Vito Sansevero
8d61eda691
Re-review fixes R2, R3, R4, R5 and R6 (job side): - R3: Apply refuses a plan with nothing to rewrite (409 nothing-to-do, no job, no backup). Only the first apply keeps a pre-workflow-storage backup; later applies (after a Cancel, a rerun) take a pooled safety backup, forced on whatever the policy, so one copy is never pruned. - R4: a second-connection writer test runs against the live job loop; with its pause removed the writer hits "database is locked" (4 of 5 links). - R5: the digest tool loads only database/workflow_documents.py by path (no package start-up, no log handler) and opens a stopped database with immutable=1, so it leaves no -wal/-shm; a live one is read through its WAL. - R6: a backup that fails on a damaged document says which one in the job line. - R2: README's changelog says images recorded by this version use the new form from the first start, and the way back is the earliest pre-workflow-storage backup (or a pre-update backup if the job never ran).
95 lines
3.5 KiB
Python
95 lines
3.5 KiB
Python
"""Digests of every image record's stored workflow and prompt graph text.
|
|
|
|
Proves the workflow storage rewrite (#249 S6) kept every text byte for byte.
|
|
Run it from this repository on the database before the rewrite (or on its
|
|
``prompts.db.pre-workflow-storage_*`` backup) and again after, then compare::
|
|
|
|
python3 tools/workflow_text_digests.py prompts.db.pre-workflow-storage_<stamp> \\
|
|
before.sha
|
|
python3 tools/workflow_text_digests.py prompts.db after.sha
|
|
diff before.sha after.sha # prints nothing when every text is identical
|
|
|
|
Each line is ``<image id> <sha256 of workflow_data> <sha256 of prompt_metadata>``
|
|
(``-`` for none), hashing the exact stored bytes: the inline column before the
|
|
rewrite, the document read through the one accessor after it.
|
|
|
|
Read-only, with no side effects: the database is opened with ``mode=ro``,
|
|
and with ``immutable=1`` when no ``-wal``/``-shm`` file exists beside it (a
|
|
stopped database or a backup), so SQLite creates none. A live database
|
|
already has them and is read through its WAL. Only
|
|
``database/workflow_documents.py`` is loaded (by path; it needs only the
|
|
standard library), so no package start-up runs and no log file or handler is
|
|
added. Run it as the user that runs ComfyUI.
|
|
"""
|
|
|
|
import argparse
|
|
import hashlib
|
|
import importlib.util
|
|
import os
|
|
import sqlite3
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
_ROOT = Path(__file__).resolve().parents[1]
|
|
|
|
|
|
def _load_documents():
|
|
"""``database/workflow_documents.py`` alone, without the ``database`` package."""
|
|
path = _ROOT / "database" / "workflow_documents.py"
|
|
spec = importlib.util.spec_from_file_location("_pm_workflow_documents", path)
|
|
module = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(module)
|
|
return module
|
|
|
|
|
|
def database_uri(db_path):
|
|
"""``mode=ro``, plus ``immutable=1`` when nothing has the database open."""
|
|
path = os.path.abspath(db_path)
|
|
uri = Path(path).as_uri() + "?mode=ro"
|
|
if not any(os.path.exists(path + suffix) for suffix in ("-wal", "-shm")):
|
|
uri += "&immutable=1"
|
|
return uri
|
|
|
|
|
|
def _digest(value):
|
|
if value is None:
|
|
return "-"
|
|
raw = value if isinstance(value, bytes) else value.encode("utf-8")
|
|
return hashlib.sha256(raw).hexdigest()
|
|
|
|
|
|
def write_digests(db_path, out):
|
|
"""Write one digest line per image record of ``db_path`` to ``out``."""
|
|
documents = _load_documents()
|
|
conn = sqlite3.connect(database_uri(db_path), uri=True)
|
|
try:
|
|
conn.row_factory = sqlite3.Row
|
|
conn.text_factory = bytes # inline text exactly as stored, even undecodable
|
|
reader = documents.DocumentReader(conn)
|
|
count = 0
|
|
with open(out, "w", encoding="utf-8") as handle:
|
|
for row in conn.execute("SELECT * FROM generated_images ORDER BY id"):
|
|
texts = documents.resolve_image_row(reader, row)
|
|
handle.write(
|
|
f"{row['id']} {_digest(texts.get('workflow_data'))} "
|
|
f"{_digest(texts.get('prompt_metadata'))}\n"
|
|
)
|
|
count += 1
|
|
return count
|
|
finally:
|
|
conn.close()
|
|
|
|
|
|
def main(argv=None):
|
|
parser = argparse.ArgumentParser(description=__doc__.splitlines()[0])
|
|
parser.add_argument("database", help="prompts.db or one of its backups")
|
|
parser.add_argument("out", help="file to write the digests to")
|
|
args = parser.parse_args(argv)
|
|
count = write_digests(args.database, args.out)
|
|
print(f"{count} image records")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|