Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(525)

Unified Diff: url/url_canon_icu.cc

Issue 23642003: Support IDNA 2008 (Closed) Base URL: svn://chrome-svn/chrome/trunk/src/
Patch Set: Created 7 years, 3 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « url/url.gyp ('k') | url/url_canon_unittest.cc » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: url/url_canon_icu.cc
===================================================================
--- url/url_canon_icu.cc (revision 225023)
+++ url/url_canon_icu.cc (working copy)
@@ -7,6 +7,7 @@
#include <stdlib.h>
#include <string.h>
+#include "base/lazy_instance.h"
#include "base/logging.h"
#include "third_party/icu/source/common/unicode/ucnv.h"
#include "third_party/icu/source/common/unicode/ucnv_cb.h"
@@ -71,6 +72,40 @@
const void* old_context_;
};
+// A wrapper to use LazyInstance<>::Leaky with ICU's UIDNA, a C pointer to
+// a UTS46/IDNA 2008 handling object opened with uidna_openUTS46().
+//
+// We use UTS46 with BiDiCheck to migrate from IDNA 2003 (with unassigned
+// code points allowed) to IDNA 2008 with
+// the backward compatibility in mind. What it does:
+//
+// 1. Use the up-to-date Unicode data.
+// 2. Define a case folding/mapping with the up-to-date Unicode data as
+// in IDNA 2003.
+// 3. Use transitional mechanism for 4 deviation characters (sharp-s,
+// final sigma, ZWJ and ZWNJ) for now.
+// 4. Continue to allow symbols and punctuations.
+// 5. Apply new BiDi check rules more permissive than the IDNA 2003 BiDI rules.
+// 6. Do not apply STD3 rules
+// 7. Do not allow unassigned code points.
+//
+// It also closely matches what IE 10 does except for the BiDi check (
+// http://goo.gl/3XBhqw ).
+// See http://http://unicode.org/reports/tr46/ and references therein
+// for more details.
+struct UIDNAWrapper {
+ UIDNAWrapper() {
+ UErrorCode err = U_ZERO_ERROR;
+ // TODO(jungshik): Change options as different parties (browsers,
+ // registrars, search engines) converge toward a consensus.
+ value = uidna_openUTS46(UIDNA_CHECK_BIDI, &err);
+ if (U_FAILURE(err))
+ value = NULL;
+ }
+
+ UIDNA* value;
+};
+
} // namespace
ICUCharsetConverter::ICUCharsetConverter(UConverter* converter)
@@ -107,6 +142,9 @@
} while (true);
}
+static base::LazyInstance<UIDNAWrapper>::Leaky
+ g_uidna = LAZY_INSTANCE_INITIALIZER;
+
// Converts the Unicode input representing a hostname to ASCII using IDN rules.
// The output must be ASCII, but is represented as wide characters.
//
@@ -116,25 +154,33 @@
// the length of the output will be set to the length of the new host name.
//
// On error, this will return false. The output in this case is undefined.
+// TODO(jungshik): use UTF-8/ASCII version of nameToASCII.
+// Change the function signature and callers accordingly to avoid unnecessary
+// conversions in our code. In addition, consider using icu::IDNA's UTF-8/ASCII
+// version with StringByteSink. That way, we can avoid C wrappers and additional
+// string conversion.
bool IDNToASCII(const base::char16* src, int src_len, CanonOutputW* output) {
DCHECK(output->length() == 0); // Output buffer is assumed empty.
+
+ UIDNA* uidna = g_uidna.Get().value;
+ DCHECK(uidna != NULL);
while (true) {
- // Use ALLOW_UNASSIGNED to be more tolerant of hostnames that violate
- // the spec (which do exist). This does not present any risk and is a
- // little more future proof.
UErrorCode err = U_ZERO_ERROR;
- int num_converted = uidna_IDNToASCII(src, src_len, output->data(),
- output->capacity(),
- UIDNA_ALLOW_UNASSIGNED, NULL, &err);
- if (err == U_ZERO_ERROR) {
- output->set_length(num_converted);
+ UIDNAInfo info = UIDNA_INFO_INITIALIZER;
+ int output_length = uidna_nameToASCII(uidna, src, src_len, output->data(),
+ output->capacity(), &info, &err);
+ if (U_SUCCESS(err) && info.errors == 0) {
+ output->set_length(output_length);
return true;
}
- if (err != U_BUFFER_OVERFLOW_ERROR)
+
+ // TODO(jungshik): Look at info.errors to handle them case-by-case basis
+ // if necessary.
+ if (err != U_BUFFER_OVERFLOW_ERROR || info.errors != 0)
return false; // Unknown error, give up.
// Not enough room in our buffer, expand.
- output->Resize(output->capacity() * 2);
+ output->Resize(output_length);
}
}
« no previous file with comments | « url/url.gyp ('k') | url/url_canon_unittest.cc » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698