language_detection 0.0.1

data/.gitignore

@@ -0,0 +1,19 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+ext/cld/*.o
+ext/cld/*.a

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in language_detection.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Vojtech Hyza
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,85 @@
+# LanguageDetection
+
+Ruby bindings for Chromium Compact Language Detector ([source](http://src.chromium.org/viewvc/chrome/trunk/src/third_party/cld/)). This gem is using source codes from [chromium-compact-language-detector](http://code.google.com/p/chromium-compact-language-detector/) port.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'language_detection'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install language_detection
+
+## Usage
+
+```ruby
+>> require 'language_detection'
+=> true
+>> language = LanguageDetection.perform("This is some example text for language detection")
+=> {:name=>"ENGLISH", :code=>"en", :reliable=>true, :text_bytes=>51, :details=>[{:name=>"ENGLISH", :code=>"en", :percent=>100, :score=>49.43273905996759}]}
+>> language.name
+=> "ENGLISH"
+>> language.code
+=> "en"
+>> language.reliable
+=> true
+>> language.details # contains up to 3 languages sorted by score
+=> [{:name=>"ENGLISH", :code=>"en", :percent=>100, :score=>49.43273905996759}]
+>> language.details.first.percent
+=> 100
+>> language.details.first.score
+=> 49.43273905996759
+```
+
+the other way is to include `LanguageDetection` module in your class
+
+```ruby
+class Article
+  include LanguageDetection
+
+  attr_accessor :title, :content
+
+  def initialize(params = {})
+    @title   = params[:title]
+    @content = params[:content]
+  end
+
+  def to_s
+    "#{title}\n#{content}"
+  end
+end
+```
+
+which provides `Article#language` method using `Article#to_s` method as parameter
+
+```ruby
+>> article = Article.new :title => "Web development that doesn't hurt", :content => "Tens of thousands of Rails applications are already live..."
+>> article.language
+=> {:name=>"ENGLISH", :code=>"en", :reliable=>true, :text_bytes=>93, :details=>[{:name=>"ENGLISH", :code=>"en", :percent=>100, :score=>80.22690437601297}]}
+```
+
+or you can add `String#language` method by `require 'language_detection/string'`
+
+```ruby
+>> require 'language_detection'
+=> true
+>> require 'language_detection/string'
+=> true
+>> "Web development that doesn't hurt".language
+=> {:name=>"ENGLISH", :code=>"en", :reliable=>true, :text_bytes=>36, :details=>[{:name=>"ENGLISH", :code=>"en", :percent=>100, :score=>39.70826580226905}]}
+```
+
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,11 @@
+require "bundler/gem_tasks"
+
+task :default => :test
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.test_files = FileList['test/*_test.rb']
+  test.verbose = true
+  # test.warning = true
+end

data/ext/cld/Makefile

@@ -0,0 +1,34 @@
+# TODO: Generate Makefile
+
+CFLAGS=-fPIC -I. -O2 -DCLD_WINDOWS
+LDFLAGS=-L.
+CC=g++
+AR=ar
+
+SOURCES = encodings/compact_lang_det/cldutil.cc \
+          encodings/compact_lang_det/cldutil_dbg_empty.cc \
+          encodings/compact_lang_det/compact_lang_det.cc \
+          encodings/compact_lang_det/compact_lang_det_impl.cc \
+          encodings/compact_lang_det/ext_lang_enc.cc \
+          encodings/compact_lang_det/getonescriptspan.cc \
+          encodings/compact_lang_det/letterscript_enum.cc \
+          encodings/compact_lang_det/tote.cc \
+          encodings/compact_lang_det/generated/cld_generated_score_quadchrome_0406.cc \
+          encodings/compact_lang_det/generated/compact_lang_det_generated_cjkbis_0.cc \
+          encodings/compact_lang_det/generated/compact_lang_det_generated_ctjkvz.cc \
+          encodings/compact_lang_det/generated/compact_lang_det_generated_deltaoctachrome.cc \
+          encodings/compact_lang_det/generated/compact_lang_det_generated_quadschrome.cc \
+          encodings/compact_lang_det/win/cld_htmlutils_windows.cc \
+          encodings/compact_lang_det/win/cld_unilib_windows.cc \
+          encodings/compact_lang_det/win/cld_utf8statetable.cc \
+          encodings/compact_lang_det/win/cld_utf8utils_windows.cc \
+          encodings/internal/encodings.cc \
+          languages/internal/languages.cc \
+          language_detection.cc
+
+install:
+		rm -f *.o
+		rm -f libcld.a
+		$(CC) -c $(CFLAGS) $(SOURCES)
+		$(AR) rcs libcld.a *.o
+		$(CC) -DCLD_WINDOWS -I. -L. -shared -o cld.so -lstdc++ *.o

data/ext/cld/base/basictypes.h

@@ -0,0 +1,348 @@
+// Copyright (c) 2010 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 BASE_BASICTYPES_H_
+#define BASE_BASICTYPES_H_
+
+#include <limits.h>         // So we can set the bounds of our types
+#include <stddef.h>         // For size_t
+#include <string.h>         // for memcpy
+
+#include "base/port.h"    // Types that only need exist on certain systems
+
+#ifndef COMPILER_MSVC
+// stdint.h is part of C99 but MSVC doesn't have it.
