-- =============================================================================
-- 001_schema.sql — pg-ai reference data and document store.
--
--   psql -h pg-ai -U postgres -d plant -f 001_schema.sql
--
-- What pg-ai is FOR: pgvector document chunks, Cube pre-aggregations, and the
-- equipment/tag reference data including the alias lists.
--
-- What pg-ai is NOT for: historian data. There is no replication job and no
-- mirror table. imh is already an isolated copy of the raw SCADA historian, so
-- Cube queries imh directly over TDS/1433 with a read-only login. The only
-- exception is 002_fixtures.sql, which stands in for imh until it exists.
--
-- Storage is UTC everywhere. Conversion to SITE_TIMEZONE happens exactly once,
-- in Cube. Never in SQL here and never in a prompt.
-- =============================================================================

CREATE EXTENSION IF NOT EXISTS vector;

-- -----------------------------------------------------------------------------
-- equipment — what the operator says.
--
-- "Pump 02" is equipment; its data lives on tags. Without this table every
-- equipment-level question fails, because no historian point is called
-- "Pump 02". Aliases are the whole point: operators do not type tag numbers.
-- -----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS equipment (
    equipment_id   TEXT PRIMARY KEY,   -- PU-302
    display_name   TEXT,               -- Pump 02
    aliases        TEXT[],             -- {'Pump 02','pump2','P2','PU-302'}
    equipment_type TEXT,               -- pump | vessel | station | piping | ...
    unit_name      TEXT,               -- WRPS
    description    TEXT
);

CREATE INDEX IF NOT EXISTS equipment_aliases_gin ON equipment USING gin (aliases);

-- -----------------------------------------------------------------------------
-- tags — the historian points and field instruments, and how to read them.
--
-- engineering_unit, range and setpoints are recorded in the units the HISTORIAN
-- stores, which are not always the units the PLC works in. Wet well level is
-- the trap: the PLC works in mm, CI Server historises percent of the spill weir
-- crest (mm / 60). The description field carries the conversion for every tag
-- where the two differ. Read it before interpreting a number.
--
-- The description also records whether a tag IS HISTORISED. Field inputs to the
-- PLC (%IW / %IX) are not published to SCADA and have no history at all. An
-- answer that trends PU-301 vibration is fabricating data.
-- -----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS tags (
    tag_id            TEXT PRIMARY KEY,   -- PS_STN_WET_WELL_LEVEL, LIT-101
    equipment_id      TEXT REFERENCES equipment(equipment_id),
    display_name      TEXT,
    aliases           TEXT[],
    signal_type       TEXT,               -- level|flow|pressure|status|state|...
    engineering_unit  TEXT,
    range_low         DOUBLE PRECISION,
    range_high        DOUBLE PRECISION,
    alarm_setpoint_hi DOUBLE PRECISION,
    alarm_setpoint_lo DOUBLE PRECISION,
    trip_setpoint     DOUBLE PRECISION,
    description       TEXT
);

CREATE INDEX IF NOT EXISTS tags_aliases_gin  ON tags USING gin (aliases);
CREATE INDEX IF NOT EXISTS tags_equipment_ix ON tags (equipment_id);

-- -----------------------------------------------------------------------------
-- doc_chunks — controlled documents, chunked and embedded.
--
-- superseded and effective_date matter more than they look. Citing a withdrawn
-- revision of a procedure is worse than finding nothing at all, so retrieval
-- filters superseded = FALSE by default and the citation always carries the
-- revision and effective date.
-- -----------------------------------------------------------------------------
CREATE TABLE IF NOT EXISTS doc_chunks (
    id             BIGSERIAL PRIMARY KEY,
    source_file    TEXT NOT NULL,
    doc_type       TEXT NOT NULL,      -- procedure|manual|rationalisation|design
    doc_number     TEXT,               -- WRPS-CTL-002
    revision       TEXT,
    effective_date DATE,
    superseded     BOOLEAN DEFAULT FALSE,
    equipment_id   TEXT,
    page           INT,
    section_title  TEXT,
    chunk_text     TEXT NOT NULL,
    embedding      VECTOR(1536),       -- text-embedding-3-small
    created_at     TIMESTAMPTZ DEFAULT now(),
    CONSTRAINT doc_chunks_type_ck
        CHECK (doc_type IN ('procedure','manual','rationalisation','design'))
);

CREATE INDEX IF NOT EXISTS doc_chunks_embedding_hnsw
    ON doc_chunks USING hnsw (embedding vector_cosine_ops);
CREATE INDEX IF NOT EXISTS doc_chunks_live_type
    ON doc_chunks (doc_type) WHERE superseded = FALSE;
CREATE INDEX IF NOT EXISTS doc_chunks_source
    ON doc_chunks (source_file);
CREATE INDEX IF NOT EXISTS doc_chunks_equipment
    ON doc_chunks (equipment_id);

-- Re-ingesting a file replaces its chunks; it must never duplicate them.
-- ingest.py deletes by source_file inside the same transaction as the insert.

-- -----------------------------------------------------------------------------
-- Cube writes its pre-aggregations into their own schema, with its own role.
-- -----------------------------------------------------------------------------
CREATE SCHEMA IF NOT EXISTS cube_preagg;

-- =============================================================================
-- Seed load. Aliases are pipe-separated in the CSVs because a Postgres array
-- literal inside CSV is unreadable and unmergeable in review. Load via a
-- staging table and split on load.
--
--   psql -h pg-ai -U postgres -d plant -v ON_ERROR_STOP=1 <<'PSQL'
--   \i 001_schema.sql
--   CREATE TEMP TABLE eq_stage (LIKE equipment INCLUDING ALL);
--   ALTER TABLE eq_stage ALTER COLUMN aliases TYPE TEXT;
--   \copy eq_stage FROM 'seed/equipment.csv' WITH (FORMAT csv, HEADER true)
--   INSERT INTO equipment
--   SELECT equipment_id, display_name, string_to_array(aliases, '|'),
--          equipment_type, unit_name, description
--   FROM eq_stage
--   ON CONFLICT (equipment_id) DO UPDATE SET
--     display_name = EXCLUDED.display_name, aliases = EXCLUDED.aliases,
--     equipment_type = EXCLUDED.equipment_type, unit_name = EXCLUDED.unit_name,
--     description = EXCLUDED.description;
--   PSQL
--
-- Same shape for tags. scripts/deploy.sh does this for you.
--
-- Phase 1 gate: every equipment item and every tag has at least one
-- human-friendly alias. Check it, do not assume it:
--
--   SELECT equipment_id FROM equipment WHERE coalesce(array_length(aliases,1),0) = 0;
--   SELECT tag_id       FROM tags      WHERE coalesce(array_length(aliases,1),0) = 0;
-- =============================================================================