList);
>+}
>+
>+#endif // !PLATFORM(COCOA)
>+
>+static bool isArmenianLookalikeCharacter(UChar32 codePoint)
>+{
>+    return codePoint == 0x0548 || codePoint == 0x054D || codePoint == 0x0578 || codePoint == 0x057D;
>+}
>+
>+static bool isArmenianScriptCharacter(UChar32 codePoint)
>+{
>+    UErrorCode error = U_ZERO_ERROR;
>+    UScriptCode script = uscript_getScript(codePoint, &error);
>+    if (error != U_ZERO_ERROR) {
>+        LOG_ERROR("got ICU error while trying to look at scripts: %d", error);
>+        return false;
>+    }
>+
>+    return script == USCRIPT_ARMENIAN;
>+}
>+
>+template<typename CharacterType> inline bool isASCIIDigitOrValidHostCharacter(CharacterType charCode)
>+{
>+    if (!isASCIIDigitOrPunctuation(charCode))
>+        return false;
>+
>+    // Things the URL Parser rejects:
>+    switch (charCode) {
>+    case '#':
>+    case '%':
>+    case '/':
>+    case ':':
>+    case '?':
>+    case '@':
>+    case '[':
>+    case '\\':
>+    case ']':
>+        return false;
>+    default:
>+        return true;
>+    }
>+}
>+
>+static bool isLookalikeCharacter(const std::optional<UChar32>& previousCodePoint, UChar32 charCode)
>+{
>+    // This function treats the following as unsafe, lookalike characters:
>+    // any non-printable character, any character considered as whitespace,
>+    // any ignorable character, and emoji characters related to locks.
>+    
>+    // We also considered the characters in Mozilla's blacklist <http://kb.mozillazine.org/Network.IDN.blacklist_chars>.
>+
>+    // Some of the characters here will never appear once ICU has encoded.
>+    // For example, ICU transforms most spaces into an ASCII space and most
>+    // slashes into an ASCII solidus. But one of the two callers uses this
>+    // on characters that have not been processed by ICU, so they are needed here.
>+    
>+    if (!u_isprint(charCode) || u_isUWhiteSpace(charCode) || u_hasBinaryProperty(charCode, UCHAR_DEFAULT_IGNORABLE_CODE_POINT))
>+        return true;
>+    
>+    switch (charCode) {
>+    case 0x00BC: /* VULGAR FRACTION ONE QUARTER */
>+    case 0x00BD: /* VULGAR FRACTION ONE HALF */
>+    case 0x00BE: /* VULGAR FRACTION THREE QUARTERS */
>+    case 0x00ED: /* LATIN SMALL LETTER I WITH ACUTE */
>+    case 0x01C3: /* LATIN LETTER RETROFLEX CLICK */
>+    case 0x0251: /* LATIN SMALL LETTER ALPHA */
>+    case 0x0261: /* LATIN SMALL LETTER SCRIPT G */
>+    case 0x02D0: /* MODIFIER LETTER TRIANGULAR COLON */
>+    case 0x0335: /* COMBINING SHORT STROKE OVERLAY */
>+    case 0x0337: /* COMBINING SHORT SOLIDUS OVERLAY */
>+    case 0x0338: /* COMBINING LONG SOLIDUS OVERLAY */
>+    case 0x0589: /* ARMENIAN FULL STOP */
>+    case 0x05B4: /* HEBREW POINT HIRIQ */
>+    case 0x05BC: /* HEBREW POINT DAGESH OR MAPIQ */
>+    case 0x05C3: /* HEBREW PUNCTUATION SOF PASUQ */
>+    case 0x05F4: /* HEBREW PUNCTUATION GERSHAYIM */
>+    case 0x0609: /* ARABIC-INDIC PER MILLE SIGN */
>+    case 0x060A: /* ARABIC-INDIC PER TEN THOUSAND SIGN */
>+    case 0x0650: /* ARABIC KASRA */
>+    case 0x0660: /* ARABIC INDIC DIGIT ZERO */
>+    case 0x066A: /* ARABIC PERCENT SIGN */
>+    case 0x06D4: /* ARABIC FULL STOP */
>+    case 0x06F0: /* EXTENDED ARABIC INDIC DIGIT ZERO */
>+    case 0x0701: /* SYRIAC SUPRALINEAR FULL STOP */
>+    case 0x0702: /* SYRIAC SUBLINEAR FULL STOP */
>+    case 0x0703: /* SYRIAC SUPRALINEAR COLON */
>+    case 0x0704: /* SYRIAC SUBLINEAR COLON */
>+    case 0x1735: /* PHILIPPINE SINGLE PUNCTUATION */
>+    case 0x1D04: /* LATIN LETTER SMALL CAPITAL C */
>+    case 0x1D0F: /* LATIN LETTER SMALL CAPITAL O */
>+    case 0x1D1C: /* LATIN LETTER SMALL CAPITAL U */
>+    case 0x1D20: /* LATIN LETTER SMALL CAPITAL V */
>+    case 0x1D21: /* LATIN LETTER SMALL CAPITAL W */
>+    case 0x1D22: /* LATIN LETTER SMALL CAPITAL Z */
>+    case 0x1ECD: /* LATIN SMALL LETTER O WITH DOT BELOW */
>+    case 0x2010: /* HYPHEN */
>+    case 0x2011: /* NON-BREAKING HYPHEN */
>+    case 0x2024: /* ONE DOT LEADER */
>+    case 0x2027: /* HYPHENATION POINT */
>+    case 0x2039: /* SINGLE LEFT-POINTING ANGLE QUOTATION MARK */
>+    case 0x203A: /* SINGLE RIGHT-POINTING ANGLE QUOTATION MARK */
>+    case 0x2041: /* CARET INSERTION POINT */
>+    case 0x2044: /* FRACTION SLASH */
>+    case 0x2052: /* COMMERCIAL MINUS SIGN */
>+    case 0x2153: /* VULGAR FRACTION ONE THIRD */
>+    case 0x2154: /* VULGAR FRACTION TWO THIRDS */
>+    case 0x2155: /* VULGAR FRACTION ONE FIFTH */
>+    case 0x2156: /* VULGAR FRACTION TWO FIFTHS */
>+    case 0x2157: /* VULGAR FRACTION THREE FIFTHS */
>+    case 0x2158: /* VULGAR FRACTION FOUR FIFTHS */
>+    case 0x2159: /* VULGAR FRACTION ONE SIXTH */
>+    case 0x215A: /* VULGAR FRACTION FIVE SIXTHS */
>+    case 0x215B: /* VULGAR FRACTION ONE EIGHT */
>+    case 0x215C: /* VULGAR FRACTION THREE EIGHTHS */
>+    case 0x215D: /* VULGAR FRACTION FIVE EIGHTHS */
>+    case 0x215E: /* VULGAR FRACTION SEVEN EIGHTHS */
>+    case 0x215F: /* FRACTION NUMERATOR ONE */
>+    case 0x2212: /* MINUS SIGN */
>+    case 0x2215: /* DIVISION SLASH */
>+    case 0x2216: /* SET MINUS */
>+    case 0x2236: /* RATIO */
>+    case 0x233F: /* APL FUNCTIONAL SYMBOL SLASH BAR */
>+    case 0x23AE: /* INTEGRAL EXTENSION */
>+    case 0x244A: /* OCR DOUBLE BACKSLASH */
>+    case 0x2571: /* DisplayType::Box DRAWINGS LIGHT DIAGONAL UPPER RIGHT TO LOWER LEFT */
>+    case 0x2572: /* DisplayType::Box DRAWINGS LIGHT DIAGONAL UPPER LEFT TO LOWER RIGHT */
>+    case 0x29F6: /* SOLIDUS WITH OVERBAR */
>+    case 0x29F8: /* BIG SOLIDUS */
>+    case 0x2AFB: /* TRIPLE SOLIDUS BINARY RELATION */
>+    case 0x2AFD: /* DOUBLE SOLIDUS OPERATOR */
>+    case 0x2FF0: /* IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT */
>+    case 0x2FF1: /* IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW */
>+    case 0x2FF2: /* IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO MIDDLE AND RIGHT */
>+    case 0x2FF3: /* IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO MIDDLE AND BELOW */
>+    case 0x2FF4: /* IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND */
>+    case 0x2FF5: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM ABOVE */
>+    case 0x2FF6: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM BELOW */
>+    case 0x2FF7: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LEFT */
>+    case 0x2FF8: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER LEFT */
>+    case 0x2FF9: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER RIGHT */
>+    case 0x2FFA: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER LEFT */
>+    case 0x2FFB: /* IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID */
>+    case 0x3002: /* IDEOGRAPHIC FULL STOP */
>+    case 0x3008: /* LEFT ANGLE BRACKET */
>+    case 0x3014: /* LEFT TORTOISE SHELL BRACKET */
>+    case 0x3015: /* RIGHT TORTOISE SHELL BRACKET */
>+    case 0x3033: /* VERTICAL KANA REPEAT MARK UPPER HALF */
>+    case 0x3035: /* VERTICAL KANA REPEAT MARK LOWER HALF */
>+    case 0x321D: /* PARENTHESIZED KOREAN CHARACTER OJEON */
>+    case 0x321E: /* PARENTHESIZED KOREAN CHARACTER O HU */
>+    case 0x33AE: /* SQUARE RAD OVER S */
>+    case 0x33AF: /* SQUARE RAD OVER S SQUARED */
>+    case 0x33C6: /* SQUARE C OVER KG */
>+    case 0x33DF: /* SQUARE A OVER M */
>+    case 0x05B9: /* HEBREW POINT HOLAM */
>+    case 0x05BA: /* HEBREW POINT HOLAM HASER FOR VAV */
>+    case 0x05C1: /* HEBREW POINT SHIN DOT */
>+    case 0x05C2: /* HEBREW POINT SIN DOT */
>+    case 0x05C4: /* HEBREW MARK UPPER DOT */
>+    case 0xA731: /* LATIN LETTER SMALL CAPITAL S */
>+    case 0xA771: /* LATIN SMALL LETTER DUM */
>+    case 0xA789: /* MODIFIER LETTER COLON */
>+    case 0xFE14: /* PRESENTATION FORM FOR VERTICAL SEMICOLON */
>+    case 0xFE15: /* PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK */
>+    case 0xFE3F: /* PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET */
>+    case 0xFE5D: /* SMALL LEFT TORTOISE SHELL BRACKET */
>+    case 0xFE5E: /* SMALL RIGHT TORTOISE SHELL BRACKET */
>+    case 0xFF0E: /* FULLWIDTH FULL STOP */
>+    case 0xFF0F: /* FULL WIDTH SOLIDUS */
>+    case 0xFF61: /* HALFWIDTH IDEOGRAPHIC FULL STOP */
>+    case 0xFFFC: /* OBJECT REPLACEMENT CHARACTER */
>+    case 0xFFFD: /* REPLACEMENT CHARACTER */
>+    case 0x1F50F: /* LOCK WITH INK PEN */
>+    case 0x1F510: /* CLOSED LOCK WITH KEY */
>+    case 0x1F511: /* KEY */
>+    case 0x1F512: /* LOCK */
>+    case 0x1F513: /* OPEN LOCK */
>+        return true;
>+    case 0x0307: /* COMBINING DOT ABOVE */
>+        return previousCodePoint == 0x0237 /* LATIN SMALL LETTER DOTLESS J */
>+            || previousCodePoint == 0x0131 /* LATIN SMALL LETTER DOTLESS I */
>+            || previousCodePoint == 0x05D5; /* HEBREW LETTER VAV */
>+    case 0x0548: /* ARMENIAN CAPITAL LETTER VO */
>+    case 0x054D: /* ARMENIAN CAPITAL LETTER SEH */
>+    case 0x0578: /* ARMENIAN SMALL LETTER VO */
>+    case 0x057D: /* ARMENIAN SMALL LETTER SEH */
>+        return previousCodePoint
>+            && !isASCIIDigitOrValidHostCharacter(previousCodePoint.value())
>+            && !isArmenianScriptCharacter(previousCodePoint.value());
>+    case '.':
>+        return false;
>+    default:
>+        return previousCodePoint
>+            && isArmenianLookalikeCharacter(previousCodePoint.value())
>+            && !(isArmenianScriptCharacter(charCode) || isASCIIDigitOrValidHostCharacter(charCode));
>+    }
>+}
>+
>+void whiteListIDNScript(const char* scriptName)
>+{
>+    int32_t script = u_getPropertyValueEnum(UCHAR_SCRIPT, scriptName);
>+    if (script >= 0 && script < USCRIPT_CODE_LIMIT) {
>+        size_t index = script / 32;
>+        uint32_t mask = 1 << (script % 32);
>+        IDNScriptWhiteList[index] |= mask;
>+    }
>+}
>+
>+void initializeDefaultIDNScriptWhiteList()
>+{
>+    const char* defaultIDNScriptWhiteList[20] = {
>+        "Common",
>+        "Inherited",
>+        "Arabic",
>+        "Armenian",
>+        "Bopomofo",
>+        "Canadian_Aboriginal",
>+        "Devanagari",
>+        "Deseret",
>+        "Gujarati",
>+        "Gurmukhi",
>+        "Hangul",
>+        "Han",
>+        "Hebrew",
>+        "Hiragana",
>+        "Katakana_Or_Hiragana",
>+        "Katakana",
>+        "Latin",
>+        "Tamil",
>+        "Thai",
>+        "Yi",
>+    };
>+    for (const char* scriptName : defaultIDNScriptWhiteList)
>+        whiteListIDNScript(scriptName);
>+}
>+
>+static bool allCharactersInIDNScriptWhiteList(const UChar* buffer, int32_t length)
>+{
>+    loadIDNScriptWhiteList();
>+    int32_t i = 0;
>+    std::optional<UChar32> previousCodePoint;
>+    while (i < length) {
>+        UChar32 c;
>+        U16_NEXT(buffer, i, length, c)
>+        UErrorCode error = U_ZERO_ERROR;
>+        UScriptCode script = uscript_getScript(c, &error);
>+        if (error != U_ZERO_ERROR) {
>+            LOG_ERROR("got ICU error while trying to look at scripts: %d", error);
>+            return false;
>+        }
>+        if (script < 0) {
>+            LOG_ERROR("got negative number for script code from ICU: %d", script);
>+            return false;
>+        }
>+        if (script >= USCRIPT_CODE_LIMIT)
>+            return false;
>+
>+        size_t index = script / 32;
>+        uint32_t mask = 1 << (script % 32);
>+        if (!(IDNScriptWhiteList[index] & mask))
>+            return false;
>+        
>+        if (isLookalikeCharacter(previousCodePoint, c))
>+            return false;
>+        previousCodePoint = c;
>+    }
>+    return true;
>+}
>+
>+static bool isSecondLevelDomainNameAllowedByTLDRules(const UChar* buffer, int32_t length, const WTF::Function<bool(UChar)>& characterIsAllowed)
>+{
>+    ASSERT(length > 0);
>+
>+    for (int32_t i = length - 1; i >= 0; --i) {
>+        UChar ch = buffer[i];
>+        
>+        if (characterIsAllowed(ch))
>+            continue;
>+        
>+        // Only check the second level domain. Lower level registrars may have different rules.
