Merge remote-tracking branch 'origin/feat/332-image-categories-pr1' into feat/331-collections-pr1

Keep both features: a duplicate removal moves collection memberships and
copies the image category; both migrations and schema checks run; the
legacy route snapshot now records the six collection routes beside the
image category routes.

database/duplicate_copies.py

@@ -13,6 +13,8 @@ IMMEDIATE`` transaction, so no row ever names a deleted file:
   union under the same keys a favorite moves by;
 - its image tags (``media_image_tags`` of its byte record), joined onto the
   kept copy's byte record as their union, in order;
+- its own image category (#332), copied to the kept copy when that copy has
+  none; the removed copy's row is kept, so a give-back loses nothing;
 - its pending Needs review items, settled: only an item still ``pending`` at
   revision 0 with no decision row is removed (``review._SETTLE_ITEM``), so a
   decided item is never touched.
@@ -24,6 +26,8 @@ import os
 
 from .annotation_schema import BYTES_TABLE, FILES_TABLE
 from .annotations import _BUMP_INDEX
+from .image_categories import COPY_SQL as COPY_CATEGORY_SQL
+from .image_categories import copy_image_category
 from .models import normalize_image_path, utc_now_iso
 from .review import _BUMP_REVIEW_INDEX, _PENDING_OF_LOCATOR, _SETTLE_ITEM
 from .review_changes import notify_review_change
@@ -89,6 +93,7 @@ FILE_LINK_SQL = (
     COPY_BYTE_SQL,
     COPY_TAG_COUNT_SQL,
     PENDING_COUNT_SQL,
+    COPY_CATEGORY_SQL,
 )
 
 
@@ -150,9 +155,11 @@ class DuplicateCopyOperations:
         removed key, kept root key, kept key)`` per listed root holding the
         file; they move its favorite and its collection memberships),
         ``removed_locator``, ``kept_locator``, ``sha256`` and the kept copy's
-        ``kept_size`` and ``kept_mtime_ns``. Returns ``{moved, merged,
-        favorites, tags, review, collections}`` (``collections``: the
-        memberships inserted on the kept copy).
+        ``kept_size`` and ``kept_mtime_ns``; ``categories``: ``(removed file
+        key, kept file key)`` pairs of the image categories (#332). Returns
+        ``{moved, merged, favorites, tags, review, collections, categories}``
+        (``collections``: the memberships inserted on the kept copy;
+        ``categories``: the image categories copied to the kept copy).
         """
         counts = dict.fromkeys(
             ("moved", "merged", "favorites", "tags", "review", "collections"), 0
@@ -191,6 +198,10 @@ class DuplicateCopyOperations:
                 counts["favorites"] += _move_favorite(conn, *favorite)
                 counts["collections"] += _move_memberships(conn, *favorite)
             counts["tags"] = self._move_copy_tags(conn, move)
+            counts["categories"] = sum(
+                copy_image_category(conn, removed, kept)
+                for removed, kept in move.get("categories", ())
+            )
             for (item_id,) in conn.execute(
                 _PENDING_OF_LOCATOR, (move["removed_locator"],)
             ).fetchall():

