Vito Sansevero
b107de70f8
The recorded run's stored prompt now links in one transaction with the file's link rows, so a file linked to another prompt is a conflict instead of a second link. The scan's stores run through survive_library_switch. A single file asks history once (a one-file _BatchHistory), the scan passes in_output=False and reads the file size only for files with prompt metadata. A conflict row reads "Kept: already linked to a different prompt". TESTING.md records the rules.
88 lines
3.4 KiB
Python
88 lines
3.4 KiB
Python
"""Link an output file to the prompt of one text, creating it when new (#247).
|
|
|
|
The store step of ingestion from file metadata when the decision is a
|
|
positive text (``utils.file_prompt``). The prompt insert and the link run in
|
|
one ``BEGIN IMMEDIATE`` transaction: two writers never store one text twice,
|
|
a failed link leaves no new prompt behind, and a file stays linked to one
|
|
prompt (a file already linked to another prompt is a ``conflict``).
|
|
"""
|
|
|
|
import logging
|
|
import os
|
|
from typing import Any, Dict, Optional, Tuple
|
|
|
|
from .pair_ingestion import Marks, file_link_rows, link_conflict, mark_created
|
|
|
|
try:
|
|
from ..utils.hashing import generate_prompt_hash
|
|
except ImportError:
|
|
from utils.hashing import generate_prompt_hash
|
|
|
|
_LOGGER = logging.getLogger("prompt_manager.database.scanned_prompts")
|
|
|
|
|
|
def store_scanned_prompt_or_raise(
|
|
db: Any, path: str, canonical: Dict[str, Any], text: str, marks: Marks
|
|
) -> Tuple[str, Optional[int]]:
|
|
"""``(status, prompt id)`` after linking ``path`` to ``text``'s prompt.
|
|
|
|
``added`` (prompt created, carrying ``marks``), ``linked`` (stored text
|
|
reused), ``unchanged`` (already linked to it) or ``conflict`` (linked to
|
|
another prompt; nothing written, id None). Database errors are raised
|
|
and roll the whole store back, so a caller can run it again.
|
|
"""
|
|
with db._pair_transaction() as conn:
|
|
rows = file_link_rows(conn, path)
|
|
if link_conflict(rows, generate_prompt_hash(text)):
|
|
return "conflict", None
|
|
if rows:
|
|
return "unchanged", rows[0]["prompt_id"]
|
|
prompt_id, created = db._pair_component_outcome(conn, text)
|
|
if created:
|
|
mark_created(conn, db, prompt_id, marks, os.path.basename(path))
|
|
db._insert_image_link(conn, prompt_id, path, canonical)
|
|
return ("added" if created else "linked"), prompt_id
|
|
|
|
|
|
def store_scanned_prompt(
|
|
db: Any, path: str, canonical: Dict[str, Any], text: str, marks: Marks
|
|
) -> Tuple[str, Optional[int]]:
|
|
"""The scan's form: an error is logged and reported as ``("found", None)``.
|
|
|
|
A write that failed because Move library switched runs again on the new
|
|
library (``survive_library_switch``); the rerun re-checks the link rows.
|
|
"""
|
|
try:
|
|
return db.survive_library_switch(
|
|
lambda: store_scanned_prompt_or_raise(db, path, canonical, text, marks)
|
|
)
|
|
except Exception as error:
|
|
_LOGGER.error(
|
|
f"Failed to store the prompt of {os.path.basename(path)}: {error}"
|
|
)
|
|
return "found", None
|
|
|
|
|
|
def link_stored_prompt_or_raise(
|
|
db: Any, path: str, canonical: Dict[str, Any], prompt_id: int
|
|
) -> Optional[str]:
|
|
"""Link ``path`` to the stored prompt ``prompt_id`` (recorded history, #342).
|
|
|
|
``linked``, ``unchanged`` (already linked to it), ``conflict`` (linked to
|
|
another prompt; nothing written) or None when the prompt is gone. One
|
|
``BEGIN IMMEDIATE`` transaction; database errors are raised.
|
|
"""
|
|
with db._pair_transaction() as conn:
|
|
rows = file_link_rows(conn, path)
|
|
if len(rows) > 1 or (rows and rows[0]["prompt_id"] != prompt_id):
|
|
return "conflict"
|
|
if rows:
|
|
return "unchanged"
|
|
exists = conn.execute(
|
|
"SELECT 1 FROM prompts WHERE id = ?", (prompt_id,)
|
|
).fetchone()
|
|
if exists is None:
|
|
return None
|
|
db._insert_image_link(conn, prompt_id, path, canonical)
|
|
return "linked"
|