forked from OSchip/llvm-project
When lexing in C11 mode, accept unicode character and string literals, per C11
6.4.4.4/1 and 6.4.5/1. llvm-svn: 176780
This commit is contained in:
Richard Smith
parent
c98bb4ed99
commit
9b36209e31
|
|
@ -1629,7 +1629,8 @@ void Lexer::LexStringLiteral(Token &Result, const char *CurPtr,
|
|||
if (!isLexingRawMode() &&
|
||||
(Kind == tok::utf8_string_literal ||
|
||||
Kind == tok::utf16_string_literal ||
|
||||
Kind == tok::utf32_string_literal))
|
||||
Kind == tok::utf32_string_literal) &&
|
||||
getLangOpts().CPlusPlus)
|
||||
Diag(BufferPtr, diag::warn_cxx98_compat_unicode_literal);
|
||||
|
||||
char C = getAndAdvanceChar(CurPtr, Result);
|
||||
|
|
@ -1794,7 +1795,8 @@ void Lexer::LexCharConstant(Token &Result, const char *CurPtr,
|
|||
const char *NulCharacter = 0; // Does this character contain the \0 character?
|
||||
|
||||
if (!isLexingRawMode() &&
|
||||
(Kind == tok::utf16_char_constant || Kind == tok::utf32_char_constant))
|
||||
(Kind == tok::utf16_char_constant || Kind == tok::utf32_char_constant) &&
|
||||
getLangOpts().CPlusPlus)
|
||||
Diag(BufferPtr, diag::warn_cxx98_compat_unicode_literal);
|
||||
|
||||
char C = getAndAdvanceChar(CurPtr, Result);
|
||||
|
|
@ -2848,11 +2850,11 @@ LexNextToken:
|
|||
MIOpt.ReadToken();
|
||||
return LexNumericConstant(Result, CurPtr);
|
||||
|
||||
case 'u': // Identifier (uber) or C++0x UTF-8 or UTF-16 string literal
|
||||
case 'u': // Identifier (uber) or C11/C++11 UTF-8 or UTF-16 string literal
|
||||
// Notify MIOpt that we read a non-whitespace/non-comment token.
|
||||
MIOpt.ReadToken();
|
||||
|
||||
if (LangOpts.CPlusPlus11) {
|
||||
if (LangOpts.CPlusPlus11 || LangOpts.C11) {
|
||||
Char = getCharAndSize(CurPtr, SizeTmp);
|
||||
|
||||
// UTF-16 string literal
|
||||
|
|
@ -2866,7 +2868,8 @@ LexNextToken:
|
|||
tok::utf16_char_constant);
|
||||
|
||||
// UTF-16 raw string literal
|
||||
if (Char == 'R' && getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
|
||||
if (Char == 'R' && LangOpts.CPlusPlus11 &&
|
||||
getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
|
||||
return LexRawStringLiteral(Result,
|
||||
ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
|
||||
SizeTmp2, Result),
|
||||
|
|
@ -2882,7 +2885,7 @@ LexNextToken:
|
|||
SizeTmp2, Result),
|
||||
tok::utf8_string_literal);
|
||||
|
||||
if (Char2 == 'R') {
|
||||
if (Char2 == 'R' && LangOpts.CPlusPlus11) {
|
||||
unsigned SizeTmp3;
|
||||
char Char3 = getCharAndSize(CurPtr + SizeTmp + SizeTmp2, SizeTmp3);
|
||||
// UTF-8 raw string literal
|
||||
|
|
@ -2900,11 +2903,11 @@ LexNextToken:
|
|||
// treat u like the start of an identifier.
|
||||
return LexIdentifier(Result, CurPtr);
|
||||
|
||||
case 'U': // Identifier (Uber) or C++0x UTF-32 string literal
|
||||
case 'U': // Identifier (Uber) or C11/C++11 UTF-32 string literal
|
||||
// Notify MIOpt that we read a non-whitespace/non-comment token.