>+        if (ch == '.')
>+            break;
>+        
>+        return false;
>+    }
>+    return true;
>+}
>+
>+#define CHECK_RULES_IF_SUFFIX_MATCHES(suffix, function) \
>+    { \
>+        static const int32_t suffixLength = sizeof(suffix) / sizeof(suffix[0]); \
>+        if (length > suffixLength && !memcmp(buffer + length - suffixLength, suffix, sizeof(suffix))) \
>+            return isSecondLevelDomainNameAllowedByTLDRules(buffer, length - suffixLength, function); \
>+    }
>+
>+static bool isRussianDomainNameCharacter(UChar ch)
>+{
>+    // Only modern Russian letters, digits and dashes are allowed.
>+    return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || isASCIIDigit(ch) || ch == '-';
>+}
>+
>+static bool allCharactersAllowedByTLDRules(const UChar* buffer, int32_t length)
>+{
>+    // Skip trailing dot for root domain.
>+    if (buffer[length - 1] == '.')
>+        length--;
>+
>+    // http://cctld.ru/files/pdf/docs/rules_ru-rf.pdf
>+    static const UChar cyrillicRF[] = {
>+        '.',
>+        0x0440, // CYRILLIC SMALL LETTER ER
>+        0x0444, // CYRILLIC SMALL LETTER EF
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicRF, isRussianDomainNameCharacter);
>+
>+    // http://rusnames.ru/rules.pl
>+    static const UChar cyrillicRUS[] = {
>+        '.',
>+        0x0440, // CYRILLIC SMALL LETTER ER
>+        0x0443, // CYRILLIC SMALL LETTER U
>+        0x0441, // CYRILLIC SMALL LETTER ES
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicRUS, isRussianDomainNameCharacter);
>+
>+    // http://ru.faitid.org/projects/moscow/documents/moskva/idn
>+    static const UChar cyrillicMOSKVA[] = {
>+        '.',
>+        0x043C, // CYRILLIC SMALL LETTER EM
>+        0x043E, // CYRILLIC SMALL LETTER O
>+        0x0441, // CYRILLIC SMALL LETTER ES
>+        0x043A, // CYRILLIC SMALL LETTER KA
>+        0x0432, // CYRILLIC SMALL LETTER VE
>+        0x0430, // CYRILLIC SMALL LETTER A
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicMOSKVA, isRussianDomainNameCharacter);
>+
>+    // http://www.dotdeti.ru/foruser/docs/regrules.php
>+    static const UChar cyrillicDETI[] = {
>+        '.',
>+        0x0434, // CYRILLIC SMALL LETTER DE
>+        0x0435, // CYRILLIC SMALL LETTER IE
>+        0x0442, // CYRILLIC SMALL LETTER TE
>+        0x0438, // CYRILLIC SMALL LETTER I
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicDETI, isRussianDomainNameCharacter);
>+
>+    // http://corenic.org - rules not published. The word is Russian, so only allowing Russian at this time,
>+    // although we may need to revise the checks if this ends up being used with other languages spoken in Russia.
>+    static const UChar cyrillicONLAYN[] = {
>+        '.',
>+        0x043E, // CYRILLIC SMALL LETTER O
>+        0x043D, // CYRILLIC SMALL LETTER EN
>+        0x043B, // CYRILLIC SMALL LETTER EL
>+        0x0430, // CYRILLIC SMALL LETTER A
>+        0x0439, // CYRILLIC SMALL LETTER SHORT I
>+        0x043D, // CYRILLIC SMALL LETTER EN
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicONLAYN, isRussianDomainNameCharacter);
>+
>+    // http://corenic.org - same as above.
>+    static const UChar cyrillicSAYT[] = {
>+        '.',
>+        0x0441, // CYRILLIC SMALL LETTER ES
>+        0x0430, // CYRILLIC SMALL LETTER A
>+        0x0439, // CYRILLIC SMALL LETTER SHORT I
>+        0x0442, // CYRILLIC SMALL LETTER TE
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicSAYT, isRussianDomainNameCharacter);
>+
>+    // http://pir.org/products/opr-domain/ - rules not published. According to the registry site,
>+    // the intended audience is "Russian and other Slavic-speaking markets".
>+    // Chrome appears to only allow Russian, so sticking with that for now.
>+    static const UChar cyrillicORG[] = {
>+        '.',
>+        0x043E, // CYRILLIC SMALL LETTER O
>+        0x0440, // CYRILLIC SMALL LETTER ER
>+        0x0433, // CYRILLIC SMALL LETTER GHE
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicORG, isRussianDomainNameCharacter);
>+
>+    // http://cctld.by/rules.html
>+    static const UChar cyrillicBEL[] = {
>+        '.',
>+        0x0431, // CYRILLIC SMALL LETTER BE
>+        0x0435, // CYRILLIC SMALL LETTER IE
>+        0x043B, // CYRILLIC SMALL LETTER EL
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicBEL, [](UChar ch) {
>+        // Russian and Byelorussian letters, digits and dashes are allowed.
>+        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x0456 || ch == 0x045E || ch == 0x2019 || isASCIIDigit(ch) || ch == '-';
>+    });
>+
>+    // http://www.nic.kz/docs/poryadok_vnedreniya_kaz_ru.pdf
>+    static const UChar cyrillicKAZ[] = {
>+        '.',
>+        0x049B, // CYRILLIC SMALL LETTER KA WITH DESCENDER
>+        0x0430, // CYRILLIC SMALL LETTER A
>+        0x0437, // CYRILLIC SMALL LETTER ZE
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicKAZ, [](UChar ch) {
>+        // Kazakh letters, digits and dashes are allowed.
>+        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x04D9 || ch == 0x0493 || ch == 0x049B || ch == 0x04A3 || ch == 0x04E9 || ch == 0x04B1 || ch == 0x04AF || ch == 0x04BB || ch == 0x0456 || isASCIIDigit(ch) || ch == '-';
>+    });
>+
>+    // http://uanic.net/docs/documents-ukr/Rules%20of%20UKR_v4.0.pdf
>+    static const UChar cyrillicUKR[] = {
>+        '.',
>+        0x0443, // CYRILLIC SMALL LETTER U
>+        0x043A, // CYRILLIC SMALL LETTER KA
>+        0x0440, // CYRILLIC SMALL LETTER ER
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicUKR, [](UChar ch) {
>+        // Russian and Ukrainian letters, digits and dashes are allowed.
>+        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x0491 || ch == 0x0404 || ch == 0x0456 || ch == 0x0457 || isASCIIDigit(ch) || ch == '-';
>+    });
>+
>+    // http://www.rnids.rs/data/DOKUMENTI/idn-srb-policy-termsofuse-v1.4-eng.pdf
>+    static const UChar cyrillicSRB[] = {
>+        '.',
>+        0x0441, // CYRILLIC SMALL LETTER ES
>+        0x0440, // CYRILLIC SMALL LETTER ER
>+        0x0431, // CYRILLIC SMALL LETTER BE
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicSRB, [](UChar ch) {
>+        // Serbian letters, digits and dashes are allowed.
>+        return (ch >= 0x0430 && ch <= 0x0438) || (ch >= 0x043A && ch <= 0x0448) || ch == 0x0452 || ch == 0x0458 || ch == 0x0459 || ch == 0x045A || ch == 0x045B || ch == 0x045F || isASCIIDigit(ch) || ch == '-';
>+    });
>+
>+    // http://marnet.mk/doc/pravilnik-mk-mkd.pdf
>+    static const UChar cyrillicMKD[] = {
>+        '.',
>+        0x043C, // CYRILLIC SMALL LETTER EM
>+        0x043A, // CYRILLIC SMALL LETTER KA
>+        0x0434, // CYRILLIC SMALL LETTER DE
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicMKD, [](UChar ch) {
>+        // Macedonian letters, digits and dashes are allowed.
>+        return (ch >= 0x0430 && ch <= 0x0438) || (ch >= 0x043A && ch <= 0x0448) || ch == 0x0453 || ch == 0x0455 || ch == 0x0458 || ch == 0x0459 || ch == 0x045A || ch == 0x045C || ch == 0x045F || isASCIIDigit(ch) || ch == '-';
>+    });
>+
>+    // https://www.mon.mn/cs/
>+    static const UChar cyrillicMON[] = {
>+        '.',
>+        0x043C, // CYRILLIC SMALL LETTER EM
>+        0x043E, // CYRILLIC SMALL LETTER O
>+        0x043D, // CYRILLIC SMALL LETTER EN
>+    };
>+    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicMON, [](UChar ch) {
>+        // Mongolian letters, digits and dashes are allowed.
>+        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x04E9 || ch == 0x04AF || isASCIIDigit(ch) || ch == '-';
>+    });
>+
>+    // Not a known top level domain with special rules.
>+    return false;
>+}
>+
>+// Return value of null means no mapping is necessary.
>+std::optional<String> mapHostName(const String& hostName, const std::optional<URLDecodeFunction>& decodeFunction)
>+{
>+    if (hostName.length() > hostNameBufferLength)
>+        return String();
>+    
>+    if (!hostName.length())
>+        return String();
>+
>+    String string;
>+    if (decodeFunction && string.contains('%'))
>+        string = (*decodeFunction)(hostName);
>+    else
>+        string = hostName;
>+
>+    unsigned length = string.length();
>+
>+    auto sourceBuffer = string.charactersWithNullTermination();
>+    
>+    UChar destinationBuffer[hostNameBufferLength];
>+    UErrorCode uerror = U_ZERO_ERROR;
>+    UIDNAInfo processingDetails = UIDNA_INFO_INITIALIZER;
>+    int32_t numCharactersConverted = (decodeFunction ? uidna_nameToASCII : uidna_nameToUnicode)(&URLParser::internationalDomainNameTranscoder(), sourceBuffer.data(), length, destinationBuffer, hostNameBufferLength, &processingDetails, &uerror);
>+    if (length && (U_FAILURE(uerror) || processingDetails.errors))
>+        return std::nullopt;
>+    
>+    if (numCharactersConverted == static_cast<int32_t>(length) && !memcmp(sourceBuffer.data(), destinationBuffer, length * sizeof(UChar)))
>+        return String();
>+
>+    if (!decodeFunction && !allCharactersInIDNScriptWhiteList(destinationBuffer, numCharactersConverted) && !allCharactersAllowedByTLDRules(destinationBuffer, numCharactersConverted))
>+        return String();
>+
>+    return String(destinationBuffer, numCharactersConverted);
>+}
>+
>+using MappingRangesVector = std::optional<Vector<std::tuple<unsigned, unsigned, String>>>;
>+
>+static void collectRangesThatNeedMapping(const String& string, unsigned location, unsigned length, MappingRangesVector& array, const std::optional<URLDecodeFunction>& decodeFunction)
>+{
>+    // Generally, we want to optimize for the case where there is one host name that does not need mapping.
>+    // Therefore, we use null to indicate no mapping here and an empty array to indicate error.
>+
>+    String substring = string.substringSharingImpl(location, length);
>+    std::optional<String> host = mapHostName(substring, decodeFunction);
>+
>+    if (host && !*host)
>+        return;
>+    
>+    if (!array)
>+        array = Vector<std::tuple<unsigned, unsigned, String>>();
>+
>+    if (host)
>+        array->constructAndAppend(location, length, *host);
>+}
>+
>+static void applyHostNameFunctionToMailToURLString(const String& string, const std::optional<URLDecodeFunction>& decodeFunction, MappingRangesVector& array)
>+{
>+    // In a mailto: URL, host names come after a '@' character and end with a '>' or ',' or '?' character.
>+    // Skip quoted strings so that characters in them don't confuse us.
>+    // When we find a '?' character, we are past the part of the URL that contains host names.
>+    
>+    unsigned stringLength = string.length();
>+    unsigned current = 0;
>+    
>+    while (1) {
>+        // Find start of host name or of quoted string.
>+        auto hostNameOrStringStart = string.find([](UChar ch) {
>+            return ch == '"' || ch == '@' || ch == '?';
>+        }, current);
>+        if (hostNameOrStringStart == notFound)
>+            return;
>+
>+        UChar c = string[hostNameOrStringStart];
>+        current = hostNameOrStringStart + 1;
>+        
>+        if (c == '?')
>+            return;
>+        
>+        if (c == '@') {
>+            // Find end of host name.
>+            unsigned hostNameStart = current;
>+            auto hostNameEnd = string.find([](UChar ch) {
>+                return ch == '>' || ch == ',' || ch == '?';
>+            }, current);
>+
>+            bool done;
>+            if (hostNameEnd == notFound) {
>+                hostNameEnd = stringLength;
>+                done = true;
>+            } else {
>+                current = hostNameEnd;
>+                done = false;
>+            }
>+            
>+            // Process host name range.
>+            collectRangesThatNeedMapping(string, hostNameStart, hostNameEnd - hostNameStart, array, decodeFunction);
>+
>+            if (done)
>+                return;
>+        } else {
>+            // Skip quoted string.
>+            ASSERT(c == '"');
>+            while (1) {
>+                auto escapedCharacterOrStringEnd = string.find([](UChar ch) {
>+                    return ch == '"' || ch == '\\';
>+                }, current);
>+                if (escapedCharacterOrStringEnd == notFound)
>+                    return;
>+
>+                c = string[escapedCharacterOrStringEnd];
>+                current = escapedCharacterOrStringEnd + 1;
>+
>+                // If we are the end of the string, then break from the string loop back to the host name loop.
>+                if (c == '"')
>+                    break;
>+                
>+                // Skip escaped character.
>+                ASSERT(c == '\\');
>+                if (current == stringLength)
>+                    return;
>+
>+                ++current;
>+            }
>+        }
>+    }
>+}
>+
>+static void applyHostNameFunctionToURLString(const String& string, const std::optional<URLDecodeFunction>& decodeFunction, MappingRangesVector& array)
>+{
>+    // Find hostnames. Too bad we can't use any real URL-parsing code to do this,
>+    // but we have to do it before doing all the %-escaping, and this is the only
>+    // code we have that parses mailto URLs anyway.
>+    
>+    // Maybe we should implement this using a character buffer instead?
>+    
>+    if (protocolIs(string, "mailto")) {
>+        applyHostNameFunctionToMailToURLString(string, decodeFunction, array);
>+        return;
>+    }
>+    
>+    // Find the host name in a hierarchical URL.
>+    // It comes after a "://" sequence, with scheme characters preceding.
>+    // If ends with the end of the string or a ":", "/", or a "?".
>+    // If there is a "@" character, the host part is just the part after the "@".
>+    static const char* separator = "://";
>+    auto separatorIndex = string.find(separator);
>+    if (separatorIndex == notFound)
>+        return;
>+
>+    unsigned authorityStart = separatorIndex + strlen(separator);
>+    
>+    // Check that all characters before the :// are valid scheme characters.
>+    auto invalidSchemeCharacter = string.substringSharingImpl(0, separatorIndex).find([](UChar ch) {
>+        static const char* allowedCharacters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+-.";
>+        static size_t length = strlen(allowedCharacters);
>+        for (size_t i = 0; i < length; ++i) {
>+            if (allowedCharacters[i] == ch)
>+                return false;
>+        }
>+        return true;
>+    });
>+
>+    if (invalidSchemeCharacter != notFound)
>+        return;
>+    
>+    unsigned stringLength = string.length();
>+    
>+    // Find terminating character.
