Stop pulling googleurl through DEPS.

This is the final patch in this series of merging the external googleurl repo
into Chromium source code base.

BUG=229660
R=brettw@chromium.org,joth@chromium.org,blundell@chromium.org,thakis@chromium.org,thestig@chromium.org
TBR=brettw

Review URL: https://chromiumcodereview.appspot.com/20349002

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@216922 0039d316-1c4b-4281-b951-d872f2087c98

12 files changed, 440 insertions, 375 deletions

diff --git a/DEPS b/DEPS
index 9c5d932..bc6feb5 100644
--- a/DEPS
+++ b/DEPS
@@ -55,9 +55,6 @@ deps = {
   "src/breakpad/src":
     (Var("googlecode_url") % "google-breakpad") + "/trunk/src@1199",
 
-  "src/googleurl":
-    (Var("googlecode_url") % "google-url") + "/trunk@185",
-
   "src/sdch/open-vcdiff":
     (Var("googlecode_url") % "open-vcdiff") + "/trunk@42",
 
@@ -513,8 +510,6 @@ include_rules = [
   "+third_party/icu/source/common/unicode",
   "+third_party/icu/source/i18n/unicode",
   "+url",
-  # TODO(tfarina): Temporary, until we finish the migration to url. Remove this!
-  "!googleurl",
 ]
 
 
@@ -523,7 +518,6 @@ skip_child_includes = [
   "breakpad",
   "chrome_frame",
   "delegate_execute",
-  "googleurl",
   "metro_driver",
   "native_client_sdk",
   "o3d",
diff --git a/android_webview/buildbot/deps_whitelist.py b/android_webview/buildbot/deps_whitelist.py
index 69c87be..105646f 100755
--- a/android_webview/buildbot/deps_whitelist.py
+++ b/android_webview/buildbot/deps_whitelist.py
@@ -32,7 +32,6 @@ class DepsWhitelist(object):
 
