feat: simulate exact userscript URL matches

Author: SysAdminDoc

CHANGELOG.md

@@ -23,6 +23,7 @@ All notable changes to ScriptHunt will be documented in this file.
 - Added installed/favorite import previews with valid, invalid, duplicate, conflict, and manager-format counts; merge, replace, skip-conflict, and cancel actions; and versioned pre-import snapshots with one-click rollback.
 - Replaced unconstrained custom-source field guessing with declarative schema-v1 manifests covering stable identity, capabilities, privacy route, response/mapping paths, and strict byte/item/time limits; legacy templates migrate to a bounded compatibility mapping.
 - Made the executable source registry authoritative for README source rows and diagnostics method/route/capability claims, with local drift tests and complete package release metadata.
+- Added exact-URL applicability simulation for userscript scheme, host, port, path, include globs, and exclusion rules while retaining domain-only host hints.
 
 ## [v0.5.1]
 

README.md

@@ -59,9 +59,9 @@ npm run qa
 | **Favorites** | Save scripts locally with versioned JSON export/import, conflict preview, recovery snapshots, and undo |
 | **Saved Searches** | Save query/filter/source combinations locally and manually refresh them to badge new or updated results |
 | **Installed Import/Export** | Preview manager/app backups before merge, replace, or conflict-skip; every write creates a versioned local snapshot with one-click rollback |
-| **Advanced Query Syntax** | `site:`, `author:`, `updated:`, `grant:` operators with domain-aware by-site.json search and metadata-backed grant filtering |
+| **Advanced Query Syntax** | `site:`, `author:`, `updated:`, `grant:` operators with domain-aware by-site.json search, exact-URL applicability simulation, and metadata-backed grant filtering |
 | **Advanced Filters** | Visible controls for source, license, installs, updated date, catalog language, @grant, risk, and applies-to domain |
-| **Applies-To Evidence** | Site-filtered results show source site matches alongside parsed `@match`, `@include`, and `@exclude` metadata evidence |
+| **Applies-To Evidence** | Domain hints show host-level evidence, while exact URL filters simulate scheme, host, port, path, `@match`, `@include`, `@exclude`, and `@exclude-match` behavior |
 | **Filter Results** | Instantly narrow loaded results by name/description/author without re-querying sources |
 | **Source Health** | Persists failing source cooldowns with retry controls and versioned per-source provenance for partiality, route, latency, HTTP status, and cache use |
 | **Offline Recent Searches** | Stores recent successful searches locally, labels stale cached results, and exposes revalidation when online |

index.html

@@ -390,7 +390,7 @@
         <div class="filter-row">
             <div class="site-filter-wrap">
                 <svg class="site-filter-icon" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><circle cx="12" cy="12" r="10"/><line x1="2" y1="12" x2="22" y2="12"/><path d="M12 2a15.3 15.3 0 0 1 4 10 15.3 15.3 0 0 1-4 10 15.3 15.3 0 0 1-4-10 15.3 15.3 0 0 1 4-10z"/></svg>
-                <input type="text" class="site-filter" id="siteFilter" placeholder="Filter by site (youtube.com)" autocomplete="off" spellcheck="false" aria-label="Filter by website domain">
+                <input type="text" class="site-filter" id="siteFilter" placeholder="Domain or exact URL" autocomplete="off" spellcheck="false" aria-label="Filter by website domain or exact URL">
             </div>
             <button class="tool-btn" id="btnBookmarklet" title="Bookmarklet tool" popovertarget="bookmarkletSection">Bookmarklet</button>
             <button class="tool-btn" id="btnSavedSearches" title="Saved searches" popovertarget="savedSearchSection">Saved</button>
@@ -2682,7 +2682,7 @@ <h3>Search userscripts everywhere</h3>
         var q = raw.trim(), site = '', author = '', updatedDays = 0, grantFilter = '';
         var m;
         m = q.match(/\bsite:(\S+)/i);
-        if (m) { site = m[1].replace(/^https?:\/\//, '').replace(/\/.*/, ''); q = q.replace(m[0], '').trim(); }
+        if (m) { site = m[1]; q = q.replace(m[0], '').trim(); }
         m = q.match(/\bauthor:(\S+)/i);
         if (m) { author = m[1]; q = q.replace(m[0], '').trim(); }
         m = q.match(/\bupdated:(\d+)d?\b/i);
@@ -2703,6 +2703,19 @@ <h3>Search userscripts everywhere</h3>
         }
     }
 