|
||||
MIOpt.ReadToken();
|
||||
|
||||
if (LangOpts.CPlusPlus11) {
|
||||
if (LangOpts.CPlusPlus11 || LangOpts.C11) {
|
||||
Char = getCharAndSize(CurPtr, SizeTmp);
|
||||
|
||||
// UTF-32 string literal
|
||||
|
|
@ -2918,7 +2921,8 @@ LexNextToken:
|
|||
tok::utf32_char_constant);
|
||||
|
||||
// UTF-32 raw string literal
|
||||
if (Char == 'R' && getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
|
||||
if (Char == 'R' && LangOpts.CPlusPlus11 &&
|
||||
getCharAndSize(CurPtr + SizeTmp, SizeTmp2) == '"')
|
||||
return LexRawStringLiteral(Result,
|
||||
ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
|
||||
SizeTmp2, Result),
|
||||
|
|
|
|||
|
|
@ -1,87 +1,107 @@
|
|||
// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=C %s
|
||||
// RUN: %clang_cc1 -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=C %s
|
||||
// RUN: %clang_cc1 -x c++ -std=c++11 -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=CPP0X %s
|
||||
// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=CHECK-C %s
|
||||
// RUN: %clang_cc1 -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=CHECK-C %s
|
||||
// RUN: %clang_cc1 -x c++ -std=c++11 -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=CHECK-CXX11 %s
|
||||
// RUN: %clang_cc1 -x c -std=c11 -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=CHECK-C11 %s
|
||||
|
||||
#include <stddef.h>
|
||||
|
||||
#ifndef __cplusplus
|
||||
typedef __WCHAR_TYPE__ wchar_t;
|
||||
typedef __CHAR16_TYPE__ char16_t;
|
||||
typedef __CHAR32_TYPE__ char32_t;
|
||||
#endif
|
||||
|
||||
int main() {
|
||||
// CHECK-C: private unnamed_addr constant [10 x i8] c"abc\00\00\00\00\00\00\00", align 1
|
||||
// CHECK-CPP0X: private unnamed_addr constant [10 x i8] c"abc\00\00\00\00\00\00\00", align 1
|
||||
// CHECK-C11: private unnamed_addr constant [10 x i8] c"abc\00\00\00\00\00\00\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [10 x i8] c"abc\00\00\00\00\00\00\00", align 1
|
||||
char a[10] = "abc";
|
||||
|
||||
// This should convert to utf8.
|
||||
// CHECK-C: private unnamed_addr constant [10 x i8] c"\E1\84\A0\C8\A0\F4\82\80\B0\00", align 1
|
||||
// CHECK-CPP0X: private unnamed_addr constant [10 x i8] c"\E1\84\A0\C8\A0\F4\82\80\B0\00", align 1
|
||||
// CHECK-C11: private unnamed_addr constant [10 x i8] c"\E1\84\A0\C8\A0\F4\82\80\B0\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [10 x i8] c"\E1\84\A0\C8\A0\F4\82\80\B0\00", align 1
|
||||
char b[10] = "\u1120\u0220\U00102030";
|
||||
|
||||
// CHECK-C: private unnamed_addr constant [3 x i32] [i32 65, i32 66, i32 0], align 4
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 65, i32 66, i32 0], align 4
|
||||
// CHECK-C11: private unnamed_addr constant [3 x i32] [i32 65, i32 66, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 65, i32 66, i32 0], align 4
|
||||
const wchar_t *foo = L"AB";
|
||||
|
||||
// CHECK-C: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110027, i32 0], align 4
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110027, i32 0], align 4
|
||||
// CHECK-C11: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110027, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110027, i32 0], align 4
|
||||
const wchar_t *bar = L"\u1234\U0010F00B";
|
||||
|
||||
// CHECK-C: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110028, i32 0], align 4
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110028, i32 0], align 4
|
||||
// CHECK-C11: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110028, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 4660, i32 1110028, i32 0], align 4
|
||||
const wchar_t *baz = L"\u1234" "\U0010F00C";
|
||||
|
||||
#if __cplusplus >= 201103L
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 67, i32 68, i32 0], align 4
|
||||
#if __cplusplus >= 201103L || __STDC_VERSION__ >= 201112L
|
||||
// CHECK-C11: private unnamed_addr constant [3 x i32] [i32 67, i32 68, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 67, i32 68, i32 0], align 4
|
||||
const char32_t *c = U"CD";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 4661, i32 1110028, i32 0], align 4
|
||||
// CHECK-C11: private unnamed_addr constant [3 x i32] [i32 4661, i32 1110028, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 4661, i32 1110028, i32 0], align 4
|
||||
const char32_t *d = U"\u1235\U0010F00C";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 4661, i32 1110027, i32 0], align 4
|
||||
// CHECK-C11: private unnamed_addr constant [3 x i32] [i32 4661, i32 1110027, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 4661, i32 1110027, i32 0], align 4
|
||||
const char32_t *o = "\u1235" U"\U0010F00B";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i16] [i16 69, i16 70, i16 0], align 2
|
||||
// CHECK-C11: private unnamed_addr constant [3 x i16] [i16 69, i16 70, i16 0], align 2
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i16] [i16 69, i16 70, i16 0], align 2
|
||||
const char16_t *e = u"EF";
|
||||
|
||||
// This should convert to utf16.
