Merge #456 (feat/444-library-folder-or) into feat/443-bulk-prompt-delete

Keeps both features: #444's folder filter, tag match (all/any/untagged),
tag search and sort with #443's archive/delete and Show archived shelf.
The ranked tag sort and the Untagged prompts count now hide archived
parents, as the other tag counts and the shelf already do.
This commit is contained in:
Vito Sansevero
2026-10-29 00:43:07 -07:00
43 changed files with 2048 additions and 178 deletions
+84 -16
View File
@@ -5,6 +5,7 @@ import sqlite3
from collections.abc import Iterator
from contextlib import contextmanager
from .library_folders import folder_condition, list_library_folders
from .library_tokens import library_edit_token
from .prompt_archive import ARCHIVED, SHELVED
@@ -128,7 +129,54 @@ def _archive(value: str) -> str:
return ARCHIVE_SCOPES[value]
def _filter(text: str, category: str | None, tags: list[str]) -> tuple[str, list]:
# How the Tags filter matches (#444): every tag (AND), any of them (OR), or
# parents without any tag.
TAG_MODES = ("all", "any", "untagged")
# A parent that no tag's Browse returns (#444 "Untagged prompts"): no tag of its
# own and no active pair carrying one. The vocabulary's untagged count uses it too.
UNTAGGED = (
"NOT EXISTS(SELECT 1 FROM prompt_tags ut WHERE ut.prompt_id=p.id) "
"AND NOT EXISTS(SELECT 1 FROM prompt_pairs up JOIN prompt_pair_tags upt "
"ON upt.pair_id=up.id WHERE up.positive_prompt_id=p.id AND up.archived=0)"
)
def _tag_mode(tag_mode: object, tags: list[str]) -> str:
if not isinstance(tag_mode, str) or tag_mode not in TAG_MODES:
raise ValueError("tag_mode must be one of " + ", ".join(TAG_MODES))
if tag_mode == "untagged" and tags:
raise ValueError("Untagged prompts cannot also filter by tags")
return tag_mode
def _tag_conditions(tags: list[str], any_tag: bool) -> tuple[list, list, list]:
"""Parent-arm and pair-arm tag conditions and the tags' parameters."""
parent_exists = (
"EXISTS(SELECT 1 FROM prompt_tags pt JOIN tags t ON t.id=pt.tag_id "
"WHERE pt.prompt_id=p.id AND t.name{test})"
)
pair_exists = (
"EXISTS(SELECT 1 FROM prompt_pair_tags pt JOIN tags t ON t.id=pt.tag_id "
"WHERE pt.pair_id=pp.id AND t.name{test})"
)
if any_tag and tags:
# One condition per arm: the card, or one active pair, carries any tag.
test = " IN (" + ",".join("?" for _ in tags) + ")"
return [parent_exists.format(test=test)], [pair_exists.format(test=test)], tags
return (
[parent_exists.format(test="=?") for _ in tags],
[pair_exists.format(test="=?") for _ in tags],
tags,
)
def _filter(
text: str,
category: str | None,
tags: list[str],
tag_mode: str = "all",
folder_prefixes: list[str] | None = None,
) -> tuple[str, list]:
if not isinstance(text, str) or len(text) > 500:
raise ValueError("Search text must be a string of at most 500 characters")
if category is not None and (not isinstance(category, str) or len(category) > 200):
@@ -139,6 +187,8 @@ def _filter(text: str, category: str | None, tags: list[str]) -> tuple[str, list
or any(not isinstance(tag, str) or not tag or len(tag) > 200 for tag in tags)
):
raise ValueError("Invalid library tags")
mode = _tag_mode(tag_mode, tags)
untagged = mode == "untagged"
parent, pair, parent_params, pair_params = [], ["pp.archived=0"], [], []
if text:
parent.append("(p.text LIKE ? ESCAPE '\\' OR ls.title LIKE ? ESCAPE '\\')")
@@ -153,17 +203,11 @@ def _filter(text: str, category: str | None, tags: list[str]) -> tuple[str, list
pair.append("pp.category=?")
parent_params.append(category)
pair_params.append(category)
for tag in tags:
parent.append(
"EXISTS(SELECT 1 FROM prompt_tags pt JOIN tags t ON t.id=pt.tag_id "
"WHERE pt.prompt_id=p.id AND t.name=?)"
)
pair.append(
"EXISTS(SELECT 1 FROM prompt_pair_tags pt JOIN tags t ON t.id=pt.tag_id "
"WHERE pt.pair_id=pp.id AND t.name=?)"
