analytics: add crawler tracking, pretty UA/IP display and copy-to-clipboard

frontend/src/analytics/format.js

@@ -3,6 +3,38 @@
  * visit trail.
  */
 
+/**
+ * IPv4 unchanged, IPv6 returns the /64 network prefix in compact form.
+ * Falls back to the original value when parsing fails.
+ */
+export const hostIP = (ip) => {
+  try {
+    if (!ip || !ip.includes(':')) return ip
+    const strip = (s) => s.replace(/^\[|\]$/g, '')
+    const norm = strip(new URL(`http://[${ip}]/`).hostname)
+    const [l, r] = norm.split('::').map((s) => (s ? s.split(':') : []))
+    const full = r
+      ? [...l, ...Array(8 - l.length - r.length).fill('0'), ...r]
+      : l
+    return strip(
+      new URL(`http://[${full.slice(0, 4).join(':')}::]/`).hostname,
+    ).replace(/::$/, '')
+  } catch (e) {
+    console.error('hostIP processing failed for:', ip, e)
+    return ip
+  }
+}
+
+/** Copy the full IP to the clipboard, ignoring failures. */
+export async function copyIp(ip) {
+  if (!ip) return
+  try {
+    await navigator.clipboard.writeText(ip)
+  } catch {
+    /* ignore */
+  }
+}
+
 /** Total page views across every page and every bucket. */
 export function calcTotalViews(views) {
   let n = 0
@@ -87,6 +119,37 @@ export function formatCounts(entries) {
   return entries.map(([value, count]) => `${value} (${count})`).join(', ')
 }
 
+/**
+ * Count distinct User-Agent strings among crawler hits, most common first.
+ * Returns an array of [ua, count] pairs.
+ */
+export function countCrawlerUas(crawlers) {
+  const counts = {}
+  for (const c of crawlers || []) {
+    const value = c.ua_pretty || c.ua || '(no UA)'
+    counts[value] = (counts[value] || 0) + 1
+  }
+  return Object.entries(counts).sort((a, b) => b[1] - a[1])
+}
+
+/**
+ * Format raw crawler hit records as rows for a technical table.  Missing
+ * values become "—".
+ */
+export function formatCrawlerRows(crawlers) {
+  const dash = (s) => (s || '—')
+  return [...(crawlers || [])].reverse().map((c) => ({
+    when: new Date(c.start).toLocaleString(),
+    entry: dash(c.entry),
+    ip: c.ip || '',
+    ipDisplay: c.host || hostIP(c.ip) || c.ip || '—',
+    ua: c.ua_pretty || c.ua || '—',
+    uaRaw: c.ua || '',
+    referer: dash(c.referer),
+    query: dash(c.query),
+  }))
+}
+
 /**
  * Format raw visit records as rows for a technical table.  Returns objects
  * with display strings; missing values become "—".  ``trail`` joins page
@@ -110,11 +173,13 @@ export function formatVisitRows(visits, pageTree) {
       when: new Date(v.start).toLocaleString(),
       trail,
       referer: dash(v.referer),
-      ip: dash(v.ip),
+      ip: v.ip || '',
+      ipDisplay: v.host || hostIP(v.ip) || v.ip || '—',
       host: dash(v.host),
       lang: dash(v.lang),
       country: dash(v.country),
-      ua: dash(v.ua),
+      ua: v.ua_pretty || v.ua || '—',
+      uaRaw: v.ua || '',
       utm: utm || '—',
     }
   })