Add llvm::sys::fs::real_path.

LLVM already has real_path like functionality, but it is
cumbersome to use and involves clean up after (e.g. you have
to call openFileForRead, then close the resulting FD).

Furthermore, on Windows it doesn't work for directories since
opening a directory and opening a file require slightly
different flags.

So I add a simple function `real_path` which works for all
paths on all platforms and has a simple to use interface.

In doing so, I add the ability to opt in to resolving tilde
expressions (e.g. ~/foo), which are normally handled by
the shell.

Differential Revision: https://reviews.llvm.org/D30668

llvm-svn: 297483

4 files changed, 207 insertions, 16 deletions

diff --git a/llvm/include/llvm/Support/FileSystem.h b/llvm/include/llvm/Support/FileSystem.h
index 06b6c7c..7fa969d 100644
--- a/llvm/include/llvm/Support/FileSystem.h
+++ b/llvm/include/llvm/Support/FileSystem.h
@@ -339,6 +339,16 @@ std::error_code create_link(const Twine &to, const Twine &from);
 /// specific error_code.
 std::error_code create_hard_link(const Twine &to, const Twine &from);
 
+/// @brief Collapse all . and .. patterns, resolve all symlinks, and optionally
+///        expand ~ expressions to the user's home directory.
+///
+/// @param path The path to resolve.
+/// @param output The location to store the resolved path.
+/// @param expand_tilde If true, resolves ~ expressions to the user's home
+///                     directory.
+std::error_code real_path(const Twine &path, SmallVectorImpl<char> &output,
+                          bool expand_tilde = false);
+
 /// @brief Get the current path.
 ///
 /// @param result Holds the current path on return.
diff --git a/llvm/lib/Support/Unix/Path.inc b/llvm/lib/Support/Unix/Path.inc
index 43549c0..cdc692b 100644
--- a/llvm/lib/Support/Unix/Path.inc
+++ b/llvm/lib/Support/Unix/Path.inc
@@ -48,6 +48,8 @@
 # endif
 #endif
 
+#include <pwd.h>
+
 #ifdef __APPLE__
 #include <mach-o/dyld.h>
 #include <sys/attr.h>
@@ -478,6 +480,45 @@ std::error_code equivalent(const Twine &A, const Twine &B, bool &result) {
   return std::error_code();
 }
 
+static void expandTildeExpr(SmallVectorImpl<char> &Path) {
+  StringRef PathStr(Path.begin(), Path.size());
+  if (PathStr.empty() || !PathStr.startswith("~"))
+    return;
+
+  PathStr = PathStr.drop_front();
+  StringRef Expr = PathStr.take_until(path::is_separator);
+  StringRef Remainder = PathStr.substr(Expr.size() + 1);
+  SmallString<128> Storage;
+  if (Expr.empty()) {
+    // This is just ~/..., resolve it to the current user's home dir.
+    if (!path::home_directory(Storage)) {
+      // For some reason we couldn't get the home directory.  Just exit.
+      return;
+    }
+
+    // Overwrite the first character and insert the rest.
+    Path[0] = Storage[0];
+    Path.insert(Path.begin() + 1, Storage.begin() + 1, Storage.end());
+    return;
+  }
+
+  // This is a string of the form ~username/, look up this user's entry in the
+  // password database.
+  struct passwd *Entry = nullptr;
+  std::string User = Expr.str();
+  Entry = ::getpwnam(User.c_str());
+
+  if (!Entry) {
+    // Unable to look up the entry, just return back the original path.
+    return;
+  }
+
+  Storage = Remainder;
+  Path.clear();
+  Path.append(Entry->pw_dir, Entry->pw_dir + strlen(Entry->pw_dir));
+  llvm::sys::path::append(Path, Storage);
+}
+
 static std::error_code fillStatus(int StatRet, const struct stat &Status,
                              file_status &Result) {
   if (StatRet != 0) {
@@ -839,6 +880,28 @@ std::error_code remove_directories(const Twine &path, bool IgnoreErrors) {
   return std::error_code();
 }
 
