transceiver-db/sql/120-form-factor-recovery.sql
root dd2c917f05 feat(data-quality): product_type classification + form_factor recovery + lead_time docs
sql/119: product_type enum (module|dac|aoc|aec|switch|nic|accessory) computed by
trigger trg_transceivers_biu from part_number/category/reach on every insert/update.
Backfilled 41008 rows (36284 module, 2791 dac, 1835 aoc, 29 aec, 27 accessory,
26 switch, 16 nic). Cables and switches/NICs no longer counted as modules;
BASE-T/RJ45 copper modules protected from cable demotion; AOC/DAC keyword beats
the optical-token guard. Consumers filter product_type=module.

sql/120: conservative form_factor recovery. Corrects only provably-wrong rows
(form_factors.max_speed < speed_gbps) via an explicit title token; 87 fixed
(e.g. 400G cables mislabelled SFP+ to QSFP-DD), 947 opaque rows left untouched
(never guessed). Scraped original preserved in new column form_factor_raw.

sql/121: document lead_time_days as not-collected (0 percent populated on all
time-series tables) so no consumer fabricates a default.

scraper/utils/db.ts: note that product_type/form_factor are trigger-maintained.
2026-07-04 16:05:28 +00:00

125 lines
6.3 KiB
PL/PgSQL

-- Migration 120: conservative form_factor recovery (provably-wrong rows only)
-- ─────────────────────────────────────────────────────────────────────────────
-- Problem: some scrapers default form_factor to 'SFP'/'SFP+', so a 400G QSFP-DD
-- DAC ends up tagged 'SFP+'. We only ever correct a form_factor that is
-- PROVABLY wrong — i.e. its max electrical speed (form_factors.max_speed_gbps)
-- is below the row's actual speed_gbps — and only when the part_number carries
-- an explicit form-factor token that CAN carry that speed. Opaque part numbers
-- (e.g. 'EOLS-1303-40-D') are left untouched; we never guess a form factor.
--
-- The scraped original is preserved in form_factor_raw for audit/rollback.
-- Ingest-time self-healing is added to the tip_transceivers_biu() trigger.
-- Idempotent.
-- ─────────────────────────────────────────────────────────────────────────────
-- 1. Preserve the scraped original ---------------------------------------------
ALTER TABLE transceivers ADD COLUMN IF NOT EXISTS form_factor_raw TEXT;
COMMENT ON COLUMN transceivers.form_factor_raw IS
'Form factor exactly as scraped, before tip_recover_form_factor() correction. Audit/rollback only.';
UPDATE transceivers SET form_factor_raw = form_factor
WHERE form_factor_raw IS NULL;
-- 2. Explicit form-factor token extraction (most-specific first) ----------------
CREATE OR REPLACE FUNCTION tip_extract_ff_token(p_part_number TEXT) RETURNS TEXT
LANGUAGE sql IMMUTABLE PARALLEL SAFE AS $$
SELECT CASE
WHEN p_part_number ~* 'qsfp-?dd-?800|qdd-?800' THEN 'QSFP-DD800'
-- Q56DD / QSFP56-DD is the 400G double-density QSFP connector (Dell naming) → QSFP-DD
WHEN p_part_number ~* 'q56dd|qsfp56-?dd' THEN 'QSFP-DD'
WHEN p_part_number ~* 'osfp-?xd' THEN 'OSFP-XD'
WHEN p_part_number ~* 'osfp224' THEN 'OSFP224'
WHEN p_part_number ~* 'osfp112' THEN 'OSFP112'
WHEN p_part_number ~* '\mosfp\M' THEN 'OSFP'
WHEN p_part_number ~* 'qsfp112' THEN 'QSFP112'
WHEN p_part_number ~* 'qsfp-?dd|\mqdd\M|qsfpdd' THEN 'QSFP-DD'
WHEN p_part_number ~* 'qsfp56|\mq56\M' THEN 'QSFP56'
WHEN p_part_number ~* 'qsfp28|\mq28\M' THEN 'QSFP28'
WHEN p_part_number ~* 'qsfp\+|qsfp-?plus' THEN 'QSFP+'
