2022-08-16 18:09:26 +03:00
|
|
|
(* This file is part of the Catala compiler, a specification language for tax
|
|
|
|
and social benefits computation rules. Copyright (C) 2020-2022 Inria,
|
|
|
|
contributor: Denis Merigoux <denis.merigoux@inria.fr>, Alain Delaët-Tixeuil
|
|
|
|
<alain.delaet--tixeuil@inria.fr>, Louis Gesbert <louis.gesbert@inria.fr>
|
|
|
|
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License"); you may not
|
|
|
|
use this file except in compliance with the License. You may obtain a copy of
|
|
|
|
the License at
|
|
|
|
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
|
|
distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
|
|
|
|
WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
|
|
|
|
License for the specific language governing permissions and limitations under
|
|
|
|
the License. *)
|
|
|
|
|
2023-02-13 17:00:23 +03:00
|
|
|
(** Functions handling the code item structures of [shared_ast], in particular
|
|
|
|
the scopes *)
|
2022-08-16 18:09:26 +03:00
|
|
|
|
2022-11-21 12:46:17 +03:00
|
|
|
open Catala_utils
|
2022-08-22 19:53:30 +03:00
|
|
|
open Definitions
|
2022-08-16 18:09:26 +03:00
|
|
|
|
|
|
|
(** {2 Traversal functions} *)
|
|
|
|
|
|
|
|
val map_exprs_in_lets :
|
2024-02-09 18:48:02 +03:00
|
|
|
?typ:(typ -> typ) ->
|
Swap boxing and annotations in expressions
This was the only reasonable solution I found to the issue raised
[here](https://github.com/CatalaLang/catala/pull/334#discussion_r987175884).
This was a pretty tedious rewrite, but it should now ensure we are doing things
correctly. As a bonus, the "smart" expression constructors are now used
everywhere to build expressions (so another refactoring like this one should be
much easier) and this makes the code overall feel more
straightforward (`Bindlib.box_apply` or `let+` no longer need to be visible!)
---
Basically, we were using values of type `gexpr box = naked_gexpr marked box`
throughout when (re-)building expressions. This was done 99% of the time by
using `Bindlib.box_apply add_mark naked_e` right after building `naked_e`. In
lots of places, we needed to recover the annotation of this expression later on,
typically to build its parent term (to inherit the position, or build the type).
Since it wasn't always possible to wrap these uses within `box_apply` (esp. as
bindlib boxes aren't a monad), here and there we had to call `Bindlib.unbox`,
just to recover the position or type. This had the very unpleasant effect of
forcing the resolution of the whole box (including applying any stored closures)
to reach the top-level annotation which isn't even dependant on specific
variable bindings. Then, generally, throwing away the result.
Therefore, the change proposed here transforms
- `naked_gexpr marked Bindlib.box` into
- `naked_gexpr Bindlib.box marked` (aliased to `boxed_gexpr` or `gexpr boxed` for
convenience)
This means only
1. not fitting the mark into the box right away when building, and
2. accessing the top-level mark directly without unboxing
The functions for building terms from module `Shared_ast.Expr` could be changed
easily. But then they needed to be consistently used throughout, without
manually building terms through `Bindlib.apply_box` -- which covers most of the
changes in this patch.
`Expr.Box.inj` is provided to swap back to a box, before binding for example.
Additionally, this gives a 40% speedup on `make -C examples pass_all_tests`,
which hints at the amount of unnecessary work we were doing --'
2022-10-06 20:13:45 +03:00
|
|
|
f:('expr1 -> 'expr2 boxed) ->
|
2022-08-25 20:46:13 +03:00
|
|
|
varf:('expr1 Var.t -> 'expr2 Var.t) ->
|
2022-08-16 18:09:26 +03:00
|
|
|
'expr1 scope_body_expr ->
|
Swap boxing and annotations in expressions
This was the only reasonable solution I found to the issue raised
[here](https://github.com/CatalaLang/catala/pull/334#discussion_r987175884).
This was a pretty tedious rewrite, but it should now ensure we are doing things
correctly. As a bonus, the "smart" expression constructors are now used
everywhere to build expressions (so another refactoring like this one should be
much easier) and this makes the code overall feel more
straightforward (`Bindlib.box_apply` or `let+` no longer need to be visible!)
---
Basically, we were using values of type `gexpr box = naked_gexpr marked box`
throughout when (re-)building expressions. This was done 99% of the time by
using `Bindlib.box_apply add_mark naked_e` right after building `naked_e`. In
lots of places, we needed to recover the annotation of this expression later on,
typically to build its parent term (to inherit the position, or build the type).
