Support IDNA 2008

url/url_canon_icu.cc

 // Copyright 2013 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 // ICU integration functions.
 
 #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"
 #include "third_party/icu/source/common/unicode/uidna.h"
 #include "url/url_canon_icu.h"
 #include "url/url_canon_internal.h"  // for _itoa_s
 
 namespace url_canon {
 
 namespace {
@@ skipping 44 matching lines @@
     ucnv_setFromUCallBack(converter_, old_callback_, old_context_, 0, 0, &err);
   }
 
  private:
   UConverter* converter_;
 
   UConverterFromUCallback old_callback_;
   const void* old_context_;
 };
 
+// A wrapper to use LazyInstance<>::Leaky with ICU's UIDNA, a C pointer to
+// UTS46/IDNA 2008 handling object opened with |uidna_openUTS46|.
+//
+// We now switch to UTS46 with BiDiCheck to migrate to IDNA 2008 with
+// the backward compatibility in mind. What it means :
+//
+// 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)
     : converter_(converter) {
 }
 
 ICUCharsetConverter::~ICUCharsetConverter() {
 }
 
 void ICUCharsetConverter::ConvertFromUTF16(const base::char16* input,
@@ skipping 16 matching lines @@
       output->set_length(begin_offset + required_capacity);
       return;
     }
 
     // Output didn't fit, expand
     dest_capacity = required_capacity;
     output->Resize(begin_offset + dest_capacity);
   } 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.
 //
 // On success, the output will be filled with the ASCII host name and it will
 // return true. Unlike most other canonicalization functions, this assumes that
 // the output is empty. The beginning of the host will be at offset 0, and
 // 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);
   }
 }
 
 bool ReadUTFChar(const char* str, int* begin, int length,
                  unsigned* code_point_out) {
   int code_point;  // Avoids warning when U8_NEXT writes -1 to it.
   U8_NEXT(str, *begin, length, code_point);
   *code_point_out = static_cast<unsigned>(code_point);
 
   // The ICU macro above moves to the next char, we want to point to the last
@@ skipping 27 matching lines @@
 
   if (U_IS_UNICODE_CHAR(*code_point))
     return true;
 
   // Invalid code point.
   *code_point = kUnicodeReplacementCharacter;
   return false;
 }
 
 }  // namespace url_canon