From 5e7834aa2ecb0cd01b72979f393a517f1c1e5add Mon Sep 17 00:00:00 2001
From: Manish Goregaokar <manishsmail@gmail.com>
Date: Sun, 13 Aug 2023 18:33:50 -0700
Subject: [PATCH] refactor(es/parser): Don't attempt to handle shebangs in
 `read_token_number_sign` (#7803)

bump() has a safety invariant that there must be input in the buffer to
read (See https://github.com/swc-project/swc/issues/7709).

This function as currently written calls `bump()` after calling
`read_token_interpreter()`, which *may* have exhausted the buffer
already in the specific case that it is handling a shebang. (The input
string `#!/bin/js` with no newline is sufficient to cause UB here)

Fortunately, shebangs never reach this function, due to `read_shebang`!
Hurray!

It's cleaner to not attempt to handle shebangs here when this code path
will never be reached, and use a debug assertion to ensure that we're
not dealing with shebangs.
---
 crates/swc_ecma_parser/src/lexer/mod.rs | 34 +++++--------------------
 1 file changed, 7 insertions(+), 27 deletions(-)

diff --git a/crates/swc_ecma_parser/src/lexer/mod.rs b/crates/swc_ecma_parser/src/lexer/mod.rs
index adc6b39232fb..2e818cfab9af 100644
--- a/crates/swc_ecma_parser/src/lexer/mod.rs
+++ b/crates/swc_ecma_parser/src/lexer/mod.rs
@@ -192,35 +192,15 @@ impl<'a> Lexer<'a> {
     fn read_token_number_sign(&mut self) -> LexResult<Option<Token>> {
         debug_assert!(self.cur().is_some());
 
-        if self.input.is_at_start() && self.read_token_interpreter()? {
-            return Ok(None);
-        }
-
         self.input.bump(); // '#'
-        Ok(Some(Token::Hash))
-    }
-
-    #[inline(never)]
-    fn read_token_interpreter(&mut self) -> LexResult<bool> {
-        if !self.input.is_at_start() {
-            return Ok(false);
-        }
 
-        let start = self.input.cur_pos();
-        self.input.bump();
-        let c = self.input.cur();
-        if c == Some('!') {
-            while let Some(c) = self.input.cur() {
-                self.input.bump();
-                if c == '\n' || c == '\r' || c == '\u{8232}' || c == '\u{8233}' {
-                    return Ok(true);
-                }
-            }
-            Ok(false)
-        } else {
-            self.input.reset_to(start);
-            Ok(false)
-        }
+        // `#` can also be a part of shebangs, however they should have been
+        // handled by `read_shebang()`
+        debug_assert!(
+            !self.input.is_at_start() || self.cur() != Some('!'),
+            "#! should have already been handled by read_shebang()"
+        );
+        Ok(Some(Token::Hash))
     }
 
     /// Read a token given `.`.