/**
 * Expand DB with comprehensive plant disease list from Wikipedia.
 *
 * Reads /tmp/plant_diseases/plant_diseases_comprehensive.txt,
 * compares against existing DB entries (by name, case-insensitive),
 * and inserts new entries with reasonable defaults.
 *
 * Usage:
 *   cd apps/web && export $(grep -v '^#' .env.development | xargs) && npx tsx scripts/expand-diseases.ts
 */

import "dotenv/config";
import { readFileSync } from "fs";
import { eq, sql } from "drizzle-orm";
import { getDb, closeDb } from "../src/lib/db/index";
import { plants, diseases } from "../src/lib/db/schema";
import type { CausalAgentType, Severity } from "../src/lib/types";

// ─── Parse the comprehensive list ─────────────────────────────────────────────

interface DiseaseEntry {
  name: string;
  sourceUrl: string;
}

function parseComprehensiveList(filePath: string): DiseaseEntry[] {
  const content = readFileSync(filePath, "utf-8");
  const entries: DiseaseEntry[] = [];
  const lines = content.split("\n");
  const nameRe = /^\d+\.\s+(.+)$/;

  for (let i = 0; i < lines.length; i++) {
    const nameMatch = lines[i].match(nameRe);
    if (nameMatch) {
      const name = nameMatch[1].trim();
      const urlLine = lines[i + 1]?.trim() || "";
      // Only add if the next line is a valid URL
      if (urlLine.startsWith("http")) {
        entries.push({ name, sourceUrl: urlLine });
        i++; // skip the URL line
      } else {
        entries.push({ name, sourceUrl: "" });
      }
    }
  }
  return entries;
}

// ─── Infer causal agent type from disease name ────────────────────────────────

function inferCausalAgent(name: string): CausalAgentType {
  const lower = name.toLowerCase();

  // Bacterial indicators
  if (
    lower.startsWith("bacterial ") ||
    lower.includes(" xanthomonas") ||
    lower.includes(" pseudomonas") ||
    lower.includes(" erwinia") ||
    lower.includes(" ralstonia") ||
    lower.includes(" clavibacter") ||
    lower.includes(" streptomyces") ||
    lower.includes(" agrobacterium") ||
    lower.includes(" corynebacterium") ||
    lower.includes(" pectobacterium") ||
    lower.includes(" dickeya")
  ) {
    return "bacterial";
  }

  // Viral indicators - strong signals
  if (
    lower.includes(" mosaic") ||
    lower.includes(" yellows") ||
    lower.includes(" leaf roll") ||
    lower.includes(" leafroll") ||
    lower.includes(" ringspot") ||
    lower.includes(" ring spot") ||
    lower.includes(" enation") ||
    lower.includes(" phyllody") ||
    lower.includes(" witches") ||
    lower.includes(" witches'") ||
    lower.includes(" crinkle") ||
    lower.includes(" rosette") ||
    lower.includes(" shoestring") ||
    lower.includes(" tristeza") ||
    lower.includes(" psorosis") ||
    lower.includes(" stubborn") ||
    lower.includes(" greening") ||
    lower.includes(" vein banding") ||
    lower.includes(" vein mottle") ||
    lower.includes(" vein clearing") ||
    lower.includes(" leaf pucker") ||
    lower.includes(" pucker leaf") ||
    lower.includes(" latent") ||
    lower.includes(" motley") ||
    lower.includes(" rugose")
  ) {
    return "viral";
  }

  // Viral - names containing "virus" or "viroid"
  if (lower.includes(" virus") || lower.includes(" viroid") || lower.includes(" virosis")) {
    return "viral";
  }

  // Nematodes
  if (
    lower.includes(" nematode") ||
    lower.includes(" nematodes") ||
    lower.includes(" eelworm") ||
    lower.includes(" root knot") ||
    lower.includes(" root-knot") ||
    lower.includes(" cyst ") ||
    lower.includes(" dagger ") ||
    lower.includes(" lance ") ||
    lower.includes(" lesion ") ||
    lower.includes(" ring ") ||
    lower.includes(" spiral ") ||
    lower.includes(" sting ") ||
    lower.includes(" stubby ") ||
    lower.includes(" needle ") ||
    lower.includes(" foliar ") ||
    lower.includes(" bulb ") ||
    lower.includes(" reniform ") ||
    lower.includes(" burrowing ")
  ) {
    // Check if it's really a nematode name
    if (lower.includes("nematode")) return "environmental";
  }