     # Dependencies that need to be merged into the Android tree.
     self._snapshot_into_android_dependencies = [
-      'googleurl',
       'sdch/open-vcdiff',
       'testing/gtest',
       'third_party/WebKit',
diff --git a/ios/public/DEPS b/ios/public/DEPS
index 3f0cd59..c04c1d5 100644
--- a/ios/public/DEPS
+++ b/ios/public/DEPS
@@ -4,7 +4,6 @@ include_rules = [
   # be kept in sync with src/DEPS.
   "-base",
   "-build",
-  "-googleurl",
   "-library_loaders",
   "-testing",
   "-third_party/icu/source/common/unicode",
diff --git a/tools/checklicenses/checklicenses.py b/tools/checklicenses/checklicenses.py
index 9c27256..25dedc2 100755
--- a/tools/checklicenses/checklicenses.py
+++ b/tools/checklicenses/checklicenses.py
@@ -128,10 +128,6 @@ PATH_SPECIFIC_WHITELISTED_LICENSES = {
     'data/tab_switching': [
         'UNKNOWN',
     ],
-    'googleurl': [  # http://code.google.com/p/google-url/issues/detail?id=15
-        'UNKNOWN',
-    ],
-
     'native_client': [  # http://crbug.com/98099
         'UNKNOWN',
     ],
diff --git a/tools/clang/plugins/ChromeClassTester.cpp b/tools/clang/plugins/ChromeClassTester.cpp
index 5784334..ee8452d 100644
--- a/tools/clang/plugins/ChromeClassTester.cpp
+++ b/tools/clang/plugins/ChromeClassTester.cpp
@@ -151,7 +151,6 @@ void ChromeClassTester::BuildBannedLists() {
   banned_directories_.push_back("ppapi/");
   banned_directories_.push_back("usr/");
   banned_directories_.push_back("testing/");
-  banned_directories_.push_back("googleurl/");
   banned_directories_.push_back("v8/");
   banned_directories_.push_back("dart/");
   banned_directories_.push_back("sdch/");
diff --git a/tools/licenses.py b/tools/licenses.py
index 4d1cb01..d2c535b 100755
--- a/tools/licenses.py
+++ b/tools/licenses.py
@@ -82,7 +82,6 @@ ADDITIONAL_PATHS = (
     os.path.join('chrome', 'common', 'extensions', 'docs', 'examples'),
     os.path.join('chrome', 'test', 'chromeos', 'autotest'),
     os.path.join('chrome', 'test', 'data'),
-    os.path.join('googleurl'),
     os.path.join('native_client'),
     os.path.join('native_client_sdk'),
     os.path.join('net', 'tools', 'spdyshark'),
@@ -97,6 +96,7 @@ ADDITIONAL_PATHS = (
     os.path.join('tools', 'grit'),
     os.path.join('tools', 'gyp'),
     os.path.join('tools', 'page_cycler', 'acid3'),
+    os.path.join('url', 'third_party', 'mozilla'),
     os.path.join('v8'),
     # Fake directory so we can include the strongtalk license.
     os.path.join('v8', 'strongtalk'),
@@ -107,12 +107,6 @@ ADDITIONAL_PATHS = (
 # can't provide a README.chromium.  Please prefer a README.chromium
 # wherever possible.
 SPECIAL_CASES = {
-    os.path.join('googleurl'): {
-        "Name": "google-url",
-        "URL": "http://code.google.com/p/google-url/",
-        "License": "BSD and MPL 1.1/GPL 2.0/LGPL 2.1",
-        "License File": "LICENSE.txt",
-    },
     os.path.join('native_client'): {
         "Name": "native client",
         "URL": "http://code.google.com/p/nativeclient",
diff --git a/url/third_party/mozilla/LICENSE.txt b/url/third_party/mozilla/LICENSE.txt
new file mode 100644
index 0000000..ac40837
--- /dev/null
+++ b/url/third_party/mozilla/LICENSE.txt
@@ -0,0 +1,65 @@
+Copyright 2007, Google Inc.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+    * Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above
+copyright notice, this list of conditions and the following disclaimer
+in the documentation and/or other materials provided with the
+distribution.
+    * Neither the name of Google Inc. nor the names of its
+contributors may be used to endorse or promote products derived from
+this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+-------------------------------------------------------------------------------
+
+The file url_parse.cc is based on nsURLParsers.cc from Mozilla. This file is
+licensed separately as follows:
+
+The contents of this file are subject to the Mozilla Public License Version
+1.1 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+http://www.mozilla.org/MPL/
+
+Software distributed under the License is distributed on an "AS IS" basis,
+WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
+for the specific language governing rights and limitations under the
+License.
+
+The Original Code is mozilla.org code.
+
+The Initial Developer of the Original Code is
+Netscape Communications Corporation.
+Portions created by the Initial Developer are Copyright (C) 1998
+the Initial Developer. All Rights Reserved.
+
+Contributor(s):
+  Darin Fisher (original author)
+
+Alternatively, the contents of this file may be used under the terms of
+either the GNU General Public License Version 2 or later (the "GPL"), or
+the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
+in which case the provisions of the GPL or the LGPL are applicable instead
+of those above. If you wish to allow use of your version of this file only
+under the terms of either the GPL or the LGPL, and not to allow others to
+use your version of this file under the terms of the MPL, indicate your
+decision by deleting the provisions above and replace them with the notice
+and other provisions required by the GPL or the LGPL. If you do not delete
+the provisions above, a recipient may use your version of this file under
+the terms of any one of the MPL, the GPL or the LGPL.
diff --git a/url/third_party/mozilla/README.chromium b/url/third_party/mozilla/README.chromium
new file mode 100644
index 0000000..ef396d3
--- /dev/null
+++ b/url/third_party/mozilla/README.chromium
@@ -0,0 +1,8 @@
+Name: url_parse
+URL: http://mxr.mozilla.org/comm-central/source/mozilla/netwerk/base/src/nsURLParsers.cpp
+License: BSD and MPL 1.1/GPL 2.0/LGPL 2.1
+License File: LICENSE.txt
+
+Description:
+
+The file url_parse.cc is based on nsURLParsers.cc from Mozilla.
diff --git a/url/url_parse.cc b/url/third_party/mozilla/url_parse.cc
index 0d9c6dd1c..52c6196 100644
--- a/url/url_parse.cc
+++ b/url/third_party/mozilla/url_parse.cc
@@ -34,7 +34,7 @@
  *
  * ***** END LICENSE BLOCK ***** */
 
-#include "url/url_parse.h"
+#include "url/third_party/mozilla/url_parse.h"
 