|
||||
// CHECK-CPP0X: private unnamed_addr constant [5 x i16] [i16 4384, i16 544, i16 -9272, i16 -9168, i16 0], align 2
|
||||
// CHECK-C11: private unnamed_addr constant [5 x i16] [i16 4384, i16 544, i16 -9272, i16 -9168, i16 0], align 2
|
||||
// CHECK-CXX11: private unnamed_addr constant [5 x i16] [i16 4384, i16 544, i16 -9272, i16 -9168, i16 0], align 2
|
||||
const char16_t *f = u"\u1120\u0220\U00102030";
|
||||
|
||||
// This should convert to utf16.
|
||||
// CHECK-CPP0X: private unnamed_addr constant [5 x i16] [i16 4384, i16 800, i16 -9272, i16 -9168, i16 0], align 2
|
||||
// CHECK-C11: private unnamed_addr constant [5 x i16] [i16 4384, i16 800, i16 -9272, i16 -9168, i16 0], align 2
|
||||
// CHECK-CXX11: private unnamed_addr constant [5 x i16] [i16 4384, i16 800, i16 -9272, i16 -9168, i16 0], align 2
|
||||
const char16_t *p = u"\u1120\u0320" "\U00102030";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [4 x i8] c"def\00", align 1
|
||||
// CHECK-C11: private unnamed_addr constant [4 x i8] c"def\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [4 x i8] c"def\00", align 1
|
||||
const char *g = u8"def";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [4 x i8] c"ghi\00", align 1
|
||||
#ifdef __cplusplus
|
||||
// CHECK-CXX11: private unnamed_addr constant [4 x i8] c"ghi\00", align 1
|
||||
const char *h = R"foo(ghi)foo";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [4 x i8] c"jkl\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [4 x i8] c"jkl\00", align 1
|
||||
const char *i = u8R"bar(jkl)bar";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i16] [i16 71, i16 72, i16 0], align 2
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i16] [i16 71, i16 72, i16 0], align 2
|
||||
const char16_t *j = uR"foo(GH)foo";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 73, i32 74, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 73, i32 74, i32 0], align 4
|
||||
const char32_t *k = UR"bar(IJ)bar";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [3 x i32] [i32 75, i32 76, i32 0], align 4
|
||||
// CHECK-CXX11: private unnamed_addr constant [3 x i32] [i32 75, i32 76, i32 0], align 4
|
||||
const wchar_t *l = LR"bar(KL)bar";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [9 x i8] c"abc\5Cndef\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [9 x i8] c"abc\5Cndef\00", align 1
|
||||
const char *m = R"(abc\ndef)";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [8 x i8] c"abc\0Adef\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [8 x i8] c"abc\0Adef\00", align 1
|
||||
const char *n = R"(abc
|
||||
def)";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [11 x i8] c"abc\0Adefghi\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [11 x i8] c"abc\0Adefghi\00", align 1
|
||||
const char *q = R"(abc
|
||||
def)" "ghi";
|
||||
|
||||
// CHECK-CPP0X: private unnamed_addr constant [13 x i8] c"abc\5C\0A??=\0Adef\00", align 1
|
||||
// CHECK-CXX11: private unnamed_addr constant [13 x i8] c"abc\5C\0A??=\0Adef\00", align 1
|
||||
const char *r = R\
|
||||
"(abc\
|
||||
??=
|
||||
def)";
|
||||
|
||||
|
||||
#endif
|
||||
#endif
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,4 +1,11 @@
|
|||
// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -Wfour-char-constants -fsyntax-only -verify %s
|
||||
// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c11 -x c -Wfour-char-constants -fsyntax-only -verify %s
|
||||
|
||||
#ifndef __cplusplus
|
||||
typedef __WCHAR_TYPE__ wchar_t;
|
||||
typedef __CHAR16_TYPE__ char16_t;
|
||||
typedef __CHAR32_TYPE__ char32_t;
|
||||
#endif
|
||||
|
||||
int a = 'ab'; // expected-warning {{multi-character character constant}}
|
||||
int b = '\xFF\xFF'; // expected-warning {{multi-character character constant}}
|
||||
|
|
@ -7,7 +14,9 @@ int c = 'APPS'; // expected-warning {{multi-character character constant}}
|
|||
char d = '⌘'; // expected-error {{character too large for enclosing character literal type}}
