Index: url/url_canon_icu.cc |
=================================================================== |
--- url/url_canon_icu.cc (revision 223643) |
+++ 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 +72,26 @@ |
const void* old_context_; |
}; |
+struct uidna_wrapper { |
+ uidna_wrapper() { |
+ UErrorCode err = U_ZERO_ERROR; |
+ // This is the option closest to what we had in the past with IDNA 2003 |
+ // API and matches what IE 10 does except for BiDi check. |
+ // IDNA 2003 always checks BiDi. We used to allow unassigned code |
+ // points. However, with our Unicode DB pretty up to date, we'd not |
+ // need to turn this on. |
+ // We didn't use STD3 rules and we continue not to. |
+ // TODO(jungshik) : Change options as different parties (browsers, |
+ // registrars, search engines) converge toward a consensus. |
+ int32_t options = UIDNA_CHECK_BIDI; |
+ value = uidna_openUTS46(options, &err); |
+ if (U_FAILURE(err)) |
+ value = NULL; |
+ } |
+ |
+ UIDNA* value; |
+}; |
+ |
} // namespace |
ICUCharsetConverter::ICUCharsetConverter(UConverter* converter) |
@@ -107,6 +128,9 @@ |
} while (true); |
} |
+static base::LazyInstance<uidna_wrapper>::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 +140,33 @@ |
// 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); |
brettw
2013/09/19 17:44:45
Under what cases might we get an error that would
jungshik at Google
2013/09/19 19:16:16
I don't think it'll fail unless we can't get acces
|
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); |
} |
} |