)
parent_params.append(tag)
pair_params.append(tag)
parent_tags, pair_tags, tag_params = _tag_conditions(tags, mode == "any")
parent.extend(parent_tags)
pair.extend(pair_tags)
parent_params.extend(tag_params)
pair_params.extend(tag_params)
condition = (
"("
+ (" AND ".join(parent) or "1=1")
@@ -175,7 +219,17 @@ def _filter(text: str, category: str | None, tags: list[str]) -> tuple[str, list
+ " AND ".join(pair)
+ ")"
)
return f"({_ELIGIBLE}) AND ({condition})", [*parent_params, *pair_params]
if untagged:
# A whole-card condition: inside the parent-or-pair OR an untagged pair
# would let a tagged parent through.
condition = f"({condition}) AND {UNTAGGED}"
params = [*parent_params, *pair_params]
if folder_prefixes:
# A whole-card condition around both arms: images link to the parent.
folder, folder_params = folder_condition(folder_prefixes)
condition = f"({condition}) AND {folder}"
params.extend(folder_params)
return f"({_ELIGIBLE}) AND ({condition})", params
class LibraryOperations:
@@ -261,6 +315,8 @@ class LibraryOperations:
text: str = "",
category: str | None = None,
tags: list[str] | None = None,
tag_mode: str = "all",
folder_prefixes: list[str] | None = None,
sort: str = "newest",
limit: int = 40,
after: dict | None = None,
@@ -271,7 +327,9 @@ class LibraryOperations:
raise ValueError("Unknown library sort order")
if not isinstance(shelf, str) or shelf not in PARENT_SCOPES:
raise ValueError("shelf must be active or archived")
where, params = _filter(text, category, [] if tags is None else tags)
where, params = _filter(
text, category, [] if tags is None else tags, tag_mode, folder_prefixes
)
if after is not None:
if (
not isinstance(after, dict)
@@ -328,6 +386,8 @@ class LibraryOperations:
"total": total,
"variant_total": variant_total,
"archived_total": archived_total,
# Echoed so a client can tell this read applied its tag match.
"tag_mode": tag_mode,
"has_more": has_more,
"next_key": next_key,
}
@@ -338,6 +398,8 @@ class LibraryOperations:
text: str = "",
category: str | None = None,
tags: list[str] | None = None,
tag_mode: str = "all",
folder_prefixes: list[str] | None = None,
sort: str = "newest",
limit: int = 40,
after: dict | None = None,
@@ -351,6 +413,8 @@ class LibraryOperations:
text=text,
category=category,
tags=tags,
tag_mode=tag_mode,
folder_prefixes=folder_prefixes,
sort=sort,
limit=limit,
after=after,
@@ -482,9 +546,13 @@ class LibraryOperations:
"categories": [row["category"] for row in rows],
}
def get_library_options(self) -> dict:
def get_library_options(self, folder_roots=None) -> dict:
"""Categories; with *folder_roots* (root spellings) also ``folders``."""
with self.library_snapshot() as (conn, epoch, _ceiling):
return self._get_library_options(conn, epoch)
result = self._get_library_options(conn, epoch)
if folder_roots is not None:
result["folders"] = list_library_folders(conn, folder_roots, _ELIGIBLE)
return result
def get_library_previews(self, positive_ids: list[int]) -> dict[int, list[dict]]:
"""Read at most two links per parent in one bounded page query."""
+111
View File
@@ -0,0 +1,111 @@
"""Library output-folder filter (#444): folder names, root prefixes and listing.
A folder is a ``/``-joined path relative to an output root, as Images' folder
filter and the legacy ``/prompt_manager/subfolders`` name them. A parent
matches a folder when one of its linked images (``generated_images.prompt_id``,
the link its previews and image count read) lies in that folder or below it,
under any spelling of any output root.
Matching compares ``generated_images.file_path``, which is always
``normcase(normpath(abspath(path)))`` (``models.normalize_image_path``), with
prefixes built by the same normalization here, so case folding is the
platform's own on both sides (Windows folds non-ASCII too, unlike SQLite's
``lower()``) and the comparison is an exact ``substr`` with no wildcards.
"""
import os
import sqlite3
_MAX_FOLDER = 1024
_MAX_PREFIXES = 64
def normalize_folder(value: object) -> str:
"""The folder as ``a/b``: ``\\`` read as ``/``, outer slashes dropped.
Empty means no folder filter. ``.``/``..``/empty segments, a drive or
control characters are refused: the value only ever names a folder below a
root, never a path of its own.
