2024-12-11 19:30:33 +03:00
|
|
|
#![cfg_attr(not(bootstrap), allow(rustc::symbol_intern_string_literal))]
|
|
|
|
|
2024-02-13 23:28:27 +00:00
|
|
|
use rustc_ast::token::{self, IdentIsRaw};
|
Remove `TokenStreamBuilder`.
`TokenStreamBuilder` exists to concatenate multiple `TokenStream`s
together. This commit removes it, and moves the concatenation
functionality directly into `TokenStream`, via two new methods
`push_tree` and `push_stream`. This makes things both simpler and
faster.
`push_tree` is particularly important. `TokenStreamBuilder` only had a
single `push` method, which pushed a stream. But in practice most of the
time we push a single token tree rather than a stream, and `push_tree`
avoids the need to build a token stream with a single entry (which
requires two allocations, one for the `Lrc` and one for the `Vec`).
The main `push_tree` use arises from a change to one of the `ToInternal`
impls in `proc_macro_server.rs`. It now returns a `SmallVec` instead of
a `TokenStream`. This return value is then iterated over by
`concat_trees`, which does `push_tree` on each element. Furthermore, the
use of `SmallVec` avoids more allocations, because there is always only
one or two token trees.
Note: the removed `TokenStreamBuilder::push` method had some code to
deal with a quadratic blowup case from #57735. This commit removes the
code. I tried and failed to reproduce the blowup from that PR, before
and after this change. Various other changes have happened to
`TokenStreamBuilder` in the meantime, so I suspect the original problem
is no longer relevant, though I don't have proof of this. Generally
speaking, repeatedly extending a `Vec` without pre-determining its
capacity is *not* quadratic. It's also incredibly common, within rustc
and many other Rust programs, so if there were performance problems
there you'd think it would show up in other places, too.
2022-10-05 10:38:15 +11:00
|
|
|
use rustc_ast::tokenstream::{TokenStream, TokenTree};
|
2021-05-05 21:31:25 +02:00
|
|
|
use rustc_span::{BytePos, Span, Symbol, create_default_session_globals_then};
|
2024-07-29 08:13:50 +10:00
|
|
|
|
2020-04-25 21:13:56 +02:00
|
|
|
use crate::parser::tests::string_to_stream;
|
2019-08-02 00:26:40 +03:00
|
|
|
|
|
|
|
fn string_to_ts(string: &str) -> TokenStream {
|
|
|
|
string_to_stream(string.to_owned())
|
|
|
|
}
|
|
|
|
|
|
|
|
fn sp(a: u32, b: u32) -> Span {
|
2019-08-11 01:44:55 +03:00
|
|
|
Span::with_root_ctxt(BytePos(a), BytePos(b))
|
2019-08-02 00:26:40 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_concat() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
2019-08-02 00:26:40 +03:00
|
|
|
let test_res = string_to_ts("foo::bar::baz");
|
|
|
|
let test_fst = string_to_ts("foo::bar");
|
|
|
|
let test_snd = string_to_ts("::baz");
|
Remove `TokenStreamBuilder`.
`TokenStreamBuilder` exists to concatenate multiple `TokenStream`s
together. This commit removes it, and moves the concatenation
functionality directly into `TokenStream`, via two new methods
`push_tree` and `push_stream`. This makes things both simpler and
faster.
`push_tree` is particularly important. `TokenStreamBuilder` only had a
single `push` method, which pushed a stream. But in practice most of the
time we push a single token tree rather than a stream, and `push_tree`
avoids the need to build a token stream with a single entry (which
requires two allocations, one for the `Lrc` and one for the `Vec`).
The main `push_tree` use arises from a change to one of the `ToInternal`
impls in `proc_macro_server.rs`. It now returns a `SmallVec` instead of
a `TokenStream`. This return value is then iterated over by
`concat_trees`, which does `push_tree` on each element. Furthermore, the
use of `SmallVec` avoids more allocations, because there is always only
one or two token trees.
Note: the removed `TokenStreamBuilder::push` method had some code to
deal with a quadratic blowup case from #57735. This commit removes the
code. I tried and failed to reproduce the blowup from that PR, before
and after this change. Various other changes have happened to
`TokenStreamBuilder` in the meantime, so I suspect the original problem
is no longer relevant, though I don't have proof of this. Generally
speaking, repeatedly extending a `Vec` without pre-determining its
capacity is *not* quadratic. It's also incredibly common, within rustc
and many other Rust programs, so if there were performance problems
there you'd think it would show up in other places, too.
