@markuplint/spec-generator 4.7.0 → 4.8.1

package/CHANGELOG.md

@@ -3,6 +3,24 @@
 All notable changes to this project will be documented in this file.
 See [Conventional Commits](https://conventionalcommits.org) for commit guidelines.
 
+## [4.8.1](https://github.com/markuplint/markuplint/compare/@markuplint/spec-generator@4.8.0...@markuplint/spec-generator@4.8.1) (2025-11-05)
+
+**Note:** Version bump only for package @markuplint/spec-generator
+
+
+
+
+
+# [4.8.0](https://github.com/markuplint/markuplint/compare/@markuplint/spec-generator@4.7.0...@markuplint/spec-generator@4.8.0) (2025-08-24)
+
+### Bug Fixes
+
+- **spec-generator:** remove debug log ([a00691b](https://github.com/markuplint/markuplint/commit/a00691bc9874ba6a8adb5bf6217e7d6c79959660))
+
+### Features
+
+- **spec-generator:** update MDN scraping logic ([45889a9](https://github.com/markuplint/markuplint/commit/45889a9a308c48ccd43df6837463d0ecabd547a8))
+
 # [4.7.0](https://github.com/markuplint/markuplint/compare/@markuplint/spec-generator@4.6.19...@markuplint/spec-generator@4.7.0) (2025-08-13)
 
 ### Bug Fixes

package/lib/html-elements.js

@@ -50,13 +50,16 @@ export async function getElements(filePattern) {
     specs.push(...obsoleteElements);
     specs = await Promise.all(specs.map(async (el) => {
         const { localName, namespace, ml } = getName(el.name);
-        const cite = `https://developer.mozilla.org/en-US/docs/Web/${ml}/Element/${localName}`;
+        const urlTagName = /^h[1-6]$/i.test(localName) ? 'Heading_Elements' : localName;
+        // https://developer.mozilla.org/en-US/docs/Web/HTML/Reference/Elements/a
+        // https://developer.mozilla.org/en-US/docs/Web/SVG/Reference/Element/a
+        const cite = `https://developer.mozilla.org/en-US/docs/Web/${ml}/Reference/Element${ml === 'HTML' ? 's' : ''}/${urlTagName}`;
         const mdnData = await fetchHTMLElement(cite);
         // @ts-ignore
         delete el.name;
         // @ts-ignore
         delete el.namespace;
-        return {
+        const spec = {
             // @ts-ignore
             name: namespace === 'http://www.w3.org/2000/svg' ? `svg:${localName}` : localName,
             namespace,
@@ -99,9 +102,9 @@ export async function getElements(filePattern) {
                 return attrs;
             })()),
         };
+        return spec;
     }));
     return specs
         .sort(nameCompare)
-        .sort((a, b) => (a.namespace == b.namespace ? 0 : a.namespace === 'http://www.w3.org/2000/svg' ? 1 : -1))
-        .filter(spec => spec.name !== 'h1-h6');
+        .sort((a, b) => (a.namespace == b.namespace ? 0 : a.namespace === 'http://www.w3.org/2000/svg' ? 1 : -1));
 }

package/lib/scraping.d.ts

@@ -1,4 +1,3 @@
 import type { ExtendedElementSpec } from '@markuplint/ml-spec';
-export declare function fetchHTMLElementLinks(): Promise<string[]>;
 export declare function fetchObsoleteElements(obsoleteList: readonly string[], specs: readonly ExtendedElementSpec[]): ExtendedElementSpec[];
 export declare function fetchHTMLElement(link: string): Promise<ExtendedElementSpec>;

