Diff
Modified: trunk/LayoutTests/ChangeLog (208901 => 208902)
--- trunk/LayoutTests/ChangeLog 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/LayoutTests/ChangeLog 2016-11-18 22:47:24 UTC (rev 208902)
@@ -1,3 +1,16 @@
+2016-11-17 Alex Christensen <achristen...@webkit.org>
+
+ Support IDN2008 with UTS #46 instead of IDN2003
+ https://bugs.webkit.org/show_bug.cgi?id=144194
+
+ Reviewed by Darin Adler.
+
+ * fast/encoding/idn-security.html:
+ Move some characters with changed IDN encodings to inside the check for old ICU.
+ * fast/url/idna2003-expected.txt:
+ * fast/url/idna2008-expected.txt:
+ Update expected results. We are now more compliant with IDN2008.
+
2016-11-18 Ryan Haddad <ryanhad...@apple.com>
Marking two js/dom/domjit-function-get-element-by-id-* tests as flaky.
Modified: trunk/LayoutTests/fast/encoding/idn-security-expected.txt (208901 => 208902)
--- trunk/LayoutTests/fast/encoding/idn-security-expected.txt 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/LayoutTests/fast/encoding/idn-security-expected.txt 2016-11-18 22:47:24 UTC (rev 208902)
@@ -34,10 +34,6 @@
PASS testIDNRoundTripNotFirstCharacter(0xe01) is '%u0E01'
PASS testIDNRoundTrip(0xa000) is '%uA000'
PASS testIDNRoundTripNotFirstCharacter(0xa000) is '%uA000'
-PASS testIDNRoundTrip(0x2024) is '.'
-PASS testIDNRoundTripNotFirstCharacter(0x2024) is '.'
-PASS testIDNRoundTrip(0xfe52) is '.'
-PASS testIDNRoundTripNotFirstCharacter(0xfe52) is '.'
PASS testIDNRoundTrip(0xff0f) is '/'
PASS testIDNRoundTripNotFirstCharacter(0xff0f) is '/'
PASS testIDNRoundTrip(0xfe68) is '%5C'
@@ -86,26 +82,6 @@
PASS testIDNRoundTripNotFirstCharacter(0x251) is 'punycode'
PASS testIDNRoundTrip(0x261) is 'punycode'
PASS testIDNRoundTripNotFirstCharacter(0x261) is 'punycode'
-PASS testIDNRoundTrip(0x337) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x337) is 'punycode'
-PASS testIDNRoundTrip(0x337) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x337) is 'punycode'
-PASS testIDNRoundTrip(0x338) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x338) is 'punycode'
-PASS testIDNRoundTrip(0x338) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x338) is 'punycode'
-PASS testIDNRoundTrip(0x5b4) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x5b4) is 'punycode'
-PASS testIDNRoundTrip(0x5bc) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x5bc) is 'punycode'
-PASS testIDNRoundTrip(0x660) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x660) is 'punycode'
-PASS testIDNRoundTrip(0x6f0) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x6f0) is 'punycode'
-PASS testIDNRoundTrip(0x115f) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x115f) is 'punycode'
-PASS testIDNRoundTrip(0x1160) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x1160) is 'punycode'
PASS testIDNRoundTrip(0x2027) is 'punycode'
PASS testIDNRoundTripNotFirstCharacter(0x2027) is 'punycode'
PASS testIDNRoundTrip(0x2039) is 'punycode'
@@ -162,12 +138,6 @@
PASS testIDNRoundTripNotFirstCharacter(0x3033) is 'punycode'
PASS testIDNRoundTrip(0x3035) is 'punycode'
