feat(amazon-shopping): parse filters and extract search candidates

skills/amazon-shopping/src/query-parser.ts

@@ -0,0 +1,68 @@
+import type { ParsedNaturalLanguageRequest, ProductFilters } from "./types.js";
+
+function cleanQuery(text: string): string {
+  return text
+    .replace(/\b(?:that|and|with|have)\b/gi, " ")
+    .replace(/\s+/g, " ")
+    .replace(/\s+(and|or|a)$/i, "")
+    .trim();
+}
+
+function removeMatched(text: string, match: RegExpMatchArray | null): string {
+  if (!match) {
+    return text;
+  }
+  return text.replace(match[0], " ");
+}
+
+export function parseNaturalLanguageRequest(input: string): ParsedNaturalLanguageRequest {
+  let remaining = input.trim();
+  const filters: ProductFilters = {
+    includeKeywords: [],
+    excludeKeywords: []
+  };
+  let limit: number | undefined;
+
+  const limitMatch = remaining.match(/\b(?:return|limit|top)\s+(\d{1,3})\b/i);
+  if (limitMatch) {
+    limit = Number(limitMatch[1]);
+    remaining = removeMatched(remaining, limitMatch);
+  }
+
+  const unitPriceMatch = remaining.match(/\b(?:cost\s+)?(?:less than|under|below)\s+\$([0-9]+(?:\.[0-9]{1,2})?)\s*(?:each|per\b|\/\s*(?:count|unit|item))\b/i);
+  if (unitPriceMatch) {
+    filters.maxUnitPrice = Number(unitPriceMatch[1]);
+    remaining = removeMatched(remaining, unitPriceMatch);
+  }
+
+  const maxPriceMatch = remaining.match(/\b(?:cost\s+)?(?:less than|under|below)\s+\$([0-9]+(?:\.[0-9]{1,2})?)\b/i);
+  if (maxPriceMatch) {
+    filters.maxPrice = Number(maxPriceMatch[1]);
+    remaining = removeMatched(remaining, maxPriceMatch);
+  }
+
+  const exclusiveReviews = remaining.match(/\b(?:over|more than|above)\s+([0-9][0-9,]*)\s*(?:reviews?|ratings?)\b/i);
+  const inclusiveReviews = remaining.match(/\b(?:at least|minimum|min\.?)\s+([0-9][0-9,]*)\s*(?:reviews?|ratings?)\b/i);
+  const reviewMatch = exclusiveReviews ?? inclusiveReviews;
+  if (reviewMatch) {
+    filters.minReviews = Number(reviewMatch[1].replace(/,/g, ""));
+    filters.reviewCountComparison = exclusiveReviews ? "gt" : "gte";
+    remaining = removeMatched(remaining, reviewMatch);
+  }
+
+  const exclusiveRating = remaining.match(/\b(?:a\s+)?(?:review score of\s+)?(?:more than|over|above|rated above)\s+([0-5](?:\.[0-9])?)\s*(?:stars?)?\b/i);
+  const inclusiveRating = remaining.match(/\b([0-5](?:\.[0-9])?)\s*stars?\s+or\s+better\b/i)
+    ?? remaining.match(/\b(?:at least|minimum|min\.?)\s+([0-5](?:\.[0-9])?)\s*(?:stars?|rating)?\b/i);
+  const ratingMatch = exclusiveRating ?? inclusiveRating;
+  if (ratingMatch) {
+    filters.minRating = Number(ratingMatch[1]);
+    filters.ratingComparison = exclusiveRating ? "gt" : "gte";
+    remaining = removeMatched(remaining, ratingMatch);
+  }
+
+  return {
+    query: cleanQuery(remaining),
+    filters,
+    limit
+  };
+}