package/lib/scraping.js

@@ -1,18 +1,6 @@
 import { fetch } from './fetch.js';
-import { getThisOutline, sortObjectByKey } from './utils.js';
-const MAIN_ARTICLE_SELECTOR = 'article.main-page-content, article.article';
-export async function fetchHTMLElementLinks() {
-    const $ = await fetch('https://developer.mozilla.org/en-US/docs/Web/HTML/Element');
-    const $listHeading = $($('#sidebar-quicklinks summary')
-        .toArray()
-        .find(el => /html elements/i.test($(el).text())));
-    const $list = $listHeading.siblings('ol,ul');
-    const lists = $list
-        .find('li a')
-        .toArray()
-        .map(el => `https://developer.mozilla.org${$(el).attr('href')}`);
-    return lists;
-}
+import { sortObjectByKey } from './utils.js';
+const MAIN_ARTICLE_SELECTOR = 'main#content';
 export function fetchObsoleteElements(obsoleteList, specs) {
     return obsoleteList
         .map(name => {
@@ -41,16 +29,13 @@ export function fetchObsoleteElements(obsoleteList, specs) {
 }
 export async function fetchHTMLElement(link) {
     const $ = await fetch(link);
-    let name = link.replace(/.+\/([\w-]+)$/, '$1').toLowerCase();
-    if (name === 'heading_elements') {
-        name = 'h1-h6';
-    }
+    const name = link.replace(/.+\/([\w-]+)$/, '$1').toLowerCase();
     const $article = $(MAIN_ARTICLE_SELECTOR);
-    $article.find('p:empty').remove();
-    const description = $article.find('h2#summary').next('div').find('> p:first-of-type').text().trim().replaceAll(/\s+/g, ' ') ||
-        $article.find('.seoSummary').closest('p').text().trim().replaceAll(/\s+/g, ' ') ||
-        $article.find('h1').next('div').find('> p:first-of-type').text().trim().replaceAll(/\s+/g, ' ') ||
-        $article.find('.section-content:eq(0)').find('> p:eq(0)').text().trim().replaceAll(/\s+/g, ' ');
+    const description = $article
+        .find('.reference-layout__header .content-section')
+        .text()
+        .trim()
+        .replaceAll(/\s+/g, ' ');
     const $bcTable = $article.find('.bc-table');
     const $bcTableFirstRow = $bcTable.find('tbody tr:first-child th');
     const isBcTableIsAvailable = $bcTableFirstRow.find('code').text().trim() === name;
@@ -98,11 +83,11 @@ export async function fetchHTMLElement(link) {
         categories.push('#palpable');
     if (/script-supporting/i.test(cat))
         categories.push('#script-supporting');
-    let { attributes } = getAttributes($, '#attributes', name);
-    const { attributes: deprecatedAttributes } = getAttributes($, '#deprecated_attributes', name);
-    const { attributes: individualAttributes } = getAttributes($, '#individual_attributes', name);
-    const { attributes: nonStandardAttributes } = getAttributes($, '#non-standard_attributes', name);
-    const { attributes: obsoleteAttributes } = getAttributes($, '#obsolete_attributes', name);
+    let { attributes } = getAttributes($, 'attributes');
+    const { attributes: deprecatedAttributes } = getAttributes($, 'deprecated_attributes');
+    const { attributes: individualAttributes } = getAttributes($, 'individual_attributes');
+    const { attributes: nonStandardAttributes } = getAttributes($, 'non-standard_attributes');
+    const { attributes: obsoleteAttributes } = getAttributes($, 'obsolete_attributes');
     attributes = sortObjectByKey({
         ...attributes,
         ...deprecatedAttributes,
@@ -134,7 +119,7 @@ export async function fetchHTMLElement(link) {
 function getProperty(
 // eslint-disable-next-line @typescript-eslint/prefer-readonly-parameter-types
 $, prop) {
-    const $tr = $(MAIN_ARTICLE_SELECTOR).find('table.properties tr') ?? $('#Technical_summary').next('table tr');
+    const $tr = $('#technical_summary ~ figure.table-container > table tr');
     const $th = $($tr
         .find('th')
         .toArray()
@@ -143,11 +128,10 @@ $, prop) {
 }
 function getAttributes(
 // eslint-disable-next-line @typescript-eslint/prefer-readonly-parameter-types
-$, heading, tagName) {
-    const $heading = $(heading);
-    const $outline = getThisOutline($, $heading);
+$, id) {
+    const $section = $(`.content-section[aria-labelledby="${id}"]`);
     const attributes = {};
-    for (const dt of $outline.find('> div > dl > dt').toArray()) {
+    for (const dt of $section.find('> dl > dt').toArray()) {
         const $dt = $(dt);
         const name = $dt.find('code').text().trim();
         if (!name) {

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@markuplint/spec-generator",
-	"version": "4.7.0",
+	"version": "4.8.1",
 	"description": "Generates @markuplint/html-spec",
 	"repository": "git@github.com:markuplint/markuplint.git",
 	"author": "Yusuke Hirao <yusukehirao@me.com>",
@@ -30,10 +30,10 @@
 		"strip-json-comments": "5.0.3"
 	},
 	"devDependencies": {
-		"@markuplint/ml-spec": "4.9.7",
-		"@markuplint/test-tools": "4.5.20",
+		"@markuplint/ml-spec": "4.10.1",
+		"@markuplint/test-tools": "4.5.22",
 		"@types/cli-progress": "3.11.6",
 		"type-fest": "4.41.0"
 	},
-	"gitHead": "acbf53f7e30d7a59f850a0f279b617383266dab3"
+	"gitHead": "6213ea30269ef404f030e67bbcc7fc7443ec1060"
 }