 #include <stdlib.h>
 
diff --git a/url/third_party/mozilla/url_parse.h b/url/third_party/mozilla/url_parse.h
new file mode 100644
index 0000000..fd974f8
--- /dev/null
+++ b/url/third_party/mozilla/url_parse.h
@@ -0,0 +1,361 @@
+// 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.
+
+#ifndef URL_THIRD_PARTY_MOZILLA_URL_PARSE_H_
+#define URL_THIRD_PARTY_MOZILLA_URL_PARSE_H_
+
+#include <string>
+
+#include "base/basictypes.h"
+#include "base/strings/string16.h"
+#include "url/url_export.h"
+
+namespace url_parse {
+
+// Deprecated, but WebKit/WebCore/platform/KURLGooglePrivate.h and
+// KURLGoogle.cpp still rely on this type.
+typedef base::char16 UTF16Char;
+
+// Component ------------------------------------------------------------------
+
+// Represents a substring for URL parsing.
+struct Component {
+  Component() : begin(0), len(-1) {}
+
+  // Normal constructor: takes an offset and a length.
+  Component(int b, int l) : begin(b), len(l) {}
+
+  int end() const {
+    return begin + len;
+  }
+
+  // Returns true if this component is valid, meaning the length is given. Even
+  // valid components may be empty to record the fact that they exist.
+  bool is_valid() const {
+    return (len != -1);
+  }
+
+  // Returns true if the given component is specified on false, the component
+  // is either empty or invalid.
+  bool is_nonempty() const {
+    return (len > 0);
+  }
+
+  void reset() {
+    begin = 0;
+    len = -1;
+  }
+
+  bool operator==(const Component& other) const {
+    return begin == other.begin && len == other.len;
+  }
+
+  int begin;  // Byte offset in the string of this component.
+  int len;    // Will be -1 if the component is unspecified.
+};
+
+// Helper that returns a component created with the given begin and ending
+// points. The ending point is non-inclusive.
+inline Component MakeRange(int begin, int end) {
+  return Component(begin, end - begin);
+}
+
+// Parsed ---------------------------------------------------------------------
+
+// A structure that holds the identified parts of an input URL. This structure
+// does NOT store the URL itself. The caller will have to store the URL text
+// and its corresponding Parsed structure separately.
+//
+// Typical usage would be:
+//
+//    url_parse::Parsed parsed;
+//    url_parse::Component scheme;
+//    if (!url_parse::ExtractScheme(url, url_len, &scheme))
+//      return I_CAN_NOT_FIND_THE_SCHEME_DUDE;
+//
+//    if (IsStandardScheme(url, scheme))  // Not provided by this component
+//      url_parseParseStandardURL(url, url_len, &parsed);
+//    else if (IsFileURL(url, scheme))    // Not provided by this component
+//      url_parse::ParseFileURL(url, url_len, &parsed);
+//    else
+//      url_parse::ParsePathURL(url, url_len, &parsed);
+//
+struct URL_EXPORT Parsed {
+  // Identifies different components.
+  enum ComponentType {
+    SCHEME,
+    USERNAME,
+    PASSWORD,
+    HOST,
+    PORT,
+    PATH,
+    QUERY,
+    REF,
+  };
+
+  // The default constructor is sufficient for the components, but inner_parsed_
+  // requires special handling.
+  Parsed();
+  Parsed(const Parsed&);
+  Parsed& operator=(const Parsed&);
+  ~Parsed();
+
+  // Returns the length of the URL (the end of the last component).
+  //
+  // Note that for some invalid, non-canonical URLs, this may not be the length
+  // of the string. For example "http://": the parsed structure will only
+  // contain an entry for the four-character scheme, and it doesn't know about
+  // the "://". For all other last-components, it will return the real length.
+  int Length() const;
+
+  // Returns the number of characters before the given component if it exists,
+  // or where the component would be if it did exist. This will return the
+  // string length if the component would be appended to the end.
+  //
+  // Note that this can get a little funny for the port, query, and ref
+  // components which have a delimiter that is not counted as part of the
+  // component. The |include_delimiter| flag controls if you want this counted
+  // as part of the component or not when the component exists.
+  //
+  // This example shows the difference between the two flags for two of these
+  // delimited components that is present (the port and query) and one that
+  // isn't (the reference). The components that this flag affects are marked
+  // with a *.
+  //                 0         1         2
+  //                 012345678901234567890
+  // Example input:  http://foo:80/?query
+  //              include_delim=true,  ...=false  ("<-" indicates different)
+  //      SCHEME: 0                    0
+  //    USERNAME: 5                    5
+  //    PASSWORD: 5                    5
+  //        HOST: 7                    7
+  //       *PORT: 10                   11 <-
+  //        PATH: 13                   13
+  //      *QUERY: 14                   15 <-
+  //        *REF: 20                   20
+  //
+  int CountCharactersBefore(ComponentType type, bool include_delimiter) const;
+
+  // Scheme without the colon: "http://foo"/ would have a scheme of "http".
+  // The length will be -1 if no scheme is specified ("foo.com"), or 0 if there
+  // is a colon but no scheme (":foo"). Note that the scheme is not guaranteed
+  // to start at the beginning of the string if there are preceeding whitespace
