Add archer import and allow date-mode bulk delete

archer import replays a sealed archive into an existing table: shard
selection (`--select`), SHA-256 pre-verification, idempotent modes
(`ignore`/`insert`/`replace`), and both LOAD DATA and batched-INSERT
engines. It reads manifest.jsonl strictly so corruption is reported
instead of skipped, and supports --dry-run, --allow-partial, and
per-shard workers.

--bulk-delete no longer rejects --shard-by date. Range deletion now
derives its bounds from the chunk's actual keys (date scanners rewrite
LastKey into a resumption cursor) and keeps safe-auto-increment
semantics by excluding the current max key. A startup warning documents
the monotonic-shard-column assumption.

Also splits CLI/format/sharding/progress/safety reference docs out of
the README, and adds the corresponding OpenSpec change artifacts.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
voidandClaude Sonnet 4.6 committed 2026-11-08 21:14:23 +08:00
1 parent bc4a6b504f
commit 366d61ca25
49 files changed
+5099 -342

No files matched your search

+21 -7
View File
@@ -63,8 +63,8 @@ func (p *Purger) DeleteChunk(ctx context.Context, exec Execer, c *row.Chunk) (in
maxKey = v
}
if p.Bulk && maxKey == nil {
return p.deleteRange(ctx, exec, c)
if p.Bulk {
return p.deleteRange(ctx, exec, c, maxKey)
}
return p.deleteInList(ctx, exec, keys, maxKey)
}
@@ -85,8 +85,13 @@ func (p *Purger) currentMax(ctx context.Context) (*row.KeyPart, error) {
return &row.KeyPart{Val: v.String}, nil
}
func (p *Purger) deleteRange(ctx context.Context, exec Execer, c *row.Chunk) (int64, error) {
lo, hi := c.FirstKey, c.LastKey
func (p *Purger) deleteRange(ctx context.Context, exec Execer, c *row.Chunk, maxKey *row.KeyPart) (int64, error) {
// Date scanners rewrite LastKey into a (shard column, key...) cursor for
// resumption, so the bare key range must come from Keys.
if len(c.Keys) == 0 {
return 0, nil
}
lo, hi := c.Keys[0], c.Keys[len(c.Keys)-1]
if lo.IsZero() || hi.IsZero() {
return 0, nil
}
@@ -95,9 +100,18 @@ func (p *Purger) deleteRange(ctx context.Context, exec Execer, c *row.Chunk) (in
args []any
)
if len(p.KeyCols) == 1 {
q = fmt.Sprintf("DELETE FROM %s WHERE %s BETWEEN ? AND ? AND (%s)",
p.table(), sqlutil.Ident(p.KeyCols[0]), p.Where)
args = []any{lo[0].DriverValue(), hi[0].DriverValue()}
col := sqlutil.Ident(p.KeyCols[0])
if maxKey != nil {
// Keep safe-auto-increment semantics: the current max row is
// excluded even when it falls inside the range.
q = fmt.Sprintf("DELETE FROM %s WHERE %s BETWEEN ? AND ? AND %s <> ? AND (%s)",
p.table(), col, col, p.Where)
args = []any{lo[0].DriverValue(), hi[0].DriverValue(), maxKey.DriverValue()}
} else {
q = fmt.Sprintf("DELETE FROM %s WHERE %s BETWEEN ? AND ? AND (%s)",
p.table(), col, p.Where)
args = []any{lo[0].DriverValue(), hi[0].DriverValue()}
}
} else {
q = fmt.Sprintf("DELETE FROM %s WHERE %s >= %s AND %s <= %s AND (%s)",
p.table(), sqlutil.RowTuple(p.KeyCols), sqlutil.ParamTuple(len(p.KeyCols)),