url: implement URL.canParse

PR-URL: #47179
Backport-PR-URL: #48345
Reviewed-By: Yagiz Nizipli <[email protected]>
Reviewed-By: Debadree Chatterjee <[email protected]>

Author: KhafraDev

benchmark/url/whatwgurl-canParse.js

@@ -0,0 +1,14 @@
+'use strict';
+const common = require('../common.js');
+
+const bench = common.createBenchmark(main, {
+  type: Object.keys(common.urls),
+  n: [25e6],
+});
+
+function main({ type, n }) {
+  bench.start();
+  for (let i = 0; i < n; i += 1)
+    URL.canParse(common.urls[type]);
+  bench.end(n);
+}

doc/api/url.md

@@ -662,6 +662,27 @@ added: v16.7.0
 Removes the stored {Blob} identified by the given ID. Attempting to revoke a
 ID that isn't registered will silently fail.
 
+#### `URL.canParse(input[, base])`
+
+<!-- YAML
+added: REPLACEME
+-->
+
+* `input` {string} The absolute or relative input URL to parse. If `input`
+  is relative, then `base` is required. If `input` is absolute, the `base`
+  is ignored. If `input` is not a string, it is [converted to a string][] first.
+* `base` {string} The base URL to resolve against if the `input` is not
+  absolute. If `base` is not a string, it is [converted to a string][] first.
+* Returns: {boolean}
+
+Checks if an `input` relative to the `base` can be parsed to a `URL`.
+
+```js
+const isValid = URL.canParse('/foo', 'https://example.org/'); // true
+
+const isNotValid = URL.canParse('/foo'); // false
+```
+
 ### Class: `URLSearchParams`
 
 <!-- YAML

lib/internal/url.js

@@ -91,6 +91,7 @@ const {
   domainToASCII: _domainToASCII,
   domainToUnicode: _domainToUnicode,
   parse,
+  canParse: _canParse,
   updateUrl,
 } = internalBinding('url');
 
@@ -793,6 +794,16 @@ class URL {
     return this[context].href;
   }
 
+  static canParse(url, base = undefined) {
+    url = `${url}`;
+
+    if (base !== undefined) {
+      base = `${base}`;
+    }
+
+    return _canParse(url, base);
+  }
+
   static createObjectURL(obj) {
     const cryptoRandom = lazyCryptoRandom();
     if (cryptoRandom === undefined)
@@ -842,6 +853,12 @@ ObjectDefineProperties(URL.prototype, {
 });
 
 ObjectDefineProperties(URL, {
+  canParse: {
+    __proto__: null,
+    configurable: true,
+    writable: true,
+    enumerable: true,
+  },
   createObjectURL: kEnumerableProperty,
   revokeObjectURL: kEnumerableProperty,
 });

src/node_url.cc

@@ -93,6 +93,30 @@ void Parse(const FunctionCallbackInfo<Value>& args) {
   args.GetReturnValue().Set(true);
 }
 
+void CanParse(const FunctionCallbackInfo<Value>& args) {
+  CHECK_GE(args.Length(), 2);
+  CHECK(args[0]->IsString());  // input
+  // args[1] // base url
+
+  Environment* env = Environment::GetCurrent(args);
+  HandleScope handle_scope(env->isolate());
+  Context::Scope context_scope(env->context());
+
+  Utf8Value input(env->isolate(), args[0]);
+  ada::result base;
+  ada::url* base_pointer = nullptr;
+  if (args[1]->IsString()) {
+    base = ada::parse(Utf8Value(env->isolate(), args[1]).ToString());
+    if (!base) {
+      return args.GetReturnValue().Set(false);
+    }
+    base_pointer = &base.value();
+  }
+  ada::result out = ada::parse(input.ToStringView(), base_pointer);
+
+  args.GetReturnValue().Set(out.has_value());
+}
+
 void DomainToASCII(const FunctionCallbackInfo<Value>& args) {
   Environment* env = Environment::GetCurrent(args);
   CHECK_GE(args.Length(), 1);
@@ -285,6 +309,7 @@ void Initialize(Local<Object> target,
                 void* priv) {
   SetMethod(context, target, "parse", Parse);
   SetMethod(context, target, "updateUrl", UpdateUrl);
+  SetMethodNoSideEffect(context, target, "canParse", CanParse);
   SetMethodNoSideEffect(context, target, "formatUrl", FormatUrl);
 
   SetMethodNoSideEffect(context, target, "domainToASCII", DomainToASCII);
@@ -294,6 +319,7 @@ void Initialize(Local<Object> target,
 
 void RegisterExternalReferences(ExternalReferenceRegistry* registry) {
   registry->Register(Parse);
+  registry->Register(CanParse);
   registry->Register(UpdateUrl);
   registry->Register(FormatUrl);
 

test/fixtures/wpt/README.md

@@ -27,7 +27,7 @@ Last update:
 - performance-timeline: https://github.com/web-platform-tests/wpt/tree/17ebc3aea0/performance-timeline
 - resources: https://github.com/web-platform-tests/wpt/tree/fbf1e7d247/resources
 - streams: https://github.com/web-platform-tests/wpt/tree/9e5ef42bd3/streams
-- url: https://github.com/web-platform-tests/wpt/tree/84caeb6fbd/url
+- url: https://github.com/web-platform-tests/wpt/tree/7c5c3cc125/url
 - user-timing: https://github.com/web-platform-tests/wpt/tree/df24fb604e/user-timing
 - wasm/jsapi: https://github.com/web-platform-tests/wpt/tree/cde25e7e3c/wasm/jsapi
 - wasm/webapi: https://github.com/web-platform-tests/wpt/tree/fd1b23eeaa/wasm/webapi

test/fixtures/wpt/url/url-statics-canparse.any.js

@@ -0,0 +1,42 @@
+// This intentionally does not use resources/urltestdata.json to preserve resources.
+[
+  {
+    "url": undefined,
+    "base": undefined,
+    "expected": false
+  },
+  {
+    "url": "a:b",
+    "base": undefined,
+    "expected": true
+  },
+  {
+    "url": undefined,
+    "base": "a:b",
+    "expected": false
+  },
+  {
+    "url": "a:/b",
+    "base": undefined,
+    "expected": true
+  },
+  {
+    "url": undefined,
+    "base": "a:/b",
+    "expected": true
+  },
+  {
+    "url": "https://test:test",
+    "base": undefined,
+    "expected": false
+  },
+  {
+    "url": "a",
+    "base": "https://b/",
+    "expected": true
+  }
+].forEach(({ url, base, expected }) => {
+  test(() => {
+    assert_equals(URL.canParse(url, base), expected);
+  }, `URL.canParse(${url}, ${base})`);
+});

test/fixtures/wpt/versions.json

@@ -68,7 +68,7 @@
     "path": "streams"
   },
   "url": {
-    "commit": "84caeb6fbdf45129f57c67448e6113ee1ced9fb3",
+    "commit": "7c5c3cc125979b4768d414471e6ab655b473aae8",
     "path": "url"
   },
   "user-timing": {