[Lldb-commits] [lldb] 46cdcf0 - [lldb] Add support for UTF-8 unicode formatting

[Luís Ferreira via lldb-commits]

Author: Luís Ferreira
Date: 2021-12-25T20:19:09Z
New Revision: 46cdcf08730012128173cd261767a7d12898c8d6

URL: https://github.com/llvm/llvm-project/commit/46cdcf08730012128173cd261767a7d12898c8d6
DIFF: https://github.com/llvm/llvm-project/commit/46cdcf08730012128173cd261767a7d12898c8d6.diff

LOG: [lldb] Add support for UTF-8 unicode formatting

This patch adds missing formatting for UTF-8 unicode.

Cross-referencing https://reviews.llvm.org/D66447

Reviewed By: labath

Differential Revision: https://reviews.llvm.org/D112564

Added: 
    

Modified: 
    lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp
    lldb/test/API/functionalities/data-formatter/builtin-formats/TestBuiltinFormats.py

Removed: 
    


################################################################################
diff  --git a/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp b/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp
index 0df95594eea2d..88c3aedb4c6b5 100644
--- a/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp
+++ b/lldb/source/Plugins/TypeSystem/Clang/TypeSystemClang.cpp
@@ -5149,6 +5149,8 @@ lldb::Format TypeSystemClang::GetFormat(lldb::opaque_compiler_type_t type) {
     case clang::BuiltinType::UChar:
     case clang::BuiltinType::WChar_U:
       return lldb::eFormatChar;
+    case clang::BuiltinType::Char8:
+      return lldb::eFormatUnicode8;
     case clang::BuiltinType::Char16:
       return lldb::eFormatUnicode16;
     case clang::BuiltinType::Char32:
@@ -8957,6 +8959,7 @@ bool TypeSystemClang::DumpTypeValue(
         case eFormatCharPrintable:
         case eFormatCharArray:
         case eFormatBytes:
+        case eFormatUnicode8:
         case eFormatBytesWithASCII:
           item_count = byte_size;
           byte_size = 1;

diff  --git a/lldb/test/API/functionalities/data-formatter/builtin-formats/TestBuiltinFormats.py b/lldb/test/API/functionalities/data-formatter/builtin-formats/TestBuiltinFormats.py
index c894b80228cfe..7763305b58db8 100644
--- a/lldb/test/API/functionalities/data-formatter/builtin-formats/TestBuiltinFormats.py
+++ b/lldb/test/API/functionalities/data-formatter/builtin-formats/TestBuiltinFormats.py
@@ -115,8 +115,7 @@ def test(self):
         self.assertIn('= \\0\\e90zaZA\\v\\t\\r\\n\\f\\b\\a \n', self.getFormatted("character array", string_expr))
         self.assertIn('= \\0\\e90zaZA\\v\\t\\r\\n\\f\\b\\a \n', self.getFormatted("character", string_expr))
         self.assertIn('= ..90zaZA....... \n', self.getFormatted("printable character", string_expr))
-        # FIXME: This should probably print the characters in the uint128_t.
-        self.assertIn('= 0x2007080c0a0d090b415a617a30391b00\n', self.getFormatted("unicode8", string_expr))
+        self.assertIn('= 0x00 0x1b 0x39 0x30 0x7a 0x61 0x5a 0x41 0x0b 0x09 0x0d 0x0a 0x0c 0x08 0x07 0x20\n', self.getFormatted("unicode8", string_expr))
 
         # OSType
         ostype_expr = "(__UINT64_TYPE__)0x"
@@ -137,6 +136,9 @@ def test(self):
         # bytes with ASCII
         self.assertIn(r'= " \U0000001b\a\b\f\n\r\t\vaA09\0"', self.getFormatted("bytes with ASCII", "cstring"))
 
+        # unicode8
+        self.assertIn('= 0x78 0x56 0x34 0x12\n', self.getFormatted("unicode8", "0x12345678"))
+
         # unicode16
         self.assertIn('= U+5678 U+1234\n', self.getFormatted("unicode16", "0x12345678"))