commit bcd6c96a05c1cb2527f1b8ac1fb0ce7645b8c37c
parent 0c89daeb02ec6e8c8dea606f2fc9846c4068b7f6
Author: Chris Peterson <cpeterson@mozilla.com>
Date: Thu, 30 Oct 2025 16:53:16 +0000
Bug 1997025 - Replace u8"" string literals in mfbt and xpcom tests. r=xpcom-reviewers,emilio
u8"" strings have type const char[] in C++17, but type const char8_t[] in C++20. Since most Firefox code is written assuming char or char16_t strings, char8_t strings cause type mismatches that would require additional overloads or string conversions.
Because Firefox .cpp files are compiled as UTF-8, "" string literals are already UTF-8 encoded and the explicit u8 prefix is unnecessary.
By removing the u8"" string literals in the MFBT and xpcom tests, we can remove nsTStringRepr's Equals() overloads for char8_t. They are now unused and casting a char8_t* string pointer to a char* string pointer is UB.
Differential Revision: https://phabricator.services.mozilla.com/D270453
Diffstat:
3 files changed, 52 insertions(+), 65 deletions(-)
diff --git a/mfbt/tests/TestUtf8.cpp b/mfbt/tests/TestUtf8.cpp
@@ -241,10 +241,10 @@ static void ExpectBadCodePoint(const Char (&aCharN)[N],
static void TestIsUtf8() {
// Note we include the U+0000 NULL in this one -- and that's fine.
- static const char asciiBytes[] = u8"How about a nice game of chess?";
+ static const char asciiBytes[] = "How about a nice game of chess?";
MOZ_RELEASE_ASSERT(IsUtf8(Span(asciiBytes, std::size(asciiBytes))));
- static const char endNonAsciiBytes[] = u8"Life is like a 🌯";
+ static const char endNonAsciiBytes[] = "Life is like a 🌯";
MOZ_RELEASE_ASSERT(
IsUtf8(Span(endNonAsciiBytes, std::size(endNonAsciiBytes) - 1)));
@@ -254,13 +254,13 @@ static void TestIsUtf8() {
// Byte-counts
// 1
- static const char oneBytes[] = u8"A"; // U+0041 LATIN CAPITAL LETTER A
+ static const char oneBytes[] = "A"; // U+0041 LATIN CAPITAL LETTER A
constexpr size_t oneBytesLen = std::size(oneBytes);
static_assert(oneBytesLen == 2, "U+0041 plus nul");
MOZ_RELEASE_ASSERT(IsUtf8(Span(oneBytes, oneBytesLen)));
// 2
- static const char twoBytes[] = u8"؆"; // U+0606 ARABIC-INDIC CUBE ROOT
+ static const char twoBytes[] = "؆"; // U+0606 ARABIC-INDIC CUBE ROOT
constexpr size_t twoBytesLen = std::size(twoBytes);
static_assert(twoBytesLen == 3, "U+0606 in two bytes plus nul");
MOZ_RELEASE_ASSERT(IsUtf8(Span(twoBytes, twoBytesLen)));
@@ -268,7 +268,7 @@ static void TestIsUtf8() {
ExpectValidCodePoint(twoBytes, 0x0606);
// 3
- static const char threeBytes[] = u8"᨞"; // U+1A1E BUGINESE PALLAWA
+ static const char threeBytes[] = "᨞"; // U+1A1E BUGINESE PALLAWA
constexpr size_t threeBytesLen = std::size(threeBytes);
static_assert(threeBytesLen == 4, "U+1A1E in three bytes plus nul");
MOZ_RELEASE_ASSERT(IsUtf8(Span(threeBytes, threeBytesLen)));
@@ -276,8 +276,7 @@ static void TestIsUtf8() {
ExpectValidCodePoint(threeBytes, 0x1A1E);
// 4
- static const char fourBytes[] =
- u8"🁡"; // U+1F061 DOMINO TILE HORIZONTAL-06-06
+ static const char fourBytes[] = "🁡"; // U+1F061 DOMINO TILE HORIZONTAL-06-06
constexpr size_t fourBytesLen = std::size(fourBytes);
static_assert(fourBytesLen == 5, "U+1F061 in four bytes plus nul");
MOZ_RELEASE_ASSERT(IsUtf8(Span(fourBytes, fourBytesLen)));
@@ -285,7 +284,7 @@ static void TestIsUtf8() {
ExpectValidCodePoint(fourBytes, 0x1F061);
// Max code point
- static const char maxCodePoint[] = u8""; // U+10FFFF
+ static const char maxCodePoint[] = ""; // U+10FFFF
constexpr size_t maxCodePointLen = std::size(maxCodePoint);
static_assert(maxCodePointLen == 5, "U+10FFFF in four bytes plus nul");
MOZ_RELEASE_ASSERT(IsUtf8(Span(maxCodePoint, maxCodePointLen)));
@@ -357,63 +356,63 @@ static void TestDecodeOneValidUtf8CodePoint() {
// Length two.
