Merge branch 'work/332-vocab' into feat/332-image-categories-pr2

This commit is contained in:
Vito Sansevero
2026-10-27 18:29:54 -07:00
4 changed files with 434 additions and 18 deletions
+55 -15
View File
@@ -13,7 +13,9 @@ same connection before commit. Owner rows and their timestamps never change.
Category consolidation is previewed in one ``library_snapshot`` and applied in
one ``_pair_transaction`` that recomputes the owner projection and requires the
preview's ``impact_token``; only rows carrying the exact source change.
preview's ``impact_token``; only rows carrying the exact source change. Image
rows holding the source (``image_categories``, #332) are owners too: they are
counted, hashed into the token and renamed with the prompts and pairs.
"""
import sqlite3
@@ -97,16 +99,30 @@ def _validate_tag_id(tag_id: object) -> None:
raise ValueError("Invalid tag ID")
# The /library/options universe: nonblank values on eligible parents or on
# active pairs, grouped exactly (whitespace and case variants stay distinct).
_CATEGORY_GROUPS = (
# Category values in Tags & categories (#332 §7): the prompt-backed values
# (nonblank values on eligible parents or on active pairs, grouped exactly, so
# whitespace and case variants stay distinct; /library/options lists the same
# prompt-backed set with its own query) plus the values only image rows hold.
# A prompt-backed value is ordered by its oldest owning positive; an image-only
# value sorts after all of them (first_pid is SQLite's INTEGER maximum, above
# any prompt id), then by value. ``image_count`` counts stored rows, including
# files missing on disk. No FULL OUTER JOIN, so it runs on SQLite 3.31+.
_IMAGE_ONLY_FIRST_PID = 2**63 - 1
_CATEGORY_ROWS = (
"WITH owners(value,pid) AS ("
"SELECT p.category,p.id FROM prompts p WHERE p.category IS NOT NULL "
"AND TRIM(p.category)!='' AND " + _ELIGIBLE + " "
"UNION SELECT pp.category,pp.positive_prompt_id FROM prompt_pairs pp "
"WHERE pp.archived=0 AND pp.category IS NOT NULL AND TRIM(pp.category)!=''),"
"grouped AS (SELECT value,MIN(pid) AS first_pid,"
"COUNT(DISTINCT pid) AS prompt_count FROM owners GROUP BY value) "
"image_values(value,image_count) AS ("
"SELECT category,COUNT(*) FROM image_categories GROUP BY category),"
"grouped(value,first_pid,prompt_count) AS ("
"SELECT value,MIN(pid),COUNT(DISTINCT pid) FROM owners GROUP BY value "
"UNION ALL SELECT value," + str(_IMAGE_ONLY_FIRST_PID) + ",0 FROM image_values "
"WHERE value NOT IN (SELECT value FROM owners)),"
"counted AS (SELECT g.value,g.first_pid,g.prompt_count,"
"COALESCE(i.image_count,0) AS image_count FROM grouped g "
"LEFT JOIN image_values i ON i.value=g.value) "
)
@@ -117,15 +133,23 @@ _CATEGORY_COMPONENTS = (
"WHERE p.category=? ORDER BY p.id"
)
_CATEGORY_PAIRS = "SELECT id,archived FROM prompt_pairs WHERE category=? ORDER BY id"
# Image rows holding one exact value (#332 DC7), an index search.
_IMAGE_CATEGORY_ROWIDS = (
"SELECT rowid FROM image_categories WHERE category=? ORDER BY rowid"
)
_CATEGORY_EXISTS = (
"SELECT EXISTS(SELECT 1 FROM prompts WHERE category=:v)"
" OR EXISTS(SELECT 1 FROM prompt_pairs WHERE category=:v)"
" OR EXISTS(SELECT 1 FROM image_categories WHERE category=:v)"
)
# Pairs after components, so a failing pair update rolls both back.
# Pairs after components and image rows last, so a failing update rolls every
# earlier one back. An image row is keyed by its file, never by its value, so
# merging into a value other files already hold cannot conflict.
_CATEGORY_UPDATES = (
"UPDATE prompts SET category=?,updated_at=? WHERE category=?",
"UPDATE prompt_pairs SET category=?,updated_at=? WHERE category=?",
"UPDATE image_categories SET category=?,updated_at=? WHERE category=?",
)
@@ -136,8 +160,15 @@ def category_impact_token(
target_exists: bool,
components: list,
pairs: list,
*,
images: list = (),
) -> str:
"""Hash a category projection like ``library_edit_token`` (no secret)."""
"""Hash a category projection like ``library_edit_token`` (no secret).
``images`` are the rowids of the image rows holding ``source`` (#332 DC7).
With none the preimage has no ``images`` key, so a prompt-only token keeps
the value it had before image categories existed.
"""
preimage = {
"epoch": epoch,
"source": source,
@@ -146,6 +177,8 @@ def category_impact_token(
"components": sorted([int(i), bool(flag)] for i, flag in components),
"pairs": sorted([int(i), bool(flag)] for i, flag in pairs),
}
if images:
preimage["images"] = sorted(int(i) for i in images)
return canonical_token(_CATEGORY_DOMAIN, preimage)
@@ -325,7 +358,8 @@ class VocabularyOperations:
pairs = [
[row[0], bool(row[1])] for row in conn.execute(_CATEGORY_PAIRS, (source,))
]
if not components and not pairs:
images = [row[0] for row in conn.execute(_IMAGE_CATEGORY_ROWIDS, (source,))]
if not components and not pairs and not images:
raise LibraryCommandError("vocabulary-conflict", epoch)
target_exists = bool(
conn.execute(_CATEGORY_EXISTS, {"v": target}).fetchone()[0]
@@ -339,9 +373,10 @@ class VocabularyOperations:
"other_prompts": len(components) - eligible,
"negative_variants": len(pairs) - archived,
"archived_negative_variants": archived,
"images": len(images),
},
"impact_token": category_impact_token(
epoch, source, target, target_exists, components, pairs
epoch, source, target, target_exists, components, pairs, images=images
),
}
@@ -365,7 +400,8 @@ class VocabularyOperations:
def apply_vocabulary_category(
self, *, expected_epoch: str, source: str, target: str, impact_token: str
) -> dict:
"""Set the exact ``source`` to ``target`` on every component and pair.
"""Set the exact ``source`` to ``target`` on every component, pair
and image row.
The recomputed projection must still match the preview's token; a
mismatch is ``vocabulary-conflict`` with nothing written.
@@ -422,15 +458,15 @@ class VocabularyOperations:
_limit(limit)
key = _category_after(after)
total = conn.execute(
_CATEGORY_GROUPS + "SELECT COUNT(*) FROM grouped"
_CATEGORY_ROWS + "SELECT COUNT(*) FROM counted"
).fetchone()[0]
where, params = "", []
if key is not None:
where = " WHERE first_pid>? OR (first_pid=? AND value>?)"
params = [key[0], key[0], key[1]]
rows = conn.execute(
_CATEGORY_GROUPS
+ "SELECT value,first_pid,prompt_count FROM grouped"
_CATEGORY_ROWS
+ "SELECT value,first_pid,prompt_count,image_count FROM counted"
+ where
+ " ORDER BY first_pid,value LIMIT ?",
[*params, limit + 1],
@@ -440,7 +476,11 @@ class VocabularyOperations:
return {
"library_epoch": epoch,
"categories": [
{"value": row["value"], "prompt_count": row["prompt_count"]}
{
"value": row["value"],
"prompt_count": row["prompt_count"],
"image_count": row["image_count"],
}
for row in rows
],
"total": total,