Rene Fichtmueller d7144731e0 feat(scraper): add 100+ OEM seed scrapers + tip-llm-guided inference layer
New OEM transceiver seed scrapers (94 cron-scheduled, 24/7):
- Media/Broadcast: Evertz, Grass Valley, Haivision, Viasat
- Asian Optical: FiberHome, Oplink, Accelink, Hisense Broadband
- Optical Mfrs: Lumentum, II-VI/Coherent, Source Photonics, O-Net,
  InnoLight, AOI, Sumitomo Electric, NeoPhotonics
- Industrial: GE Grid, Schweitzer, Moxa Industrial, Cisco IE,
  Phoenix Contact, Beckhoff, Omron, ABB, Siemens, Schneider, Rockwell, Belden
- Enterprise/DC: Arista, Pica8, Pluribus, DriveNets, Cisco (Meraki/Catalyst/Nexus/ASR)
- Cloud: AWS, Azure, Google Cloud, Meta
- Storage: NetApp, Pure Storage, HPE Storage, IBM Storage, Dell Storage, Hitachi Vantara
- 5G/RAN: Samsung Networks, Nokia AirScale, Ericsson RAN, Mavenir
- Security: Check Point, Barracuda, Fortinet, Palo Alto
- Telecom Optical: ADVA, PacketLight, FiberHome, Accelink, Hisense

API: tip-llm-guided inference layer (strict schema + repair-retry + safe fallback)
- POST /api/tip-llm/infer|research-plan|extract|finding|health
- Hard JSON schema enforcement, create_finding=false on empty evidence
- Confidence gate (>= 0.4), validation with consistency check

Build: added incremental=true to scraper tsconfig (OOM prevention)
Scheduler: 87 → 94 registered workers
2026-04-27 00:00:14 +02:00

332 lines
11 KiB
TypeScript

/**
* Microsoft Azure OEM Transceiver Catalog Seed
*
* Seeds Microsoft Azure-branded transceiver PIDs used in ExpressRoute
* dedicated ports and Azure Stack Hub/HCI hardware. Azure uses an AZ-
* prefix for SFP/QSFP optics validated on its custom Azurite/SONiC-based
* network ASICs and Azure Stack hardware.
*
* Sources:
* - Azure ExpressRoute prerequisites (azure.microsoft.com/products/expressroute/)
* - Azure Stack Hub network hardware guide
* - SFF-8024 / IEEE 802.3 speed codes
*
* Run: tsx packages/scraper/src/scrapers/azure-oem.ts
* Cron: daily at 07:30
*/
import { pool, ensureVendor } from "../utils/db";
interface AzurePID {
pid: string;
formFactor: string;
speedGbps: number;
speed: string;
reachMeters: number;
reachLabel: string;
fiberType: string;
connector: string;
wavelengths?: string;
standard?: string;
category?: string;
notes?: string;
}
// PIDs that map to telecom / DWDM variants (ZR, ER4)
const TELECOM_PIDS = new Set([
"AZ-SFP-10G-ZR",
"AZ-QSFP28-100G-ER4",
]);
const AZURE_PIDS: AzurePID[] = [
// ── 1G SFP ───────────────────────────────────────────────────────────────
{
pid: "AZ-SFP-1G-SX",
formFactor: "SFP",
speedGbps: 1,
speed: "1G",
reachMeters: 550,
reachLabel: "SX",
fiberType: "MMF",
connector: "LC",
wavelengths: "850nm",
standard: "1000BASE-SX",
category: "DataCenter",
notes: "1GbE SFP SX; Azure Stack Hub management port; OM2/OM3 MMF up to 550m",
},
{
pid: "AZ-SFP-1G-LX",
formFactor: "SFP",
speedGbps: 1,
speed: "1G",
reachMeters: 10000,
reachLabel: "LX",
fiberType: "SMF",
connector: "LC",
wavelengths: "1310nm",
standard: "1000BASE-LX",
category: "DataCenter",
notes: "1GbE SFP LX; Azure Stack Hub management port; OS2 SMF up to 10km",
},
// ── 1G Copper SFP ────────────────────────────────────────────────────────
{
pid: "AZ-SFP-GE-T",
formFactor: "SFP",
speedGbps: 1,
speed: "1G",
reachMeters: 100,
reachLabel: "T",
fiberType: "DAC",
