[libc] Implement strnlen.

[cgyurgyik]

Summary

Implementation for strnlen using memchr, with corresponding unit tests.

[sivachandra]

Can you also add the entries in config/spec/posix.td and config/linux/api.td files?

libc/src/string/strnlen.h

2

Clang format messed it up this way. Also in the .cpp fle.

[cgyurgyik]

In D84247#2165024, @sivachandra wrote:

Can you also add the entries in config/spec/posix.td and config/linux/api.td files?

Added, PTAL for correctness.

[sivachandra]

Please check if integration tests are OK (you need to run them without ASAN.) So, OK to land if integration tests are OK.

libc/config/linux/aarch64/entrypoints.txt

 set(TARGET_LIBC_ENTRYPOINTS
     # errno.h entrypoints
     libc.src.errno.__errno_location
 
     # string.h entrypoints
     libc.src.string.bzero
     libc.src.string.memcpy
     libc.src.string.memset
     libc.src.string.strcpy
     libc.src.string.strcat
     libc.src.string.strlen
     libc.src.string.memchr
     libc.src.string.strchr
     libc.src.string.strstr
+    libc.src.string.strnlen
 )
 
 set(TARGET_LIBM_ENTRYPOINTS
     # math.h entrypoints
     libc.src.math.copysign
     libc.src.math.copysignf
     libc.src.math.copysignl
     libc.src.math.ceil

libc/config/linux/api.td

let Functions = [
     "strcspn",
     "strpbrk",
     "strrchr",
     "strspn",
     "strstr",
     "strtok",
     "strerror",
     "strlen",
+    "strnlen"
   ];
 
   let TypeDeclarations = [
     SizeT,
   ];
 
   let Macros = [
     NullMacro,

libc/config/linux/x86_64/entrypoints.txt

set(TARGET_LIBC_ENTRYPOINTS
     libc.src.string.memset
     libc.src.string.strcpy
     libc.src.string.strcat
     libc.src.string.strlen
     libc.src.string.strcmp
     libc.src.string.memchr
     libc.src.string.strchr
     libc.src.string.strstr
+    libc.src.string.strnlen
 
     # sys/mman.h entrypoints
     libc.src.sys.mman.mmap
     libc.src.sys.mman.munmap
 
     # threads.h entrypoints
     libc.src.threads.call_once
     libc.src.threads.mtx_init

libc/spec/posix.td

 def SigSetType : NamedType<"sigset_t">;
 def SigSetPtrType : PtrType<SigSetType>;
 def ConstSigSetPtrType : ConstType<SigSetPtrType>;
 def RestrictSigSetType : RestrictedPtrType<SigSetType>;
 def ConstRestrictSigSetType : ConstType<RestrictSigSetType>;
 
 def StructSigaction : NamedType<"struct sigaction">;
 def StructSigactionPtr : PtrType<StructSigaction>;
 def ConstStructSigactionPtr : ConstType<StructSigactionPtr>;
 def RestrictStructSigactionPtr : RestrictedPtrType<StructSigaction>;
 def ConstRestrictStructSigactionPtr : ConstType<RestrictStructSigactionPtr>;
 
 def POSIX : StandardSpec<"POSIX"> {
+  PtrType CharPtr = PtrType<CharType>;
+  ConstType ConstCharPtr = ConstType<CharPtr>;
   NamedType OffTType = NamedType<"off_t">;
   NamedType SSizeTType = NamedType<"ssize_t">;
 
   HeaderSpec Errno = HeaderSpec<
       "errno.h",
       [
         Macro<"E2BIG">,
         Macro<"EACCES">,
HeaderSpec UniStd = HeaderSpec<
     [
         FunctionSpec<
           "write",
           RetValSpec<SSizeTType>,
           [ArgSpec<IntType>, ArgSpec<ConstVoidPtr>, ArgSpec<SizeTType>]
         >,
     ]
   >;
   
+  HeaderSpec String = HeaderSpec<
+    "string.h",
+    [
+        Macro<"NULL">,
+    ],
+    [
+        SizeTType,
+    ],
+    [], // Enumerations
+    [
+        FunctionSpec<
+            "strnlen",
+             RetValSpec<SizeTType>,
+             [ArgSpec<ConstCharPtr>, ArgSpec<SizeTType>]
+        >,
+    ]
+  >;
+
   let Headers = [
     Errno,
     SysMMan,
     Signal,
     UniStd,
+    String
   ];
 }

libc/src/string/CMakeLists.txt

 add_entrypoint_object(
   strstr
   SRCS
     strstr.cpp
   HDRS
     strstr.h
 )
 
