Split IDNA logic from url_canon_icu.cc into its own file

The ICU-based converter and the ICU-based IDNA logic use different
datasets from ICU.  This allows external embedders that only need IDNA
to avoid depending on huge (over 2 MiB) character set conversion
dataset.

Change-Id: I9e61208051d9553ddf93ec517ea07a7e54410e5e
Reviewed-on: https://chromium-review.googlesource.com/1185215Reviewed-by: Chris Palmer <palmer@chromium.org>
Commit-Queue: Victor Vasiliev <vasilvv@chromium.org>
Cr-Commit-Position: refs/heads/master@{#585989}

url/BUILD.gn

@@ -76,7 +76,7 @@ component("url") {
   # ICU support.
   if (use_platform_icu_alternatives) {
     if (is_android) {
-      sources += [ "url_canon_icu_alternatives_android.cc" ]
+      sources += [ "url_idna_icu_alternatives_android.cc" ]
       deps += [
         ":url_features",
         ":url_java",
@@ -85,7 +85,7 @@ component("url") {
         "//base/third_party/dynamic_annotations",
       ]
     } else if (is_ios) {
-      sources += [ "url_canon_icu_alternatives_ios.mm" ]
+      sources += [ "url_idna_icu_alternatives_ios.mm" ]
     } else {
       assert(false,
              "ICU alternative is not implemented for platform: " + target_os)
@@ -95,6 +95,7 @@ component("url") {
     sources += [
       "url_canon_icu.cc",
       "url_canon_icu.h",
+      "url_idna_icu.cc",
     ]
     deps += [ "//third_party/icu" ]
   }

url/DEPS

@@ -10,7 +10,7 @@ specific_include_rules = {
   "gurl_fuzzer.cc": [
     "+base/i18n",
   ],
-  "url_canon_icu(\.cc|_unittest\.cc)": [
+  "url_(canon|idna)_icu(\.cc|_unittest\.cc)": [
     "+third_party/icu",
   ],
   "run_all_unittests\.cc": [

url/url_canon_icu.cc

@@ -2,17 +2,15 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
-// ICU integration functions.
+// ICU-based character set converter.
 
 #include <stdint.h>
 #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 "third_party/icu/source/common/unicode/utypes.h"
 #include "url/url_canon_icu.h"
 #include "url/url_canon_internal.h"  // for _itoa_s
@@ -74,46 +72,6 @@ class AppendHandlerInstaller {
   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)) {
-      CHECK(false) << "failed to open UTS46 data with error: "
-                   << u_errorName(err)
-                   << ". If you see this error message in a test environment "
-                   << "your test environment likely lacks the required data "
-                   << "tables for libicu. See https://crbug.com/778929.";
-      value = NULL;
-    }
-  }
-
-  UIDNA* value;
-};
-
 }  // namespace
 
 ICUCharsetConverter::ICUCharsetConverter(UConverter* converter)
@@ -149,46 +107,4 @@ void ICUCharsetConverter::ConvertFromUTF16(const base::char16* input,
   } 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) {
-    UErrorCode err = U_ZERO_ERROR;
-    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;
-    }
-
-    // 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_length);
-  }
-}
-
 }  // namespace url

url/url_idna_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-based IDNA converter.
+
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "base/lazy_instance.h"
+#include "base/logging.h"
+#include "third_party/icu/source/common/unicode/uidna.h"
+#include "third_party/icu/source/common/unicode/utypes.h"
+#include "url/url_canon_icu.h"
+#include "url/url_canon_internal.h"  // for _itoa_s
+
+namespace url {
+
+namespace {
+
+// 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)) {
+      CHECK(false) << "failed to open UTS46 data with error: "
+                   << u_errorName(err)
+                   << ". If you see this error message in a test environment "
+                   << "your test environment likely lacks the required data "
+                   << "tables for libicu. See https://crbug.com/778929.";
+      value = NULL;
+    }
+  }
+
+  UIDNA* value;
+};
+
+}  // namespace
+
+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) {
+    UErrorCode err = U_ZERO_ERROR;
+    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;
+    }
+
+    // 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_length);
+  }
+}
+
+}  // namespace url