zturner created this revision.
zturner added a reviewer: jingham.
char16, char32, and wchar_t were previously broken. If you had a simple
variable like `wchar_t x = L'1'` and wrote `p x` LLDB would output `(wchar_t) x
= 1\0`. This is because it was using `eFormatChar` with a size of 2. What we
needed was to introduce a special format specifically for `wchar_t`. The only
valid sizes of `wchar_t` on all existing compilers are 2 and 4, so there's no
real point trying to handle sizes of 1 and 8.
Along the way, I accidentally stumbled across the reason that references that
char16 and char32 types were also formatting incorrectly, so I fixed that as
well.
https://reviews.llvm.org/D53989
Files:
lldb/include/lldb/lldb-enumerations.h
lldb/lit/SymbolFile/NativePDB/globals-fundamental.cpp
lldb/source/Commands/CommandObjectMemory.cpp
lldb/source/Core/DumpDataExtractor.cpp
lldb/source/Core/ValueObject.cpp
lldb/source/DataFormatters/FormatManager.cpp
lldb/source/DataFormatters/VectorType.cpp
lldb/source/Symbol/ClangASTContext.cpp
Index: lldb/source/Symbol/ClangASTContext.cpp
===================================================================
--- lldb/source/Symbol/ClangASTContext.cpp
+++ lldb/source/Symbol/ClangASTContext.cpp
@@ -5257,11 +5257,12 @@
return lldb::eFormatBoolean;
case clang::BuiltinType::Char_S:
case clang::BuiltinType::SChar:
- case clang::BuiltinType::WChar_S:
case clang::BuiltinType::Char_U:
case clang::BuiltinType::UChar:
- case clang::BuiltinType::WChar_U:
return lldb::eFormatChar;
+ case clang::BuiltinType::WChar_S:
+ case clang::BuiltinType::WChar_U:
+ return lldb::eFormatWchar;
case clang::BuiltinType::Char16:
return lldb::eFormatUnicode16;
case clang::BuiltinType::Char32:
Index: lldb/source/DataFormatters/VectorType.cpp
===================================================================
--- lldb/source/DataFormatters/VectorType.cpp
+++ lldb/source/DataFormatters/VectorType.cpp
@@ -64,9 +64,12 @@
case lldb::eFormatHexFloat:
return type_system->GetBasicTypeFromAST(lldb::eBasicTypeFloat);
+ case lldb::eFormatWchar:
+ return type_system->GetBasicTypeFromAST(lldb::eBasicTypeWChar);
case lldb::eFormatUnicode16:
+ return type_system->GetBasicTypeFromAST(lldb::eBasicTypeChar16);
case lldb::eFormatUnicode32:
-
+ return type_system->GetBasicTypeFromAST(lldb::eBasicTypeChar32);
case lldb::eFormatUnsigned:
return type_system->GetBasicTypeFromAST(lldb::eBasicTypeUnsignedInt);
Index: lldb/source/DataFormatters/FormatManager.cpp
===================================================================
--- lldb/source/DataFormatters/FormatManager.cpp
+++ lldb/source/DataFormatters/FormatManager.cpp
@@ -43,6 +43,7 @@
{eFormatBytesWithASCII, 'Y', "bytes with ASCII"},
{eFormatChar, 'c', "character"},
{eFormatCharPrintable, 'C', "printable character"},
+ {eFormatWchar, 'L', "wide character"},
{eFormatComplexFloat, 'F', "complex float"},
{eFormatCString, 's', "c-string"},
{eFormatDecimal, 'd', "decimal"},
Index: lldb/source/Core/ValueObject.cpp
===================================================================
--- lldb/source/Core/ValueObject.cpp
+++ lldb/source/Core/ValueObject.cpp
@@ -1383,6 +1383,7 @@
(custom_format == eFormatOSType) ||
(custom_format == eFormatUnicode16) ||
(custom_format == eFormatUnicode32) ||
+ (custom_format == eFormatWchar) ||
(custom_format == eFormatUnsigned) ||
(custom_format == eFormatPointer) ||
(custom_format == eFormatComplexInteger) ||
Index: lldb/source/Core/DumpDataExtractor.cpp
===================================================================
--- lldb/source/Core/DumpDataExtractor.cpp
+++ lldb/source/Core/DumpDataExtractor.cpp
@@ -637,6 +637,23 @@
}
} break;
+ case eFormatWchar: {
+ s->PutChar('L');
+ s->PutChar(item_count == 1 ? '\'' : '\"');
+
+ const uint64_t ch = DE.GetMaxU64(&offset, item_byte_size);
+ // wchar_t semantics vary across platforms, and this is complicated even
+ // more by the fact that the host may not be the same as the target, so to
+ // be faithful we would have to follow the target's semantics. For
+ // simplicity, just print the character if it's ascii.