database/image_categories.py

@@ -0,0 +1,249 @@
+"""Image categories (#332): an image file's own category.
+
+An image shows its own category when it has one, otherwise the category its
+link supplies (its recipe's, else its positive prompt's); this table holds
+only the own values. A row is keyed by the file key: the deepest configured
+output source that contains the file (its real, case-normalized path) and the
+path below it, case-folded where the OS folds case
+(``py/api/images.py`` ``image_category_key``). Without nested sources the key
+equals a favorite's key. Nothing follows a moved file: its row stays and is
+hidden until a file appears at the same path again.
+
+Writes validate strictly (the route strips the value and applies
+``validate_category``). Startup checks the structure only, so a value saved
+under older rules never stops the library opening; restore also checks the
+values. Optional in old backups, required once a database is current.
+"""
+
+import re
+import sqlite3
+from typing import Iterable
+
+TABLE = "image_categories"
+INDEX = "idx_image_categories_category"
+MAX_KEY_LENGTH = 4096
+MAX_CATEGORY_LENGTH = 100
+_DDL = (
+    f"CREATE TABLE {TABLE} (root_key TEXT NOT NULL, relative_path TEXT NOT NULL, "
+    "category TEXT NOT NULL, updated_at TEXT NOT NULL, "
+    "PRIMARY KEY (root_key, relative_path))"
+)
+_INDEX_DDL = f"CREATE INDEX {INDEX} ON {TABLE}(category)"
+_AUTOINDEX = f"sqlite_autoindex_{TABLE}_1"
+_COLUMNS = (
+    ("root_key", "TEXT", 1, 1),
+    ("relative_path", "TEXT", 1, 2),
+    ("category", "TEXT", 1, 0),
+    ("updated_at", "TEXT", 1, 0),
+)
+# A category may not hold a character below U+0020 (validate_category).
+_CONTROL_GLOB = "*[" + "".join(chr(code) for code in range(1, 32)) + "]*"
+
+CATEGORY_OF_SQL = (
+    f"SELECT category FROM {TABLE} WHERE root_key = ? AND relative_path = ?"
+)
+CATEGORIES_OF_ROOT_SQL = (
+    f"SELECT relative_path, category FROM {TABLE} WHERE root_key = ?"
+)
+UPSERT_SQL = (
+    f"INSERT INTO {TABLE} (root_key, relative_path, category, updated_at) "
+    "VALUES (?, ?, ?, ?) ON CONFLICT(root_key, relative_path) "
+    "DO UPDATE SET category = excluded.category, updated_at = excluded.updated_at"
+)
+DELETE_SQL = f"DELETE FROM {TABLE} WHERE root_key = ? AND relative_path = ?"
+# The duplicate cleanup's copy (#332 MC11): the removed copy's row is copied
+# to the kept copy only when the kept copy has none; it is never deleted.
+COPY_SQL = (
+    f"INSERT OR IGNORE INTO {TABLE} (root_key, relative_path, category, updated_at) "
+    f"SELECT ?, ?, category, updated_at FROM {TABLE} "
+    "WHERE root_key = ? AND relative_path = ?"
+)
+STATEMENTS = (CATEGORY_OF_SQL, CATEGORIES_OF_ROOT_SQL, UPSERT_SQL, DELETE_SQL, COPY_SQL)
+
+
+def _compact(sql: str) -> str:
+    return re.sub(r"\s+", "", sql or "").lower()
+
+
+def _structure_error(
+    conn: sqlite3.Connection, allow_missing: bool, allow_missing_index: bool = False
+) -> str | None:
+    objects = conn.execute(
+        "SELECT type,name,sql FROM sqlite_master WHERE name=? "
+        "OR (type IN ('index','trigger') AND tbl_name=?)",
+        (TABLE, TABLE),
+    ).fetchall()
+    if not objects:
+        return None if allow_missing else "Missing image categories schema"
+    tables = [sql for kind, _name, sql in objects if kind == "table"]
+    others = {(kind, name) for kind, name, _sql in objects if kind != "table"}
+    expected = {("index", _AUTOINDEX), ("index", INDEX)}
+    # Before its install, a table without the category index is repaired by
+    # CREATE INDEX IF NOT EXISTS rather than refused.
+    if allow_missing_index and others == {("index", _AUTOINDEX)}:
+        expected = others
+    if len(tables) != 1 or others != expected:
+        return "Image categories name is reserved by an unsupported schema object"
+    if _compact(tables[0]) != _compact(_DDL):
+        return "Image categories has an invalid table definition"
+    index_sql = next((sql for kind, name, sql in objects if name == INDEX), None)
+    if ("index", INDEX) in expected and _compact(index_sql) != _compact(_INDEX_DDL):
+        return "Image categories has an invalid index"
+    autoindex_sql = next(sql for kind, name, sql in objects if name == _AUTOINDEX)
+    if autoindex_sql is not None:
+        return "Image categories has an invalid index"
+    columns = tuple(
+        (row[1], row[2].upper(), row[3], row[5])
+        for row in conn.execute(f"PRAGMA table_info({TABLE})")
+    )
+    if columns != _COLUMNS:
+        return "Image categories has invalid columns"
+    return None
+
+
+def _values_error(conn: sqlite3.Connection) -> str | None:
+    # Bytes bound characters from above (UTF-8 is at most 4 bytes each).
+    limit = MAX_KEY_LENGTH * 4
+    if conn.execute(
+        f"SELECT 1 FROM {TABLE} WHERE typeof(root_key) != 'text' "  # nosec B608
+        "OR typeof(relative_path) != 'text' OR typeof(category) != 'text' "
+        "OR typeof(updated_at) != 'text' "
+        f"OR length(CAST(root_key AS BLOB)) > {limit} "
+        f"OR length(CAST(relative_path AS BLOB)) > {limit} "
+        "OR length(CAST(updated_at AS BLOB)) > 64 "
+        "OR instr(CAST(category AS BLOB), x'00') > 0 "
+        f"OR length(category) < 1 OR length(category) > {MAX_CATEGORY_LENGTH} "
+        "OR category != TRIM(category) OR category GLOB ? LIMIT 1",
+        (_CONTROL_GLOB,),
+    ).fetchone():