+    function normalizeSiteTarget(site) {
+        var raw = String(site || '').trim();
+        if (!raw) return null;
+        if (/^(https?|file|ftp):\/\//i.test(raw)) {
+            try {
+                var url = new URL(raw);
+                return { mode: 'exact-url', raw: raw, url: url, host: url.hostname.replace(/^www\./, '').toLowerCase(), label: url.toString() };
+            } catch(e) {}
+        }
+        var host = normalizeSiteHost(raw);
+        return host ? { mode: 'host-hint', raw: raw, url: null, host: host, label: host } : null;
+    }
+
     function hostMatchesPattern(host, patternHost) {
         host = normalizeSiteHost(host);
         patternHost = (patternHost || '').toLowerCase().replace(/^www\./, '');
@@ -2723,7 +2736,7 @@ <h3>Search userscripts everywhere</h3>
         if (!pattern) return false;
         if (pattern === '<all_urls>') return true;
         var m = String(pattern).match(/^(?:\*|https?|file):\/\/([^/]+)\//i);
-        if (m) return hostMatchesPattern(host, m[1]);
+        if (m) return hostMatchesPattern(host, m[1].replace(/:\d+$/, ''));
         return false;
     }
 
@@ -2734,27 +2747,77 @@ <h3>Search userscripts everywhere</h3>
         return candidates.some(function(c) { return rx.test(c); });
     }
 
+    function matchDirectiveAgainstUrl(pattern, url) {
+        if (pattern === '<all_urls>') {
+            return /^(https?|file|ftp):$/.test(url.protocol) ? { matched: true, reason: '' } : { matched: false, reason: 'scheme is outside <all_urls>' };
+        }
+        var parsed = String(pattern || '').match(/^(\*|https?|file|ftp):\/\/([^/]*)(\/.*)$/i);
+        if (!parsed) return { matched: false, reason: 'invalid @match pattern' };
+        var scheme = parsed[1].toLowerCase();
+        if (scheme === '*') {
+            if (url.protocol !== 'http:' && url.protocol !== 'https:') return { matched: false, reason: 'scheme mismatch' };
+        } else if (url.protocol !== scheme + ':') return { matched: false, reason: 'scheme mismatch' };
+        var hostPattern = parsed[2];
+        if (scheme === 'file') {
+            if (hostPattern && hostPattern !== '*' && hostPattern !== url.host) return { matched: false, reason: 'file host mismatch' };
+        } else {
+            var patternPort = '';
+            var hostOnly = hostPattern;
+            var portMatch = hostPattern.match(/^(.*):(\d+)$/);
+            if (portMatch) { hostOnly = portMatch[1]; patternPort = portMatch[2]; }
+            if (!hostMatchesPattern(url.hostname, hostOnly)) return { matched: false, reason: 'host mismatch' };
+            if (patternPort && url.port !== patternPort) return { matched: false, reason: 'port mismatch' };
+        }
+        if (!globToRegex(parsed[3]).test(url.pathname + url.search)) return { matched: false, reason: 'path mismatch' };
+        return { matched: true, reason: '' };
+    }
+
+    function includeDirectiveAgainstUrl(pattern, url) {
+        try {
+            return globToRegex(pattern).test(url.toString()) ? { matched: true, reason: '' } : { matched: false, reason: 'URL glob mismatch' };
+        } catch(e) {
+            return { matched: false, reason: 'invalid URL glob' };
+        }
+    }
+
     function metaArray(meta, key) {
         var val = meta && meta[key];
         if (!val) return [];
         return Array.isArray(val) ? val : [val];
     }
 
