Implement the ? format specifier for strings and characters

stl/inc/chrono

@@ -4685,17 +4685,6 @@ namespace chrono {
 #ifdef __cpp_lib_concepts
   // [time.format]
 
-template <class _CharT>
-_NODISCARD constexpr const _CharT* _Choose_literal(const char* const _Str, const wchar_t* const _WStr) noexcept {
-    if constexpr (is_same_v<_CharT, char>) {
-        return _Str;
-    } else {
-        return _WStr;
-    }
-}
-
-#define _STATICALLY_WIDEN(_CharT, _Literal) (_Choose_literal<_CharT>(_Literal, L##_Literal))
-
 // clang-format off
 template <class _Ty, class _CharT>
 concept _Chrono_parse_spec_callbacks = _Parse_align_callbacks<_Ty, _CharT>
@@ -6031,8 +6020,6 @@ inline namespace literals {
 } // namespace literals
 #endif // _HAS_CXX20
 
-#undef _STATICALLY_WIDEN
-
 _STD_END
 #pragma pop_macro("new")
 _STL_RESTORE_CLANG_WARNINGS

stl/inc/yvals_core.h

@@ -337,6 +337,8 @@
 // P2186R2 Removing Garbage Collection Support
 // P2273R3 constexpr unique_ptr
 // P2278R4 cbegin Should Always Return A Constant Iterator
+// P2286R8 Formatting Ranges
+//     (only the '?' format specifier for strings and characters)
 // P2291R3 constexpr Integral <charconv>
 // P2302R4 ranges::contains, ranges::contains_subrange
 // P2321R2 zip
@@ -362,6 +364,7 @@
 // P2540R1 Empty Product For Certain Views
 // P2549R1 unexpected<E>::error()
 // P2652R2 Disallowing User Specialization Of allocator_traits
+// P2713R1 Escaping Improvements In std::format
 
 // _HAS_CXX23 and _SILENCE_ALL_CXX23_DEPRECATION_WARNINGS control:
 // P1413R3 Deprecate aligned_storage And aligned_union

tests/std/test.lst

@@ -569,6 +569,9 @@ tests\P2278R4_const_span
 tests\P2278R4_ranges_const_iterator_machinery
 tests\P2278R4_ranges_const_range_machinery
 tests\P2278R4_views_as_const
+tests\P2286R8_formatting_ranges
+tests\P2286R8_formatting_ranges_legacy_text_encoding
+tests\P2286R8_formatting_ranges_utf8
 tests\P2302R4_ranges_alg_contains
 tests\P2302R4_ranges_alg_contains_subrange
 tests\P2321R2_proxy_reference

tests/std/tests/P2286R8_formatting_ranges/env.lst

@@ -0,0 +1,4 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+RUNALL_INCLUDE ..\concepts_latest_matrix.lst

