From 615af97043cbc822f65fa4deb361ee24a530604b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C5=99emysl=20Eric=20Janouch?= <p@janouch.name>
Date: Sat, 21 Dec 2024 10:49:20 +0100
Subject: [PATCH] Add a sync option to exclude paths by regexp

---
 main.go | 23 ++++++++++++++++++++++-
 test.sh |  7 +++++--
 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/main.go b/main.go
index 23087c0..84d3218 100644
--- a/main.go
+++ b/main.go
@@ -1286,6 +1286,9 @@ type syncContext struct {
 	stmtDisposeSub *sql.Stmt
 	stmtDisposeAll *sql.Stmt
 
+	// exclude specifies filesystem paths that should be seen as missing.
+	exclude *regexp.Regexp
+
 	// linked tracks which image hashes we've checked so far in the run.
 	linked map[string]struct{}
 }
@@ -1694,6 +1697,12 @@ func syncDirectory(c *syncContext, dbParent int64, fsPath string) error {
 		fs = nil
 	}
 
+	if c.exclude != nil {
+		fs = slices.DeleteFunc(fs, func(f syncFile) bool {
+			return c.exclude.MatchString(filepath.Join(fsPath, f.fsName))
+		})
+	}
+
 	// Convert differences to a form more convenient for processing.
 	iDB, iFS, pairs := 0, 0, []syncPair{}
 	for iDB < len(db) && iFS < len(fs) {
@@ -1869,9 +1878,21 @@ const disposeCTE = `WITH RECURSIVE
 		HAVING count = total
 	)`
 
+type excludeRE struct{ re *regexp.Regexp }
+
+func (re *excludeRE) String() string { return fmt.Sprintf("%v", re.re) }
+
+func (re *excludeRE) Set(value string) error {
+	var err error
+	re.re, err = regexp.Compile(value)
+	return err
+}
+
 // cmdSync ensures the given (sub)roots are accurately reflected
 // in the database.
 func cmdSync(fs *flag.FlagSet, args []string) error {
+	var exclude excludeRE
+	fs.Var(&exclude, "exclude", "exclude paths matching regular expression")
 	fullpaths := fs.Bool("fullpaths", false, "don't basename arguments")
 	if err := fs.Parse(args); err != nil {
 		return err
@@ -1909,7 +1930,7 @@ func cmdSync(fs *flag.FlagSet, args []string) error {
 	}
 
 	c := syncContext{ctx: ctx, tx: tx, pb: newProgressBar(-1),
-		linked: make(map[string]struct{})}
+		exclude: exclude.re, linked: make(map[string]struct{})}
 	defer c.pb.Stop()
 
 	if c.stmtOrphan, err = c.tx.Prepare(disposeCTE + `
diff --git a/test.sh b/test.sh
index 2f12d07..89db5f4 100755
--- a/test.sh
+++ b/test.sh
@@ -16,6 +16,9 @@ sha1duplicate=$sha1
 cp $input/Test/dhash.png \
 	$input/Test/multiple-paths.png
 
+gen -seed 15 -size 256x256 plasma:fractal \
+	$input/Test/excluded.png
+
 gen -seed 20 -size 160x128 plasma:fractal \
 	-bordercolor transparent -border 64 \
 	$input/Test/transparent-wide.png
@@ -36,7 +39,7 @@ gen $input/Test/animation-small.gif \
 	$input/Test/video.mp4
 
 ./gallery init $target
-./gallery sync $target $input "$@"
+./gallery sync -exclude '/excluded[.]' $target $input "$@"
 ./gallery thumbnail $target
 ./gallery dhash $target
 ./gallery tag $target test "Test space" <<-END
@@ -47,7 +50,7 @@ END
 
 # TODO: Test all the various possible sync transitions.
 mv $input/Test $input/Plasma
-./gallery sync $target $input
+./gallery sync -exclude '/excluded[.]' $target $input
 
 ./gallery web $target :8080 &
 web=$!