+  // or control characters.
+  Component scheme;
+
+  // Username. Specified in URLs with an @ sign before the host. See |password|
+  Component username;
+
+  // Password. The length will be -1 if unspecified, 0 if specified but empty.
+  // Not all URLs with a username have a password, as in "http://me@host/".
+  // The password is separated form the username with a colon, as in
+  // "http://me:secret@host/"
+  Component password;
+
+  // Host name.
+  Component host;
+
+  // Port number.
+  Component port;
+
+  // Path, this is everything following the host name. Length will be -1 if
+  // unspecified. This includes the preceeding slash, so the path on
+  // http://www.google.com/asdf" is "/asdf". As a result, it is impossible to
+  // have a 0 length path, it will be -1 in cases like "http://host?foo".
+  // Note that we treat backslashes the same as slashes.
+  Component path;
+
+  // Stuff between the ? and the # after the path. This does not include the
+  // preceeding ? character. Length will be -1 if unspecified, 0 if there is
+  // a question mark but no query string.
+  Component query;
+
+  // Indicated by a #, this is everything following the hash sign (not
+  // including it). If there are multiple hash signs, we'll use the last one.
+  // Length will be -1 if there is no hash sign, or 0 if there is one but
+  // nothing follows it.
+  Component ref;
+
+  // This is used for nested URL types, currently only filesystem.  If you
+  // parse a filesystem URL, the resulting Parsed will have a nested
+  // inner_parsed_ to hold the parsed inner URL's component information.
+  // For all other url types [including the inner URL], it will be NULL.
+  Parsed* inner_parsed() const {
+    return inner_parsed_;
+  }
+
+  void set_inner_parsed(const Parsed& inner_parsed) {
+    if (!inner_parsed_)
+      inner_parsed_ = new Parsed(inner_parsed);
+    else
+      *inner_parsed_ = inner_parsed;
+  }
+
+  void clear_inner_parsed() {
+    if (inner_parsed_) {
+      delete inner_parsed_;
+      inner_parsed_ = NULL;
+    }
+  }
+
+ private:
+  Parsed* inner_parsed_;  // This object is owned and managed by this struct.
+};
+
+// Initialization functions ---------------------------------------------------
+//
+// These functions parse the given URL, filling in all of the structure's
+// components. These functions can not fail, they will always do their best
+// at interpreting the input given.
+//
+// The string length of the URL MUST be specified, we do not check for NULLs
+// at any point in the process, and will actually handle embedded NULLs.
+//
+// IMPORTANT: These functions do NOT hang on to the given pointer or copy it
+// in any way. See the comment above the struct.
+//
+// The 8-bit versions require UTF-8 encoding.
+
+// StandardURL is for when the scheme is known to be one that has an
+// authority (host) like "http". This function will not handle weird ones
+// like "about:" and "javascript:", or do the right thing for "file:" URLs.
+URL_EXPORT void ParseStandardURL(const char* url,
+                                 int url_len,
+                                 Parsed* parsed);
+URL_EXPORT void ParseStandardURL(const base::char16* url,
+                                 int url_len,
+                                 Parsed* parsed);
+
+// PathURL is for when the scheme is known not to have an authority (host)
+// section but that aren't file URLs either. The scheme is parsed, and
+// everything after the scheme is considered as the path. This is used for
+// things like "about:" and "javascript:"
+URL_EXPORT void ParsePathURL(const char* url, int url_len, Parsed* parsed);
+URL_EXPORT void ParsePathURL(const base::char16* url,
+                             int url_len,
+                             Parsed* parsed);
+
+// FileURL is for file URLs. There are some special rules for interpreting
+// these.
+URL_EXPORT void ParseFileURL(const char* url, int url_len, Parsed* parsed);
+URL_EXPORT void ParseFileURL(const base::char16* url,
+                             int url_len,
+                             Parsed* parsed);
+
+// Filesystem URLs are structured differently than other URLs.
+URL_EXPORT void ParseFileSystemURL(const char* url,
+                                   int url_len,
+                                   Parsed* parsed);
+URL_EXPORT void ParseFileSystemURL(const base::char16* url,
+                                   int url_len,
+                                   Parsed* parsed);
+
+// MailtoURL is for mailto: urls. They are made up scheme,path,query
+URL_EXPORT void ParseMailtoURL(const char* url, int url_len, Parsed* parsed);
+URL_EXPORT void ParseMailtoURL(const base::char16* url,
+                               int url_len,
+                               Parsed* parsed);
+
+// Helper functions -----------------------------------------------------------
+
+// Locates the scheme according to the URL  parser's rules. This function is
+// designed so the caller can find the scheme and call the correct Init*
+// function according to their known scheme types.
+//
+// It also does not perform any validation on the scheme.
+//
+// This function will return true if the scheme is found and will put the
+// scheme's range into *scheme. False means no scheme could be found. Note
