[Lldb-commits] [clang] [lldb] [lldb] Re-use clang's keyword enable/disable mechanism in CPlusPlusNameParser.cpp (PR #164284)
via lldb-commits
lldb-commits at lists.llvm.org
Mon Oct 20 10:25:56 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
Author: Daniel Sanders (dsandersllvm)
<details>
<summary>Changes</summary>
The problem is that CPlusPlusNameParser doesn't respect the language dialect for `target variable Class::constant`. If `constant` is a keyword in some (downstream in this case) dialects then it lexes `constant` as `kw_constant` instead of `kw_raw_identifier` even if that dialect is not active. As a result:
* `target variable constant` works
* `target variable Class::constant` fails to look up constant because it sees `kw_raw_identifier, kw_coloncolon, kw_constant` instead of `kw_raw_identifier, kw_coloncolon, kw_raw_identifier`
* `expr -l c++ -- Class::constant` works because clang is parsing it
Note: There's seemingly a separate bug where GetLangOptions() does not account for the process/frame language and just uses a pre-defined set of language options. I have not attempted to fix that since, for now, at least hardcoding my dialect to be disabled by that function does the right thing for existing tests.
Also fixed a trivial return-after-else that clangd pointed out in the same area
---
Full diff: https://github.com/llvm/llvm-project/pull/164284.diff
3 Files Affected:
- (modified) clang/include/clang/Basic/IdentifierTable.h (+53)
- (modified) clang/lib/Basic/IdentifierTable.cpp (+1-52)
- (modified) lldb/source/Plugins/Language/CPlusPlus/CPlusPlusNameParser.cpp (+13-7)
``````````diff
diff --git a/clang/include/clang/Basic/IdentifierTable.h b/clang/include/clang/Basic/IdentifierTable.h
index e4044bcdfcc60..8177029f13ca9 100644
--- a/clang/include/clang/Basic/IdentifierTable.h
+++ b/clang/include/clang/Basic/IdentifierTable.h
@@ -46,6 +46,59 @@ class LangOptions;
class MultiKeywordSelector;
class SourceLocation;
+// This is an inline namespace to allow both clang and lldb to use them without
+// namespace prefixes (via `using namespace` in lldb's case).
+inline namespace TokenKeyEnumerators {
+enum TokenKey : unsigned {
+ KEYC99 = 0x1,
+ KEYCXX = 0x2,
+ KEYCXX11 = 0x4,
+ KEYGNU = 0x8,
+ KEYMS = 0x10,
+ BOOLSUPPORT = 0x20,
+ KEYALTIVEC = 0x40,
+ KEYNOCXX = 0x80,
+ KEYBORLAND = 0x100,
+ KEYOPENCLC = 0x200,
+ KEYC23 = 0x400,
+ KEYNOMS18 = 0x800,
+ KEYNOOPENCL = 0x1000,
+ WCHARSUPPORT = 0x2000,
+ HALFSUPPORT = 0x4000,
+ CHAR8SUPPORT = 0x8000,
+ KEYOBJC = 0x10000,
+ KEYZVECTOR = 0x20000,
+ KEYCOROUTINES = 0x40000,
+ KEYMODULES = 0x80000,
+ KEYCXX20 = 0x100000,
+ KEYOPENCLCXX = 0x200000,
+ KEYMSCOMPAT = 0x400000,
+ KEYSYCL = 0x800000,
+ KEYCUDA = 0x1000000,
+ KEYZOS = 0x2000000,
+ KEYNOZOS = 0x4000000,
+ KEYHLSL = 0x8000000,
+ KEYFIXEDPOINT = 0x10000000,
+ KEYMAX = KEYFIXEDPOINT, // The maximum key
+ KEYALLCXX = KEYCXX | KEYCXX11 | KEYCXX20,
+ KEYALL = (KEYMAX | (KEYMAX - 1)) & ~KEYNOMS18 & ~KEYNOOPENCL &
+ ~KEYNOZOS // KEYNOMS18, KEYNOOPENCL, KEYNOZOS are excluded.
+};
+} // namespace TokenKeyEnumerators
+
+/// How a keyword is treated in the selected standard. This enum is ordered
+/// intentionally so that the value that 'wins' is the most 'permissive'.
+enum KeywordStatus {
+ KS_Unknown, // Not yet calculated. Used when figuring out the status.