2022-10-05 10:38:15 +11:00
|
|
|
let mut eq_res = TokenStream::default();
|
|
|
|
eq_res.push_stream(test_fst);
|
|
|
|
eq_res.push_stream(test_snd);
|
2019-08-02 00:26:40 +03:00
|
|
|
assert_eq!(test_res.trees().count(), 5);
|
|
|
|
assert_eq!(eq_res.trees().count(), 5);
|
|
|
|
assert_eq!(test_res.eq_unspanned(&eq_res), true);
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_to_from_bijection() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
2019-08-02 00:26:40 +03:00
|
|
|
let test_start = string_to_ts("foo::bar(baz)");
|
2022-05-16 18:58:15 +03:00
|
|
|
let test_end = test_start.trees().cloned().collect();
|
2019-08-02 00:26:40 +03:00
|
|
|
assert_eq!(test_start, test_end)
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_eq_0() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
2019-08-02 00:26:40 +03:00
|
|
|
let test_res = string_to_ts("foo");
|
|
|
|
let test_eqs = string_to_ts("foo");
|
|
|
|
assert_eq!(test_res, test_eqs)
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_eq_1() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
2019-08-02 00:26:40 +03:00
|
|
|
let test_res = string_to_ts("::bar::baz");
|
|
|
|
let test_eqs = string_to_ts("::bar::baz");
|
|
|
|
assert_eq!(test_res, test_eqs)
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_eq_3() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
2019-08-02 00:26:40 +03:00
|
|
|
let test_res = string_to_ts("");
|
|
|
|
let test_eqs = string_to_ts("");
|
|
|
|
assert_eq!(test_res, test_eqs)
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_diseq_0() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
2019-08-02 00:26:40 +03:00
|
|
|
let test_res = string_to_ts("::bar::baz");
|
|
|
|
let test_eqs = string_to_ts("bar::baz");
|
|
|
|
assert_eq!(test_res == test_eqs, false)
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_diseq_1() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
2019-08-02 00:26:40 +03:00
|
|
|
let test_res = string_to_ts("(bar,baz)");
|
|
|
|
let test_eqs = string_to_ts("bar,baz");
|
|
|
|
assert_eq!(test_res == test_eqs, false)
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_is_empty() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
Remove `TreeAndSpacing`.
A `TokenStream` contains a `Lrc<Vec<(TokenTree, Spacing)>>`. But this is
not quite right. `Spacing` makes sense for `TokenTree::Token`, but does
not make sense for `TokenTree::Delimited`, because a
`TokenTree::Delimited` cannot be joined with another `TokenTree`.
This commit fixes this problem, by adding `Spacing` to `TokenTree::Token`,
changing `TokenStream` to contain a `Lrc<Vec<TokenTree>>`, and removing the
`TreeAndSpacing` typedef.
The commit removes these two impls:
- `impl From<TokenTree> for TokenStream`
- `impl From<TokenTree> for TreeAndSpacing`
These were useful, but also resulted in code with many `.into()` calls
that was hard to read, particularly for anyone not highly familiar with
the relevant types. This commit makes some other changes to compensate:
- `TokenTree::token()` becomes `TokenTree::token_{alone,joint}()`.
- `TokenStream::token_{alone,joint}()` are added.
- `TokenStream::delimited` is added.
This results in things like this:
```rust
TokenTree::token(token::Semi, stmt.span).into()
```
changing to this:
```rust
TokenStream::token_alone(token::Semi, stmt.span)
```
This makes the type of the result, and its spacing, clearer.
These changes also simplifies `Cursor` and `CursorRef`, because they no longer
need to distinguish between `next` and `next_with_spacing`.
2022-07-28 10:31:04 +10:00
|
|
|
let test0 = TokenStream::default();
|
2024-02-13 23:28:27 +00:00
|
|
|
let test1 =
|
|
|
|
TokenStream::token_alone(token::Ident(Symbol::intern("a"), IdentIsRaw::No), sp(0, 1));
|
2019-08-02 00:26:40 +03:00
|
|
|
let test2 = string_to_ts("foo(bar::baz)");
|
|
|
|
|
|
|
|
assert_eq!(test0.is_empty(), true);
|
|
|
|
assert_eq!(test1.is_empty(), false);
|
|
|
|
assert_eq!(test2.is_empty(), false);
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn test_dotdotdot() {
|
2021-05-05 21:31:25 +02:00
|
|
|
create_default_session_globals_then(|| {
|
Remove `TokenStreamBuilder`.
`TokenStreamBuilder` exists to concatenate multiple `TokenStream`s
together. This commit removes it, and moves the concatenation
functionality directly into `TokenStream`, via two new methods
`push_tree` and `push_stream`. This makes things both simpler and
faster.
`push_tree` is particularly important. `TokenStreamBuilder` only had a
single `push` method, which pushed a stream. But in practice most of the
time we push a single token tree rather than a stream, and `push_tree`
avoids the need to build a token stream with a single entry (which
requires two allocations, one for the `Lrc` and one for the `Vec`).
The main `push_tree` use arises from a change to one of the `ToInternal`
impls in `proc_macro_server.rs`. It now returns a `SmallVec` instead of
a `TokenStream`. This return value is then iterated over by
`concat_trees`, which does `push_tree` on each element. Furthermore, the
use of `SmallVec` avoids more allocations, because there is always only
one or two token trees.
Note: the removed `TokenStreamBuilder::push` method had some code to
deal with a quadratic blowup case from #57735. This commit removes the
code. I tried and failed to reproduce the blowup from that PR, before
and after this change. Various other changes have happened to
`TokenStreamBuilder` in the meantime, so I suspect the original problem
is no longer relevant, though I don't have proof of this. Generally
speaking, repeatedly extending a `Vec` without pre-determining its
capacity is *not* quadratic. It's also incredibly common, within rustc
and many other Rust programs, so if there were performance problems
there you'd think it would show up in other places, too.
2022-10-05 10:38:15 +11:00
|
|
|
let mut stream = TokenStream::default();
|
|
|
|
stream.push_tree(TokenTree::token_joint(token::Dot, sp(0, 1)));
|
|
|
|
stream.push_tree(TokenTree::token_joint(token::Dot, sp(1, 2)));
|
|
|
|
stream.push_tree(TokenTree::token_alone(token::Dot, sp(2, 3)));
|
2019-08-02 00:26:40 +03:00
|
|
|
assert!(stream.eq_unspanned(&string_to_ts("...")));
|
|
|
|
assert_eq!(stream.trees().count(), 1);
|
|
|
|
})
|
|
|
|
}
|