- ExpectValidCodePoint(u8"", 0x80); // <control>
- ExpectValidCodePoint(u8"©", 0xA9); // COPYRIGHT SIGN
- ExpectValidCodePoint(u8"¶", 0xB6); // PILCROW SIGN
- ExpectValidCodePoint(u8"¾", 0xBE); // VULGAR FRACTION THREE QUARTERS
- ExpectValidCodePoint(u8"÷", 0xF7); // DIVISION SIGN
- ExpectValidCodePoint(u8"ÿ", 0xFF); // LATIN SMALL LETTER Y WITH DIAERESIS
- ExpectValidCodePoint(u8"Ā", 0x100); // LATIN CAPITAL LETTER A WITH MACRON
- ExpectValidCodePoint(u8"IJ", 0x132); // LATIN CAPITAL LETTER LIGATURE IJ
- ExpectValidCodePoint(u8"ͼ", 0x37C); // GREEK SMALL DOTTED LUNATE SIGMA SYMBOL
- ExpectValidCodePoint(u8"Ӝ",
+ ExpectValidCodePoint("", 0x80); // <control>
+ ExpectValidCodePoint("©", 0xA9); // COPYRIGHT SIGN
+ ExpectValidCodePoint("¶", 0xB6); // PILCROW SIGN
+ ExpectValidCodePoint("¾", 0xBE); // VULGAR FRACTION THREE QUARTERS
+ ExpectValidCodePoint("÷", 0xF7); // DIVISION SIGN
+ ExpectValidCodePoint("ÿ", 0xFF); // LATIN SMALL LETTER Y WITH DIAERESIS
+ ExpectValidCodePoint("Ā", 0x100); // LATIN CAPITAL LETTER A WITH MACRON
+ ExpectValidCodePoint("IJ", 0x132); // LATIN CAPITAL LETTER LIGATURE IJ
+ ExpectValidCodePoint("ͼ", 0x37C); // GREEK SMALL DOTTED LUNATE SIGMA SYMBOL
+ ExpectValidCodePoint("Ӝ",
0x4DC); // CYRILLIC CAPITAL LETTER ZHE WITTH DIAERESIS
- ExpectValidCodePoint(u8"۩", 0x6E9); // ARABIC PLACE OF SAJDAH
- ExpectValidCodePoint(u8"߿", 0x7FF); // <not assigned>
+ ExpectValidCodePoint("۩", 0x6E9); // ARABIC PLACE OF SAJDAH
+ ExpectValidCodePoint("߿", 0x7FF); // <not assigned>
// Length three.
