core: Implement len() on tuples. #489

Merged
sb10q merged 4 commits from feature/tuple-len into master 2024-08-13 15:02:59 +08:00
4 changed files with 135 additions and 105 deletions

View File

@ -1,17 +1,20 @@
use inkwell::types::BasicTypeEnum;
use inkwell::values::{BasicValue, BasicValueEnum, PointerValue};
use inkwell::values::{BasicValue, BasicValueEnum, IntValue, PointerValue};
use inkwell::{FloatPredicate, IntPredicate, OptimizationLevel};
use itertools::Itertools;
use crate::codegen::classes::{
NDArrayValue, ProxyValue, UntypedArrayLikeAccessor, UntypedArrayLikeMutator,
ArrayLikeValue, NDArrayValue, ProxyValue, RangeValue, TypedArrayLikeAccessor,
UntypedArrayLikeAccessor, UntypedArrayLikeMutator,
};
use crate::codegen::expr::destructure_range;
use crate::codegen::irrt::calculate_len_for_slice_range;
use crate::codegen::numpy::ndarray_elementwise_unaryop_impl;
use crate::codegen::stmt::gen_for_callback_incrementing;
use crate::codegen::{extern_fns, irrt, llvm_intrinsics, numpy, CodeGenContext, CodeGenerator};
use crate::toplevel::helper::PrimDef;
use crate::toplevel::numpy::unpack_ndarray_var_tys;
use crate::typecheck::typedef::Type;
use crate::typecheck::typedef::{Type, TypeEnum};
/// Shorthand for [`unreachable!()`] when a type of argument is not supported.
///
@ -23,6 +26,67 @@ fn unsupported_type(ctx: &CodeGenContext<'_, '_>, fn_name: &str, tys: &[Type]) -
)
}
/// Invokes the `len` builtin function.
pub fn call_len<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,
ctx: &mut CodeGenContext<'ctx, '_>,
n: (Type, BasicValueEnum<'ctx>),
) -> Result<IntValue<'ctx>, String> {
let llvm_i32 = ctx.ctx.i32_type();
let range_ty = ctx.primitives.range;
let (arg_ty, arg) = n;
Ok(if ctx.unifier.unioned(arg_ty, range_ty) {
let arg = RangeValue::from_ptr_val(arg.into_pointer_value(), Some("range"));
let (start, end, step) = destructure_range(ctx, arg);
calculate_len_for_slice_range(generator, ctx, start, end, step)
} else {
match &*ctx.unifier.get_ty_immutable(arg_ty) {
TypeEnum::TTuple { ty, .. } => llvm_i32.const_int(ty.len() as u64, false),
TypeEnum::TObj { obj_id, .. } if *obj_id == PrimDef::List.id() => {
let zero = llvm_i32.const_zero();
let len = ctx
.build_gep_and_load(
arg.into_pointer_value(),
&[zero, llvm_i32.const_int(1, false)],
None,
)
.into_int_value();
ctx.builder.build_int_truncate_or_bit_cast(len, llvm_i32, "len").unwrap()
}
TypeEnum::TObj { obj_id, .. } if *obj_id == PrimDef::NDArray.id() => {
let llvm_usize = generator.get_size_type(ctx.ctx);
let arg = NDArrayValue::from_ptr_val(arg.into_pointer_value(), llvm_usize, None);
let ndims = arg.dim_sizes().size(ctx, generator);
ctx.make_assert(
generator,
ctx.builder
.build_int_compare(IntPredicate::NE, ndims, llvm_usize.const_zero(), "")
.unwrap(),
"0:TypeError",
"len() of unsized object",
[None, None, None],
ctx.current_loc,
);
let len = unsafe {
arg.dim_sizes().get_typed_unchecked(
ctx,
generator,
&llvm_usize.const_zero(),
None,
)
};
ctx.builder.build_int_truncate_or_bit_cast(len, llvm_i32, "len").unwrap()
}
_ => unreachable!(),
}
})
}
/// Invokes the `int32` builtin function.
pub fn call_int32<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,