+std::error_code real_path(const Twine &path, SmallVectorImpl<char> &dest,
+                          bool expand_tilde) {
+  dest.clear();
+  if (path.isTriviallyEmpty())
+    return std::error_code();
+
+  if (expand_tilde) {
+    SmallString<128> Storage;
+    path.toVector(Storage);
+    expandTildeExpr(Storage);
+    return real_path(Storage, dest, false);
+  }
+
+  int fd;
+  std::error_code EC = openFileForRead(path, fd, &dest);
+
+  if (EC)
+    return EC;
+  ::close(fd);
+  return std::error_code();
+}
+
 } // end namespace fs
 
 namespace path {
@@ -849,7 +912,6 @@ bool home_directory(SmallVectorImpl<char> &result) {
     result.append(RequestedDir, RequestedDir + strlen(RequestedDir));
     return true;
   }
-
   return false;
 }
 
diff --git a/llvm/lib/Support/Windows/Path.inc b/llvm/lib/Support/Windows/Path.inc
index dc69222..c758289 100644
--- a/llvm/lib/Support/Windows/Path.inc
+++ b/llvm/lib/Support/Windows/Path.inc
@@ -780,6 +780,52 @@ std::error_code detail::directory_iterator_increment(detail::DirIterState &it) {
   return std::error_code();
 }
 
+static std::error_code realPathFromHandle(HANDLE H,
+                                          SmallVectorImpl<char> &RealPath) {
+  RealPath.clear();
+  llvm::SmallVector<wchar_t, MAX_PATH> Buffer;
+  DWORD CountChars = ::GetFinalPathNameByHandleW(
+      H, Buffer.begin(), Buffer.capacity() - 1, FILE_NAME_NORMALIZED);
+  if (CountChars > Buffer.capacity()) {
+    // The buffer wasn't big enough, try again.  In this case the return value
+    // *does* indicate the size of the null terminator.
+    Buffer.reserve(CountChars);
+    CountChars = ::GetFinalPathNameByHandleW(
+        H, Buffer.data(), Buffer.capacity() - 1, FILE_NAME_NORMALIZED);
+  }
+  if (CountChars == 0)
+    return mapWindowsError(GetLastError());
+
+  const wchar_t *Data = Buffer.data();
+  if (CountChars >= 4) {
+    if (0 == ::memcmp(Data, L"\\\\?\\", 8)) {
+      CountChars -= 4;
+      Data += 4;
+    }
+  }
+
+  // Convert the result from UTF-16 to UTF-8.
+  return UTF16ToUTF8(Data, CountChars, RealPath);
+}
+
+static std::error_code directoryRealPath(const Twine &Name,
+                                         SmallVectorImpl<char> &RealPath) {
+  SmallVector<wchar_t, 128> PathUTF16;
+
+  if (std::error_code EC = widenPath(Name, PathUTF16))
+    return EC;
+
+  HANDLE H =
+      ::CreateFileW(PathUTF16.begin(), GENERIC_READ,
+                    FILE_SHARE_READ | FILE_SHARE_WRITE | FILE_SHARE_DELETE,
+                    NULL, OPEN_EXISTING, FILE_FLAG_BACKUP_SEMANTICS, NULL);
+  if (H == INVALID_HANDLE_VALUE)
+    return mapWindowsError(GetLastError());
+  std::error_code EC = realPathFromHandle(H, RealPath);
+  ::CloseHandle(H);
+  return EC;
+}
+
 std::error_code openFileForRead(const Twine &Name, int &ResultFD,
                                 SmallVectorImpl<char> *RealPath) {
   SmallVector<wchar_t, 128> PathUTF16;
@@ -811,23 +857,12 @@ std::error_code openFileForRead(const Twine &Name, int &ResultFD,
   }
 
   // Fetch the real name of the file, if the user asked
-  if (RealPath) {
-    RealPath->clear();
-    wchar_t RealPathUTF16[MAX_PATH];
-    DWORD CountChars =
-      ::GetFinalPathNameByHandleW(H, RealPathUTF16, MAX_PATH,
-                                  FILE_NAME_NORMALIZED);
-    if (CountChars > 0 && CountChars < MAX_PATH) {
-      // Convert the result from UTF-16 to UTF-8.
-      SmallString<MAX_PATH> RealPathUTF8;
-      if (!UTF16ToUTF8(RealPathUTF16, CountChars, RealPathUTF8))
-        RealPath->append(RealPathUTF8.data(),
-                         RealPathUTF8.data() + strlen(RealPathUTF8.data()));
-    }
-  }
+  std::error_code EC;
+  if (RealPath)
+    EC = realPathFromHandle(H, *RealPath);
 
