Auto merge of rust-lang#87262 - dtolnay:negative, r=Aaron1011

Support negative numbers in Literal::from_str

proc_macro::Literal has allowed negative numbers in a single literal token ever since Rust 1.29, using https://doc.rust-lang.org/stable/proc_macro/struct.Literal.html#method.isize_unsuffixed and similar constructors.

```rust
let lit = proc_macro::Literal::isize_unsuffixed(-10);
```

However, the suite of constructors on Literal is not sufficient for all use cases, for example arbitrary precision floats, or custom suffixes in FFI macros.

```rust
let lit = proc_macro::Literal::f64_unsuffixed(0.101001000100001000001000000100000001); // :(
let lit = proc_macro::Literal::i???_suffixed(10ulong); // :(
```

For those, macros construct the literal using from_str instead, which preserves arbitrary precision, custom suffixes, base, and digit grouping.

```rust
let lit = "0.101001000100001000001000000100000001".parse::<Literal>().unwrap();
let lit = "10ulong".parse::<Literal>().unwrap();
let lit = "0b1000_0100_0010_0001".parse::<Literal>().unwrap();
```

However, until this PR it was not possible to construct a literal token that is **both** negative **and** preserving of arbitrary precision etc.

This PR fixes `Literal::from_str` to recognize negative integer and float literals.

Author: bors

compiler/rustc_expand/src/proc_macro_server.rs

@@ -1,7 +1,7 @@
 use crate::base::{ExtCtxt, ResolverExpand};
 
 use rustc_ast as ast;
-use rustc_ast::token::{self, Nonterminal, NtIdent, TokenKind};
+use rustc_ast::token::{self, Nonterminal, NtIdent};
 use rustc_ast::tokenstream::{self, CanSynthesizeMissingTokens};
 use rustc_ast::tokenstream::{DelimSpan, Spacing::*, TokenStream, TreeAndSpacing};
 use rustc_ast_pretty::pprust;
@@ -537,30 +537,49 @@ impl server::Ident for Rustc<'_> {
 
 impl server::Literal for Rustc<'_> {
     fn from_str(&mut self, s: &str) -> Result<Self::Literal, ()> {
-        let override_span = None;
-        let stream = parse_stream_from_source_str(
-            FileName::proc_macro_source_code(s),
-            s.to_owned(),
-            self.sess,
-            override_span,
-        );
-        if stream.len() != 1 {
-            return Err(());
-        }
-        let tree = stream.into_trees().next().unwrap();
-        let token = match tree {
-            tokenstream::TokenTree::Token(token) => token,
-            tokenstream::TokenTree::Delimited { .. } => return Err(()),
+        let name = FileName::proc_macro_source_code(s);
+        let mut parser = rustc_parse::new_parser_from_source_str(self.sess, name, s.to_owned());
+
+        let first_span = parser.token.span.data();
+        let minus_present = parser.eat(&token::BinOp(token::Minus));
+
+        let lit_span = parser.token.span.data();
+        let mut lit = match parser.token.kind {
+            token::Literal(lit) => lit,
+            _ => return Err(()),
         };
-        let span_data = token.span.data();
-        if (span_data.hi.0 - span_data.lo.0) as usize != s.len() {
-            // There is a comment or whitespace adjacent to the literal.
+
+        // Check no comment or whitespace surrounding the (possibly negative)
+        // literal, or more tokens after it.
+        if (lit_span.hi.0 - first_span.lo.0) as usize != s.len() {
             return Err(());
         }
-        let lit = match token.kind {
-            TokenKind::Literal(lit) => lit,
-            _ => return Err(()),
-        };
+
+        if minus_present {
+            // If minus is present, check no comment or whitespace in between it
+            // and the literal token.
+            if first_span.hi.0 != lit_span.lo.0 {
+                return Err(());
+            }
+
+            // Check literal is a kind we allow to be negated in a proc macro token.
+            match lit.kind {
+                token::LitKind::Bool
+                | token::LitKind::Byte
+                | token::LitKind::Char
+                | token::LitKind::Str
+                | token::LitKind::StrRaw(_)
+                | token::LitKind::ByteStr
+                | token::LitKind::ByteStrRaw(_)
+                | token::LitKind::Err => return Err(()),
+                token::LitKind::Integer | token::LitKind::Float => {}
+            }
+
+            // Synthesize a new symbol that includes the minus sign.
+            let symbol = Symbol::intern(&s[..1 + lit.symbol.len()]);
+            lit = token::Lit::new(lit.kind, symbol, lit.suffix);
+        }
+
         Ok(Literal { lit, span: self.call_site })
     }
     fn debug_kind(&mut self, literal: &Self::Literal) -> String {

compiler/rustc_span/src/symbol.rs

@@ -1600,6 +1600,10 @@ impl Symbol {
         self.0.as_u32()
     }
 
+    pub fn len(self) -> usize {
+        with_interner(|interner| interner.get(self).len())
+    }
+
     pub fn is_empty(self) -> bool {
         self == kw::Empty
     }

src/test/ui/proc-macro/auxiliary/api/parse.rs

@@ -1,9 +1,15 @@
 use proc_macro::Literal;
 
 pub fn test() {
+    test_display_literal();
     test_parse_literal();
 }
 
+fn test_display_literal() {
+    assert_eq!(Literal::isize_unsuffixed(-10).to_string(), "- 10");
+    assert_eq!(Literal::isize_suffixed(-10).to_string(), "- 10isize");
+}
+
 fn test_parse_literal() {
     assert_eq!("1".parse::<Literal>().unwrap().to_string(), "1");
     assert_eq!("1.0".parse::<Literal>().unwrap().to_string(), "1.0");
@@ -12,12 +18,17 @@ fn test_parse_literal() {
     assert_eq!("b\"\"".parse::<Literal>().unwrap().to_string(), "b\"\"");
     assert_eq!("r##\"\"##".parse::<Literal>().unwrap().to_string(), "r##\"\"##");
     assert_eq!("10ulong".parse::<Literal>().unwrap().to_string(), "10ulong");
+    assert_eq!("-10ulong".parse::<Literal>().unwrap().to_string(), "- 10ulong");
 
+    assert!("true".parse::<Literal>().is_err());
+    assert!(".8".parse::<Literal>().is_err());
     assert!("0 1".parse::<Literal>().is_err());
     assert!("'a".parse::<Literal>().is_err());
     assert!(" 0".parse::<Literal>().is_err());
     assert!("0 ".parse::<Literal>().is_err());
     assert!("/* comment */0".parse::<Literal>().is_err());
     assert!("0/* comment */".parse::<Literal>().is_err());
     assert!("0// comment".parse::<Literal>().is_err());
+    assert!("- 10".parse::<Literal>().is_err());
+    assert!("-'x'".parse::<Literal>().is_err());
 }