tests/std/tests/P2286R8_formatting_ranges/test.cpp

@@ -0,0 +1,125 @@
+// Copyright (c) Microsoft Corporation.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+#include <cassert>
+#include <format>
+#include <string>
+#include <string_view>
+#include <type_traits>
+#include <utility>
+
+using namespace std;
+
+template <typename CharT>
+[[nodiscard]] constexpr const CharT* choose_literal(const char* const str, const wchar_t* const wstr) noexcept {
+    if constexpr (is_same_v<CharT, char>) {
+        return str;
+    } else {
+        return wstr;
+    }
+}
+
+#define STR(Literal) (choose_literal<CharT>(Literal, L##Literal))
+
+template <class charT, class... Args>
+auto make_testing_format_args(Args&&... vals) {
+    if constexpr (is_same_v<charT, wchar_t>) {
+        return make_wformat_args(forward<Args>(vals)...);
+    } else {
+        return make_format_args(forward<Args>(vals)...);
+    }
+}
+
+template <class CharT, class T>
+void test_escaped_character() {
+    assert(format(STR("{:?}"), T('\t')) == STR(R"('\t')"));
+    assert(format(STR("{:?}"), T('\n')) == STR(R"('\n')"));
+    assert(format(STR("{:?}"), T('\r')) == STR(R"('\r')"));
+    assert(format(STR("{:?}"), T('\"')) == STR(R"('"')"));
+    assert(format(STR("{:?}"), T('\'')) == STR(R"('\'')"));
+    assert(format(STR("{:?}"), T('\\')) == STR(R"('\\')"));
+
+    assert(format(STR("{:?}"), T('\0')) == STR(R"('\u{0}')"));
+    assert(format(STR("{:?}"), T('\v')) == STR(R"('\u{b}')"));
+    assert(format(STR("{:?}"), T('\f')) == STR(R"('\u{c}')"));
+    assert(format(STR("{:?}"), T('\x7F')) == STR(R"('\u{7f}')"));
+
+    assert(format(STR("{:?}"), T(' ')) == STR("' '"));
+    assert(format(STR("{:?}"), T('~')) == STR("'~'"));
+
+    if constexpr (is_same_v<CharT, wchar_t> && is_same_v<T, wchar_t>) {
+        assert(format(L"{:?}", L'\xA0') == LR"('\u{a0}')"); // U+00A0 NO-BREAK SPACE
+        assert(format(L"{:?}", L'\x300') == LR"('\u{300}')"); // U+0300 COMBINING GRAVE ACCENT
+
+        assert(format(L"{:?}", L'\xA1') == L"'\xA1'"); // U+00A1 INVERTED EXCLAMATION MARK
+
+        assert(format(L"{:?}", L'\xD800') == LR"('\x{d800}')");
+        assert(format(L"{:?}", L'\xDFFF') == LR"('\x{dfff}')");
+    }
+}
+
+template <class CharT>
+void test_escaped_string() {
+    assert(format(STR("{:?}"), STR("\t")) == STR(R"("\t")"));
+    assert(format(STR("{:?}"), STR("\n")) == STR(R"("\n")"));
+    assert(format(STR("{:?}"), STR("\r")) == STR(R"("\r")"));
+    assert(format(STR("{:?}"), STR("\"")) == STR("\"\\\"\""));
+    assert(format(STR("{:?}"), STR("\'")) == STR(R"("'")"));
+    assert(format(STR("{:?}"), STR("\\")) == STR(R"("\\")"));
+
+    assert(format(STR("{:?}"), STR("\v")) == STR(R"("\u{b}")"));
+    assert(format(STR("{:?}"), STR("\f")) == STR(R"("\u{c}")"));
+    assert(format(STR("{:?}"), STR("\x7F")) == STR(R"("\u{7f}")"));
+
+    assert(format(STR("{:?}"), STR(" ")) == STR("\" \""));
+    assert(format(STR("{:?}"), STR("~")) == STR("\"~\""));
+
+    assert(format(STR("[{:?}]"), basic_string{STR("\0 \n \t \x02 \x1b"), 9}) == STR(R"(["\u{0} \n \t \u{2} \u{1b}"])"));
+    assert(format(STR("[{:?}]"), basic_string_view{STR("\0 \n \t \x02 \x1b"), 9})
+           == STR(R"(["\u{0} \n \t \u{2} \u{1b}"])"));
+
+    if constexpr (is_same_v<CharT, wchar_t>) {
+        assert(format(L"{:?}", L"\xA0") == LR"("\u{a0}")"); // U+00A0 NO-BREAK SPACE
+        assert(format(L"{:?}", L"\U0010FFFF") == LR"("\u{10ffff}")"); // noncharacter
+        assert(format(L"{:?}", L"\x300") == LR"("\u{300}")"); // U+0300 COMBINING GRAVE ACCENT
+
+        assert(format(L"{:?}", L"\xA1") == L"\"\xA1\""); // U+00A1 INVERTED EXCLAMATION MARK
+        assert(format(L"{:?}", L"\U00010000") == L"\"\U00010000\""); // U+10000 LINEAR B SYLLABLE B008 A
+
+        assert(format(L"{:?}", L"\xD800") == L"\"\\x{d800}\"");
+        assert(format(L"{:?}", L"\xDFFF") == L"\"\\x{dfff}\"");
+        assert(format(L"{:?}", L"\xDFFF\xD800") == L"\"\\x{dfff}\\x{d800}\"");
+
+        assert(format(L"{:?}", L"\xA0\x300") == L"\"\\u{a0}\\u{300}\"");
+        assert(format(L"{:?}", L" \x300") == L"\" \x300\"");
+        assert(format(L"{:?}", L"~\x300") == L"\"~\x300\"");
+    }
+}
+
+template <class CharT, class T>
+void test_format_specs() {
+    assert(format(STR("{:5?}"), T('\n')) == STR(R"('\n' )"));
+    try {
+        (void) vformat(STR("{:.3?}"), make_testing_format_args<CharT>(T('\n')));
+        assert(false);
+    } catch (const format_error&) {
+    }
+
+    assert(format(STR("{:5?}"), STR("\n")) == STR(R"("\n" )"));
+    assert(format(STR("{:.3?}"), STR("\n")) == STR(R"("\n)"));
+    assert(format(STR("{:5.3?}"), STR("\n")) == STR(R"("\n  )"));
+    assert(format(STR("{:>5.3?}"), STR("\n")) == STR(R"(  "\n)"));
+}
+
+int main() {
+    test_escaped_character<char, char>();
+    test_escaped_character<wchar_t, char>();
+    test_escaped_character<wchar_t, wchar_t>();
+
+    test_escaped_string<char>();
+    test_escaped_string<wchar_t>();
+
+    test_format_specs<char, char>();
+    test_format_specs<wchar_t, char>();
+    test_format_specs<wchar_t, wchar_t>();
+}

