carbon-language/carbon-lang
1
0
Fork 0
mirror of https://github.com/carbon-language/carbon-lang.git synced 2026-10-05 22:02:55 +01:00
Code Issues Packages Projects Releases 10 Wiki Activity

Support parse/check/lower for char (#5901)

Browse Source 
toolchain/check/testdata/builtins/char/basics.carbon and
toolchain/lower/testdata/builtins/char.carbon are probably the most
interesting tests here. The parse tests is required because this adds a
new node kind, and we need coverage of it; but the attached info is
minor. There's a fair amount of test churn here because I'm adding the
Core.Char and Core.CharLiteral types as new singletons.

My intent here is that `CharId` is always a unicode code point, even
when the type is a `Char` and thus must be a single UTF-8 code unit
(single byte). This mainly means the stored value of a `CharValue` can
be printed internally without knowing the type.

---------

Co-authored-by: josh11b <15258583+josh11b@users.noreply.github.com>
Co-authored-by: Richard Smith <richard@metafoo.co.uk>
This commit is contained in:
Jon Ross-Perkins
2025-08-06 20:39:01 +00:00
committed by GitHub
co-authored by josh11b Richard Smith
parent 9c7e0f6bd5
commit 37d5046ceb
109 changed files with 1520 additions and 1077 deletions
Download Patch File Download Diff File Expand all files Collapse all files
toolchain/check/eval.cpp
+36
View File
@@ -9,6 +9,7 @@
#include <optional>
#include <utility>
#include "llvm/Support/ConvertUTF.h"
#include "toolchain/base/canonical_value_store.h"
#include "toolchain/base/kind_switch.h"
#include "toolchain/check/action.h"
@@ -951,6 +952,28 @@ static auto PerformArrayIndex(EvalContext& eval_context, SemIR::ArrayIndex inst)
return eval_context.GetConstantValue(elements[index_val.getZExtValue()]);
}
// Performs a conversion between character types, diagnosing if the value
// doesn't fit in the destination type.
static auto PerformCheckedCharConvert(Context& context, SemIR::LocId loc_id,
SemIR::InstId arg_id,
SemIR::TypeId dest_type_id)
-> SemIR::ConstantId {
auto arg = context.insts().GetAs<SemIR::CharLiteralValue>(arg_id);
// Values over 0x80 require multiple code units in UTF-8.
if (arg.value.index >= 0x80) {
CARBON_DIAGNOSTIC(CharTooLargeForType, Error,
"character value {0} too large for type {1}",
SemIR::CharId, SemIR::TypeId);
context.emitter().Emit(loc_id, CharTooLargeForType, arg.value,
dest_type_id);
return SemIR::ErrorInst::ConstantId;
}
llvm::APInt int_val(8, arg.value.index, /*isSigned=*/false);
return MakeIntResult(context, dest_type_id, /*is_signed=*/false, int_val);
}
// Forms a constant int type as an evaluation result. Requires that width_id is
// constant.
static auto MakeIntTypeResult(Context& context, SemIR::LocId loc_id,
@@ -1590,6 +1613,10 @@ static auto MakeConstantForBuiltinCall(EvalContext& eval_context,
return MakeFacetTypeResult(eval_context.context(), combined_info, phase);
}
case SemIR::BuiltinFunctionKind::CharLiteralMakeType: {
return context.constant_values().Get(SemIR::CharLiteralType::TypeInstId);
}
case SemIR::BuiltinFunctionKind::IntLiteralMakeType: {
return context.constant_values().Get(SemIR::IntLiteralType::TypeInstId);
}
@@ -1619,6 +1646,15 @@ static auto MakeConstantForBuiltinCall(EvalContext& eval_context,
return context.constant_values().Get(SemIR::BoolType::TypeInstId);
}
// Character conversions.
case SemIR::BuiltinFunctionKind::CharConvertChecked: {
if (phase != Phase::Concrete) {
return MakeConstantResult(context, call, phase);
}
return PerformCheckedCharConvert(context, loc_id, arg_ids[0],
call.type_id);
}
// Integer conversions.
case SemIR::BuiltinFunctionKind::IntConvert: {
if (phase != Phase::Concrete) {