diff options
| author | Eli Friedman <eli.friedman@gmail.com> | 2011-11-01 02:26:36 +0000 |
|---|---|---|
| committer | Eli Friedman <eli.friedman@gmail.com> | 2011-11-01 02:26:36 +0000 |
| commit | f12e1b928053ccec033eee4c1e683bb1c54c220a (patch) | |
| tree | 9f9bb8cd75fe07474ff130860f59abab8a8784ac /test/CodeGen/string-literal-unicode-conversion.c | |
| parent | 64f45a24b19eb89ff88f7c3ff0df9be8e861ac97 (diff) | |
| download | clang-f12e1b928053ccec033eee4c1e683bb1c54c220a.tar.gz | |
Tests for UTF-8 encoding in strings in source code. Patch by Seth Cantrell.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@143418 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/string-literal-unicode-conversion.c')
| -rw-r--r-- | test/CodeGen/string-literal-unicode-conversion.c | 58 |
1 files changed, 58 insertions, 0 deletions
diff --git a/test/CodeGen/string-literal-unicode-conversion.c b/test/CodeGen/string-literal-unicode-conversion.c new file mode 100644 index 0000000000..40acd735c4 --- /dev/null +++ b/test/CodeGen/string-literal-unicode-conversion.c @@ -0,0 +1,58 @@ +// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=C %s +// RUN: %clang_cc1 -x c++ -std=c++0x -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=CPP0X %s +// RUN: %clang_cc1 -x c++ -std=c++0x -fshort-wchar -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -check-prefix=SHORTWCHAR %s + +// This file contains a mix of ISO-8859-1 and UTF-8 encoded data. +// the literal assigned to 'aa' should be the ISO-8859-1 encoding for the code +// points U+00C0 U+00E9 U+00EE U+00F5 U+00FC + +// The rest of the literals should contain the UTF-8 encoding for U+041A U+043E +// U+0448 U+043A U+0430 + +#ifndef __cplusplus +#include <wchar.h> +#endif + +#ifdef __cplusplus +extern "C" +#endif +void f() { + // CHECK-C: private unnamed_addr constant [6 x i8] c"\C0\E9\EE\F5\FC\00", align 1 + // CHECK-CPP0X: private unnamed_addr constant [6 x i8] c"\C0\E9\EE\F5\FC\00", align 1 + char const *aa = "Àéîõü"; + + // CHECK-C: private unnamed_addr constant [11 x i8] c"\D0\9A\D0\BE\D1\88\D0\BA\D0\B0\00", align 1 + // CHECK-CPP0X: private unnamed_addr constant [11 x i8] c"\D0\9A\D0\BE\D1\88\D0\BA\D0\B0\00", align 1 + char const *a = "Кошка"; + + // CHECK-C: private unnamed_addr constant [6 x i32] [i32 1050, i32 1086, i32 1096, i32 1082, i32 1072, i32 0], align 4 + // CHECK-SHORTWCHAR: private unnamed_addr constant [6 x i16] [i16 1050, i16 1086, i16 1096, i16 1082, i16 1072, i16 0], align 2 + // CHECK-CPP0X: private unnamed_addr constant [6 x i32] [i32 1050, i32 1086, i32 1096, i32 1082, i32 1072, i32 0], align 4 + wchar_t const *b = L"Кошка"; + +#if __cplusplus >= 201103L + + // CHECK-CPP0X: private unnamed_addr constant [12 x i8] c"1\D0\9A\D0\BE\D1\88\D0\BA\D0\B0\00", align 1 + char const *c = u8"1Кошка"; + + // CHECK-CPP0X: private unnamed_addr constant [7 x i16] [i16 50, i16 1050, i16 1086, i16 1096, i16 1082, i16 1072, i16 0], align 2 + char16_t const *e = u"2Кошка"; + + // CHECK-CPP0X: private unnamed_addr constant [7 x i32] [i32 51, i32 1050, i32 1086, i32 1096, i32 1082, i32 1072, i32 0], align 4 + char32_t const *f = U"3Кошка"; + + // CHECK-CPP0X: private unnamed_addr constant [12 x i8] c"4\D0\9A\D0\BE\D1\88\D0\BA\D0\B0\00", align 1 + char const *d = u8R"(4Кошка)"; + + // CHECK-CPP0X: private unnamed_addr constant [7 x i16] [i16 53, i16 1050, i16 1086, i16 1096, i16 1082, i16 1072, i16 0], align 2 + char16_t const *g = uR"(5Кошка)"; + + // CHECK-CPP0X: private unnamed_addr constant [7 x i32] [i32 54, i32 1050, i32 1086, i32 1096, i32 1082, i32 1072, i32 0], align 4 + char32_t const *h = UR"(6Кошка)"; + + // CHECK-SHORTWCHAR: private unnamed_addr constant [7 x i16] [i16 55, i16 1050, i16 1086, i16 1096, i16 1082, i16 1072, i16 0], align 2 + // CHECK-CPP0X: private unnamed_addr constant [7 x i32] [i32 55, i32 1050, i32 1086, i32 1096, i32 1082, i32 1072, i32 0], align 4 + wchar_t const *i = LR"(7Кошка)"; + +#endif +} |