@pseolint/core 0.4.0 → 0.4.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/auditor.d.ts +12 -1
- package/dist/auditor.d.ts.map +1 -1
- package/dist/auditor.js +317 -43
- package/dist/auditor.js.map +1 -1
- package/dist/formatters/bucket-findings.d.ts +43 -0
- package/dist/formatters/bucket-findings.d.ts.map +1 -0
- package/dist/formatters/bucket-findings.js +110 -0
- package/dist/formatters/bucket-findings.js.map +1 -0
- package/dist/formatters/console.d.ts.map +1 -1
- package/dist/formatters/console.js +103 -34
- package/dist/formatters/console.js.map +1 -1
- package/dist/formatters/fixplan.d.ts +13 -0
- package/dist/formatters/fixplan.d.ts.map +1 -0
- package/dist/formatters/fixplan.js +328 -0
- package/dist/formatters/fixplan.js.map +1 -0
- package/dist/formatters/html.d.ts.map +1 -1
- package/dist/formatters/html.js +27 -0
- package/dist/formatters/html.js.map +1 -1
- package/dist/formatters/index.d.ts +2 -0
- package/dist/formatters/index.d.ts.map +1 -1
- package/dist/formatters/index.js +1 -0
- package/dist/formatters/index.js.map +1 -1
- package/dist/formatters/markdown.d.ts.map +1 -1
- package/dist/formatters/markdown.js +77 -7
- package/dist/formatters/markdown.js.map +1 -1
- package/dist/page-filter.d.ts +108 -0
- package/dist/page-filter.d.ts.map +1 -0
- package/dist/page-filter.js +207 -0
- package/dist/page-filter.js.map +1 -0
- package/dist/rules/aeo/answer-first.d.ts.map +1 -1
- package/dist/rules/aeo/answer-first.js +17 -3
- package/dist/rules/aeo/answer-first.js.map +1 -1
- package/dist/rules/aeo/citable-facts.d.ts.map +1 -1
- package/dist/rules/aeo/citable-facts.js +12 -1
- package/dist/rules/aeo/citable-facts.js.map +1 -1
- package/dist/rules/aeo/content-modularity.d.ts.map +1 -1
- package/dist/rules/aeo/content-modularity.js +3 -0
- package/dist/rules/aeo/content-modularity.js.map +1 -1
- package/dist/rules/aeo/crawler-access.d.ts.map +1 -1
- package/dist/rules/aeo/crawler-access.js +6 -0
- package/dist/rules/aeo/crawler-access.js.map +1 -1
- package/dist/rules/aeo/faq-coverage.d.ts.map +1 -1
- package/dist/rules/aeo/faq-coverage.js +4 -0
- package/dist/rules/aeo/faq-coverage.js.map +1 -1
- package/dist/rules/aeo/freshness-signals.d.ts.map +1 -1
- package/dist/rules/aeo/freshness-signals.js +9 -2
- package/dist/rules/aeo/freshness-signals.js.map +1 -1
- package/dist/rules/aeo/llms-txt.d.ts.map +1 -1
- package/dist/rules/aeo/llms-txt.js +6 -1
- package/dist/rules/aeo/llms-txt.js.map +1 -1
- package/dist/rules/aeo/summary-bait.d.ts.map +1 -1
- package/dist/rules/aeo/summary-bait.js +5 -2
- package/dist/rules/aeo/summary-bait.js.map +1 -1
- package/dist/rules/content/missing-author.d.ts.map +1 -1
- package/dist/rules/content/missing-author.js +10 -2
- package/dist/rules/content/missing-author.js.map +1 -1
- package/dist/rules/spam/thin-content.d.ts.map +1 -1
- package/dist/rules/spam/thin-content.js +9 -1
- package/dist/rules/spam/thin-content.js.map +1 -1
- package/dist/site-classifier.d.ts +1 -1
- package/dist/site-classifier.d.ts.map +1 -1
- package/dist/site-classifier.js +216 -0
- package/dist/site-classifier.js.map +1 -1
- package/dist/types.d.ts +77 -2
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js.map +1 -1
- package/package.json +1 -1
package/dist/formatters/html.js
CHANGED
|
@@ -82,6 +82,13 @@ function renderCategoryTiles(categories) {
|
|
|
82
82
|
})
|
|
83
83
|
.join("");
|
|
84
84
|
}
|
|
85
|
+
function confidenceCaveat(c) {
|
|
86
|
+
if (c === "low")
|
|
87
|
+
return "low confidence — known false-positive risk on this site type";
|
|
88
|
+
if (c === "speculative")
|
|
89
|
+
return "speculative — heuristic match; verify before acting";
|
|
90
|
+
return null;
|
|
91
|
+
}
|
|
85
92
|
function renderFindingRow(f) {
|
|
86
93
|
const tone = severityTone(f.severity);
|
|
87
94
|
const effortPill = f.effort
|
|
@@ -90,6 +97,10 @@ function renderFindingRow(f) {
|
|
|
90
97
|
const url = f.pageUrl ? `<span class="finding-url mono">${escapeHtml(shortenUrl(f.pageUrl))}</span>` : "";
|
|
91
98
|
const fix = f.fix ? `<div class="fix"><span class="fix-label">Fix</span>${escapeHtml(f.fix)}</div>` : "";
|
|
92
99
|
const docsHref = f.docsUrl ?? `https://pseolint.dev/rules/${f.ruleId.split("/").pop() ?? f.ruleId}`;
|
|
100
|
+
const caveat = confidenceCaveat(f.confidence);
|
|
101
|
+
const caveatPill = caveat
|
|
102
|
+
? `<div class="caveat">${escapeHtml(caveat)}</div>`
|
|
103
|
+
: "";
|
|
93
104
|
// Cluster context (collapsed details) — only on findings that carry one.