+#include <stdint.h>         // For intptr_t.
+#endif
+
+typedef signed char         schar;
+typedef signed char         int8;
+typedef short               int16;
+// TODO(mbelshe) Remove these type guards.  These are
+//               temporary to avoid conflicts with npapi.h.
+#ifndef _INT32
+#define _INT32
+typedef int                 int32;
+#endif
+
+// The NSPR system headers define 64-bit as |long| when possible.  In order to
+// not have typedef mismatches, we do the same on LP64.
+#if __LP64__
+typedef long                int64;
+#else
+typedef long long           int64;
+#endif
+
+// NOTE: unsigned types are DANGEROUS in loops and other arithmetical
+// places.  Use the signed types unless your variable represents a bit
+// pattern (eg a hash value) or you really need the extra bit.  Do NOT
+// use 'unsigned' to express "this value should always be positive";
+// use assertions for this.
+
+typedef unsigned char      uint8;
+typedef unsigned short     uint16;
+// TODO(mbelshe) Remove these type guards.  These are
+//               temporary to avoid conflicts with npapi.h.
+#ifndef _UINT32
+#define _UINT32
+typedef unsigned int       uint32;
+#endif
+
+// See the comment above about NSPR and 64-bit.
+#if __LP64__
+typedef unsigned long uint64;
+#else
+typedef unsigned long long uint64;
+#endif
+
+// A type to represent a Unicode code-point value. As of Unicode 4.0,
+// such values require up to 21 bits.
+// (For type-checking on pointers, make this explicitly signed,
+// and it should always be the signed version of whatever int32 is.)
+typedef signed int         char32;
+
+const uint8  kuint8max  = (( uint8) 0xFF);
+const uint16 kuint16max = ((uint16) 0xFFFF);
+const uint32 kuint32max = ((uint32) 0xFFFFFFFF);
+const uint64 kuint64max = ((uint64) GG_LONGLONG(0xFFFFFFFFFFFFFFFF));
+const  int8  kint8min   = ((  int8) 0x80);
+const  int8  kint8max   = ((  int8) 0x7F);
+const  int16 kint16min  = (( int16) 0x8000);
+const  int16 kint16max  = (( int16) 0x7FFF);
+const  int32 kint32min  = (( int32) 0x80000000);
+const  int32 kint32max  = (( int32) 0x7FFFFFFF);
+const  int64 kint64min  = (( int64) GG_LONGLONG(0x8000000000000000));
+const  int64 kint64max  = (( int64) GG_LONGLONG(0x7FFFFFFFFFFFFFFF));
+
+// A macro to disallow the copy constructor and operator= functions
+// This should be used in the private: declarations for a class
+#define DISALLOW_COPY_AND_ASSIGN(TypeName) \
+  TypeName(const TypeName&);               \
+  void operator=(const TypeName&)
+
+// An older, deprecated, politically incorrect name for the above.
+#define DISALLOW_EVIL_CONSTRUCTORS(TypeName) DISALLOW_COPY_AND_ASSIGN(TypeName)
+
+// A macro to disallow all the implicit constructors, namely the
+// default constructor, copy constructor and operator= functions.