PASS testIDNRoundTripNotFirstCharacter(0x3035) is 'punycode'
-PASS testIDNRoundTrip(0x3164) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x3164) is 'punycode'
-PASS testIDNRoundTrip(0x321d) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x321d) is 'punycode'
-PASS testIDNRoundTrip(0x321e) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0x321e) is 'punycode'
PASS testIDNRoundTrip(0x33ae) is 'punycode'
PASS testIDNRoundTripNotFirstCharacter(0x33ae) is 'punycode'
PASS testIDNRoundTrip(0x33af) is 'punycode'
@@ -176,10 +146,6 @@
PASS testIDNRoundTripNotFirstCharacter(0x33c6) is 'punycode'
PASS testIDNRoundTrip(0x33df) is 'punycode'
PASS testIDNRoundTripNotFirstCharacter(0x33df) is 'punycode'
-PASS testIDNRoundTrip(0xfe14) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0xfe14) is 'punycode'
-PASS testIDNRoundTrip(0xfe15) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0xfe15) is 'punycode'
PASS testIDNRoundTrip(0xfe3f) is 'punycode'
PASS testIDNRoundTripNotFirstCharacter(0xfe3f) is 'punycode'
PASS testIDNRoundTrip(0xfe5d) is 'punycode'
@@ -186,8 +152,6 @@
PASS testIDNRoundTripNotFirstCharacter(0xfe5d) is 'punycode'
PASS testIDNRoundTrip(0xfe5e) is 'punycode'
PASS testIDNRoundTripNotFirstCharacter(0xfe5e) is 'punycode'
-PASS testIDNRoundTrip(0xffa0) is 'punycode'
-PASS testIDNRoundTripNotFirstCharacter(0xffa0) is 'punycode'
PASS testIDNEncode(0x2028) is '%u2028'
PASS testIDNEncodeNotFirstCharacter(0x2028) is '%u2028'
PASS testIDNEncode(0x2029) is '%u2029'
@@ -244,4 +208,40 @@
PASS testIDNRoundTripNotFirstCharacter(0xff61) is '.'
PASS testIDNEncode(0xfeff) is '%uFEFF'
PASS testIDNRoundTripNotFirstCharacter(0xfeff) is ''
+PASS testIDNRoundTrip(0x2024) is '%u2024'
+PASS testIDNRoundTripNotFirstCharacter(0x2024) is '%u2024'
+PASS testIDNRoundTrip(0xfe52) is '%uFE52'
+PASS testIDNRoundTripNotFirstCharacter(0xfe52) is '%uFE52'
+PASS testIDNRoundTrip(0x337) is '%u0337'
+PASS testIDNRoundTripNotFirstCharacter(0x337) is 'punycode'
+PASS testIDNRoundTrip(0x337) is '%u0337'
+PASS testIDNRoundTripNotFirstCharacter(0x337) is 'punycode'
+PASS testIDNRoundTrip(0x338) is '%u0338'
+PASS testIDNRoundTripNotFirstCharacter(0x338) is 'punycode'
+PASS testIDNRoundTrip(0x338) is '%u0338'
+PASS testIDNRoundTripNotFirstCharacter(0x338) is 'punycode'
+PASS testIDNRoundTrip(0x5b4) is '%u05B4'
+PASS testIDNRoundTripNotFirstCharacter(0x5b4) is 'punycode'
+PASS testIDNRoundTrip(0x5bc) is '%u05BC'
+PASS testIDNRoundTripNotFirstCharacter(0x5bc) is 'punycode'
+PASS testIDNRoundTrip(0x660) is '%u0660'
+PASS testIDNRoundTripNotFirstCharacter(0x660) is '%u0660'
+PASS testIDNRoundTrip(0x6f0) is 'punycode'
+PASS testIDNRoundTripNotFirstCharacter(0x6f0) is 'punycode'
+PASS testIDNRoundTrip(0x115f) is '%u115F'
+PASS testIDNRoundTripNotFirstCharacter(0x115f) is '%u115F'
+PASS testIDNRoundTrip(0x1160) is '%u1160'
+PASS testIDNRoundTripNotFirstCharacter(0x1160) is '%u1160'
+PASS testIDNRoundTrip(0x3164) is '%u3164'
+PASS testIDNRoundTripNotFirstCharacter(0x3164) is '%u3164'
+PASS testIDNRoundTrip(0x321d) is '%28%uC624%uC804%29'