>+    auto hostNameTerminator = string.find([](UChar ch) {
>+        static const char* terminatingCharacters = ":/?#";
>+        static size_t length = strlen(terminatingCharacters);
>+        for (size_t i = 0; i < length; ++i) {
>+            if (terminatingCharacters[i] == ch)
>+                return true;
>+        }
>+        return false;
>+    }, authorityStart);
>+    unsigned hostNameEnd = hostNameTerminator == notFound ? stringLength : hostNameTerminator;
>+    
>+    // Find "@" for the start of the host name.
>+    auto userInfoTerminator = string.substringSharingImpl(0, hostNameEnd).find('@', authorityStart);
>+    unsigned hostNameStart = userInfoTerminator == notFound ? authorityStart : userInfoTerminator + 1;
>+    
>+    collectRangesThatNeedMapping(string, hostNameStart, hostNameEnd - hostNameStart, array, decodeFunction);
>+}
>+
>+String mapHostNames(const String& string, const std::optional<URLDecodeFunction>& decodeFunction)
>+{
>+    // Generally, we want to optimize for the case where there is one host name that does not need mapping.
>+    
>+    if (decodeFunction && string.isAllASCII())
>+        return string;
>+    
>+    // Make a list of ranges that actually need mapping.
>+    MappingRangesVector hostNameRanges;
>+    applyHostNameFunctionToURLString(string, decodeFunction, hostNameRanges);
>+    if (!hostNameRanges)
>+        return string;
>+
>+    if (hostNameRanges->isEmpty())
>+        return { };
>+
>+    // Do the mapping.
>+    String result = string;
>+    while (!hostNameRanges->isEmpty()) {
>+        unsigned location, length;
>+        String mappedHostName;
>+        std::tie(location, length, mappedHostName) = hostNameRanges->takeLast();
>+        result = result.replace(location, length, mappedHostName);
>+    }
>+    return result;
>+}
>+
>+static String createStringWithEscapedUnsafeCharacters(const Vector<UChar, urlBytesBufferLength>& sourceBuffer)
>+{
>+    Vector<UChar, urlBytesBufferLength> outBuffer;
>+
>+    const size_t length = sourceBuffer.size();
>+    
>+    std::optional<UChar32> previousCodePoint;
>+    size_t i = 0;
>+    while (i < length) {
>+        UChar32 c;
>+        U16_NEXT(sourceBuffer, i, length, c)
>+        
>+        if (isLookalikeCharacter(previousCodePoint, c)) {
>+            uint8_t utf8Buffer[4];
>+            size_t offset = 0;
>+            UBool failure = false;
>+            U8_APPEND(utf8Buffer, offset, 4, c, failure)
>+            ASSERT(!failure);
>+            
>+            for (size_t j = 0; j < offset; ++j) {
>+                outBuffer.append('%');
>+                outBuffer.append(upperNibbleToASCIIHexDigit(utf8Buffer[j]));
>+                outBuffer.append(lowerNibbleToASCIIHexDigit(utf8Buffer[j]));
>+            }
>+        } else {
>+            UChar utf16Buffer[2];
>+            size_t offset = 0;
>+            UBool failure = false;
>+            U16_APPEND(utf16Buffer, offset, 2, c, failure)
>+            ASSERT(!failure);
>+            for (size_t j = 0; j < offset; ++j)
>+                outBuffer.append(utf16Buffer[j]);
>+        }
>+        previousCodePoint = c;
>+    }
>+
>+    return String::adopt(WTFMove(outBuffer));
>+}
>+
>+String userVisibleURL(const CString& url)
>+{
>+    auto* before = reinterpret_cast<const unsigned char*>(url.data());
>+    int length = url.length();
>+
>+    if (!length)
>+        return { };
>+
>+    bool mayNeedHostNameDecoding = false;
>+
>+    // The buffer should be large enough to %-escape every character.
>+    int bufferLength = (length * 3) + 1;
>+    Vector<char, urlBytesBufferLength> after(bufferLength);
>+
>+    char* q = after.data();
>+    {
>+        const unsigned char* p = before;
>+        for (int i = 0; i < length; i++) {
>+            unsigned char c = p[i];
>+            // unescape escape sequences that indicate bytes greater than 0x7f
>+            if (c == '%' && i + 2 < length && isASCIIHexDigit(p[i + 1]) && isASCIIHexDigit(p[i + 2])) {
>+                auto u = toASCIIHexValue(p[i + 1], p[i + 2]);
>+                if (u > 0x7f) {
>+                    // unescape
>+                    *q++ = u;
>+                } else {
>+                    // do not unescape
>+                    *q++ = p[i];
>+                    *q++ = p[i + 1];
>+                    *q++ = p[i + 2];
>+                }
>+                i += 2;
>+            } else {
>+                *q++ = c;
>+                
>+                // Check for "xn--" in an efficient, non-case-sensitive, way.
>+                if (c == '-' && i >= 3 && !mayNeedHostNameDecoding && (q[-4] | 0x20) == 'x' && (q[-3] | 0x20) == 'n' && q[-2] == '-')
>+                    mayNeedHostNameDecoding = true;
>+            }
>+        }
>+        *q = '\0';
>+    }
>+    
>+    // Check string to see if it can be converted to display using UTF-8  
>+    String result = String::fromUTF8(after.data());
>+    if (!result) {
>+        // Could not convert to UTF-8.
>+        // Convert characters greater than 0x7f to escape sequences.
>+        // Shift current string to the end of the buffer
>+        // then we will copy back bytes to the start of the buffer 
>+        // as we convert.
>+        int afterlength = q - after.data();
>+        char* p = after.data() + bufferLength - afterlength - 1;
>+        memmove(p, after.data(), afterlength + 1); // copies trailing '\0'
>+        char* q = after.data();
>+        while (*p) {
>+            unsigned char c = *p;
>+            if (c > 0x7f) {
>+                *q++ = '%';
>+                *q++ = upperNibbleToASCIIHexDigit(c);
>+                *q++ = lowerNibbleToASCIIHexDigit(c);
>+            } else
>+                *q++ = *p;
>+            p++;
>+        }
>+        *q = '\0';
>+        // Note: after.data() points to a null-terminated, pure ASCII string.
>+        result = String::fromUTF8(after.data());
>+        ASSERT(!!result);
>+    }
>+
>+    // Note: result is UTFâ16 string, created from either a valid UTF-8 string,
>+    //       or a pure ASCII string (where all bytes with the high bit set are
>+    //       percent-encoded).
>+
>+    if (mayNeedHostNameDecoding) {
>+        // FIXME: Is it good to ignore the failure of mapHostNames and keep result intact?
>+        auto mappedResult = mapHostNames(result, std::nullopt);
>+        if (!!mappedResult)
>+            result = mappedResult;
>+    }
>+
>+    auto sourceBuffer = result.charactersWithNullTermination();
>+    ASSERT(sourceBuffer.last() == '\0');
>+    sourceBuffer.removeLast();
>+
>+    Vector<UChar, urlBytesBufferLength> normalizedCharacters(sourceBuffer.size());
>+    UErrorCode uerror = U_ZERO_ERROR;
>+    const UNormalizer2 *normalizer = unorm2_getNFCInstance(&uerror);
>+    int32_t normalizedLength = unorm2_normalize(normalizer, sourceBuffer.data(), sourceBuffer.size(), normalizedCharacters.data(), normalizedCharacters.size(), &uerror);
>+    if (uerror == U_BUFFER_OVERFLOW_ERROR) {
>+        uerror = U_ZERO_ERROR;
>+        normalizedCharacters.resize(normalizedLength);
>+        normalizedLength = unorm2_normalize(normalizer, sourceBuffer.data(), sourceBuffer.size(), normalizedCharacters.data(), normalizedLength, &uerror);
>+    }
>+    if (U_FAILURE(uerror))
>+        return { };
>+
>+    return createStringWithEscapedUnsafeCharacters(normalizedCharacters);
>+}
>+
>+} // namespace URLHelpers
>+} // namespace WTF
>diff --git a/Source/WTF/wtf/URLHelpers.h b/Source/WTF/wtf/URLHelpers.h
>new file mode 100644
>index 00000000000..4d2064b1851
>--- /dev/null
>+++ b/Source/WTF/wtf/URLHelpers.h
>@@ -0,0 +1,49 @@
>+/*
>+ * Copyright (C) 2005, 2007, 2014 Apple Inc. All rights reserved.
>+ * Copyright (C) 2018 Igalia S.L.
>+ *
>+ * Redistribution and use in source and binary forms, with or without
>+ * modification, are permitted provided that the following conditions
>+ * are met:
>+ *
>+ * 1.  Redistributions of source code must retain the above copyright
>+ *     notice, this list of conditions and the following disclaimer.
>+ * 2.  Redistributions in binary form must reproduce the above copyright
>+ *     notice, this list of conditions and the following disclaimer in the
>+ *     documentation and/or other materials provided with the distribution.
>+ * 3.  Neither the name of Apple Inc. ("Apple") nor the names of
>+ *     its contributors may be used to endorse or promote products derived
>+ *     from this software without specific prior written permission.
>+ *
>+ * THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY
>+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
>+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
>+ * DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY
>+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
>+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
>+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
>+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
>+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
>+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
>+ */
>+
>+#pragma once
>+
>+#include <wtf/Forward.h>
>+#include <wtf/Optional.h>
>+#include <wtf/text/WTFString.h>
>+
>+namespace WTF {
>+namespace URLHelpers {
>+
>+using URLDecodeFunction = String(&)(const String&);
>+
>+WTF_EXPORT_PRIVATE String userVisibleURL(const CString& URL);
>+void loadIDNScriptWhiteList();
>+void whiteListIDNScript(const char* scriptName);
>+void initializeDefaultIDNScriptWhiteList();
>+std::optional<String> mapHostName(const String&, const std::optional<URLDecodeFunction>&);
>+String mapHostNames(const String&, const std::optional<URLDecodeFunction>&);
>+
>+} // namespace URLHelpers
>+} // namespace WTF
>diff --git a/Source/WTF/wtf/cocoa/NSURLExtras.mm b/Source/WTF/wtf/cocoa/NSURLExtras.mm
>index 135e42db5a0..c8f8957efae 100644
>--- a/Source/WTF/wtf/cocoa/NSURLExtras.mm
>+++ b/Source/WTF/wtf/cocoa/NSURLExtras.mm
>@@ -36,228 +36,14 @@
> #import <wtf/HexNumber.h>
> #import <wtf/ObjCRuntimeExtras.h>
> #import <wtf/RetainPtr.h>
>+#import <wtf/URLHelpers.h>
> #import <wtf/Vector.h>
>-#import <unicode/uchar.h>
>-#import <unicode/uidna.h>
>-#import <unicode/uscript.h>
> 
>-// Needs to be big enough to hold an IDN-encoded name.
>-// For host names bigger than this, we won't do IDN encoding, which is almost certainly OK.
>-#define HOST_NAME_BUFFER_LENGTH 2048
> #define URL_BYTES_BUFFER_LENGTH 2048
> 
>-typedef void (* StringRangeApplierFunction)(NSString *, NSRange, RetainPtr<NSMutableArray>&);
>-
>-static uint32_t IDNScriptWhiteList[(USCRIPT_CODE_LIMIT + 31) / 32];
>-
> namespace WTF {
> 
>-static bool isArmenianLookalikeCharacter(UChar32 codePoint)
>-{
>-    return codePoint == 0x0548 || codePoint == 0x054D || codePoint == 0x0578 || codePoint == 0x057D;
>-}
>-
>-static bool isArmenianScriptCharacter(UChar32 codePoint)
>-{
>-    UErrorCode error = U_ZERO_ERROR;
>-    UScriptCode script = uscript_getScript(codePoint, &error);
>-    if (error != U_ZERO_ERROR) {
>-        LOG_ERROR("got ICU error while trying to look at scripts: %d", error);
>-        return false;
>-    }
>-
>-    return script == USCRIPT_ARMENIAN;
>-}
>-
>-
>-template<typename CharacterType> inline bool isASCIIDigitOrValidHostCharacter(CharacterType charCode)
>-{
>-    if (!isASCIIDigitOrPunctuation(charCode))
>-        return false;
>-
>-    // Things the URL Parser rejects:
>-    switch (charCode) {
>-    case '#':
>-    case '%':
>-    case '/':
>-    case ':':
>-    case '?':
>-    case '@':
>-    case '[':
>-    case '\\':
>-    case ']':
>-        return false;
>-    default:
>-        return true;
>-    }
>-}
>-
>-
>-
>-static BOOL isLookalikeCharacter(std::optional<UChar32> previousCodePoint, UChar32 charCode)
>-{
>-    // This function treats the following as unsafe, lookalike characters:
>-    // any non-printable character, any character considered as whitespace,
>-    // any ignorable character, and emoji characters related to locks.
>-    
>-    // We also considered the characters in Mozilla's blacklist <http://kb.mozillazine.org/Network.IDN.blacklist_chars>.
>-
>-    // Some of the characters here will never appear once ICU has encoded.
>-    // For example, ICU transforms most spaces into an ASCII space and most
>-    // slashes into an ASCII solidus. But one of the two callers uses this
>-    // on characters that have not been processed by ICU, so they are needed here.
