feat(dead-props): ensure replication on copy
This commit is contained in:
Edouard Vanbelle
@@ -0,0 +1,223 @@
|
||||
-- ════════════════════════════════════════════════════════════════════════════
|
||||
-- COPY: duplicate dead properties along with files and folders
|
||||
-- ════════════════════════════════════════════════════════════════════════════
|
||||
-- RFC 4918 §8.8 — "If a property cannot be copied live, then its value
|
||||
-- MUST be duplicated, exactly as it would be for a PROPPATCH SET
|
||||
-- operation, in the copy." Dead properties are by definition not live
|
||||
-- (the server stores them verbatim with no interpretation), so every
|
||||
-- COPY MUST duplicate the source's dead properties onto the new
|
||||
-- resource.
|
||||
--
|
||||
-- The pre-rekey path-based store handled this by accident in some
|
||||
-- cases and missed it in others; the id-keyed store (migration
|
||||
-- 20260830000001) makes the requirement explicit — dead properties
|
||||
-- key on `folder_id` / `file_id`, so a copy that doesn't insert new
|
||||
-- rows for the destination's ids loses the properties entirely.
|
||||
--
|
||||
-- This migration replaces `storage.copy_folder_tree` with a version
|
||||
-- that:
|
||||
--
|
||||
-- 1. Pre-allocates destination file ids in a new temp table
|
||||
-- `_copy_file_map(old_id, new_id)` — analogous to the
|
||||
-- pre-existing `_copy_map` that already does this for folders.
|
||||
-- Previously, file ids were generated by the `gen_random_uuid()`
|
||||
-- DEFAULT during the batch INSERT, leaving no way to relate src
|
||||
-- and dst files afterward.
|
||||
-- 2. Switches the batch file INSERT to use the explicit
|
||||
-- pre-allocated id, so src→dst is bidirectionally known by
|
||||
-- `_copy_file_map`.
|
||||
-- 3. Adds two `INSERT INTO storage.webdav_dead_properties` SELECTs
|
||||
-- at the end that duplicate dead-property rows for every copied
|
||||
-- folder (via `_copy_map`) and every copied file (via
|
||||
-- `_copy_file_map`). Each duplicated row carries the same
|
||||
-- `(namespace, local_name, value)` triple as the source — the
|
||||
-- definition of "duplicate" in RFC 4918 §8.8.
|
||||
--
|
||||
-- Idempotent via CREATE OR REPLACE FUNCTION. No callers change (the
|
||||
-- function signature and return shape are unchanged).
|
||||
--
|
||||
-- COPY semantics out of scope for this migration:
|
||||
-- * Cross-user permission handling on the copied resources is the
|
||||
-- caller's responsibility (the `_with_perms` service variant
|
||||
-- already enforces this on the source side). Dead properties
|
||||
-- hitch a ride on the resource's ACL; nothing additional needed.
|
||||
-- * Trash: trashed source rows are excluded by the existing
|
||||
-- `NOT is_trashed` filter; dead-props on trashed rows live on
|
||||
-- until the resource itself is hard-deleted, at which point
|
||||
-- CASCADE handles them. Same model holds in the new COPY path.
|
||||
|
||||
CREATE OR REPLACE FUNCTION storage.copy_folder_tree(
|
||||
p_source_id UUID,
|
||||
p_target_parent_id UUID, -- NULL = copy to root (keeps source drive)
|
||||
p_dest_name TEXT DEFAULT NULL -- NULL = keep source folder name
|
||||
) RETURNS TABLE(new_root_id TEXT, folders_copied BIGINT, files_copied BIGINT) AS $$
|
||||
DECLARE
|
||||
v_root_lpath ltree;
|
||||
v_root_depth INT;
|
||||
v_max_depth INT;
|
||||
v_level INT;
|
||||
v_folders BIGINT := 0;
|
||||
v_files BIGINT := 0;
|
||||
v_inserted BIGINT;
|
||||
v_new_root UUID;
|
||||
v_dest_drive_id UUID;
|
||||
BEGIN
|
||||
-- Validate source exists
|
||||
SELECT fo.lpath, nlevel(fo.lpath)
|
||||
INTO v_root_lpath, v_root_depth
|
||||
FROM storage.folders fo
|
||||
WHERE fo.id = p_source_id AND NOT fo.is_trashed;
|
||||
|
||||
IF v_root_lpath IS NULL THEN
|
||||
RAISE EXCEPTION 'Source folder not found: %', p_source_id
|
||||
USING ERRCODE = 'P0002'; -- no_data_found
|
||||
END IF;
|
||||
|
||||
-- Resolve the destination drive_id ONCE up front. The whole copied
|
||||
-- subtree lands in this drive; pulling it per-row from `fo.drive_id`
|
||||
-- (the previous body) was the cross-drive bug.