Since it wasn't always possible to wrap these uses within `box_apply` (esp. as
bindlib boxes aren't a monad), here and there we had to call `Bindlib.unbox`,
just to recover the position or type. This had the very unpleasant effect of
forcing the resolution of the whole box (including applying any stored closures)
to reach the top-level annotation which isn't even dependant on specific
variable bindings. Then, generally, throwing away the result.
Therefore, the change proposed here transforms
- `naked_gexpr marked Bindlib.box` into
- `naked_gexpr Bindlib.box marked` (aliased to `boxed_gexpr` or `gexpr boxed` for
convenience)
This means only
1. not fitting the mark into the box right away when building, and
2. accessing the top-level mark directly without unboxing
The functions for building terms from module `Shared_ast.Expr` could be changed
easily. But then they needed to be consistently used throughout, without
manually building terms through `Bindlib.apply_box` -- which covers most of the
changes in this patch.
`Expr.Box.inj` is provided to swap back to a box, before binding for example.
Additionally, this gives a 40% speedup on `make -C examples pass_all_tests`,
which hints at the amount of unnecessary work we were doing --'
2022-10-06 20:13:45 +03:00
|
|
|
'expr2 scope_body_expr Bindlib.box
|
2023-03-28 10:38:47 +03:00
|
|
|
(** Usage
|
|
|
|
[map_exprs_in_lets ~f:(fun e -> ...) ~varf:(fun var -> ...) scope_body_expr],
|
|
|
|
where [e] is the right-hand-side of a scope let or the result of the scope
|
|
|
|
body, and [var] represents the left-hand-side variable of a scope let.
|
|
|
|
[~varf] is usually the identity function or [Var.translate] when the map
|
|
|
|
sends the expression to a new flavor of the shared AST. If [~reset_types] is
|
|
|
|
activated, then the resulting types in the scope let left-hand-sides will be
|
|
|
|
reset to [TAny]. *)
|
2022-08-16 18:09:26 +03:00
|
|
|
|
|
|
|
val map_exprs :
|
2024-02-09 18:48:02 +03:00
|
|
|
?typ:(typ -> typ) ->
|
Swap boxing and annotations in expressions
This was the only reasonable solution I found to the issue raised
[here](https://github.com/CatalaLang/catala/pull/334#discussion_r987175884).
This was a pretty tedious rewrite, but it should now ensure we are doing things
correctly. As a bonus, the "smart" expression constructors are now used
everywhere to build expressions (so another refactoring like this one should be
much easier) and this makes the code overall feel more
straightforward (`Bindlib.box_apply` or `let+` no longer need to be visible!)
---
Basically, we were using values of type `gexpr box = naked_gexpr marked box`
throughout when (re-)building expressions. This was done 99% of the time by
using `Bindlib.box_apply add_mark naked_e` right after building `naked_e`. In
lots of places, we needed to recover the annotation of this expression later on,
typically to build its parent term (to inherit the position, or build the type).
Since it wasn't always possible to wrap these uses within `box_apply` (esp. as
bindlib boxes aren't a monad), here and there we had to call `Bindlib.unbox`,
just to recover the position or type. This had the very unpleasant effect of
forcing the resolution of the whole box (including applying any stored closures)
to reach the top-level annotation which isn't even dependant on specific
variable bindings. Then, generally, throwing away the result.
Therefore, the change proposed here transforms
- `naked_gexpr marked Bindlib.box` into
- `naked_gexpr Bindlib.box marked` (aliased to `boxed_gexpr` or `gexpr boxed` for
convenience)
This means only
1. not fitting the mark into the box right away when building, and
2. accessing the top-level mark directly without unboxing
The functions for building terms from module `Shared_ast.Expr` could be changed
easily. But then they needed to be consistently used throughout, without
manually building terms through `Bindlib.apply_box` -- which covers most of the
changes in this patch.
`Expr.Box.inj` is provided to swap back to a box, before binding for example.
Additionally, this gives a 40% speedup on `make -C examples pass_all_tests`,
which hints at the amount of unnecessary work we were doing --'
2022-10-06 20:13:45 +03:00
|
|
|
f:('expr1 -> 'expr2 boxed) ->
|
2022-08-25 20:46:13 +03:00
|
|
|
varf:('expr1 Var.t -> 'expr2 Var.t) ->
|
2023-01-23 14:19:36 +03:00
|
|
|
'expr1 code_item_list ->
|
|
|
|
'expr2 code_item_list Bindlib.box
|
2022-08-16 18:09:26 +03:00
|
|
|
(** This is the main map visitor for all the expressions inside all the scopes
|
|
|
|
of the program. *)
|
|
|
|
|
Implement safe renaming of idents for backend printing
Previously we had some heuristics in the backends trying to achieve this with a
lot of holes ; this should be much more solid, relying on `Bindlib` to do the
correct renamings.