View File

@ -14,9 +14,7 @@ use strum::IntoEnumIterator;
use crate::{
codegen::{
builtin_fns,
classes::{ArrayLikeValue, NDArrayValue, ProxyValue, RangeValue, TypedArrayLikeAccessor},
expr::destructure_range,
irrt::*,
classes::{ProxyValue, RangeValue},
numpy::*,
stmt::exn_constructor,
},
@ -1466,36 +1464,21 @@ impl<'a> BuiltinBuilder<'a> {
fn build_len_function(&mut self) -> TopLevelDef {
let prim = PrimDef::FunLen;
let PrimitiveStore { uint64, int32, .. } = *self.primitives;
// Type handled in [`Inferencer::try_fold_special_call`]
let arg_tvar = self.unifier.get_dummy_var();
let tvar = self.unifier.get_fresh_var(Some("L".into()), None);
let list = self
.unifier
.subst(
self.primitives.list,
&into_var_map([TypeVar { id: self.list_tvar.id, ty: tvar.ty }]),
)
.unwrap();
let ndims = self.unifier.get_fresh_const_generic_var(uint64, Some("N".into()), None);
let ndarray = make_ndarray_ty(self.unifier, self.primitives, Some(tvar.ty), Some(ndims.ty));
let arg_ty = self.unifier.get_fresh_var_with_range(
&[list, ndarray, self.primitives.range],
Some("I".into()),
None,
);
TopLevelDef::Function {
name: prim.name().into(),
simple_name: prim.simple_name().into(),
signature: self.unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![FuncArg {
name: "ls".into(),
ty: arg_ty.ty,
name: "obj".into(),
ty: arg_tvar.ty,
default_value: None,
is_vararg: false,
}],
ret: int32,
vars: into_var_map([tvar, arg_ty]),
ret: self.primitives.int32,
vars: into_var_map([arg_tvar]),
})),
var_id: Vec::default(),
instance_to_symbol: HashMap::default(),
@ -1503,86 +1486,10 @@ impl<'a> BuiltinBuilder<'a> {
resolver: None,
codegen_callback: Some(Arc::new(GenCall::new(Box::new(
move |ctx, _, fun, args, generator| {
let range_ty = ctx.primitives.range;
let arg_ty = fun.0.args[0].ty;
let arg = args[0].1.clone().to_basic_value_enum(ctx, generator, arg_ty)?;
Ok(if ctx.unifier.unioned(arg_ty, range_ty) {
let arg = RangeValue::from_ptr_val(arg.into_pointer_value(), Some("range"));
let (start, end, step) = destructure_range(ctx, arg);
Some(calculate_len_for_slice_range(generator, ctx, start, end, step).into())
} else {
match &*ctx.unifier.get_ty_immutable(arg_ty) {
TypeEnum::TObj { obj_id, .. } if *obj_id == PrimDef::List.id() => {
let int32 = ctx.ctx.i32_type();
let zero = int32.const_zero();
let len = ctx
.build_gep_and_load(
arg.into_pointer_value(),
&[zero, int32.const_int(1, false)],
None,
)
.into_int_value();
if len.get_type().get_bit_width() == 32 {
Some(len.into())
} else {
Some(
ctx.builder
.build_int_truncate(len, int32, "len2i32")
.map(Into::into)
.unwrap(),
)
}
}
TypeEnum::TObj { obj_id, .. } if *obj_id == PrimDef::NDArray.id() => {
let llvm_i32 = ctx.ctx.i32_type();
let llvm_usize = generator.get_size_type(ctx.ctx);
let arg = NDArrayValue::from_ptr_val(
arg.into_pointer_value(),
llvm_usize,
None,
);
let ndims = arg.dim_sizes().size(ctx, generator);
ctx.make_assert(
generator,
ctx.builder
.build_int_compare(
IntPredicate::NE,
ndims,
llvm_usize.const_zero(),
"",
)
.unwrap(),
"0:TypeError",
&format!("{name}() of unsized object", name = prim.name()),
[None, None, None],
ctx.current_loc,
);
let len = unsafe {
arg.dim_sizes().get_typed_unchecked(
ctx,
generator,
&llvm_usize.const_zero(),
None,
)
};
if len.get_type().get_bit_width() == 32 {
Some(len.into())
} else {
Some(
ctx.builder
.build_int_truncate(len, llvm_i32, "len")
.map(Into::into)
.unwrap(),
)
}
}
_ => unreachable!(),
}
})
builtin_fns::call_len(generator, ctx, (arg_ty, arg)).map(|ret| Some(ret.into()))
},
)))),
loc: None,

View File

@ -1069,6 +1069,58 @@ impl<'a> Inferencer<'a> {
}));
}
if id == &"len".into() && args.len() == 1 {
let obj = self.fold_expr(args.remove(0))?;
let obj_ty = obj.custom.unwrap();
match &*self.unifier.get_ty(obj_ty) {
TypeEnum::TObj { obj_id, .. }
if *obj_id == self.primitives.range.obj_id(self.unifier).unwrap() => {}
TypeEnum::TObj { obj_id, .. }
if *obj_id == self.primitives.list.obj_id(self.unifier).unwrap() => {}
TypeEnum::TObj { obj_id, .. }
if *obj_id == self.primitives.ndarray.obj_id(self.unifier).unwrap() => {}
TypeEnum::TTuple { .. } => {}
_ => {
return report_error(
format!(
"len() only accepts range, list, ndarray, or tuple. Got {}",
self.unifier.stringify(obj_ty)
)
.as_str(),
obj.location,
)
}
}
let ret_ty = self.primitives.int32;
let func_ty = self.unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![FuncArg {
name: "obj".into(),
ty: obj_ty,
default_value: None,
is_vararg: false,
}],
ret: ret_ty,
vars: VarMap::new(),
}));
return Ok(Some(Located {
location,
custom: Some(ret_ty),
node: ExprKind::Call {
func: Box::new(Located {
custom: Some(func_ty),
location: func.location,
node: ExprKind::Name { id: *id, ctx: *ctx },
}),
args: vec![obj],
keywords: vec![],
},
}));
}
if ["int32", "float", "bool", "round", "round64", "np_isnan", "np_isinf"]
.iter()
.any(|fun_id| id == &(*fun_id).into())

View File

@ -26,4 +26,11 @@ def run() -> int32:
output_int32(tl[0][1])
output_int32(tl[1])
output_int32(len(()))
output_int32(len((1,)))
output_int32(len((1, 2)))
output_int32(len((1, 2, 3)))
output_int32(len((1, 2, 3, 4)))
output_int32(len((1, 2, 3, 4, 5)))
return 0