|
|
94
105
|
let cluster = "";
|
|
95
106
|
if (f.context?.type === "cluster") {
|
|
@@ -115,11 +126,23 @@ function renderFindingRow(f) {
|
|
|
115
126
|
${url}
|
|
116
127
|
</div>
|
|
117
128
|
<p class="finding-msg">${escapeHtml(f.message)}</p>
|
|
129
|
+
${caveatPill}
|
|
118
130
|
${fix}
|
|
119
131
|
${cluster}
|
|
120
132
|
<a class="docs-link" href="${escapeHtml(docsHref)}" target="_blank" rel="noopener">${escapeHtml(docsHref.replace(/^https?:\/\//, ""))} ↗</a>
|
|
121
133
|
</li>`;
|
|
122
134
|
}
|
|
135
|
+
/** v0.4.3 — "Audited as <type>" line shown under the verdict badge. */
|
|
136
|
+
function auditedAsHtml(c) {
|
|
137
|
+
if (!c)
|
|
138
|
+
return "";
|
|
139
|
+
const confPct = Math.round(c.confidence * 100);
|
|
140
|
+
const suppressed = c.suppressedRules.length;
|
|
141
|
+
const suppressedPart = suppressed > 0
|
|
142
|
+
? ` ${suppressed} pSEO-only rule${suppressed === 1 ? "" : "s"} suppressed.`
|
|
143
|
+
: "";
|
|
144
|
+
return `<div class="audited-as">Audited as <strong>${escapeHtml(c.type)}</strong> (${confPct}% confidence).${escapeHtml(suppressedPart)}</div>`;
|
|
145
|
+
}
|
|
123
146
|
function renderBucketSection(label, items, tone) {
|
|
124
147
|
if (items.length === 0) {
|
|
125
148
|
return `<section class="bucket bucket-empty">
|
|
@@ -311,6 +334,9 @@ export function formatHtml(summary, _options) {
|
|
|
311
334
|
.sev.sev-warning{background:color-mix(in oklab,var(--warning) 14%,transparent);color:var(--warning);border-color:color-mix(in oklab,var(--warning) 35%,transparent)}
|
|
312
335
|
.sev.sev-muted{background:var(--card-2);color:var(--muted);border-color:var(--border-strong)}
|
|
313
336
|
|
|
337
|
+
.caveat{margin-top:6px;padding:6px 10px;border-radius:8px;background:color-mix(in oklab,var(--warning) 8%,transparent);color:var(--warning);font-size:12px;line-height:1.4;border:1px solid color-mix(in oklab,var(--warning) 22%,transparent)}
|
|
338
|
+
.audited-as{display:block;margin-top:10px;font-size:13px;color:var(--muted);font-family:ui-monospace,"SFMono-Regular",Menlo,Consolas,monospace}
|
|
339
|
+
.audited-as strong{color:var(--fg)}
|
|
314
340
|
.fix{margin-top:8px;padding:10px 12px;background:var(--card-2);border-radius:10px;color:var(--muted);font-size:13px;line-height:1.55}
|
|
315
341
|
.fix-label{display:inline-block;margin-right:8px;padding:1px 6px;border-radius:4px;
|
|
316
342
|
background:color-mix(in oklab,var(--primary) 18%,transparent);color:var(--primary);
|
|
@@ -361,6 +387,7 @@ export function formatHtml(summary, _options) {
|
|
|
361
387
|
|
|
362
388
|
<section class="card">
|
|
363
389
|
<span class="verdict-badge tone-${verdictTone}"><span class="verdict-dot"></span>${escapeHtml(VERDICT_LABEL[verdict])}</span>
|
|
390
|
+
${auditedAsHtml(summary.siteClassification)}
|
|
364
391
|
<span class="verdict-headline">${escapeHtml(summary.headline)}</span>
|
|
365
392
|
<div class="cat-grid">${renderCategoryTiles(summary.categories)}</div>
|
|
366
393
|
</section>
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"html.js","sourceRoot":"","sources":["../../src/formatters/html.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"html.js","sourceRoot":"","sources":["../../src/formatters/html.ts"],"names":[],"mappings":"AAkBA,MAAM,aAAa,GAA4B;IAC7C,KAAK,EAAE,OAAO;IACd,OAAO,EAAE,SAAS;IAClB,UAAU,EAAE,YAAY;IACxB,QAAQ,EAAE,UAAU;CACrB,CAAC;AAEF,MAAM,YAAY,GAAwE;IACxF,KAAK,EAAE,SAAS;IAChB,OAAO,EAAE,SAAS;IAClB,UAAU,EAAE,aAAa;IACzB,QAAQ,EAAE,UAAU;CACrB,CAAC;AAEF,MAAM,UAAU,GAAsE;IACpF,CAAC,EAAE,SAAS;IACZ,CAAC,EAAE,SAAS;IACZ,CAAC,EAAE,SAAS;IACZ,CAAC,EAAE,aAAa;IAChB,CAAC,EAAE,UAAU;CACd,CAAC;AAEF,MAAM,cAAc,GAAkD;IACpE,SAAS,EAAE,WAAW;IACtB,eAAe,EAAE,iBAAiB;IAClC,QAAQ,EAAE,UAAU;IACpB,IAAI,EAAE,MAAM;CACb,CAAC;AAEF,SAAS,UAAU,CAAC,IAAY;IAC9B,OAAO,IAAI;SACR,OAAO,CAAC,IAAI,EAAE,OAAO,CAAC;SACtB,OAAO,CAAC,IAAI,EAAE,MAAM,CAAC;SACrB,OAAO,CAAC,IAAI,EAAE,MAAM,CAAC;SACrB,OAAO,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;AAC7B,CAAC;AAED,SAAS,UAAU,CAAC,GAAW;IAC7B,IAAI,CAAC;QACH,OAAO,IAAI,GAAG,CAAC,GAAG,CAAC,CAAC,QAAQ,IAAI,GAAG,CAAC;IACtC,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,GAAG,CAAC;IACb,CAAC;AACH,CAAC;AAED,SAAS,YAAY,CAAC,CAAS;IAC7B,IAAI,CAAC,KAAK,UAAU,IAAI,CAAC,KAAK,OAAO;QAAE,OAAO,aAAa,CAAC;IAC5D,IAAI,CAAC,KAAK,SAAS;QAAE,OAAO,SAAS,CAAC;IACtC,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,WAAW,CAAC,MAAc;IACjC,QAAQ,MAAM,EAAE,CAAC;QACf,KAAK,OAAO;YACV,OAAO,WAAW,CAAC;QACrB,KAAK,UAAU;YACb,OAAO,UAAU,CAAC;QACpB,KAAK,YAAY;YACf,OAAO,YAAY,CAAC;QACtB;YACE,OAAO,MAAM,CAAC;IAClB,CAAC;AACH,CAAC;AAED,SAAS,kBAAkB,CAAC,KAAa,EAAE,IAAmB;IAC5D,MAAM,IAAI,GAAG,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACpC,MAAM,WAAW,GACf,IAAI,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,QAAQ,EAAE,CAAC;IAC/F,OAAO,4BAA4B,IAAI;6BACZ,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC;6BACtB,UAAU,CAAC,KAAK,CAAC;mCACX,UAAU,CAAC,WAAW,CAAC;SACjD,CAAC;AACV,CAAC;AAED,SAAS,mBAAmB,CAAC,UAA0B;IACrD,MAAM,KAAK,GAAyC;QAClD,WAAW;QACX,iBAAiB;QACjB,UAAU;QACV,MAAM;KACP,CAAC;IACF,OAAO,KAAK;SACT,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;QACX,MAAM,IAAI,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC;QAC7B,IAAI,CAAC,IAAI;YAAE,OAAO,EAAE,CAAC;QACrB,OAAO,kBAAkB,CAAC,cAAc,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC;IACvD,CAAC,CAAC;SACD,IAAI,CAAC,EAAE,CAAC,CAAC;AACd,CAAC;AAED,SAAS,gBAAgB,CAAC,CAAyB;IACjD,IAAI,CAAC,KAAK,KAAK;QAAE,OAAO,8DAA8D,CAAC;IACvF,IAAI,CAAC,KAAK,aAAa;QAAE,OAAO,qDAAqD,CAAC;IACtF,OAAO,IAAI,CAAC;AACd,CAAC;AAED,SAAS,gBAAgB,CAAC,CAAa;IACrC,MAAM,IAAI,GAAG,YAAY,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC;IACtC,MAAM,UAAU,GAAG,CAAC,CAAC,MAAM;QACzB,CAAC,CAAC,oCAAoC,UAAU,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,UAAU,CAAC,WAAW,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,SAAS;QACzG,CAAC,CAAC,EAAE,CAAC;IACP,MAAM,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,kCAAkC,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC;IAC1G,MAAM,GAAG,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,sDAAsD,UAAU,CAAC,CAAC,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC;IACzG,MAAM,QAAQ,GACZ,CAAC,CAAC,OAAO,IAAI,8BAA8B,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC;IACrF,MAAM,MAAM,GAAG,gBAAgB,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC;IAC9C,MAAM,UAAU,GAAG,MAAM;QACvB,CAAC,CAAC,uBAAuB,UAAU,CAAC,MAAM,CAAC,QAAQ;QACnD,CAAC,CAAC,EAAE,CAAC;IAEP,yEAAyE;IACzE,IAAI,OAAO,GAAG,EAAE,CAAC;IACjB,IAAI,CAAC,CAAC,OAAO,EAAE,IAAI,KAAK,SAAS,EAAE,CAAC;QAClC,MAAM,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC;QACtB,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,GAAG,CAAC,eAAe,CAAC;QAC7C,MAAM,UAAU,GAAG,GAAG,CAAC,UAAU;aAC9B,GAAG,CACF,CAAC,CAAC,EAAE,EAAE,CACJ,0BAA0B,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,gCAAgC,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,kCAAkC,CAAC,CAAC,CAAC,UAAU,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,CAC1M;aACA,IAAI,CAAC,EAAE,CAAC,CAAC;QACZ,MAAM,OAAO,GAAG,GAAG,CAAC,OAAO;aACxB,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,oBAAoB,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC;aAChE,IAAI,CAAC,EAAE,CAAC,CAAC;QACZ,OAAO,GAAG;iBACG,GAAG,CAAC,WAAW,uBAAuB,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC;;8BAE/E,UAAU;;gCAER,OAAO;eACxB,CAAC;IACd,CAAC;IAED,OAAO,8BAA8B,IAAI;;8BAEb,UAAU,CAAC,CAAC,CAAC,MAAM,CAAC,UAAU,UAAU;QAC9D,GAAG;;6BAEkB,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC;MAC5C,UAAU;MACV,GAAG;MACH,OAAO;iCACoB,UAAU,CAAC,QAAQ,CAAC,oCAAoC,UAAU,CAAC,QAAQ,CAAC,OAAO,CAAC,cAAc,EAAE,EAAE,CAAC,CAAC;QACjI,CAAC;AACT,CAAC;AAED,uEAAuE;AACvE,SAAS,aAAa,CAAC,CAAiC;IACtD,IAAI,CAAC,CAAC;QAAE,OAAO,EAAE,CAAC;IAClB,MAAM,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,UAAU,GAAG,GAAG,CAAC,CAAC;IAC/C,MAAM,UAAU,GAAG,CAAC,CAAC,eAAe,CAAC,MAAM,CAAC;IAC5C,MAAM,cAAc,GAClB,UAAU,GAAG,CAAC;QACZ,CAAC,CAAC,IAAI,UAAU,kBAAkB,UAAU,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,cAAc;QAC3E,CAAC,CAAC,EAAE,CAAC;IACT,OAAO,8CAA8C,UAAU,CAAC,CAAC,CAAC,IAAI,CAAC,cAAc,OAAO,iBAAiB,UAAU,CAAC,cAAc,CAAC,QAAQ,CAAC;AAClJ,CAAC;AAED,SAAS,mBAAmB,CAAC,KAAa,EAAE,KAAmB,EAAE,IAAY;IAC3E,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,OAAO;yCAC8B,IAAI,qCAAqC,UAAU,CAAC,KAAK,CAAC;eACpF,CAAC;IACd,CAAC;IACD,MAAM,IAAI,GAAG,KAAK,CAAC,GAAG,CAAC,gBAAgB,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAClD,OAAO;uCAC8B,IAAI,qCAAqC,UAAU,CAAC,KAAK,CAAC,+BAA+B,KAAK,CAAC,MAAM;+BAC7G,IAAI;aACtB,CAAC;AACd,CAAC;AAED,SAAS,yBAAyB,CAAC,MAA0C;IAC3E,IAAI,CAAC,MAAM;QAAE,OAAO,EAAE,CAAC;IACvB,MAAM,WAAW,GACf,MAAM,CAAC,OAAO,KAAK,OAAO;QACxB,CAAC,CAAC,SAAS;QACX,CAAC,CAAC,MAAM,CAAC,OAAO,KAAK,YAAY;YAC/B,CAAC,CAAC,SAAS;YACX,CAAC,CAAC,aAAa,CAAC;IACtB,MAAM,EAAE,GAAG,MAAM,CAAC,iBAAiB,CAAC,CAAC,CAAC,iBAAiB,UAAU,CAAC,MAAM,CAAC,iBAAiB,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;IACnG,OAAO;;;gCAGuB,MAAM,CAAC,cAAc,cAAc,MAAM,CAAC,cAAc,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,GAAG,EAAE;;;+EAGhC,WAAW,KAAK,UAAU,CAAC,MAAM,CAAC,OAAO,CAAC;+EAC1C,MAAM,CAAC,QAAQ;4EAClB,MAAM,CAAC,KAAK;kFACN,CAAC,MAAM,CAAC,gBAAgB,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC;qFACvC,CAAC,MAAM,CAAC,gBAAgB,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC;;aAElH,CAAC;AACd,CAAC;AAED,SAAS,gBAAgB,CAAC,MAA2C;IACnE,MAAM,MAAM,GAAG,MAAM,CAAC,UAAU,CAAC,KAAK,EAAE,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC,CAAC;IACjF,MAAM,IAAI,GACR,MAAM,CAAC,gBAAgB,KAAK,SAAS,CAAC,CAAC,CAAC,WAAW,MAAM,CAAC,gBAAgB,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;IAC/F,MAAM,UAAU,GAAG,MAAM,CAAC,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,OAAO,CAAC;IACxD,MAAM,MAAM,GAAG,GAAG,MAAM,CAAC,UAAU,CAAC,KAAK,CAAC,cAAc,EAAE,SAAS,MAAM,CAAC,UAAU,CAAC,MAAM,CAAC,cAAc,EAAE,MAAM,CAAC;IACnH,MAAM,MAAM,GAAG,MAAM;SAClB,GAAG,CACF,CAAC,CAAC,EAAE,EAAE,CAAC;;;oCAGuB,CAAC,CAAC,QAAQ;cAChC,UAAU,CAAC,CAAC,CAAC,KAAK,CAAC;+BACF,YAAY,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,UAAU,CAAC,CAAC,CAAC,QAAQ,CAAC;;8BAEpD,CAAC,CAAC,aAAa,eAAe,CAAC,CAAC,eAAe,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;8BAC1E,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC;UAC3C,CACL;SACA,IAAI,CAAC,EAAE,CAAC,CAAC;IAEZ,OAAO;;;;8BAIqB,UAAU,CAAC,MAAM,CAAC,SAAS,CAAC,MAAM,UAAU,MAAM,MAAM,GAAG,IAAI;;IAEzF,MAAM,CAAC,SAAS,CAAC,CAAC,CAAC,wBAAwB,UAAU,CAAC,MAAM,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE;uBAC/D,MAAM;WAClB,CAAC;AACZ,CAAC;AAED,MAAM,UAAU,UAAU,CAAC,OAAqB,EAAE,QAA4B;IAC5E,MAAM,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC;IAChC,MAAM,WAAW,GAAG,YAAY,CAAC,OAAO,CAAC,CAAC;IAC1C,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC;IAC9B,MAAM,KAAK,GAAG,OAAO,CAAC,WAAW,EAAE,UAAU,CAAC;IAC9C,MAAM,SAAS,GAAG,OAAO,CAAC,WAAW,EAAE,eAAe,CAAC;IAEvD,MAAM,SAAS,GAAG,KAAK;QACrB,CAAC,CAAC,GAAG,KAAK,CAAC,OAAO,cAAc,KAAK,CAAC,UAAU,iBAAiB,KAAK,CAAC,OAAO,UAAU;QACxF,CAAC,CAAC,GAAG,OAAO,CAAC,SAAS,QAAQ,CAAC;IAEjC,OAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;mCAiK0B,WAAW;;;;;;6BAMjB,UAAU,CAAC,SAAS,CAAC;;2BAEvB,UAAU,CAAC,OAAO,CAAC,aAAa,CAAC;;;sCAGtB,WAAW,sCAAsC,UAAU,CAAC,aAAa,CAAC,OAAO,CAAC,CAAC;MACnH,aAAa,CAAC,OAAO,CAAC,kBAAkB,CAAC;qCACV,UAAU,CAAC,OAAO,CAAC,QAAQ,CAAC;4BACrC,mBAAmB,CAAC,OAAO,CAAC,UAAU,CAAC;;;IAG/D,OAAO,CAAC,gBAAgB,CAAC,CAAC,CAAC,oLAAoL,CAAC,CAAC,CAAC,EAAE;;IAEpN,yBAAyB,CAAC,SAAS,CAAC;;IAEpC,mBAAmB,CAAC,UAAU,EAAE,MAAM,CAAC,QAAQ,EAAE,aAAa,CAAC;IAC/D,mBAAmB,CAAC,YAAY,EAAE,MAAM,CAAC,SAAS,EAAE,SAAS,CAAC;IAC9D,mBAAmB,CAAC,eAAe,EAAE,MAAM,CAAC,aAAa,EAAE,OAAO,CAAC;;IAEnE,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,gBAAgB,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAE;;;;;;;;;QASlD,CAAC;AACT,CAAC"}
