/* WPSiteBeam Scanner — Sitemap Tab Auto-split from Scanner.jsx. */ (function () { 'use strict'; const ScanEmptyState = window.ScanEmptyState; const Icon = window.Icon; function ScannerSitemapTab({ data, payloads }) { const { useState, useMemo } = React; /* Hooks first (Rules of Hooks) */ const [filter, setFilter] = useState(''); const [collapsedGroups, setCollapsedGroups] = useState({}); const [showExtras, setShowExtras] = useState(false); /* 2026-05-18 v4 per Jordan: track if user has manually toggled any group, so the default-collapse for large sites doesn't override their choice. */ const [userToggled, setUserToggled] = useState(false); /* Filter out non-page protocol URLs that sometimes leak into sitemap data from anchor extraction. tel:/mailto:/sms:/javascript:/# are interactive links, not navigable pages — they shouldn't appear in a site map. Also filter empty/null paths defensively. The filter is conservative: we keep anything that starts with / or http (real URLs) and reject the known-bad protocols by prefix match. */ const PROTOCOL_BLOCKLIST = ['tel:', 'mailto:', 'sms:', 'javascript:', 'data:', 'callto:', 'fax:']; const rawSitemap = Array.isArray(data?.sitemap) ? data.sitemap : []; const sitemap = rawSitemap.filter(n => { if (!n || typeof n.p !== 'string') return false; const path = n.p.trim(); if (!path || path === '#') return false; const lower = path.toLowerCase(); for (const proto of PROTOCOL_BLOCKLIST) { if (lower.startsWith(proto)) return false; } return true; }); const totalPages = data?.pages || sitemap.length; /* 2026-05-18 v4 per Jordan: extract "discovered extras" — URLs the scanner crawled that aren't in the published sitemap.xml. Previously we only teased "...and N more pages discovered" without letting users see them. Source: data._raw.urls (the raw crawl list from Railway). Diff against sitemap paths; result is shown in a collapsible section at the bottom. If _raw.urls isn't available (older scans), fall back to the teaser. */ const discoveredExtras = useMemo(() => { const rawUrls = Array.isArray(data?._raw?.urls) ? data._raw.urls : []; if (rawUrls.length === 0) return []; // Build a Set of sitemap paths for O(1) lookup const sitemapPaths = new Set(sitemap.map(n => n.p.replace(/\/$/, ''))); // Get domain for stripping host portion const siteDomain = (data?.site || '').replace(/^https?:\/\//, '').replace(/\/$/, ''); const extras = []; for (const u of rawUrls) { try { const url = typeof u === 'string' ? u : (u.url || u.href || ''); if (!url) continue; const parsed = new URL(url); // Only same-domain if (siteDomain && !parsed.hostname.includes(siteDomain.replace(/^www\./, ''))) continue; const path = parsed.pathname.replace(/\/$/, '') || '/'; if (!sitemapPaths.has(path)) { extras.push({ path, url }); } } catch(e) { /* skip malformed */ } } return extras; }, [data?._raw?.urls, sitemap.length, data?.site]); /* Build a path → label + group map. Small sites (≤20 pages): flat list, no grouping overhead. Larger sites: group by first path segment, collapsible sections. Home is always shown un-grouped at the top. */ const SMALL_SITE_THRESHOLD = 20; const LARGE_SITE_THRESHOLD = 30; const useGroupedView = sitemap.length > SMALL_SITE_THRESHOLD; const isLargeSite = sitemap.length > LARGE_SITE_THRESHOLD; /* Derived structure: {home: node, groups: [{key, label, pages: []}]} */ const structured = useMemo(() => { const home = sitemap.find(n => n.p === '/') || null; const nonHome = sitemap.filter(n => n.p !== '/'); /* Filter by text if provided */ const normalized = filter.trim().toLowerCase(); const matchesFilter = (n) => !normalized || n.p.toLowerCase().includes(normalized); if (!useGroupedView) { /* Flat list for small sites */ return { mode: 'flat', home: home && matchesFilter(home) ? home : null, pages: nonHome.filter(matchesFilter), }; } /* Grouped by first path segment (e.g. /blog/post → "blog" group) */ const groups = {}; nonHome.filter(matchesFilter).forEach(n => { const segments = n.p.split('/').filter(Boolean); const groupKey = segments[0] || 'root'; if (!groups[groupKey]) groups[groupKey] = []; groups[groupKey].push(n); }); const sortedGroups = Object.keys(groups).sort().map(key => ({ key, label: key === 'root' ? 'Top level' : `/${key}`, pages: groups[key].sort((a, b) => a.p.localeCompare(b.p)), })); return { mode: 'grouped', home: home && matchesFilter(home) ? home : null, groups: sortedGroups, }; }, [sitemap, filter, useGroupedView]); const shownCount = structured.mode === 'flat' ? (structured.home ? 