>-    
>-    if (!u_isprint(charCode) || u_isUWhiteSpace(charCode) || u_hasBinaryProperty(charCode, UCHAR_DEFAULT_IGNORABLE_CODE_POINT))
>-        return YES;
>-    
>-    switch (charCode) {
>-        case 0x00BC: /* VULGAR FRACTION ONE QUARTER */
>-        case 0x00BD: /* VULGAR FRACTION ONE HALF */
>-        case 0x00BE: /* VULGAR FRACTION THREE QUARTERS */
>-        case 0x00ED: /* LATIN SMALL LETTER I WITH ACUTE */
>-        case 0x01C3: /* LATIN LETTER RETROFLEX CLICK */
>-        case 0x0251: /* LATIN SMALL LETTER ALPHA */
>-        case 0x0261: /* LATIN SMALL LETTER SCRIPT G */
>-        case 0x02D0: /* MODIFIER LETTER TRIANGULAR COLON */
>-        case 0x0335: /* COMBINING SHORT STROKE OVERLAY */
>-        case 0x0337: /* COMBINING SHORT SOLIDUS OVERLAY */
>-        case 0x0338: /* COMBINING LONG SOLIDUS OVERLAY */
>-        case 0x0589: /* ARMENIAN FULL STOP */
>-        case 0x05B4: /* HEBREW POINT HIRIQ */
>-        case 0x05BC: /* HEBREW POINT DAGESH OR MAPIQ */
>-        case 0x05C3: /* HEBREW PUNCTUATION SOF PASUQ */
>-        case 0x05F4: /* HEBREW PUNCTUATION GERSHAYIM */
>-        case 0x0609: /* ARABIC-INDIC PER MILLE SIGN */
>-        case 0x060A: /* ARABIC-INDIC PER TEN THOUSAND SIGN */
>-        case 0x0650: /* ARABIC KASRA */
>-        case 0x0660: /* ARABIC INDIC DIGIT ZERO */
>-        case 0x066A: /* ARABIC PERCENT SIGN */
>-        case 0x06D4: /* ARABIC FULL STOP */
>-        case 0x06F0: /* EXTENDED ARABIC INDIC DIGIT ZERO */
>-        case 0x0701: /* SYRIAC SUPRALINEAR FULL STOP */
>-        case 0x0702: /* SYRIAC SUBLINEAR FULL STOP */
>-        case 0x0703: /* SYRIAC SUPRALINEAR COLON */
>-        case 0x0704: /* SYRIAC SUBLINEAR COLON */
>-        case 0x1735: /* PHILIPPINE SINGLE PUNCTUATION */
>-        case 0x1D04: /* LATIN LETTER SMALL CAPITAL C */
>-        case 0x1D0F: /* LATIN LETTER SMALL CAPITAL O */
>-        case 0x1D1C: /* LATIN LETTER SMALL CAPITAL U */
>-        case 0x1D20: /* LATIN LETTER SMALL CAPITAL V */
>-        case 0x1D21: /* LATIN LETTER SMALL CAPITAL W */
>-        case 0x1D22: /* LATIN LETTER SMALL CAPITAL Z */
>-        case 0x1ECD: /* LATIN SMALL LETTER O WITH DOT BELOW */
>-        case 0x2010: /* HYPHEN */
>-        case 0x2011: /* NON-BREAKING HYPHEN */
>-        case 0x2024: /* ONE DOT LEADER */
>-        case 0x2027: /* HYPHENATION POINT */
>-        case 0x2039: /* SINGLE LEFT-POINTING ANGLE QUOTATION MARK */
>-        case 0x203A: /* SINGLE RIGHT-POINTING ANGLE QUOTATION MARK */
>-        case 0x2041: /* CARET INSERTION POINT */
>-        case 0x2044: /* FRACTION SLASH */
>-        case 0x2052: /* COMMERCIAL MINUS SIGN */
>-        case 0x2153: /* VULGAR FRACTION ONE THIRD */
>-        case 0x2154: /* VULGAR FRACTION TWO THIRDS */
>-        case 0x2155: /* VULGAR FRACTION ONE FIFTH */
>-        case 0x2156: /* VULGAR FRACTION TWO FIFTHS */
>-        case 0x2157: /* VULGAR FRACTION THREE FIFTHS */
>-        case 0x2158: /* VULGAR FRACTION FOUR FIFTHS */
>-        case 0x2159: /* VULGAR FRACTION ONE SIXTH */
>-        case 0x215A: /* VULGAR FRACTION FIVE SIXTHS */
>-        case 0x215B: /* VULGAR FRACTION ONE EIGHT */
>-        case 0x215C: /* VULGAR FRACTION THREE EIGHTHS */
>-        case 0x215D: /* VULGAR FRACTION FIVE EIGHTHS */
>-        case 0x215E: /* VULGAR FRACTION SEVEN EIGHTHS */
>-        case 0x215F: /* FRACTION NUMERATOR ONE */
>-        case 0x2212: /* MINUS SIGN */
>-        case 0x2215: /* DIVISION SLASH */
>-        case 0x2216: /* SET MINUS */
>-        case 0x2236: /* RATIO */
>-        case 0x233F: /* APL FUNCTIONAL SYMBOL SLASH BAR */
>-        case 0x23AE: /* INTEGRAL EXTENSION */
>-        case 0x244A: /* OCR DOUBLE BACKSLASH */
>-        case 0x2571: /* DisplayType::Box DRAWINGS LIGHT DIAGONAL UPPER RIGHT TO LOWER LEFT */
>-        case 0x2572: /* DisplayType::Box DRAWINGS LIGHT DIAGONAL UPPER LEFT TO LOWER RIGHT */
>-        case 0x29F6: /* SOLIDUS WITH OVERBAR */
>-        case 0x29F8: /* BIG SOLIDUS */
>-        case 0x2AFB: /* TRIPLE SOLIDUS BINARY RELATION */
>-        case 0x2AFD: /* DOUBLE SOLIDUS OPERATOR */
>-        case 0x2FF0: /* IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT */
>-        case 0x2FF1: /* IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO BELOW */
>-        case 0x2FF2: /* IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO MIDDLE AND RIGHT */
>-        case 0x2FF3: /* IDEOGRAPHIC DESCRIPTION CHARACTER ABOVE TO MIDDLE AND BELOW */
>-        case 0x2FF4: /* IDEOGRAPHIC DESCRIPTION CHARACTER FULL SURROUND */
>-        case 0x2FF5: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM ABOVE */
>-        case 0x2FF6: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM BELOW */
>-        case 0x2FF7: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LEFT */
>-        case 0x2FF8: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER LEFT */
>-        case 0x2FF9: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM UPPER RIGHT */
>-        case 0x2FFA: /* IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER LEFT */
>-        case 0x2FFB: /* IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID */
>-        case 0x3002: /* IDEOGRAPHIC FULL STOP */
>-        case 0x3008: /* LEFT ANGLE BRACKET */
>-        case 0x3014: /* LEFT TORTOISE SHELL BRACKET */
>-        case 0x3015: /* RIGHT TORTOISE SHELL BRACKET */
>-        case 0x3033: /* VERTICAL KANA REPEAT MARK UPPER HALF */
>-        case 0x3035: /* VERTICAL KANA REPEAT MARK LOWER HALF */
>-        case 0x321D: /* PARENTHESIZED KOREAN CHARACTER OJEON */
>-        case 0x321E: /* PARENTHESIZED KOREAN CHARACTER O HU */
>-        case 0x33AE: /* SQUARE RAD OVER S */
>-        case 0x33AF: /* SQUARE RAD OVER S SQUARED */
>-        case 0x33C6: /* SQUARE C OVER KG */
>-        case 0x33DF: /* SQUARE A OVER M */
>-        case 0x05B9: /* HEBREW POINT HOLAM */
>-        case 0x05BA: /* HEBREW POINT HOLAM HASER FOR VAV */
>-        case 0x05C1: /* HEBREW POINT SHIN DOT */
>-        case 0x05C2: /* HEBREW POINT SIN DOT */
>-        case 0x05C4: /* HEBREW MARK UPPER DOT */
>-        case 0xA731: /* LATIN LETTER SMALL CAPITAL S */
>-        case 0xA771: /* LATIN SMALL LETTER DUM */
>-        case 0xA789: /* MODIFIER LETTER COLON */
>-        case 0xFE14: /* PRESENTATION FORM FOR VERTICAL SEMICOLON */
>-        case 0xFE15: /* PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK */
>-        case 0xFE3F: /* PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET */
>-        case 0xFE5D: /* SMALL LEFT TORTOISE SHELL BRACKET */
>-        case 0xFE5E: /* SMALL RIGHT TORTOISE SHELL BRACKET */
>-        case 0xFF0E: /* FULLWIDTH FULL STOP */
>-        case 0xFF0F: /* FULL WIDTH SOLIDUS */
>-        case 0xFF61: /* HALFWIDTH IDEOGRAPHIC FULL STOP */
>-        case 0xFFFC: /* OBJECT REPLACEMENT CHARACTER */
>-        case 0xFFFD: /* REPLACEMENT CHARACTER */
>-        case 0x1F50F: /* LOCK WITH INK PEN */
>-        case 0x1F510: /* CLOSED LOCK WITH KEY */
>-        case 0x1F511: /* KEY */
>-        case 0x1F512: /* LOCK */
>-        case 0x1F513: /* OPEN LOCK */
>-            return YES;
>-        case 0x0307: /* COMBINING DOT ABOVE */
>-            return previousCodePoint == 0x0237 /* LATIN SMALL LETTER DOTLESS J */
>-                || previousCodePoint == 0x0131 /* LATIN SMALL LETTER DOTLESS I */
>-                || previousCodePoint == 0x05D5; /* HEBREW LETTER VAV */
>-        case 0x0548: /* ARMENIAN CAPITAL LETTER VO */
>-        case 0x054D: /* ARMENIAN CAPITAL LETTER SEH */
>-        case 0x0578: /* ARMENIAN SMALL LETTER VO */
>-        case 0x057D: /* ARMENIAN SMALL LETTER SEH */
>-            return previousCodePoint
>-                && !isASCIIDigitOrValidHostCharacter(previousCodePoint.value())
>-                && !isArmenianScriptCharacter(previousCodePoint.value());
>-        case '.':
>-            return NO;
>-        default:
>-            return previousCodePoint
>-                && isArmenianLookalikeCharacter(previousCodePoint.value())
>-                && !(isArmenianScriptCharacter(charCode) || isASCIIDigitOrValidHostCharacter(charCode));
>-    }
>-}
>-
>-static void whiteListIDNScript(const char* scriptName)
>-{
>-    int32_t script = u_getPropertyValueEnum(UCHAR_SCRIPT, scriptName);
>-    if (script >= 0 && script < USCRIPT_CODE_LIMIT) {
>-        size_t index = script / 32;
>-        uint32_t mask = 1 << (script % 32);
>-        IDNScriptWhiteList[index] |= mask;
>-    }
>-}
>+using namespace URLHelpers;
> 
> static BOOL readIDNScriptWhiteListFile(NSString *filename)
> {
>@@ -290,7 +76,9 @@ static BOOL readIDNScriptWhiteListFile(NSString *filename)
>     return YES;
> }
> 
>-static BOOL allCharactersInIDNScriptWhiteList(const UChar *buffer, int32_t length)
>+namespace URLHelpers {
>+
>+void loadIDNScriptWhiteList()
> {
>     static dispatch_once_t flag;
>     dispatch_once(&flag, ^{
>@@ -301,508 +89,37 @@ static BOOL allCharactersInIDNScriptWhiteList(const UChar *buffer, int32_t lengt
>             if (readIDNScriptWhiteListFile([[dirs objectAtIndex:i] stringByAppendingPathComponent:@"IDNScriptWhiteList.txt"]))
>                 return;
>         }
>-        const char* defaultIDNScriptWhiteList[20] = {
>-            "Common",
>-            "Inherited",
>-            "Arabic",
>-            "Armenian",
>-            "Bopomofo",
>-            "Canadian_Aboriginal",
>-            "Devanagari",
>-            "Deseret",
>-            "Gujarati",
>-            "Gurmukhi",
>-            "Hangul",
>-            "Han",
>-            "Hebrew",
>-            "Hiragana",
>-            "Katakana_Or_Hiragana",
>-            "Katakana",
>-            "Latin",
>-            "Tamil",
>-            "Thai",
>-            "Yi",
>-        };
>-        for (const char* scriptName : defaultIDNScriptWhiteList)
>-            whiteListIDNScript(scriptName);
>+        initializeDefaultIDNScriptWhiteList();
>     });
>-    
>-    int32_t i = 0;
>-    std::optional<UChar32> previousCodePoint;
>-    while (i < length) {
>-        UChar32 c;
>-        U16_NEXT(buffer, i, length, c)
>-        UErrorCode error = U_ZERO_ERROR;
>-        UScriptCode script = uscript_getScript(c, &error);
>-        if (error != U_ZERO_ERROR) {
>-            LOG_ERROR("got ICU error while trying to look at scripts: %d", error);
>-            return NO;
>-        }
>-        if (script < 0) {
>-            LOG_ERROR("got negative number for script code from ICU: %d", script);
>-            return NO;
>-        }
>-        if (script >= USCRIPT_CODE_LIMIT)
>-            return NO;
>-
>-        size_t index = script / 32;
>-        uint32_t mask = 1 << (script % 32);
>-        if (!(IDNScriptWhiteList[index] & mask))
>-            return NO;
>-        
>-        if (isLookalikeCharacter(previousCodePoint, c))
>-            return NO;
>-        previousCodePoint = c;
>-    }
>-    return YES;
>-}
>-
>-static bool isSecondLevelDomainNameAllowedByTLDRules(const UChar* buffer, int32_t length, const WTF::Function<bool(UChar)>& characterIsAllowed)
>-{
>-    ASSERT(length > 0);
>-
>-    for (int32_t i = length - 1; i >= 0; --i) {
>-        UChar ch = buffer[i];
>-        
>-        if (characterIsAllowed(ch))
>-            continue;
>-        
>-        // Only check the second level domain. Lower level registrars may have different rules.
>-        if (ch == '.')
>-            break;
>-        
>-        return false;
>-    }
>-    return true;
> }
> 
>-#define CHECK_RULES_IF_SUFFIX_MATCHES(suffix, function) \
>-    { \
>-        static const int32_t suffixLength = sizeof(suffix) / sizeof(suffix[0]); \
>-        if (length > suffixLength && 0 == memcmp(buffer + length - suffixLength, suffix, sizeof(suffix))) \
>-            return isSecondLevelDomainNameAllowedByTLDRules(buffer, length - suffixLength, function); \
>-    }
>-
>-static bool isRussianDomainNameCharacter(UChar ch)
>-{
>-    // Only modern Russian letters, digits and dashes are allowed.
>-    return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || isASCIIDigit(ch) || ch == '-';
>-}
>-
>-static BOOL allCharactersAllowedByTLDRules(const UChar* buffer, int32_t length)
>-{
>-    // Skip trailing dot for root domain.
>-    if (buffer[length - 1] == '.')
>-        length--;
>-
>-    // http://cctld.ru/files/pdf/docs/rules_ru-rf.pdf
>-    static const UChar cyrillicRF[] = {
>-        '.',
>-        0x0440, // CYRILLIC SMALL LETTER ER
>-        0x0444  // CYRILLIC SMALL LETTER EF
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicRF, isRussianDomainNameCharacter);
>-
>-    // http://rusnames.ru/rules.pl
>-    static const UChar cyrillicRUS[] = {
>-        '.',
>-        0x0440, // CYRILLIC SMALL LETTER ER
>-        0x0443, // CYRILLIC SMALL LETTER U
>-        0x0441  // CYRILLIC SMALL LETTER ES
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicRUS, isRussianDomainNameCharacter);
>-
>-    // http://ru.faitid.org/projects/moscow/documents/moskva/idn
>-    static const UChar cyrillicMOSKVA[] = {
>-        '.',
>-        0x043C, // CYRILLIC SMALL LETTER EM
>-        0x043E, // CYRILLIC SMALL LETTER O
>-        0x0441, // CYRILLIC SMALL LETTER ES
>-        0x043A, // CYRILLIC SMALL LETTER KA
>-        0x0432, // CYRILLIC SMALL LETTER VE
>-        0x0430  // CYRILLIC SMALL LETTER A
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicMOSKVA, isRussianDomainNameCharacter);
>-
>-    // http://www.dotdeti.ru/foruser/docs/regrules.php
>-    static const UChar cyrillicDETI[] = {
>-        '.',
>-        0x0434, // CYRILLIC SMALL LETTER DE
>-        0x0435, // CYRILLIC SMALL LETTER IE
>-        0x0442, // CYRILLIC SMALL LETTER TE
>-        0x0438  // CYRILLIC SMALL LETTER I
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicDETI, isRussianDomainNameCharacter);
>-
>-    // http://corenic.org - rules not published. The word is Russian, so only allowing Russian at this time,
>-    // although we may need to revise the checks if this ends up being used with other languages spoken in Russia.