|
|
@@ -6,4 +6,6 @@ export { formatMarkdown } from "./markdown.js";
|
|
|
6
6
|
export type { MarkdownFormatOptions } from "./markdown.js";
|
|
7
7
|
export { formatHtml } from "./html.js";
|
|
8
8
|
export type { HtmlFormatOptions } from "./html.js";
|
|
9
|
+
export { formatFixplan } from "./fixplan.js";
|
|
10
|
+
export type { FixplanFormatOptions } from "./fixplan.js";
|
|
9
11
|
//# sourceMappingURL=index.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/formatters/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC;AAC5D,YAAY,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACzD,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AACvC,YAAY,EAAE,iBAAiB,EAAE,MAAM,WAAW,CAAC;AACnD,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAC;AAC/C,YAAY,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AAC3D,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AACvC,YAAY,EAAE,iBAAiB,EAAE,MAAM,WAAW,CAAC"}
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/formatters/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC;AAC5D,YAAY,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACzD,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AACvC,YAAY,EAAE,iBAAiB,EAAE,MAAM,WAAW,CAAC;AACnD,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAC;AAC/C,YAAY,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AAC3D,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AACvC,YAAY,EAAE,iBAAiB,EAAE,MAAM,WAAW,CAAC;AACnD,OAAO,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC;AAC7C,YAAY,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC"}
|
package/dist/formatters/index.js
CHANGED
|
@@ -2,4 +2,5 @@ export { formatConsole, aeoScoreLabel } from "./console.js";
|
|
|
2
2
|
export { formatJson } from "./json.js";
|
|
3
3
|
export { formatMarkdown } from "./markdown.js";
|
|
4
4
|
export { formatHtml } from "./html.js";
|
|
5
|
+
export { formatFixplan } from "./fixplan.js";
|
|
5
6
|
//# sourceMappingURL=index.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/formatters/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC;AAE5D,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AAEvC,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAC;AAE/C,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC"}
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/formatters/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC;AAE5D,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AAEvC,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAC;AAE/C,OAAO,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AAEvC,OAAO,EAAE,aAAa,EAAE,MAAM,cAAc,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"markdown.d.ts","sourceRoot":"","sources":["../../src/formatters/markdown.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,YAAY,
|
|
1
|
+
{"version":3,"file":"markdown.d.ts","sourceRoot":"","sources":["../../src/formatters/markdown.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,YAAY,EAQb,MAAM,aAAa,CAAC;AAIrB,MAAM,WAAW,qBAAqB;IACpC,oIAAoI;IACpI,OAAO,CAAC,EAAE,OAAO,CAAC;CACnB;AAuBD,iBAAS,UAAU,CAAC,GAAG,EAAE,MAAM,GAAG,SAAS,GAAG,MAAM,CAOnD;AA0ID,wBAAgB,cAAc,CAC5B,OAAO,EAAE,YAAY,EACrB,QAAQ,CAAC,EAAE,qBAAqB,GAC/B,MAAM,CAwDR;AAGD,OAAO,EAAE,UAAU,EAAE,CAAC"}
|
|
@@ -1,3 +1,4 @@
|
|
|
1
|
+
import { bucketByTemplate } from "./bucket-findings.js";
|
|
1
2
|
const VERDICT_GLYPH = {
|
|
2
3
|
ready: "✅",
|
|
3
4
|
caution: "⚠️",
|
|
@@ -26,10 +27,33 @@ function shortenUrl(url) {
|
|
|
26
27
|
return url;
|
|
27
28
|
}
|
|
28
29
|
}
|
|
29
|
-
function
|
|
30
|
-
const url =
|
|
30
|
+
function bucketDocsLink(b) {
|
|
31
|
+
const url = b.representativeDocsUrl ??
