Add basic char*_t support for libc (partial WG14 N2653) #90360

Febbe · 2024-04-27T21:22:40Z

This PR implements a part of WG14 N2653:

Define C23 char8_t
Define C11 char16_t
Define C11 char32_t

Missing goals are:
- The type of UTF-8 character literals is changed from unsigned char to char8_t. (Since UTF-8 character literals already have type unsigned char, this is not a semantic change).
- New mbrtoc8() and c8rtomb() functions declared in <uchar.h> enable conversions between multibyte characters and UTF-8.
- A new ATOMIC_CHAR8_T_LOCK_FREE macro.
- A new atomic_char8_t typedef name.

github-actions · 2024-04-27T21:22:59Z

Thank you for submitting a Pull Request (PR) to the LLVM Project!

This PR will be automatically labeled and the relevant teams will be
notified.

If you wish to, you can add reviewers by using the "Reviewers" section on this page.

If this is not working for you, it is probably because you do not have write
permissions for the repository. In which case you can instead tag reviewers by
name in a comment by using @ followed by their GitHub username.

If you have received no comments on your PR for a week, you can request a review
by "ping"ing the PR by adding a comment “Ping”. The common courtesy "ping" rate
is once a week. Please remember that you are asking for valuable time from other developers.

If you have further questions, they may be answered by the LLVM GitHub User Guide.

You can also ask questions in a comment on this PR, on the LLVM Discord or on the forums.

llvmbot · 2024-04-27T21:23:30Z

@llvm/pr-subscribers-libc

Author: Fabian Keßler (Febbe)

Changes

Define C23 char8_t
Define C11 char16_t
Define C11 char32_t

Full diff: https://github.com/llvm/llvm-project/pull/90360.diff

9 Files Affected:

(modified) libc/config/baremetal/api.td (+6-1)
(modified) libc/config/linux/x86_64/headers.txt (+1)
(modified) libc/include/CMakeLists.txt (+3)
(modified) libc/include/llvm-libc-types/CMakeLists.txt (+3)
(added) libc/include/llvm-libc-types/char16_t.h (+17)
(added) libc/include/llvm-libc-types/char32_t.h (+17)
(added) libc/include/llvm-libc-types/char8_t.h (+16)
(modified) libc/spec/spec.td (+3)
(modified) libc/spec/stdc.td (+3)

diff --git a/libc/config/baremetal/api.td b/libc/config/baremetal/api.td
index 25aa06aacb642e..a6547d843c85ee 100644
--- a/libc/config/baremetal/api.td
+++ b/libc/config/baremetal/api.td
@@ -85,5 +85,10 @@ def TimeAPI : PublicAPI<"time.h"> {
 }
 
 def UCharAPI : PublicAPI<"uchar.h"> {
-  let Types = ["mbstate_t"];
+  let Types = [
+    "mbstate_t",
+    "char8_t",
+    "char16_t",
+    "char32_t",
+  ];
 }
diff --git a/libc/config/linux/x86_64/headers.txt b/libc/config/linux/x86_64/headers.txt
index e51c7931942706..44d640b75e2bf7 100644
--- a/libc/config/linux/x86_64/headers.txt
+++ b/libc/config/linux/x86_64/headers.txt
@@ -29,6 +29,7 @@ set(TARGET_PUBLIC_HEADERS
     libc.include.time
     libc.include.unistd
     libc.include.wchar
+    libc.include.uchar
 
     libc.include.arpa_inet
 
diff --git a/libc/include/CMakeLists.txt b/libc/include/CMakeLists.txt
index aeef46aabfce5c..6dea8e539969d0 100644
--- a/libc/include/CMakeLists.txt
+++ b/libc/include/CMakeLists.txt
@@ -603,6 +603,9 @@ add_gen_header(
   DEPENDS
     .llvm_libc_common_h
     .llvm-libc-types.mbstate_t
+    .llvm-libc-types.char8_t
+    .llvm-libc-types.char16_t
+    .llvm-libc-types.char32_t
 )
 