  // Fungal indicators
  if (
    lower.includes(" mildew") ||
    lower.includes(" rust") ||
    lower.includes(" smut") ||
    lower.includes(" blight") ||
    lower.includes(" canker") ||
    lower.includes(" rot") ||
    lower.includes(" scab") ||
    lower.includes(" mold") ||
    lower.includes(" anthracnose") ||
    lower.includes(" bunt") ||
    lower.includes(" ergot") ||
    lower.includes(" dieback") ||
    lower.includes(" scald") ||
    lower.includes(" blotch") ||
    lower.includes(" speckle") ||
    lower.includes(" sooty") ||
    lower.includes(" flyspeck") ||
    lower.includes(" fusarium") ||
    lower.includes(" alternaria") ||
    lower.includes(" botrytis") ||
    lower.includes(" rhizoctonia") ||
    lower.includes(" pythium") ||
    lower.includes(" phytophthora") ||
    lower.includes(" sclerotinia") ||
    lower.includes(" verticillium") ||
    lower.includes(" ascochyta") ||
    lower.includes(" cercospora") ||
    lower.includes(" septoria") ||
    lower.includes(" colletotrichum") ||
    lower.includes(" phomopsis") ||
    lower.includes(" diaporthe") ||
    lower.includes(" diplodia") ||
    lower.includes(" macrophomina") ||
    lower.includes(" cylindrocladium") ||
    lower.includes(" mycosphaerella") ||
    lower.includes(" helminthosporium") ||
    lower.includes(" curvularia") ||
    lower.includes(" bipolaris") ||
    lower.includes(" exserohilum") ||
    lower.includes(" dothiorella") ||
    lower.includes(" fusicoccum") ||
    lower.includes(" pestalotia") ||
    lower.includes(" glomerella") ||
    lower.includes(" nectria") ||
    lower.includes(" eutypa") ||
    lower.includes(" armillaria") ||
    lower.includes(" ganoderma") ||
    lower.includes(" phoma") ||
    lower.includes(" cladosporium") ||
    lower.includes(" penicillium") ||
    lower.includes(" aspergillus") ||
    lower.includes(" rhizopus") ||
    lower.includes(" mucor") ||
    lower.includes(" downy mildew") ||
    lower.includes(" powdery mildew") ||
    lower.includes(" pink rot") ||
    lower.includes(" pink mold") ||
    lower.includes(" pink root") ||
    lower.includes(" gray mold") ||
    lower.includes(" grey mold") ||
    lower.includes(" white rot") ||
    lower.includes(" white mold") ||
    lower.includes(" brown rot") ||
    lower.includes(" black rot") ||
    lower.includes(" soft rot") ||
    lower.includes(" dry rot") ||
    lower.includes(" fruit rot") ||
    lower.includes(" root rot") ||
    lower.includes(" stem rot") ||
    lower.includes(" ear rot") ||
    lower.includes(" crown rot") ||
    lower.includes(" collar rot") ||
    lower.includes(" pod rot") ||
    lower.includes(" kernel rot") ||
    lower.includes(" stalk rot") ||
    lower.includes(" head rot") ||
    lower.includes(" butt rot") ||
    lower.includes(" stump rot") ||
    lower.includes(" wood rot") ||
    lower.includes(" seed rot") ||
    lower.includes(" leaf spot") ||
    lower.includes(" leaf blight") ||
    lower.includes(" leaf blotch") ||
    lower.includes(" leaf rust") ||
    lower.includes(" brown spot") ||
    lower.includes(" black spot") ||
    lower.includes(" black leg") ||
    lower.includes(" blackleg") ||
    lower.includes(" black foot") ||
    lower.includes(" white rust") ||
    lower.includes(" white smut") ||
    lower.includes(" white scab") ||
    lower.includes(" tar spot") ||
    lower.includes(" target spot") ||
    lower.includes(" dollar spot") ||
    lower.includes(" fairy ring") ||
    lower.includes(" snow mold") ||
    lower.includes(" pink disease") ||
    lower.includes(" thread blight") ||
    lower.includes(" web blight") ||
    lower.includes(" sclerotial") ||
    lower.includes(" sore shin") ||
    lower.includes(" wart") ||
    lower.includes(" scurf") ||
    lower.includes(" silver scurf") ||
    lower.includes(" shot hole") ||
    lower.includes(" timber rot") ||
    lower.includes(" cottony rot") ||
    lower.includes(" watery rot") ||
    lower.includes(" sour rot") ||
    lower.includes(" seepage") ||
    lower.includes(" bunch rot") ||
    lower.includes(" noble rot") ||
    lower.includes(" bitter rot") ||
    lower.includes(" ripe rot") ||
    lower.includes(" ring rot") ||
    lower.includes(" coral spot") ||
    lower.includes(" stem canker") ||
    lower.includes(" branch canker") ||
    lower.includes(" perennial canker") ||
    lower.includes(" brand canker") ||
    lower.includes(" blister canker") ||
    lower.includes(" bleeding canker") ||
    lower.includes(" bark canker") ||
    lower.includes(" gum canker") ||
    lower.includes(" collar crack") ||
    lower.includes(" fasciation") ||
    lower.includes(" exobasidium") ||
    lower.includes(" mycorrhiza") ||
    lower.includes(" lichen") ||
    lower.includes(" algal") ||
    lower.includes(" chlorosis") ||
    lower.includes(" leaf blister") ||
    lower.includes(" leaf curl")
  ) {
    return "fungal";
  }