>-    static const UChar cyrillicONLAYN[] = {
>-        '.',
>-        0x043E, // CYRILLIC SMALL LETTER O
>-        0x043D, // CYRILLIC SMALL LETTER EN
>-        0x043B, // CYRILLIC SMALL LETTER EL
>-        0x0430, // CYRILLIC SMALL LETTER A
>-        0x0439, // CYRILLIC SMALL LETTER SHORT I
>-        0x043D  // CYRILLIC SMALL LETTER EN
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicONLAYN, isRussianDomainNameCharacter);
>-
>-    // http://corenic.org - same as above.
>-    static const UChar cyrillicSAYT[] = {
>-        '.',
>-        0x0441, // CYRILLIC SMALL LETTER ES
>-        0x0430, // CYRILLIC SMALL LETTER A
>-        0x0439, // CYRILLIC SMALL LETTER SHORT I
>-        0x0442  // CYRILLIC SMALL LETTER TE
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicSAYT, isRussianDomainNameCharacter);
>-
>-    // http://pir.org/products/opr-domain/ - rules not published. According to the registry site,
>-    // the intended audience is "Russian and other Slavic-speaking markets".
>-    // Chrome appears to only allow Russian, so sticking with that for now.
>-    static const UChar cyrillicORG[] = {
>-        '.',
>-        0x043E, // CYRILLIC SMALL LETTER O
>-        0x0440, // CYRILLIC SMALL LETTER ER
>-        0x0433  // CYRILLIC SMALL LETTER GHE
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicORG, isRussianDomainNameCharacter);
>-
>-    // http://cctld.by/rules.html
>-    static const UChar cyrillicBEL[] = {
>-        '.',
>-        0x0431, // CYRILLIC SMALL LETTER BE
>-        0x0435, // CYRILLIC SMALL LETTER IE
>-        0x043B  // CYRILLIC SMALL LETTER EL
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicBEL, [](UChar ch) {
>-        // Russian and Byelorussian letters, digits and dashes are allowed.
>-        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x0456 || ch == 0x045E || ch == 0x2019 || isASCIIDigit(ch) || ch == '-';
>-    });
>-
>-    // http://www.nic.kz/docs/poryadok_vnedreniya_kaz_ru.pdf
>-    static const UChar cyrillicKAZ[] = {
>-        '.',
>-        0x049B, // CYRILLIC SMALL LETTER KA WITH DESCENDER
>-        0x0430, // CYRILLIC SMALL LETTER A
>-        0x0437  // CYRILLIC SMALL LETTER ZE
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicKAZ, [](UChar ch) {
>-        // Kazakh letters, digits and dashes are allowed.
>-        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x04D9 || ch == 0x0493 || ch == 0x049B || ch == 0x04A3 || ch == 0x04E9 || ch == 0x04B1 || ch == 0x04AF || ch == 0x04BB || ch == 0x0456 || isASCIIDigit(ch) || ch == '-';
>-    });
>-
>-    // http://uanic.net/docs/documents-ukr/Rules%20of%20UKR_v4.0.pdf
>-    static const UChar cyrillicUKR[] = {
>-        '.',
>-        0x0443, // CYRILLIC SMALL LETTER U
>-        0x043A, // CYRILLIC SMALL LETTER KA
>-        0x0440  // CYRILLIC SMALL LETTER ER
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicUKR, [](UChar ch) {
>-        // Russian and Ukrainian letters, digits and dashes are allowed.
>-        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x0491 || ch == 0x0404 || ch == 0x0456 || ch == 0x0457 || isASCIIDigit(ch) || ch == '-';
>-    });
>-
>-    // http://www.rnids.rs/data/DOKUMENTI/idn-srb-policy-termsofuse-v1.4-eng.pdf
>-    static const UChar cyrillicSRB[] = {
>-        '.',
>-        0x0441, // CYRILLIC SMALL LETTER ES
>-        0x0440, // CYRILLIC SMALL LETTER ER
>-        0x0431  // CYRILLIC SMALL LETTER BE
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicSRB, [](UChar ch) {
>-        // Serbian letters, digits and dashes are allowed.
>-        return (ch >= 0x0430 && ch <= 0x0438) || (ch >= 0x043A && ch <= 0x0448) || ch == 0x0452 || ch == 0x0458 || ch == 0x0459 || ch == 0x045A || ch == 0x045B || ch == 0x045F || isASCIIDigit(ch) || ch == '-';
>-    });
>-
>-    // http://marnet.mk/doc/pravilnik-mk-mkd.pdf
>-    static const UChar cyrillicMKD[] = {
>-        '.',
>-        0x043C, // CYRILLIC SMALL LETTER EM
>-        0x043A, // CYRILLIC SMALL LETTER KA
>-        0x0434  // CYRILLIC SMALL LETTER DE
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicMKD, [](UChar ch) {
>-        // Macedonian letters, digits and dashes are allowed.
>-        return (ch >= 0x0430 && ch <= 0x0438) || (ch >= 0x043A && ch <= 0x0448) || ch == 0x0453 || ch == 0x0455 || ch == 0x0458 || ch == 0x0459 || ch == 0x045A || ch == 0x045C || ch == 0x045F || isASCIIDigit(ch) || ch == '-';
>-    });
>-
>-    // https://www.mon.mn/cs/
>-    static const UChar cyrillicMON[] = {
>-        '.',
>-        0x043C, // CYRILLIC SMALL LETTER EM
>-        0x043E, // CYRILLIC SMALL LETTER O
>-        0x043D  // CYRILLIC SMALL LETTER EN
>-    };
>-    CHECK_RULES_IF_SUFFIX_MATCHES(cyrillicMON, [](UChar ch) {
>-        // Mongolian letters, digits and dashes are allowed.
>-        return (ch >= 0x0430 && ch <= 0x044f) || ch == 0x0451 || ch == 0x04E9 || ch == 0x04AF || isASCIIDigit(ch) || ch == '-';
>-    });
>-
>-    // Not a known top level domain with special rules.
>-    return NO;
>-}
>-
>-// Return value of nil means no mapping is necessary.
>-// If makeString is NO, then return value is either nil or self to indicate mapping is necessary.
>-// If makeString is YES, then return value is either nil or the mapped string.
>-static NSString *mapHostNameWithRange(NSString *string, NSRange range, BOOL encode, BOOL makeString, BOOL *error)
>-{
>-    if (range.length > HOST_NAME_BUFFER_LENGTH)
>-        return nil;
>-    
>-    if (![string length])
>-        return nil;
>-    
>-    UChar sourceBuffer[HOST_NAME_BUFFER_LENGTH];
>-    UChar destinationBuffer[HOST_NAME_BUFFER_LENGTH];
>-    
>-    if (encode && [string rangeOfString:@"%" options:NSLiteralSearch range:range].location != NSNotFound) {
>-        NSString *substring = [string substringWithRange:range];
>-        substring = CFBridgingRelease(CFURLCreateStringByReplacingPercentEscapes(nullptr, (CFStringRef)substring, CFSTR("")));
>-        if (substring) {
>-            string = substring;
>-            range = NSMakeRange(0, [string length]);
>-        }
>-    }
>+} // namespace URLHelpers
>     
>-    int length = range.length;
>-    [string getCharacters:sourceBuffer range:range];
>-    
>-    UErrorCode uerror = U_ZERO_ERROR;
>-    UIDNAInfo processingDetails = UIDNA_INFO_INITIALIZER;
>-    int32_t numCharactersConverted = (encode ? uidna_nameToASCII : uidna_nameToUnicode)(&URLParser::internationalDomainNameTranscoder(), sourceBuffer, length, destinationBuffer, HOST_NAME_BUFFER_LENGTH, &processingDetails, &uerror);
>-    if (length && (U_FAILURE(uerror) || processingDetails.errors)) {
>-        *error = YES;
>-        return nil;
>-    }
>-    
>-    if (numCharactersConverted == length && !memcmp(sourceBuffer, destinationBuffer, length * sizeof(UChar)))
>-        return nil;
>-    
>-    if (!encode && !allCharactersInIDNScriptWhiteList(destinationBuffer, numCharactersConverted) && !allCharactersAllowedByTLDRules(destinationBuffer, numCharactersConverted))
>-        return nil;
>-    
>-    return makeString ? [NSString stringWithCharacters:destinationBuffer length:numCharactersConverted] : string;
>-}
>-
>-static BOOL hostNameNeedsDecodingWithRange(NSString *string, NSRange range, BOOL *error)
>-{
>-    return mapHostNameWithRange(string, range, NO, NO, error) != nil;
>-}
>- 
>-static BOOL hostNameNeedsEncodingWithRange(NSString *string, NSRange range, BOOL *error)
>+static String decodePercentEscapes(const String& string)
> {
>-    return mapHostNameWithRange(string, range, YES,  NO, error) != nil;
>-}
>+    NSString *substring = (NSString *)string;
>+    substring = CFBridgingRelease(CFURLCreateStringByReplacingPercentEscapes(nullptr, (CFStringRef)substring, CFSTR("")));
> 
>-static NSString *decodeHostNameWithRange(NSString *string, NSRange range)
>-{
>-    BOOL error = NO;
>-    NSString *host = mapHostNameWithRange(string, range, NO, YES, &error);
>-    if (error)
>-        return nil;
>-    return !host ? string : host;
>-}
>+    if (!substring)
>+        return string;
> 
>-static NSString *encodeHostNameWithRange(NSString *string, NSRange range)
>-{
>-    BOOL error = NO;
>-    NSString *host = mapHostNameWithRange(string, range, YES, YES, &error);
>-    if (error)
>-        return nil;
>-    return !host ? string : host;
>+    return (String)substring;
> }
> 
> NSString *decodeHostName(NSString *string)
> {
>-    BOOL error = NO;
>-    NSString *host = mapHostNameWithRange(string, NSMakeRange(0, [string length]), NO, YES, &error);
>-    if (error)
>+    std::optional<String> host = mapHostName(string, std::nullopt);
>+    if (!host)
>         return nil;
>-    return !host ? string : host;
>+    return !*host ? string : (NSString *)*host;
> }
> 
> NSString *encodeHostName(NSString *string)
> {
>-    BOOL error = NO;
>-    NSString *host = mapHostNameWithRange(string, NSMakeRange(0, [string length]), YES, YES, &error);
>-    if (error)
>+    std::optional<String> host = mapHostName(string, decodePercentEscapes);
>+    if (!host)
>         return nil;
>-    return !host ? string : host;
>-}
>-
>-static void collectRangesThatNeedMapping(NSString *string, NSRange range, RetainPtr<NSMutableArray>& array, BOOL encode)
>-{
>-    // Generally, we want to optimize for the case where there is one host name that does not need mapping.
>-    // Therefore, we use nil to indicate no mapping here and an empty array to indicate error.
>-
>-    BOOL error = NO;
>-    BOOL needsMapping = encode ? hostNameNeedsEncodingWithRange(string, range, &error) : hostNameNeedsDecodingWithRange(string, range, &error);
>-    if (!error && !needsMapping)
>-        return;
>-    
>-    if (!array)
>-        array = adoptNS([NSMutableArray new]);
>-
>-    if (!error)
>-        [array addObject:[NSValue valueWithRange:range]];
>-}
>-
>-static void collectRangesThatNeedEncoding(NSString *string, NSRange range, RetainPtr<NSMutableArray>& array)
>-{
>-    return collectRangesThatNeedMapping(string, range, array, YES);
>-}
>-
>-static void collectRangesThatNeedDecoding(NSString *string, NSRange range, RetainPtr<NSMutableArray>& array)
>-{
>-    return collectRangesThatNeedMapping(string, range, array, NO);
>-}
>-
>-static void applyHostNameFunctionToMailToURLString(NSString *string, StringRangeApplierFunction f, RetainPtr<NSMutableArray>& array)
>-{
>-    // In a mailto: URL, host names come after a '@' character and end with a '>' or ',' or '?' character.
>-    // Skip quoted strings so that characters in them don't confuse us.
>-    // When we find a '?' character, we are past the part of the URL that contains host names.
>-    
>-    static NeverDestroyed<RetainPtr<NSCharacterSet>> hostNameOrStringStartCharacters = [NSCharacterSet characterSetWithCharactersInString:@"\"@?"];
>-    static NeverDestroyed<RetainPtr<NSCharacterSet>> hostNameEndCharacters = [NSCharacterSet characterSetWithCharactersInString:@">,?"];
>-    static NeverDestroyed<RetainPtr<NSCharacterSet>> quotedStringCharacters = [NSCharacterSet characterSetWithCharactersInString:@"\"\\"];
>-    
>-    unsigned stringLength = [string length];
>-    NSRange remaining = NSMakeRange(0, stringLength);
>-    
>-    while (1) {
>-        // Find start of host name or of quoted string.
>-        NSRange hostNameOrStringStart = [string rangeOfCharacterFromSet:hostNameOrStringStartCharacters.get().get() options:0 range:remaining];
>-        if (hostNameOrStringStart.location == NSNotFound)
>-            return;
>-
>-        unichar c = [string characterAtIndex:hostNameOrStringStart.location];
>-        remaining.location = NSMaxRange(hostNameOrStringStart);
>-        remaining.length = stringLength - remaining.location;
>-        
>-        if (c == '?')
>-            return;
>-        
>-        if (c == '@') {
>-            // Find end of host name.
>-            unsigned hostNameStart = remaining.location;
>-            NSRange hostNameEnd = [string rangeOfCharacterFromSet:hostNameEndCharacters.get().get() options:0 range:remaining];
>-            BOOL done;
>-            if (hostNameEnd.location == NSNotFound) {
>-                hostNameEnd.location = stringLength;
>-                done = YES;
>-            } else {
>-                remaining.location = hostNameEnd.location;
>-                remaining.length = stringLength - remaining.location;
>-                done = NO;
>-            }
>-            
>-            // Process host name range.
>-            f(string, NSMakeRange(hostNameStart, hostNameEnd.location - hostNameStart), array);
>-            
>-            if (done)
>-                return;
>-        } else {
>-            // Skip quoted string.
>-            ASSERT(c == '"');
>-            while (1) {
>-                NSRange escapedCharacterOrStringEnd = [string rangeOfCharacterFromSet:quotedStringCharacters.get().get() options:0 range:remaining];
>-                if (escapedCharacterOrStringEnd.location == NSNotFound)
>-                    return;
>-
>-                c = [string characterAtIndex:escapedCharacterOrStringEnd.location];
>-                remaining.location = NSMaxRange(escapedCharacterOrStringEnd);
>-                remaining.length = stringLength - remaining.location;
>-                
>-                // If we are the end of the string, then break from the string loop back to the host name loop.
>-                if (c == '"')
>-                    break;
>-                
>-                // Skip escaped character.