+PASS testIDNRoundTripNotFirstCharacter(0x321d) is '%28%uC624%uC804%29'
+PASS testIDNRoundTrip(0x321e) is '%28%uC624%uD6C4%29'
+PASS testIDNRoundTripNotFirstCharacter(0x321e) is '%28%uC624%uD6C4%29'
+PASS testIDNRoundTrip(0xfe14) is '%3B'
+PASS testIDNRoundTripNotFirstCharacter(0xfe14) is '%3B'
+PASS testIDNRoundTrip(0xfe15) is '%21'
+PASS testIDNRoundTripNotFirstCharacter(0xfe15) is '%21'
+PASS testIDNRoundTrip(0xffa0) is '%uFFA0'
+PASS testIDNRoundTripNotFirstCharacter(0xffa0) is '%uFFA0'
Modified: trunk/LayoutTests/fast/encoding/idn-security.html (208901 => 208902)
--- trunk/LayoutTests/fast/encoding/idn-security.html 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/LayoutTests/fast/encoding/idn-security.html 2016-11-18 22:47:24 UTC (rev 208902)
@@ -134,8 +134,6 @@
testIDNCharacter(0xA000, "allowed");
/* ICU converts these to other allowed characters, so the original character can't be used to get to a phishy domain name */
-testIDNCharacter(0x2024, ".");
-testIDNCharacter(0xFE52, ".");
testIDNCharacter(0xFF0F, "/");
/* ICU converts these characters to backslash, so the original character can't be used to get to a phishy domain name */
@@ -168,16 +166,6 @@
testIDNCharacter(0x01C3, "disallowed");
testIDNCharacter(0x0251, "disallowed");
testIDNCharacter(0x0261, "disallowed");
-testIDNCharacter(0x0337, "disallowed");
-testIDNCharacter(0x0337, "disallowed");
-testIDNCharacter(0x0338, "disallowed");
-testIDNCharacter(0x0338, "disallowed");
-testIDNCharacter(0x05B4, "disallowed");
-testIDNCharacter(0x05BC, "disallowed");
-testIDNCharacter(0x0660, "disallowed");
-testIDNCharacter(0x06F0, "disallowed");
-testIDNCharacter(0x115F, "disallowed");
-testIDNCharacter(0x1160, "disallowed");
testIDNCharacter(0x2027, "disallowed");
testIDNCharacter(0x2039, "disallowed");
testIDNCharacter(0x203A, "disallowed");
@@ -206,19 +194,13 @@
testIDNCharacter(0x3015, "disallowed");
testIDNCharacter(0x3033, "disallowed");
testIDNCharacter(0x3035, "disallowed");
-testIDNCharacter(0x3164, "disallowed");
-testIDNCharacter(0x321D, "disallowed");
-testIDNCharacter(0x321E, "disallowed");
testIDNCharacter(0x33AE, "disallowed");
testIDNCharacter(0x33AF, "disallowed");
testIDNCharacter(0x33C6, "disallowed");
testIDNCharacter(0x33DF, "disallowed");
-testIDNCharacter(0xFE14, "disallowed");
-testIDNCharacter(0xFE15, "disallowed");
testIDNCharacter(0xFE3F, "disallowed");
testIDNCharacter(0xFE5D, "disallowed");
testIDNCharacter(0xFE5E, "disallowed");
-testIDNCharacter(0xFFA0, "disallowed");
/* ICU won't encode these characters in IDN, thus we should always get 'host not found'. */
testIDNCharacter(0x2028, "does not encode");
@@ -258,6 +240,24 @@
testIDNCharacter(0xFF0E, ".");
testIDNCharacter(0xFF61, ".");
testIDNCharacter(0xFEFF, "");
+ testIDNCharacter(0x2024, ".");
+ testIDNCharacter(0xFE52, ".");
+ testIDNCharacter(0x0337, "disallowed");
+ testIDNCharacter(0x0337, "disallowed");
+ testIDNCharacter(0x0338, "disallowed");
+ testIDNCharacter(0x0338, "disallowed");
+ testIDNCharacter(0x05B4, "disallowed");
+ testIDNCharacter(0x05BC, "disallowed");