+ if (ch <= CHAR_MAX && llvm::isPrint(ch))
+ s->PutChar(ch);
+ else
+ s->PutChar(NON_PRINTABLE_CHAR);
+
+ s->PutChar(item_count == 1 ? '\'' : '\"');
+ } break;
+
case eFormatUnicode16:
s->Printf("U+%4.4x", DE.GetU16(&offset));
break;
Index: lldb/source/Commands/CommandObjectMemory.cpp
===================================================================
--- lldb/source/Commands/CommandObjectMemory.cpp
+++ lldb/source/Commands/CommandObjectMemory.cpp
@@ -167,6 +167,15 @@
format_options.GetCountValue() = 8;
break;
+ case eFormatWchar:
+ if (!byte_size_option_set)
+ byte_size_value =
+ target->GetArchitecture().GetTriple().isOSWindows() ? 2 : 4;
+ if (!num_per_line_option_set)
+ m_num_per_line = 1;
+ if (!count_option_set)
+ format_options.GetCountValue() = 8;
+ break;
case eFormatBinary:
case eFormatFloat:
case eFormatOctal:
@@ -1412,6 +1421,7 @@
case eFormatBytesWithASCII:
case eFormatComplex:
case eFormatEnum:
+ case eFormatWchar:
case eFormatUnicode16:
case eFormatUnicode32:
case eFormatVectorOfChar:
Index: lldb/lit/SymbolFile/NativePDB/globals-fundamental.cpp
===================================================================
--- lldb/lit/SymbolFile/NativePDB/globals-fundamental.cpp
+++ lldb/lit/SymbolFile/NativePDB/globals-fundamental.cpp
@@ -637,32 +637,32 @@
char16_t &RC16_24 = C16_24;
// CHECK: (lldb) target variable RC16_24
-// FIXME: (char16_t &) RC16_24 = {{.*}} (&::RC16_24 = U+0014)
+// CHECK: (char16_t &) RC16_24 = {{.*}} (&::RC16_24 = U+0014)
char32_t &RC32_42 = C32_42;
// CHECK: (lldb) target variable RC32_42
-// FIXME: (char32_t &) RC32_42 = {{.*}} (&::RC32_42 = U+0x00000022)
+// CHECK: (char32_t &) RC32_42 = {{.*}} (&::RC32_42 = U+0x00000022)
wchar_t &RWC1 = WC1;
// CHECK: (lldb) target variable RWC1
-// FIXME: (wchar_t &) RWC1 = {{.*}} (&::RWC1 = L'1')
+// CHECK: (wchar_t &) RWC1 = {{.*}} (&::RWC1 = L'1')
wchar_t &RWCP = WCP;
// CHECK: (lldb) target variable RWCP
-// FIXME: (wchar_t &) RWCP = {{.*}} (&::RWCP = L'P')
+// CHECK: (wchar_t &) RWCP = {{.*}} (&::RWCP = L'P')
const char16_t &CRC16_24 = C16_24;
// CHECK: (lldb) target variable CRC16_24
-// FIXME: (const char16_t &) CRC16_24 = {{.*}} (&::CRC16_24 = U+0014)
+// CHECK: (const char16_t &) CRC16_24 = {{.*}} (&::CRC16_24 = U+0014)
const char32_t &CRC32_42 = C32_42;
// CHECK: (lldb) target variable CRC32_42
-// FIXME: (const char32_t &) CRC32_42 = {{.*}} (&::CRC32_42 = U+0x00000022)
+// CHECK: (const char32_t &) CRC32_42 = {{.*}} (&::CRC32_42 = U+0x00000022)
const wchar_t &CRWC1 = WC1;
// CHECK: (lldb) target variable CRWC1
-// FIXME: (const wchar_t &) CRWC1 = {{.*}} (&::CRWC1 = L'1')
+// CHECK: (const wchar_t &) CRWC1 = {{.*}} (&::CRWC1 = L'1')
const wchar_t &CRWCP = WCP;
// CHECK: (lldb) target variable CRWCP
-// FIXME: (const wchar_t &) CRWCP = {{.*}} (&::CRWCP = L'P')
+// CHECK: (const wchar_t &) CRWCP = {{.*}} (&::CRWCP = L'P')
// CHECK: (lldb) quit
int main(int argc, char **argv) {
return CIMax;
}
\ No newline at end of file
Index: lldb/include/lldb/lldb-enumerations.h
===================================================================
--- lldb/include/lldb/lldb-enumerations.h
+++ lldb/include/lldb/lldb-enumerations.h
@@ -162,6 +162,7 @@
eFormatBytes,
eFormatBytesWithASCII,
eFormatChar,
+ eFormatWchar,
eFormatCharPrintable, // Only printable characters, space if not printable
eFormatComplex, // Floating point complex type
eFormatComplexFloat = eFormatComplex,
_______________________________________________
lldb-commits mailing list
lldb-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/lldb-commits