>-                ASSERT(c == '\\');
>-                if (!remaining.length)
>-                    return;
>-
>-                remaining.location += 1;
>-                remaining.length -= 1;
>-            }
>-        }
>-    }
>-}
>-
>-static void applyHostNameFunctionToURLString(NSString *string, StringRangeApplierFunction f, RetainPtr<NSMutableArray>& array)
>-{
>-    // Find hostnames. Too bad we can't use any real URL-parsing code to do this,
>-    // but we have to do it before doing all the %-escaping, and this is the only
>-    // code we have that parses mailto URLs anyway.
>-    
>-    // Maybe we should implement this using a character buffer instead?
>-    
>-    if (protocolIs(string, "mailto")) {
>-        applyHostNameFunctionToMailToURLString(string, f, array);
>-        return;
>-    }
>-    
>-    // Find the host name in a hierarchical URL.
>-    // It comes after a "://" sequence, with scheme characters preceding.
>-    // If ends with the end of the string or a ":", "/", or a "?".
>-    // If there is a "@" character, the host part is just the part after the "@".
>-    NSRange separatorRange = [string rangeOfString:@"://"];
>-    if (separatorRange.location == NSNotFound)
>-        return;
>-    
>-    // Check that all characters before the :// are valid scheme characters.
>-    static NeverDestroyed<RetainPtr<NSCharacterSet>> nonSchemeCharacters = [[NSCharacterSet characterSetWithCharactersInString:@"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+-."] invertedSet];
>-    if ([string rangeOfCharacterFromSet:nonSchemeCharacters.get().get() options:0 range:NSMakeRange(0, separatorRange.location)].location != NSNotFound)
>-        return;
>-    
>-    unsigned stringLength = [string length];
>-    
>-    static NeverDestroyed<RetainPtr<NSCharacterSet>> hostTerminators = [NSCharacterSet characterSetWithCharactersInString:@":/?#"];
>-    
>-    // Start after the separator.
>-    unsigned authorityStart = NSMaxRange(separatorRange);
>-    
>-    // Find terminating character.
>-    NSRange hostNameTerminator = [string rangeOfCharacterFromSet:hostTerminators.get().get() options:0 range:NSMakeRange(authorityStart, stringLength - authorityStart)];
>-    unsigned hostNameEnd = hostNameTerminator.location == NSNotFound ? stringLength : hostNameTerminator.location;
>-    
>-    // Find "@" for the start of the host name.
>-    NSRange userInfoTerminator = [string rangeOfString:@"@" options:0 range:NSMakeRange(authorityStart, hostNameEnd - authorityStart)];
>-    unsigned hostNameStart = userInfoTerminator.location == NSNotFound ? authorityStart : NSMaxRange(userInfoTerminator);
>-    
>-    return f(string, NSMakeRange(hostNameStart, hostNameEnd - hostNameStart), array);
>-}
>-
>-static RetainPtr<NSString> mapHostNames(NSString *string, BOOL encode)
>-{
>-    // Generally, we want to optimize for the case where there is one host name that does not need mapping.
>-    
>-    if (encode && [string canBeConvertedToEncoding:NSASCIIStringEncoding])
>-        return string;
>-    
>-    // Make a list of ranges that actually need mapping.
>-    RetainPtr<NSMutableArray> hostNameRanges;
>-    StringRangeApplierFunction f = encode ? collectRangesThatNeedEncoding : collectRangesThatNeedDecoding;
>-    applyHostNameFunctionToURLString(string, f, hostNameRanges);
>-    if (!hostNameRanges)
>-        return string;
>-
>-    if (![hostNameRanges count])
>-        return nil;
>-    
>-    // Do the mapping.
>-    auto mutableCopy = adoptNS([string mutableCopy]);
>-    unsigned i = [hostNameRanges count];
>-    while (i--) {
>-        NSRange hostNameRange = [[hostNameRanges objectAtIndex:i] rangeValue];
>-        NSString *mappedHostName = encode ? encodeHostNameWithRange(string, hostNameRange) : decodeHostNameWithRange(string, hostNameRange);
>-        [mutableCopy replaceCharactersInRange:hostNameRange withString:mappedHostName];
>-    }
>-    return mutableCopy;
>+    return !*host ? string : (NSString *)*host;
> }
> 
> static RetainPtr<NSString> stringByTrimmingWhitespace(NSString *string)
>@@ -904,18 +221,18 @@ NSURL *URLWithUserTypedString(NSString *string, NSURL *nsURL)
>     if (!string)
>         return nil;
> 
>-    auto mappedString = mapHostNames(stringByTrimmingWhitespace(string).get(), YES);
>+    auto mappedString = mapHostNames(stringByTrimmingWhitespace(string).get(), decodePercentEscapes);
>     if (!mappedString)
>         return nil;
> 
>     // Let's check whether the URL is bogus.
>-    URL url { URL { nsURL }, mappedString.get() };
>+    URL url { URL { nsURL }, mappedString };
>     if (!url.createCFURL())
>         return nil;
> 
>     // FIXME: https://bugs.webkit.org/show_bug.cgi?id=186057
>     // We should be able to use url.createCFURL instead of using directly CFURL parsing routines.
>-    NSData *data = dataWithUserTypedString(mappedString.get());
>+    NSData *data = dataWithUserTypedString(mappedString);
>     if (!data)
>         return [NSURL URLWithString:@""];
> 
>@@ -1054,119 +371,11 @@ NSData *originalURLData(NSURL *URL)
>     return data;
> }
> 
>-static CFStringRef createStringWithEscapedUnsafeCharacters(CFStringRef string)
>-{
>-    CFIndex length = CFStringGetLength(string);
>-    Vector<UChar, URL_BYTES_BUFFER_LENGTH> sourceBuffer(length);
>-    CFStringGetCharacters(string, CFRangeMake(0, length), sourceBuffer.data());
>-    
>-    Vector<UChar, URL_BYTES_BUFFER_LENGTH> outBuffer;
>-    
>-    std::optional<UChar32> previousCodePoint;
>-    CFIndex i = 0;
>-    while (i < length) {
>-        UChar32 c;
>-        U16_NEXT(sourceBuffer, i, length, c)
>-        
>-        if (isLookalikeCharacter(previousCodePoint, c)) {
>-            uint8_t utf8Buffer[4];
>-            CFIndex offset = 0;
>-            UBool failure = false;
>-            U8_APPEND(utf8Buffer, offset, 4, c, failure)
>-            ASSERT(!failure);
>-            
>-            for (CFIndex j = 0; j < offset; ++j) {
>-                outBuffer.append('%');
>-                outBuffer.append(upperNibbleToASCIIHexDigit(utf8Buffer[j]));
>-                outBuffer.append(lowerNibbleToASCIIHexDigit(utf8Buffer[j]));
>-            }
>-        } else {
>-            UChar utf16Buffer[2];
>-            CFIndex offset = 0;
>-            UBool failure = false;
>-            U16_APPEND(utf16Buffer, offset, 2, c, failure)
>-            ASSERT(!failure);
>-            for (CFIndex j = 0; j < offset; ++j)
>-                outBuffer.append(utf16Buffer[j]);
>-        }
>-        previousCodePoint = c;
>-    }
>-    
>-    return CFStringCreateWithCharacters(nullptr, outBuffer.data(), outBuffer.size());
>-}
>-
> NSString *userVisibleString(NSURL *URL)
> {
>     NSData *data = originalURLData(URL);
>-    const unsigned char *before = static_cast<const unsigned char*>([data bytes]);
>-    int length = [data length];
>-    
>-    bool mayNeedHostNameDecoding = false;
>-    
>-    const unsigned char *p = before;
>-    int bufferLength = (length * 3) + 1;
>-    Vector<char, URL_BYTES_BUFFER_LENGTH> after(bufferLength); // large enough to %-escape every character
>-    char *q = after.data();
>-    for (int i = 0; i < length; i++) {
>-        unsigned char c = p[i];
>-        // unescape escape sequences that indicate bytes greater than 0x7f
>-        if (c == '%' && (i + 1 < length && isASCIIHexDigit(p[i + 1])) && i + 2 < length && isASCIIHexDigit(p[i + 2])) {
>-            auto u = toASCIIHexValue(p[i + 1], p[i + 2]);
>-            if (u > 0x7f) {
>-                // unescape
>-                *q++ = u;
>-            } else {
>-                // do not unescape
>-                *q++ = p[i];
>-                *q++ = p[i + 1];
>-                *q++ = p[i + 2];
>-            }
>-            i += 2;
>-        } else {
>-            *q++ = c;
>-            
>-            // Check for "xn--" in an efficient, non-case-sensitive, way.
>-            if (c == '-' && i >= 3 && !mayNeedHostNameDecoding && (q[-4] | 0x20) == 'x' && (q[-3] | 0x20) == 'n' && q[-2] == '-')
>-                mayNeedHostNameDecoding = true;
>-        }
>-    }
>-    *q = '\0';
>-    
>-    // Check string to see if it can be converted to display using UTF-8  
>-    RetainPtr<NSString> result = [NSString stringWithUTF8String:after.data()];
>-    if (!result) {
>-        // Could not convert to UTF-8.
>-        // Convert characters greater than 0x7f to escape sequences.
>-        // Shift current string to the end of the buffer
>-        // then we will copy back bytes to the start of the buffer 
>-        // as we convert.
>-        int afterlength = q - after.data();
>-        char *p = after.data() + bufferLength - afterlength - 1;
>-        memmove(p, after.data(), afterlength + 1); // copies trailing '\0'
>-        char *q = after.data();
>-        while (*p) {
>-            unsigned char c = *p;
>-            if (c > 0x7f) {
>-                *q++ = '%';
>-                *q++ = upperNibbleToASCIIHexDigit(c);
>-                *q++ = lowerNibbleToASCIIHexDigit(c);
>-            } else
>-                *q++ = *p;
>-            p++;
>-        }
>-        *q = '\0';
>-        result = [NSString stringWithUTF8String:after.data()];
>-    }
>-    
>-    if (mayNeedHostNameDecoding) {
>-        // FIXME: Is it good to ignore the failure of mapHostNames and keep result intact?
>-        auto mappedResult = mapHostNames(result.get(), NO);
>-        if (mappedResult)
>-            result = mappedResult;
>-    }
>-
>-    result = [result precomposedStringWithCanonicalMapping];
>-    return CFBridgingRelease(createStringWithEscapedUnsafeCharacters((__bridge CFStringRef)result.get()));
>+    CString string(static_cast<const char*>([data bytes]), [data length]);
>+    return userVisibleURL(string);
> }
> 
> BOOL isUserVisibleURL(NSString *string)
>diff --git a/Source/WebCore/ChangeLog b/Source/WebCore/ChangeLog
>index 203064a3760..4ed1ea1311f 100644
>--- a/Source/WebCore/ChangeLog
>+++ b/Source/WebCore/ChangeLog
>@@ -1,3 +1,15 @@
>+2018-12-14  Ms2ger  <Ms2ger@igalia.com>
>+
>+        [GTK][WPE] Need a function to convert internal URI to display ("pretty") URI
>+        https://bugs.webkit.org/show_bug.cgi?id=174816
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        Tests: enabled fast/url/user-visible/.
>+
>+        * testing/Internals.cpp:
>+        (WebCore::Internals::userVisibleString): Enable method on all platforms.
>+
> 2018-12-13  Eric Carlson  <eric.carlson@apple.com>
> 
>         [MediaStream] Calculate width or height when constraints contain only the other
>diff --git a/Source/WebCore/testing/Internals.cpp b/Source/WebCore/testing/Internals.cpp
>index c3227214ae8..a7719e27ee1 100644
>--- a/Source/WebCore/testing/Internals.cpp
>+++ b/Source/WebCore/testing/Internals.cpp
>@@ -185,6 +185,7 @@
> #include <wtf/Language.h>
> #include <wtf/MemoryPressureHandler.h>
> #include <wtf/MonotonicTime.h>
>+#include <wtf/URLHelpers.h>
> #include <wtf/text/StringBuffer.h>
> #include <wtf/text/StringBuilder.h>
> #include <wtf/text/StringConcatenateNumbers.h>
>@@ -4209,10 +4210,9 @@ String Internals::getCurrentMediaControlsStatusForElement(HTMLMediaElement& medi
> 
> #if !PLATFORM(COCOA)
> 
>-String Internals::userVisibleString(const DOMURL&)
>+String Internals::userVisibleString(const DOMURL& url)
> {
>-    // Cocoa-specific function. Could ASSERT_NOT_REACHED, but that's probably overkill.
>-    return String();
>+    return WTF::URLHelpers::userVisibleURL(url.href().string().utf8());
> }
> 
> #endif
>diff --git a/Source/WebKit/ChangeLog b/Source/WebKit/ChangeLog
>index a7196883fc5..4ae2cf55c81 100644
>--- a/Source/WebKit/ChangeLog
>+++ b/Source/WebKit/ChangeLog
>@@ -1,3 +1,27 @@
>+2018-12-14  Ms2ger  <Ms2ger@igalia.com>
>+
>+        [GTK][WPE] Need a function to convert internal URI to display ("pretty") URI
>+        https://bugs.webkit.org/show_bug.cgi?id=174816
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        Add webkit_uri_for_display for GTK and WPE.
>+
>+        * PlatformGTK.cmake:
>+        * PlatformWPE.cmake:
>+        * SourcesGTK.txt:
>+        * SourcesWPE.txt:
>+        * UIProcess/API/glib/WebKitURIUtilities.cpp: Added.
>+        (webkit_uri_for_display):
>+        * UIProcess/API/gtk/WebKitURIUtilities.h: Added.
>+        * UIProcess/API/gtk/docs/webkit2gtk-4.0-sections.txt:
>+        * UIProcess/API/gtk/docs/webkit2gtk-docs.sgml:
>+        * UIProcess/API/gtk/webkit2.h:
>+        * UIProcess/API/wpe/WebKitURIUtilities.h: Added.
