New upstream version 1.71.1+dfsg1

[rustc.git] / compiler / rustc_lexer / src / lib.rs

diff --git a/compiler/rustc_lexer/src/lib.rs b/compiler/rustc_lexer/src/lib.rs
index b3f4b5cd5e5a0dda101ebfcb30d0a6dda3886e5c..29335a8c0f4cd3db73b3daf1b2d07e2ad2370943 100644 (file)
--- a/compiler/rustc_lexer/src/lib.rs
+++ b/compiler/rustc_lexer/src/lib.rs
@@ -186,12 +186,16 @@ pub enum LiteralKind {
     Str { terminated: bool },
     /// "b"abc"", "b"abc"
     ByteStr { terminated: bool },
+    /// `c"abc"`, `c"abc`
+    CStr { terminated: bool },
     /// "r"abc"", "r#"abc"#", "r####"ab"###"c"####", "r#"a". `None` indicates
     /// an invalid literal.
     RawStr { n_hashes: Option<u8> },
     /// "br"abc"", "br#"abc"#", "br####"ab"###"c"####", "br#"a". `None`
     /// indicates an invalid literal.
     RawByteStr { n_hashes: Option<u8> },
+    /// `cr"abc"`, "cr#"abc"#", `cr#"a`. `None` indicates an invalid literal.
+    RawCStr { n_hashes: Option<u8> },
 }
 
 #[derive(Clone, Copy, Debug, PartialEq, Eq, PartialOrd, Ord)]
@@ -357,39 +361,11 @@ impl Cursor<'_> {
             },
 
             // Byte literal, byte string literal, raw byte string literal or identifier.
-            'b' => match (self.first(), self.second()) {
-                ('\'', _) => {
-                    self.bump();
-                    let terminated = self.single_quoted_string();
-                    let suffix_start = self.pos_within_token();
-                    if terminated {
-                        self.eat_literal_suffix();
-                    }
-                    let kind = Byte { terminated };
-                    Literal { kind, suffix_start }
-                }
-                ('"', _) => {
-                    self.bump();
-                    let terminated = self.double_quoted_string();
-                    let suffix_start = self.pos_within_token();
-                    if terminated {
-                        self.eat_literal_suffix();
-                    }
-                    let kind = ByteStr { terminated };
-                    Literal { kind, suffix_start }
-                }
-                ('r', '"') | ('r', '#') => {
-                    self.bump();
-                    let res = self.raw_double_quoted_string(2);
-                    let suffix_start = self.pos_within_token();
-                    if res.is_ok() {
-                        self.eat_literal_suffix();
-                    }
-                    let kind = RawByteStr { n_hashes: res.ok() };
-                    Literal { kind, suffix_start }
-                }
-                _ => self.ident_or_unknown_prefix(),
-            },
+            'b' => self.c_or_byte_string(
+                |terminated| ByteStr { terminated },
+                |n_hashes| RawByteStr { n_hashes },
+                Some(|terminated| Byte { terminated }),
+            ),
 
             // Identifier (this should be checked after other variant that can
             // start as identifier).
@@ -553,39 +529,84 @@ impl Cursor<'_> {
         }
     }
 
+    fn c_or_byte_string(
+        &mut self,
+        mk_kind: impl FnOnce(bool) -> LiteralKind,
+        mk_kind_raw: impl FnOnce(Option<u8>) -> LiteralKind,
+        single_quoted: Option<fn(bool) -> LiteralKind>,
+    ) -> TokenKind {
+        match (self.first(), self.second(), single_quoted) {
+            ('\'', _, Some(mk_kind)) => {
+                self.bump();
+                let terminated = self.single_quoted_string();
+                let suffix_start = self.pos_within_token();
+                if terminated {
+                    self.eat_literal_suffix();
+                }
+                let kind = mk_kind(terminated);
+                Literal { kind, suffix_start }
+            }
+            ('"', _, _) => {
+                self.bump();
+                let terminated = self.double_quoted_string();
+                let suffix_start = self.pos_within_token();
+                if terminated {
+                    self.eat_literal_suffix();
+                }
+                let kind = mk_kind(terminated);
+                Literal { kind, suffix_start }
+            }
+            ('r', '"', _) | ('r', '#', _) => {
+                self.bump();
+                let res = self.raw_double_quoted_string(2);
+                let suffix_start = self.pos_within_token();
+                if res.is_ok() {
+                    self.eat_literal_suffix();
+                }
+                let kind = mk_kind_raw(res.ok());
+                Literal { kind, suffix_start }
+            }
+            _ => self.ident_or_unknown_prefix(),
+        }
+    }
+
     fn number(&mut self, first_digit: char) -> LiteralKind {
         debug_assert!('0' <= self.prev() && self.prev() <= '9');
         let mut base = Base::Decimal;
         if first_digit == '0' {
             // Attempt to parse encoding base.
-            let has_digits = match self.first() {
+            match self.first() {
                 'b' => {
                     base = Base::Binary;
                     self.bump();
-                    self.eat_decimal_digits()
+                    if !self.eat_decimal_digits() {
+                        return Int { base, empty_int: true };
+                    }
                 }
                 'o' => {
                     base = Base::Octal;
                     self.bump();
-                    self.eat_decimal_digits()
+                    if !self.eat_decimal_digits() {
+                        return Int { base, empty_int: true };
+                    }
                 }
                 'x' => {
                     base = Base::Hexadecimal;
                     self.bump();
-                    self.eat_hexadecimal_digits()
+                    if !self.eat_hexadecimal_digits() {
+                        return Int { base, empty_int: true };
+                    }
                 }
-                // Not a base prefix.
-                '0'..='9' | '_' | '.' | 'e' | 'E' => {
+                // Not a base prefix; consume additional digits.
+                '0'..='9' | '_' => {
                     self.eat_decimal_digits();
-                    true
                 }
+
+                // Also not a base prefix; nothing more to do here.
+                '.' | 'e' | 'E' => {}
+
                 // Just a 0.
                 _ => return Int { base, empty_int: false },
-            };
-            // Base prefix was provided, but there were no digits
-            // after it, e.g. "0x".
-            if !has_digits {
-                return Int { base, empty_int: true };
             }
         } else {
             // No base prefix, parse number in the usual way.