+// that a URL beginning with a colon has a scheme, but it is empty, so this
+// function will return true but *scheme will = (0,0).
+//
+// The scheme is found by skipping spaces and control characters at the
+// beginning, and taking everything from there to the first colon to be the
+// scheme. The character at scheme.end() will be the colon (we may enhance
+// this to handle full width colons or something, so don't count on the
+// actual character value). The character at scheme.end()+1 will be the
+// beginning of the rest of the URL, be it the authority or the path (or the
+// end of the string).
+//
+// The 8-bit version requires UTF-8 encoding.
+URL_EXPORT bool ExtractScheme(const char* url,
+                              int url_len,
+                              Component* scheme);
+URL_EXPORT bool ExtractScheme(const base::char16* url,
+                              int url_len,
+                              Component* scheme);
+
+// Returns true if ch is a character that terminates the authority segment
+// of a URL.
+URL_EXPORT bool IsAuthorityTerminator(base::char16 ch);
+
+// Does a best effort parse of input |spec|, in range |auth|. If a particular
+// component is not found, it will be set to invalid.
+URL_EXPORT void ParseAuthority(const char* spec,
+                               const Component& auth,
+                               Component* username,
+                               Component* password,
+                               Component* hostname,
+                               Component* port_num);
+URL_EXPORT void ParseAuthority(const base::char16* spec,
+                               const Component& auth,
+                               Component* username,
+                               Component* password,
+                               Component* hostname,
+                               Component* port_num);
+
+// Computes the integer port value from the given port component. The port
+// component should have been identified by one of the init functions on
+// |Parsed| for the given input url.
+//
+// The return value will be a positive integer between 0 and 64K, or one of
+// the two special values below.
+enum SpecialPort { PORT_UNSPECIFIED = -1, PORT_INVALID = -2 };
+URL_EXPORT int ParsePort(const char* url, const Component& port);
+URL_EXPORT int ParsePort(const base::char16* url, const Component& port);
+
+// Extracts the range of the file name in the given url. The path must
+// already have been computed by the parse function, and the matching URL
+// and extracted path are provided to this function. The filename is
+// defined as being everything from the last slash/backslash of the path
+// to the end of the path.
+//
+// The file name will be empty if the path is empty or there is nothing
+// following the last slash.
+//
+// The 8-bit version requires UTF-8 encoding.
+URL_EXPORT void ExtractFileName(const char* url,
+                                const Component& path,
+                                Component* file_name);
+URL_EXPORT void ExtractFileName(const base::char16* url,
+                                const Component& path,
+                                Component* file_name);
+
+// Extract the first key/value from the range defined by |*query|. Updates
+// |*query| to start at the end of the extracted key/value pair. This is
+// designed for use in a loop: you can keep calling it with the same query
+// object and it will iterate over all items in the query.
+//
+// Some key/value pairs may have the key, the value, or both be empty (for
+// example, the query string "?&"). These will be returned. Note that an empty
+// last parameter "foo.com?" or foo.com?a&" will not be returned, this case
+// is the same as "done."
+//
+// The initial query component should not include the '?' (this is the default
+// for parsed URLs).
+//
+// If no key/value are found |*key| and |*value| will be unchanged and it will
+// return false.
+URL_EXPORT bool ExtractQueryKeyValue(const char* url,
+                                     Component* query,
+                                     Component* key,
+                                     Component* value);
+URL_EXPORT bool ExtractQueryKeyValue(const base::char16* url,
+                                     Component* query,
+                                     Component* key,
+                                     Component* value);
+
+}  // namespace url_parse
+
+#endif  // URL_THIRD_PARTY_MOZILLA_URL_PARSE_H_
diff --git a/url/url.gyp b/url/url.gyp
index a9a1a19d..fe4d5fd 100644
--- a/url/url.gyp
+++ b/url/url.gyp
@@ -22,6 +22,8 @@
       'sources': [
         'gurl.cc',
         'gurl.h',
+        'third_party/mozilla/url_parse.cc',
+        'third_party/mozilla/url_parse.h',
         'url_canon.h',
         'url_canon_etc.cc',
         'url_canon_filesystemurl.cc',
@@ -42,8 +44,6 @@
         'url_canon_stdstring.h',
         'url_canon_stdurl.cc',
         'url_file.h',
-        'url_parse.cc',
-        'url_parse.h',
         'url_parse_file.cc',
         'url_parse_internal.h',
         'url_util.cc',
diff --git a/url/url_parse.h b/url/url_parse.h
index 21033dd..3b9c546 100644
--- a/url/url_parse.h
+++ b/url/url_parse.h
@@ -5,357 +5,7 @@
 #ifndef URL_URL_PARSE_H_
 #define URL_URL_PARSE_H_
 