- ExpectValidCodePoint(u8"ࠀ", 0x800); // SAMARITAN LETTER ALAF
- ExpectValidCodePoint(u8"ࡁ", 0x841); // MANDAIC LETTER AB
- ExpectValidCodePoint(u8"ࣿ", 0x8FF); // ARABIC MARK SIDEWAYS NOON GHUNNA
- ExpectValidCodePoint(u8"ஆ", 0xB86); // TAMIL LETTER AA
- ExpectValidCodePoint(u8"༃",
+ ExpectValidCodePoint("ࠀ", 0x800); // SAMARITAN LETTER ALAF
+ ExpectValidCodePoint("ࡁ", 0x841); // MANDAIC LETTER AB
+ ExpectValidCodePoint("ࣿ", 0x8FF); // ARABIC MARK SIDEWAYS NOON GHUNNA
+ ExpectValidCodePoint("ஆ", 0xB86); // TAMIL LETTER AA
+ ExpectValidCodePoint("༃",
0xF03); // TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA
ExpectValidCodePoint(
- u8"࿉",
+ "࿉",
0xFC9); // TIBETAN SYMBOL NOR BU (but on my system it really looks like
// SOFT-SERVE ICE CREAM FROM ABOVE THE PLANE if you ask me)
- ExpectValidCodePoint(u8"ဪ", 0x102A); // MYANMAR LETTER AU
- ExpectValidCodePoint(u8"ᚏ", 0x168F); // OGHAM LETTER RUIS
+ ExpectValidCodePoint("ဪ", 0x102A); // MYANMAR LETTER AU
+ ExpectValidCodePoint("ᚏ", 0x168F); // OGHAM LETTER RUIS
ExpectValidCodePoint("\xE2\x80\xA8", 0x2028); // (the hated) LINE SEPARATOR
ExpectValidCodePoint("\xE2\x80\xA9",
- 0x2029); // (the hated) PARAGRAPH SEPARATOR
- ExpectValidCodePoint(u8"☬", 0x262C); // ADI SHAKTI
- ExpectValidCodePoint(u8"㊮", 0x32AE); // CIRCLED IDEOGRAPH RESOURCE
- ExpectValidCodePoint(u8"㏖", 0x33D6); // SQUARE MOL
- ExpectValidCodePoint(u8"ꔄ", 0xA504); // VAI SYLLABLE WEEN
- ExpectValidCodePoint(u8"ퟕ", 0xD7D5); // HANGUL JONGSEONG RIEUL-SSANGKIYEOK
- ExpectValidCodePoint(u8"", 0xD7FF); // <not assigned>
- ExpectValidCodePoint(u8"", 0xE000); // <Private Use>
- ExpectValidCodePoint(u8"鱗", 0xF9F2); // CJK COMPATIBILITY IDEOGRAPH-F9F
+ 0x2029); // (the hated) PARAGRAPH SEPARATOR
+ ExpectValidCodePoint("☬", 0x262C); // ADI SHAKTI
+ ExpectValidCodePoint("㊮", 0x32AE); // CIRCLED IDEOGRAPH RESOURCE
+ ExpectValidCodePoint("㏖", 0x33D6); // SQUARE MOL
+ ExpectValidCodePoint("ꔄ", 0xA504); // VAI SYLLABLE WEEN
+ ExpectValidCodePoint("ퟕ", 0xD7D5); // HANGUL JONGSEONG RIEUL-SSANGKIYEOK
+ ExpectValidCodePoint("", 0xD7FF); // <not assigned>
+ ExpectValidCodePoint("", 0xE000); // <Private Use>
+ ExpectValidCodePoint("鱗", 0xF9F2); // CJK COMPATIBILITY IDEOGRAPH-F9F
ExpectValidCodePoint(
- u8"﷽", 0xFDFD); // ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHHHEEEEM
- ExpectValidCodePoint(u8"", 0xFFFF); // <not assigned>
+ "﷽", 0xFDFD); // ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHHHEEEEM
+ ExpectValidCodePoint("", 0xFFFF); // <not assigned>
// Length four.
