Improve long path name support on Windows.

Windows normally limits the length of an absolute path name to 260
characters; directories can have lower limits.  These limits increase
to about 32K if you use absolute paths with the special '\\?\'
prefix. Teach Support\Windows\Path.inc to use that prefix as needed.

TODO: Other parts of Support could also learn to use this prefix.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221841 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Support/Windows/Path.inc b/lib/Support/Windows/Path.inc
index d90d408e6618ce15ffdb8e27a20d9eb219f74cd4..140aadcfe66c0a026d9e9256e24ad1ce8480a999 100644 (file)
--- a/lib/Support/Windows/Path.inc
+++ b/lib/Support/Windows/Path.inc
@@ -59,6 +59,59 @@ static bool is_separator(const wchar_t value) {
   }
 }
 
   }
 }
 

+// Convert a UTF-8 path to UTF-16.  Also, if the absolute equivalent of the
+// path is longer than CreateDirectory can tolerate, make it absolute and
+// prefixed by '\\?\'.
+static std::error_code widenPath(const Twine &Path8,
+                                 SmallVectorImpl<wchar_t> &Path16) {
+  const size_t MaxDirLen = MAX_PATH - 12; // Must leave room for 8.3 filename.
+
+  // Several operations would convert Path8 to SmallString; more efficient to
+  // do it once up front.
+  SmallString<128> Path8Str;
+  Path8.toVector(Path8Str);
+
+  // If we made this path absolute, how much longer would it get?
+  size_t CurPathLen;
+  if (llvm::sys::path::is_absolute(Twine(Path8Str)))
+    CurPathLen = 0; // No contribution from current_path needed.
+  else {
+    CurPathLen = ::GetCurrentDirectoryW(0, NULL);
+    if (CurPathLen == 0)
+      return windows_error(::GetLastError());
+  }
+
+  // Would the absolute path be longer than our limit?
+  if ((Path8Str.size() + CurPathLen) >= MaxDirLen &&
+      !Path8Str.startswith("\\\\?\\")) {
+    SmallString<2*MAX_PATH> FullPath("\\\\?\\");
+    if (CurPathLen) {
+      SmallString<80> CurPath;
+      if (std::error_code EC = llvm::sys::fs::current_path(CurPath))
+        return EC;
+      FullPath.append(CurPath);
+    }
+    // Traverse the requested path, canonicalizing . and .. as we go (because
+    // the \\?\ prefix is documented to treat them as real components).
+    // The iterators don't report separators and append() always attaches
+    // preferred_separator so we don't need to call native() on the result.
+    for (llvm::sys::path::const_iterator I = llvm::sys::path::begin(Path8Str),
+                                         E = llvm::sys::path::end(Path8Str);
+                                         I != E; ++I) {
+      if (I->size() == 1 && *I == ".")
+        continue;
+      if (I->size() == 2 && *I == "..")
+        llvm::sys::path::remove_filename(FullPath);
+      else
+        llvm::sys::path::append(FullPath, *I);
+    }
+    return UTF8ToUTF16(FullPath, Path16);
+  }
+
+  // Just use the caller's original path.
+  return UTF8ToUTF16(Path8Str, Path16);
+}
+

 namespace llvm {
 namespace sys  {
 namespace fs {
 namespace llvm {
 namespace sys  {
 namespace fs {


@@ -130,11 +183,9 @@ std::error_code current_path(SmallVectorImpl<char> &result) {
 }
 
 std::error_code create_directory(const Twine &path, bool IgnoreExisting) {
 }
 
 std::error_code create_directory(const Twine &path, bool IgnoreExisting) {

-  SmallString<128> path_storage;

   SmallVector<wchar_t, 128> path_utf16;
 
   SmallVector<wchar_t, 128> path_utf16;
 