-#include <string>
-
-#include "base/basictypes.h"
-#include "base/strings/string16.h"
-#include "url/url_export.h"
-
-namespace url_parse {
-
-// Deprecated, but WebKit/WebCore/platform/KURLGooglePrivate.h and
-// KURLGoogle.cpp still rely on this type.
-typedef base::char16 UTF16Char;
-
-// Component ------------------------------------------------------------------
-
-// Represents a substring for URL parsing.
-struct Component {
-  Component() : begin(0), len(-1) {}
-
-  // Normal constructor: takes an offset and a length.
-  Component(int b, int l) : begin(b), len(l) {}
-
-  int end() const {
-    return begin + len;
-  }
-
-  // Returns true if this component is valid, meaning the length is given. Even
-  // valid components may be empty to record the fact that they exist.
-  bool is_valid() const {
-    return (len != -1);
-  }
-
-  // Returns true if the given component is specified on false, the component
-  // is either empty or invalid.
-  bool is_nonempty() const {
-    return (len > 0);
-  }
-
-  void reset() {
-    begin = 0;
-    len = -1;
-  }
-
-  bool operator==(const Component& other) const {
-    return begin == other.begin && len == other.len;
-  }
-
-  int begin;  // Byte offset in the string of this component.
-  int len;    // Will be -1 if the component is unspecified.
-};
-
-// Helper that returns a component created with the given begin and ending
-// points. The ending point is non-inclusive.
-inline Component MakeRange(int begin, int end) {
-  return Component(begin, end - begin);
-}
-
-// Parsed ---------------------------------------------------------------------
-
-// A structure that holds the identified parts of an input URL. This structure
-// does NOT store the URL itself. The caller will have to store the URL text
-// and its corresponding Parsed structure separately.
-//
-// Typical usage would be:
-//
-//    url_parse::Parsed parsed;
-//    url_parse::Component scheme;
-//    if (!url_parse::ExtractScheme(url, url_len, &scheme))
-//      return I_CAN_NOT_FIND_THE_SCHEME_DUDE;
-//
-//    if (IsStandardScheme(url, scheme))  // Not provided by this component
-//      url_parseParseStandardURL(url, url_len, &parsed);
-//    else if (IsFileURL(url, scheme))    // Not provided by this component
-//      url_parse::ParseFileURL(url, url_len, &parsed);
-//    else
-//      url_parse::ParsePathURL(url, url_len, &parsed);
-//
-struct URL_EXPORT Parsed {
-  // Identifies different components.
-  enum ComponentType {
-    SCHEME,
-    USERNAME,
-    PASSWORD,
-    HOST,
-    PORT,
-    PATH,
-    QUERY,
-    REF,
-  };
-
-  // The default constructor is sufficient for the components, but inner_parsed_
-  // requires special handling.
-  Parsed();
-  Parsed(const Parsed&);
-  Parsed& operator=(const Parsed&);
-  ~Parsed();
-
-  // Returns the length of the URL (the end of the last component).
-  //
-  // Note that for some invalid, non-canonical URLs, this may not be the length
-  // of the string. For example "http://": the parsed structure will only
-  // contain an entry for the four-character scheme, and it doesn't know about
-  // the "://". For all other last-components, it will return the real length.
-  int Length() const;
-
-  // Returns the number of characters before the given component if it exists,
-  // or where the component would be if it did exist. This will return the
-  // string length if the component would be appended to the end.
-  //
-  // Note that this can get a little funny for the port, query, and ref
-  // components which have a delimiter that is not counted as part of the
-  // component. The |include_delimiter| flag controls if you want this counted
-  // as part of the component or not when the component exists.
-  //
-  // This example shows the difference between the two flags for two of these
-  // delimited components that is present (the port and query) and one that
-  // isn't (the reference). The components that this flag affects are marked
-  // with a *.
-  //                 0         1         2
-  //                 012345678901234567890
-  // Example input:  http://foo:80/?query
-  //              include_delim=true,  ...=false  ("<-" indicates different)
-  //      SCHEME: 0                    0
-  //    USERNAME: 5                    5
-  //    PASSWORD: 5                    5
-  //        HOST: 7                    7
-  //       *PORT: 10                   11 <-
-  //        PATH: 13                   13
-  //      *QUERY: 14                   15 <-
-  //        *REF: 20                   20
-  //
-  int CountCharactersBefore(ComponentType type, bool include_delimiter) const;
-
-  // Scheme without the colon: "http://foo"/ would have a scheme of "http".
-  // The length will be -1 if no scheme is specified ("foo.com"), or 0 if there
-  // is a colon but no scheme (":foo"). Note that the scheme is not guaranteed
-  // to start at the beginning of the string if there are preceeding whitespace