     function buildAppliesToEvidence(item, site, meta) {
-        var host = normalizeSiteHost(site);
-        if (!host) return null;
+        var target = normalizeSiteTarget(site);
+        if (!target) return null;
+        var host = target.host;
         var matches = [];
         var excludes = [];
-        metaArray(meta, 'match').forEach(function(p) { if (matchDirectiveTargetsHost(p, host)) matches.push('@match ' + p); });
-        metaArray(meta, 'include').forEach(function(p) { if (includeDirectiveTargetsHost(p, host)) matches.push('@include ' + p); });
-        metaArray(meta, 'exclude').forEach(function(p) { if (includeDirectiveTargetsHost(p, host) || matchDirectiveTargetsHost(p, host)) excludes.push('@exclude ' + p); });
-        metaArray(meta, 'exclude-match').forEach(function(p) { if (matchDirectiveTargetsHost(p, host)) excludes.push('@exclude-match ' + p); });
+        var failed = [];
+        metaArray(meta, 'match').forEach(function(p) {
+            var result = target.url ? matchDirectiveAgainstUrl(p, target.url) : { matched: matchDirectiveTargetsHost(p, host), reason: 'host hint mismatch' };
+            if (result.matched) matches.push('@match ' + p); else if (target.url) failed.push('@match ' + p + ' — ' + result.reason);
+        });
+        metaArray(meta, 'include').forEach(function(p) {
+            var result = target.url ? includeDirectiveAgainstUrl(p, target.url) : { matched: includeDirectiveTargetsHost(p, host), reason: 'host hint mismatch' };
+            if (result.matched) matches.push('@include ' + p); else if (target.url) failed.push('@include ' + p + ' — ' + result.reason);
+        });
+        metaArray(meta, 'exclude').forEach(function(p) {
+            var result = target.url ? includeDirectiveAgainstUrl(p, target.url) : { matched: includeDirectiveTargetsHost(p, host) || matchDirectiveTargetsHost(p, host) };
+            if (result.matched) excludes.push('@exclude ' + p);
+        });
+        metaArray(meta, 'exclude-match').forEach(function(p) {
+            var result = target.url ? matchDirectiveAgainstUrl(p, target.url) : { matched: matchDirectiveTargetsHost(p, host) };
+            if (result.matched) excludes.push('@exclude-match ' + p);
+        });
         return {
             host: host,
+            target: target.label,
+            mode: target.mode,
             source: item._appliesSource || null,
             checkedMeta: !!meta,
             matchedPatterns: matches,
             excludedPatterns: excludes,
+            failedPatterns: failed.slice(0, 8),
         };
     }
 
@@ -2774,7 +2837,7 @@ <h3>Search userscripts everywhere</h3>
     function appliesSummary(applies) {
         if (!applies) return 'Not checked';
         if (applies.excludedPatterns && applies.excludedPatterns.length) return 'Excluded by metadata';
-        if (applies.matchedPatterns && applies.matchedPatterns.length) return 'Metadata match';
+        if (applies.matchedPatterns && applies.matchedPatterns.length) return applies.mode === 'exact-url' ? 'Exact URL match' : 'Host hint match';
         if (applies.source && applies.checkedMeta) return 'Source match; metadata not matched';
         if (applies.source) return 'Source site match';
         if (applies.checkedMeta) return 'No metadata match';
@@ -2783,10 +2846,11 @@ <h3>Search userscripts everywhere</h3>
 