1 : 0) + structured.pages.length : (structured.home ? 1 : 0) + structured.groups.reduce((n, g) => n + g.pages.length, 0); function toggleGroup(key) { setUserToggled(true); setCollapsedGroups(s => ({ ...s, [key]: !s[key] })); } function isGroupCollapsed(key) { // If user has explicitly toggled groups, respect their state. // Otherwise, large sites default to collapsed so the page isn't an endless scroll. if (userToggled) return !!collapsedGroups[key]; if (isLargeSite) return collapsedGroups[key] === undefined ? true : !!collapsedGroups[key]; return !!collapsedGroups[key]; } function expandAll() { setUserToggled(true); const allKeys = structured.mode === 'grouped' ? Object.fromEntries(structured.groups.map(g => [g.key, false])) : {}; setCollapsedGroups(allKeys); } function collapseAll() { setUserToggled(true); const allKeys = structured.mode === 'grouped' ? Object.fromEntries(structured.groups.map(g => [g.key, true])) : {}; setCollapsedGroups(allKeys); } function renderPageRow(n, isHome = false, indent = 0) { const label = isHome ? 'Home' : n.p; return (
{isHome ? '●' : '└─'} e.currentTarget.style.color = 'var(--beam)'} onMouseLeave={e => e.currentTarget.style.color = ''}> {label} {isHome && /}
); } return (

Sitemap · {totalPages} pages

FROM /sitemap.xml
{/* Filter — only shown when grouped view is in use (large sites) */} {useGroupedView && (
setFilter(e.target.value)} placeholder="Filter paths…" aria-label="Filter sitemap paths" style={{ width:'100%', padding:'6px 10px', background:'var(--surface-2, rgba(255,255,255,0.04))', border:'1px solid var(--border)', borderRadius:4, color:'var(--text)', fontSize:'.76rem', fontFamily:'var(--font-mono)', }} />
Showing {shownCount} of {sitemap.length} sitemap entries {isLargeSite ? ' · groups collapsed by default for large sites' : ''}
{/* 2026-05-18 v4 per Jordan: expand-all / collapse-all controls so users can quickly toggle visibility for large sitemaps. */} {isLargeSite && (
)}
)}
{sitemap.length === 0 && (
No sitemap entries available.
)} {/* Home row — always first, always visible */} {structured.home && renderPageRow(structured.home, true, 0)} {/* Flat list mode (small sites) */} {structured.mode === 'flat' && structured.pages.map(n => renderPageRow(n, false, 20))} {/* Grouped mode (large sites) */} {structured.mode === 'grouped' && structured.groups.map(group => { const isCollapsed = isGroupCollapsed(group.key); return (
{!isCollapsed && group.pages.map(n => renderPageRow(n, false, 20))}
); })} {shownCount === 0 && filter && (
No paths match "{filter}".
)} {/* 2026-05-18 v4 per Jordan: actual discovered-extras list (was a tease). Replaces "...and N more pages discovered (not in sitemap.xml)" with a collapsible section that LISTS the URLs. Pulls from _raw.urls diffed against sitemap paths. If _raw.urls isn't available (older scans), falls back to the original teaser line. */} {discoveredExtras.length > 0 ? (
{showExtras && (
These URLs were crawled by WPSiteBeam but aren't listed in sitemap.xml. Consider adding them so search engines can index them properly.
{discoveredExtras.map((extra, i) => (
e.currentTarget.style.color = 'var(--text)'} onMouseOut={e => e.currentTarget.style.color = 'var(--muted)'}> {extra.path}
))}
)}
) : (totalPages > sitemap.length && (
…and {totalPages - sitemap.length} more pages discovered during the scan (not in sitemap.xml)
))}
); } /* ═════════════════════════════════════════════════════════════════════ PagesTab — per-page content viewer (v1 parity) Renders a left-sidebar page selector + right content panel showing per-page Identity, SEO, Headings, Content, and Images. Data comes from data.pagesList[] populated by enrichPagesData() — each entry has {url, label, menu_name, title, description, meta, headings, content, images, content_length, image_count, heading_count}. Migration-focused features: • Per-page content export: JSON bundle of all page data • Per-page image download: ZIP of just this page's images • Global export: single JSON with every page (for migration tools) • Copy-to-clipboard on URLs, titles, descriptions for quick re-use Design notes: • Sidebar fixed-width 260px, content panel fills remaining width • Content panel scrolls independently (sticky sidebar) • Headings rendered as visual hierarchy (indent by H1/H2/H3 level) • Content renders narrative as prose + [TABLE DATA] blocks as tables • Images grid uses same tile + Save button pattern as ScannerImagesTab • Mobile: sidebar collapses to a