|
|
32
|
+
`https://pseolint.dev/rules/${b.ruleId.split("/").pop() ?? b.ruleId}`;
|
|
31
33
|
return `[docs](${url})`;
|
|
32
34
|
}
|
|
35
|
+
function effortPrefix(effort) {
|
|
36
|
+
return effort ? `[${effort}] ` : "";
|
|
37
|
+
}
|
|
38
|
+
/** v0.4.3 — caveat suffix for low-confidence findings, rendered inline. */
|
|
39
|
+
function confidenceCaveat(c) {
|
|
40
|
+
if (c === "low")
|
|
41
|
+
return "low confidence — known false-positive risk on this site type";
|
|
42
|
+
if (c === "speculative")
|
|
43
|
+
return "speculative — heuristic match; verify before acting";
|
|
44
|
+
return null;
|
|
45
|
+
}
|
|
46
|
+
/** v0.4.3 — "Audited as <type>" line shown under the verdict header. */
|
|
47
|
+
function auditedAsLine(c) {
|
|
48
|
+
if (!c)
|
|
49
|
+
return null;
|
|
50
|
+
const confPct = Math.round(c.confidence * 100);
|
|
51
|
+
const suppressed = c.suppressedRules.length;
|
|
52
|
+
const suppressedPart = suppressed > 0
|
|
53
|
+
? ` ${suppressed} pSEO-only rule${suppressed === 1 ? "" : "s"} suppressed.`
|
|
54
|
+
: "";
|
|
55
|
+
return `_Audited as **${c.type}** (${confPct}% confidence).${suppressedPart}_`;
|
|
56
|
+
}
|
|
33
57
|
function renderTriageMarkdown(triage) {
|
|
34
58
|
const lines = ["", "## AI Triage", ""];
|
|
35
59
|
const cost = triage.estimatedCostUsd !== undefined ? `, est $${triage.estimatedCostUsd.toFixed(2)}` : "";
|
|
@@ -55,17 +79,58 @@ function renderTriageMarkdown(triage) {
|
|
|
55
79
|
}
|
|
56
80
|
return lines.join("\n");
|
|
57
81
|
}
|
|
82
|
+
/**
|
|
83
|
+
* Render a severity bucket. Findings are first collapsed by template
|
|
84
|
+
* signature so a single template bug surfaces once with a "Fix once,
|
|
85
|
+
* resolve all N" callout instead of N near-identical lines.
|
|
86
|
+
*
|
|
87
|
+
* Single-instance findings keep the legacy bullet format (no `### header`)
|
|
88
|
+
* so simple, low-volume reports still read like a flat list.
|
|
89
|
+
*/
|
|
58
90
|
function renderBucket(label, items) {
|
|
59
91
|
const lines = [];
|
|
60
92
|
if (items.length === 0)
|
|
61
93
|
return lines;
|
|
62
94
|
lines.push(`## ${label} (${items.length})`);
|
|
63
|
-
for (const f of items) {
|
|
64
|
-
const target = f.pageUrl ? ` — ${f.pageUrl}` : "";
|
|
65
|
-
const message = f.fix ?? f.message;
|
|
66
|
-
lines.push(`- **\`${f.ruleId}\`**${target} — ${message} ${docsLink(f)}`);
|
|
67
|
-
}
|
|
68
95
|
lines.push("");
|
|
96
|
+
const buckets = bucketByTemplate(items);
|
|
97
|
+
for (const b of buckets) {
|
|
98
|
+
const caveat = confidenceCaveat(b.representativeConfidence);
|
|
99
|
+
if (b.count === 1) {
|
|
100
|
+
const target = b.representativeUrl !== "<site-wide>" ? ` — ${b.representativeUrl}` : "";
|
|
101
|
+
const message = b.representativeFix ?? b.representativeMessage;
|
|
102
|
+
const eff = effortPrefix(b.effort);
|
|
103
|
+
lines.push(`- **\`${b.ruleId}\`**${target} — ${eff}${message} ${bucketDocsLink(b)}`);
|
|
104
|
+
if (caveat)
|
|
105
|
+
lines.push(` - _${caveat}_`);
|
|
106
|
+
continue;
|
|
107
|
+
}
|
|
108
|
+
// Multi-instance bucket: dedicated header + body block.