+//
+// This should be used in the private: declarations for a class
+// that wants to prevent anyone from instantiating it. This is
+// especially useful for classes containing only static methods.
+#define DISALLOW_IMPLICIT_CONSTRUCTORS(TypeName) \
+  TypeName();                                    \
+  DISALLOW_COPY_AND_ASSIGN(TypeName)
+
+// The arraysize(arr) macro returns the # of elements in an array arr.
+// The expression is a compile-time constant, and therefore can be
+// used in defining new arrays, for example.  If you use arraysize on
+// a pointer by mistake, you will get a compile-time error.
+//
+// One caveat is that arraysize() doesn't accept any array of an
+// anonymous type or a type defined inside a function.  In these rare
+// cases, you have to use the unsafe ARRAYSIZE_UNSAFE() macro below.  This is
+// due to a limitation in C++'s template system.  The limitation might
+// eventually be removed, but it hasn't happened yet.
+
+// This template function declaration is used in defining arraysize.
+// Note that the function doesn't need an implementation, as we only
+// use its type.
+template <typename T, size_t N>
+char (&ArraySizeHelper(T (&array)[N]))[N];
+
+// That gcc wants both of these prototypes seems mysterious. VC, for
+// its part, can't decide which to use (another mystery). Matching of
+// template overloads: the final frontier.
+#ifndef _MSC_VER
+template <typename T, size_t N>
+char (&ArraySizeHelper(const T (&array)[N]))[N];
+#endif
+
+#define arraysize(array) (sizeof(ArraySizeHelper(array)))
+
+// ARRAYSIZE_UNSAFE performs essentially the same calculation as arraysize,
+// but can be used on anonymous types or types defined inside
+// functions.  It's less safe than arraysize as it accepts some
+// (although not all) pointers.  Therefore, you should use arraysize
+// whenever possible.
+//
+// The expression ARRAYSIZE_UNSAFE(a) is a compile-time constant of type
+// size_t.
+//
+// ARRAYSIZE_UNSAFE catches a few type errors.  If you see a compiler error
+//
+//   "warning: division by zero in ..."
+//
+// when using ARRAYSIZE_UNSAFE, you are (wrongfully) giving it a pointer.
+// You should only use ARRAYSIZE_UNSAFE on statically allocated arrays.
+//
+// The following comments are on the implementation details, and can
+// be ignored by the users.
+//
+// ARRAYSIZE_UNSAFE(arr) works by inspecting sizeof(arr) (the # of bytes in
+// the array) and sizeof(*(arr)) (the # of bytes in one array
+// element).  If the former is divisible by the latter, perhaps arr is
+// indeed an array, in which case the division result is the # of
+// elements in the array.  Otherwise, arr cannot possibly be an array,
+// and we generate a compiler error to prevent the code from
+// compiling.
+//
+// Since the size of bool is implementation-defined, we need to cast
+// !(sizeof(a) & sizeof(*(a))) to size_t in order to ensure the final
+// result has type size_t.
+//
+// This macro is not perfect as it wrongfully accepts certain
+// pointers, namely where the pointer size is divisible by the pointee
+// size.  Since all our code has to go through a 32-bit compiler,
+// where a pointer is 4 bytes, this means all pointers to a type whose
+// size is 3 or greater than 4 will be (righteously) rejected.
+
+#define ARRAYSIZE_UNSAFE(a) \
+  ((sizeof(a) / sizeof(*(a))) / \
+   static_cast<size_t>(!(sizeof(a) % sizeof(*(a)))))
+
+
+// Use implicit_cast as a safe version of static_cast or const_cast
+// for upcasting in the type hierarchy (i.e. casting a pointer to Foo
+// to a pointer to SuperclassOfFoo or casting a pointer to Foo to
+// a const pointer to Foo).
+// When you use implicit_cast, the compiler checks that the cast is safe.
+// Such explicit implicit_casts are necessary in surprisingly many
+// situations where C++ demands an exact type match instead of an
+// argument type convertable to a target type.
+//
+// The From type can be inferred, so the preferred syntax for using
+// implicit_cast is the same as for static_cast etc.:
+//
+//   implicit_cast<ToType>(expr)
+//
+// implicit_cast would have been part of the C++ standard library,
+// but the proposal was submitted too late.  It will probably make
+// its way into the language in the future.
