Windows: Add support for unicode command lines

Summary:
The MSVCRT deliberately sends main() code-page specific characters.
This isn't too useful to LLVM as we end up converting the arguments to
UTF-16 and subsequently attempt to use the result as, for example, a
file name.  Instead, we need to have the ability to access the Unicode
command line and transform it to UTF-8.

This has the distinct advantage over using the MSVC-specific wmain()
function as our entry point because:
 - It doesn't work on cygwin.
 - It only work on MinGW with caveats and only then on certain versions.
 - We get to keep our entry point as main(). :)

N.B.  This patch includes fixes to other parts of lib/Support/Windows
s.t. we would be able to take advantage of getting the Unicode paths.
E.G.  clang spawning clang -cc1 would want to give it Unicode arguments.

Reviewers: aaron.ballman, Bigcheese, rnk, ruiu

Reviewed By: rnk

CC: llvm-commits, ygao

Differential Revision: http://llvm-reviews.chandlerc.com/D1834

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192069 91177308-0d34-0410-b5e6-96231b3b80d8

autoconf/configure.ac

@@ -1399,6 +1399,7 @@ AC_CHECK_LIB(m,sin)
 if test "$llvm_cv_os_type" = "MingW" ; then
   AC_CHECK_LIB(imagehlp, main)
   AC_CHECK_LIB(psapi, main)
+  AC_CHECK_LIB(shell32, main)
 fi
 
 dnl dlopen() is required for plugin support.

cmake/config-ix.cmake

@@ -415,6 +415,7 @@ endif ()
 if( MINGW )
   set(HAVE_LIBIMAGEHLP 1)
   set(HAVE_LIBPSAPI 1)
+  set(HAVE_LIBSHELL32 1)
   # TODO: Check existence of libraries.
   #   include(CheckLibraryExists)
   #   CHECK_LIBRARY_EXISTS(imagehlp ??? . HAVE_LIBIMAGEHLP)

cmake/modules/LLVM-Config.cmake

@@ -2,7 +2,7 @@ function(get_system_libs return_var)
   # Returns in `return_var' a list of system libraries used by LLVM.
   if( NOT MSVC )
     if( MINGW )
-      set(system_libs ${system_libs} imagehlp psapi)
+      set(system_libs ${system_libs} imagehlp psapi shell32)
     elseif( CMAKE_HOST_UNIX )
       if( HAVE_LIBRT )
         set(system_libs ${system_libs} rt)

cmake/modules/TableGen.cmake

@@ -128,7 +128,7 @@ macro(add_tablegen target project)
   endif()
 
   if( MINGW )
-    target_link_libraries(${target} imagehlp psapi)
+    target_link_libraries(${target} imagehlp psapi shell32)
     if(CMAKE_SIZEOF_VOID_P MATCHES "8")
       set_target_properties(${target} PROPERTIES LINK_FLAGS -Wl,--stack,16777216)
     endif(CMAKE_SIZEOF_VOID_P MATCHES "8")

include/llvm/Config/config.h.cmake

@@ -203,6 +203,9 @@
 /* Define to 1 if you have the `pthread' library (-lpthread). */
 #cmakedefine HAVE_LIBPTHREAD ${HAVE_LIBPTHREAD}
 
+/* Define to 1 if you have the `shell32' library (-lshell32). */
+#cmakedefine HAVE_LIBSHELL32 ${HAVE_LIBSHELL32}
+
 /* Define to 1 if you have the `udis86' library (-ludis86). */
 #undef HAVE_LIBUDIS86
 

include/llvm/Config/config.h.in

@@ -217,6 +217,9 @@
 /* Define to 1 if you have the `pthread' library (-lpthread). */
 #undef HAVE_LIBPTHREAD
 
+/* Define to 1 if you have the `shell32' library (-lshell32). */
+#undef HAVE_LIBSHELL32
+
 /* Define to 1 if you have the `udis86' library (-ludis86). */
 #undef HAVE_LIBUDIS86
 

include/llvm/Support/Process.h

@@ -25,8 +25,11 @@
 #ifndef LLVM_SUPPORT_PROCESS_H
 #define LLVM_SUPPORT_PROCESS_H
 
