fix(v1): consistent slug & hash-link generation

packages/docusaurus-1.x/lib/core/__tests__/toSlug.test.js

@@ -5,14 +5,15 @@
  * LICENSE file in the root directory of this source tree.
  */
 
+const GitHubSlugger = require('github-slugger');
 const toSlug = require('../toSlug');
 
 [
   ['Hello world! ', 'hello-world'],
   ['React 16', 'react-16'],
-  ['Hello.   // (world?)! ', 'hello-world'],
+  ['Hello.   // (world?)! ', 'hello----world'],
   ['Привет мир! ', 'привет-мир'],
-  ['Über Café.', 'uber-cafe'],
+  ['Über Café.', 'über-café'],
   ['Someting long ...', 'someting-long-'],
   ['foo_bar', 'foo_bar'],
   ['some _ heading', 'some-_-heading'],
@@ -24,7 +25,7 @@ const toSlug = require('../toSlug');
   });
 });
 
-test('unique slugs if `context` argument passed', () => {
+test('unique slugs if `slug` argument passed', () => {
   [
     ['foo', 'foo'],
     ['foo', 'foo-1'],
@@ -34,9 +35,9 @@ test('unique slugs if `context` argument passed', () => {
     ['foo', 'foo-3'],
     ['foo_bar', 'foo_bar'],
     ['some _ heading', 'some-_-heading'],
-  ].reduce((context, [input, output]) => {
-    expect(toSlug(input, context)).toBe(output);
+  ].reduce((slugger, [input, output]) => {
+    expect(toSlug(input, slugger)).toBe(output);
 
-    return context;
-  }, {});
+    return slugger;
+  }, new GitHubSlugger());
 });

packages/docusaurus-1.x/lib/core/__tests__/toc.test.js

@@ -43,15 +43,15 @@ describe('getTOC', () => {
     test('correctly removes', () => {
       const headings = getTOC(`## <a name="foo"></a> Foo`, 'h2', []);
 
-      expect(headings[0].hashLink).toEqual('foo');
+      expect(headings[0].hashLink).toEqual('a-namefooa-foo');
       expect(headings[0].rawContent).toEqual(`<a name="foo"></a> Foo`);
       expect(headings[0].content).toEqual('Foo');
     });
 
     test('retains formatting from Markdown', () => {
       const headings = getTOC(`## <a name="foo"></a> _Foo_`, 'h2', []);
 
-      expect(headings[0].hashLink).toEqual('foo');
+      expect(headings[0].hashLink).toEqual('a-namefooa-_foo_');
       expect(headings[0].rawContent).toEqual(`<a name="foo"></a> _Foo_`);
       expect(headings[0].content).toEqual('<em>Foo</em>');
     });

packages/docusaurus-1.x/lib/core/anchors.js

@@ -5,7 +5,8 @@
  * LICENSE file in the root directory of this source tree.
  */
 
-const toSlug = require('./toSlug.js');
+const GithubSlugger = require('github-slugger');
+const toSlug = require('./toSlug');
 
 /**
  * The anchors plugin adds GFM-style anchors to headings.
@@ -14,11 +15,14 @@ function anchors(md) {
   const originalRender = md.renderer.rules.heading_open;
 
   md.renderer.rules.heading_open = function(tokens, idx, options, env) {
+    if (!env.slugger) {
+      env.slugger = new GithubSlugger();
+    }
+    const slugger = env.slugger;
     const textToken = tokens[idx + 1];
 
     if (textToken.content) {
-      const anchor = toSlug(textToken.content, env);
-
+      const anchor = toSlug(textToken.content, slugger);
       return `<h${tokens[idx].hLevel}><a class="anchor" aria-hidden="true" id="${anchor}"></a><a href="#${anchor}" aria-hidden="true" class="hash-link"><svg class="hash-link-icon" aria-hidden="true" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>`;
     }
 

packages/docusaurus-1.x/lib/core/toSlug.js

@@ -5,76 +5,17 @@
  * LICENSE file in the root directory of this source tree.
  */
 
-// ES2015 does not support regexp with unicode categories,
-// so we need to list all the unicode ranges manually
-// to get analog of [\P{L}\P{N}] from ES2018
-// see: https://github.com/danielberndt/babel-plugin-utf-8-regex
-const letters =
-  '\u0041-\u005A\u0061-\u007A\u00AA\u00B5\u00BA\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u0527\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0\u08A2-\u08AC\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0977\u0979-\u097F\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3D\u0C58\u0C59\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D60\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F4\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191C\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19C1-\u19C7\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FCC\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA697\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA78E\uA790-\uA793\uA7A0-\uA7AA\uA7F8-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA80-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uABC0-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC';
-const numbers =
-  '\u0030-\u0039\u00B2\u00B3\u00B9\u00BC-\u00BE\u0660-\u0669\u06F0-\u06F9\u07C0-\u07C9\u0966-\u096F\u09E6-\u09EF\u09F4-\u09F9\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0B72-\u0B77\u0BE6-\u0BF2\u0C66-\u0C6F\u0C78-\u0C7E\u0CE6-\u0CEF\u0D66-\u0D75\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F33\u1040-\u1049\u1090-\u1099\u1369-\u137C\u16EE-\u16F0\u17E0-\u17E9\u17F0-\u17F9\u1810-\u1819\u1946-\u194F\u19D0-\u19DA\u1A80-\u1A89\u1A90-\u1A99\u1B50-\u1B59\u1BB0-\u1BB9\u1C40-\u1C49\u1C50-\u1C59\u2070\u2074-\u2079\u2080-\u2089\u2150-\u2182\u2185-\u2189\u2460-\u249B\u24EA-\u24FF\u2776-\u2793\u2CFD\u3007\u3021-\u3029\u3038-\u303A\u3192-\u3195\u3220-\u3229\u3248-\u324F\u3251-\u325F\u3280-\u3289\u32B1-\u32BF\uA620-\uA629\uA6E6-\uA6EF\uA830-\uA835\uA8D0-\uA8D9\uA900-\uA909\uA9D0-\uA9D9\uAA50-\uAA59\uABF0-\uABF9\uFF10-\uFF19';
-const exceptAlphanumAndUnderscore = new RegExp(
-  `[^${[letters, numbers].join('')}_]`,
-  'g',
-);
+const GitHubSlugger = require('github-slugger');
 