-  // or control characters.
-  Component scheme;
-
-  // Username. Specified in URLs with an @ sign before the host. See |password|
-  Component username;
-
-  // Password. The length will be -1 if unspecified, 0 if specified but empty.
-  // Not all URLs with a username have a password, as in "http://me@host/".
-  // The password is separated form the username with a colon, as in
-  // "http://me:secret@host/"
-  Component password;
-
-  // Host name.
-  Component host;
-
-  // Port number.
-  Component port;
-
-  // Path, this is everything following the host name. Length will be -1 if
-  // unspecified. This includes the preceeding slash, so the path on
-  // http://www.google.com/asdf" is "/asdf". As a result, it is impossible to
-  // have a 0 length path, it will be -1 in cases like "http://host?foo".
-  // Note that we treat backslashes the same as slashes.
-  Component path;
-
-  // Stuff between the ? and the # after the path. This does not include the
-  // preceeding ? character. Length will be -1 if unspecified, 0 if there is
-  // a question mark but no query string.
-  Component query;
-
-  // Indicated by a #, this is everything following the hash sign (not
-  // including it). If there are multiple hash signs, we'll use the last one.
-  // Length will be -1 if there is no hash sign, or 0 if there is one but
-  // nothing follows it.
-  Component ref;
-
-  // This is used for nested URL types, currently only filesystem.  If you
-  // parse a filesystem URL, the resulting Parsed will have a nested
-  // inner_parsed_ to hold the parsed inner URL's component information.
-  // For all other url types [including the inner URL], it will be NULL.
-  Parsed* inner_parsed() const {
-    return inner_parsed_;
-  }
-
-  void set_inner_parsed(const Parsed& inner_parsed) {
-    if (!inner_parsed_)
-      inner_parsed_ = new Parsed(inner_parsed);
-    else
-      *inner_parsed_ = inner_parsed;
-  }
-
-  void clear_inner_parsed() {
-    if (inner_parsed_) {
-      delete inner_parsed_;
-      inner_parsed_ = NULL;
-    }
-  }
-
- private:
-  Parsed* inner_parsed_;  // This object is owned and managed by this struct.
-};
-
-// Initialization functions ---------------------------------------------------
-//
-// These functions parse the given URL, filling in all of the structure's
-// components. These functions can not fail, they will always do their best
-// at interpreting the input given.
-//
-// The string length of the URL MUST be specified, we do not check for NULLs
-// at any point in the process, and will actually handle embedded NULLs.
-//
-// IMPORTANT: These functions do NOT hang on to the given pointer or copy it
-// in any way. See the comment above the struct.
-//
-// The 8-bit versions require UTF-8 encoding.
-
-// StandardURL is for when the scheme is known to be one that has an
-// authority (host) like "http". This function will not handle weird ones
-// like "about:" and "javascript:", or do the right thing for "file:" URLs.
-URL_EXPORT void ParseStandardURL(const char* url,
-                                 int url_len,
-                                 Parsed* parsed);
-URL_EXPORT void ParseStandardURL(const base::char16* url,
-                                 int url_len,
-                                 Parsed* parsed);
-
-// PathURL is for when the scheme is known not to have an authority (host)
-// section but that aren't file URLs either. The scheme is parsed, and
-// everything after the scheme is considered as the path. This is used for
-// things like "about:" and "javascript:"
-URL_EXPORT void ParsePathURL(const char* url, int url_len, Parsed* parsed);
-URL_EXPORT void ParsePathURL(const base::char16* url,
-                             int url_len,
-                             Parsed* parsed);
-
-// FileURL is for file URLs. There are some special rules for interpreting
-// these.
-URL_EXPORT void ParseFileURL(const char* url, int url_len, Parsed* parsed);
-URL_EXPORT void ParseFileURL(const base::char16* url,
-                             int url_len,
-                             Parsed* parsed);
-
-// Filesystem URLs are structured differently than other URLs.
-URL_EXPORT void ParseFileSystemURL(const char* url,
-                                   int url_len,
-                                   Parsed* parsed);
-URL_EXPORT void ParseFileSystemURL(const base::char16* url,
-                                   int url_len,
-                                   Parsed* parsed);
-
-// MailtoURL is for mailto: urls. They are made up scheme,path,query
-URL_EXPORT void ParseMailtoURL(const char* url, int url_len, Parsed* parsed);
-URL_EXPORT void ParseMailtoURL(const base::char16* url,
-                               int url_len,
-                               Parsed* parsed);
-
-// Helper functions -----------------------------------------------------------
-
-// Locates the scheme according to the URL  parser's rules. This function is