     function renderAppliesToEvidence(applies) {
         if (!applies) return '';
-        var html = '<div class="applies-matrix"><strong>Applies to ' + esc(applies.host) + ':</strong> ' + esc(appliesSummary(applies));
+        var html = '<div class="applies-matrix"><strong>' + (applies.mode === 'exact-url' ? 'Exact URL simulation' : 'Host hint') + ' — ' + esc(applies.target || applies.host) + ':</strong> ' + esc(appliesSummary(applies));
         if (applies.source) html += '<div><span class="applies-pill source">' + esc(applies.source.label) + '</span></div>';
         if (applies.matchedPatterns && applies.matchedPatterns.length) html += '<div>' + applies.matchedPatterns.map(function(p) { return '<span class="applies-pill">' + esc(p) + '</span>'; }).join('') + '</div>';
         if (applies.excludedPatterns && applies.excludedPatterns.length) html += '<div>' + applies.excludedPatterns.map(function(p) { return '<span class="applies-pill exclude">' + esc(p) + '</span>'; }).join('') + '</div>';
+        if (applies.failedPatterns && applies.failedPatterns.length) html += '<div>' + applies.failedPatterns.map(function(p) { return '<span class="applies-pill miss">' + esc(p) + '</span>'; }).join('') + '</div>';
         if (applies.checkedMeta && !applies.matchedPatterns.length && !applies.excludedPatterns.length) html += '<div><span class="applies-pill miss">No @match/@include hit</span></div>';
         if (!applies.source && !applies.checkedMeta) html += '<div><span class="applies-pill miss">Metadata unavailable</span></div>';
         return html + '</div>';
@@ -2917,7 +2981,7 @@ <h3>Search userscripts everywhere</h3>
             var srcDef = SOURCES[srcId];
             var page = state.sourcePages[srcId] || 1;
             try {
-                var result = await srcDef.search(parsed.query, page, siteVal, filters.language, searchController.signal);
+                var result = await srcDef.search(parsed.query, page, normalizeSiteHost(siteVal), filters.language, searchController.signal);
                 if (!result || result.schemaVersion !== SOURCE_ENVELOPE_VERSION || !Array.isArray(result.items)) throw new Error('invalid source result envelope');
                 var items = result.items;
                 var total = result.total;
@@ -3369,7 +3433,7 @@ <h3>Search userscripts everywhere</h3>
             h += '<div class="compare-row"><span class="compare-label">License</span><span class="compare-value">' + esc(item.license || 'N/A') + '</span></div>';
             h += '<div class="compare-row"><span class="compare-label">Staleness</span><span class="compare-value">' + (stale ? stale.label : 'N/A') + '</span></div>';
             h += '<div class="compare-row"><span class="compare-label">Updated</span><span class="compare-value">' + (item.updatedAt ? timeAgo(item.updatedAt) : 'N/A') + '</span></div>';
-            if (state.siteFilter) h += '<div class="compare-row"><span class="compare-label">Applies to ' + esc(normalizeSiteHost(state.siteFilter)) + '</span><span class="compare-value">' + esc(appliesSummary(item._appliesTo)) + '</span></div>';
+            if (state.siteFilter) h += '<div class="compare-row"><span class="compare-label">Applies to ' + esc((item._appliesTo && item._appliesTo.target) || normalizeSiteHost(state.siteFilter)) + '</span><span class="compare-value">' + esc(appliesSummary(item._appliesTo)) + '</span></div>';
             if (item._scan) {
                 h += '<div class="compare-row"><span class="compare-label">Scan score</span><span class="compare-value">' + (item._scan.unavailable ? 'Unknown' : item._scan.score + '/100') + '</span></div>';
                 h += '<div class="compare-row"><span class="compare-label">Code Size</span><span class="compare-value">' + fmtNum(item._scan.codeSize || 0) + 'B</span></div>';

