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

1 files changed, 15 insertions, 14 deletions

diff --git a/lib/Support/Windows/Path.inc b/lib/Support/Windows/Path.inc
index 94a501b..998ec42 100644
--- a/lib/Support/Windows/Path.inc
+++ b/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);
 }