+ KS_Disabled, // Disabled
+ KS_Future, // Is a keyword in future standard
+ KS_Extension, // Is an extension
+ KS_Enabled, // Enabled
+};
+
+KeywordStatus getKeywordStatus(const LangOptions &LangOpts,
+ unsigned Flags);
+
enum class ReservedIdentifierStatus {
NotReserved = 0,
StartsWithUnderscoreAtGlobalScope,
diff --git a/clang/lib/Basic/IdentifierTable.cpp b/clang/lib/Basic/IdentifierTable.cpp
index 4a2b77cd16bfc..65ed1273350c5 100644
--- a/clang/lib/Basic/IdentifierTable.cpp
+++ b/clang/lib/Basic/IdentifierTable.cpp
@@ -77,57 +77,6 @@ IdentifierTable::IdentifierTable(const LangOptions &LangOpts,
// Language Keyword Implementation
//===----------------------------------------------------------------------===//
-// Constants for TokenKinds.def
-namespace {
-
-enum TokenKey : unsigned {
- KEYC99 = 0x1,
- KEYCXX = 0x2,
- KEYCXX11 = 0x4,
- KEYGNU = 0x8,
- KEYMS = 0x10,
- BOOLSUPPORT = 0x20,
- KEYALTIVEC = 0x40,
- KEYNOCXX = 0x80,
- KEYBORLAND = 0x100,
- KEYOPENCLC = 0x200,
- KEYC23 = 0x400,
- KEYNOMS18 = 0x800,
- KEYNOOPENCL = 0x1000,
- WCHARSUPPORT = 0x2000,
- HALFSUPPORT = 0x4000,
- CHAR8SUPPORT = 0x8000,
- KEYOBJC = 0x10000,
- KEYZVECTOR = 0x20000,
- KEYCOROUTINES = 0x40000,
- KEYMODULES = 0x80000,
- KEYCXX20 = 0x100000,
- KEYOPENCLCXX = 0x200000,
- KEYMSCOMPAT = 0x400000,
- KEYSYCL = 0x800000,
- KEYCUDA = 0x1000000,
- KEYZOS = 0x2000000,
- KEYNOZOS = 0x4000000,
- KEYHLSL = 0x8000000,
- KEYFIXEDPOINT = 0x10000000,
- KEYMAX = KEYFIXEDPOINT, // The maximum key
- KEYALLCXX = KEYCXX | KEYCXX11 | KEYCXX20,
- KEYALL = (KEYMAX | (KEYMAX - 1)) & ~KEYNOMS18 & ~KEYNOOPENCL &
- ~KEYNOZOS // KEYNOMS18, KEYNOOPENCL, KEYNOZOS are excluded.
-};
-
-/// How a keyword is treated in the selected standard. This enum is ordered
-/// intentionally so that the value that 'wins' is the most 'permissive'.
-enum KeywordStatus {
- KS_Unknown, // Not yet calculated. Used when figuring out the status.
- KS_Disabled, // Disabled
- KS_Future, // Is a keyword in future standard
- KS_Extension, // Is an extension
- KS_Enabled, // Enabled
-};
-
-} // namespace
-
// This works on a single TokenKey flag and checks the LangOpts to get the
// KeywordStatus based exclusively on this flag, so that it can be merged in
// getKeywordStatus. Most should be enabled/disabled, but some might imply
@@ -222,7 +171,7 @@ static KeywordStatus getKeywordStatusHelper(const LangOptions &LangOpts,
/// Translates flags as specified in TokenKinds.def into keyword status
/// in the given language standard.
-static KeywordStatus getKeywordStatus(const LangOptions &LangOpts,
+KeywordStatus clang::getKeywordStatus(const LangOptions &LangOpts,
unsigned Flags) {
// KEYALL means always enabled, so special case this one.
if (Flags == KEYALL) return KS_Enabled;
diff --git a/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusNameParser.cpp b/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusNameParser.cpp
index d8c095d6edeb7..13cea5e513005 100644
--- a/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusNameParser.cpp
+++ b/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusNameParser.cpp
@@ -719,9 +719,8 @@ CPlusPlusNameParser::ParseFullNameImpl() {
}
start_position.Remove();
return result;
- } else {
- return std::nullopt;
}
+ return std::nullopt;
}
llvm::StringRef CPlusPlusNameParser::GetTextForRange(const Range &range) {
@@ -755,12 +754,19 @@ static const clang::LangOptions &GetLangOptions() {
return g_options;
}
-static const llvm::StringMap<tok::TokenKind> &GetKeywordsMap() {
- static llvm::StringMap<tok::TokenKind> g_map{
-#define KEYWORD(Name, Flags) {llvm::StringRef(#Name), tok::kw_##Name},
+static const llvm::StringMap<tok::TokenKind> GetKeywordsMap() {
+ using namespace clang::TokenKeyEnumerators;
+ llvm::StringMap<tok::TokenKind> g_map;
+
+ auto LangOpts = GetLangOptions();
+
+ clang::KeywordStatus AddResult;
+#define KEYWORD(NAME, FLAGS) \
+ AddResult = getKeywordStatus(LangOpts, FLAGS); \
+ if (AddResult != clang::KS_Disabled) \
+ g_map[llvm::StringRef(#NAME)] = tok::kw_##NAME;
#include "clang/Basic/TokenKinds.def"
#undef KEYWORD
- };
return g_map;
}
@@ -769,7 +775,7 @@ void CPlusPlusNameParser::ExtractTokens() {
return;
clang::Lexer lexer(clang::SourceLocation(), GetLangOptions(), m_text.data(),
m_text.data(), m_text.data() + m_text.size());
- const auto &kw_map = GetKeywordsMap();
+ const auto kw_map = GetKeywordsMap();
clang::Token token;
for (lexer.LexFromRawLexer(token); !token.is(clang::tok::eof);
lexer.LexFromRawLexer(token)) {
``````````
</details>
https://github.com/llvm/llvm-project/pull/164284
More information about the lldb-commits
mailing list