+ testIDNCharacter(0x0660, "disallowed");
+ testIDNCharacter(0x06F0, "disallowed");
+ testIDNCharacter(0x115F, "disallowed");
+ testIDNCharacter(0x1160, "disallowed");
+ testIDNCharacter(0x3164, "disallowed");
+ testIDNCharacter(0x321D, "disallowed");
+ testIDNCharacter(0x321E, "disallowed");
+ testIDNCharacter(0xFE14, "disallowed");
+ testIDNCharacter(0xFE15, "disallowed");
+ testIDNCharacter(0xFFA0, "disallowed");
} else {
testIDNCharacter(0x200B, "does not encode", "");
testIDNCharacter(0x3002, "does not encode", ".");
@@ -264,6 +264,24 @@
testIDNCharacter(0xFF0E, "does not encode", ".");
testIDNCharacter(0xFF61, "does not encode", ".");
testIDNCharacter(0xFEFF, "does not encode", "");
+ testIDNCharacter(0x2024, "%u2024");
+ testIDNCharacter(0xFE52, "%uFE52");
+ testIDNCharacter(0x0337, "%u0337", "punycode");
+ testIDNCharacter(0x0337, "%u0337", "punycode");
+ testIDNCharacter(0x0338, "%u0338", "punycode");
+ testIDNCharacter(0x0338, "%u0338", "punycode");
+ testIDNCharacter(0x05B4, "%u05B4", "punycode");
+ testIDNCharacter(0x05BC, "%u05BC", "punycode");
+ testIDNCharacter(0x0660, "%u0660");
+ testIDNCharacter(0x06F0, "disallowed");
+ testIDNCharacter(0x115F, "%u115F");
+ testIDNCharacter(0x1160, "%u1160");
+ testIDNCharacter(0x3164, "%u3164");
+ testIDNCharacter(0x321D, "%28%uC624%uC804%29");
+ testIDNCharacter(0x321E, "%28%uC624%uD6C4%29");
+ testIDNCharacter(0xFE14, "%3B");
+ testIDNCharacter(0xFE15, "%21");
+ testIDNCharacter(0xFFA0, "%uFFA0");
}
</script>
Modified: trunk/LayoutTests/fast/url/idna2003-expected.txt (208901 => 208902)
--- trunk/LayoutTests/fast/url/idna2003-expected.txt 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/LayoutTests/fast/url/idna2003-expected.txt 2016-11-18 22:47:24 UTC (rev 208902)
@@ -4,15 +4,15 @@
The PASS/FAIL results of this test are set to the behavior in IDNA2003.
-PASS canonicalize('http://faß.de/') is 'http://fass.de/'
-PASS canonicalize('http://βόλος.com/') is 'http://xn--nxasmq6b.com/'
-PASS canonicalize('http://ශ්රී.com/') is 'http://xn--10cl1a0b.com/'
-PASS canonicalize('http://نامهای.com/') is 'http://xn--mgba3gch31f.com/'
+FAIL canonicalize('http://faß.de/') should be http://fass.de/. Was http://xn--fa-hia.de/.
+FAIL canonicalize('http://βόλος.com/') should be http://xn--nxasmq6b.com/. Was http://xn--nxasmm1c.com/.
+FAIL canonicalize('http://ශ්රී.com/') should be http://xn--10cl1a0b.com/. Was http://xn--10cl1a0b660p.com/.
+FAIL canonicalize('http://نامهای.com/') should be http://xn--mgba3gch31f.com/. Was http://xn--mgba3gch31f060k.com/.
PASS canonicalize('http://www.looĸout.net/') is 'http://www.xn--looout-5bb.net/'
PASS canonicalize('http://ᗯᗯᗯ.lookout.net/') is 'http://xn--1qeaa.lookout.net/'
PASS canonicalize('http://www.lookout.сом/') is 'http://www.lookout.xn--l1adi/'
FAIL canonicalize('http://www.lookout.net：80/') should be http://www.lookout.net:80/. Was http://www.lookout.net：80/.
-PASS canonicalize('http://www‥lookout.net/') is 'http://www..lookout.net/'
+FAIL canonicalize('http://www‥lookout.net/') should be http://www..lookout.net/. Was http://www‥lookout.net/.