+add_entrypoint_object(
+  strnlen
+  SRCS
+    strnlen.cpp
+  HDRS
+    strnlen.h
+  DEPENDS
+    .memchr
+)
+
 # Helper to define a function with multiple implementations
 # - Computes flags to satisfy required/rejected features and arch,
 # - Declares an entry point,
 # - Attach the REQUIRE_CPU_FEATURES property to the target,
 # - Add the fully qualified target to `${name}_implementations` global property for tests.
 function(add_implementation name impl_name)
   cmake_parse_arguments(
     "ADD_IMPL"

libc/src/string/strnlen.h

+//===-- Implementation header for strnlen ------------------------*- 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_STRNLEN_H
+#define LLVM_LIBC_SRC_STRING_STRNLEN_H
+
+#include <stddef.h>
+
+namespace __llvm_libc {
+
+size_t strnlen(const char *src, size_t n);
+
+} // namespace __llvm_libc
+
+#endif // LLVM_LIBC_SRC_STRING_STRNLEN_H

libc/src/string/strnlen.cpp

+//===-- Implementation of strnlen------------------------------------------===//
+//
+// 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/strnlen.h"
+
+#include "src/__support/common.h"
+#include "src/string/memchr.h"
+#include <stddef.h>
+
+namespace __llvm_libc {
+
+size_t LLVM_LIBC_ENTRYPOINT(strnlen)(const char *src, size_t n) {
+  const char *temp =
+      reinterpret_cast<char *>(__llvm_libc::memchr(src, '\0', n));
+  return temp ? temp - src : n;
+}
+
+} // namespace __llvm_libc

libc/test/src/string/CMakeLists.txt

add_libc_unittest(
   SUITE
     libc_string_unittests
   SRCS
     strstr_test.cpp
   DEPENDS
     libc.src.string.strstr
 )
 
+add_libc_unittest(
+  strnlen_test
+  SUITE
+    libc_string_unittests
+  SRCS
+    strnlen_test.cpp
+  DEPENDS
+    libc.src.string.strnlen
+)
+
 # Tests all implementations that can run on the host.
 function(add_libc_multi_impl_test name)
   get_property(fq_implementations GLOBAL PROPERTY ${name}_implementations)
   foreach(fq_config_name IN LISTS fq_implementations)
     get_target_property(required_cpu_features ${fq_config_name} REQUIRE_CPU_FEATURES)
     host_supports(can_run "${required_cpu_features}")
     if(can_run)
       add_libc_unittest(

libc/test/src/string/strnlen_test.cpp

+//===-- Unittests for strnlen----------------------------------------------===//
+//
+// 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/strnlen.h"
+#include "utils/UnitTest/Test.h"
+#include <stddef.h>
+
+TEST(StrNLenTest, EmptyString) {
+  const char *empty = "";
+  ASSERT_EQ(static_cast<size_t>(0), __llvm_libc::strnlen(empty, 0));
+  // If N is greater than string length, this should still return 0.
+  ASSERT_EQ(static_cast<size_t>(0), __llvm_libc::strnlen(empty, 1));
+}
+
+TEST(StrNLenTest, OneCharacterString) {
+  const char *single = "X";
+  ASSERT_EQ(static_cast<size_t>(1), __llvm_libc::strnlen(single, 1));
+  // If N is zero, this should return 0.
+  ASSERT_EQ(static_cast<size_t>(0), __llvm_libc::strnlen(single, 0));
+  // If N is greater than string length, this should still return 1.
+  ASSERT_EQ(static_cast<size_t>(1), __llvm_libc::strnlen(single, 2));
+}
+
+TEST(StrNLenTest, ManyCharacterString) {
+  const char *many = "123456789";
+  ASSERT_EQ(static_cast<size_t>(9), __llvm_libc::strnlen(many, 9));
+  // If N is smaller than the string length, it should return N.
+  ASSERT_EQ(static_cast<size_t>(3), __llvm_libc::strnlen(many, 3));
+  // If N is zero, this should return 0.
+  ASSERT_EQ(static_cast<size_t>(0), __llvm_libc::strnlen(many, 0));
+  // If N is greater than the string length, this should still return 9.
+  ASSERT_EQ(static_cast<size_t>(9), __llvm_libc::strnlen(many, 42));
+}
+
+TEST(StrNLenTest, CharactersAfterNullTerminatorShouldNotBeIncluded) {
+  const char str[5] = {'a', 'b', 'c', '\0', 'd'};
+  ASSERT_EQ(static_cast<size_t>(3), __llvm_libc::strnlen(str, 3));
+  // This should only read up to the null terminator.
+  ASSERT_EQ(static_cast<size_t>(3), __llvm_libc::strnlen(str, 4));
+  ASSERT_EQ(static_cast<size_t>(3), __llvm_libc::strnlen(str, 5));
+}