-  if (std::error_code ec =
-          UTF8ToUTF16(path.toStringRef(path_storage), path_utf16))
+  if (std::error_code ec = widenPath(path, path_utf16))

     return ec;
 
   if (!::CreateDirectoryW(path_utf16.begin(), NULL)) {
     return ec;
 
   if (!::CreateDirectoryW(path_utf16.begin(), NULL)) {


@@ -148,18 +199,12 @@ std::error_code create_directory(const Twine &path, bool IgnoreExisting) {
 
 // We can't use symbolic links for windows.
 std::error_code create_link(const Twine &to, const Twine &from) {
 
 // We can't use symbolic links for windows.
 std::error_code create_link(const Twine &to, const Twine &from) {

-  // Get arguments.
-  SmallString<128> from_storage;
-  SmallString<128> to_storage;
-  StringRef f = from.toStringRef(from_storage);
-  StringRef t = to.toStringRef(to_storage);
-

   // Convert to utf-16.
   SmallVector<wchar_t, 128> wide_from;
   SmallVector<wchar_t, 128> wide_to;
   // Convert to utf-16.
   SmallVector<wchar_t, 128> wide_from;
   SmallVector<wchar_t, 128> wide_to;

-  if (std::error_code ec = UTF8ToUTF16(f, wide_from))
+  if (std::error_code ec = widenPath(from, wide_from))

     return ec;
     return ec;

-  if (std::error_code ec = UTF8ToUTF16(t, wide_to))
+  if (std::error_code ec = widenPath(to, wide_to))

     return ec;
 
   if (!::CreateHardLinkW(wide_from.begin(), wide_to.begin(), NULL))
     return ec;
 
   if (!::CreateHardLinkW(wide_from.begin(), wide_to.begin(), NULL))


@@ -169,7 +214,6 @@ std::error_code create_link(const Twine &to, const Twine &from) {
 }
 
 std::error_code remove(const Twine &path, bool IgnoreNonExisting) {
 }
 
 std::error_code remove(const Twine &path, bool IgnoreNonExisting) {

-  SmallString<128> path_storage;

   SmallVector<wchar_t, 128> path_utf16;
 
   file_status ST;
   SmallVector<wchar_t, 128> path_utf16;
 
   file_status ST;


@@ -179,8 +223,7 @@ std::error_code remove(const Twine &path, bool IgnoreNonExisting) {
     return std::error_code();
   }
 
     return std::error_code();
   }
 

-  if (std::error_code ec =
-          UTF8ToUTF16(path.toStringRef(path_storage), path_utf16))
+  if (std::error_code ec = widenPath(path, path_utf16))

     return ec;
 
   if (ST.type() == file_type::directory_file) {
     return ec;
 
   if (ST.type() == file_type::directory_file) {


@@ -200,18 +243,12 @@ std::error_code remove(const Twine &path, bool IgnoreNonExisting) {
 }
 
 std::error_code rename(const Twine &from, const Twine &to) {
 }
 
 std::error_code rename(const Twine &from, const Twine &to) {

-  // Get arguments.
-  SmallString<128> from_storage;
-  SmallString<128> to_storage;
-  StringRef f = from.toStringRef(from_storage);
-  StringRef t = to.toStringRef(to_storage);
-

   // Convert to utf-16.
   SmallVector<wchar_t, 128> wide_from;
   SmallVector<wchar_t, 128> wide_to;
   // Convert to utf-16.
   SmallVector<wchar_t, 128> wide_from;
   SmallVector<wchar_t, 128> wide_to;

-  if (std::error_code ec = UTF8ToUTF16(f, wide_from))
+  if (std::error_code ec = widenPath(from, wide_from))

     return ec;
     return ec;

-  if (std::error_code ec = UTF8ToUTF16(t, wide_to))
+  if (std::error_code ec = widenPath(to, wide_to))

     return ec;
 
   std::error_code ec = std::error_code();
     return ec;
 
   std::error_code ec = std::error_code();


