/**
 * Deduplication utilities for palace memories.
 *
 * Detects near-duplicate content using cosine similarity over embeddings.
 * Products handle the Cosmos/DB queries; this module operates on pure data.
 */

import { cosineSimilarity } from './cosine.js';

/**
 * Check if a candidate embedding is a near-duplicate of any existing embedding.
 *
 * @param candidate - Embedding of the new memory
 * @param existingEmbeddings - Embeddings of existing memories in the same room/hall
 * @param threshold - Cosine similarity threshold (default: 0.90)
 * @returns true if any existing embedding exceeds the threshold
 */
export function isContentDuplicate(
  candidate: number[],
  existingEmbeddings: number[][],
  threshold = 0.9
): boolean {
  for (const existing of existingEmbeddings) {
    if (existing.length !== candidate.length) continue;
    if (cosineSimilarity(candidate, existing) > threshold) {
      return true;
    }
  }
  return false;
}

/**
 * Check if two text strings are exact duplicates after normalization.
 * Trims whitespace and lowercases before comparison.
 */
export function isExactDuplicate(a: string, b: string): boolean {
  return a.trim().toLowerCase() === b.trim().toLowerCase();
}

/**
 * Find the most similar embedding and return its index + score.
 * Returns null if no embeddings exist or none exceed minScore.
 */
export function findClosestMatch(
  candidate: number[],
  existingEmbeddings: number[][],
  minScore = 0
): { index: number; score: number } | null {
  let bestIndex = -1;
  let bestScore = minScore;

  for (let i = 0; i < existingEmbeddings.length; i++) {
    const existing = existingEmbeddings[i];
    if (existing.length !== candidate.length) continue;

    const score = cosineSimilarity(candidate, existing);
    if (score > bestScore) {
      bestScore = score;
      bestIndex = i;
    }
  }

  return bestIndex >= 0 ? { index: bestIndex, score: bestScore } : null;
}