 add_gen_header(
diff --git a/libc/include/llvm-libc-types/CMakeLists.txt b/libc/include/llvm-libc-types/CMakeLists.txt
index 310374fb62ffe0..c8999f3d25f4cd 100644
--- a/libc/include/llvm-libc-types/CMakeLists.txt
+++ b/libc/include/llvm-libc-types/CMakeLists.txt
@@ -90,6 +90,9 @@ add_header(tcflag_t HDR tcflag_t.h)
 add_header(struct_termios HDR struct_termios.h DEPENDS .cc_t .speed_t .tcflag_t)
 add_header(__getoptargv_t HDR __getoptargv_t.h)
 add_header(wchar_t HDR wchar_t.h)
+add_header(char8_t HDR char8_t.h)
+add_header(char16_t HDR char16_t.h)
+add_header(char32_t HDR char32_t.h)
 add_header(wint_t HDR wint_t.h)
 add_header(sa_family_t HDR sa_family_t.h)
 add_header(socklen_t HDR socklen_t.h)
diff --git a/libc/include/llvm-libc-types/char16_t.h b/libc/include/llvm-libc-types/char16_t.h
new file mode 100644
index 00000000000000..59810d0f6e5d85
--- /dev/null
+++ b/libc/include/llvm-libc-types/char16_t.h
@@ -0,0 +1,17 @@
+//===-- Definition of clock_t type ----------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIBC_TYPES_CHAR8_T_H
+#define LLVM_LIBC_TYPES_CHAR8_T_H
+
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
+#include <stdint.h>
+typedef uint_least16_t char16_t;
+#endif
+
+#endif // LLVM_LIBC_TYPES_CHAR8_T_H
\ No newline at end of file
diff --git a/libc/include/llvm-libc-types/char32_t.h b/libc/include/llvm-libc-types/char32_t.h
new file mode 100644
index 00000000000000..5cbd21e78a808a
--- /dev/null
+++ b/libc/include/llvm-libc-types/char32_t.h
@@ -0,0 +1,17 @@
+//===-- Definition of clock_t type ----------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIBC_TYPES_CHAR8_T_H
+#define LLVM_LIBC_TYPES_CHAR8_T_H
+
+#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
+#include <stdint.h>
+typedef uint_least32_t char32_t;
+#endif
+
+#endif // LLVM_LIBC_TYPES_CHAR8_T_H
\ No newline at end of file
diff --git a/libc/include/llvm-libc-types/char8_t.h b/libc/include/llvm-libc-types/char8_t.h
new file mode 100644
index 00000000000000..12972161c7e466
--- /dev/null
+++ b/libc/include/llvm-libc-types/char8_t.h
@@ -0,0 +1,16 @@
+//===-- Definition of clock_t type ----------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIBC_TYPES_CHAR8_T_H
+#define LLVM_LIBC_TYPES_CHAR8_T_H
+
+#if !defined(__cplusplus) && defined(__STDC_VERSION__) && __STDC_VERSION__ >= 202311L
+typedef unsigned char char8_t;
+#endif
+
+#endif // LLVM_LIBC_TYPES_CHAR8_T_H
\ No newline at end of file
diff --git a/libc/spec/spec.td b/libc/spec/spec.td
index 87bf4435e16724..ea8fa4cd373cf3 100644
--- a/libc/spec/spec.td
+++ b/libc/spec/spec.td
@@ -65,6 +65,9 @@ def SizeTType : NamedType<"size_t">;
 def SizeTPtr : PtrType<SizeTType>;
 def RestrictedSizeTPtr : RestrictedPtrType<SizeTType>;
 
+def Char8TType : NamedType<"char8_t">;
+def Char16TType : NamedType<"char16_t">;
+def Char32TType : NamedType<"char32_t">;
 def WCharType : NamedType<"wchar_t">;
 def WIntType : NamedType<"wint_t">;
 
diff --git a/libc/spec/stdc.td b/libc/spec/stdc.td
index 01aa7c70b3b9df..88758dec643fd4 100644
--- a/libc/spec/stdc.td
+++ b/libc/spec/stdc.td
@@ -1396,6 +1396,9 @@ def StdC : StandardSpec<"stdc"> {
       [], // Macros
       [ //Types
         MBStateTType,
+        Char8TType,
+        Char16TType,
+        Char32TType,
       ],
       [], // Enumerations
       []

github-actions · 2024-04-27T21:25:27Z

✅ With the latest revision this PR passed the C/C++ code formatter.

- Define C23 char8_t - Define C11 char16_t - Define C11 char32_t Preparation for functions like `mbrtoc8` and `c8rtomb` which are introduced in C23.

Febbe · 2024-04-28T11:12:40Z

@tahonermann I am asking for a review.

libc/config/baremetal/api.td

libc/include/llvm-libc-types/char16_t.h

libc/include/llvm-libc-types/char32_t.h

Febbe · 2024-04-29T21:20:10Z

Thank you for the feedback. I applied all of your changes and added uchar (and wchar) also to the list of included headers on linux-aarch, linux-arm, linux-riscv

michaelrj-google

Overall looks good with some minor style nits

libc/include/llvm-libc-types/CMakeLists.txt

libc/include/llvm-libc-types/char16_t.h

- headers fixed - included `stdint-macros.h` instead of `stdint.h` - Updated dependencies of `char16_t` and `char32_t` - Added uchar support for linux-riscv - Added uchar & wchar support for linux-arm & linux-aarch64 - Added UCharAPI type to linux/api.td

Febbe · 2024-04-30T19:28:01Z

Ok, now everything should be fixed. I can squash the commits together if that's desired. But I don't have merge rights, someone has to merge this.

michaelrj-google · 2024-04-30T22:08:24Z

Github automatically squashes, I can merge this for you.

github-actions · 2024-04-30T22:09:03Z

@Febbe Congratulations on having your first Pull Request (PR) merged into the LLVM Project!

