pf_app/setup_sql/01_schema.sql
Paul Trowbridge 07d92ccd74 Keep master data for a dim_group instead of re-deriving it from the source
Every question about a part -- what values exist, what attributes go with
one -- was answered by querying the source, and the source is the wrong
place to ask. It is a view over a transaction table, so the query is slow
(76s for one ILIKE against 6.9M rows), it describes only what was
transacted, and it cannot express intent: there is no way to say a part is
discontinued, or to name one that has not sold yet.

pf.dim_member holds the app's own list: one row per key value per group,
siblings in jsonb, keyed on (source_id, dim_group, key_value). Refresh is a
merge rather than a replace, so curation survives it -- members absent from
the source are marked source_seen = false, not deleted. Triggered from
Setup, next to Generate SQL, because it reads the whole source and the
answer only changes when the catalogue does.

A key can carry several attribute sets across history -- 11,290 parts
against 13,662 combinations on osm_skinny -- so the refresh takes the most
recent by the source's date column. That also fixes the sibling autofill,
which used to run a DISTINCT ... LIMIT 2 against the source and silently
fill nothing whenever a part came back ambiguous. A member row is one
definition by construction.

The client fetches each group's list once per source and does both
completion and autofill against it in memory, so neither costs a request.
Columns outside a group, or a group never refreshed, still fall back to the
version's values endpoint.

Run 01_schema.sql to create the table.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 00:19:39 -04:00

117 lines
5.1 KiB
SQL

-- Pivot Forecast schema install
-- Run once against target database: psql -d <db> -f setup_sql/01_schema.sql
CREATE SCHEMA IF NOT EXISTS pf;
CREATE TABLE IF NOT EXISTS pf.source (
id serial PRIMARY KEY,
schema text NOT NULL,
tname text NOT NULL,
label text,
status text NOT NULL DEFAULT 'active', -- active | archived
default_layout jsonb, -- Perspective view config used as the per-source default
created_at timestamptz NOT NULL DEFAULT now(),
created_by text,
UNIQUE (schema, tname)
);
-- backfill columns for existing installs
ALTER TABLE pf.source ADD COLUMN IF NOT EXISTS default_layout jsonb;
-- pf.dim_period: run setup_sql/gen_dim_period.sql to create and populate
CREATE TABLE IF NOT EXISTS pf.col_meta (
id serial PRIMARY KEY,
source_id integer NOT NULL REFERENCES pf.source(id) ON DELETE CASCADE,
cname text NOT NULL,
label text,
role text NOT NULL DEFAULT 'ignore', -- dimension | value | units | date | ignore
is_key boolean NOT NULL DEFAULT false, -- true = usable in WHERE slice
dim_group text, -- groups functionally dependent columns
dim_period_col text, -- pf.dim_period column this dimension derives from
in_grain boolean NOT NULL DEFAULT false, -- true = column defines the display grain
opos integer,
UNIQUE (source_id, cname)
);
-- backfill columns for existing installs (must follow the CREATE above)
ALTER TABLE pf.col_meta ADD COLUMN IF NOT EXISTS dim_group text;
ALTER TABLE pf.col_meta ADD COLUMN IF NOT EXISTS dim_period_col text;
ALTER TABLE pf.col_meta ADD COLUMN IF NOT EXISTS in_grain boolean NOT NULL DEFAULT false;
CREATE TABLE IF NOT EXISTS pf.version (
id serial PRIMARY KEY,
source_id integer NOT NULL REFERENCES pf.source(id) ON DELETE RESTRICT,
name text NOT NULL,
description text,
status text NOT NULL DEFAULT 'open', -- open | closed
exclude_iters jsonb NOT NULL DEFAULT '["reference"]'::jsonb,
created_at timestamptz NOT NULL DEFAULT now(),
created_by text,
closed_at timestamptz,
closed_by text,
UNIQUE (source_id, name)
);
CREATE TABLE IF NOT EXISTS pf.log (
id bigserial PRIMARY KEY,
version_id integer NOT NULL REFERENCES pf.version(id) ON DELETE CASCADE,
pf_user text NOT NULL,
stamp timestamptz NOT NULL DEFAULT now(),
operation text NOT NULL, -- baseline | reference | scale | recode | clone
slice jsonb,
params jsonb,
note text,
tag text -- initiative label, e.g. 'reduce_spend'; groups
-- adjustments into a bridge from baseline to current
);
-- adding tags to an install that predates them
ALTER TABLE pf.log ADD COLUMN IF NOT EXISTS tag text;
CREATE INDEX IF NOT EXISTS log_tag_idx ON pf.log (tag) WHERE tag IS NOT NULL;
-- seed tags for loads that predate the column: a baseline/reference note is the
-- segment's name ('Open Orders', 'Prior Year'), which is exactly what tag holds.
-- Adjustment notes are free text, not labels, so they are left alone.
UPDATE pf.log
SET tag = note
WHERE TRUE
AND tag IS NULL
AND note IS NOT NULL
AND note <> ''
AND operation IN ('baseline', 'reference');
-- Master data for a dim_group: one row per key value, with its sibling columns.
--
-- The source is transactional and often a view over all history, so deriving a
-- member list from it is both slow and wrong -- slow because it means scanning
-- millions of rows, wrong because it can only describe what was transacted and
-- has no way to say a part is discontinued or that a new one exists before it
-- has sold. This table is the app's own list, refreshed from the source but
-- curatable independently of it.
CREATE TABLE IF NOT EXISTS pf.dim_member (
source_id integer NOT NULL REFERENCES pf.source(id) ON DELETE CASCADE,
dim_group text NOT NULL, -- matches pf.col_meta.dim_group
key_value text NOT NULL, -- the is_key column's value
attrs jsonb NOT NULL DEFAULT '{}'::jsonb, -- the sibling columns
is_active boolean NOT NULL DEFAULT true,
source_seen boolean NOT NULL DEFAULT true, -- present in the source at last refresh
added_at timestamptz NOT NULL DEFAULT now(),
updated_at timestamptz NOT NULL DEFAULT now(),
refreshed_at timestamptz,
PRIMARY KEY (source_id, dim_group, key_value)
);
CREATE INDEX IF NOT EXISTS dim_member_active_idx
ON pf.dim_member (source_id, dim_group) WHERE is_active;
-- generated operation SQL per source, stored after col_meta is configured
CREATE TABLE IF NOT EXISTS pf.sql (
id serial PRIMARY KEY,
source_id integer NOT NULL REFERENCES pf.source(id) ON DELETE CASCADE,
operation text NOT NULL, -- get_data | baseline | reference | scale | recode | clone | undo
sql text NOT NULL,
generated_at timestamptz NOT NULL DEFAULT now(),
UNIQUE (source_id, operation)
);