Expose source candidates and unresolved classification gaps

apps/docs/src/components/AICompanyResearch.tsx

@@ -3,6 +3,7 @@ import { useRouter } from "next/router";
 import IncomeDistribution from "./IncomeDistribution";
 import ArrDisclosures from "./ArrDisclosures";
 import BusinessModelAssessment from "./BusinessModelAssessment";
+import ResearchCandidates from "./ResearchCandidates";
 import {
   categorySummary, evidenceUrl, technicalReviewLabels, reviewCompanyIds, type ResearchEvidence, type ResearchReview, type ResearchSnapshot,
 } from "@/lib/ai-research";
@@ -57,7 +58,7 @@ export default function AICompanyResearch() {
     : router.isReady && typeof linkedCompany === "string" && data?.companies.some((c) => c.id === linkedCompany)
       ? linkedCompany : null;
   function setSelected(id: string | null) { setSelection({ route: router.asPath, id }); }
-  const [tab, setTab] = useState<"companies" | "revenue" | "models" | "sources" | "reviews">("companies");
+  const [tab, setTab] = useState<"companies" | "candidates" | "revenue" | "models" | "sources" | "reviews">("companies");
   const companySection = useRef<HTMLElement>(null);
   const detailSection = useRef<HTMLElement>(null);
   useEffect(() => {
@@ -129,7 +130,7 @@ export default function AICompanyResearch() {
     <section ref={companySection} className="research-section" aria-labelledby="research-records-title">
       <h2 id="research-records-title">研究数据</h2>
       <div className="research-tabs" role="group" aria-label="研究数据视图">
-        {([['companies','公司与产品'],['revenue','收入观测'],['models','商业模式初评'],['sources','原始证据'],['reviews','核查记录']] as const).map(([id,label]) =>
+        {([['companies','公司与产品'],['candidates','候选与缺项'],['revenue','收入观测'],['models','商业模式初评'],['sources','原始证据'],['reviews','核查记录']] as const).map(([id,label]) =>
           <button key={id} aria-pressed={tab === id} onClick={() => setTab(id)}>{label}</button>)}
       </div>
       {tab === "companies" && <>
@@ -155,6 +156,7 @@ export default function AICompanyResearch() {
         {filtered.length > pageSize && <nav className="research-pagination" aria-label="公司数据分页"><button disabled={page === 0} onClick={() => setPage((n) => n - 1)}>上一页</button><span>{page + 1} / {Math.ceil(filtered.length / pageSize)}</span><button disabled={(page + 1) * pageSize >= filtered.length} onClick={() => setPage((n) => n + 1)}>下一页</button></nav>}
       </>}
       {tab === "models" && <BusinessModelAssessment data={data} onSelect={setSelected} onChooseCategory={chooseCategory} />}
+      {tab === "candidates" && <ResearchCandidates data={data} onSelect={setSelected} onChooseCategory={chooseCategory} />}
       {tab === "revenue" && <>
         <IncomeDistribution data={data} onSelect={setSelected} />
         <ArrDisclosures data={data} onSelect={setSelected} />

