Add flag to avoid crawling hidden files

3 files changed, 25 insertions, 10 deletions

diff --git a/cmd/index.go b/cmd/index.go
index f072599..2f18fe0 100644
--- a/cmd/index.go
+++ b/cmd/index.go
@@ -19,10 +19,19 @@ type IndexFlags struct {
 }
 
 func setupIndexFlags(args []string, fs *flag.FlagSet, flags *IndexFlags) {
+	flags.ParseLinks = true
+	flags.ParseMeta = true
 	fs.BoolVar(&flags.IgnoreDateError, "ignoreBadDates", false, "ignore malformed dates while indexing")
 	fs.BoolVar(&flags.IgnoreMetaError, "ignoreMetaError", false, "ignore errors while parsing general YAML header info")
-	fs.BoolVar(&flags.ParseMeta, "parseMeta", true, "parse YAML header values other title, authors, date, tags")
-	fs.BoolVar(&flags.ParseLinks, "parseLinks", true, "parse file contents for links")
+	fs.BoolFunc("ignoreMeta", "don't parse YAML header values other title, authors, date, tags", func(s string) error {
+		flags.ParseMeta = false
+		return nil
+	})
+	fs.BoolFunc("ignoreLinks", "don't parse file contents for links", func(s string) error {
+		flags.ParseLinks = false
+		return nil
+	})
+	fs.BoolVar(&flags.IgnoreHidden, "ignoreHidden", false, "ignore hidden files while crawling")
 
 	fs.Usage = func() {
 		f := fs.Output()
@@ -84,7 +93,7 @@ func runIndex(gFlags GlobalFlags, iFlags IndexFlags, db *data.Query) byte {
 			)
 		}
 
-		traversedFiles := idx.Traverse(gFlags.NumWorkers)
+		traversedFiles := idx.Traverse(gFlags.NumWorkers, iFlags.IgnoreHidden)
 		fmt.Print("Crawled ", len(traversedFiles))
 
 		filteredFiles := idx.Filter(traversedFiles, gFlags.NumWorkers)
diff --git a/pkg/index/index.go b/pkg/index/index.go
index 4db1eb4..cfa4138 100644
--- a/pkg/index/index.go
+++ b/pkg/index/index.go
@@ -7,6 +7,7 @@ import (
 	"io"
 	"log/slog"
 	"os"
+	"path"
 	"regexp"
 	"slices"
 	"strings"
@@ -38,6 +39,7 @@ type ParseOpts struct {
 	ParseLinks      bool
 	IgnoreDateError bool
 	IgnoreMetaError bool
+	IgnoreHidden    bool
 }
 
 type InfoPath struct {
@@ -195,16 +197,20 @@ func (doc Document) Equal(other Document) bool {
 	return true
 }
 
-func visit(file InfoPath, visitQueue chan<- InfoPath, filterQueue chan<- InfoPath, wg *sync.WaitGroup) {
+func visit(file InfoPath, visitQueue chan<- InfoPath, filterQueue chan<- InfoPath, ignoreHidden bool, wg *sync.WaitGroup) {
 	// TODO: check if symlink, and handle appropriately
 	// TODO: extract error out of function
 
+	if ignoreHidden && path.Base(file.Path)[0] == '.' {
+		wg.Done()
+		return
+	}
+
 	if file.Info.IsDir() {
 		entries, err := os.ReadDir(file.Path)
 		if err != nil {
 			panic(err)
 		}
-
 		wg.Add(len(entries))
 		for _, entry := range entries {
 			entryInfo, err := entry.Info()
@@ -223,13 +229,13 @@ func visit(file InfoPath, visitQueue chan<- InfoPath, filterQueue chan<- InfoPat
 	wg.Done()
 }
 
-func workerTraverse(wg *sync.WaitGroup, visitQueue chan InfoPath, filterQueue chan<- InfoPath) {
+func workerTraverse(wg *sync.WaitGroup, ignoreHidden bool, visitQueue chan InfoPath, filterQueue chan<- InfoPath) {
 	for work := range visitQueue {
-		visit(work, visitQueue, filterQueue, wg)
+		visit(work, visitQueue, filterQueue, ignoreHidden, wg)
 	}
 }
 
-func (idx Index) Traverse(numWorkers uint) []string {
+func (idx Index) Traverse(numWorkers uint, ignoreHidden bool) []string {
 	if numWorkers <= 1 {
 		panic(fmt.Sprint("Invalid number of workers: ", numWorkers))
 	}
@@ -247,7 +253,7 @@ func (idx Index) Traverse(numWorkers uint) []string {
 
 	// start workers
 	for range numWorkers {
-		go workerTraverse(activeJobs, jobs, filterQueue)
+		go workerTraverse(activeJobs, ignoreHidden, jobs, filterQueue)
 	}
 
 	// init send
diff --git a/pkg/index/index_test.go b/pkg/index/index_test.go
index 69600c2..4242ce1 100644
--- a/pkg/index/index_test.go
+++ b/pkg/index/index_test.go
@@ -80,7 +80,7 @@ func TestIndex_Traverse(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			idx := tt.indexCase(t)
-			got := idx.Traverse(tt.numWorkers)
+			got := idx.Traverse(tt.numWorkers, true)
 
 			slices.Sort(got)
 			slices.Sort(tt.want)