Merge pull request #1416 from alexcrichton/js-string-valid-utf16

Add warnings about UTF-16 vs UTF-8 strings

crates/js-sys/src/lib.rs

@@ -3522,6 +3522,37 @@ impl JsString {
             None
         }
     }
+
+    /// Returns whether this string is a valid UTF-16 string.
+    ///
+    /// This is useful for learning whether `String::from(..)` will return a
+    /// lossless representation of the JS string. If this string contains
+    /// unpaired surrogates then `String::from` will succeed but it will be a
+    /// lossy representation of the JS string because unpaired surrogates will
+    /// become replacement characters.
+    ///
+    /// If this function returns `false` then to get a lossless representation
+    /// of the string you'll need to manually use the `iter` method (or the
+    /// `char_code_at` accessor) to view the raw character codes.
+    ///
+    /// For more information, see the documentation on [JS strings vs Rust
+    /// strings][docs]
+    ///
+    /// [docs]: https://rustwasm.github.io/docs/wasm-bindgen/reference/types/str.html
+    pub fn is_valid_utf16(&self) -> bool {
+        std::char::decode_utf16(self.iter()).all(|i| i.is_ok())
+    }
+
+    /// Returns an iterator over the `u16` character codes that make up this JS
+    /// string.
+    ///
+    /// This method will call `char_code_at` for each code in this JS string,
+    /// returning an iterator of the codes in sequence.
+    pub fn iter<'a>(
+        &'a self,
+    ) -> impl ExactSizeIterator<Item = u16> + DoubleEndedIterator<Item = u16> + 'a {
+        (0..self.length()).map(move |i| self.char_code_at(i) as u16)
+    }
 }
 
 impl PartialEq<str> for JsString {

crates/js-sys/tests/wasm/JsString.rs

@@ -541,3 +541,15 @@ fn raw() {
     );
     assert!(JsString::raw_0(&JsValue::null().unchecked_into()).is_err());
 }
+
+#[wasm_bindgen_test]
+fn is_valid_utf16() {
+    assert!(JsString::from("a").is_valid_utf16());
+    assert!(JsString::from("").is_valid_utf16());
+    assert!(JsString::from("🥑").is_valid_utf16());
+    assert!(JsString::from("Why hello there this, 🥑, is 🥑 and is 🥑").is_valid_utf16());
+
+    assert!(JsString::from_char_code1(0x00).is_valid_utf16());
+    assert!(!JsString::from_char_code1(0xd800).is_valid_utf16());
+    assert!(!JsString::from_char_code1(0xdc00).is_valid_utf16());
+}

examples/without-a-bundler/index.html

@@ -25,7 +25,12 @@
         // Also note that the promise, when resolved, yields the wasm module's
         // exports which is the same as importing the `*_bg` module in other
         // modes
-        await init('./pkg/without_a_bundler_bg.wasm');
+        // await init('./pkg/without_a_bundler_bg.wasm');
+
+        const url = await fetch('http://localhost:8001/pkg/without_a_bundler_bg.wasm');
+        const body = await url.arrayBuffer();
+        const module = await WebAssembly.compile(body);
+        await init(module);
 
         // And afterwards we can use all the functionality defined in wasm.
         const result = add(1, 2);

guide/src/reference/types/str.md

@@ -20,3 +20,30 @@ with handles to JavaScript string values, use the `js_sys::JsString` type.
 ```js
 {{#include ../../../../examples/guide-supported-types-examples/str.js}}
 ```
+
+## UTF-16 vs UTF-8
+
+Strings in JavaScript are encoded as UTF-16, but with one major exception: they
+can contain unpaired surrogates. For some Unicode characters UTF-16 uses two
+16-byte values.  These are called "surrogate pairs" because they always come in
+pairs. In JavaScript, it is possible for these surrogate pairs to be missing the
+other half, creating an "unpaired surrogate".
+
+When passing a string from JavaScript to Rust, it uses the `TextEncoder` API to
+convert from UTF-16 to UTF-8. This is normally perfectly fine... unless there
+are unpaired surrogates. In that case it will replace the unpaired surrogates
+with U+FFFD (�, the replacement character). That means the string in Rust is
+now different from the string in JavaScript!
+
+If you want to guarantee that the Rust string is the same as the JavaScript
+string, you should instead use `js_sys::JsString` (which keeps the string in
+JavaScript and doesn't copy it into Rust).
+
+If you want to access the raw value of a JS string, you can use `JsString::iter`,
+which returns an `Iterator<Item = u16>`. This perfectly preserves everything
+(including unpaired surrogates), but it does not do any encoding (so you
+have to do that yourself!).
+
+If you simply want to ignore strings which contain unpaired surrogates, you can
+use `JsString::is_valid_utf16` to test whether the string contains unpaired
+surrogates or not.

guide/src/reference/types/string.md

@@ -8,6 +8,9 @@ Copies the string's contents back and forth between the JavaScript
 garbage-collected heap and the Wasm linear memory with `TextDecoder` and
 `TextEncoder`
 
+> **Note**: Be sure to check out the [documentation for `str`](str.html) to
+> learn about some caveats when working with strings between JS and Rust.
+
 ## Example Rust Usage
 
 ```rust

src/lib.rs

@@ -260,6 +260,16 @@ impl JsValue {
     ///
     /// If this JS value is not an instance of a string or if it's not valid
     /// utf-8 then this returns `None`.
+    ///
+    /// # UTF-16 vs UTF-8
+    ///
+    /// JavaScript strings in general are encoded as UTF-16, but Rust strings
+    /// are encoded as UTF-8. This can cause the Rust string to look a bit
+    /// different than the JS string sometimes. For more details see the
+    /// [documentation about the `str` type][caveats] which contains a few
+    /// caveats about the encodings.
+    ///
+    /// [caveats]: https://rustwasm.github.io/docs/wasm-bindgen/reference/types/str.html
     #[cfg(feature = "std")]
     pub fn as_string(&self) -> Option<String> {
         unsafe {