+        return "Image categories contains invalid values"
+    for root, path in conn.execute(
+        f"SELECT CAST(root_key AS BLOB), CAST(relative_path AS BLOB) "  # nosec B608
+        f"FROM {TABLE} WHERE length(CAST(root_key AS BLOB)) > {MAX_KEY_LENGTH} "
+        f"OR length(CAST(relative_path AS BLOB)) > {MAX_KEY_LENGTH}"
+    ):
+        for raw in (root, path):
+            if len(bytes(raw).decode("utf-8", "replace")) > MAX_KEY_LENGTH:
+                return "Image categories contains invalid values"
+    return None
+
+
+def image_categories_schema_error(
+    conn: sqlite3.Connection,
+    *,
+    allow_missing: bool = True,
+    check_values: bool = True,
+) -> str | None:
+    """Reject an unsupported image categories schema (and, optionally, values).
+
+    Reads only. A missing table is acceptable for backups that predate it
+    unless ``allow_missing`` is false. ``check_values`` also refuses a stored
+    value the write path could never have written.
+    """
+    error = _structure_error(conn, allow_missing)
+    if error is not None or not check_values:
+        return error
+    exists = conn.execute(
+        "SELECT 1 FROM sqlite_master WHERE type='table' AND name=?", (TABLE,)
+    ).fetchone()
+    return _values_error(conn) if exists else None
+
+
+def migrate_image_categories(conn: sqlite3.Connection) -> None:
+    """Install the table and its index atomically; structure is checked
+    before and after. Reads only ``sqlite_master`` and this table's PRAGMAs
+    and writes only its own two objects (no backfill)."""
+    conn.execute("SAVEPOINT image_categories_schema")
+    try:
+        error = _structure_error(conn, True, allow_missing_index=True)
+        if error:
+            raise sqlite3.DatabaseError(error)
+        conn.execute(_DDL.replace("CREATE TABLE", "CREATE TABLE IF NOT EXISTS", 1))
+        conn.execute(
+            _INDEX_DDL.replace("CREATE INDEX", "CREATE INDEX IF NOT EXISTS", 1)
+        )
+        error = image_categories_schema_error(
+            conn, allow_missing=False, check_values=False
+        )
+        if error:
+            raise sqlite3.DatabaseError(error)
+        conn.execute("RELEASE image_categories_schema")
+    except BaseException:
+        conn.execute("ROLLBACK TO image_categories_schema")
+        conn.execute("RELEASE image_categories_schema")
+        raise
+
+
+def copy_image_category(conn: sqlite3.Connection, removed_key, kept_key) -> int:
+    """Give the kept copy the removed copy's category when it has none.
+
+    Runs inside the caller's transaction; never deletes the removed copy's
+    row, so a give-back or a failed delete loses nothing. Returns 1 when a
+    row was inserted, else 0.
+    """
+    if tuple(removed_key) == tuple(kept_key):
+        return 0
+    return max(conn.execute(COPY_SQL, (*kept_key, *removed_key)).rowcount, 0)
+
+
+class ImageCategoryOperations:
+    """PromptDatabase mixin: set, clear and read images' own categories.
+
+    Never reads or writes ``prompts``, ``prompt_pairs`` or
+    ``generated_images``.
+    """
+
+    def image_category(self, root_key: str, relative_key: str) -> str | None:
+        """One file's own category, or None."""
+        row = (
+            self.model.get_connection()
+            .execute(CATEGORY_OF_SQL, (root_key, relative_key))
+            .fetchone()
+        )
+        return row[0] if row else None
+
+    def own_categories_of(self, root_keys: Iterable[str]) -> dict:
+        """``{(root key, relative key): category}`` under the given sources.
+
+        One primary-key range read per source.
+        """
+        found = {}
+        conn = self.model.get_connection()
+        for root_key in dict.fromkeys(root_keys):
+            for relative, category in conn.execute(CATEGORIES_OF_ROOT_SQL, (root_key,)):
+                found[(root_key, relative)] = category
+        return found
+
+    def set_image_categories(self, file_keys, category: str) -> dict:
+        """Set *category* on every file key, in one transaction.
+
+        ``file_keys``: ``(root key, relative key)`` pairs from any number of
+        sources. Returns ``{updated, unchanged}``; a file that already had
+        exactly this value is ``unchanged`` and keeps its ``updated_at``.
+        """
+        from .models import utc_now_iso  # models imports this module's schema
+
+        keys = list(dict.fromkeys(tuple(key) for key in file_keys))
+        counts = {"updated": 0, "unchanged": 0}
+        now = utc_now_iso()
+        with self._pair_transaction() as conn:
+            for key in keys:
+                row = conn.execute(CATEGORY_OF_SQL, key).fetchone()
+                if row is not None and row[0] == category:
+                    counts["unchanged"] += 1
+                    continue
+                conn.execute(UPSERT_SQL, (*key, category, now))
+                counts["updated"] += 1
+        return counts
+
+    def clear_image_categories(self, file_keys) -> int:
+        """Remove the own category of every file key (one transaction).
+
+        Returns the number of rows removed.
+        """
+        keys = list(dict.fromkeys(tuple(key) for key in file_keys))
+        removed = 0
+        with self._pair_transaction() as conn:
+            for key in keys:
+                removed += conn.execute(DELETE_SQL, key).rowcount
+        return removed