@@ -232,11 +269,9 @@ std::error_code rename(const Twine &from, const Twine &to) {
 }
 
 std::error_code resize_file(const Twine &path, uint64_t size) {
 }
 
 std::error_code resize_file(const Twine &path, uint64_t size) {

-  SmallString<128> path_storage;

   SmallVector<wchar_t, 128> path_utf16;
 
   SmallVector<wchar_t, 128> path_utf16;
 

-  if (std::error_code ec =
-          UTF8ToUTF16(path.toStringRef(path_storage), path_utf16))
+  if (std::error_code ec = widenPath(path, path_utf16))

     return ec;
 
   int fd = ::_wopen(path_utf16.begin(), O_BINARY | _O_RDWR, S_IWRITE);
     return ec;
 
   int fd = ::_wopen(path_utf16.begin(), O_BINARY | _O_RDWR, S_IWRITE);


@@ -252,11 +287,9 @@ std::error_code resize_file(const Twine &path, uint64_t size) {
 }
 
 std::error_code access(const Twine &Path, AccessMode Mode) {
 }
 
 std::error_code access(const Twine &Path, AccessMode Mode) {

-  SmallString<128> PathStorage;

   SmallVector<wchar_t, 128> PathUtf16;
 
   SmallVector<wchar_t, 128> PathUtf16;
 

-  if (std::error_code EC =
-          UTF8ToUTF16(Path.toStringRef(PathStorage), PathUtf16))
+  if (std::error_code EC = widenPath(Path, PathUtf16))

     return EC;
 
   DWORD Attributes = ::GetFileAttributesW(PathUtf16.begin());
     return EC;
 
   DWORD Attributes = ::GetFileAttributesW(PathUtf16.begin());


@@ -382,7 +415,7 @@ std::error_code status(const Twine &path, file_status &result) {
     return std::error_code();
   }
 
     return std::error_code();
   }
 

-  if (std::error_code ec = UTF8ToUTF16(path8, path_utf16))
+  if (std::error_code ec = widenPath(path8, path_utf16))

     return ec;
 
   DWORD attr = ::GetFileAttributesW(path_utf16.begin());
     return ec;
 
   DWORD attr = ::GetFileAttributesW(path_utf16.begin());


@@ -525,11 +558,10 @@ mapped_file_region::mapped_file_region(const Twine &path,
   , FileDescriptor()
   , FileHandle(INVALID_HANDLE_VALUE)
   , FileMappingHandle() {
   , FileDescriptor()
   , FileHandle(INVALID_HANDLE_VALUE)
   , FileMappingHandle() {

-  SmallString<128> path_storage;

   SmallVector<wchar_t, 128> path_utf16;
 
   // Convert path to UTF-16.
   SmallVector<wchar_t, 128> path_utf16;
 
   // Convert path to UTF-16.

-  if ((ec = UTF8ToUTF16(path.toStringRef(path_storage), path_utf16)))
+  if (ec = widenPath(path, path_utf16))

     return;
 
   // Get file handle for creating a file mapping.
     return;
 
   // Get file handle for creating a file mapping.


@@ -635,7 +667,7 @@ std::error_code detail::directory_iterator_construct(detail::DirIterState &it,
                                                 StringRef path){
   SmallVector<wchar_t, 128> path_utf16;
 
                                                 StringRef path){
   SmallVector<wchar_t, 128> path_utf16;
 

-  if (std::error_code ec = UTF8ToUTF16(path, path_utf16))
+  if (std::error_code ec = widenPath(path, path_utf16))

     return ec;
 
   // Convert path to the format that Windows is happy with.
     return ec;
 
   // Convert path to the format that Windows is happy with.