PASS canonicalize('http://www.lookout‧net/') is 'http://www.xn--lookoutnet-406e/'
PASS canonicalize('http://www.looĸout.net/') is 'http://www.xn--looout-5bb.net/'
FAIL canonicalize('http://www.lookout.net⩴80/') should be http://www.lookout.net::%3D80/. Was http://www.lookout.net⩴80/.
Modified: trunk/LayoutTests/fast/url/idna2008-expected.txt (208901 => 208902)
--- trunk/LayoutTests/fast/url/idna2008-expected.txt 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/LayoutTests/fast/url/idna2008-expected.txt 2016-11-18 22:47:24 UTC (rev 208902)
@@ -5,20 +5,20 @@
The PASS/FAIL results of this test are set to the behavior in IDNA2008.
PASS canonicalize('http://Bücher.de/') is 'http://xn--bcher-kva.de/'
-FAIL canonicalize('http://faß.de/') should be http://xn--fa-hia.de/. Was http://fass.de/.
-FAIL canonicalize('http://βόλος.com/') should be http://xn--nxasmm1c.com/. Was http://xn--nxasmq6b.com/.
-FAIL canonicalize('http://ශ්රී.com/') should be http://xn--10cl1a0b660p.com/. Was http://xn--10cl1a0b.com/.
-FAIL canonicalize('http://نامهای.com/') should be http://xn--mgba3gch31f060k.com/. Was http://xn--mgba3gch31f.com/.
+PASS canonicalize('http://faß.de/') is 'http://xn--fa-hia.de/'
+PASS canonicalize('http://βόλος.com/') is 'http://xn--nxasmm1c.com/'
+PASS canonicalize('http://ශ්රී.com/') is 'http://xn--10cl1a0b660p.com/'
+PASS canonicalize('http://نامهای.com/') is 'http://xn--mgba3gch31f060k.com/'
FAIL canonicalize('http://♥.net/') should be http://�.net/. Was http://xn--g6h.net/.
-FAIL canonicalize('http://.net/') should be http://�.net/. Was http://xn--zva.net/.
-FAIL canonicalize('http://Ӏ.com/') should be http://�.com/. Was http://xn--d5a.com/.
-FAIL canonicalize('http://㛼.com/') should be http://�.com/. Was http://xn--j74i.com/.
-FAIL canonicalize('http://Ↄ.com/') should be http://�.com/. Was http://xn--q5g.com/.
+FAIL canonicalize('http://.net/') should be http://�.net/. Was http://.net/.
+FAIL canonicalize('http://Ӏ.com/') should be http://�.com/. Was http://Ӏ.com/.
+FAIL canonicalize('http://㛼.com/') should be http://�.com/. Was http://㛼.com/.
+FAIL canonicalize('http://Ↄ.com/') should be http://�.com/. Was http://Ↄ.com/.
PASS canonicalize('http://look͏out.net/') is 'http://lookout.net/'
PASS canonicalize('http://gOoGle.com/') is 'http://google.com/'
FAIL canonicalize('http://ড়.com/') should be http://ড়.com/. Was http://xn--15b8c.com/.
-FAIL canonicalize('http://ẞ.com/') should be http://ss.com/. Was http://xn--kkg.com/.
-FAIL canonicalize('http://ẞ.foo.com/') should be http://ss.foo.com/. Was http://xn--kkg.foo.com/.
+PASS canonicalize('http://ẞ.com/') is 'http://ss.com/'
+PASS canonicalize('http://ẞ.foo.com/') is 'http://ss.foo.com/'
FAIL canonicalize('http://-foo.bar.com/') should be http:///. Was http://-foo.bar.com/.
FAIL canonicalize('http://foo-.bar.com/') should be http:///. Was http://foo-.bar.com/.
FAIL canonicalize('http://ab--cd.com/') should be http:///. Was http://ab--cd.com/.