connector: "RJ45",
standard: "1000BASE-T",
category: "DataCenter",
notes: "1GbE copper SFP RJ45; Azure Stack Hub management copper option; Cat5e/6",
},
// ── 10G SFP+ ─────────────────────────────────────────────────────────────
{
pid: "AZ-SFP-10G-SR",
formFactor: "SFP+",
speedGbps: 10,
speed: "10G",
reachMeters: 300,
reachLabel: "SR",
fiberType: "MMF",
connector: "LC",
wavelengths: "850nm",
standard: "10GBASE-SR",
category: "DataCenter",
notes: "10GbE SFP+ SR; Azure Stack Hub server uplink; OM3/OM4 MMF up to 300m",
},
{
pid: "AZ-SFP-10G-LR",
formFactor: "SFP+",
speedGbps: 10,
speed: "10G",
reachMeters: 10000,
reachLabel: "LR",
fiberType: "SMF",
connector: "LC",
wavelengths: "1310nm",
standard: "10GBASE-LR",
category: "DataCenter",
notes: "10GbE SFP+ LR; Azure ExpressRoute 10G port; OS2 SMF up to 10km",
},
{
pid: "AZ-SFP-10G-ER",
formFactor: "SFP+",
speedGbps: 10,
speed: "10G",
reachMeters: 40000,
reachLabel: "ER",
fiberType: "SMF",
connector: "LC",
wavelengths: "1550nm",
standard: "10GBASE-ER",
category: "DataCenter",
notes: "10GbE SFP+ ER; Azure ExpressRoute extended-reach; OS2 SMF up to 40km",
},
{
pid: "AZ-SFP-10G-ZR",
formFactor: "SFP+",
speedGbps: 10,
speed: "10G",
reachMeters: 80000,
reachLabel: "ZR",
fiberType: "SMF",
connector: "LC",
wavelengths: "1550nm",
standard: "10GBASE-ZR",
category: "Telecom",
notes: "10GbE SFP+ ZR; Azure ExpressRoute long-haul DWDM 80km; OS2 SMF",
},
// ── 25G SFP28 ────────────────────────────────────────────────────────────
{
pid: "AZ-SFP28-25G-SR",
formFactor: "SFP28",
speedGbps: 25,
speed: "25G",
reachMeters: 100,
reachLabel: "SR",
fiberType: "MMF",
connector: "LC",
wavelengths: "850nm",
standard: "25GBASE-SR",
category: "DataCenter",
notes: "25GbE SFP28 SR; Azure Stack HCI server host port; OM4 MMF up to 100m",
},
{
pid: "AZ-SFP28-25G-LR",
formFactor: "SFP28",
speedGbps: 25,
speed: "25G",
reachMeters: 10000,
reachLabel: "LR",
fiberType: "SMF",
connector: "LC",
wavelengths: "1310nm",
standard: "25GBASE-LR",
category: "DataCenter",
notes: "25GbE SFP28 LR; Azure Stack HCI server host port; OS2 SMF up to 10km",
},
// ── 40G QSFP+ ────────────────────────────────────────────────────────────
{
pid: "AZ-QSFP-40G-SR4",
formFactor: "QSFP+",
speedGbps: 40,
speed: "40G",
reachMeters: 150,
reachLabel: "SR4",
fiberType: "MMF",
connector: "MPO",
wavelengths: "850nm",
standard: "40GBASE-SR4",
category: "DataCenter",
notes: "40GbE QSFP+ SR4; Azure Stack Hub Top-of-Rack spine uplink; OM3/OM4 MPO-12 up to 150m",
},
{
pid: "AZ-QSFP-40G-LR4",
formFactor: "QSFP+",
speedGbps: 40,
speed: "40G",
reachMeters: 10000,
reachLabel: "LR4",
fiberType: "SMF",
connector: "LC",
wavelengths: "1270-1330nm",
standard: "40GBASE-LR4",
category: "DataCenter",
notes: "40GbE QSFP+ LR4; Azure ExpressRoute 40G port; OS2 SMF up to 10km",
},
// ── 100G QSFP28 ──────────────────────────────────────────────────────────
{
pid: "AZ-QSFP28-100G-SR4",
formFactor: "QSFP28",
speedGbps: 100,
speed: "100G",
reachMeters: 100,
reachLabel: "SR4",
fiberType: "MMF",
connector: "MPO",
wavelengths: "850nm",
standard: "100GBASE-SR4",
category: "DataCenter",
notes: "100GbE QSFP28 SR4; Azure ExpressRoute 100G / Stack HCI spine; OM4 MPO-12 up to 100m",
},
{
pid: "AZ-QSFP28-100G-LR4",
formFactor: "QSFP28",
speedGbps: 100,
speed: "100G",
reachMeters: 10000,
