È Index accents (#1476)

.changeset/gentle-buckets-cheat.md

@@ -0,0 +1,6 @@
+---
+"myst-directives": patch
+"myst-transforms": patch
+---
+
+Ensure é ends up in the E index.

docs/glossaries-and-terms.md

@@ -6,8 +6,10 @@ short_title: Glossaries, Terms, & Index Pages
 You can define Terms and generate reference pages for them with Glossaries and Index Pages. This allows you to centralize definitions and pointers to where various items are mentioned throughout your documents.
 
 :::{seealso} See our index and glossary page
+
 - The [glossary for these docs](#glossary-page)
 - The [index for these docs](#index-page)
+
 :::
 
 ## Glossaries
@@ -23,7 +25,7 @@ term
 : A term is a [word with a specialized meaning](https://en.wikipedia.org/wiki/Terminology).
 
 index
-: An [organized list of information in a publication](https://en.wikipedia.org/wiki/Index_(publishing)).
+: An [organized list of information in a publication](<https://en.wikipedia.org/wiki/Index_(publishing)>).
 
 index entry
 : A word or phrase that has been marked for inclusion in the index with the `index` directive or role.
@@ -83,10 +85,10 @@ The existing syntax for `index` directives and `index` roles has been taken dire
 
 You can define index entries with Directives like so:
 
-````
+```
 :::{index} my first index item
 :::
-````
+```
 
 % This won't show up in the content
 :::{index} my first index item

docs/glossary.md

@@ -4,6 +4,7 @@ description: Glossary of terms used throughout the MyST ecosystem.
 ---
 
 (glossary-page)=
+
 ## Glossary
 
 :::{glossary}
@@ -66,7 +67,9 @@ and build a variety of outputs for interactivity and document publishing.
 :::
 
 (index-page)=
+
 ## Index
 
 ```{show-index}
-```
+
+```

packages/myst-transforms/src/indices.spec.ts

@@ -1,5 +1,5 @@
 import { describe, expect, test } from 'vitest';
-import { indexIdentifierTransform } from './indices';
+import { getNormalizedFirstLetter, indexIdentifierTransform } from './indices';
 
 describe('Test indexEntry plugin', () => {
   test('adds label/identifier/html_id to indexEntries', () => {
@@ -15,4 +15,12 @@ describe('Test indexEntry plugin', () => {
     expect(mdast.children[1].identifier).toBeTruthy();
     expect(mdast.children[1].html_id).toBeTruthy();
   });
+  test('index letter', () => {
+    expect(getNormalizedFirstLetter('éxxx')).toBe('E');
+    expect(getNormalizedFirstLetter('öxxx')).toBe('O');
+    expect(getNormalizedFirstLetter('Ñxxx')).toBe('N');
+    expect(getNormalizedFirstLetter('ø')).toBe('Other');
+    expect(getNormalizedFirstLetter('100 Steps')).toBe('1');
+    expect(getNormalizedFirstLetter(' spaces! ')).toBe('S');
+  });
 });

packages/myst-transforms/src/indices.ts

@@ -5,7 +5,18 @@ import { selectAll } from 'unist-util-select';
 import type { IReferenceStateResolver, ReferenceState, Target } from './enumerate.js';
 import type { VFile } from 'vfile';
 
-const ALPHABET_UPPER = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ';
+const ALLOWED_INDEX_CHARS = '123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ';
+
+/** Changes é to E etc. */
+export function getNormalizedFirstLetter(entry: string): string {
+  if (!entry) return 'Other';
+  const char = entry
+    .trim()[0]
+    .normalize('NFD')
+    .replace(/\p{Diacritic}/gu, '')
+    .toUpperCase();
+  return ALLOWED_INDEX_CHARS.includes(char) ? char : 'Other';
+}
 
 /**
  * Ensure all nodes with index entries have label/identifier/html_id
@@ -58,9 +69,7 @@ function organizeTargetEntries(indexTargets: Target[], vfile: VFile) {
   > = {};
   indexTargets.forEach(({ node }) => {
     node.indexEntries?.forEach(({ entry, subEntry, emphasis }) => {
-      const letter = ALPHABET_UPPER.includes(entry[0]?.toUpperCase())
-        ? entry[0].toUpperCase()
-        : 'Other';
+      const letter = getNormalizedFirstLetter(entry);
       if (!entryDict[letter]) entryDict[letter] = {};
       const indexTargetInfo: IndexTargetInfo = { node, emphasis };
       if (!entryDict[letter][entry]) {
@@ -166,9 +175,7 @@ function resolveIndexPrefix(
           value: ', ',
         });
       }
-      const xrefLetter = ALPHABET_UPPER.includes(value[0]?.toUpperCase())
-        ? value[0].toLowerCase()
-        : 'other';
+      const xrefLetter = getNormalizedFirstLetter(value).toLowerCase();
       const xref = {
         type: 'crossReference',
         identifier: `index-heading-${xrefLetter}`,
@@ -228,7 +235,7 @@ export function buildIndexTransform(
     .map((entryItems) => [...Object.keys(entryItems)])
     .flat();
   const indexContent: GenericNode[] = [];
-  [...ALPHABET_UPPER, 'Other'].forEach((letter) => {
+  [...ALLOWED_INDEX_CHARS, 'Other'].forEach((letter) => {
     if (!entryDict[letter]) return;
     const term = {
       type: 'definitionTerm',