From 703568dab3c19eb392db3fe2b02451be1f7f745e Mon Sep 17 00:00:00 2001
From: Simon Cambier <simon.cambier@protonmail.com>
Date: Sun, 17 Dec 2023 13:50:07 +0100
Subject: [PATCH] Fixed bug with diacritcs and quoted searches

Also added more cached data
---
 src/cache-manager.ts     |  4 ++++
 src/globals.ts           |  1 +
 src/search/omnisearch.ts | 11 +++++------
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/src/cache-manager.ts b/src/cache-manager.ts
index f778525..9a96fbc 100644
--- a/src/cache-manager.ts
+++ b/src/cache-manager.ts
@@ -17,6 +17,8 @@ import {
   isFilenameIndexable,
   logDebug,
   makeMD5,
+  removeDiacritics,
+  stripMarkdownCharacters,
 } from './tools/utils'
 import type { CanvasData } from 'obsidian/canvas'
 import type { AsPlainObject } from 'minisearch'
@@ -143,6 +145,8 @@ async function getAndMapIndexedDocument(
   return {
     basename: file.basename,
     content,
+    /** Content without diacritics and markdown chars */
+    cleanedContent: stripMarkdownCharacters(removeDiacritics(content)),
     path: file.path,
     mtime: file.stat.mtime,
 
diff --git a/src/globals.ts b/src/globals.ts
index 86344c9..2c20d06 100644
--- a/src/globals.ts
+++ b/src/globals.ts
@@ -53,6 +53,7 @@ export type IndexedDocument = {
   mtime: number
 
   content: string
+  cleanedContent: string
   aliases: string
   tags: string[]
   unmarkedTags: string[]
diff --git a/src/search/omnisearch.ts b/src/search/omnisearch.ts
index 4e3f141..b23d285 100644
--- a/src/search/omnisearch.ts
+++ b/src/search/omnisearch.ts
@@ -13,7 +13,6 @@ import {
   removeDiacritics,
   splitCamelCase,
   splitHyphens,
-  stripMarkdownCharacters,
 } from '../tools/utils'
 import { Notice } from 'obsidian'
 import type { Query } from './query'
@@ -321,10 +320,10 @@ export class Omnisearch {
       results = results.filter(r => {
         const document = documents.find(d => d.path === r.id)
         const title = document?.path.toLowerCase() ?? ''
-        const content = stripMarkdownCharacters(
-          document?.content ?? ''
-        ).toLowerCase()
-        return exactTerms.every(q => content.includes(q) || title.includes(q))
+        const content = (document?.cleanedContent ?? '').toLowerCase()
+        return exactTerms.every(
+          q => content.includes(q) || removeDiacritics(title).includes(q)
+        )
       })
     }
 
@@ -333,7 +332,7 @@ export class Omnisearch {
     if (exclusions.length) {
       logDebug('Filtering with exclusions')
       results = results.filter(r => {
-        const content = stripMarkdownCharacters(
+        const content = (
           documents.find(d => d.path === r.id)?.content ?? ''
         ).toLowerCase()
         return exclusions.every(q => !content.includes(q))