+template<typename To, typename From>
+inline To implicit_cast(From const &f) {
+  return f;
+}
+
+// The COMPILE_ASSERT macro can be used to verify that a compile time
+// expression is true. For example, you could use it to verify the
+// size of a static array:
+//
+//   COMPILE_ASSERT(ARRAYSIZE_UNSAFE(content_type_names) == CONTENT_NUM_TYPES,
+//                  content_type_names_incorrect_size);
+//
+// or to make sure a struct is smaller than a certain size:
+//
+//   COMPILE_ASSERT(sizeof(foo) < 128, foo_too_large);
+//
+// The second argument to the macro is the name of the variable. If
+// the expression is false, most compilers will issue a warning/error
+// containing the name of the variable.
+
+template <bool>
+struct CompileAssert {
+};
+
+#undef COMPILE_ASSERT
+#define COMPILE_ASSERT(expr, msg) \
+  typedef CompileAssert<(bool(expr))> msg[bool(expr) ? 1 : -1]
+
+// Implementation details of COMPILE_ASSERT:
+//
+// - COMPILE_ASSERT works by defining an array type that has -1
+//   elements (and thus is invalid) when the expression is false.
+//
+// - The simpler definition
+//
+//     #define COMPILE_ASSERT(expr, msg) typedef char msg[(expr) ? 1 : -1]
+//
+//   does not work, as gcc supports variable-length arrays whose sizes
+//   are determined at run-time (this is gcc's extension and not part
+//   of the C++ standard).  As a result, gcc fails to reject the
+//   following code with the simple definition:
+//
+//     int foo;
+//     COMPILE_ASSERT(foo, msg); // not supposed to compile as foo is
+//                               // not a compile-time constant.
+//
+// - By using the type CompileAssert<(bool(expr))>, we ensures that
+//   expr is a compile-time constant.  (Template arguments must be
+//   determined at compile-time.)
+//
+// - The outter parentheses in CompileAssert<(bool(expr))> are necessary
+//   to work around a bug in gcc 3.4.4 and 4.0.1.  If we had written
+//
+//     CompileAssert<bool(expr)>
+//
+//   instead, these compilers will refuse to compile
+//
+//     COMPILE_ASSERT(5 > 0, some_message);
+//
+//   (They seem to think the ">" in "5 > 0" marks the end of the
+//   template argument list.)
+//
+// - The array size is (bool(expr) ? 1 : -1), instead of simply
+//
+//     ((expr) ? 1 : -1).
+//
+//   This is to avoid running into a bug in MS VC 7.1, which
+//   causes ((0.0) ? 1 : -1) to incorrectly evaluate to 1.
+
+
+// MetatagId refers to metatag-id that we assign to
+// each metatag <name, value> pair..
+typedef uint32 MetatagId;
+
+// Argument type used in interfaces that can optionally take ownership
+// of a passed in argument.  If TAKE_OWNERSHIP is passed, the called
+// object takes ownership of the argument.  Otherwise it does not.
+enum Ownership {
+  DO_NOT_TAKE_OWNERSHIP,
+  TAKE_OWNERSHIP
+};
+
+// bit_cast<Dest,Source> is a template function that implements the
+// equivalent of "*reinterpret_cast<Dest*>(&source)".  We need this in
+// very low-level functions like the protobuf library and fast math
+// support.
+//
+//   float f = 3.14159265358979;
+//   int i = bit_cast<int32>(f);
+//   // i = 0x40490fdb
+//
+// The classical address-casting method is:
+//
+//   // WRONG
+//   float f = 3.14159265358979;            // WRONG
+//   int i = * reinterpret_cast<int*>(&f);  // WRONG
+//
+// The address-casting method actually produces undefined behavior
+// according to ISO C++ specification section 3.10 -15 -.  Roughly, this
+// section says: if an object in memory has one type, and a program
+// accesses it with a different type, then the result is undefined
+// behavior for most values of "different type".
+//
+// This is true for any cast syntax, either *(int*)&f or
+// *reinterpret_cast<int*>(&f).  And it is particularly true for
+// conversions betweeen integral lvalues and floating-point lvalues.
