Store mtime to the nanosecond so a same-second rewrite is re-hashed (closes #12)
check / check (push) Canceled after 0s

scan recorded mtime in whole seconds, so a file rewritten in place at
the same size within the same second as its recorded mtime was classed
unchanged and kept its old hashes. The files table keeps mtime as whole
Unix seconds and gains mtime_nsec, the nanoseconds within that second.
scan holds the mtime as a time.Time and decides "newer" by comparing
Unix() and then Nanosecond(), so any time a filesystem can record
compares in the right order; After would misorder one too late for a
time.Time to hold without wrapping. The walk, a file given as an
operand, and the content phase's recheck all move over. PRAGMA
user_version stays 1, per the owner's ruling. README states what both
columns hold.

Model: opus-5-5
This commit was merged in pull request #96.
This commit is contained in:
2026-10-08 02:51:53 +02:00
parent 0064eba542
commit 5900feb515
8 changed files with 335 additions and 68 deletions
+18 -7
View File
@@ -17,6 +17,7 @@ import (
"strings"
"sync"
"syscall"
"time"
)
// The duplicate ladder (see hashSignature and README "Duplicate
@@ -68,7 +69,7 @@ var errInterrupted = errors.New("scan interrupted")
type fileRec struct {
path string
size int64
mtime int64
mtime time.Time
dev uint64
ino uint64
}
@@ -79,7 +80,7 @@ type fileRec struct {
// they would dominate the scan's memory.
type fileMeta struct {
size int64
mtime int64
mtime time.Time
hashed bool
}
@@ -369,7 +370,7 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
s.existing = make(map[string]fileMeta)
return loadFileMeta(ctx, s.db,
func(path string, size, mtime int64, hashed bool) {
func(path string, size int64, mtime time.Time, hashed bool) {
prog.increment()
if underAnyRoot(path, roots) {
@@ -415,7 +416,7 @@ func (s *scanState) walkPhase(
old, ok := s.existing[ev.rec.path]
switch {
case !ok || old.size != ev.rec.size || old.mtime < ev.rec.mtime:
case !ok || old.size != ev.rec.size || mtimeAfter(ev.rec.mtime, old.mtime):
changed = append(changed, ev.rec)
case old.hashed:
delete(s.existing, ev.rec.path)
@@ -807,7 +808,7 @@ func unchangedFile(r scanRec) (fileRec, bool, error) {
}
if !fi.Mode().IsRegular() || fi.Size() != r.size ||
fi.ModTime().Unix() > r.mtime {
mtimeAfter(fi.ModTime(), r.mtime) {
return fileRec{}, false, nil
}
@@ -818,6 +819,16 @@ func unchangedFile(r scanRec) (fileRec, bool, error) {
}, true, nil
}
// mtimeAfter reports whether mtime a is later than mtime b.
// Not a.After(b): time.Time wraps an mtime past year 292 billion; Unix() undoes it.
func mtimeAfter(a, b time.Time) bool {
if a.Unix() != b.Unix() {
return a.Unix() > b.Unix()
}
return a.Nanosecond() > b.Nanosecond()
}
// underAnyRoot reports whether path is any of the roots or lies under
// one of them.
func underAnyRoot(path string, roots []string) bool {
@@ -966,7 +977,7 @@ func seedRoot(ctx context.Context, root string,
sendEvent(ctx, events, walkEvent{rec: fileRec{
path: root,
size: fi.Size(),
mtime: fi.ModTime().Unix(),
mtime: fi.ModTime(),
dev: dev,
ino: ino,
}})
@@ -1124,7 +1135,7 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
sendEvent(ctx, events, walkEvent{rec: fileRec{
path: p,
size: info.Size(),
mtime: info.ModTime().Unix(),
mtime: info.ModTime(),
dev: dev,
ino: ino,
}})