[libc] Add support for 'string.h' locale variants #105719
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-libc Author: Joseph Huber (jhuber6) ChangesSummary: Full diff: https://github.com/llvm/llvm-project/pull/105719.diff 10 Files Affected:
diff --git a/libc/config/gpu/entrypoints.txt b/libc/config/gpu/entrypoints.txt
index 7b869902074d8e..8b7de6b93ec3b6 100644
--- a/libc/config/gpu/entrypoints.txt
+++ b/libc/config/gpu/entrypoints.txt
@@ -58,6 +58,7 @@ set(TARGET_LIBC_ENTRYPOINTS
libc.src.string.strchrnul
libc.src.string.strcmp
libc.src.string.strcoll
+ libc.src.string.strcoll_l
libc.src.string.strcpy
libc.src.string.strcspn
libc.src.string.strdup
@@ -79,6 +80,7 @@ set(TARGET_LIBC_ENTRYPOINTS
libc.src.string.strtok
libc.src.string.strtok_r
libc.src.string.strxfrm
+ libc.src.string.strxfrm_l
# stdbit.h entrypoints
libc.src.stdbit.stdc_bit_ceil_uc
diff --git a/libc/config/linux/x86_64/entrypoints.txt b/libc/config/linux/x86_64/entrypoints.txt
index bac1e3cfa85da7..1078b7882b1d0c 100644
--- a/libc/config/linux/x86_64/entrypoints.txt
+++ b/libc/config/linux/x86_64/entrypoints.txt
@@ -798,6 +798,10 @@ if(LLVM_LIBC_FULL_BUILD)
libc.src.ctype.tolower_l
libc.src.ctype.toupper_l
+ # string.h entrypoints
+ libc.src.string.strcoll_l
+ libc.src.string.strxfrm_l
+
# assert.h entrypoints
libc.src.assert.__assert_fail
diff --git a/libc/include/string.h.def b/libc/include/string.h.def
index 1bd2687db2beac..e180f0d2561d3a 100644
--- a/libc/include/string.h.def
+++ b/libc/include/string.h.def
@@ -11,6 +11,7 @@
#include "__llvm-libc-common.h"
+#include "llvm-libc-types/locale_t.h"
#include "llvm-libc-macros/null-macro.h"
%%public_api()
diff --git a/libc/newhdrgen/yaml/string.yaml b/libc/newhdrgen/yaml/string.yaml
index 1d6e64bfb9cf60..af1750e91243ea 100644
--- a/libc/newhdrgen/yaml/string.yaml
+++ b/libc/newhdrgen/yaml/string.yaml
@@ -144,6 +144,14 @@ functions:
arguments:
- type: const char *
- type: const char *
+ - name: strcoll_l
+ standards:
+ - stdc
+ return_type: int
+ arguments:
+ - type: const char *
+ - type: const char *
+ - type: locale_t
- name: strcpy
standards:
- stdc
@@ -300,3 +308,12 @@ functions:
- type: char *__restrict
- type: const char *__restrict
- type: size_t
+ - name: strxfrm_l
+ standards:
+ - stdc
+ return_type: size_t
+ arguments:
+ - type: char *__restrict
+ - type: const char *__restrict
+ - type: size_t
+ - type: locale_t
diff --git a/libc/spec/stdc.td b/libc/spec/stdc.td
index 6d8be9f8e4016d..d50823d6a4d3a6 100644
--- a/libc/spec/stdc.td
+++ b/libc/spec/stdc.td
@@ -354,6 +354,11 @@ def StdC : StandardSpec<"stdc"> {
RetValSpec<IntType>,
[ArgSpec<ConstCharPtr>, ArgSpec<ConstCharPtr>]
>,
+ FunctionSpec<
+ "strcoll_l",
+ RetValSpec<IntType>,
+ [ArgSpec<ConstCharPtr>, ArgSpec<ConstCharPtr>, ArgSpec<LocaleT>]
+ >,
FunctionSpec<
"strncmp",
RetValSpec<IntType>,
@@ -366,6 +371,14 @@ def StdC : StandardSpec<"stdc"> {
ArgSpec<ConstCharRestrictedPtr>,
ArgSpec<SizeTType>]
>,
+ FunctionSpec<
+ "strxfrm_l",
+ RetValSpec<SizeTType>,
+ [ArgSpec<CharRestrictedPtr>,
+ ArgSpec<ConstCharRestrictedPtr>,
+ ArgSpec<SizeTType>,
+ ArgSpec<LocaleT>]
+ >,
FunctionSpec<
"strchr",
RetValSpec<CharPtr>,
diff --git a/libc/src/string/CMakeLists.txt b/libc/src/string/CMakeLists.txt
index 56588ffafb86f0..787188ab3beb91 100644
--- a/libc/src/string/CMakeLists.txt
+++ b/libc/src/string/CMakeLists.txt
@@ -200,6 +200,14 @@ add_entrypoint_object(
strcoll.h
)
+add_entrypoint_object(
+ strcoll_l
+ SRCS
+ strcoll_l.cpp
+ HDRS
+ strcoll_l.h
+)
+
add_entrypoint_object(
strcpy
SRCS
@@ -441,6 +449,17 @@ add_entrypoint_object(
.memory_utils.inline_memcpy
)
+add_entrypoint_object(
+ strxfrm_l
+ SRCS
+ strxfrm_l.cpp
+ HDRS
+ strxfrm_l.h
+ DEPENDS
+ .string_utils
+ .memory_utils.inline_memcpy
+)
+
add_entrypoint_object(
memset_explicit
SRCS
diff --git a/libc/src/string/strcoll_l.cpp b/libc/src/string/strcoll_l.cpp
new file mode 100644
index 00000000000000..f664a3c7c03f37
--- /dev/null
+++ b/libc/src/string/strcoll_l.cpp
@@ -0,0 +1,24 @@
+//===-- Implementation of strcoll_l ---------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "src/string/strcoll_l.h"
+
+#include "src/__support/common.h"
+#include "src/__support/macros/config.h"
+
+namespace LIBC_NAMESPACE_DECL {
+
+// TODO: Add support for locales.
