arborist/tests/test_snapshot.py
russell@unturf.com 1f5bf7318d
add corpus-level snapshots: single-hash identity for the forest
A snapshot_root is MerkleTree.build([sorted DISTINCT document_roots]).root
— one 32-byte hash naming the entire content-addressed forest at a
point in time. Two peers that ingested the same dump compute bit-
identical snapshot_roots, so cross-machine "are we synced?" becomes
an O(1) hash comparison; the same root doubles as the TF-IDF
scope_root we sketched in the mesh design (snapshot_root *is* a
scope), and pins Q&A answers to a verifiable corpus state.

Schema: one new table, additive over existing data.
  snapshots(snapshot_root PK, taken_at, audit_event_hash, doc_count,
            parent_snapshot, reason)
  + idx_snapshots_taken_at

API:
  compute_snapshot_root(conn, *, document_roots=None) -> (root, count)
  create_snapshot(conn, *, reason, parent_snapshot=None) -> dict
  verify_snapshot(conn, snapshot_root) -> dict (matches: bool)
  diff_against_current(conn, snapshot_root) -> dict (added/removed/unchanged)
  list_snapshots(conn, *, limit) -> list[dict]

CLI:
  aborist snapshot create [--reason "..."] [--parent <hex>]
  aborist snapshot list   [--limit N]
  aborist snapshot verify <snapshot_root>
  aborist snapshot diff   <snapshot_root>

Cross-shard: with --shards-dir + --db, the snapshot is computed over
the cluster-wide UNION view but persisted into args.db (a dedicated
snapshots store, conventionally ~/.aborist/shards/snapshots.db).
parent_snapshot auto-links to the latest prior snapshot in the
writer DB, giving a chain for free.

Each snapshot creation writes an audit_event of type 'snapshot_create'
with subject_root=snapshot_root, so the corpus's pinned states are
themselves tamper-evidently logged.

Defect caught + fixed during live test on the 2010 enwiki ingest:
verify and diff disagreed on the same connection because compute used
a list (with cross-shard duplicate document_roots) while diff used a
set. Two shards can land identical document_roots when canonicalize()
maps two structurally-similar pages to the same byte stream — rare
but real. Switched the underlying SQL to SELECT DISTINCT so a
membership snapshot is always order- AND multiplicity-independent.

Live test: 2010-11 enwiki corpus snapshotted at
  43797e46605de08dbab06cdcaf5be7ad78243b193c56f8580200dee6bcc7e1b9
  doc_count: 3,468,134 (after dedup)
verify + diff round-trip both report identical against current state.

11 new tests covering empty corpus, single-doc degenerate, order
independence, drift detection, audit-chain pinning, parent auto-link,
and idempotent creation on unchanged corpus. 136 tests + 1 skipped.
2026-04-27 21:29:10 -04:00