Your changes will be combined with recent changes from other authors, then tested
by our build bots. If there is a problem with a build, you may receive a report in an email or a comment on this PR.

Please check whether problems have been caused by your change specifically, as
the builds can include changes from many authors. It is not uncommon for your
change to be included in a build that fails due to someone else's changes, or
infrastructure issues.

How to do this, and the rest of the post-merge process, is covered in detail here.

If your change does cause a problem, it may be reverted, or you can revert it yourself.
This is a normal part of LLVM development. You can fix your changes and open a new PR to merge them again.

If you don't get any reports, no action is required from you. Your changes are working as expected, well done!

llvmbot added the libc label Apr 27, 2024

Febbe force-pushed the Add-C23-char-_t-support branch from 68236e5 to c73c973 Compare April 28, 2024 09:29

Add basic char*_t support for libc

1a3366e

- Define C23 char8_t - Define C11 char16_t - Define C11 char32_t Preparation for functions like `mbrtoc8` and `c8rtomb` which are introduced in C23.

Febbe force-pushed the Add-C23-char-_t-support branch from c73c973 to 1a3366e Compare April 28, 2024 09:45

Febbe changed the title ~~Add basic char*_t support for libc~~ Add basic char*_t support for libc (partial WG14 N2653) Apr 28, 2024

check char*_t in the c23 status rst

5e96b86

michaelrj-google reviewed Apr 29, 2024

View reviewed changes

libc/config/baremetal/api.td Show resolved Hide resolved

libc/include/llvm-libc-types/char16_t.h Outdated Show resolved Hide resolved

libc/include/llvm-libc-types/char16_t.h Outdated Show resolved Hide resolved

lntue reviewed Apr 29, 2024

View reviewed changes

libc/include/llvm-libc-types/char32_t.h Outdated Show resolved Hide resolved

Febbe force-pushed the Add-C23-char-_t-support branch from 288221b to 40e9779 Compare April 29, 2024 21:18

michaelrj-google reviewed Apr 29, 2024

View reviewed changes

libc/include/llvm-libc-types/CMakeLists.txt Outdated Show resolved Hide resolved

libc/include/llvm-libc-types/char16_t.h Outdated Show resolved Hide resolved

Applied feedback

97ad4a7

- headers fixed - included `stdint-macros.h` instead of `stdint.h` - Updated dependencies of `char16_t` and `char32_t` - Added uchar support for linux-riscv - Added uchar & wchar support for linux-arm & linux-aarch64 - Added UCharAPI type to linux/api.td

Febbe force-pushed the Add-C23-char-_t-support branch from 40e9779 to 97ad4a7 Compare April 30, 2024 08:33

michaelrj-google merged commit cd7a7a5 into llvm:main Apr 30, 2024

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add basic char*_t support for libc (partial WG14 N2653) #90360

Add basic char*_t support for libc (partial WG14 N2653) #90360

Uh oh!

Febbe commented Apr 27, 2024 •

edited

Loading

Uh oh!

github-actions bot commented Apr 27, 2024

Uh oh!

llvmbot commented Apr 27, 2024

Uh oh!

github-actions bot commented Apr 27, 2024 •

edited

Loading

Uh oh!

Febbe commented Apr 28, 2024

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Febbe commented Apr 29, 2024

Uh oh!

michaelrj-google left a comment

Uh oh!

Uh oh!

Uh oh!

Febbe commented Apr 30, 2024

Uh oh!

michaelrj-google commented Apr 30, 2024

Uh oh!

github-actions bot commented Apr 30, 2024

Uh oh!

Uh oh!

Add basic char*_t support for libc (partial WG14 N2653) #90360

Add basic char*_t support for libc (partial WG14 N2653) #90360

Uh oh!

Conversation

Febbe commented Apr 27, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Apr 27, 2024

Uh oh!

llvmbot commented Apr 27, 2024

Uh oh!

github-actions bot commented Apr 27, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Febbe commented Apr 28, 2024

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Febbe commented Apr 29, 2024

Uh oh!

michaelrj-google left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Febbe commented Apr 30, 2024

Uh oh!

michaelrj-google commented Apr 30, 2024

Uh oh!

github-actions bot commented Apr 30, 2024

Uh oh!

Uh oh!

Febbe commented Apr 27, 2024 •

edited

Loading

github-actions bot commented Apr 27, 2024 •

edited

Loading