-// designed so the caller can find the scheme and call the correct Init*
-// function according to their known scheme types.
-//
-// It also does not perform any validation on the scheme.
-//
-// This function will return true if the scheme is found and will put the
-// scheme's range into *scheme. False means no scheme could be found. Note
-// that a URL beginning with a colon has a scheme, but it is empty, so this
-// function will return true but *scheme will = (0,0).
-//
-// The scheme is found by skipping spaces and control characters at the
-// beginning, and taking everything from there to the first colon to be the
-// scheme. The character at scheme.end() will be the colon (we may enhance
-// this to handle full width colons or something, so don't count on the
-// actual character value). The character at scheme.end()+1 will be the
-// beginning of the rest of the URL, be it the authority or the path (or the
-// end of the string).
-//
-// The 8-bit version requires UTF-8 encoding.
-URL_EXPORT bool ExtractScheme(const char* url,
-                              int url_len,
-                              Component* scheme);
-URL_EXPORT bool ExtractScheme(const base::char16* url,
-                              int url_len,
-                              Component* scheme);
-
-// Returns true if ch is a character that terminates the authority segment
-// of a URL.
-URL_EXPORT bool IsAuthorityTerminator(base::char16 ch);
-
-// Does a best effort parse of input |spec|, in range |auth|. If a particular
-// component is not found, it will be set to invalid.
-URL_EXPORT void ParseAuthority(const char* spec,
-                               const Component& auth,
-                               Component* username,
-                               Component* password,
-                               Component* hostname,
-                               Component* port_num);
-URL_EXPORT void ParseAuthority(const base::char16* spec,
-                               const Component& auth,
-                               Component* username,
-                               Component* password,
-                               Component* hostname,
-                               Component* port_num);
-
-// Computes the integer port value from the given port component. The port
-// component should have been identified by one of the init functions on
-// |Parsed| for the given input url.
-//
-// The return value will be a positive integer between 0 and 64K, or one of
-// the two special values below.
-enum SpecialPort { PORT_UNSPECIFIED = -1, PORT_INVALID = -2 };
-URL_EXPORT int ParsePort(const char* url, const Component& port);
-URL_EXPORT int ParsePort(const base::char16* url, const Component& port);
-
-// Extracts the range of the file name in the given url. The path must
-// already have been computed by the parse function, and the matching URL
-// and extracted path are provided to this function. The filename is
-// defined as being everything from the last slash/backslash of the path
-// to the end of the path.
-//
-// The file name will be empty if the path is empty or there is nothing
-// following the last slash.
-//
-// The 8-bit version requires UTF-8 encoding.
-URL_EXPORT void ExtractFileName(const char* url,
-                                const Component& path,
-                                Component* file_name);
-URL_EXPORT void ExtractFileName(const base::char16* url,
-                                const Component& path,
-                                Component* file_name);
-
-// Extract the first key/value from the range defined by |*query|. Updates
-// |*query| to start at the end of the extracted key/value pair. This is
-// designed for use in a loop: you can keep calling it with the same query
-// object and it will iterate over all items in the query.
-//
-// Some key/value pairs may have the key, the value, or both be empty (for
-// example, the query string "?&"). These will be returned. Note that an empty
-// last parameter "foo.com?" or foo.com?a&" will not be returned, this case
-// is the same as "done."
-//
-// The initial query component should not include the '?' (this is the default
-// for parsed URLs).
-//
-// If no key/value are found |*key| and |*value| will be unchanged and it will
-// return false.
-URL_EXPORT bool ExtractQueryKeyValue(const char* url,
-                                     Component* query,
-                                     Component* key,
-                                     Component* value);
-URL_EXPORT bool ExtractQueryKeyValue(const base::char16* url,
-                                     Component* query,
-                                     Component* key,
-                                     Component* value);
-
-}  // namespace url_parse
+// TODO(tfarina): Remove this file when the callers are updated.
+#include "url/third_party/mozilla/url_parse.h"
 
 #endif  // URL_URL_PARSE_H_