+//
+// The purpose of 3.10 -15- is to allow optimizing compilers to assume
+// that expressions with different types refer to different memory.  gcc
+// 4.0.1 has an optimizer that takes advantage of this.  So a
+// non-conforming program quietly produces wildly incorrect output.
+//
+// The problem is not the use of reinterpret_cast.  The problem is type
+// punning: holding an object in memory of one type and reading its bits
+// back using a different type.
+//
+// The C++ standard is more subtle and complex than this, but that
+// is the basic idea.
+//
+// Anyways ...
+//
+// bit_cast<> calls memcpy() which is blessed by the standard,
+// especially by the example in section 3.9 .  Also, of course,
+// bit_cast<> wraps up the nasty logic in one place.
+//
+// Fortunately memcpy() is very fast.  In optimized mode, with a
+// constant size, gcc 2.95.3, gcc 4.0.1, and msvc 7.1 produce inline
+// code with the minimal amount of data movement.  On a 32-bit system,
+// memcpy(d,s,4) compiles to one load and one store, and memcpy(d,s,8)
+// compiles to two loads and two stores.
+//
+// I tested this code with gcc 2.95.3, gcc 4.0.1, icc 8.1, and msvc 7.1.
+//
+// WARNING: if Dest or Source is a non-POD type, the result of the memcpy
+// is likely to surprise you.
+
+template <class Dest, class Source>
+inline Dest bit_cast(const Source& source) {
+  // Compile time assertion: sizeof(Dest) == sizeof(Source)
+  // A compile error here means your Dest and Source have different sizes.
+  typedef char VerifySizesAreEqual [sizeof(Dest) == sizeof(Source) ? 1 : -1];
+
+  Dest dest;
+  memcpy(&dest, &source, sizeof(dest));
+  return dest;
+}
+
+// The following enum should be used only as a constructor argument to indicate
+// that the variable has static storage class, and that the constructor should
+// do nothing to its state.  It indicates to the reader that it is legal to
+// declare a static instance of the class, provided the constructor is given
+// the base::LINKER_INITIALIZED argument.  Normally, it is unsafe to declare a
+// static variable that has a constructor or a destructor because invocation
+// order is undefined.  However, IF the type can be initialized by filling with
+// zeroes (which the loader does for static variables), AND the destructor also
+// does nothing to the storage, AND there are no virtual methods, then a
+// constructor declared as
+//       explicit MyClass(base::LinkerInitialized x) {}
+// and invoked as
+//       static MyClass my_variable_name(base::LINKER_INITIALIZED);
+namespace base {
+enum LinkerInitialized { LINKER_INITIALIZED };
+}  // base
+
+
+#endif  // BASE_BASICTYPES_H_

data/ext/cld/base/build_config.h

@@ -0,0 +1,124 @@
+// Copyright (c) 2011 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.
+
+// This file adds defines about the platform we're currently building on.
+//  Operating System:
+//    OS_WIN / OS_MACOSX / OS_LINUX / OS_POSIX (MACOSX or LINUX)
+//  Compiler:
+//    COMPILER_MSVC / COMPILER_GCC
+//  Processor:
+//    ARCH_CPU_X86 / ARCH_CPU_X86_64 / ARCH_CPU_X86_FAMILY (X86 or X86_64)
+//    ARCH_CPU_32_BITS / ARCH_CPU_64_BITS
+
+#ifndef BUILD_BUILD_CONFIG_H_
+#define BUILD_BUILD_CONFIG_H_
+
+// A set of macros to use for platform detection.
+#if defined(__APPLE__)
+#define OS_MACOSX 1
+#elif defined(__linux__)
+#define OS_LINUX 1
+// Use TOOLKIT_GTK on linux if TOOLKIT_VIEWS isn't defined.