217 lines
7.2 KiB
Python

"""Tests for corpus-level snapshots.
Snapshots pin a forest of document_roots into a single Merkle root
that's bit-identical across machines that ingested the same dump.
"""
from __future__ import annotations
import time
import pytest
from aborist.document import Document
from aborist.ingest import ingest_source
from aborist.snapshot import (
EMPTY_SNAPSHOT_ROOT,
compute_snapshot_root,
create_snapshot,
diff_against_current,
list_snapshots,
verify_snapshot,
)
from aborist.source import Source
from aborist.store import connect
class _FakeSource(Source):
source_type = "test"
def __init__(self, docs):
self._docs = docs
def iter_documents(self):
for d in self._docs:
yield d
def _doc(uri: str, content: str) -> Document:
return Document(uri=uri, content=content, source_type="test", title=uri)
# ---------------------------------------------------------------------------
# Pure compute
# ---------------------------------------------------------------------------
def test_compute_snapshot_root_empty_corpus(tmp_path):
conn = connect(tmp_path / "a.db")
try:
root, count = compute_snapshot_root(conn)
assert root == EMPTY_SNAPSHOT_ROOT
assert count == 0
finally:
conn.close()
def test_compute_snapshot_root_single_doc_uses_doc_root(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
root, count = compute_snapshot_root(conn)
# Degenerate single-leaf: snapshot_root == document_root.
doc_row = conn.execute(
"SELECT document_root FROM documents"
).fetchone()
assert root == doc_row["document_root"]
assert count == 1
finally:
conn.close()
def test_compute_snapshot_root_is_order_independent(tmp_path):
"""Two corpora with the same documents in different ingest order
must produce the same snapshot_root. That's the cross-machine
convergence property."""
a = tmp_path / "a.db"
b = tmp_path / "b.db"
docs1 = [_doc("test://x", "x" * 100), _doc("test://y", "y" * 100)]
docs2 = list(reversed(docs1))
conn_a = connect(a)
conn_b = connect(b)
try:
ingest_source(conn_a, _FakeSource(docs1))
ingest_source(conn_b, _FakeSource(docs2))
root_a, _ = compute_snapshot_root(conn_a)
root_b, _ = compute_snapshot_root(conn_b)
assert root_a == root_b
finally:
conn_a.close()
conn_b.close()
def test_compute_snapshot_root_changes_when_doc_added(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "alpha alpha alpha alpha")]))
root1, _ = compute_snapshot_root(conn)
ingest_source(conn, _FakeSource([_doc("test://b", "beta beta beta beta")]))
root2, _ = compute_snapshot_root(conn)
assert root1 != root2
finally:
conn.close()
# ---------------------------------------------------------------------------
# Persistence + audit chain
# ---------------------------------------------------------------------------
def test_create_snapshot_persists_and_audits(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
result = create_snapshot(conn, reason="post-ingest")
assert result["doc_count"] == 1
assert len(result["snapshot_root"]) == 64
assert len(result["audit_event_hash"]) == 64
rows = list_snapshots(conn)
assert len(rows) == 1
assert rows[0]["snapshot_root"] == result["snapshot_root"]
assert rows[0]["reason"] == "post-ingest"
# Audit chain has a snapshot_create event linked to the snapshot_root.
audit = conn.execute(
"SELECT event_type, subject_root FROM audit_events "
"WHERE event_type = 'snapshot_create' ORDER BY seq DESC LIMIT 1"
).fetchone()
assert audit["event_type"] == "snapshot_create"
assert audit["subject_root"] == result["snapshot_root"]
finally:
conn.close()
def test_create_snapshot_auto_links_to_prior(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
first = create_snapshot(conn, reason="first")
# Add a doc; second snapshot's parent should auto-link to first.
ingest_source(conn, _FakeSource([_doc("test://b", "beta beta beta beta")]))
# Sleep briefly so taken_at differs even on fast machines.
time.sleep(1.1)
second = create_snapshot(conn, reason="second")
assert second["snapshot_root"] != first["snapshot_root"]
assert second["parent_snapshot"] == first["snapshot_root"]
finally:
conn.close()
def test_create_snapshot_idempotent_on_unchanged_corpus(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
a = create_snapshot(conn, reason="first")
b = create_snapshot(conn, reason="second-no-change")
# Same corpus -> same snapshot_root. Second insert is a no-op
# against the PK; we don't get a duplicate row.
assert a["snapshot_root"] == b["snapshot_root"]
assert len(list_snapshots(conn)) == 1
finally:
conn.close()
# ---------------------------------------------------------------------------
# Verify + diff
# ---------------------------------------------------------------------------
def test_verify_snapshot_matches_when_corpus_unchanged(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
s = create_snapshot(conn)
result = verify_snapshot(conn, s["snapshot_root"])
assert result["matches"]
finally:
conn.close()
def test_verify_snapshot_rejects_after_drift(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
s = create_snapshot(conn)
ingest_source(conn, _FakeSource([_doc("test://b", "beta beta beta beta")]))
result = verify_snapshot(conn, s["snapshot_root"])
assert not result["matches"]
assert result["current_doc_count"] == 2
finally:
conn.close()
def test_diff_returns_identical_for_matching_root(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
s = create_snapshot(conn)
result = diff_against_current(conn, s["snapshot_root"])
assert result["diff"] == "identical"
finally:
conn.close()
def test_diff_reports_drift_after_adds(tmp_path):
conn = connect(tmp_path / "a.db")
try:
ingest_source(conn, _FakeSource([_doc("test://a", "hello world a")]))
s = create_snapshot(conn)
ingest_source(conn, _FakeSource([_doc("test://b", "beta beta beta beta")]))
result = diff_against_current(conn, s["snapshot_root"])
assert result["diff"] == "drifted"
assert result["snapshot_root"] != result["current_root"]
finally:
conn.close()