+#include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/Config/llvm-config.h"
+#include "llvm/Support/Allocator.h"
+#include "llvm/Support/system_error.h"
 #include "llvm/Support/DataTypes.h"
 #include "llvm/Support/TimeValue.h"
 
@@ -168,6 +171,14 @@ class Process {
   // string. \arg Name is assumed to be in UTF-8 encoding too.
   static Optional<std::string> GetEnv(StringRef name);
 
+  /// This function returns a SmallVector containing the arguments passed from
+  /// the operating system to the program.  This function expects to be handed
+  /// the vector passed in from main.
+  static error_code
+  GetArgumentVector(SmallVectorImpl<const char *> &Args,
+                    ArrayRef<const char *> ArgsFromMain,
+                    SpecificBumpPtrAllocator<char> &ArgAllocator);
+
   /// This function determines if the standard input is connected directly
   /// to a user's input (keyboard probably), rather than coming from a file
   /// or pipe.

lib/Support/Unix/Process.inc

@@ -190,6 +190,14 @@ Optional<std::string> Process::GetEnv(StringRef Name) {
   return std::string(Val);
 }
 
+error_code Process::GetArgumentVector(SmallVectorImpl<const char *> &ArgsOut,
+                                      ArrayRef<const char *> ArgsIn,
+                                      SpecificBumpPtrAllocator<char> &) {
+  ArgsOut.append(ArgsIn.begin(), ArgsIn.end());
+
+  return error_code::success();
+}
+
 bool Process::StandardInIsUserInput() {
   return FileDescriptorIsDisplayed(STDIN_FILENO);
 }

lib/Support/Windows/DynamicLibrary.inc

@@ -83,8 +83,15 @@ DynamicLibrary DynamicLibrary::getPermanentLibrary(const char *filename,
     // This is mostly to ensure that the return value still shows up as "valid".
     return DynamicLibrary(&OpenedHandles);
   }
+
+  SmallVector<wchar_t, MAX_PATH> filenameUnicode;
+  if (error_code ec = windows::UTF8ToUTF16(filename, filenameUnicode)) {
+    SetLastError(ec.value());
+    MakeErrMsg(errMsg, std::string(filename) + ": Can't convert to UTF-16: ");
+    return DynamicLibrary();
+  }
 
-  HMODULE a_handle = LoadLibrary(filename);
+  HMODULE a_handle = LoadLibraryW(filenameUnicode.data());
 
   if (a_handle == 0) {
     MakeErrMsg(errMsg, std::string(filename) + ": Can't open : ");

lib/Support/Windows/Path.inc

@@ -128,7 +128,7 @@ retry_random_path:
       BYTE val = 0;
       if (!::CryptGenRandom(CryptoProvider, 1, &val))
           return windows_error(::GetLastError());
-      random_path_utf16.push_back("0123456789abcdef"[val & 15]);
+      random_path_utf16.push_back(L"0123456789abcdef"[val & 15]);
     }
     else
       random_path_utf16.push_back(*i);
@@ -241,22 +241,23 @@ TimeValue file_status::getLastModificationTime() const {
 }
 
 error_code current_path(SmallVectorImpl<char> &result) {
-  SmallVector<wchar_t, 128> cur_path;
-  cur_path.reserve(128);
-retry_cur_dir:
-  DWORD len = ::GetCurrentDirectoryW(cur_path.capacity(), cur_path.data());
+  SmallVector<wchar_t, MAX_PATH> cur_path;
+  DWORD len = MAX_PATH;
 
-  // A zero return value indicates a failure other than insufficient space.
-  if (len == 0)
-    return windows_error(::GetLastError());
-
-  // If there's insufficient space, the len returned is larger than the len
-  // given.
-  if (len > cur_path.capacity()) {
+  do {
     cur_path.reserve(len);
-    goto retry_cur_dir;
-  }
+    len = ::GetCurrentDirectoryW(cur_path.capacity(), cur_path.data());
+
+    // A zero return value indicates a failure other than insufficient space.
+    if (len == 0)
+      return windows_error(::GetLastError());
+
+    // If there's insufficient space, the len returned is larger than the len
+    // given.
+  } while (len > cur_path.capacity());
 