+#if !defined(TOOLKIT_VIEWS)
+#define TOOLKIT_GTK
+#endif
+#elif defined(_WIN32)
+#define OS_WIN 1
+#define TOOLKIT_VIEWS 1
+#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
+#define OS_FREEBSD 1
+#define TOOLKIT_GTK
+#elif defined(__NetBSD__)
+#define OS_NETBSD 1
+#define TOOLKIT_GTK
+#elif defined(__OpenBSD__)
+#define OS_OPENBSD 1
+#define TOOLKIT_GTK
+#elif defined(__DragonFly__)
+#define OS_DRAGONFLY 1
+#define TOOLKIT_GTK
+#elif defined(__sun)
+#define OS_SOLARIS 1
+#define TOOLKIT_GTK
+#else
+#error Please add support for your platform in build/build_config.h
+#endif
+
+// A flag derived from the above flags, used to cover GTK code in
+// both TOOLKIT_GTK and TOOLKIT_VIEWS.
+#if defined(TOOLKIT_GTK) || (defined(TOOLKIT_VIEWS) && !defined(OS_WIN))
+#define TOOLKIT_USES_GTK 1
+#endif
+
+#if defined(OS_LINUX) || defined(OS_FREEBSD) || defined(OS_OPENBSD) || defined(OS_NETBSD) || defined(OS_DRAGONFLY)
+#define USE_NSS 1  // Use NSS for crypto.
+#define USE_X11 1  // Use X for graphics.
+#endif
+
+// For access to standard POSIXish features, use OS_POSIX instead of a
+// more specific macro.
+#if defined(OS_MACOSX) || defined(OS_LINUX) || defined(OS_FREEBSD) || defined(OS_OPENBSD) || defined(OS_NETBSD) || defined(OS_SOLARIS) || defined(OS_DRAGONFLY)
+#define OS_POSIX 1
+// Use base::DataPack for name/value pairs.
+#define USE_BASE_DATA_PACK 1
+#endif
+
+// Use tcmalloc
+#if defined(OS_WIN) && ! defined(NO_TCMALLOC)
+#define USE_TCMALLOC 1
+#endif
+
+// Compiler detection.
+#if defined(__GNUC__)
+#define COMPILER_GCC 1
+#elif defined(_MSC_VER)
+#define COMPILER_MSVC 1
+#else
+#error Please add support for your compiler in build/build_config.h
+#endif
+
+// Processor architecture detection.  For more info on what's defined, see:
+//   http://msdn.microsoft.com/en-us/library/b0084kay.aspx
+//   http://www.agner.org/optimize/calling_conventions.pdf
+//   or with gcc, run: "echo | gcc -E -dM -"
+#if defined(_M_X64) || defined(__x86_64__)
+#define ARCH_CPU_X86_FAMILY 1
+#define ARCH_CPU_X86_64 1
+#define ARCH_CPU_64_BITS 1
+#elif defined(_M_IX86) || defined(__i386__)
+#define ARCH_CPU_X86_FAMILY 1
+#define ARCH_CPU_X86 1
+#define ARCH_CPU_32_BITS 1
+#elif defined(__ARMEL__)
+#define ARCH_CPU_ARM_FAMILY 1
+#define ARCH_CPU_ARMEL 1
+#define ARCH_CPU_32_BITS 1
+#define WCHAR_T_IS_UNSIGNED 1
+#elif defined(__ARCH_PPC) || defined(__ppc__)
+#define ARCH_CPU_PPC_FAMILY 1
+#define ARCH_CPU_32_BITS 1
+#else
+#error Please add support for your architecture in build/build_config.h
+#endif
+
+// Type detection for wchar_t.
+#if defined(OS_WIN)
+#define WCHAR_T_IS_UTF16
+#elif defined(OS_POSIX) && defined(COMPILER_GCC) && \
+    defined(__WCHAR_MAX__) && \
+    (__WCHAR_MAX__ == 0x7fffffff || __WCHAR_MAX__ == 0xffffffff)
+#define WCHAR_T_IS_UTF32
+#elif defined(OS_POSIX) && defined(COMPILER_GCC) && \
+    defined(__WCHAR_MAX__) && \
+    (__WCHAR_MAX__ == 0x7fff || __WCHAR_MAX__ == 0xffff)
+// On Posix, we'll detect short wchar_t, but projects aren't guaranteed to
+// compile in this mode (in particular, Chrome doesn't). This is intended for
+// other projects using base who manage their own dependencies and make sure
+// short wchar works for them.
+#define WCHAR_T_IS_UTF16
+#else
+#error Please add support for your compiler in build/build_config.h
+#endif
+
+#endif  // BUILD_BUILD_CONFIG_H_