Modified: trunk/Source/WebCore/ChangeLog (208901 => 208902)
--- trunk/Source/WebCore/ChangeLog 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/Source/WebCore/ChangeLog 2016-11-18 22:47:24 UTC (rev 208902)
@@ -1,3 +1,37 @@
+2016-11-17 Alex Christensen <achristen...@webkit.org>
+
+ Support IDN2008 with UTS #46 instead of IDN2003
+ https://bugs.webkit.org/show_bug.cgi?id=144194
+
+ Reviewed by Darin Adler.
+
+ Use uidna_nameToASCII instead of the deprecated uidna_IDNToASCII.
+ It uses IDN2008 instead of IDN2003, and it uses UTF #46 when used with a UIDNA opened with uidna_openUTS46.
+ This follows https://url.spec.whatwg.org/#concept-domain-to-ascii except we do not use Transitional_Processing
+ to prevent homograph attacks on german domain names with "ß" and "ss" in them. These are now treated as separate domains.
+ Firefox also doesn't use Transitional_Processing. Chrome and the current specification use Transitional_processing,
+ but https://github.com/whatwg/url/issues/110 might change the spec.
+
+ In addition, http://unicode.org/reports/tr46/ says:
+ "implementations are encouraged to apply the Bidi and ContextJ validity criteria"
+ Bidi checks prevent domain names with bidirectional text, such as latin and hebrew characters in the same domain. Chrome and Firefox do this.
+
+ ContextJ checks prevent code points such as U+200D, which is a zero-width joiner which users would not see when looking at the domain name.
+ Firefox currently enables ContextJ checks and it is suggested by UTS #46, so we'll do it.
+
+ ContextO checks, which we do not use and neither does any other browser nor the spec, would fail if a domain contains code points such as U+30FB,
+ which looks somewhat like a dot. We can investigate enabling these checks later.
+
+ Covered by new API tests and rebased LayoutTests.
+ The new API tests verify that we do not use transitional processing, that we do apply the Bidi and ContextJ checks, but not ContextO checks.
+
+ * platform/URLParser.cpp:
+ (WebCore::URLParser::domainToASCII):
+ (WebCore::URLParser::internationalDomainNameTranscoder):
+ * platform/URLParser.h:
+ * platform/mac/WebCoreNSURLExtras.mm:
+ (WebCore::mapHostNameWithRange):
+
2016-11-18 Dean Jackson <d...@apple.com>
Better testing for accessibility media queries
Modified: trunk/Source/WebCore/platform/URLParser.cpp (208901 => 208902)
--- trunk/Source/WebCore/platform/URLParser.cpp 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/Source/WebCore/platform/URLParser.cpp 2016-11-18 22:47:24 UTC (rev 208902)
@@ -29,6 +29,7 @@
#include "Logging.h"
#include "RuntimeApplicationChecks.h"
#include <array>
+#include <mutex>
#include <unicode/uidna.h>
#include <unicode/utypes.h>
@@ -2479,19 +2480,11 @@
UChar hostnameBuffer[defaultInlineBufferSize];
UErrorCode error = U_ZERO_ERROR;
-
-#if COMPILER(GCC) || COMPILER(CLANG)
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-#endif
- // FIXME: This should use uidna_openUTS46 / uidna_close instead
- int32_t numCharactersConverted = uidna_IDNToASCII(StringView(domain).upconvertedCharacters(), domain.length(), hostnameBuffer, defaultInlineBufferSize, UIDNA_ALLOW_UNASSIGNED, nullptr, &error);
-#if COMPILER(GCC) || COMPILER(CLANG)
-#pragma GCC diagnostic pop
-#endif
+ UIDNAInfo processingDetails = UIDNA_INFO_INITIALIZER;
+ int32_t numCharactersConverted = uidna_nameToASCII(&internationalDomainNameTranscoder(), StringView(domain).upconvertedCharacters(), domain.length(), hostnameBuffer, defaultInlineBufferSize, &processingDetails, &error);