database/models.py

@@ -38,6 +38,7 @@ from .review_schema import (
     review_without_annotations_error,
 )
 from .saved_views import migrate_saved_views, saved_views_schema_error
+from .image_categories import image_categories_schema_error, migrate_image_categories
 from .workflow_documents import (
     DOCUMENT_ID_COLUMNS,
     migrate_workflow_documents,
@@ -355,6 +356,8 @@ class PromptModel:
         migrate_annotation_state(conn)
         migrate_review_state(conn)
         migrate_autotag_state(conn)
+        # Image categories (#332): independent of every table above.
+        migrate_image_categories(conn)
         # Last: the older generated_images rebuilds run only before file_path.
         migrate_workflow_documents(conn)
 
@@ -1160,8 +1163,9 @@ class PromptModel:
         Args:
             path: File to inspect
             require_library_state: Also require the tables every current
-                database has (Library state, image favorites, saved views,
-                collections, image annotations and the review queue), as a migrated
+                database has (Library state, image favorites, image
+                categories, saved views, collections, image annotations and
+                the review queue), as a migrated
                 restore stage must; old backups may lack them.
             documents: Read every workflow document and refuse a damaged
                 one. A restore checks its upload without it and repairs
@@ -1225,6 +1229,11 @@ class PromptModel:
             )
             if favorites_error:
                 return False, favorites_error
+            categories_error = image_categories_schema_error(
+                conn, allow_missing=not require_library_state
+            )
+            if categories_error:
+                return False, categories_error
             views_error = saved_views_schema_error(
                 conn, allow_missing=not require_library_state
             )

database/operations.py

@@ -28,6 +28,7 @@ from .health import HealthOperations, iter_consistency_issues
 from .duplicate_copies import DuplicateCopyOperations
 from .workflow_storage import WorkflowStorageOperations
 from .category_import import CategoryImportOperations, EmptyReplacement  # noqa: F401
+from .image_categories import ImageCategoryOperations
 from .workflow_documents import (
     DocumentReader,
     documents_of_rows,
@@ -370,6 +371,7 @@ class PromptDatabase(
     DuplicateCopyOperations,
     WorkflowStorageOperations,
     CategoryImportOperations,
+    ImageCategoryOperations,
 ):
     """Database operations class for managing prompts."""