WHEN p_part_number ~* 'sfp-?dd|sfpdd' THEN 'SFP-DD'
WHEN p_part_number ~* 'sfp112' THEN 'SFP112'
WHEN p_part_number ~* 'sfp56' THEN 'SFP56'
WHEN p_part_number ~* 'sfp28' THEN 'SFP28'
WHEN p_part_number ~* 'sfp\+|sfp-?plus' THEN 'SFP+'
WHEN p_part_number ~* 'cfp2-?dco' THEN 'CFP2-DCO'
WHEN p_part_number ~* 'cfp2' THEN 'CFP2'
WHEN p_part_number ~* 'cfp8' THEN 'CFP8'
WHEN p_part_number ~* 'cfp4' THEN 'CFP4'
WHEN p_part_number ~* '\mcfp\M' THEN 'CFP'
WHEN p_part_number ~* '\mxfp\M' THEN 'XFP'
ELSE NULL
END;
$$;
-- 3. Recovery: return corrected FF only when the current one is PROVABLY wrong ---
CREATE OR REPLACE FUNCTION tip_recover_form_factor(
p_part_number TEXT, p_form_factor TEXT, p_speed_gbps NUMERIC
) RETURNS TEXT
LANGUAGE plpgsql STABLE PARALLEL SAFE AS $$
DECLARE
v_token TEXT := tip_extract_ff_token(p_part_number);
v_cur_max NUMERIC;
v_tok_max NUMERIC;
BEGIN
IF v_token IS NULL OR p_form_factor IS NULL OR p_speed_gbps IS NULL THEN
RETURN p_form_factor;
END IF;
IF upper(v_token) = upper(p_form_factor) THEN
RETURN p_form_factor; -- already correct
END IF;
SELECT max_speed_gbps INTO v_cur_max FROM form_factors WHERE upper(name) = upper(p_form_factor);
SELECT max_speed_gbps INTO v_tok_max FROM form_factors WHERE name = v_token;
-- current provably wrong for the speed, and the token can actually carry it
IF v_cur_max IS NOT NULL AND v_tok_max IS NOT NULL
AND p_speed_gbps > v_cur_max AND v_tok_max >= p_speed_gbps THEN
RETURN v_token;
END IF;
RETURN p_form_factor; -- not confident → leave as-is
END;
$$;
-- 4. Backfill the confidently-recoverable rows ---------------------------------
UPDATE transceivers
SET form_factor = tip_recover_form_factor(part_number, form_factor, speed_gbps)
WHERE form_factor IS DISTINCT FROM tip_recover_form_factor(part_number, form_factor, speed_gbps);
-- 5. Extend the ingest trigger with FF self-healing ----------------------------
CREATE OR REPLACE FUNCTION tip_transceivers_biu() RETURNS TRIGGER
LANGUAGE plpgsql AS $$
BEGIN
-- product_type: recompute only when a classification input changed
IF TG_OP = 'INSERT'
OR NEW.product_type IS NULL
OR NEW.part_number IS DISTINCT FROM OLD.part_number
OR NEW.category IS DISTINCT FROM OLD.category
OR NEW.reach_label IS DISTINCT FROM OLD.reach_label
THEN
NEW.product_type := tip_classify_product_type(NEW.part_number, NEW.category, NEW.reach_label);
END IF;
-- form_factor: preserve the scraped original, then correct only provably-wrong values
NEW.form_factor_raw := COALESCE(NEW.form_factor_raw, NEW.form_factor);
NEW.form_factor := tip_recover_form_factor(NEW.part_number, NEW.form_factor, NEW.speed_gbps);
RETURN NEW;
END;
$$;
-- (trigger trg_transceivers_biu already bound in migration 119 — replacing the
-- function body above is sufficient.)
INSERT INTO _migrations (filename)
VALUES ('120-form-factor-recovery.sql')
ON CONFLICT (filename) DO NOTHING;
-- 6. Report --------------------------------------------------------------------
DO $$
DECLARE v_fixed INT; v_left INT;
BEGIN
SELECT count(*) INTO v_fixed FROM transceivers WHERE form_factor IS DISTINCT FROM form_factor_raw;
SELECT count(*) INTO v_left FROM transceivers t JOIN form_factors f ON upper(f.name)=upper(t.form_factor)
WHERE t.speed_gbps > f.max_speed_gbps;
RAISE NOTICE 'form_factor corrected on % rows; % provably-wrong rows left untouched (opaque, not guessed).', v_fixed, v_left;
END;
$$;