"""
if not isinstance(value, str) or len(value) > _MAX_FOLDER:
raise ValueError(f"folder must be text of at most {_MAX_FOLDER} characters")
folder = value.replace("\\", "/").strip("/")
if not folder:
return ""
parts = folder.split("/")
if (
any(part in ("", ".", "..") for part in parts)
or ":" in parts[0]
or any(ord(char) < 32 or ord(char) == 127 for char in folder)
):
raise ValueError("folder must be a folder below an output root")
return folder
def _base(root: object, pathmod) -> str:
return pathmod.normcase(pathmod.normpath(str(root)))
def folder_prefixes(roots, folder: str, pathmod=os.path) -> list[str]:
"""One ``file_path`` prefix per root spelling for a normalized folder."""
prefixes = []
for root in roots:
joined = pathmod.join(_base(root, pathmod), *folder.split("/"))
prefix = pathmod.normcase(pathmod.normpath(joined)) + pathmod.sep
if prefix not in prefixes:
prefixes.append(prefix)
if not prefixes or len(prefixes) > _MAX_PREFIXES:
raise ValueError("No output folder to filter by")
return prefixes
def folder_condition(prefixes: list[str]) -> tuple[str, list]:
"""A condition on alias ``p``: one linked image under any prefix."""
tests = " OR ".join("substr(fg.file_path,1,?)=?" for _ in prefixes)
params = [value for prefix in prefixes for value in (len(prefix), prefix)]
return (
"EXISTS(SELECT 1 FROM generated_images fg WHERE fg.prompt_id=p.id "
f"AND ({tests}))",
params,
)
def relative_folder(image_path: str, roots, pathmod=os.path) -> str | None:
"""The folder of *image_path* below the first root spelling holding it.
The spelling of the stored path is kept (its case on Windows); ``None``
for an image directly in a root or outside every root.
"""
directory = pathmod.normpath(pathmod.dirname(image_path))
folded = pathmod.normcase(directory)
for root in roots:
base = _base(root, pathmod)
start = base if base.endswith(pathmod.sep) else base + pathmod.sep
if not folded.startswith(start):
continue
# normcase keeps the length for ordinary names; else show the folded form.
rest = (directory if len(directory) == len(folded) else folded)[len(start) :]
parts = rest.split(pathmod.sep)
if any(part in ("", ".", "..") for part in parts):
return None
return "/".join(parts)
return None
def list_library_folders(
conn: sqlite3.Connection, roots, eligible: str, pathmod=os.path
) -> list[str]:
"""Every folder (and ancestor) holding an image of an eligible parent."""
folders = set()
for (image_path,) in conn.execute(
"SELECT DISTINCT g.image_path FROM generated_images g "
"JOIN prompts p ON p.id=g.prompt_id WHERE " + eligible
):
if not isinstance(image_path, str) or not image_path:
continue
folder = relative_folder(image_path, roots, pathmod)
if folder is None:
continue
parts = folder.split("/")
folders.update("/".join(parts[:index]) for index in range(1, len(parts) + 1))
return sorted(folders, key=lambda value: (value.casefold(), value))
+11
View File
@@ -33,6 +33,9 @@ MAX_TAG_LENGTH = 50
_IMAGE_SORTS = ("newest", "oldest", "name", "name-desc", "rating")
_LIBRARY_SORTS = ("newest", "oldest", "name", "rating")
_MEDIA = ("all", "image", "video")
# How a Library view's Tags match (#444): every tag, any of them, or parents
# without tags ("untagged" never goes with tags; the listing refuses both).
_TAG_MODES = ("all", "any", "untagged")
_CONTROL = re.compile(r"[\x00-\x1f\x7f]")
_SOURCE = re.compile(r"all|0|[1-9][0-9]{0,8}")