|
||||
char e = '\u2318'; // expected-error {{character too large for enclosing character literal type}}
|
||||
|
||||
#ifdef __cplusplus
|
||||
auto f = '\xE2\x8C\x98'; // expected-warning {{multi-character character constant}}
|
||||
#endif
|
||||
|
||||
char16_t g = u'ab'; // expected-error {{Unicode character literals may not contain multiple characters}}
|
||||
char16_t h = u'\U0010FFFD'; // expected-error {{character too large for enclosing character literal type}}
|
||||
|
|
@ -24,4 +33,11 @@ char32_t n = U'ab'; // expected-error {{Unicode character literals may not conta
|
|||
char16_t o = '👽'; // expected-error {{character too large for enclosing character literal type}}
|
||||
|
||||
char16_t p[2] = u"\U0000FFFF";
|
||||
char16_t q[2] = u"\U00010000"; // expected-error {{too long}}
|
||||
char16_t q[2] = u"\U00010000";
|
||||
#ifdef __cplusplus
|
||||
// expected-error@-2 {{too long}}
|
||||
#else
|
||||
// FIXME: The above should be accepted in C11 mode.
|
||||
// expected-error@-6 {{must be an initializer list}}
|
||||
// expected-error@-6 {{must be an initializer list}}
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -1,33 +1,48 @@
|
|||
// RUN: %clang_cc1 -std=c++11 -fsyntax-only -verify %s
|
||||
// RUN: %clang_cc1 -std=c11 -x c -fsyntax-only -verify %s
|
||||
|
||||
#ifndef __cplusplus
|
||||
typedef __WCHAR_TYPE__ wchar_t;
|
||||
typedef __CHAR16_TYPE__ char16_t;
|
||||
typedef __CHAR32_TYPE__ char32_t;
|
||||
#endif
|
||||
|
||||
void f() {
|
||||
|
||||
const char* a = u8"abc" u"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char* b = u8"abc" U"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char* c = u8"abc" L"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#ifdef __cplusplus
|
||||
const char* d = u8"abc" uR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char* e = u8"abc" UR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char* f = u8"abc" LR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#endif
|
||||
|
||||
const char16_t* g = u"abc" u8"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char16_t* h = u"abc" U"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char16_t* i = u"abc" L"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#ifdef __cplusplus
|
||||
const char16_t* j = u"abc" u8R"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char16_t* k = u"abc" UR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char16_t* l = u"abc" LR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#endif
|
||||
|
||||
const char32_t* m = U"abc" u8"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char32_t* n = U"abc" u"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char32_t* o = U"abc" L"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#ifdef __cplusplus
|
||||
const char32_t* p = U"abc" u8R"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char32_t* q = U"abc" uR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const char32_t* r = U"abc" LR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#endif
|
||||
|
||||
const wchar_t* s = L"abc" u8"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const wchar_t* t = L"abc" u"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const wchar_t* u = L"abc" U"abc"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#ifdef __cplusplus
|
||||
const wchar_t* v = L"abc" u8R"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const wchar_t* w = L"abc" uR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
const wchar_t* x = L"abc" UR"(abc)"; // expected-error {{unsupported non-standard concatenation of string literals}}
|
||||
#endif
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -fsyntax-only -verify %s
|
||||
// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c11 -x c -fsyntax-only -verify %s
|
||||
|
||||
int array0[u'ñ' == u'\xf1'? 1 : -1];
|
||||
int array1['\xF1' != u'\xf1'? 1 : -1];
|
||||
|
|
|
|||
Loading…
Reference in New Issue