More UTF string conversion wrappers

Added new string conversion wrappers that convert between `std::string` (of UTF-8 bytes) and `std::wstring`, which is particularly useful for Win32 interop. Also fixed a missing string conversion for `getenv` on Win32, using these new wrappers.
The motivation behind this is to provide the support functions required for LLDB to work properly on Windows with non-ASCII data; however, the functions are not LLDB specific.

Patch by cameron314

Differential Revision: http://reviews.llvm.org/D17549

llvm-svn: 263247

1 files changed, 19 insertions, 0 deletions

diff --git a/llvm/lib/Support/CommandLine.cpp b/llvm/lib/Support/CommandLine.cpp
index c1615a0a683..b0867b453de 100644
--- a/llvm/lib/Support/CommandLine.cpp
+++ b/llvm/lib/Support/CommandLine.cpp
@@ -787,9 +787,28 @@ void cl::ParseEnvironmentOptions(const char *progName, const char *envVar,
   assert(envVar && "Environment variable name missing");
 
   // Get the environment variable they want us to parse options out of.
+#ifdef _WIN32
+  std::wstring wenvVar;
+  if (!llvm::ConvertUTF8toWide(envVar, wenvVar)) {
+    assert(false &&
+           "Unicode conversion of environment variable name failed");
+    return;
+  }
+  const wchar_t *wenvValue = _wgetenv(wenvVar.c_str());
+  if (!wenvValue)
+    return;
+  std::string envValueBuffer;
+  if (!llvm::convertWideToUTF8(wenvValue, envValueBuffer)) {
+    assert(false &&
+           "Unicode conversion of environment variable value failed");
+    return;
+  }
+  const char *envValue = envValueBuffer.c_str();
+#else
   const char *envValue = getenv(envVar);
   if (!envValue)
     return;
+#endif
 
   // Get program's "name", which we wouldn't know without the caller
   // telling us.