import { join } from 'node:path';

import {
  createEmbedder,
  hasFlag,
  loadRagRuntime,
  readArg,
  readConfig,
  repoRoot,
} from './rag-utils.mjs';

const config = readConfig();
const query = readArg(process.argv, '--query') ?? process.argv.slice(2).join(' ');
const limit = Number(readArg(process.argv, '--limit', '8'));
const maxChars = Number(readArg(process.argv, '--max-chars', '12000'));
const format = readArg(process.argv, '--format', 'context');
const includeText = !hasFlag(process.argv, '--no-text');

if (!query) {
  throw new Error(
    'Usage: node scripts/rag/search-docs.mjs --query "搜索内容" [--limit 8] [--format context|json|jsonl|text] [--max-chars 12000]',
  );
}

if (!['context', 'json', 'jsonl', 'text'].includes(format)) {
  throw new Error(`Unsupported --format value: ${format}`);
}

if (!Number.isFinite(limit) || limit <= 0 || !Number.isInteger(limit)) {
  throw new Error(`Invalid --limit value: ${limit}`);
}

if (!Number.isFinite(maxChars) || maxChars <= 0 || !Number.isInteger(maxChars)) {
  throw new Error(`Invalid --max-chars value: ${maxChars}`);
}

const { lancedb, transformers } = await loadRagRuntime(config);
const embed = await createEmbedder(transformers, config.model);
const queryVector = await embed(query, 'query');

const db = await lancedb.connect(join(repoRoot, config.databaseDir));
const table = await db.openTable(config.tableName);
const rawResults = await table
  .vectorSearch(queryVector)
  .select(['id', 'path', 'title', 'chunk_index', 'source_weight', 'text', '_distance'])
  .limit(Math.max(limit * 3, limit))
  .toArray();

const results = rawResults
  .map((row) => ({
    ...row,
    score: (1 / (1 + Number(row._distance ?? 0))) * Number(row.source_weight ?? 1),
  }))
  .sort((a, b) => b.score - a.score)
  .slice(0, limit);

const payload = buildAgentPayload(query, results, {
  model: config.model,
  tableName: config.tableName,
  maxChars,
  includeText,
});

if (format === 'json') {
  console.log(JSON.stringify(payload, null, 2));
} else if (format === 'jsonl') {
  for (const result of payload.results) {
    console.log(JSON.stringify(result));
  }
} else if (format === 'text') {
  printTextResults(payload.results);
} else {
  console.log(formatContextPack(payload));
}

function buildAgentPayload(searchQuery, rows, options) {
  const outputRows = [];
  let remainingChars = options.maxChars;

  for (const [index, row] of rows.entries()) {
    const source = `${row.path}#${row.chunk_index}`;
    const text = String(row.text ?? '').trim();
    const result = {
      rank: index + 1,
      id: row.id,
      source,
      path: row.path,
      title: row.title,
      chunkIndex: Number(row.chunk_index),
      score: Number(row.score),
      distance: Number(row._distance ?? 0),
      sourceWeight: Number(row.source_weight ?? 1),
    };

    if (options.includeText) {
      const capped = capText(text, Math.max(0, remainingChars));
      result.text = capped.text;
      result.truncated = capped.truncated;
      remainingChars -= result.text.length;
    }

    outputRows.push(result);
  }

  return {
    kind: 'genarrative-rag-context',
    query: searchQuery,
    generatedAt: new Date().toISOString(),
    model: options.model,
    table: options.tableName,
    maxChars: options.maxChars,
    remainingChars,
    resultCount: outputRows.length,
    usage: [
      'This context pack is primarily for Agent consumption.',
      'Use sources as candidate context and inspect authoritative files before editing when exact line-level changes matter.',
      'Prefer docs/project-memory and current docs over stale historical notes when sources conflict.',
    ],
    results: outputRows,
  };
}

function capText(text, budget) {
  if (budget <= 0) {
    return { text: '', truncated: text.length > 0 };
  }
  if (text.length <= budget) {
    return { text, truncated: false };
  }
  return { text: `${text.slice(0, Math.max(0, budget - 18)).trimEnd()}\n[TRUNCATED]`, truncated: true };
}

function formatContextPack(payload) {
  const lines = [
    '# Genarrative RAG Context',
    '',
    `query: ${payload.query}`,
    `model: ${payload.model}`,
    `results: ${payload.resultCount}`,
    `maxChars: ${payload.maxChars}`,
    '',
    '## Agent Usage',
    '',
    '- This context pack is primarily for Agent consumption.',
    '- Treat sources as candidate context; inspect authoritative files before exact edits.',
    '- If sources conflict, prefer current code and current docs over stale historical notes.',
    '',
    '## Sources',
    '',
  ];

  for (const result of payload.results) {
    lines.push(
      `${result.rank}. ${result.source} score=${result.score.toFixed(4)} distance=${result.distance.toFixed(4)} title=${result.title}`,
    );
  }

  lines.push('', '## Context', '');

  for (const result of payload.results) {
    const fence = buildMarkdownFence(result.text ?? '');
    lines.push(
      `### [${result.rank}] ${result.title}`,
      '',
      `source: ${result.source}`,
      `score: ${result.score.toFixed(4)}`,
      '',
      `${fence}text`,
      result.text ?? '',
      fence,
      '',
    );
  }

  return lines.join('\n');
}

function buildMarkdownFence(text) {
  const longest = Math.max(3, ...Array.from(text.matchAll(/`+/gu), (match) => match[0].length));
  return '`'.repeat(longest + 1);
}

function printTextResults(rows) {
  for (const result of rows) {
    const preview = String(result.text ?? '').replace(/\s+/gu, ' ').slice(0, 260);
    console.log(
      [
        `${result.rank}. ${result.source}`,
        `   title: ${result.title}`,
        `   score: ${result.score.toFixed(4)} distance: ${result.distance.toFixed(4)}`,
        `   ${preview}`,
      ].join('\n'),
    );
  }
}