[llvm] f6eb5da - [Support] Fix Windows directory_iterator_construct out of bounds

[Andrew Ng via llvm-commits]

Author: Andrew Ng
Date: 2020-07-15T10:13:45+01:00
New Revision: f6eb5daa16368fb90d5a59b14a72bfd8ddbcd2a0

URL: https://github.com/llvm/llvm-project/commit/f6eb5daa16368fb90d5a59b14a72bfd8ddbcd2a0
DIFF: https://github.com/llvm/llvm-project/commit/f6eb5daa16368fb90d5a59b14a72bfd8ddbcd2a0.diff

LOG: [Support] Fix Windows directory_iterator_construct out of bounds

Fix incorrect use of the size of Path when accessing PathUTF16, as the
UTF-16 path can be shorter. Added unit test for coverage of this test
case.

Thanks to Ding Fei (danix800) for the code fix, see
https://reviews.llvm.org/D83321.

Differential Revision: https://reviews.llvm.org/D83689

Added: 
    

Modified: 
    llvm/lib/Support/Windows/Path.inc
    llvm/unittests/Support/Path.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Support/Windows/Path.inc b/llvm/lib/Support/Windows/Path.inc
index 399a0cc7a25c..e352beb77616 100644
--- a/llvm/lib/Support/Windows/Path.inc
+++ b/llvm/lib/Support/Windows/Path.inc
@@ -957,9 +957,9 @@ std::error_code detail::directory_iterator_construct(detail::DirIterState &IT,
     return EC;
 
   // Convert path to the format that Windows is happy with.
-  if (PathUTF16.size() > 0 &&
-      !is_separator(PathUTF16[Path.size() - 1]) &&
-      PathUTF16[Path.size() - 1] != L':') {
+  size_t PathUTF16Len = PathUTF16.size();
+  if (PathUTF16Len > 0 && !is_separator(PathUTF16[PathUTF16Len - 1]) &&
+      PathUTF16[PathUTF16Len - 1] != L':') {
     PathUTF16.push_back(L'\\');
     PathUTF16.push_back(L'*');
   } else {

diff  --git a/llvm/unittests/Support/Path.cpp b/llvm/unittests/Support/Path.cpp
index 6a228f093987..19ff49d25426 100644
--- a/llvm/unittests/Support/Path.cpp
+++ b/llvm/unittests/Support/Path.cpp
@@ -1149,6 +1149,39 @@ TEST_F(FileSystemTest, BrokenSymlinkDirectoryIteration) {
 }
 #endif
 
+#ifdef _WIN32
+TEST_F(FileSystemTest, UTF8ToUTF16DirectoryIteration) {
+  // The Windows filesystem support uses UTF-16 and converts paths from the
+  // input UTF-8. The UTF-16 equivalent of the input path can be shorter in
+  // length.
+
+  // This test relies on TestDirectory not being so long such that MAX_PATH
+  // would be exceeded (see widenPath). If that were the case, the UTF-16
+  // path is likely to be longer than the input.
+  const char *Pi = "\xcf\x80"; // UTF-8 lower case pi.
+  std::string RootDir = (TestDirectory + "/" + Pi).str();
+
+  // Create test directories.
+  ASSERT_NO_ERROR(fs::create_directories(Twine(RootDir) + "/a"));
+  ASSERT_NO_ERROR(fs::create_directories(Twine(RootDir) + "/b"));
+
+  std::error_code EC;
+  unsigned Count = 0;
+  for (fs::directory_iterator I(Twine(RootDir), EC), E; I != E;
+       I.increment(EC)) {
+    ASSERT_NO_ERROR(EC);
+    StringRef DirName = path::filename(I->path());
+    EXPECT_TRUE(DirName == "a" || DirName == "b");
+    ++Count;
+  }
+  EXPECT_EQ(Count, 2U);
+
+  ASSERT_NO_ERROR(fs::remove(Twine(RootDir) + "/a"));
+  ASSERT_NO_ERROR(fs::remove(Twine(RootDir) + "/b"));
+  ASSERT_NO_ERROR(fs::remove(Twine(RootDir)));
+}
+#endif
+
 TEST_F(FileSystemTest, Remove) {
   SmallString<64> BaseDir;
   SmallString<64> Paths[4];