tests/adapter.spec.js

@@ -672,3 +672,50 @@ test('custom source manifests constrain mapping, limits, and legacy migration',
   expect(outcome.legacy.response.itemsPath).toBe('$legacy');
   expect(outcome.unsafeError).toContain('safe declarative data paths');
 });
+
+test('exact URL applicability evaluates scheme, host, port, path, globs, and exclusions', async ({ page }) => {
+  await page.goto('/');
+
+  const evidence = await page.evaluate(() => {
+    const item = { _appliesSource: { label: 'Fixture source match', domain: 'example.com' } };
+    const meta = {
+      match: [
+        'https://*.example.com:8443/app/*',
+        'http://*.example.com:8443/app/*',
+        'https://*.example.com:9443/app/*',
+        'https://*.example.com:8443/admin/*',
+      ],
+      include: ['https://sub.example.com:8443/app/*'],
+      'exclude-match': ['https://*.example.com:8443/app/private*'],
+      exclude: ['*logout*'],
+    };
+    return {
+      exact: buildAppliesToEvidence(item, 'https://sub.example.com:8443/app/page?x=1', meta),
+      excluded: buildAppliesToEvidence(item, 'https://sub.example.com:8443/app/private/settings', meta),
+      host: buildAppliesToEvidence(item, 'sub.example.com', meta),
+      file: buildAppliesToEvidence({}, 'file:///C:/scripts/test.user.js', {
+        match: ['file:///*', '<all_urls>'],
+      }),
+    };
+  });
+
+  expect(evidence.exact).toMatchObject({
+    mode: 'exact-url',
+    host: 'sub.example.com',
+    target: 'https://sub.example.com:8443/app/page?x=1',
+  });
+  expect(evidence.exact.matchedPatterns).toEqual([
+    '@match https://*.example.com:8443/app/*',
+    '@include https://sub.example.com:8443/app/*',
+  ]);
+  expect(evidence.exact.failedPatterns).toEqual(expect.arrayContaining([
+    expect.stringContaining('scheme mismatch'),
+    expect.stringContaining('port mismatch'),
+    expect.stringContaining('path mismatch'),
+  ]));
+  expect(evidence.exact.excludedPatterns).toEqual([]);
+  expect(evidence.excluded.excludedPatterns).toContain('@exclude-match https://*.example.com:8443/app/private*');
+  expect(evidence.host.mode).toBe('host-hint');
+  expect(evidence.host.matchedPatterns).toContain('@match https://*.example.com:8443/app/*');
+  expect(evidence.file.matchedPatterns).toEqual(['@match file:///*', '@match <all_urls>']);
+});

tests/smoke.spec.js

@@ -746,7 +746,7 @@ test('metadata viewer caps oversized repeated directives without losing parsed f
   await runSearch(page, 'oversized');
 
   const card = page.locator('.result-card').filter({ hasText: 'YouTube Enhancer' });
-  await expect(card.locator('.applies-matrix')).toContainText('Metadata match');
+  await expect(card.locator('.applies-matrix')).toContainText('Host hint match');
   const metadataButton = card.locator('[data-action="meta"]');
   await expect(metadataButton).toBeVisible();
   await metadataButton.click();
@@ -884,7 +884,7 @@ test('site filter shows source and metadata applies-to evidence', async ({ page
   await runSearch(page, 'youtube');
 
   const youtube = page.locator('.result-card').filter({ hasText: 'YouTube Enhancer' });
-  await expect(youtube.locator('.applies-matrix')).toContainText('Metadata match');
+  await expect(youtube.locator('.applies-matrix')).toContainText('Host hint match');
   await expect(youtube.locator('.applies-matrix')).toContainText('Greasy Fork site match');
   await expect(youtube.locator('.applies-matrix')).toContainText('@match https://*.youtube.com/*');
 
@@ -893,6 +893,19 @@ test('site filter shows source and metadata applies-to evidence', async ({ page
   await expect(darkMode.locator('.applies-matrix')).toContainText('No @match/@include hit');
 });
 
+test('exact URL filter renders exclusion simulation and rule failures', async ({ page }) => {
+  await page.goto('/');
+  await page.fill('#siteFilter', 'https://ads.youtube.com/watch?v=1');
+  await runSearch(page, 'youtube');
+
+  const card = page.locator('.result-card').filter({ hasText: 'YouTube Enhancer' });
+  const evidence = card.locator('.applies-matrix');
+  await expect(evidence).toContainText('Exact URL simulation');
+  await expect(evidence).toContainText('Excluded by metadata');
+  await expect(evidence).toContainText('@exclude-match https://ads.youtube.com/*');
+  await expect(evidence).toContainText('URL glob mismatch');
+});
+
 test('comparison modal includes applies-to summary for site-filtered results', async ({ page }) => {
   await page.goto('/');
   await page.fill('#siteFilter', 'youtube.com');
@@ -905,7 +918,7 @@ test('comparison modal includes applies-to summary for site-filtered results', a
 
   await expect(page.locator('.modal-overlay')).toHaveClass(/visible/);
   await expect(page.locator('.compare-label', { hasText: 'Applies to youtube.com' })).toHaveCount(2);
-  await expect(page.locator('.compare-value', { hasText: 'Metadata match' })).toBeVisible();
+  await expect(page.locator('.compare-value', { hasText: 'Host hint match' })).toBeVisible();
 });
 
 test('grant query filters by metadata and labels unknown metadata', async ({ page }) => {