+LLVM_LIBC_FUNCTION(int, strcoll_l,
+ (const char *left, const char *right, locale_t)) {
+ for (; *left && *left == *right; ++left, ++right)
+ ;
+ return static_cast<int>(*left) - static_cast<int>(*right);
+}
+
+} // namespace LIBC_NAMESPACE_DECL
diff --git a/libc/src/string/strcoll_l.h b/libc/src/string/strcoll_l.h
new file mode 100644
index 00000000000000..97230fb811236c
--- /dev/null
+++ b/libc/src/string/strcoll_l.h
@@ -0,0 +1,21 @@
+//===-- Implementation header for strcoll_l ---------------------*- C++ -*-===//
+//
+// 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_SRC_STRING_STRCOLL_L_H
+#define LLVM_LIBC_SRC_STRING_STRCOLL_L_H
+
+#include "include/llvm-libc-types/locale_t.h"
+#include "src/__support/macros/config.h"
+
+namespace LIBC_NAMESPACE_DECL {
+
+int strcoll_l(const char *left, const char *right, locale_t locale);
+
+} // namespace LIBC_NAMESPACE_DECL
+
+#endif // LLVM_LIBC_SRC_STRING_STRCOLL_L_H
diff --git a/libc/src/string/strxfrm_l.cpp b/libc/src/string/strxfrm_l.cpp
new file mode 100644
index 00000000000000..ae758e1fcba6d8
--- /dev/null
+++ b/libc/src/string/strxfrm_l.cpp
@@ -0,0 +1,28 @@
+//===-- Implementation of strxfrm_l ---------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "src/string/strxfrm_l.h"
+#include "src/__support/macros/config.h"
+#include "src/string/memory_utils/inline_memcpy.h"
+#include "src/string/string_utils.h"
+
+#include "src/__support/common.h"
+
+namespace LIBC_NAMESPACE_DECL {
+
+// TODO: Add support for locales.
+LLVM_LIBC_FUNCTION(size_t, strxfrm_l,
+ (char *__restrict dest, const char *__restrict src, size_t n,
+ locale_t)) {
+ size_t len = internal::string_length(src);
+ if (n > len)
+ inline_memcpy(dest, src, len + 1);
+ return len;
+}
+
+} // namespace LIBC_NAMESPACE_DECL
diff --git a/libc/src/string/strxfrm_l.h b/libc/src/string/strxfrm_l.h
new file mode 100644
index 00000000000000..af0f181601184b
--- /dev/null
+++ b/libc/src/string/strxfrm_l.h
@@ -0,0 +1,23 @@
+//===-- Implementation header for strxfrm_l ---------------------*- C++ -*-===//
+//
+// 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_SRC_STRING_STRXFRM_L_H
+#define LLVM_LIBC_SRC_STRING_STRXFRM_L_H
+
+#include "include/llvm-libc-types/locale_t.h"
+#include "src/__support/macros/config.h"
+#include <stddef.h> // For size_t
+
+namespace LIBC_NAMESPACE_DECL {
+
+size_t strxfrm_l(char *__restrict dest, const char *__restrict src, size_t n,
+ locale_t locale);
+
+} // namespace LIBC_NAMESPACE_DECL
+
+#endif // LLVM_LIBC_SRC_STRING_STRXFRM_L_H
|
| // TODO: Add support for locales. | ||
| LLVM_LIBC_FUNCTION(int, strcoll_l, | ||
| (const char *left, const char *right, locale_t)) { | ||
| for (; *left && *left == *right; ++left, ++right) |
There was a problem hiding this comment.
should we add an assert to check that the locale passed is the default C locale?
There was a problem hiding this comment.
Do we expose asserts in entrypoints? I'm unsure if people would prefer it be ignored or terminate their program.
There was a problem hiding this comment.
That's fair, this is fine for now then. We should add something to the docs explaining that this is the behavior though.
|
ping |
michaelrj-google
approved these changes
Aug 28, 2024
Summary: This adds the locale variants of the string functions. As previously, these do not use the locale information at all and simply copy the non-locale version which expects the "C" locale.
s-barannikov
reviewed
May 9, 2025
| @@ -144,6 +144,14 @@ functions: | |||
| arguments: | |||
| - type: const char * | |||
| - type: const char * | |||
| - name: strcoll_l | |||
| standards: | |||
| - stdc | |||
There was a problem hiding this comment.
These two functions are POSIX (2008), not stdc.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
This adds the locale variants of the string functions. As previously,
these do not use the locale information at all and simply copy the
non-locale version which expects the "C" locale.