apps/docs/src/components/ResearchCandidates.tsx

@@ -0,0 +1,75 @@
+import { useMemo, useState } from "react";
+import { evidenceUrl, type ResearchCandidateBatch, type ResearchSnapshot } from "@/lib/ai-research";
+
+type CandidateStatus = ResearchCandidateBatch["records"][number]["status"];
+const statusLabels: Record<CandidateStatus, string> = {
+  "pending-year": "成立年或主体待核", "pending-ai": "AI 主营待核", linked: "已关联公司",
+  "existing-outside-cohort": "已关联范围外对照", "outside-cohort": "范围外候选", promotion: "推广活动",
+};
+const pageSize = 20;
+const sourceNames: Record<string, string> = {
+  S01: "Y Combinator", S02: "TechCrunch AI", S04: "Product Hunt", S05: "Sacra",
+  S10: "机器之心", S11: "36氪", S13: "TrustMRR", S14: "a16z Speedrun",
+};
+const sourceLabel = (id: string) => `${id} · ${sourceNames[id] ?? "其他来源"}`;
+
+function SourceLink({ url, label }: { url: string | null; label: string }) {
+  const safe = url && evidenceUrl(url);
+  return safe ? <a href={safe} target="_blank" rel="noopener noreferrer">{label} ↗</a> : <span>{label}（链接未取得）</span>;
+}
+
+export default function ResearchCandidates({ data, onSelect, onChooseCategory }: {
+  data: ResearchSnapshot; onSelect: (id: string) => void; onChooseCategory: (id: string) => void;
+}) {
+  const [source, setSource] = useState("");
+  const [batchId, setBatchId] = useState("");
+  const [category, setCategory] = useState("");
+  const [status, setStatus] = useState<CandidateStatus | "pending" | "">("pending");
+  const [query, setQuery] = useState("");
+  const [page, setPage] = useState(0);
+  const all = useMemo(() => (data.candidateBatches ?? []).flatMap((batch) => batch.records.map((record) => ({ batch, record }))), [data.candidateBatches]);
+  const sources = [...new Set(all.map(({ batch }) => batch.sourceId))].sort();
+  const batches = (data.candidateBatches ?? []).filter((batch) => !source || batch.sourceId === source);
+  const matched = all.filter(({ batch, record }) => (!source || batch.sourceId === source)
+    && (!batchId || batch.id === batchId) && (!category || record.categoryId === category)
+    && `${record.name} ${record.id} ${record.note}`.toLocaleLowerCase().includes(query.trim().toLocaleLowerCase()));
+  const pending = (value: CandidateStatus) => value === "pending-year" || value === "pending-ai";
+  const rows = matched.filter(({ record }) => !status || (status === "pending" ? pending(record.status) : record.status === status));
+  const companies = new Map(data.companies.map((company) => [company.id, company]));
+  const evidence = new Map(data.evidence.map((item) => [item.id, item]));
+  const categories = new Map(data.categories.map((item) => [item.id, item.name]));
+  return <section aria-labelledby="research-candidates-title">
+    <h3 id="research-candidates-title">候选与缺项</h3>
+    <p>展示已登记的有限来源批次及后续核查。默认显示成立年、主体或 AI 主营待核的条目；待核不是确认排除，也不计入公司表。每行是一次发现位置，同一公司或产品可以重复出现。</p>
+    <p className="research-muted">候选初分类与公司表数量分开，来源批次不等全年或全站名单。原始发现范围及后续结论见每行说明；暂无收入资料不作零，推广活动也不算公司。</p>
+    <div className="research-filters">
+      <label className="research-query">搜索候选<input type="search" value={query} placeholder="名称、编号或核查说明" onChange={(event) => { setQuery(event.target.value); setPage(0); }} /></label>
+      <label>发现来源<select value={source} onChange={(event) => { setSource(event.target.value); setBatchId(""); setPage(0); }}><option value="">全部已登记来源</option>{sources.map((id) => <option key={id} value={id}>{sourceLabel(id)}</option>)}</select></label>
+      <label>发现批次<select value={batchId} onChange={(event) => { setBatchId(event.target.value); setPage(0); }}><option value="">全部批次</option>{batches.map((batch) => <option key={batch.id} value={batch.id}>{batch.id}</option>)}</select></label>
+      <label>候选初分类<select value={category} onChange={(event) => { setCategory(event.target.value); setPage(0); }}><option value="">全部分类</option>{data.categories.map((item) => <option key={item.id} value={item.id}>{item.name}</option>)}</select></label>
+      <label>核查状态<select value={status} onChange={(event) => { setStatus(event.target.value as typeof status); setPage(0); }}>
+        <option value="">全部状态（{matched.length}）</option><option value="pending">全部待核（{matched.filter(({ record }) => pending(record.status)).length}）</option>
+        {Object.entries(statusLabels).map(([id, label]) => <option key={id} value={id}>{label}（{matched.filter(({ record }) => record.status === id).length}）</option>)}
+      </select></label>
+    </div>
+    <p role="status">{rows.length} 个发现位置匹配；不是独立公司数。</p>
+    <div className="research-table-wrap"><table>
+      <caption>有限来源候选与处理记录；选择关联公司查看主数据，原始证据直接链接来源</caption>
+      <thead><tr><th scope="col">候选</th><th scope="col">初分类 / 状态</th><th scope="col">来源及范围</th><th scope="col">核查结论 / 缺项</th><th scope="col">关联公司 / 证据</th></tr></thead>
+      <tbody>{rows.slice(page * pageSize, (page + 1) * pageSize).map(({ batch, record }) => {
+        const company = record.companyId && companies.get(record.companyId);
+        return <tr key={record.id}>
+          <td><SourceLink url={record.url} label={record.name} /><small>{record.id}</small></td>
+          <td><button onClick={() => onChooseCategory(record.categoryId)} aria-label={`查看${categories.get(record.categoryId)}分类内的公司`}>{categories.get(record.categoryId)}</button><small>{statusLabels[record.status]}</small></td>
+          <td><SourceLink url={batch.url} label={sourceLabel(batch.sourceId)} /><small>{batch.id} · 读取 {batch.accessedAt}</small><details><summary>发现批次范围</summary><p>{batch.scope}</p><p>{batch.complete ? "该批次标记已完成；不代表来源全站覆盖。" : "该批次仍保留覆盖缺项。"}</p></details></td>
+          <td>{record.note}</td>
+          <td>{company ? <button className="research-company-name" onClick={() => onSelect(company.id)}>{company.name}</button> : <small>尚未关联公司主记录</small>}
+            {record.evidenceIds?.map((id) => { const item = evidence.get(id); return item ? <p key={id}><SourceLink url={item.url} label={id} /></p> : null; })}
+          </td>
+        </tr>;
+      })}</tbody>
+    </table></div>
+    {!rows.length && <p>当前筛选没有已登记的候选记录；不代表该来源或分类没有公司。</p>}
+    {rows.length > pageSize && <nav className="research-pagination" aria-label="候选与缺项分页"><button disabled={page === 0} onClick={() => setPage((value) => value - 1)}>上一页</button><span>{page + 1} / {Math.ceil(rows.length / pageSize)}</span><button disabled={(page + 1) * pageSize >= rows.length} onClick={() => setPage((value) => value + 1)}>下一页</button></nav>}
+  </section>;
+}