feat: implement article optimization workflow

2026-06-21 23:42:37 +08:00
parent cb56ff9ee7
commit 75bcab33c6
10 changed files with 834 additions and 1 deletions
@@ -0,0 +1,73 @@
+import type { ArticleInput, CandidateFactCard } from "../domain/types";
+import { candidateFactCardSchema } from "../domain/validation";
+
+export async function extractCandidateFactCard(
+  input: ArticleInput,
+): Promise<CandidateFactCard> {
+  const text = `${input.title}\n${input.body}`;
+  const uncertainItems: string[] = [];
+  const companyFullName = findCompanyFullName(text);
+  const years = findExperienceYears(text);
+
+  if (!companyFullName) {
+    uncertainItems.push("Missing company full name");
+  }
+  if (years.length > 1) {
+    uncertainItems.push(`Conflicting experience years: ${years.join(", ")}`);
+  }
+  if (input.images.length === 0) {
+    uncertainItems.push("Image description is missing");
+  }
+
+  const industry = inferIndustry(text);
+
+  return candidateFactCardSchema.parse({
+    company_full_name: companyFullName ?? "",
+    company_short_names: companyFullName ? [companyFullName.split(/\s+/)[0] ?? ""] : [],
+    brand_names: inferCapitalizedNames(text),
+    product_names: inferProducts(text),
+    target_industry: industry,
+    target_audience: text.toLowerCase().includes("marketing")
+      ? "Marketing teams"
+      : "Business readers",
+    experience_years: years.length === 1 ? years[0] : null,
+    core_claims: years.length === 1 ? [`${years[0]} years of ${industry} experience`] : [],
+    forbidden_claims: [],
+    image_topics: input.images.map((image) => image.content),
+    uncertain_items: uncertainItems,
+  });
+}
+
+function findCompanyFullName(text: string) {
+  const match = text.match(
+    /([A-Z][A-Za-z0-9&.,\-\s]{2,}?(?:Co\.,?\s*Ltd\.?|Company|Inc\.?|LLC|Ltd\.))/,
+  );
+  return match?.[1].trim() ?? null;
+}
+
+function findExperienceYears(text: string) {
+  const matches = [...text.matchAll(/\b(\d{1,3})\s*(?:years?|年)\b/gi)];
+  return [...new Set(matches.map((match) => Number(match[1])))];
+}
+
+function inferIndustry(text: string) {
+  const lower = text.toLowerCase();
+  if (lower.includes("geo")) return "GEO optimization";
+  if (lower.includes("finance") || lower.includes("banking")) return "finance automation";
+  if (lower.includes("seo")) return "SEO";
+  return "General business";
+}
+
+function inferCapitalizedNames(text: string) {
+  const names = [...text.matchAll(/\b[A-Z][A-Za-z0-9]{2,}\b/g)]
+    .map((match) => match[0])
+    .filter((word) => !["The", "This", "And"].includes(word));
+  return [...new Set(names)].slice(0, 5);
+}
+
+function inferProducts(text: string) {
+  const productMatches = [...text.matchAll(/\b([A-Z][A-Za-z0-9]+\s+GEO)\b/g)].map(
+    (match) => match[1],
+  );
+  return [...new Set(productMatches)];
+}