@@ -718,11 +750,9 @@ std::error_code detail::directory_iterator_increment(detail::DirIterState &it) {
 }
 
 std::error_code openFileForRead(const Twine &Name, int &ResultFD) {
 }
 
 std::error_code openFileForRead(const Twine &Name, int &ResultFD) {

-  SmallString<128> PathStorage;

   SmallVector<wchar_t, 128> PathUTF16;
 
   SmallVector<wchar_t, 128> PathUTF16;
 

-  if (std::error_code EC =
-          UTF8ToUTF16(Name.toStringRef(PathStorage), PathUTF16))
+  if (std::error_code EC = widenPath(Name, PathUTF16))

     return EC;
 
   HANDLE H = ::CreateFileW(PathUTF16.begin(), GENERIC_READ,
     return EC;
 
   HANDLE H = ::CreateFileW(PathUTF16.begin(), GENERIC_READ,


@@ -757,11 +787,9 @@ std::error_code openFileForWrite(const Twine &Name, int &ResultFD,
   assert((!(Flags & sys::fs::F_Excl) || !(Flags & sys::fs::F_Append)) &&
          "Cannot specify both 'excl' and 'append' file creation flags!");
 
   assert((!(Flags & sys::fs::F_Excl) || !(Flags & sys::fs::F_Append)) &&
          "Cannot specify both 'excl' and 'append' file creation flags!");
 

-  SmallString<128> PathStorage;

   SmallVector<wchar_t, 128> PathUTF16;
 
   SmallVector<wchar_t, 128> PathUTF16;
 

-  if (std::error_code EC =
-          UTF8ToUTF16(Name.toStringRef(PathStorage), PathUTF16))
+  if (std::error_code EC = widenPath(Name, PathUTF16))

     return EC;
 
   DWORD CreationDisposition;
     return EC;
 
   DWORD CreationDisposition;

diff --git a/unittests/Support/Path.cpp b/unittests/Support/Path.cpp
index ae4c9eb207fe95cd6ed35d6a60ae1b48a9fe4bf1..d7c216a5777e6b8b47f3a0bd5f781461b31ba746 100644 (file)
--- a/unittests/Support/Path.cpp
+++ b/unittests/Support/Path.cpp
@@ -16,6 +16,7 @@
 #include "gtest/gtest.h"
 
 #ifdef LLVM_ON_WIN32
 #include "gtest/gtest.h"
 
 #ifdef LLVM_ON_WIN32

+#include <Windows.h>

 #include <winerror.h>
 #endif
 
 #include <winerror.h>
 #endif
 


@@ -261,7 +262,7 @@ TEST(Support, HomeDirectory) {
 class FileSystemTest : public testing::Test {
 protected:
   /// Unique temporary directory in which all created filesystem entities must
 class FileSystemTest : public testing::Test {
 protected:
   /// Unique temporary directory in which all created filesystem entities must

-  /// be placed. It is recursively removed at the end of each test.
+  /// be placed. It is removed at the end of each test (must be empty).

   SmallString<128> TestDirectory;
 
   virtual void SetUp() {
   SmallString<128> TestDirectory;
 
   virtual void SetUp() {


@@ -397,7 +398,15 @@ TEST_F(FileSystemTest, TempFiles) {
     "abcdefghijklmnopqrstuvwxyz3abcdefghijklmnopqrstuvwxyz2"
     "abcdefghijklmnopqrstuvwxyz1abcdefghijklmnopqrstuvwxyz0";
   EXPECT_EQ(fs::createUniqueFile(Twine(Path270), FileDescriptor, TempPath),
     "abcdefghijklmnopqrstuvwxyz3abcdefghijklmnopqrstuvwxyz2"
     "abcdefghijklmnopqrstuvwxyz1abcdefghijklmnopqrstuvwxyz0";
   EXPECT_EQ(fs::createUniqueFile(Twine(Path270), FileDescriptor, TempPath),

-            errc::no_such_file_or_directory);
+            errc::invalid_argument);
+  // Relative path < 247 chars, no problem.
+  const char *Path216 =
+    "abcdefghijklmnopqrstuvwxyz7abcdefghijklmnopqrstuvwxyz6"
+    "abcdefghijklmnopqrstuvwxyz5abcdefghijklmnopqrstuvwxyz4"
+    "abcdefghijklmnopqrstuvwxyz3abcdefghijklmnopqrstuvwxyz2"
+    "abcdefghijklmnopqrstuvwxyz1abcdefghijklmnopqrstuvwxyz0";
+  ASSERT_NO_ERROR(fs::createTemporaryFile(Twine(Path216), "", TempPath));
+  ASSERT_NO_ERROR(fs::remove(Twine(TempPath)));