 /**
  * Converts a string to a slug, that can be used in heading anchors
  *
  * @param  {string} string
- * @param  {Object} [context={}] - an optional context to track used slugs and
+ * @param  {() => string} [slugger] - reused slugger to track used slugs and
  *                                 ensure that new slug will be unique
  *
  * @return {string}
  */
-module.exports = (string, context = {}) => {
-  //  var accents = "àáäâèéëêìíïîòóöôùúüûñç";
-  const accents =
-    '\u00e0\u00e1\u00e4\u00e2\u00e8' +
-    '\u00e9\u00eb\u00ea\u00ec\u00ed\u00ef' +
-    '\u00ee\u00f2\u00f3\u00f6\u00f4\u00f9' +
-    '\u00fa\u00fc\u00fb\u00f1\u00e7';
-
-  const without = 'aaaaeeeeiiiioooouuuunc';
-
-  let slug = string
-    .toString()
-    // Handle uppercase characters
-    .toLowerCase()
-    // Handle accentuated characters
-    .replace(new RegExp(`[${accents}]`, 'g'), c =>
-      without.charAt(accents.indexOf(c)),
-    )
-    // Replace `'`, `’`, `.`, `(` and `?` with blank string like GitHub does
-    .replace(/'|’|\.|\(|\?/g, '')
-    // Dash special characters except '_' (underscore)
-    .replace(exceptAlphanumAndUnderscore, '-')
-    // Compress multiple dash
-    .replace(/-+/g, '-')
-    // Trim dashes
-    .replace(/^-|-$/g, '');
-
-  // Add trailing `-` if string contains ` ...` in the end like Github does
-  if (/\s[.]{1,}/.test(string)) {
-    slug += '-';
-  }
-
-  if (!context.slugStats) {
-    context.slugStats = {};
-  }
-
-  if (typeof context.slugStats[slug] === 'number') {
-    // search for an index, that will not clash with an existing headings
-    while (
-      typeof context.slugStats[`${slug}-${++context.slugStats[slug]}`] ===
-      'number'
-    );
-    slug += `-${context.slugStats[slug]}`;
-  }
-
-  // we are tracking both original anchors and suffixed to avoid future name
-  // clashing with headings with numbers e.g. `#Foo 1` may clash with the second `#Foo`
-  context.slugStats[slug] = 0;
-
-  return slug;
+module.exports = (string, slugger = new GitHubSlugger()) => {
+  return slugger.slug(string);
 };

packages/docusaurus-1.x/lib/core/toc.js

@@ -8,6 +8,7 @@
 const {Remarkable} = require('remarkable');
 const mdToc = require('markdown-toc');
 const striptags = require('striptags');
+const GithubSlugger = require('github-slugger');
 const toSlug = require('./toSlug');
 
 const tocRegex = new RegExp('<AUTOGENERATED_TABLE_OF_CONTENTS>', 'i');
@@ -29,19 +30,15 @@ function getTOC(content, headingTags = 'h2', subHeadingTags = 'h3') {
   const md = new Remarkable();
   const headings = mdToc(content).json;
   const toc = [];
-  const context = {};
+  const slugger = new GithubSlugger();
   let current;
 
   headings.forEach(heading => {
-    // we need always generate slugs to ensure, that we will have consistent
-    // slug indexes for headings with the same names
     const rawContent = heading.content;
     const safeContent = striptags(rawContent);
     const rendered = md.renderInline(safeContent);
 
-    // We striptags again here as to not end up with html tags
-    // from markdown or markdown in our links
-    const hashLink = toSlug(striptags(rendered), context);
+    const hashLink = toSlug(rawContent, slugger);
     if (!allowedHeadingLevels.includes(heading.lvl)) {
       return;
     }

packages/docusaurus-1.x/package.json

@@ -49,6 +49,7 @@
     "feed": "^1.1.0",
     "fs-extra": "^8.1.0",
     "gaze": "^1.1.3",
+    "github-slugger": "^1.2.1",
     "glob": "^7.1.5",
     "highlight.js": "^9.16.1",
     "imagemin": "^6.0.0",