|
||||
--
|
||||
-- When p_target_parent_id is NULL the caller asked for "copy to
|
||||
-- root" — there is no global root in the multi-drive world, so we
|
||||
-- preserve the source's drive_id (legacy behaviour, defensive).
|
||||
-- Real API call sites always pass a concrete target folder.
|
||||
IF p_target_parent_id IS NULL THEN
|
||||
SELECT fo.drive_id INTO v_dest_drive_id
|
||||
FROM storage.folders fo
|
||||
WHERE fo.id = p_source_id;
|
||||
ELSE
|
||||
SELECT fo.drive_id INTO v_dest_drive_id
|
||||
FROM storage.folders fo
|
||||
WHERE fo.id = p_target_parent_id AND NOT fo.is_trashed;
|
||||
IF v_dest_drive_id IS NULL THEN
|
||||
RAISE EXCEPTION 'Target parent folder not found: %', p_target_parent_id
|
||||
USING ERRCODE = 'P0002'; -- no_data_found
|
||||
END IF;
|
||||
END IF;
|
||||
|
||||
-- Temp mapping: every folder in the subtree → new UUID
|
||||
CREATE TEMP TABLE IF NOT EXISTS _copy_map(
|
||||
old_id UUID PRIMARY KEY,
|
||||
new_id UUID NOT NULL DEFAULT gen_random_uuid()
|
||||
) ON COMMIT DROP;
|
||||
TRUNCATE _copy_map;
|
||||
|
||||
INSERT INTO _copy_map(old_id)
|
||||
SELECT fo.id
|
||||
FROM storage.folders fo
|
||||
WHERE NOT fo.is_trashed
|
||||
AND fo.lpath <@ v_root_lpath;
|
||||
|
||||
-- Remember new root ID
|
||||
SELECT cm.new_id INTO v_new_root
|
||||
FROM _copy_map cm WHERE cm.old_id = p_source_id;
|
||||
|
||||
-- Max depth for level iteration
|
||||
SELECT MAX(nlevel(fo.lpath))
|
||||
INTO v_max_depth
|
||||
FROM storage.folders fo
|
||||
JOIN _copy_map cm ON fo.id = cm.old_id;
|
||||
|
||||
-- ── Insert folders level by level ──
|
||||
-- Each level is a separate INSERT so the BEFORE INSERT trigger
|
||||
-- (trg_folders_path) can resolve the parent's path/lpath from rows
|
||||
-- inserted in the previous level. drive_id is the destination's
|
||||
-- (resolved once above); user_id + provenance preserved from source.
|
||||
FOR v_level IN v_root_depth .. v_max_depth LOOP
|
||||
INSERT INTO storage.folders(
|
||||
id, name, parent_id, user_id,
|
||||
drive_id, created_by, updated_by
|
||||
)
|
||||
SELECT cm.new_id,
|
||||
CASE WHEN fo.id = p_source_id AND p_dest_name IS NOT NULL
|
||||
THEN p_dest_name ELSE fo.name END,
|
||||
CASE WHEN fo.id = p_source_id THEN p_target_parent_id
|
||||
ELSE pm.new_id END,
|
||||
fo.user_id,
|
||||
v_dest_drive_id,
|
||||
fo.created_by,
|
||||
fo.updated_by
|
||||
FROM storage.folders fo
|
||||
JOIN _copy_map cm ON fo.id = cm.old_id
|
||||
LEFT JOIN _copy_map pm ON fo.parent_id = pm.old_id
|
||||
WHERE NOT fo.is_trashed
|
||||
AND nlevel(fo.lpath) = v_level;
|
||||
|
||||
GET DIAGNOSTICS v_inserted = ROW_COUNT;
|
||||
v_folders := v_folders + v_inserted;
|
||||
END LOOP;
|
||||
|
||||
-- ── NEW: temp mapping for files src→dst ───────────────────────────
|
||||
-- Pre-allocate destination ids so we can:
|
||||
-- (a) reference each dst file by id in the dead-property INSERT
|
||||
-- below — a batched INSERT...RETURNING couldn't tell us which
|
||||
-- new id corresponded to which source id, so the mapping
|
||||
-- has to be stamped at planning time, not after the fact;
|
||||
-- (b) batch the file INSERT with explicit ids exactly the same
|
||||
-- way folders are batched.