>+        * UIProcess/API/wpe/docs/wpe-0.1-sections.txt:
>+        * UIProcess/API/wpe/docs/wpe-docs.sgml:
>+        * UIProcess/API/wpe/webkit.h:
>+
> 2018-12-13  Chris Fleizach  <cfleizach@apple.com>
> 
>         [meta][WebKit] Remove using namespace WebCore and WebKit in the global scope for unified source builds
>diff --git a/Source/WebKit/PlatformGTK.cmake b/Source/WebKit/PlatformGTK.cmake
>index 2281274cf0c..172970941e3 100644
>--- a/Source/WebKit/PlatformGTK.cmake
>+++ b/Source/WebKit/PlatformGTK.cmake
>@@ -103,6 +103,7 @@ set(WebKit2GTK_INSTALLED_HEADERS
>     ${WEBKIT_DIR}/UIProcess/API/gtk/WebKitURIRequest.h
>     ${WEBKIT_DIR}/UIProcess/API/gtk/WebKitURIResponse.h
>     ${WEBKIT_DIR}/UIProcess/API/gtk/WebKitURISchemeRequest.h
>+    ${WEBKIT_DIR}/UIProcess/API/gtk/WebKitURIUtilities.h
>     ${WEBKIT_DIR}/UIProcess/API/gtk/WebKitUserContent.h
>     ${WEBKIT_DIR}/UIProcess/API/gtk/WebKitUserContentManager.h
>     ${WEBKIT_DIR}/UIProcess/API/gtk/WebKitUserMediaPermissionRequest.h
>diff --git a/Source/WebKit/PlatformWPE.cmake b/Source/WebKit/PlatformWPE.cmake
>index 1f675c44e4c..c39c1c379ef 100644
>--- a/Source/WebKit/PlatformWPE.cmake
>+++ b/Source/WebKit/PlatformWPE.cmake
>@@ -132,6 +132,7 @@ set(WPE_API_INSTALLED_HEADERS
>     ${WEBKIT_DIR}/UIProcess/API/wpe/WebKitURIRequest.h
>     ${WEBKIT_DIR}/UIProcess/API/wpe/WebKitURIResponse.h
>     ${WEBKIT_DIR}/UIProcess/API/wpe/WebKitURISchemeRequest.h
>+    ${WEBKIT_DIR}/UIProcess/API/wpe/WebKitURIUtilities.h
>     ${WEBKIT_DIR}/UIProcess/API/wpe/WebKitUserContent.h
>     ${WEBKIT_DIR}/UIProcess/API/wpe/WebKitUserContentManager.h
>     ${WEBKIT_DIR}/UIProcess/API/wpe/WebKitUserMediaPermissionRequest.h
>diff --git a/Source/WebKit/SourcesGTK.txt b/Source/WebKit/SourcesGTK.txt
>index 265384b6418..59b08140cb8 100644
>--- a/Source/WebKit/SourcesGTK.txt
>+++ b/Source/WebKit/SourcesGTK.txt
>@@ -167,6 +167,7 @@ UIProcess/API/glib/WebKitSecurityOrigin.cpp @no-unify
> UIProcess/API/glib/WebKitSettings.cpp @no-unify
> UIProcess/API/glib/WebKitUIClient.cpp @no-unify
> UIProcess/API/glib/WebKitURISchemeRequest.cpp @no-unify
>+UIProcess/API/glib/WebKitURIUtilities.cpp @no-unify
> UIProcess/API/glib/WebKitUserContent.cpp @no-unify
> UIProcess/API/glib/WebKitUserContentManager.cpp @no-unify
> UIProcess/API/glib/WebKitUserMediaPermissionRequest.cpp @no-unify
>diff --git a/Source/WebKit/SourcesWPE.txt b/Source/WebKit/SourcesWPE.txt
>index 8ee2fef42a6..b9a08bc0b7a 100644
>--- a/Source/WebKit/SourcesWPE.txt
>+++ b/Source/WebKit/SourcesWPE.txt
>@@ -152,6 +152,7 @@ UIProcess/API/glib/WebKitSecurityOrigin.cpp @no-unify
> UIProcess/API/glib/WebKitSettings.cpp @no-unify
> UIProcess/API/glib/WebKitUIClient.cpp @no-unify
> UIProcess/API/glib/WebKitURISchemeRequest.cpp @no-unify
>+UIProcess/API/glib/WebKitURIUtilities.cpp @no-unify
> UIProcess/API/glib/WebKitUserContent.cpp @no-unify
> UIProcess/API/glib/WebKitUserContentManager.cpp @no-unify
> UIProcess/API/glib/WebKitUserMediaPermissionRequest.cpp @no-unify
>diff --git a/Source/WebKit/UIProcess/API/glib/WebKitURIUtilities.cpp b/Source/WebKit/UIProcess/API/glib/WebKitURIUtilities.cpp
>new file mode 100644
>index 00000000000..4940fe89b1d
>--- /dev/null
>+++ b/Source/WebKit/UIProcess/API/glib/WebKitURIUtilities.cpp
>@@ -0,0 +1,57 @@
>+/*
>+ * Copyright (C) 2018 Igalia S.L.
>+ *
>+ * This library is free software; you can redistribute it and/or
>+ * modify it under the terms of the GNU Library General Public
>+ * License as published by the Free Software Foundation; either
>+ * version 2 of the License, or (at your option) any later version.
>+ *
>+ * This library is distributed in the hope that it will be useful,
>+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
>+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
>+ * Library General Public License for more details.
>+ *
>+ * You should have received a copy of the GNU Library General Public License
>+ * along with this library; see the file COPYING.LIB.  If not, write to
>+ * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
>+ * Boston, MA 02110-1301, USA.
>+ */
>+
>+#include "config.h"
>+#include "WebKitURIUtilities.h"
>+
>+#include <wtf/URLHelpers.h>
>+#include <wtf/text/CString.h>
>+#include <wtf/text/WTFString.h>
>+
>+/**
>+ * SECTION: WebKitURIUtilities
>+ * @Short_description: Utility functions to manipulate URIs
>+ * @Title: WebKitURIUtilities
>+ */
>+
>+/**
>+ * webkit_uri_for_display:
>+ * @uri: the URI to be converted
>+ *
>+ * Use this function to format a URI for display. The URIs used internally by
>+ * WebKit may contain percent-encoded characters or Punycode, which are not
>+ * generally suitable to display to users. This function provides protection
>+ * against IDN homograph attacks, so in some cases the host part of the returned
>+ * URI may be in Punycode if the safety check fails.
>+ *
>+ * Returns: (nullable) (transfer full): @uri suitable for display, or %NULL in
>+ *    case of error.
>+ *
>+ * Since: 2.24
>+ */
>+gchar* webkit_uri_for_display(const gchar* uri)
>+{
>+    g_return_val_if_fail(uri, nullptr);
>+
>+    String result = WTF::URLHelpers::userVisibleURL(uri);
>+    if (!result)
>+        return nullptr;
>+
>+    return g_strdup(result.utf8().data());
>+}
>diff --git a/Source/WebKit/UIProcess/API/gtk/WebKitURIUtilities.h b/Source/WebKit/UIProcess/API/gtk/WebKitURIUtilities.h
>new file mode 100644
>index 00000000000..3a307766137
>--- /dev/null
>+++ b/Source/WebKit/UIProcess/API/gtk/WebKitURIUtilities.h
>@@ -0,0 +1,37 @@
>+/*
>+ * Copyright (C) 2018 Igalia S.L.
>+ *
>+ * This library is free software; you can redistribute it and/or
>+ * modify it under the terms of the GNU Library General Public
>+ * License as published by the Free Software Foundation; either
>+ * version 2 of the License, or (at your option) any later version.
>+ *
>+ * This library is distributed in the hope that it will be useful,
>+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
>+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
>+ * Library General Public License for more details.
>+ *
>+ * You should have received a copy of the GNU Library General Public License
>+ * along with this library; see the file COPYING.LIB.  If not, write to
>+ * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
>+ * Boston, MA 02110-1301, USA.
>+ */
>+
>+#if !defined(__WEBKIT2_H_INSIDE__) && !defined(WEBKIT2_COMPILATION)
>+#error "Only <webkit2/webkit2.h> can be included directly."
>+#endif
>+
>+#ifndef WebKitURIUtilities_h
>+#define WebKitURIUtilities_h
>+
>+#include <glib.h>
>+#include <webkit2/WebKitDefines.h>
>+
>+G_BEGIN_DECLS
>+
>+WEBKIT_API gchar *
>+webkit_uri_for_display (const gchar *uri);
>+
>+G_END_DECLS
>+
>+#endif
>diff --git a/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-4.0-sections.txt b/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-4.0-sections.txt
>index 756aaa4de72..6421859bd0d 100644
>--- a/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-4.0-sections.txt
>+++ b/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-4.0-sections.txt
>@@ -1645,3 +1645,8 @@ WEBKIT_PRINT_CUSTOM_WIDGET_GET_CLASS
> WebKitPrintCustomWidgetPrivate
> webkit_print_custom_widget_get_type
> </SECTION>
>+
>+<SECTION>
>+<FILE>WebKitURIUtilities</FILE>
>+webkit_uri_for_display
>+</SECTION>
>diff --git a/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-docs.sgml b/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-docs.sgml
>index 8d11fbdb9fd..f18b3fd8c3a 100644
>--- a/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-docs.sgml
>+++ b/Source/WebKit/UIProcess/API/gtk/docs/webkit2gtk-docs.sgml
>@@ -74,6 +74,11 @@
>     <xi:include href="xml/WebKitConsoleMessage.xml"/>
>   </chapter>
> 
>+  <chapter>
>+    <title>Utilities</title>
>+    <xi:include href="xml/WebKitURIUtilities.xml"/>
>+  </chapter>
>+
>   <index id="index-all">
>     <title>Index</title>
>   </index>
>diff --git a/Source/WebKit/UIProcess/API/gtk/webkit2.h b/Source/WebKit/UIProcess/API/gtk/webkit2.h
>index b9c000970a0..5c6e4ccec5a 100644
>--- a/Source/WebKit/UIProcess/API/gtk/webkit2.h
>+++ b/Source/WebKit/UIProcess/API/gtk/webkit2.h
>@@ -73,6 +73,7 @@
> #include <webkit2/WebKitURIRequest.h>
> #include <webkit2/WebKitURIResponse.h>
> #include <webkit2/WebKitURISchemeRequest.h>
>+#include <webkit2/WebKitURIUtilities.h>
> #include <webkit2/WebKitUserContent.h>
> #include <webkit2/WebKitUserContentManager.h>
> #include <webkit2/WebKitUserMediaPermissionRequest.h>
>diff --git a/Source/WebKit/UIProcess/API/wpe/WebKitURIUtilities.h b/Source/WebKit/UIProcess/API/wpe/WebKitURIUtilities.h
>new file mode 100644
>index 00000000000..cb05f000ad5
>--- /dev/null
>+++ b/Source/WebKit/UIProcess/API/wpe/WebKitURIUtilities.h
>@@ -0,0 +1,37 @@
>+/*
>+ * Copyright (C) 2018 Igalia S.L.
>+ *
>+ * This library is free software; you can redistribute it and/or
>+ * modify it under the terms of the GNU Library General Public
>+ * License as published by the Free Software Foundation; either
>+ * version 2 of the License, or (at your option) any later version.
>+ *
>+ * This library is distributed in the hope that it will be useful,
>+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
>+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
>+ * Library General Public License for more details.
>+ *
>+ * You should have received a copy of the GNU Library General Public License
>+ * along with this library; see the file COPYING.LIB.  If not, write to
>+ * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
>+ * Boston, MA 02110-1301, USA.
>+ */
>+
>+#if !defined(__WEBKIT_H_INSIDE__) && !defined(WEBKIT2_COMPILATION)
>+#error "Only <wpe/webkit.h> can be included directly."
>+#endif
>+
>+#ifndef WebKitURIUtilities_h
>+#define WebKitURIUtilities_h
>+
>+#include <glib.h>
>+#include <wpe/WebKitDefines.h>
>+
>+G_BEGIN_DECLS
>+
>+WEBKIT_API gchar *
>+webkit_uri_for_display (const gchar *uri);
>+
>+G_END_DECLS
>+
>+#endif
>diff --git a/Source/WebKit/UIProcess/API/wpe/docs/wpe-0.1-sections.txt b/Source/WebKit/UIProcess/API/wpe/docs/wpe-0.1-sections.txt
>index 14d13856320..cc402ab1015 100644
>--- a/Source/WebKit/UIProcess/API/wpe/docs/wpe-0.1-sections.txt
>+++ b/Source/WebKit/UIProcess/API/wpe/docs/wpe-0.1-sections.txt
>@@ -1305,3 +1305,8 @@ webkit_application_info_get_type
> <SUBSECTION Standard>
> WEBKIT_TYPE_APPLICATION_INFO
> </SECTION>
>+
>+<SECTION>
>+<FILE>WebKitURIUtilities</FILE>
>+webkit_uri_for_display
>+</SECTION>
>diff --git a/Source/WebKit/UIProcess/API/wpe/docs/wpe-docs.sgml b/Source/WebKit/UIProcess/API/wpe/docs/wpe-docs.sgml
>index d152566f61a..c8f9e3b36ea 100644
>--- a/Source/WebKit/UIProcess/API/wpe/docs/wpe-docs.sgml
>+++ b/Source/WebKit/UIProcess/API/wpe/docs/wpe-docs.sgml
>@@ -56,6 +56,11 @@
>     <xi:include href="xml/WebKitApplicationInfo.xml"/>
>   </chapter>
> 
>+  <chapter>
>+    <title>Utilities</title>
>+    <xi:include href="xml/WebKitURIUtilities.xml"/>
>+  </chapter>
>+
>   <index id="index-all">
>     <title>Index</title>
>   </index>
>diff --git a/Source/WebKit/UIProcess/API/wpe/webkit.h b/Source/WebKit/UIProcess/API/wpe/webkit.h
>index 0f27191f669..9955a40f8fe 100644
>--- a/Source/WebKit/UIProcess/API/wpe/webkit.h
>+++ b/Source/WebKit/UIProcess/API/wpe/webkit.h
>@@ -67,6 +67,7 @@
> #include <wpe/WebKitURIRequest.h>
> #include <wpe/WebKitURIResponse.h>
> #include <wpe/WebKitURISchemeRequest.h>
>+#include <wpe/WebKitURIUtilities.h>
> #include <wpe/WebKitUserContent.h>
> #include <wpe/WebKitUserContentManager.h>
> #include <wpe/WebKitUserMediaPermissionRequest.h>
>diff --git a/Tools/ChangeLog b/Tools/ChangeLog
>index 6ef294951e3..f33c9e18f3a 100644
>--- a/Tools/ChangeLog
>+++ b/Tools/ChangeLog
>@@ -1,3 +1,23 @@
>+2018-12-14  Ms2ger  <Ms2ger@igalia.com>
>+
>+        [GTK][WPE] Need a function to convert internal URI to display ("pretty") URI
>+        https://bugs.webkit.org/show_bug.cgi?id=174816
>+
>+        Reviewed by NOBODY (OOPS!).
>+
>+        Add tests for userVisibleString() and (for GTK and WPE) webkit_uri_for_display().
>+
>+        * TestWebKitAPI/CMakeLists.txt:
>+        * TestWebKitAPI/TestWebKitAPI.xcodeproj/project.pbxproj:
>+        * TestWebKitAPI/Tests/WTF/URLHelpers.cpp: Added.
>+        (TestWebKitAPI::TEST):
>+        * TestWebKitAPI/Tests/WebKitGLib/TestWebKitURIUtilities.cpp: Added.