tests/std/tests/P2286R8_formatting_ranges_legacy_text_encoding/env.lst

@@ -0,0 +1,28 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+# This is `concepts_latest_matrix.lst` with `/execution-charset:.932` added.
+# clang is excluded since it doesn't support non-UTF-8 execution charsets.
+
+RUNALL_INCLUDE ..\prefix.lst
+RUNALL_CROSSLIST
+PM_CL="/w14640 /Zc:threadSafeInit- /EHsc /std:c++latest /execution-charset:.932"
+RUNALL_CROSSLIST
+PM_CL="/MD /D_ITERATOR_DEBUG_LEVEL=0 /permissive- /Zc:noexceptTypes-"
+PM_CL="/MD /D_ITERATOR_DEBUG_LEVEL=1 /permissive-"
+PM_CL="/MD /D_ITERATOR_DEBUG_LEVEL=0 /permissive- /Zc:char8_t- /Zc:preprocessor"
+PM_CL="/MDd /D_ITERATOR_DEBUG_LEVEL=0 /permissive- /Zc:wchar_t-"
+PM_CL="/MDd /D_ITERATOR_DEBUG_LEVEL=1 /permissive-"
+PM_CL="/MDd /D_ITERATOR_DEBUG_LEVEL=2 /permissive- /fp:except /Zc:preprocessor"
+PM_CL="/MT /D_ITERATOR_DEBUG_LEVEL=0 /permissive-"
+PM_CL="/MT /D_ITERATOR_DEBUG_LEVEL=0 /permissive- /analyze:only /analyze:autolog-"
+PM_CL="/MT /D_ITERATOR_DEBUG_LEVEL=1 /permissive-"
+PM_CL="/MTd /D_ITERATOR_DEBUG_LEVEL=0 /permissive- /fp:strict"
+PM_CL="/MTd /D_ITERATOR_DEBUG_LEVEL=1 /permissive-"
+PM_CL="/MTd /D_ITERATOR_DEBUG_LEVEL=2 /permissive"
+PM_CL="/MTd /D_ITERATOR_DEBUG_LEVEL=2 /permissive- /analyze:only /analyze:autolog-"
+# PM_CL="/permissive- /BE /c /MD"
+# PM_CL="/permissive- /BE /c /MTd"
+# PM_COMPILER="clang-cl" PM_CL="-fno-ms-compatibility -fno-delayed-template-parsing -Wno-unqualified-std-cast-call /permissive- /MD"
+# PM_COMPILER="clang-cl" PM_CL="-fno-ms-compatibility -fno-delayed-template-parsing -Wno-unqualified-std-cast-call /permissive- /MTd /fp:strict"
+# PM_COMPILER="clang-cl" PM_CL="-fno-ms-compatibility -fno-delayed-template-parsing -Wno-unqualified-std-cast-call /permissive- /MT /fp:strict -fsanitize=undefined -fno-sanitize-recover=undefined"

