#176 - WIP tokenization of CamelCase words

Technically works, but highlighting needs a rework

src/search/omnisearch.ts

@@ -10,6 +10,7 @@ import { settings } from '../settings'
 import {
   chunkArray,
   removeDiacritics,
+  splitCamelCase,
   stringsToRegex,
   stripMarkdownCharacters,
 } from '../tools/utils'
@@ -25,7 +26,7 @@ const tokenize = (text: string): string[] => {
     return tokens.flatMap(word =>
       chsRegex.test(word) ? chsSegmenter.cut(word) : [word]
     )
-  } else return tokens
+  } else return tokens.flatMap(splitCamelCase)
 }
 
 export class Omnisearch {

src/tools/utils.ts

@@ -307,3 +307,11 @@ export function chunkArray<T>(arr: T[], len: number): T[][] {
 
   return chunks
 }
+
+/**
+ * Converts a 'fooBarBAZLorem' into ['foo', 'Bar', 'BAZ', 'Lorem]
+ * @param text
+ */
+export function splitCamelCase(text: string): string[] {
+  return text.replace(/([a-z](?=[A-Z]))/g, '$1 ').split(' ')
+}