ASSERT(numCharactersConverted <= static_cast<int32_t>(defaultInlineBufferSize));
- if (error == U_ZERO_ERROR) {
+ if (U_SUCCESS(error) && !processingDetails.errors) {
for (int32_t i = 0; i < numCharactersConverted; ++i) {
ASSERT(isASCII(hostnameBuffer[i]));
ASSERT(!isASCIIUpper(hostnameBuffer[i]));
@@ -2760,6 +2753,19 @@
return String::adopt(WTFMove(output));
}
+const UIDNA& URLParser::internationalDomainNameTranscoder()
+{
+ static UIDNA* encoder;
+ static std::once_flag onceFlag;
+ std::call_once(onceFlag, [] {
+ UErrorCode error = U_ZERO_ERROR;
+ encoder = uidna_openUTS46(UIDNA_CHECK_BIDI | UIDNA_CHECK_CONTEXTJ | UIDNA_NONTRANSITIONAL_TO_UNICODE | UIDNA_NONTRANSITIONAL_TO_ASCII, &error);
+ RELEASE_ASSERT(U_SUCCESS(error));
+ RELEASE_ASSERT(encoder);
+ });
+ return *encoder;
+}
+
bool URLParser::allValuesEqual(const URL& a, const URL& b)
{
// FIXME: m_cannotBeABaseURL is not compared because the old URL::parse did not use it,
Modified: trunk/Source/WebCore/platform/URLParser.h (208901 => 208902)
--- trunk/Source/WebCore/platform/URLParser.h 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/Source/WebCore/platform/URLParser.h 2016-11-18 22:47:24 UTC (rev 208902)
@@ -29,6 +29,8 @@
#include "URL.h"
#include <wtf/Forward.h>
+struct UIDNA;
+
namespace WebCore {
template<typename CharacterType> class CodePointIterator;
@@ -48,6 +50,8 @@
static URLEncodedForm parseURLEncodedForm(StringView);
static String serialize(const URLEncodedForm&);
+ static const UIDNA& internationalDomainNameTranscoder();
+
private:
static Optional<uint16_t> defaultPortForProtocol(StringView);
friend Optional<uint16_t> defaultPortForProtocol(StringView);
Modified: trunk/Source/WebCore/platform/mac/WebCoreNSURLExtras.mm (208901 => 208902)
--- trunk/Source/WebCore/platform/mac/WebCoreNSURLExtras.mm 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/Source/WebCore/platform/mac/WebCoreNSURLExtras.mm 2016-11-18 22:47:24 UTC (rev 208902)
@@ -27,6 +27,7 @@
*/
#import "config.h"
+#import "URLParser.h"
#import "WebCoreObjCExtras.h"
#import "WebCoreNSStringExtras.h"
#import "WebCoreNSURLExtras.h"
@@ -478,8 +479,9 @@
[string getCharacters:sourceBuffer range:range];
UErrorCode uerror = U_ZERO_ERROR;
- int32_t numCharactersConverted = (encode ? uidna_IDNToASCII : uidna_IDNToUnicode)(sourceBuffer, length, destinationBuffer, HOST_NAME_BUFFER_LENGTH, UIDNA_ALLOW_UNASSIGNED, NULL, &uerror);
- if (U_FAILURE(uerror)) {
+ 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 (U_FAILURE(uerror) || processingDetails.errors) {
*error = YES;
return nil;
}
Modified: trunk/Tools/ChangeLog (208901 => 208902)
--- trunk/Tools/ChangeLog 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/Tools/ChangeLog 2016-11-18 22:47:24 UTC (rev 208902)
@@ -1,3 +1,19 @@
+2016-11-17 Alex Christensen <achristen...@webkit.org>
+
+ Support IDN2008 with UTS #46 instead of IDN2003
+ https://bugs.webkit.org/show_bug.cgi?id=144194
+
+ Reviewed by Darin Adler.
+
+ * TestWebKitAPI/Tests/WebCore/URLParser.cpp:
+ (TestWebKitAPI::TEST_F):
+ Add some tests from http://unicode.org/faq/idn.html verifying that we follow UTS46's deviations from IDN2008.
+ Add some tests based on https://tools.ietf.org/html/rfc5893 verifying that we check for bidirectional text.
+ Add a test based on https://tools.ietf.org/html/rfc5892 verifying that we do not do ContextO check.
+ Add a test for U+321D and U+321E which have particularly interesting punycode encodings. We match Firefox here now.