tests/std/tests/P2286R8_formatting_ranges_legacy_text_encoding/test.cpp

@@ -0,0 +1,22 @@
+// Copyright (c) Microsoft Corporation.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+#include <cassert>
+#include <format>
+
+using namespace std;
+
+void test_escaped_string() {
+    assert(format("{:?}", "\x81\x40") == "\"\\u{3000}\""); // U+3000 IDEOGRAPHIC SPACE
+
+    assert(format("{:?}", "\x81\x41") == "\"\x81\x41\"");
+
+    assert(format("{:?}", "\x81") == "\"\\x{81}\"");
+    assert(format("{:?}", "\xEB!") == "\"\\x{eb}!\"");
+
+    assert(format("{:?}", "\x81\x40\x40\x81") == "\"\\u{3000}\x40\\x{81}\"");
+}
+
+int main() {
+    test_escaped_string();
+}

tests/std/tests/P2286R8_formatting_ranges_utf8/env.lst

@@ -0,0 +1,6 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+RUNALL_INCLUDE ..\concepts_latest_matrix.lst
+RUNALL_CROSSLIST
+PM_CL="/utf-8"

tests/std/tests/P2286R8_formatting_ranges_utf8/test.cpp

@@ -0,0 +1,35 @@
+// Copyright (c) Microsoft Corporation.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+#include <cassert>
+#include <clocale>
+#include <format>
+
+using namespace std;
+
+void test_escaped_string() {
+    assert(format("{:?}", "\u00A0") == "\"\\u{a0}\""); // U+00A0 NO-BREAK SPACE
+    assert(format("{:?}", "\u0300") == "\"\\u{300}\""); // U+0300 COMBINING GRAVE ACCENT
+
+    assert(format("{:?}", "\u00A1") == "\"\u00A1\""); // U+00A1 INVERTED EXCLAMATION MARK
+    assert(format("{:?}", "\U00010000") == "\"\U00010000\""); // U+10000 LINEAR B SYLLABLE B008 A
+
+    assert(format("{:?}", "\xC0\x80") == "\"\\x{c0}\\x{80}\""); // ill-formed code unit sequence
+
+    assert(format("{:?}", "\u00A0\u0300") == "\"\\u{a0}\\u{300}\"");
+    assert(format("{:?}", " \u0300") == "\" \u0300\"");
+    assert(format("{:?}", "a\u0300") == "\"a\u0300\"");
+}
+
+int main() {
+    test_escaped_string();
+
+    assert(setlocale(LC_ALL, ".1252") != nullptr);
+    test_escaped_string();
+
+    assert(setlocale(LC_ALL, ".932") != nullptr);
+    test_escaped_string();
+
+    assert(setlocale(LC_ALL, ".UTF-8") != nullptr);
+    test_escaped_string();
+}

tools/unicode_properties_parse/.gitignore

@@ -5,5 +5,7 @@
 # they can be downloaded from unicode.org.
 # See the documentation in each script for more info.
 emoji-data.txt
+DerivedCoreProperties.txt
+DerivedGeneralCategory.txt
 GraphemeBreakProperty.txt
 GraphemeBreakTest.txt