# A collection id as the listing's ``collection`` query takes it (#331): none
@@ -67,6 +70,9 @@ _STATE_FIELDS = {
"category": ("text", 100, ""),
"sort": ("choice", _LIBRARY_SORTS, "newest"),
"tags": ("tags", None, ()),
# #444: the Tags match and the output folder (relative, "/"-joined).
"tag_mode": ("choice", _TAG_MODES, "all"),
"folder": ("text", 1024, ""),
},
}
@@ -152,6 +158,8 @@ def encode_state(page: object, state: object) -> str:
_validate_value(key, kind, limit, state[key])
if state.get("favorites") is True and state.get("collection"):
raise SavedViewInvalid("A view cannot filter by favorites and a collection")
if state.get("tag_mode") == "untagged" and state.get("tags"):
raise SavedViewInvalid("A view cannot list untagged prompts and filter tags")
encoded = json.dumps(
{key: state[key] for key in fields}, ensure_ascii=False, separators=(",", ":")
)
@@ -195,6 +203,9 @@ def normalize_state(page: str, raw: object) -> dict:
# as the listing does for a URL with both (#331 D140).
if state.get("favorites") is True and state.get("collection"):
state["favorites"] = False
# Never written by this build either: the tags win.
if state.get("tag_mode") == "untagged" and state.get("tags"):
state["tag_mode"] = "all"
return state
+141 -10
View File
@@ -20,7 +20,7 @@ counted, hashed into the token and renamed with the prompts and pairs.
import sqlite3
from .library import _ELIGIBLE, SHELVED_PAIR, _limit
from .library import _ELIGIBLE, SHELVED_PAIR, UNTAGGED, _escape, _limit
from .prompt_archive import SHELVED
from .library_commands import _TOKEN, LibraryCommandError, _validate_epoch
from .library_tokens import canonical_token
@@ -39,7 +39,7 @@ _IMAGE_FILES = (
)
def _tag_rows(page: str) -> str:
def _tag_rows(page: str, order: str = "page.id") -> str:
"""Count rows for the registry rows selected by ``page`` (id, name)."""
# Eligible parent components on the shelf carrying a tag in the page,
# plus the positive parent of every active pair carrying it (always
@@ -62,11 +62,53 @@ def _tag_rows(page: str) -> str:
"COALESCE(MAX(images.n),0) AS image_count "
"FROM page LEFT JOIN owners ON owners.tag_id=page.id "
"LEFT JOIN images ON images.tag_id=page.id "
"GROUP BY page.id ORDER BY page.id"
"GROUP BY page.id ORDER BY " + order
)
_TAG_PAGE = _tag_rows("SELECT id,name FROM tags WHERE id>? ORDER BY id LIMIT ?")
# #444 tag sorts: sort -> (key expression on tags/counted, direction). Ties and
# "created" follow the id, so every order is total and keyset pages are exact.
TAG_SORTS = {
"created": (None, "ASC"),
"name": ("name COLLATE NOCASE", "ASC"),
"name-desc": ("name COLLATE NOCASE", "DESC"),
"prompts": ("prompt_count", "DESC"),
"prompts-asc": ("prompt_count", "ASC"),
}
_MAX_SEARCH = 200
_TAG_SEARCH = "name LIKE ? ESCAPE '\\'"
# Every matching tag ranked by the prompt count its row shows (the owners rule
# of ``_tag_rows``), then one keyset page of it with its image counts.
_RANKED_TAG_PAGE = (
"WITH owners(tag_id,pid) AS ("
"SELECT pt.tag_id,p.id FROM prompts p "
"JOIN prompt_tags pt ON pt.prompt_id=p.id WHERE " + _ELIGIBLE + " "
"AND " + SHELVED + " "
"UNION SELECT ppt.tag_id,pp.positive_prompt_id FROM prompt_pairs pp "
"JOIN prompt_pair_tags ppt ON ppt.pair_id=pp.id WHERE pp.archived=0 "
"AND " + SHELVED_PAIR + "),"
"counted AS (SELECT t.id,t.name,COUNT(DISTINCT o.pid) AS prompt_count "
"FROM tags t LEFT JOIN owners o ON o.tag_id=t.id WHERE {search} "
"GROUP BY t.id),"
"page AS (SELECT id,name,prompt_count FROM counted WHERE {after} "
"ORDER BY prompt_count {direction},id LIMIT ?),"
"images(tag_id,n) AS (" + _IMAGE_FILES + " "
"WHERE mit.tag_id IN (SELECT id FROM page) GROUP BY mit.tag_id) "
"SELECT page.id,page.name,page.prompt_count,"
"COALESCE(images.n,0) AS image_count FROM page "
"LEFT JOIN images ON images.tag_id=page.id "
"ORDER BY page.prompt_count {direction},page.id"
)
_UNTAGGED_COUNT = (
"SELECT COUNT(*) FROM prompts p WHERE ("
+ _ELIGIBLE
+ ") AND "
+ UNTAGGED
# Untagged prompts opens the shelf, which hides archived parents (#443).
+ " AND "
+ SHELVED
)
_TAG_ONE = _tag_rows("SELECT id,name FROM tags WHERE id=?")