reachLabel: "LR4",
fiberType: "SMF",
connector: "LC",
wavelengths: "1295-1310nm",
standard: "100GBASE-LR4",
category: "DataCenter",
notes: "100GbE QSFP28 LR4; Azure ExpressRoute 100G dedicated connection; OS2 SMF up to 10km",
},
{
pid: "AZ-QSFP28-100G-ER4",
formFactor: "QSFP28",
speedGbps: 100,
speed: "100G",
reachMeters: 40000,
reachLabel: "ER4",
fiberType: "SMF",
connector: "LC",
wavelengths: "1295-1310nm",
standard: "100GBASE-ER4",
category: "Telecom",
notes: "100G QSFP28 ER4; Azure ExpressRoute long-reach 40km inter-datacenter replication; OS2 SMF",
},
// ── 400G QSFP-DD ─────────────────────────────────────────────────────────
{
pid: "AZ-QSFP-DD-400G-DR4",
formFactor: "QSFP-DD",
speedGbps: 400,
speed: "400G",
reachMeters: 500,
reachLabel: "DR4",
fiberType: "SMF",
connector: "MPO",
wavelengths: "1310nm",
standard: "400GBASE-DR4",
category: "DataCenter",
notes: "400GbE QSFP-DD DR4; Azure next-gen datacenter spine interconnect; OS2 SMF up to 500m",
},
{
pid: "AZ-QSFP-DD-400G-SR8",
formFactor: "QSFP-DD",
speedGbps: 400,
speed: "400G",
reachMeters: 100,
reachLabel: "SR8",
fiberType: "MMF",
connector: "MPO",
wavelengths: "850nm",
standard: "400GBASE-SR8",
category: "DataCenter",
notes: "400GbE QSFP-DD SR8; Azure next-gen datacenter spine interconnect; OM4/OM5 MPO-16 up to 100m",
},
];
export async function scrapeAzureOem(): Promise<void> {
console.log("=== Microsoft Azure OEM Transceiver Seed ===\n");
const vendorId = await ensureVendor(
"Microsoft Azure",
"oem",
"https://azure.microsoft.com/en-us/products/expressroute/",
undefined
);
let inserted = 0;
let updated = 0;
let errors = 0;
for (const p of AZURE_PIDS) {
const slug = `azure-${p.pid.toLowerCase().replace(/[^a-z0-9]+/g, "-")}`;
const category = TELECOM_PIDS.has(p.pid) ? "Telecom" : (p.category ?? "DataCenter");
try {
const res = await pool.query(
`INSERT INTO transceivers
(slug, part_number, vendor_id, form_factor, speed, speed_gbps,
reach_meters, reach_label, fiber_type, connector, wavelengths,
dom_support, ieee_reference, market_status, category, notes)
VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9,$10,$11,true,$12,'Mainstream',$13,$14)
ON CONFLICT (slug) DO UPDATE SET
speed_gbps = EXCLUDED.speed_gbps,
reach_meters = CASE WHEN EXCLUDED.reach_meters > 0 THEN EXCLUDED.reach_meters ELSE transceivers.reach_meters END,
fiber_type = CASE WHEN EXCLUDED.fiber_type <> '' THEN EXCLUDED.fiber_type ELSE transceivers.fiber_type END,
wavelengths = COALESCE(EXCLUDED.wavelengths, transceivers.wavelengths),
updated_at = NOW()
RETURNING (xmax = 0) as was_inserted`,
[slug, p.pid, vendorId, p.formFactor, p.speed, p.speedGbps,
p.reachMeters, p.reachLabel, p.fiberType, p.connector,
p.wavelengths ?? null, p.standard ?? null, category, p.notes ?? null]
);
if (res.rows[0]?.was_inserted) inserted++; else updated++;
} catch (err) {
console.warn(` Skip ${p.pid}: ${(err as Error).message.slice(0, 80)}`);
errors++;
}
}
console.log(`\n=== Microsoft Azure OEM Seed Complete ===`);
console.log(` Inserted: ${inserted}`);
console.log(` Updated: ${updated}`);
console.log(` Errors: ${errors}`);
console.log(` Total PIDs: ${AZURE_PIDS.length}\n`);
}
if (require.main === module) {
scrapeAzureOem()
.then(() => pool.end())
.catch((err) => {
console.error("Fatal:", err);
pool.end();
process.exit(1);
});
}