Merge branch '2024-10_edition-2024-reservations'

Author: mattheww

src/lexlucid/pretokenisation/pretokenisation_rules.rs

@@ -29,6 +29,7 @@ enum RuleName {
     LineComment,
     BlockComment,
     UnterminatedBlockComment,
+    ReservedHashForms2024,
     Punctuation,
     SingleQuotedLiteral,
     RawLifetimeOrLabel2021,
@@ -108,6 +109,7 @@ const RULES_FOR_EDITION_2024: &[RuleName] = [
     RuleName::LineComment,
     RuleName::BlockComment,
     RuleName::UnterminatedBlockComment,
+    RuleName::ReservedHashForms2024,
     RuleName::Punctuation,
     RuleName::SingleQuotedLiteral,
     RuleName::RawLifetimeOrLabel2021,
@@ -177,6 +179,14 @@ fn make_named_rules() -> BTreeMap<RuleName, Rule> {
                 / \*
             "##)),
 
+       // Reserved hashes (Rust 2024)
+       (RuleName::ReservedHashForms2024,
+        Rule::new_regex(
+            |_| PretokenData::Reserved, r##"\A
+                \#
+                ( \# | " )
+            "##)),
+
        // Punctuation
        (RuleName::Punctuation,
         Rule::new_regex(

src/testcases.rs

@@ -146,6 +146,11 @@ pub const LONGLIST: &[&str] = [
     "@=",
     "~=",
 
+    "##",
+    "###",
+    "####",
+    "#####",
+
     "x ➖ y",
 
 
@@ -488,11 +493,25 @@ pub const LONGLIST: &[&str] = [
     "'r#super",
     "'r#Self",
 
-    //// Possible future forms
-
-    // See rfc3593
-    r##" #"xxx"# "##,
+    //// Forms related to the "Guarded string literals" 2024 reservations
+    " #\"xxx\"# ",
+    " ##\"xxx\"## ",
+    " ###\"xxx\"### ",
+    " ####\"xxx\"#### ",
+    " #####\"xxx\"##### ",
+    " #\"xxx\" ",
+    " ##\"xxx\"# ",
+    " #\"xxx",
+    " #\"\"# ",
+    " ##\"\"## ",
+    " #\"\" ",
+    " ##\"\"# ",
+    " #\"",
+    " ###############################################################################################################################################################################################################################################################\"aaa\"############################################################################################################################################################################################################################################################### ",
+    " ################################################################################################################################################################################################################################################################\"aaa\"################################################################################################################################################################################################################################################################ ",
+    "£#\"\"#",
     "#'xxx'#",
+    "#''#",
 
 
     //// Lifetime/label non-ascii

writeup/introduction.md

@@ -11,28 +11,28 @@ and a framework for comparing its output to `rustc`'s.
 
 ### Rust language version
 
-This document describes Rust version 1.81, with the addition of
-[pr126452] (Raw syntax and reserved prefixes for lifetimes and labels),
-which is targeted for Rust 1.83.
+This document describes Rust version 1.83 (as it is expected to be, as of 2024-10-12).
 
-That means it describes `c""` literals, but not
+That means it describes raw lifetimes/labels and the additional reservations in the 2024 edition, but not
 
 - [rfc3349] (*Mixed UTF-8 literals*)
-- [rfc3593] (reserving `#"..."#` string literals)
 
-Other statements in this document are intended to be true as of September 2024.
+Other statements in this document are intended to be true as of October 2024.
 
 The comparable implementation is intended to be compiled against (and compared against)\
 `rustc 1.83.0-nightly (1bc403daa 2024-10-11)`
 
 
 ### Editions
 
-This document describes the editions supported by Rust 1.80:
+This document describes the editions supported by Rust 1.83:
 - 2015
 - 2018
 - 2021
 
+and the expected changes for the in-development edition:
+- 2024
+
 There are no differences in lexing behaviour between the 2015 and 2018 editions.
 
 In the comparable implementation, "2015" is used to refer to the common behaviour of Rust 2015 and Rust 2018.

writeup/rationale.md

@@ -2,7 +2,7 @@
 
 ### Pretokenising
 
-The main difference between the model described in this document and the way the Reference (as of Rust 1.81) describes lexing is the split into pretokenisation and reprocessing.
+The main difference between the model described in this document and the way the Reference (as of Rust 1.83) describes lexing is the split into pretokenisation and reprocessing.
 
 There are a number of forms which are errors at lexing time, even though in principle they could be analysed as multiple tokens.
 

writeup/rules.md

@@ -4,6 +4,7 @@
 [Line comment](#line-comment)\
 [Block comment](#block-comment)\
 [Unterminated block comment](#unterminated-block-comment)\
+[Reserved hash forms (Rust 2024)](#reserved-hash-forms-rust-2024)\
 [Punctuation](#punctuation)\
 [Single-quoted literal](#single-quoted-literal)\
 [Raw lifetime or label (Rust 2021)](#raw-lifetime-or-label-rust-2021)\
@@ -139,6 +140,21 @@ when `character_sequence` represents an iterator over the sequence of characters
 (none)
 
 
+#### Reserved hash forms (Rust 2024) { .rule }
+
+##### Pattern
+```
+\#
+( \# | " )
+```
+
+##### Pretoken kind
+`Reserved`
+
+##### Attributes
+(none)
+
+
 #### Punctuation { .rule }
 
 ##### Pattern

writeup/rustc_oddities.md

@@ -8,7 +8,7 @@ See [rfc2457].
 
 But this doesn't happen for lifetimes or labels, so `'Kelvin` and `'Kelvin` are different as lifetimes or labels.
 
-For example, [this][playground-lifetime] compiles without warning in Rust 1.81, while [this][playground-ident] doesn't.
+For example, [this][playground-lifetime] compiles without warning in Rust 1.83, while [this][playground-ident] doesn't.
 
 In this writeup, the <var>represented identifier</var> attribute of `Identifier` and `RawIdentifier` fine-grained tokens is in NFC,
 and the <var>name</var> attribute of `LifetimeOrLabel` and `RawLifetimeOrLabel` tokens isn't.