[llvm] [SystemZ][z/OS] Query if a file is text and set the text flag accordingly (PR #109664)

[Abhina Sree via llvm-commits]

https://github.com/abhina-sree created https://github.com/llvm/llvm-project/pull/109664

This patch sets the text flag correctly when opening files by querying the file tag on z/OS. For other platforms, there will be no change in behaviour.

>From 244ad16b5f64e38ef2470cf6cda1d0f8d3dc0d34 Mon Sep 17 00:00:00 2001
From: Abhina Sreeskantharajan <Abhina.Sreeskantharajan at ibm.com>
Date: Mon, 23 Sep 2024 09:39:45 -0400
Subject: [PATCH] Query if a file is text and set the text flag accordingly

---
 llvm/include/llvm/Support/AutoConvert.h |  6 ++++++
 llvm/lib/Support/AutoConvert.cpp        | 26 +++++++++++++++++++++++++
 llvm/lib/Support/VirtualFileSystem.cpp  | 10 +++++++++-
 3 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/llvm/include/llvm/Support/AutoConvert.h b/llvm/include/llvm/Support/AutoConvert.h
index 6f45c4683f7775..8ef6d3e8cf973e 100644
--- a/llvm/include/llvm/Support/AutoConvert.h
+++ b/llvm/include/llvm/Support/AutoConvert.h
@@ -52,6 +52,12 @@ std::error_code restorezOSStdHandleAutoConversion(int FD);
 /// \brief Set the tag information for a file descriptor.
 std::error_code setzOSFileTag(int FD, int CCSID, bool Text);
 
+// Get the the tag ccsid for a file name or a file descriptor.
+ErrorOr<__ccsid_t> getzOSFileTag(const char *FileName, const int FD = -1);
+
+// Query the file tag to determine if the file is a text file.
+ErrorOr<bool> iszOSTextFile(const char *Filename, const int FD = -1);
+
 } // namespace llvm
 #endif // __cplusplus
 
diff --git a/llvm/lib/Support/AutoConvert.cpp b/llvm/lib/Support/AutoConvert.cpp
index 66570735f8fc88..06130876c67f05 100644
--- a/llvm/lib/Support/AutoConvert.cpp
+++ b/llvm/lib/Support/AutoConvert.cpp
@@ -116,4 +116,30 @@ std::error_code llvm::setzOSFileTag(int FD, int CCSID, bool Text) {
   return std::error_code();
 }
 
+ErrorOr<__ccsid_t> llvm::getzOSFileTag(const char *FileName, const int FD) {
+  // If we have a file descriptor, use it to find out file tagging. Otherwise we
+  // need to use stat() with the file path.
+  if (FD != -1) {
+    struct f_cnvrt Query = {
+        QUERYCVT, // cvtcmd
+        0,        // pccsid
+        0,        // fccsid
+    };
+    if (fcntl(FD, F_CONTROL_CVT, &Query) == -1)
+      return std::error_code(errno, std::generic_category());
+    return Query.fccsid;
+  }
+  struct stat Attr;
+  if (stat(FileName, &Attr) == -1)
+    return std::error_code(errno, std::generic_category());
+  return Attr.st_tag.ft_ccsid;
+}
+
+ErrorOr<bool> llvm::iszOSTextFile(const char *Filename, const int FD) {
+  ErrorOr<__ccsid_t> Ccsid = getzOSFileTag(Filename, FD);
+  if (std::error_code EC = Ccsid.getError())
+    return EC;
+  return *Ccsid != FT_BINARY;
+}
+
 #endif // __MVS__
diff --git a/llvm/lib/Support/VirtualFileSystem.cpp b/llvm/lib/Support/VirtualFileSystem.cpp
index 928c0b5a24ed65..50aa60363db166 100644
--- a/llvm/lib/Support/VirtualFileSystem.cpp
+++ b/llvm/lib/Support/VirtualFileSystem.cpp
@@ -325,8 +325,16 @@ ErrorOr<Status> RealFileSystem::status(const Twine &Path) {
 ErrorOr<std::unique_ptr<File>>
 RealFileSystem::openFileForRead(const Twine &Name) {
   SmallString<256> RealName, Storage;
+  auto OpenFlags = sys::fs::OF_None;
+#ifdef __MVS__
+  // If the file is tagged with a text ccsid, it may require autoconversion.
+  llvm::ErrorOr<bool> IsFileText =
+      llvm::iszOSTextFile(Name.str().c_str());
+  if (IsFileText && *IsFileText)
+    OpenFlags |= sys::fs::OF_Text;
+#endif
   Expected<file_t> FDOrErr = sys::fs::openNativeFileForRead(
-      adjustPath(Name, Storage), sys::fs::OF_None, &RealName);
+      adjustPath(Name, Storage), OpenFlags, &RealName);
   if (!FDOrErr)
     return errorToErrorCode(FDOrErr.takeError());
   return std::unique_ptr<File>(