  // Physiological / environmental indicators
  if (
    lower.includes(" sunscald") ||
    lower.includes(" sunburn") ||
    lower.includes(" chilling") ||
    lower.includes(" blossom end rot") ||
    lower.includes(" edema") ||
    lower.includes(" deficiency") ||
    lower.includes(" toxicity") ||
    lower.includes(" ozone") ||
    lower.includes(" drought") ||
    lower.includes(" frost") ||
    lower.includes(" herbicide") ||
    lower.includes(" pesticide") ||
    lower.includes(" phytotoxicity") ||
    lower.includes(" catface") ||
    lower.includes(" fruit cracking") ||
    lower.includes(" russeting") ||
    lower.includes(" growth crack") ||
    lower.includes(" mealiness") ||
    lower.includes(" wind scar") ||
    lower.includes(" hail") ||
    lower.includes(" salt ") ||
    lower.includes(" nutritional") ||
    lower.includes(" mineral") ||
    lower.includes(" overwatering") ||
    lower.includes(" under watering") ||
    lower.includes(" waterlogging") ||
    lower.includes(" chemical injury") ||
    lower.includes(" spray injury") ||
    lower.includes(" fertilizer burn") ||
    lower.includes(" lightning") ||
    lower.includes(" bruising") ||
    lower.includes(" pressure bruise") ||
    lower.includes(" impact damage") ||
    lower.includes(" transit rot")
  ) {
    return "environmental";
  }

  // Insect/mite/pest indicators
  if (
    lower.includes(" mite") ||
    lower.includes(" beetle") ||
    lower.includes(" weevil") ||
    lower.includes(" aphid") ||
    lower.includes(" bollworm") ||
    lower.includes(" leaf miner") ||
    lower.includes(" mealybug") ||
    lower.includes(" thrips") ||
    lower.includes(" whitefly") ||
    lower.includes(" caterpillar") ||
    lower.includes(" sawfly") ||
    lower.includes(" scale ") ||
    lower.includes(" leafhopper") ||
    lower.includes(" psylla") ||
    lower.includes(" slug") ||
    lower.includes(" snail") ||
    lower.includes(" borer") ||
    lower.includes(" maggot") ||
    lower.includes(" grub") ||
    lower.includes(" earwig") ||
    lower.includes(" grasshopper")
  ) {
    return "environmental";
  }