+ Also add a test from http://www.unicode.org/reports/tr46/#IDNAComparison verifying we are not using IDN2003.
+ We should consider importing all of http://www.unicode.org/Public/idna/9.0.0/IdnaTest.txt as URL domain tests.
+
2016-11-17 Carlos Garcia Campos <cgar...@igalia.com>
Downloads started by context menu actions should also have a web view associated
Modified: trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp (208901 => 208902)
--- trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp 2016-11-18 22:32:01 UTC (rev 208901)
+++ trunk/Tools/TestWebKitAPI/Tests/WebCore/URLParser.cpp 2016-11-18 22:47:24 UTC (rev 208902)
@@ -1093,6 +1093,32 @@
checkRelativeURLDifferences("a://b", "//[aBc]",
{"a", "", "", "b", 0, "", "", "", "a://b"},
{"", "", "", "", 0, "", "", "", "a://b"});
+ checkURL(utf16String(u"http://öbb.at"), {"http", "", "", "xn--bb-eka.at", 0, "/", "", "", "http://xn--bb-eka.at/"});
+ checkURL(utf16String(u"http://ÖBB.at"), {"http", "", "", "xn--bb-eka.at", 0, "/", "", "", "http://xn--bb-eka.at/"});
+ checkURL(utf16String(u"http://√.com"), {"http", "", "", "xn--19g.com", 0, "/", "", "", "http://xn--19g.com/"});
+ checkURLDifferences(utf16String(u"http://faß.de"),
+ {"http", "", "", "xn--fa-hia.de", 0, "/", "", "", "http://xn--fa-hia.de/"},
+ {"http", "", "", "fass.de", 0, "/", "", "", "http://fass.de/"});
+ checkURL(utf16String(u"http://ԛәлп.com"), {"http", "", "", "xn--k1ai47bhi.com", 0, "/", "", "", "http://xn--k1ai47bhi.com/"});
+ checkURLDifferences(utf16String(u"http://Ⱥbby.com"),
+ {"http", "", "", "xn--bby-iy0b.com", 0, "/", "", "", "http://xn--bby-iy0b.com/"},
+ {"http", "", "", "xn--bby-spb.com", 0, "/", "", "", "http://xn--bby-spb.com/"});
+ checkURLDifferences(utf16String(u"http://\u2132"),
+ {"", "", "", "", 0, "", "", "", utf16String(u"http://Ⅎ")},
+ {"http", "", "", "xn--f3g", 0, "/", "", "", "http://xn--f3g/"});
+ checkURLDifferences(utf16String(u"http://\u05D9\u05B4\u05D5\u05D0\u05B8/"),
+ {"http", "", "", "xn--cdbi5etas", 0, "/", "", "", "http://xn--cdbi5etas/"},
+ {"", "", "", "", 0, "", "", "", "about:blank"}, TestTabs::No);
+ checkURLDifferences(utf16String(u"http://bidirectional\u0786\u07AE\u0782\u07B0\u0795\u07A9\u0793\u07A6\u0783\u07AA/"),
+ {"", "", "", "", 0, "", "", "", utf16String(u"http://bidirectionalކޮންޕީޓަރު/")},
+ {"", "", "", "", 0, "", "", "", "about:blank"}, TestTabs::No);
+ checkURLDifferences(utf16String(u"http://contextj\u200D"),
+ {"", "", "", "", 0, "", "", "", utf16String(u"http://contextj\u200D")},
+ {"http", "", "", "contextj", 0, "/", "", "", "http://contextj/"});
+ checkURL(utf16String(u"http://contexto\u30FB"), {"http", "", "", "xn--contexto-wg5g", 0, "/", "", "", "http://xn--contexto-wg5g/"});
+ checkURLDifferences(utf16String(u"http://\u321D\u321E/"),
+ {"http", "", "", "xn--()()-bs0sc174agx4b", 0, "/", "", "", "http://xn--()()-bs0sc174agx4b/"},
+ {"http", "", "", "xn--5mkc", 0, "/", "", "", "http://xn--5mkc/"});
}
TEST_F(URLParserTest, DefaultPort)