 #endif
 }
 
 #endif
 }
 


@@ -407,6 +416,54 @@ TEST_F(FileSystemTest, CreateDir) {
   ASSERT_EQ(fs::create_directory(Twine(TestDirectory) + "foo", false),
             errc::file_exists);
   ASSERT_NO_ERROR(fs::remove(Twine(TestDirectory) + "foo"));
   ASSERT_EQ(fs::create_directory(Twine(TestDirectory) + "foo", false),
             errc::file_exists);
   ASSERT_NO_ERROR(fs::remove(Twine(TestDirectory) + "foo"));

+
+#ifdef LLVM_ON_WIN32
+  // Prove that create_directories() can handle a pathname > 248 characters,
+  // which is the documented limit for CreateDirectory().
+  // (248 is MAX_PATH subtracting room for an 8.3 filename.)
+  // Generate a directory path guaranteed to fall into that range.
+  size_t TmpLen = TestDirectory.size();
+  const char *OneDir = "\\123456789";
+  size_t OneDirLen = strlen(OneDir);
+  ASSERT_LT(OneDirLen, 12);
+  size_t NLevels = ((248 - TmpLen) / OneDirLen) + 1;
+  SmallString<260> LongDir(TestDirectory);
+  for (size_t I = 0; I < NLevels; ++I)
+    LongDir.append(OneDir);
+  ASSERT_NO_ERROR(fs::create_directories(Twine(LongDir)));
+  ASSERT_NO_ERROR(fs::create_directories(Twine(LongDir)));
+  ASSERT_EQ(fs::create_directories(Twine(LongDir), false),
+            errc::file_exists);
+  // Tidy up, "recursively" removing the directories.
+  StringRef ThisDir(LongDir);
+  for (size_t J = 0; J < NLevels; ++J) {
+    ASSERT_NO_ERROR(fs::remove(ThisDir));
+    ThisDir = path::parent_path(ThisDir);
+  }
+
+  // Similarly for a relative pathname.  Need to set the current directory to
+  // TestDirectory so that the one we create ends up in the right place.
+  char PreviousDir[260];
+  size_t PreviousDirLen = ::GetCurrentDirectoryA(260, PreviousDir);
+  ASSERT_GT(PreviousDirLen, 0);
+  ASSERT_LT(PreviousDirLen, 260);
+  ASSERT_NE(::SetCurrentDirectoryA(TestDirectory.c_str()), 0);
+  LongDir.clear();
+  // Generate a relative directory name with absolute length > 248.
+  size_t LongDirLen = 249 - TestDirectory.size();
+  LongDir.assign(LongDirLen, 'a');
+  ASSERT_NO_ERROR(fs::create_directory(Twine(LongDir)));
+  // While we're here, prove that .. and . handling works in these long paths.
+  const char *DotDotDirs = "\\..\\.\\b";
+  LongDir.append(DotDotDirs);
+  ASSERT_NO_ERROR(fs::create_directory(Twine("b")));
+  ASSERT_EQ(fs::create_directory(Twine(LongDir), false), errc::file_exists);
+  // And clean up.
+  ASSERT_NO_ERROR(fs::remove(Twine("b")));
+  ASSERT_NO_ERROR(fs::remove(
+    Twine(LongDir.substr(0, LongDir.size() - strlen(DotDotDirs)))));
+  ASSERT_NE(::SetCurrentDirectoryA(PreviousDir), 0);
+#endif

 }
 
 TEST_F(FileSystemTest, DirectoryIteration) {
 }
 
 TEST_F(FileSystemTest, DirectoryIteration) {