  // Fungal genus names
  const fungalGenera = [
    "armillaria",
    "aspergillus",
    "alternaria",
    "botrytis",
    "cercospora",
    "cladosporium",
    "colletotrichum",
    "curvularia",
    "cylindrocladium",
    "diplodia",
    "fusarium",
    "ganoderma",
    "glomerella",
    "helminthosporium",
    "macrophomina",
    "mycosphaerella",
    "nectria",
    "penicillium",
    "pestalotia",
    "phoma",
    "phomopsis",
    "phytophthora",
    "pythium",
    "rhizoctonia",
    "sclerotinia",
    "septoria",
    "verticillium",
    "ascochyta",
    "cercoseptoria",
    "phaeoisariopsis",
    "phaeoseptoria",
    "stagonospora",
    "stemphylium",
    "myrothecium",
    "myriogenospora",
    "dactuliophora",
    "dilophospora",
    "coniothecium",
    "coniosporium",
    "cryptostictis",
    "catacauma",
    "botryodiplodia",
    "botryosphaeria",
    "cephalosporium",
    "ceratocystis",
    "chalara",
    "choanephora",
    "clitocybe",
    "coprinus",
    "cordana",
    "corticium",
    "corynespora",
    "coryneum",
    "cylindrocarpon",
    "cylindrocladiella",
    "cylindrosporium",
    "cytospora",
    "cytosporina",
    "dematophora",
    "didymella",
    "dothiorella",
    "drechslera",
    "endothia",
    "eutypa",
    "eutypella",
    "exobasidium",
    "fusicladium",
    "fusicoccum",
    "gibberella",
    "glomerella",
    "gnomonia",
    "graphiola",
    "guignardia",
    "hendersonia",
    "hendersonula",
    "hymenochaete",
    "hypoxylon",
    "lasiodiplodia",
    "leptosphaeria",
    "leucostoma",
    "lophodermium",
    "macrophoma",
    "marasmiellus",
    "marasmius",
    "massaria",
    "monilia",
    "monosporascus",
    "mystrosporium",
    "neocosmospora",
    "nigrospora",
    "omphalia",
    "ophiobolus",
    "ovulinia",
    "ozonium",
    "panagrolaimus",
    "periconia",
    "pestalosphaeria",
    "pestalotiopsis",
    "phialophora",
    "phymatotrichum",
    "physalospora",
    "phytophthora",
    "plasmodiophora",
    "plectosporium",
    "polyporus",
    "poria",
    "pseudocercosporella",
    "pseudopeziza",
    "pseudoseptoria",
    "puccinia",
    "pyrenochaeta",
    "pythium",
    "ramularia",
    "rhizoctonia",
    "rhizopus",
    "rhynchosporium",
    "rosellinia",
    "sclerophthora",
    "sclerotinia",
    "sclerotium",
    "septoria",
    "sphaceloma",
    "sphaeropsis",
    "spongospora",
    "stagonospora",
    "stemphylium",
    "stereum",
    "stigmina",
    "thanatephorus",
    "thielaviopsis",
    "tippula",
    "typhula",
    "ulocladium",
    "uredo",
    "ustilago",
    "valsa",
    "venturia",
    "verticillium",
    "xylaria",
  ];
  for (const genus of fungalGenera) {
    if (lower.includes(genus)) return "fungal";
  }

  // Default to fungal (most plant diseases are fungal)
  return "fungal";
}

// ─── Infer severity ───────────────────────────────────────────────────────────

function inferSeverity(name: string): Severity {
  const lower = name.toLowerCase();
  if (
    lower.includes(" lethal") ||
    lower.includes(" devastating") ||
    lower.includes(" destructive") ||
    lower.includes(" fatal") ||
    lower.includes(" severe") ||
    lower.includes(" blight") ||
    lower.includes(" wilt") ||
    lower.includes(" canker") ||
    lower.includes(" dieback") ||
    lower.includes(" decline") ||
    lower.includes(" rot") ||
    lower.includes(" gall") ||
    lower.includes(" gummosis") ||
    lower.includes(" necrosis") ||
    lower.includes(" erwinia")
  ) {
    return "high";
  }
  if (
    lower.includes(" minor") ||
    lower.includes(" mild") ||
    lower.includes(" slight") ||
    lower.includes(" speckle") ||
    lower.includes(" fleck") ||
    lower.includes(" freckle") ||
    lower.includes(" chlorosis") ||
    lower.includes(" translucence") ||
    lower.includes(" superficial")
  ) {
    return "low";
  }
  return "moderate";
}

// ─── Generate a deterministic slug ────────────────────────────────────────────

function toSlug(name: string): string {
  return (
    "wiki-" +
    name
      .toLowerCase()
      .replace(/[^a-z0-9]+/g, "-")
      .replace(/^-|-$/g, "")
      .replace(/-+/g, "-")
  );
}

// ─── Main ─────────────────────────────────────────────────────────────────────

async function main() {
  const db = getDb();

  // 1. Get existing disease names from DB
  const existingDiseases = await db.select({ name: diseases.name }).from(diseases);
  const existingNames = new Set(existingDiseases.map((d) => d.name.toLowerCase().trim()));

  console.log(`Existing diseases in DB: ${existingNames.size}`);