   ResultFD = FD;
-  return std::error_code();
+  return EC;
 }
 
 std::error_code openFileForWrite(const Twine &Name, int &ResultFD,
@@ -949,6 +984,54 @@ std::error_code remove_directories(const Twine &path, bool IgnoreErrors) {
   return std::error_code();
 }
 
+static void expandTildeExpr(SmallVectorImpl<char> &Path) {
+  // Path does not begin with a tilde expression.
+  if (Path.empty() || Path[0] != '~')
+    return;
+
+  StringRef PathStr(Path.begin(), Path.size());
+  PathStr = PathStr.drop_front();
+  StringRef Expr = PathStr.take_until(path::is_separator);
+
+  if (!Expr.empty()) {
+    // This is probably a ~username/ expression.  Don't support this on Windows.
+    return;
+  }
+
+  SmallString<128> HomeDir;
+  if (!path::home_directory(HomeDir)) {
+    // For some reason we couldn't get the home directory.  Just exit.
+    return;
+  }
+
+  // Overwrite the first character and insert the rest.
+  Path[0] = HomeDir[0];
+  Path.insert(Path.begin() + 1, HomeDir.begin() + 1, HomeDir.end());
+}
+
+std::error_code real_path(const Twine &path, SmallVectorImpl<char> &dest,
+                          bool expand_tilde) {
+  dest.clear();
+  if (path.isTriviallyEmpty())
+    return std::error_code();
+
+  if (expand_tilde) {
+    SmallString<128> Storage;
+    path.toVector(Storage);
+    expandTildeExpr(Storage);
+    return real_path(Storage, dest, false);
+  }
+
+  if (is_directory(path))
+    return directoryRealPath(path, dest);
+
+  int fd;
+  if (std::error_code EC = llvm::sys::fs::openFileForRead(path, fd, &dest))
+    return EC;
+  ::close(fd);
+  return std::error_code();
+}
+
 } // end namespace fs
 
 namespace path {
diff --git a/llvm/unittests/Support/Path.cpp b/llvm/unittests/Support/Path.cpp
index 3ad7e70..571edaa 100644
--- a/llvm/unittests/Support/Path.cpp
+++ b/llvm/unittests/Support/Path.cpp
@@ -499,6 +499,42 @@ TEST_F(FileSystemTest, Unique) {
   ASSERT_NO_ERROR(fs::remove(TempPath));
 }
 
+TEST_F(FileSystemTest, RealPath) {
+  ASSERT_NO_ERROR(
+      fs::create_directories(Twine(TestDirectory) + "/test1/test2/test3"));
+  ASSERT_TRUE(fs::exists(Twine(TestDirectory) + "/test1/test2/test3"));
+
+  SmallString<64> RealBase;
+  SmallString<64> Expected;
+  SmallString<64> Actual;
+
+  // TestDirectory itself might be under a symlink or have been specified with
+  // a different case than the existing temp directory.  In such cases real_path
+  // on the concatenated path will differ in the TestDirectory portion from
+  // how we specified it.  Make sure to compare against the real_path of the
+  // TestDirectory, and not just the value of TestDirectory.
+  ASSERT_NO_ERROR(fs::real_path(TestDirectory, RealBase));
+  path::native(Twine(RealBase) + "/test1/test2", Expected);
+
+  ASSERT_NO_ERROR(fs::real_path(
+      Twine(TestDirectory) + "/././test1/../test1/test2/./test3/..", Actual));
+
+  EXPECT_EQ(Expected, Actual);
+
+  SmallString<64> HomeDir;
+  ASSERT_TRUE(llvm::sys::path::home_directory(HomeDir));
+  ASSERT_NO_ERROR(fs::real_path(HomeDir, Expected));
+  ASSERT_NO_ERROR(fs::real_path("~", Actual, true));
+  EXPECT_EQ(Expected, Actual);
+  ASSERT_NO_ERROR(fs::real_path("~/", Actual, true));
+  EXPECT_EQ(Expected, Actual);
+
+  fs::real_path(Twine(TestDirectory) + "/does_not_exist", Actual);
+  EXPECT_EQ("", Actual);
+
+  ASSERT_NO_ERROR(fs::remove_directories(Twine(TestDirectory) + "/test1"));
+}
+
 TEST_F(FileSystemTest, TempFiles) {
   // Create a temp file.
   int FileDescriptor;