- ExpectValidCodePoint(u8"𐀀", 0x10000); // LINEAR B SYLLABLE B008 A
- ExpectValidCodePoint(u8"𔑀", 0x14440); // ANATOLIAN HIEROGLYPH A058
- ExpectValidCodePoint(u8"𝛗", 0x1D6D7); // MATHEMATICAL BOLD SMALL PHI
- ExpectValidCodePoint(u8"💩", 0x1F4A9); // PILE OF POO
- ExpectValidCodePoint(u8"🔫", 0x1F52B); // PISTOL
- ExpectValidCodePoint(u8"🥌", 0x1F94C); // CURLING STONE
- ExpectValidCodePoint(u8"🥏", 0x1F94F); // FLYING DISC
- ExpectValidCodePoint(u8"𠍆", 0x20346); // CJK UNIFIED IDEOGRAPH-20346
- ExpectValidCodePoint(u8"𡠺", 0x2183A); // CJK UNIFIED IDEOGRAPH-2183A
- ExpectValidCodePoint(u8"", 0x417F6); // <not assigned>
- ExpectValidCodePoint(u8"", 0x7E836); // <not assigned>
- ExpectValidCodePoint(u8"", 0xFEF67); // <Plane 15 Private Use>
- ExpectValidCodePoint(u8"", 0x10FFFF); //
+ ExpectValidCodePoint("𐀀", 0x10000); // LINEAR B SYLLABLE B008 A
+ ExpectValidCodePoint("𔑀", 0x14440); // ANATOLIAN HIEROGLYPH A058
+ ExpectValidCodePoint("𝛗", 0x1D6D7); // MATHEMATICAL BOLD SMALL PHI
+ ExpectValidCodePoint("💩", 0x1F4A9); // PILE OF POO
+ ExpectValidCodePoint("🔫", 0x1F52B); // PISTOL
+ ExpectValidCodePoint("🥌", 0x1F94C); // CURLING STONE
+ ExpectValidCodePoint("🥏", 0x1F94F); // FLYING DISC
+ ExpectValidCodePoint("𠍆", 0x20346); // CJK UNIFIED IDEOGRAPH-20346
+ ExpectValidCodePoint("𡠺", 0x2183A); // CJK UNIFIED IDEOGRAPH-2183A
+ ExpectValidCodePoint("", 0x417F6); // <not assigned>
+ ExpectValidCodePoint("", 0x7E836); // <not assigned>
+ ExpectValidCodePoint("", 0xFEF67); // <Plane 15 Private Use>
+ ExpectValidCodePoint("", 0x10FFFF); //
}
static void TestDecodeBadLeadUnit() {
diff --git a/xpcom/string/nsTStringRepr.h b/xpcom/string/nsTStringRepr.h
@@ -253,18 +253,6 @@ class nsTStringRepr {
*/
bool EqualsIgnoreCase(const std::string_view& aString) const;
-#ifdef __cpp_char8_t
- template <typename Q = T, typename EnableIfChar = mozilla::CharOnlyT<Q>>
- bool NS_FASTCALL Equals(const char8_t* aData) const {
- return Equals(reinterpret_cast<const char*>(aData));
- }
-
- template <typename Q = T, typename EnableIfChar = mozilla::CharOnlyT<Q>>
- bool NS_FASTCALL Equals(const char8_t* aData, comparator_type aComp) const {
- return Equals(reinterpret_cast<const char*>(aData), aComp);
- }
-#endif
-
#if defined(MOZ_USE_CHAR16_WRAPPER)
template <typename Q = T, typename EnableIfChar16 = Char16OnlyT<Q>>
bool NS_FASTCALL Equals(char16ptr_t aData) const {
diff --git a/xpcom/tests/gtest/TestStrings.cpp b/xpcom/tests/gtest/TestStrings.cpp
@@ -1464,7 +1464,7 @@ TEST_F(Strings, bulk_write_fail) {
EXPECT_TRUE(handleOrErr.isOk());
}
EXPECT_EQ(s.Length(), 3U);
- EXPECT_TRUE(s.Equals(u8"\uFFFD"));
+ EXPECT_TRUE(s.Equals("\uFFFD"));
}
TEST_F(Strings, huge_capacity) {