>+        (testURIForDisplayUnaffected):
>+        (testURIForDisplayAffected):
>+        (beforeAll):
>+        (afterAll):
>+        * TestWebKitAPI/glib/CMakeLists.txt:
>+
> 2018-12-13  Carlos Eduardo Ramalho  <cadubentzen@gmail.com>
> 
>         [GStreamer][JHBuild] update-webkit{gtk,wpe}-libs fails with libfdk-2.0.0
>diff --git a/Tools/TestWebKitAPI/CMakeLists.txt b/Tools/TestWebKitAPI/CMakeLists.txt
>index b24900898b3..1af1d48553b 100644
>--- a/Tools/TestWebKitAPI/CMakeLists.txt
>+++ b/Tools/TestWebKitAPI/CMakeLists.txt
>@@ -177,6 +177,7 @@ set(TestWTF_SOURCES
>     ${TESTWEBKITAPI_DIR}/Tests/WTF/Threading.cpp
>     ${TESTWEBKITAPI_DIR}/Tests/WTF/Time.cpp
>     ${TESTWEBKITAPI_DIR}/Tests/WTF/URL.cpp
>+    ${TESTWEBKITAPI_DIR}/Tests/WTF/URLHelpers.cpp
>     ${TESTWEBKITAPI_DIR}/Tests/WTF/URLParser.cpp
>     ${TESTWEBKITAPI_DIR}/Tests/WTF/UniqueArray.cpp
>     ${TESTWEBKITAPI_DIR}/Tests/WTF/UniqueRef.cpp
>diff --git a/Tools/TestWebKitAPI/TestWebKitAPI.xcodeproj/project.pbxproj b/Tools/TestWebKitAPI/TestWebKitAPI.xcodeproj/project.pbxproj
>index a89e05b7d8f..b832bfcf8dd 100644
>--- a/Tools/TestWebKitAPI/TestWebKitAPI.xcodeproj/project.pbxproj
>+++ b/Tools/TestWebKitAPI/TestWebKitAPI.xcodeproj/project.pbxproj
>@@ -314,6 +314,7 @@
> 		5CE354D91E70DA5C00BEFE3B /* WKContentExtensionStore.mm in Sources */ = {isa = PBXBuildFile; fileRef = 5CE354D81E70D9C300BEFE3B /* WKContentExtensionStore.mm */; };
> 		5CEAB5E11FA939F400A77FAA /* _WKInputDelegate.mm in Sources */ = {isa = PBXBuildFile; fileRef = 5CEAB5DF1FA937CB00A77FAA /* _WKInputDelegate.mm */; };
> 		5E4B1D2E1D404C6100053621 /* WKScrollViewDelegate.mm in Sources */ = {isa = PBXBuildFile; fileRef = 5E4B1D2C1D404C6100053621 /* WKScrollViewDelegate.mm */; };
>+		5FAD3AE421B97EEE00BEE178 /* URLHelpers.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 5FAD3AE321B97C5000BEE178 /* URLHelpers.cpp */; };
> 		631EFFF61E7B5E8D00D2EBB8 /* Geolocation.mm in Sources */ = {isa = PBXBuildFile; fileRef = 631EFFF51E7B5E8D00D2EBB8 /* Geolocation.mm */; };
> 		634910E01E9D3FF300880309 /* CoreLocation.framework in Frameworks */ = {isa = PBXBuildFile; fileRef = 634910DF1E9D3FF300880309 /* CoreLocation.framework */; };
> 		6354F4D11F7C3AB500D89DF3 /* ApplicationManifestParser.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 6354F4D01F7C3AB500D89DF3 /* ApplicationManifestParser.cpp */; };
>@@ -1659,6 +1660,7 @@
> 		5CE354D81E70D9C300BEFE3B /* WKContentExtensionStore.mm */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.objcpp; path = WKContentExtensionStore.mm; sourceTree = "<group>"; };
> 		5CEAB5DF1FA937CB00A77FAA /* _WKInputDelegate.mm */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.objcpp; path = _WKInputDelegate.mm; sourceTree = "<group>"; };
> 		5E4B1D2C1D404C6100053621 /* WKScrollViewDelegate.mm */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.objcpp; name = WKScrollViewDelegate.mm; path = ../ios/WKScrollViewDelegate.mm; sourceTree = "<group>"; };
>+		5FAD3AE321B97C5000BEE178 /* URLHelpers.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = URLHelpers.cpp; path = Tests/WTF/URLHelpers.cpp; sourceTree = "<group>"; };
> 		631EFFF51E7B5E8D00D2EBB8 /* Geolocation.mm */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.objcpp; path = Geolocation.mm; sourceTree = "<group>"; };
> 		634910DF1E9D3FF300880309 /* CoreLocation.framework */ = {isa = PBXFileReference; lastKnownFileType = wrapper.framework; name = CoreLocation.framework; path = System/Library/Frameworks/CoreLocation.framework; sourceTree = SDKROOT; };
> 		6354F4D01F7C3AB500D89DF3 /* ApplicationManifestParser.cpp */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.cpp; path = ApplicationManifestParser.cpp; sourceTree = "<group>"; };
>@@ -2283,6 +2285,7 @@
> 		08FB7794FE84155DC02AAC07 /* TestWebKitAPI */ = {
> 			isa = PBXGroup;
> 			children = (
>+				5FAD3AE321B97C5000BEE178 /* URLHelpers.cpp */,
> 				08FB7795FE84155DC02AAC07 /* Source */,
> 				BCB9EB66112366D800A137E0 /* Tests */,
> 				BC90957D12554CEA00083756 /* Configurations */,
>@@ -3810,6 +3813,7 @@
> 			buildActionMask = 2147483647;
> 			files = (
> 				7C83DFA21D0A5AE400FEBCF3 /* mainIOS.mm in Sources */,
>+				5FAD3AE421B97EEE00BEE178 /* URLHelpers.cpp in Sources */,
> 				7C83DFAD1D0A5AE400FEBCF3 /* mainMac.mm in Sources */,
> 			);
> 			runOnlyForDeploymentPostprocessing = 0;
>diff --git a/Tools/TestWebKitAPI/Tests/WTF/URLHelpers.cpp b/Tools/TestWebKitAPI/Tests/WTF/URLHelpers.cpp
>new file mode 100644
>index 00000000000..bf4dd2c8fad
>--- /dev/null
>+++ b/Tools/TestWebKitAPI/Tests/WTF/URLHelpers.cpp
>@@ -0,0 +1,116 @@
>+/*
>+ * Copyright (C) 2011, 2012 Apple Inc. All rights reserved.
>+ * Copyright (C) 2018 Igalia S.L.
>+ *
>+ * Redistribution and use in source and binary forms, with or without
>+ * modification, are permitted provided that the following conditions
>+ * are met:
>+ * 1. Redistributions of source code must retain the above copyright
>+ *    notice, this list of conditions and the following disclaimer.
>+ * 2. Redistributions in binary form must reproduce the above copyright
>+ *    notice, this list of conditions and the following disclaimer in the
>+ *    documentation and/or other materials provided with the distribution.
>+ *
>+ * THIS SOFTWARE IS PROVIDED BY APPLE INC. AND ITS CONTRIBUTORS ``AS IS''
>+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
>+ * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
>+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR ITS CONTRIBUTORS
>+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
>+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
>+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
>+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
>+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
>+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
>+ * THE POSSIBILITY OF SUCH DAMAGE.
>+ */
>+
>+#include "config.h"
>+#include <wtf/URLHelpers.h>
>+#include <wtf/text/CString.h>
>+#include <wtf/text/WTFString.h>
>+
>+namespace TestWebKitAPI {
>+
>+using namespace WTF;
>+using namespace WTF::URLHelpers;
>+
>+TEST(WTF, UserVisibleURLUnaffected)
>+{
>+    const char* const items[] = {
>+        "http://site.com",
>+        "http://%77ebsite.com",
>+        "http://xn--cfa45g/", // U+0131, U+0307
>+        "http://xn--tma03b/", // U+0237, U+0307
>+        "http://xn--tma03bxga/", // U+0237, U+034F, U+034F, U+0307
>+        "http://xn--tma03bl01e/", // U+0237, U+200B, U+0307
>+        "http://xn--a-egb/", // a, U+034F
>+        "http://xn--a-qgn/", // a, U+200B
>+        "http://xn--a-mgn/", // a, U+2009
>+        "http://xn--u7f/", // U+1D04
>+        "http://xn--57f/", // U+1D0F
>+        "http://xn--i38a/", // U+A731
>+        "http://xn--j8f/", // U+1D1C
>+        "http://xn--n8f/", // U+1D20
>+        "http://xn--o8f/", // U+1D21
>+        "http://xn--p8f/", // U+1D22
>+        "http://xn--0na/", // U+0261
>+        "http://xn--cn-ded/", // U+054D
>+        "http://xn--ews-nfe.org/", // U+054D
>+        "http://xn--yotube-qkh/", // U+0578
>+        "http://xn--cla-7fe.edu/", // U+0578
>+        "http://xn--rsa94l/", // U+05D5 U+0307
>+        "http://xn--hdb9c/", // U+05D5 U+05B9
>+        "http://xn--idb7c/", // U+05D5 U+05BA
>+        "http://xn--pdb3b/", // U+05D5 U+05C1
>+        "http://xn--qdb1b/", // U+05D5 U+05C2
>+        "http://xn--sdb7a/", // U+05D5 U+05C4
>+        "http://xn--2-zic/", // U+0032 U+05E1
>+
>+        // Valid mixtures of Armenian and other scripts
>+        "https://en.wikipedia.org/wiki/.\u0570\u0561\u0575",
>+        "https://\u0573\u0574\u0578.\u0570\u0561\u0575",
>+        "https://\u0573-1-\u0574\u0578.\u0570\u0561\u0575",
>+        "https://2\u0573_\u0574\u0578.\u0570\u0561\u0575",
>+        "https://\u0573_\u0574\u05783.\u0570\u0561\u0575",
>+        "https://got\u0551\u0535\u0543.com",
>+        "https://\u0551\u0535\u0543fans.net",
>+        "https://\u0551\u0535or\u0575\u0543.biz",
>+        "https://\u0551\u0535and!$^&*()-~+={}or<>,.?\u0575\u0543.biz",
>+    };
>+
>+    for (auto& item : items) {
>+        CString input(item);
>+        String result = userVisibleURL(input);
>+        EXPECT_EQ(result.utf8(), item);
>+    }
>+}
>+
>+TEST(WTF, UserVisibleURLAffected)
>+{
>+    struct {
>+        const char* input;
>+        const char* output;
>+    } const items[] = {
>+        // Division sign: an allowed non-ASCII character, since it's not a
>+        // lookalike character.
>+        { "http://site.com\xC3\xB7othersite.org", "http://site.com\xC3\xB7othersite.org" },
>+        { "http://site.com%C3%B7othersite.org", "http://site.com\xC3\xB7othersite.org" },
>+
>+        // Full width solidus: disallowed because it looks like the solidus,
>+        // which is the character that indicates the end of the host name.
>+        { "http://site.com\xEF\xBC\x8Fothersite.org", "http://site.com%EF%BC%8Fothersite.org" },
>+        { "http://site.com%EF%BC%8Fothersite.org", "http://site.com%EF%BC%8Fothersite.org" },
>+
>+        // Ideographic space: disallowed because it looks like the ASCII space.
>+        { "http://site.com\xE3\x80\x80othersite.org", "http://site.com%E3%80%80othersite.org" },
>+        { "http://site.com%E3%80%80othersite.org", "http://site.com%E3%80%80othersite.org" },
>+    };
>+
>+    for (auto& item : items) {
>+        CString input(item.input);
>+        String result = userVisibleURL(input);
>+        EXPECT_EQ(result.utf8(), item.output);
>+    }
>+}
>+
>+} // namespace TestWebKitAPI
>diff --git a/Tools/TestWebKitAPI/Tests/WebKitGLib/TestWebKitURIUtilities.cpp b/Tools/TestWebKitAPI/Tests/WebKitGLib/TestWebKitURIUtilities.cpp
>new file mode 100644
>index 00000000000..0250eda146d
>--- /dev/null
>+++ b/Tools/TestWebKitAPI/Tests/WebKitGLib/TestWebKitURIUtilities.cpp
>@@ -0,0 +1,51 @@
>+/*
>+ * Copyright (C) 2011, 2012 Apple Inc. All rights reserved.
>+ * Copyright (C) 2018 Igalia S.L.
>+ *
>+ * Redistribution and use in source and binary forms, with or without
>+ * modification, are permitted provided that the following conditions
>+ * are met:
>+ * 1. Redistributions of source code must retain the above copyright
>+ *    notice, this list of conditions and the following disclaimer.
>+ * 2. Redistributions in binary form must reproduce the above copyright
>+ *    notice, this list of conditions and the following disclaimer in the
>+ *    documentation and/or other materials provided with the distribution.
>+ *
>+ * THIS SOFTWARE IS PROVIDED BY APPLE INC. AND ITS CONTRIBUTORS ``AS IS''
>+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
>+ * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
>+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR ITS CONTRIBUTORS
>+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
>+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
>+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
>+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
>+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
>+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
>+ * THE POSSIBILITY OF SUCH DAMAGE.
>+ */
>+
>+#include "config.h"
>+
>+#include "TestMain.h"
>+
>+static void testURIForDisplayUnaffected(Test*, gconstpointer)
>+{
>+    GUniquePtr<char> displayURI(webkit_uri_for_display("http://site.com\xC3\xB7othersite.org"));
>+    g_assert_cmpstr(displayURI.get(), ==, "http://site.com\xC3\xB7othersite.org");
>+}
>+
>+static void testURIForDisplayAffected(Test*, gconstpointer)
>+{
>+    GUniquePtr<char> displayURI(webkit_uri_for_display("http://site.com%C3%B7othersite.org"));
>+    g_assert_cmpstr(displayURI.get(), ==, "http://site.com\xC3\xB7othersite.org");
>+}
>+
>+void beforeAll()
>+{
>+    Test::add("WebKitURIUtilities", "uri-for-display-unaffected", testURIForDisplayUnaffected);
>+    Test::add("WebKitURIUtilities", "uri-for-display-affected", testURIForDisplayAffected);
>+}
>+
>+void afterAll()
>+{
>+}
>diff --git a/Tools/TestWebKitAPI/glib/CMakeLists.txt b/Tools/TestWebKitAPI/glib/CMakeLists.txt
>index f4c1e69663b..5fee6a525e5 100644
>--- a/Tools/TestWebKitAPI/glib/CMakeLists.txt
>+++ b/Tools/TestWebKitAPI/glib/CMakeLists.txt
>@@ -134,6 +134,7 @@ ADD_WK2_TEST(TestWebExtensions ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestW
> ADD_WK2_TEST(TestWebKitPolicyClient ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestWebKitPolicyClient.cpp)
> ADD_WK2_TEST(TestWebKitSecurityOrigin ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestWebKitSecurityOrigin.cpp)
> ADD_WK2_TEST(TestWebKitSettings ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestWebKitSettings.cpp)
>+ADD_WK2_TEST(TestWebKitURIUtilities ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestWebKitURIUtilities.cpp)
> ADD_WK2_TEST(TestWebKitWebContext ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestWebKitWebContext.cpp)
> ADD_WK2_TEST(TestWebKitWebView ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestWebKitWebView.cpp)
> ADD_WK2_TEST(TestWebKitUserContentManager ${TOOLS_DIR}/TestWebKitAPI/Tests/WebKitGLib/TestWebKitUserContentManager.cpp)

Actions: View | Formatted Diff | Diff

Attachments on bug 174816: 330658 | 330687 | 331338 | 331339 | 331342 | 331343 | 331345 | 331840 | 331841 | 331842 | 331843 | 332474 | 332477 | 332478 | 332480 | 342542 | 343057 | 343059 | 343066 | 343806 | 344291 | 344294 | 344298 | 356804 | 356808 | 357043 | 357316 | 357550 | 357551 | 360348 | 360451 | 360462 | 360561 | 360567