Hash every file's head, tail and content in the hash phase (closes #132)
check / check (push) Canceled after 0s

Every file the walk records now gets three hashes: head and tail, of
its first and last 64 KiB, and content. The content hash covers the
whole file under 100 MiB, and 1 MiB at each gigabyte from 100 MiB up,
so a large file is never read in full. One 100 MiB constant replaces
the 10 MiB and 50 MiB thresholds. The size census, the records stored
without hashes and the content phase are gone, so a rescan reads only
new and changed files. report and trees no longer special-case a
missing content hash. README "Duplicate detection" and "Rationale" are
rewritten.

Judgement call: info drops its two hash-count lines, which now always
equal the record count.

Model: opus-5-5
This commit is contained in:
2026-10-26 00:33:38 +00:00
committed by sneak
parent f4ddb58ae1
commit b2af329e3c
16 changed files with 537 additions and 1774 deletions
-59
View File
@@ -612,62 +612,3 @@ func TestApplyChangesBatching(t *testing.T) {
t.Fatalf("records = %d, want 0", len(got))
}
}
// TestCountContentCandidates checks that countContentCandidates counts
// the records the content phase's search returns: those of each group
// of two or more records of headTailMin or more with a head, where at
// least one has no content hash.
func TestCountContentCandidates(t *testing.T) {
t.Parallel()
db := openTestDB(t)
// Each group's records: size, head, and content, one per record.
groups := []struct {
size int64
head string
contents []string
}{
{headTailMin, "h", []string{"", "c", "c"}}, // returned
{headTailMin + 1, "h", []string{"", ""}}, // returned
{headTailMin + 2, "h", []string{"c", "c"}}, // all hashed
{headTailMin + 3, "h", []string{""}}, // one record
{headTailMin - 1, "h", []string{"", ""}}, // too small
{headTailMin + 4, "", []string{"", ""}}, // no head
}
var recs []scanRec
for _, g := range groups {
for _, content := range g.contents {
recs = append(recs, scanRec{
size: g.size, mtime: time.Unix(1, 0), head: g.head,
tail: "t", content: content,
path: fmt.Sprintf("/r/%d", len(recs)),
})
}
}
err := applyChanges(t.Context(), db, recs, nil, nil)
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
got, err := countContentCandidates(t.Context(), db)
if err != nil {
t.Fatalf("countContentCandidates: %v", err)
}
var returned int64
err = loadContentCandidates(t.Context(), db,
func(scanRec, bool) { returned++ })
if err != nil {
t.Fatalf("loadContentCandidates: %v", err)
}
if got != 5 || returned != 5 {
t.Errorf("count = %d, records returned = %d, want 5 and 5",
got, returned)
}
}