  // 2. Parse the comprehensive list
  const entries = parseComprehensiveList("/tmp/plant_diseases/plant_diseases_comprehensive.txt");
  console.log(`Total entries in comprehensive file: ${entries.length}`);

  // 3. Find or create catch-all plants
  for (const plantId of ["general", "unknown"]) {
    const existing = await db.select().from(plants).where(eq(plants.id, plantId)).get();

    if (!existing) {
      console.log(`Creating '${plantId}' plant for catch-all diseases...`);
      await db.insert(plants).values({
        id: plantId,
        commonName: plantId === "general" ? "General (Multiple Plants)" : "Unknown Plant",
        scientificName: "Various",
        family: "Various",
        category: "houseplant",
        careSummary:
          plantId === "general"
            ? "General plant diseases affecting multiple species."
            : "Plant disease with unknown host plant.",
        imageUrl: "",
      });
      console.log(`Created '${plantId}' plant.`);
    }
  }

  // 4. Filter new entries (deduplicate within file + against DB)
  const newEntries: DiseaseEntry[] = [];
  const skipped: string[] = [];
  const seen = new Set<string>();

  for (const entry of entries) {
    const key = entry.name.toLowerCase().trim();
    if (seen.has(key)) continue;
    seen.add(key);

    if (existingNames.has(key)) {
      skipped.push(entry.name);
    } else {
      newEntries.push(entry);
    }
  }

  console.log(`\nNew entries to insert: ${newEntries.length}`);
  console.log(`Already existing (skipped): ${skipped.length}`);

  if (skipped.length > 0) {
    console.log(`\nFirst 10 skipped (of ${skipped.length}):`);
    skipped.slice(0, 10).forEach((s) => console.log(`  - ${s}`));
  }

  // 5. Insert new entries in batches
  if (newEntries.length === 0) {
    console.log("\n✅ No new diseases to insert.");
    closeDb();
    return;
  }

  const BATCH_SIZE = 50;
  let inserted = 0;
  let errors = 0;

  for (let i = 0; i < newEntries.length; i += BATCH_SIZE) {
    const batch = newEntries.slice(i, i + BATCH_SIZE);
    const values = batch.map((entry) => {
      const causalAgent = inferCausalAgent(entry.name);
      const severity = inferSeverity(entry.name);
      return {
        id: toSlug(entry.name),
        plantId: "general",
        name: entry.name,
        scientificName: "",
        causalAgentType: causalAgent,
        description: `A plant disease known as "${entry.name}". Source: Wikipedia.`,
        symptoms: [],
        causes: [],
        treatment: [],
        prevention: [],
        lookalikeIds: [],
        severity,
        sourceUrl: entry.sourceUrl,
        imageUrl: "",
      };
    });

    try {
      await db.insert(diseases).values(values).onConflictDoNothing();
      inserted += values.length;
    } catch (err) {
      // Fall back to individual inserts for this batch if batch fails
      console.log(`  Batch failed, trying individually...`);
      for (const val of values) {
        try {
          await db.insert(diseases).values(val).onConflictDoNothing();
          inserted++;
        } catch (e2) {
          // If it's a duplicate key, count it as skipped
          if (String(e2).includes("UNIQUE") || String(e2).includes("duplicate")) {
            // Already handled by onConflictDoNothing, shouldn't happen
            inserted++;
          } else {
            console.error(`  Error inserting "${val.name}":`, e2);
            errors++;
          }
        }
      }
    }

    if ((i + BATCH_SIZE) % 200 === 0 || i + BATCH_SIZE >= newEntries.length) {
      console.log(
        `  Progress: ${Math.min(i + BATCH_SIZE, newEntries.length)}/${newEntries.length} (${inserted} inserted, ${errors} errors)`,
      );
    }
  }

  // 6. Summary
  const totalDiseases = await db
    .select({ count: sql<number>`COUNT(*)` })
    .from(diseases)
    .get();
  const totalPlants = await db
    .select({ count: sql<number>`COUNT(*)` })
    .from(plants)
    .get();

  console.log(`\n📊 Results:`);
  console.log(`   Inserted: ${inserted}`);
  console.log(`   Errors: ${errors}`);
  console.log(`   Skipped (already existed): ${skipped.length}`);
  console.log(`\n📊 Database now has:`);
  console.log(`   ${totalPlants?.count ?? 0} plants`);
  console.log(`   ${totalDiseases?.count ?? 0} diseases`);

  closeDb();
}

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