|
||||
CREATE TEMP TABLE IF NOT EXISTS _copy_file_map(
|
||||
old_id UUID PRIMARY KEY,
|
||||
new_id UUID NOT NULL DEFAULT gen_random_uuid()
|
||||
) ON COMMIT DROP;
|
||||
TRUNCATE _copy_file_map;
|
||||
|
||||
INSERT INTO _copy_file_map(old_id)
|
||||
SELECT f.id
|
||||
FROM storage.files f
|
||||
JOIN _copy_map cm ON f.folder_id = cm.old_id
|
||||
WHERE NOT f.is_trashed;
|
||||
|
||||
-- ── Batch copy all files (zero-copy: same blob_hash) ──
|
||||
-- drive_id from destination; everything else (user_id, created_by,
|
||||
-- updated_by) preserved from source so authorship survives the copy.
|
||||
-- `id` is the pre-allocated dst id from _copy_file_map.
|
||||
INSERT INTO storage.files(
|
||||
id, name, folder_id, user_id, blob_hash, size, mime_type,
|
||||
media_sort_date, drive_id, created_by, updated_by
|
||||
)
|
||||
SELECT fm.new_id, f.name, cm.new_id, f.user_id, f.blob_hash, f.size,
|
||||
f.mime_type, f.media_sort_date, v_dest_drive_id, f.created_by,
|
||||
f.updated_by
|
||||
FROM storage.files f
|
||||
JOIN _copy_map cm ON f.folder_id = cm.old_id
|
||||
JOIN _copy_file_map fm ON fm.old_id = f.id
|
||||
WHERE NOT f.is_trashed;
|
||||
|
||||
GET DIAGNOSTICS v_files = ROW_COUNT;
|
||||
|
||||
-- ── Batch increment blob ref_counts ──
|
||||
IF v_files > 0 THEN
|
||||
UPDATE storage.blobs b
|
||||
SET ref_count = ref_count + hc.cnt
|
||||
FROM (
|
||||
SELECT f.blob_hash, COUNT(*)::int AS cnt
|
||||
FROM storage.files f
|
||||
JOIN _copy_map cm ON f.folder_id = cm.new_id
|
||||
WHERE NOT f.is_trashed
|
||||
GROUP BY f.blob_hash
|
||||
) hc
|
||||
WHERE b.hash = hc.blob_hash;
|
||||
END IF;
|
||||
|
||||
-- ── NEW: duplicate dead properties for every copied folder ────────
|
||||
-- RFC 4918 §8.8 — dead properties MUST be duplicated. The id-keyed
|
||||
-- store (migration 20260830000001) keys on `folder_id`, so we
|
||||
-- emit a new row per source dead-property pointing at the
|
||||
-- destination folder id. `(namespace, local_name, value)` is
|
||||
-- preserved verbatim — that's the "duplicate" definition.
|
||||
INSERT INTO storage.webdav_dead_properties
|
||||
(folder_id, namespace, local_name, value)
|
||||
SELECT cm.new_id, dp.namespace, dp.local_name, dp.value
|
||||
FROM storage.webdav_dead_properties dp
|
||||
JOIN _copy_map cm ON dp.folder_id = cm.old_id;
|
||||
|
||||
-- ── NEW: duplicate dead properties for every copied file ──────────
|
||||
INSERT INTO storage.webdav_dead_properties
|
||||
(file_id, namespace, local_name, value)
|
||||
SELECT fm.new_id, dp.namespace, dp.local_name, dp.value
|
||||
FROM storage.webdav_dead_properties dp
|
||||
JOIN _copy_file_map fm ON dp.file_id = fm.old_id;
|
||||
|
||||
RETURN QUERY SELECT v_new_root::text, v_folders, v_files;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
Reference in New Issue
Block a user