perf(ext/web): add op_encode_binary_string (#16352)

Add a new op to use in `reader.readAsBinaryString(blob)`.

```
File API binary string: 400b    35.12 µs/iter    (21.93 µs … 3.27 ms)  31.87 µs 131.95 µs 217.63 µs
File API binary string: 4kb     46.49 µs/iter    (29.36 µs … 4.42 ms)   42.5 µs 122.48 µs  155.1 µs
File API binary string: 2.2mb    4.17 ms/iter     (1.75 ms … 8.54 ms)   5.48 ms   7.39 ms   8.54 ms
```

**main**

```
benchmark                          time (avg)             (min … max)       p75       p99      p995
--------------------------------------------------------------------- -----------------------------
File API binary string: 400b    56.17 µs/iter  (43.09 µs … 784.52 µs)   49.6 µs 177.18 µs 241.23 µs
File API binary string: 4kb     277.2 µs/iter   (240.29 µs … 1.84 ms) 269.87 µs 649.79 µs 774.46 µs
File API binary string: 2.2mb  180.03 ms/iter (173.32 ms … 194.35 ms) 182.54 ms 194.35 ms 194.35 ms
```

It can also handle bigger files, when encoding a 200mb file, main
crashes with OOM

```
<--- Last few GCs --->

[132677:0x560504676550]     5012 ms: Scavenge 417.3 (434.6) -> 401.8 (434.6) MB, 0.1 / 0.0 ms  (average mu = 0.824, current mu = 0.825) allocation failure; 
[132677:0x560504676550]     5038 ms: Scavenge 417.3 (434.6) -> 401.8 (434.6) MB, 0.1 / 0.0 ms  (average mu = 0.824, current mu = 0.825) allocation failure; 
[132677:0x560504676550]     5064 ms: Scavenge 417.3 (434.6) -> 401.8 (434.6) MB, 0.1 / 0.0 ms  (average mu = 0.824, current mu = 0.825) allocation failure;
```

cli/tests/unit/text_encoding_test.ts

@@ -247,6 +247,7 @@ Deno.test(function toStringShouldBeWebCompatibility() {
   const decoder = new TextDecoder();
   assertEquals(decoder.toString(), "[object TextDecoder]");
 });
+
 Deno.test(function textEncoderShouldCoerceToString() {
   const encoder = new TextEncoder();
   const fixutreText = "text";
@@ -261,3 +262,60 @@ Deno.test(function textEncoderShouldCoerceToString() {
   const decoded = decoder.decode(bytes);
   assertEquals(decoded, fixutreText);
 });
+
+Deno.test(function binaryEncode() {
+  // @ts-ignore: Deno.core allowed
+  const ops = Deno.core.ops;
+  function asBinaryString(bytes: Uint8Array): string {
+    return Array.from(bytes).map(
+      (v: number) => String.fromCodePoint(v),
+    ).join("");
+  }
+
+  function decodeBinary(binaryString: string) {
+    const chars: string[] = Array.from(binaryString);
+    return chars.map((v: string): number | undefined => v.codePointAt(0));
+  }
+
+  // invalid utf-8 code points
+  const invalid = new Uint8Array([0xC0]);
+  assertEquals(
+    ops.op_encode_binary_string(invalid),
+    asBinaryString(invalid),
+  );
+
+  const invalid2 = new Uint8Array([0xC1]);
+  assertEquals(
+    ops.op_encode_binary_string(invalid2),
+    asBinaryString(invalid2),
+  );
+
+  for (let i = 0, j = 255; i <= 255; i++, j--) {
+    const bytes = new Uint8Array([i, j]);
+    const binaryString = ops.op_encode_binary_string(bytes);
+    assertEquals(
+      binaryString,
+      asBinaryString(bytes),
+    );
+    assertEquals(Array.from(bytes), decodeBinary(binaryString));
+  }
+
+  const inputs = [
+    "σ😀",
+    "Кириллица is Cyrillic",
+    "𝓽𝓮𝔁𝓽",
+    "lone𝄞\ud888surrogate",
+    "\udc00\ud800",
+    "\ud800",
+  ];
+  for (const input of inputs) {
+    const bytes = new TextEncoder().encode(input);
+    const binaryString = ops.op_encode_binary_string(bytes);
+    assertEquals(
+      binaryString,
+      asBinaryString(bytes),
+    );
+
+    assertEquals(Array.from(bytes), decodeBinary(binaryString));
+  }
+});

ext/web/10_filereader.js

@@ -13,6 +13,7 @@
 "use strict";
 
 ((window) => {
+  const core = window.Deno.core;
   const webidl = window.__bootstrap.webidl;
   const { forgivingBase64Encode } = window.__bootstrap.infra;
   const { ProgressEvent } = window.__bootstrap.event;
@@ -21,8 +22,6 @@
   const { parseMimeType } = window.__bootstrap.mimesniff;
   const { DOMException } = window.__bootstrap.domException;
   const {
-    ArrayPrototypeJoin,
-    ArrayPrototypeMap,
     ArrayPrototypePush,
     ArrayPrototypeReduce,
     FunctionPrototypeCall,
@@ -33,7 +32,6 @@
     ObjectPrototypeIsPrototypeOf,
     queueMicrotask,
     SafeArrayIterator,
-    StringFromCodePoint,
     Symbol,
     TypedArrayPrototypeSet,
     TypeError,
@@ -170,13 +168,7 @@
                     break;
                   }
                   case "BinaryString":
-                    this[result] = ArrayPrototypeJoin(
+                    this[result] = core.ops.op_encode_binary_string(bytes);
-                      ArrayPrototypeMap(
-                        [...new Uint8Array(bytes.buffer)],
-                        (v) => StringFromCodePoint(v),
-                      ),
-                      "",
-                    );
                     break;
                   case "Text": {
                     let decoder = undefined;

ext/web/lib.rs

@@ -94,6 +94,7 @@ pub fn init<P: TimersPermission + 'static>(
       op_encoding_new_decoder::decl(),
       op_encoding_decode::decl(),
       op_encoding_encode_into::decl(),
+      op_encode_binary_string::decl(),
       op_blob_create_part::decl(),
       op_blob_slice_part::decl(),
       op_blob_read_part::decl(),
@@ -337,6 +338,11 @@ fn op_encoding_encode_into(
   Ok(())
 }
 
+#[op]
+fn op_encode_binary_string(s: &[u8]) -> ByteString {
+  ByteString::from(s)
+}
+
 /// Creates a [`CancelHandle`] resource that can be used to cancel invocations of certain ops.
 #[op(fast)]
 pub fn op_cancel_handle(state: &mut OpState) -> u32 {