**Note1**: it's not plugged into the backends other than OCaml at the moment.
**Note2**: the related, obsolete heuristics haven't been cleaned out yet
**Note3**: we conservatively suppose a single namespace at the moment. This is
required for e.g. Python, but it forces vars named like struct fields to be
renamed, which is more verbose in e.g. OCaml. The renaming engine could be
improved to support different namespaces, with a way to select how to route the
different kinds of identifiers into them.
Similarly, customisation for what needs to be uppercase or lowercase is not
available yet.
**Note4**: besides excluding keywords, we should also be careful to exclude (or
namespace):
- the idents used in the runtime (e.g. `o_add_int_int`)
- the dynamically generated idents (e.g. `embed_*`)
**Note5**: module names themselves aren't handled yet. The reason is that they
must be discoverable by the user, and even need to match the filenames, etc. In
other words, imagine that `Mod` is a keyword in the target language. You can't
rename a module called `Mod` to `Mod1` without knowing the whole module context,
because that would destroy the mapping for a module already called `Mod1`.
A reliable solution would be to translate all module names to e.g.
`CatalaModule_*`, which we can assume will never conflict with any built-in, and
forbid idents starting with that prefix. We may also want to restrict their
names to ASCII ? Currently we use a projection, but what if I have two modules
called `Là` and `La` ?
2024-08-05 18:08:36 +03:00
|
|
|
val map_last_item :
|
|
|
|
varf:(('a, 'm) naked_gexpr Bindlib.var -> 'e2 Bindlib.var) ->
|
|
|
|
('a, 'm) naked_gexpr list ->
|
|
|
|
'e2 list Bindlib.box
|
|
|
|
|
|
|
|
(** Helper function to handle the [code_item_list] terminator when manually
|
|
|
|
mapping on [code_item_list] *)
|
|
|
|
|
2024-02-09 18:48:02 +03:00
|
|
|
val fold_exprs :
|
|
|
|
f:('acc -> 'expr -> typ -> 'acc) -> init:'acc -> 'expr code_item_list -> 'acc
|
2022-08-17 12:49:16 +03:00
|
|
|
|
|
|
|
(** {2 Conversions} *)
|
|
|
|
|
2024-02-09 18:48:02 +03:00
|
|
|
val to_expr : decl_ctx -> ('a any, 'm) gexpr scope_body -> ('a, 'm) boxed_gexpr
|
2022-08-17 12:49:16 +03:00
|
|
|
(** Usage: [to_expr ctx body scope_position] where [scope_position] corresponds
|
|
|
|
to the line of the scope declaration for instance. *)
|
|
|
|
|
|
|
|
val unfold :
|
2024-02-09 18:48:02 +03:00
|
|
|
decl_ctx -> ((_, 'm) gexpr as 'e) code_item_list -> ScopeName.t -> 'e boxed
|
|
|
|
|
|
|
|
val typ : _ scope_body -> typ
|
|
|
|
(** builds the arrow type for the specified scope *)
|
2022-08-17 12:49:16 +03:00
|
|
|
|
2023-11-03 19:15:55 +03:00
|
|
|
val input_type : typ -> Runtime.io_input Mark.pos -> typ
|
2023-11-07 20:25:57 +03:00
|
|
|
(** Returns the correct input type for scope input variables: this is [typ] for
|
|
|
|
non-reentrant variables, but for reentrant variables, it is nested in a
|
|
|
|
[TDefault], which only applies to the return type on functions. Note that
|
|
|
|
this doesn't take thunking into account (thunking is added during the
|
|
|
|
scopelang->dcalc translation) *)
|
2023-11-03 19:15:55 +03:00
|
|
|
|
2022-08-17 12:49:16 +03:00
|
|
|
(** {2 Analysis and tests} *)
|
|
|
|
|
2022-08-26 12:06:00 +03:00
|
|
|
val free_vars_body_expr : 'e scope_body_expr -> 'e Var.Set.t
|
2023-01-23 14:19:36 +03:00
|
|
|
val free_vars_item : 'e code_item -> 'e Var.Set.t
|
|
|
|
val free_vars : 'e code_item_list -> 'e Var.Set.t
|