Rename Unterminated_ nonterminals to Reserved_

The writeup now has an explicit notion of a reserved-form nonterminal,
so it seems better if they all have names beginning "Reserved_".

Author: mattheww

src/reimplementation/tokenisation/processing.rs

@@ -39,8 +39,8 @@ pub fn process(match_data: &TokenisationMatch) -> Result<FineToken, Error> {
         Nonterminal::Raw_ident => process_raw_ident(match_data)?,
         Nonterminal::Ident => process_ident(match_data)?,
         Nonterminal::Punctuation => process_punctuation(match_data)?,
-        Nonterminal::Unterminated_block_comment
-        | Nonterminal::Unterminated_literal_2015
+        Nonterminal::Reserved_block_comment_start
+        | Nonterminal::Reserved_literal_2015
         | Nonterminal::Reserved_literal_2021
         | Nonterminal::Reserved_single_quoted_literal_2015
         | Nonterminal::Reserved_single_quoted_literal_2021

src/reimplementation/tokenisation/tokenise.pest

@@ -7,14 +7,14 @@ TOKEN_2015 = {
     Whitespace |
     Line_comment |
     Block_comment |
-    Unterminated_block_comment |
+    Reserved_block_comment_start |
     Character_literal |
     Byte_literal |
     String_literal |
     Byte_string_literal |
     Raw_string_literal |
     Raw_byte_string_literal |
-    Unterminated_literal_2015 |
+    Reserved_literal_2015 |
     Reserved_single_quoted_literal_2015 |
     Float_literal |
     Reserved_float |
@@ -30,7 +30,7 @@ TOKEN_2021 = {
     Whitespace |
     Line_comment |
     Block_comment |
-    Unterminated_block_comment |
+    Reserved_block_comment_start |
     Character_literal |
     Byte_literal |
     String_literal |
@@ -57,7 +57,7 @@ TOKEN_2024 = {
     Whitespace |
     Line_comment |
     Block_comment |
-    Unterminated_block_comment |
+    Reserved_block_comment_start |
     Character_literal |
     Byte_literal |
     String_literal |
@@ -98,9 +98,9 @@ BLOCK_COMMENT = { "/*" ~ BLOCK_COMMENT_CONTENT ~ "*/" }
 BLOCK_COMMENT_CONTENT = { ( BLOCK_COMMENT | !"*/" ~ !"/*" ~ ANY ) * }
 // ANCHOR_END: block_comment
 
-// ANCHOR: unterminated_block_comment
-Unterminated_block_comment = { "/*" }
-// ANCHOR_END: unterminated_block_comment
+// ANCHOR: reserved_block_comment_start
+Reserved_block_comment_start = { "/*" }
+// ANCHOR_END: reserved_block_comment_start
 
 
 // ANCHOR: single_quoted_literals_common
@@ -177,10 +177,10 @@ Raw_c_string_literal = { "cr" ~ RAW_DOUBLE_QUOTED_FORM }
 // ANCHOR_END: raw_c_string_literal
 
 
-// ANCHOR: unterminated_literal
-Unterminated_literal_2015 = { "r" ~ DOUBLEQUOTE | "br" ~ DOUBLEQUOTE | "b'" }
+// ANCHOR: reserved_literal
+Reserved_literal_2015 = { "r" ~ DOUBLEQUOTE | "br" ~ DOUBLEQUOTE | "b'" }
 Reserved_literal_2021 = { IDENT ~ ( DOUBLEQUOTE | "'" ) }
-// ANCHOR_END: unterminated_literal
+// ANCHOR_END: reserved_literal
 
 // ANCHOR: reserved_single_quoted_literal
 Reserved_single_quoted_literal_2015 = { "'" ~ IDENT ~ "'" }

writeup/quoted_literal_tokens.md

@@ -273,21 +273,21 @@ The match is rejected if:
 
 ### Reserved forms
 
-#### Reserved or unterminated literal { .processing }
+#### Reserved literal { .processing }
 
 ##### Grammar
 ```
-{{#include tokenise_anchored.pest:unterminated_literal}}
+{{#include tokenise_anchored.pest:reserved_literal}}
 ```
 
 ##### Rejection
 
 All matches are rejected.
 
-> Note: I believe in the `Unterminated_literal_2015` definition only the `b'` form is strictly needed:
+> Note: I believe in the `Reserved_literal_2015` definition only the `b'` form is strictly needed:
 > if that definition matches using one of the other subexpressions
 > then the input will be rejected eventually anyway
-> (given that the corresponding string literal nonterminal didn't match).
+> (given that the corresponding quoted literal nonterminal didn't match).
 
 > Note: `Reserved_literal_2021` catches both reserved forms and unterminated `b'` literals.
 

writeup/tokenising.md

@@ -27,16 +27,16 @@ A nonterminal whose name appears in the following table is a <dfn>reserved-form
 
 | Reserved form                         |
 |---------------------------------------|
+| `Reserved_block_comment_start`        |
 | `Reserved_float`                      |
 | `Reserved_guard`                      |
 | `Reserved_lifetime_or_label_prefix`   |
+| `Reserved_literal_2015`               |
 | `Reserved_literal_2021`               |
 | `Reserved_prefix_2015`                |
 | `Reserved_prefix_2021`                |
 | `Reserved_single_quoted_literal_2015` |
 | `Reserved_single_quoted_literal_2021` |
-| `Unterminated_block_comment`          |
-| `Unterminated_literal_2015`           |
 
 A token nonterminal or reserved-form nonterminal is a <dfn>tokenisation nonterminal</dfn>.
 

writeup/whitespace_and_comment_tokens.md

@@ -99,11 +99,11 @@ The token's <var>style</var> and <var>body</var> are determined from the block c
 The match is rejected if the token's <var>body</var> would include a <kbd>CR</kbd> character.
 
 
-#### Unterminated block comment { .processing }
+#### Reserved block comment start { .processing }
 
 ##### Grammar
 ```
-{{#include tokenise_anchored.pest:unterminated_block_comment}}
+{{#include tokenise_anchored.pest:reserved_block_comment_start}}
 ```
 
 ##### Rejection