feat(@angular-devkit/schematics): support unicode character HTML element names

The HTML specification allows for a wide variety of characters to be present within a custom element name.  The previous behavior limited the names to mostly alphanumeric characters.  This change opens up the names to include the characters specified within the specification for custom element names.

Author: clydin

packages/angular_devkit/schematics/src/formats/html-selector.ts

@@ -5,18 +5,47 @@
  * Use of this source code is governed by an MIT-style license that can be
  * found in the LICENSE file at https://angular.io/license
  */
-
 import { schema } from '@angular-devkit/core';
 
+// As per https://html.spec.whatwg.org/multipage/custom-elements.html#valid-custom-element-name
+// * Without mandatory `-` as the application prefix will generally cover its inclusion
+// * And an allowance for upper alpha characters
+
+// NOTE: This should eventually be broken out into two formats: full and partial (allows for prefix)
+
+const unicodeRanges = [
+  [0xC0, 0xD6],
+  [0xD8, 0xF6],
+  [0xF8, 0x37D],
+  [0x37F, 0x1FFF],
+  [0x200C, 0x200D],
+  [0x203F, 0x2040],
+  [0x2070, 0x218F],
+  [0x2C00, 0x2FEF],
+  [0x3001, 0xD7FF],
+  [0xF900, 0xFDCF],
+  [0xFDF0, 0xFFFD],
+  [0x10000, 0xEFFFF],
+];
+
+function isValidElementName(name: string) {
+  let regex = '^[a-zA-Z][';
+
+  regex += '-.0-9_a-zA-Z\\u{B7}';
+
+  for (const range of unicodeRanges) {
+    regex += `\\u{${range[0].toString(16)}}-\\u{${range[1].toString(16)}}`;
+  }
+
+  regex += ']*$';
 
-// Must start with a letter, and must contain only alphanumeric characters or dashes.
-// When adding a dash the segment after the dash must also start with a letter.
-export const htmlSelectorRe = /^[a-zA-Z][.0-9a-zA-Z]*(:?-[a-zA-Z][.0-9a-zA-Z]*)*$/;
+  return new RegExp(regex, 'u').test(name);
+}
 
 export const htmlSelectorFormat: schema.SchemaFormat = {
   name: 'html-selector',
   formatter: {
     async: false,
-    validate: (selector: string) => htmlSelectorRe.test(selector),
+    validate: name => typeof name === 'string' && isValidElementName(name),
   },
 };

packages/angular_devkit/schematics/src/formats/html-selector_spec.ts

@@ -5,12 +5,10 @@
  * Use of this source code is governed by an MIT-style license that can be
  * found in the LICENSE file at https://angular.io/license
  */
-
 import { map } from 'rxjs/operators';
 import { formatValidator } from './format-validator';
 import { htmlSelectorFormat } from './html-selector';
 
-
 describe('Schematics HTML selector format', () => {
   it('accepts correct selectors', done => {
     const data = { selector: 'my-selector' };
@@ -45,14 +43,25 @@ describe('Schematics HTML selector format', () => {
       .toPromise().then(done, done.fail);
   });
 
-  it('rejects selectors with non-letter after dash', done => {
+  it('accepts selectors with non-letter after dash', done => {
     const data = { selector: 'my-1selector' };
     const dataSchema = {
       properties: { selector: { type: 'string', format: 'html-selector' } },
     };
 
     formatValidator(data, dataSchema, [htmlSelectorFormat])
-      .pipe(map(result => expect(result.success).toBe(false)))
+      .pipe(map(result => expect(result.success).toBe(true)))
+      .toPromise().then(done, done.fail);
+  });
+
+  it('accepts selectors with unicode', done => {
+    const data = { selector: 'app-root😀' };
+    const dataSchema = {
+      properties: { selector: { type: 'string', format: 'html-selector' } },
+    };
+
+    formatValidator(data, dataSchema, [htmlSelectorFormat])
+      .pipe(map(result => expect(result.success).toBe(true)))
       .toPromise().then(done, done.fail);
   });
 });