plant-disease-id/apps/web/scripts/fix-classifications.ts

#!/usr/bin/env node
/**
 * fix-classifications.ts — Fix misclassified diseases in the DB.
 *
 * Fixes:
 *   1. Diseases named with viral indicators (mosaic, mottle, ringspot, virus, etc.)
 *      that are incorrectly tagged as "fungal"
 *   2. Other suspicious patterns
 *
 * Usage: cd apps/web && npx tsx scripts/fix-classifications.ts
 */

import { readFileSync } from "fs";
import { resolve } from "path";

// Manually load .env.development
const envPath = resolve(__dirname, "../.env.development");
try {
  const env = readFileSync(envPath, "utf-8");
  for (const line of env.split("\n")) {
    const trimmed = line.trim();
    if (trimmed && !trimmed.startsWith("#")) {
      const eqIdx = trimmed.indexOf("=");
      if (eqIdx > 0) {
        const key = trimmed.slice(0, eqIdx).trim();
        const val = trimmed.slice(eqIdx + 1).trim();
        if (!process.env[key]) process.env[key] = val;
      }
    }
  }
} catch {}

import { getDb, closeDb } from "../src/lib/db/index";
import { diseases } from "../src/lib/db/schema";
import { createClient } from "@libsql/client";

type AgentType = "fungal" | "bacterial" | "viral" | "environmental";

interface FixRule {
  test: (name: string) => boolean;
  correctAgent: AgentType;
  reason: string;
}

const FIX_RULES: FixRule[] = [
  // Diseases explicitly named as "virus" or "viral"
  {
    test: (name) => /\b(virus|viral|viroid)\b/i.test(name),
    correctAgent: "viral",
    reason: "Name explicitly indicates viral disease",
  },
  // Potexvirus, carlavirus, etc.
  {
    test: (name) =>
      /\b(virus\b|potex|carla|tobamo|poty|cucumo|ilar|nepo|tymovirus|geminivir|tom bushy stunt)\b/i.test(
        name,
      ),
    correctAgent: "viral",
    reason: "Recognized virus genus in name",
  },
  // "Mosaic" diseases (typically viral)
  {
    test: (name) => /\bmosaic\b/i.test(name),
    correctAgent: "viral",
    reason: "Mosaic symptoms are typically caused by viruses",
  },
  // "Mottle" diseases (typically viral)
  {
    test: (name) => /\bmottle\b/i.test(name),
    correctAgent: "viral",
    reason: "Mottle symptoms are typically caused by viruses",
  },
  // "Ringspot" diseases (typically viral)
  {
    test: (name) => /\bringspot\b/i.test(name),
    correctAgent: "viral",
    reason: "Ringspot symptoms are typically caused by viruses",
  },
  // "Leaf curl" (many are viral)
  {
    test: (name) => /\bleaf curl\b|\bleafroll\b|\bleaf-roll\b/i.test(name),
    correctAgent: "viral",
    reason: "Leaf curl/roll diseases are often viral",
  },
  // "Rosette" (often viral or phytoplasma)
  {
    test: (name) => /\brosette\b/i.test(name),
    correctAgent: "viral",
    reason: "Rosette diseases are typically viral or phytoplasma",
  },
  // "Yellows" (often phytoplasma/viral)
  {
    test: (name) => /\byellows\b/i.test(name) && !/\bpeach\b/i.test(name),
    correctAgent: "viral",
    reason: "Yellows diseases are typically phytoplasma or viral",
  },
  // "Stunt" / "Dwarf" (often viral)
  {
    test: (name) => /\b(stunt|dwarf(ism)?)\b/i.test(name),
    correctAgent: "viral",
    reason: "Stunting/dwarfing diseases are often viral",
  },
  // Explicit bacterial in name
  {
    test: (name) =>
      /\bbacterial\b|\bbacterium\b|\berwinia\b|\bpseudomonas\b|\bxanthomonas\b|\bralstonia\b|\bclavibacter\b|\bstreptomyces\b|\bagrobacterium\b/i.test(
        name,
      ),
    correctAgent: "bacterial",
    reason: "Name indicates bacterial disease",
  },
  // Environmental/abiotic indicators
  {
    test: (name) =>
      /\b(deficiency|abiotic|environmental|injury|damage|stress|sunscald|sunburn|chilling|freeze|frost|wind|hail|nutrient|toxicity|snow\s+(mold|scald)|winter\s+(injury|rot|kill))\b/i.test(
        name,
      ),
    correctAgent: "environmental",
    reason: "Name indicates abiotic/environmental cause",
  },
];

async function main() {
  console.log("🔍 Fixing disease classifications\n");
  const db = getDb();
  const allDiseases = await db
    .select({ id: diseases.id, name: diseases.name, causalAgentType: diseases.causalAgentType })
    .from(diseases)
    .all();
  console.log(`📋 ${allDiseases.length} total diseases\n`);

  const rawClient = createClient({
    url: process.env.DATABASE_URL!,
    authToken: process.env.DATABASE_TOKEN!,
  });

  const updates: { id: string; newAgent: AgentType; rule: FixRule; oldAgent: string }[] = [];

  for (const d of allDiseases) {
    for (const rule of FIX_RULES) {
      if (rule.test(d.name)) {
        if (d.causalAgentType !== rule.correctAgent) {
          updates.push({
            id: d.id,
            newAgent: rule.correctAgent,
            rule,
            oldAgent: d.causalAgentType,
          });
        }
        break; // First matching rule wins
      }
    }
  }

  console.log(`Found ${updates.length} diseases needing reclassification:\n`);

  // Group by correction type
  const grouped: Record<string, { from: string; to: string; items: string[] }> = {};
  for (const u of updates) {
    const key = `${u.oldAgent}→${u.newAgent}`;
    if (!grouped[key]) grouped[key] = { from: u.oldAgent, to: u.newAgent, items: [] };
    grouped[key].items.push(`  ${u.id}`);
  }

  for (const [, g] of Object.entries(grouped)) {
    console.log(`${g.from} → ${g.to} (${g.items.length} diseases):`);
    g.items.slice(0, 10).forEach((l) => console.log(l));
    if (g.items.length > 10) console.log(`  ... and ${g.items.length - 10} more`);
    console.log();
  }

  // Apply updates
  if (updates.length === 0) {
    console.log("✅ No corrections needed");
  } else {
    console.log(`Applying ${updates.length} corrections...\n`);

    // Batch update in groups of 50
    for (let i = 0; i < updates.length; i += 50) {
      const batch = updates.slice(i, i + 50);
      await rawClient.batch(
        batch.map((u) => ({
          sql: "UPDATE diseases SET causal_agent_type = ?, updated_at = datetime('now') WHERE id = ?",
          args: [u.newAgent, u.id],
        })),
        "write",
      );
      process.stdout.write(`  ${Math.min(i + 50, updates.length)}/${updates.length}\n`);
    }

    console.log(`\n✅ ${updates.length} diseases reclassified`);
  }

  // Print summary stats
  const after = await db.select({ causalAgentType: diseases.causalAgentType }).from(diseases).all();
  const counts: Record<string, number> = {};
  after.forEach((d) => {
    counts[d.causalAgentType] = (counts[d.causalAgentType] || 0) + 1;
  });
  console.log("\n📊 Updated distribution:");
  for (const [type, count] of Object.entries(counts).sort()) {
    console.log(`  ${type}: ${count}`);
  }

  rawClient.close();
  closeDb();
}

main().catch((err) => {
  console.error("\n❌", err);
  process.exit(1);
});