# Every owner kind a tag can sit on, for the delete confirmation.
_TAG_IMPACT = (
@@ -219,6 +261,28 @@ def _tag_after(after: object) -> int:
return after
def _tag_search(search: object) -> str:
if not isinstance(search, str) or len(search) > _MAX_SEARCH:
raise ValueError(f"Tag search must be text of at most {_MAX_SEARCH} characters")
return search.strip()
def _sorted_tag_after(after: object, sort: str) -> tuple | None:
"""The ``[key, id]`` cursor of a name or prompt-count sort."""
if after is None:
return None
key_type = str if sort.startswith("name") else int
if (
not isinstance(after, list)
or len(after) != 2
or type(after[0]) is not key_type
or type(after[1]) is not int
or after[1] <= 0
):
raise ValueError("Invalid vocabulary cursor")
return after[0], after[1]
def _category_after(after: object) -> tuple[int, str] | None:
if after is None:
return None
@@ -440,22 +504,80 @@ class VocabularyOperations:
epoch: str,
*,
limit: int = 100,
after: int | None = None,
after: object = None,
search: str = "",
sort: str = "created",
) -> dict:
"""One page of tags matching ``search`` (a literal, case-insensitive
substring) in ``sort`` order, with the untagged parents' count."""
_limit(limit)
start = _tag_after(after)
total = conn.execute("SELECT COUNT(*) FROM tags").fetchone()[0]
rows = [dict(row) for row in conn.execute(_TAG_PAGE, (start, limit + 1))]
search = _tag_search(search)
if not isinstance(sort, str) or sort not in TAG_SORTS:
raise ValueError("sort must be one of " + ", ".join(TAG_SORTS))
where, params = "1=1", []
if search:
where, params = _TAG_SEARCH, [f"%{_escape(search)}%"]
total, untagged = conn.execute(
f"SELECT (SELECT COUNT(*) FROM tags WHERE {where}),({_UNTAGGED_COUNT})",
params,
).fetchone()
rows = [
dict(row) for row in self._tag_page(conn, where, params, sort, after, limit)
]
has_more = len(rows) > limit
rows = rows[:limit]
key, _direction = TAG_SORTS[sort]
next_key = None
if has_more:
last = rows[-1]
next_key = (
last["id"]
if key is None
else [
last["prompt_count" if key == "prompt_count" else "name"],
last["id"],
]
)
return {
"library_epoch": epoch,
"tags": rows,
"total": total,
"untagged_count": untagged,
# Echoed so a client can tell this read applied its search and sort.
"search": search,
"sort": sort,
"has_more": has_more,
"next_key": rows[-1]["id"] if has_more else None,
"next_key": next_key,
}
@staticmethod
def _tag_page(conn, where, params, sort, after, limit):
key, direction = TAG_SORTS[sort]
if key is None:
page = (
f"SELECT id,name FROM tags WHERE {where} AND id>? ORDER BY id LIMIT ?"
)
return conn.execute(
_tag_rows(page), [*params, _tag_after(after), limit + 1]
)
cursor = _sorted_tag_after(after, sort)
operator = ">" if direction == "ASC" else "<"
keyset, keys = "1=1", []
if cursor is not None:
keyset = f"({key}{operator}? OR ({key}=? AND id>?))"
keys = [cursor[0], cursor[0], cursor[1]]
if key == "prompt_count":
sql = _RANKED_TAG_PAGE.format(
search=where, after=keyset, direction=direction
)
return conn.execute(sql, [*params, *keys, limit + 1])
page = (
f"SELECT id,name FROM tags WHERE {where} AND {keyset} "
f"ORDER BY {key} {direction},id LIMIT ?"
)
order = f"page.{key} {direction},page.id"
return conn.execute(_tag_rows(page, order), [*params, *keys, limit + 1])
def _vocabulary_categories(
self,
conn: sqlite3.Connection,
@@ -499,9 +621,18 @@ class VocabularyOperations:
),
}
def list_vocabulary_tags(self, *, limit: int = 100, after: int | None = None):
def list_vocabulary_tags(
self,
*,
limit: int = 100,
after: object = None,
search: str = "",
sort: str = "created",
):
with self.library_snapshot() as (conn, epoch, _ceiling):
return self._vocabulary_tags(conn, epoch, limit=limit, after=after)
return self._vocabulary_tags(
conn, epoch, limit=limit, after=after, search=search, sort=sort
)
def list_vocabulary_categories(
self, *, limit: int = 100, after: list | None = None