fix(ext/node): lossy UTF-8 read node_modules files (#24140)

Previously various reads of files in `node_modules` would error on
invalid UTF-8. These were cases involving:

- reading package.json from Rust
- reading package.json from JS
- reading CommonJS files from JS
- reading CommonJS files from Rust (for ESM translation)
- reading ESM files from Rust

1 files changed, 17 insertions, 8 deletions

diff --git a/ext/fs/interface.rs b/ext/fs/interface.rs
index 70f9fdf63..5031dc134 100644
--- a/ext/fs/interface.rs
+++ b/ext/fs/interface.rs
@@ -1,5 +1,6 @@
 // Copyright 2018-2024 the Deno authors. All rights reserved. MIT license.
 
+use std::borrow::Cow;
 use std::path::Path;
 use std::path::PathBuf;
 use std::rc::Rc;
@@ -284,24 +285,32 @@ pub trait FileSystem: std::fmt::Debug + MaybeSend + MaybeSync {
     self.stat_sync(path).is_ok()
   }
 
-  fn read_text_file_sync(
+  fn read_text_file_lossy_sync(
     &self,
     path: &Path,
     access_check: Option<AccessCheckCb>,
   ) -> FsResult<String> {
     let buf = self.read_file_sync(path, access_check)?;
-    String::from_utf8(buf).map_err(|err| {
-      std::io::Error::new(std::io::ErrorKind::InvalidData, err).into()
-    })
+    Ok(string_from_utf8_lossy(buf))
   }
-  async fn read_text_file_async<'a>(
+  async fn read_text_file_lossy_async<'a>(
     &'a self,
     path: PathBuf,
     access_check: Option<AccessCheckCb<'a>>,
   ) -> FsResult<String> {
     let buf = self.read_file_async(path, access_check).await?;
-    String::from_utf8(buf).map_err(|err| {
-      std::io::Error::new(std::io::ErrorKind::InvalidData, err).into()
-    })
+    Ok(string_from_utf8_lossy(buf))
+  }
+}
+
+// Like String::from_utf8_lossy but operates on owned values
+#[inline(always)]
+fn string_from_utf8_lossy(buf: Vec<u8>) -> String {
+  match String::from_utf8_lossy(&buf) {
+    // buf contained non-utf8 chars than have been patched
+    Cow::Owned(s) => s,
+    // SAFETY: if Borrowed then the buf only contains utf8 chars,
+    // we do this instead of .into_owned() to avoid copying the input buf
+    Cow::Borrowed(_) => unsafe { String::from_utf8_unchecked(buf) },
   }
 }