From 7af5da9622abb3c1ae6d39492efcaea6fd95133c Mon Sep 17 00:00:00 2001
From: MickaelK <mickael@kerjean.me>
Date: Sun, 17 Aug 2025 18:46:42 +1000
Subject: [PATCH] chore (plg_search_sqlitefts): remove unused code

---
 .../crawler/configuration.go                  |  4 +--
 .../crawler/daemon_state.go                   |  1 -
 .../crawler/phase_explore.go                  | 33 -------------------
 3 files changed, 2 insertions(+), 36 deletions(-)

diff --git a/server/plugin/plg_search_sqlitefts/crawler/configuration.go b/server/plugin/plg_search_sqlitefts/crawler/configuration.go
index 26b75a2c..81a90b4b 100644
--- a/server/plugin/plg_search_sqlitefts/crawler/configuration.go
+++ b/server/plugin/plg_search_sqlitefts/crawler/configuration.go
@@ -45,7 +45,7 @@ var SEARCH_EXCLUSION = func() []string {
 		f.Id = "folder_exclusion"
 		f.Name = "folder_exclusion"
 		f.Type = "text"
-		f.Description = "Exclude folders during the exploration phase"
+		f.Description = "Exclude some specific folder from the crawl / index"
 		f.Placeholder = "Default: node_modules,bower_components,.cache,.npm,.git"
 		f.Default = "node_modules,bower_components,.cache,.npm,.git"
 		return f
@@ -138,7 +138,7 @@ var INDEXING_EXT = func() string {
 		f.Id = "indexer_ext"
 		f.Name = "indexer_ext"
 		f.Type = "text"
-		f.Description = "File extension we want to see indexed"
+		f.Description = "Extensions that will be handled by the full text search engine"
 		f.Placeholder = "Default: org,txt,docx,pdf,md,form"
 		f.Default = "org,txt,docx,pdf,md,form"
 		return f
diff --git a/server/plugin/plg_search_sqlitefts/crawler/daemon_state.go b/server/plugin/plg_search_sqlitefts/crawler/daemon_state.go
index ba881986..b4de23c3 100644
--- a/server/plugin/plg_search_sqlitefts/crawler/daemon_state.go
+++ b/server/plugin/plg_search_sqlitefts/crawler/daemon_state.go
@@ -26,7 +26,6 @@ type Crawler struct {
 	Backend        IBackend
 	State          indexer.Index
 	mu             sync.Mutex
-	lastHash       string
 }
 
 func NewCrawler(id string, b IBackend) (Crawler, error) {
diff --git a/server/plugin/plg_search_sqlitefts/crawler/phase_explore.go b/server/plugin/plg_search_sqlitefts/crawler/phase_explore.go
index 03134639..e6e3ab80 100644
--- a/server/plugin/plg_search_sqlitefts/crawler/phase_explore.go
+++ b/server/plugin/plg_search_sqlitefts/crawler/phase_explore.go
@@ -2,10 +2,7 @@ package plg_search_sqlitefts
 
 import (
 	"container/heap"
-	"encoding/base64"
-	"hash/fnv"
 	"path/filepath"
-	"strconv"
 	"strings"
 	"time"
 
@@ -30,36 +27,7 @@ func (this *Crawler) Discover(tx indexer.Manager) bool {
 		this.CurrentPhase = ""
 		return true
 	}
-	if len(files) == 0 {
-		return true
-	}
 
-	// We don't want our indexer to go wild and diverge over time. As such we need to detect those edge cases: aka
-	// recursive folder structure. Our detection is relying on a Hash of []os.FileInfo
-	hashFiles := func() string {
-		var step int = len(files) / 50
-		if step == 0 {
-			step = 1
-		}
-		hasher := fnv.New32()
-		hasher.Write([]byte(strconv.Itoa(len(files))))
-		for i := 0; i < len(files); i = i + step {
-			hasher.Write([]byte(files[i].Name()))
-		}
-		return base64.StdEncoding.EncodeToString(hasher.Sum(nil))
-	}()
-	if hashFiles == this.lastHash {
-		return true
-	}
-	this.lastHash = ""
-	for i := 0; i < this.FoldersUnknown.Len(); i++ {
-		if this.FoldersUnknown[i].Hash == hashFiles && filepath.Base(doc.Path) != filepath.Base(this.FoldersUnknown[i].Path) {
-			this.lastHash = hashFiles
-			return true
-		}
-	}
-
-	// Insert the newly found data within our index
 	excluded := SEARCH_EXCLUSION()
 	for i := range files {
 		f := files[i]
@@ -105,7 +73,6 @@ func (this *Crawler) Discover(tx indexer.Manager) bool {
 					Path:    p,
 					Size:    f.Size(),
 					ModTime: f.ModTime(),
-					Hash:    hashFiles,
 				})
 			}
 		} else {