+  // On success, GetCurrentDirectoryW returns the number of characters not
+  // including the null-terminator.
   cur_path.set_size(len);
   return UTF16ToUTF8(cur_path.begin(), cur_path.size(), result);
 }

lib/Support/Windows/Process.inc

@@ -11,18 +11,25 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/Support/Allocator.h"
+
 #include "Windows.h"
 #include <direct.h>
 #include <io.h>
 #include <malloc.h>
 #include <psapi.h>
+#include <Shellapi.h>
 
 #ifdef __MINGW32__
  #if (HAVE_LIBPSAPI != 1)
   #error "libpsapi.a should be present"
  #endif
+ #if (HAVE_LIBSHELL32 != 1)
+  #error "libshell32.a should be present"
+ #endif
 #else
- #pragma comment(lib, "psapi.lib")
+#pragma comment(lib, "psapi.lib")
+#pragma comment(lib, "Shell32.lib")
 #endif
 
 //===----------------------------------------------------------------------===//
@@ -151,25 +158,58 @@ Optional<std::string> Process::GetEnv(StringRef Name) {
   // Environment variable can be encoded in non-UTF8 encoding, and there's no
   // way to know what the encoding is. The only reliable way to look up
   // multibyte environment variable is to use GetEnvironmentVariableW().
-  std::vector<wchar_t> Buf(16);
-  size_t Size = 0;
-  for (;;) {
-    Size = GetEnvironmentVariableW(&NameUTF16[0], &Buf[0], Buf.size());
-    if (Size < Buf.size())
-      break;
+  SmallVector<wchar_t, MAX_PATH> Buf;
+  size_t Size = MAX_PATH;
+  do {
+    Buf.reserve(Size);
+    Size = GetEnvironmentVariableW(&NameUTF16[0], &Buf[0], Buf.capacity());
+    if (Size == 0)
+      return None;
+
     // Try again with larger buffer.
-    Buf.resize(Size + 1);
-  }
-  if (Size == 0)
-    return None;
+  } while (Size > Buf.capacity());
+  Buf.set_size(Size);
 
   // Convert the result from UTF-16 to UTF-8.
-  SmallVector<char, 128> Res;
+  SmallVector<char, MAX_PATH> Res;
   if (error_code ec = windows::UTF16ToUTF8(&Buf[0], Size, Res))
     return None;
   return std::string(&Res[0]);
 }
 
+error_code
+Process::GetArgumentVector(SmallVectorImpl<const char *> &Args,
+                           ArrayRef<const char *>,
+                           SpecificBumpPtrAllocator<char> &ArgAllocator) {
+  int NewArgCount;
+  error_code ec;
+
+  wchar_t **UnicodeCommandLine = CommandLineToArgvW(GetCommandLineW(),
+                                                    &NewArgCount);
+  if (!UnicodeCommandLine)
+    return windows_error(::GetLastError());
+
+  Args.reserve(NewArgCount);
+
+  for (int i = 0; i < NewArgCount; ++i) {
+    SmallVector<char, MAX_PATH> NewArgString;
+    ec = windows::UTF16ToUTF8(UnicodeCommandLine[i],
+                              wcslen(UnicodeCommandLine[i]),
+                              NewArgString);
+    if (ec)
+      break;
+
+    char *Buffer = ArgAllocator.Allocate(NewArgString.size() + 1);
+    ::memcpy(Buffer, NewArgString.data(), NewArgString.size() + 1);
+    Args.push_back(Buffer);
+  }
+  LocalFree(UnicodeCommandLine);
+  if (ec)
+    return ec;
+
+  return error_code::success();
+}
+
 bool Process::StandardInIsUserInput() {
   return FileDescriptorIsDisplayed(0);
 }