|
|
109
|
+
const isTemplateBucket = b.templateSignature !== null;
|
|
110
|
+
const eff = effortPrefix(b.effort);
|
|
111
|
+
const countLabel = isTemplateBucket
|
|
112
|
+
? `× ${b.count} instances on \`${b.templateSignature}\` template`
|
|
113
|
+
: `× ${b.count} affected pages`;
|
|
114
|
+
lines.push(`### ${eff}\`${b.ruleId}\` ${countLabel}`);
|
|
115
|
+
lines.push("");
|
|
116
|
+
const moreSuffix = isTemplateBucket
|
|
117
|
+
? ` — and ${b.count - 1} more page${b.count - 1 === 1 ? "" : "s"} match${b.count - 1 === 1 ? "es" : ""} this template.`
|
|
118
|
+
: ` — affecting ${b.count} pages total.`;
|
|
119
|
+
lines.push(`\`${b.representativeUrl}\` ${b.representativeMessage}${moreSuffix}`);
|
|
120
|
+
lines.push("");
|
|
121
|
+
if (caveat) {
|
|
122
|
+
lines.push(`> _${caveat}_`);
|
|
123
|
+
lines.push("");
|
|
124
|
+
}
|
|
125
|
+
if (b.representativeFix) {
|
|
126
|
+
const fixOnce = isTemplateBucket ? ` Fix once, resolve all ${b.count}.` : "";
|
|
127
|
+
lines.push(`**Fix:** ${b.representativeFix}${fixOnce} ${bucketDocsLink(b)}`);
|
|
128
|
+
}
|
|
129
|
+
else {
|
|
130
|
+
lines.push(bucketDocsLink(b));
|
|
131
|
+
}
|
|
132
|
+
lines.push("");
|
|
133
|
+
}
|
|
69
134
|
return lines;
|
|
70
135
|
}
|
|
71
136
|
function categoryRows(categories) {
|
|
@@ -89,6 +154,11 @@ export function formatMarkdown(summary, _options) {
|
|
|
89
154
|
lines.push(`# pseolint report`);
|
|
90
155
|
lines.push("");
|
|
91
156
|
lines.push(`**Verdict:** ${VERDICT_GLYPH[summary.verdict]} ${VERDICT_LABEL[summary.verdict]}`);
|
|
157
|
+
// v0.4.3 — show "Audited as <type>" right under the verdict so the
|
|
158
|
+
// operator knows which scoring profile produced the verdict.
|
|
159
|
+
const audited = auditedAsLine(summary.siteClassification);
|
|
160
|
+
if (audited)
|
|
161
|
+
lines.push(audited);
|
|
92
162
|
lines.push(`**Risk:** ${summary.risk} / 100 (lower is better)`);
|
|
93
163
|
lines.push("");
|
|
94
164
|
lines.push(`**Headline:** ${summary.headline}`);
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"markdown.js","sourceRoot":"","sources":["../../src/formatters/markdown.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"markdown.js","sourceRoot":"","sources":["../../src/formatters/markdown.ts"],"names":[],"mappings":"AAWA,OAAO,EAAwB,gBAAgB,EAAE,MAAM,sBAAsB,CAAC;AAO9E,MAAM,aAAa,GAA4B;IAC7C,KAAK,EAAE,GAAG;IACV,OAAO,EAAE,IAAI;IACb,UAAU,EAAE,IAAI;IAChB,QAAQ,EAAE,IAAI;CACf,CAAC;AAEF,MAAM,aAAa,GAA4B;IAC7C,KAAK,EAAE,OAAO;IACd,OAAO,EAAE,SAAS;IAClB,UAAU,EAAE,YAAY;IACxB,QAAQ,EAAE,UAAU;CACrB,CAAC;AAEF,MAAM,cAAc,GAAkD;IACpE,SAAS,EAAE,WAAW;IACtB,eAAe,EAAE,iBAAiB;IAClC,QAAQ,EAAE,UAAU;IACpB,IAAI,EAAE,MAAM;CACb,CAAC;AAEF,SAAS,UAAU,CAAC,GAAuB;IACzC,IAAI,CAAC,GAAG;QAAE,OAAO,EAAE,CAAC;IACpB,IAAI,CAAC;QACH,OAAO,IAAI,GAAG,CAAC,GAAG,CAAC,CAAC,QAAQ,IAAI,GAAG,CAAC;IACtC,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,GAAG,CAAC;IACb,CAAC;AACH,CAAC;AAED,SAAS,cAAc,CAAC,CAAkB;IACxC,MAAM,GAAG,GACP,CAAC,CAAC,qBAAqB;QACvB,8BAA8B,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC;IACxE,OAAO,UAAU,GAAG,GAAG,CAAC;AAC1B,CAAC;AAED,SAAS,YAAY,CAAC,MAA6B;IACjD,OAAO,MAAM,CAAC,CAAC,CAAC,IAAI,MAAM,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;AACtC,CAAC;AAED,2EAA2E;AAC3E,SAAS,gBAAgB,CAAC,CAAyB;IACjD,IAAI,CAAC,KAAK,KAAK;QAAE,OAAO,8DAA8D,CAAC;IACvF,IAAI,CAAC,KAAK,aAAa;QAAE,OAAO,qDAAqD,CAAC;IACtF,OAAO,IAAI,CAAC;AACd,CAAC;AAED,wEAAwE;AACxE,SAAS,aAAa,CAAC,CAAiC;IACtD,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAC;IACpB,MAAM,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,UAAU,GAAG,GAAG,CAAC,CAAC;IAC/C,MAAM,UAAU,GAAG,CAAC,CAAC,eAAe,CAAC,MAAM,CAAC;IAC5C,MAAM,cAAc,GAClB,UAAU,GAAG,CAAC;QACZ,CAAC,CAAC,IAAI,UAAU,kBAAkB,UAAU,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,cAAc;QAC3E,CAAC,CAAC,EAAE,CAAC;IACT,OAAO,iBAAiB,CAAC,CAAC,IAAI,OAAO,OAAO,iBAAiB,cAAc,GAAG,CAAC;AACjF,CAAC;AAED,SAAS,oBAAoB,CAAC,MAA2C;IACvE,MAAM,KAAK,GAAa,CAAC,EAAE,EAAE,cAAc,EAAE,EAAE,CAAC,CAAC;IACjD,MAAM,IAAI,GACR,MAAM,CAAC,gBAAgB,KAAK,SAAS,CAAC,CAAC,CAAC,UAAU,MAAM,CAAC,gBAAgB,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;IAC9F,MAAM,UAAU,GAAG,MAAM,CAAC,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,YAAY,CAAC;IAC7D,KAAK,CAAC,IAAI,CACR,aAAa,MAAM,CAAC,SAAS,KAAK,UAAU,MAAM,MAAM,CAAC,UAAU,CAAC,KAAK,CAAC,cAAc,EAAE,SAAS,MAAM,CAAC,UAAU,CAAC,MAAM,CAAC,cAAc,EAAE,OAAO,IAAI,IAAI,CAC5J,CAAC;IACF,IAAI,MAAM,CAAC,SAAS,EAAE,CAAC;QACrB,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACf,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;IAC/B,CAAC;IACD,IAAI,MAAM,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACjC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACf,KAAK,CAAC,IAAI,CAAC,2DAA2D,CAAC,CAAC;QACxE,KAAK,CAAC,IAAI,CAAC,uBAAuB,CAAC,CAAC;QACpC,MAAM,MAAM,GAAG,MAAM,CAAC,UAAU,CAAC,KAAK,EAAE,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC,CAAC;QACjF,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;YACvB,KAAK,CAAC,IAAI,CACR,KAAK,CAAC,CAAC,QAAQ,MAAM,CAAC,CAAC,KAAK,MAAM,CAAC,CAAC,QAAQ,MAAM,CAAC,CAAC,aAAa,MAAM,CAAC,CAAC,eAAe,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CACxG,CAAC;QACJ,CAAC;QACD,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACf,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;YACvB,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,KAAK,OAAO,CAAC,CAAC,SAAS,EAAE,CAAC,CAAC;YAC5D,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACjB,CAAC;IACH,CAAC;IACD,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC1B,CAAC;AAED;;;;;;;GAOG;AACH,SAAS,YAAY,CAAC,KAAa,EAAE,KAAmB;IACtD,MAAM,KAAK,GAAa,EAAE,CAAC;IAC3B,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IACrC,KAAK,CAAC,IAAI,CAAC,MAAM,KAAK,KAAK,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC;IAC5C,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAEf,MAAM,OAAO,GAAG,gBAAgB,CAAC,KAAK,CAAC,CAAC;IACxC,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;QACxB,MAAM,MAAM,GAAG,gBAAgB,CAAC,CAAC,CAAC,wBAAwB,CAAC,CAAC;QAC5D,IAAI,CAAC,CAAC,KAAK,KAAK,CAAC,EAAE,CAAC;YAClB,MAAM,MAAM,GAAG,CAAC,CAAC,iBAAiB,KAAK,aAAa,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,iBAAiB,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;YACxF,MAAM,OAAO,GAAG,CAAC,CAAC,iBAAiB,IAAI,CAAC,CAAC,qBAAqB,CAAC;YAC/D,MAAM,GAAG,GAAG,YAAY,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;YACnC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,MAAM,OAAO,MAAM,MAAM,GAAG,GAAG,OAAO,IAAI,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;YACrF,IAAI,MAAM;gBAAE,KAAK,CAAC,IAAI,CAAC,QAAQ,MAAM,GAAG,CAAC,CAAC;YAC1C,SAAS;QACX,CAAC;QAED,wDAAwD;QACxD,MAAM,gBAAgB,GAAG,CAAC,CAAC,iBAAiB,KAAK,IAAI,CAAC;QACtD,MAAM,GAAG,GAAG,YAAY,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC;QACnC,MAAM,UAAU,GAAG,gBAAgB;YACjC,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,mBAAmB,CAAC,CAAC,iBAAiB,aAAa;YACjE,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,iBAAiB,CAAC;QAClC,KAAK,CAAC,IAAI,CAAC,OAAO,GAAG,KAAK,CAAC,CAAC,MAAM,MAAM,UAAU,EAAE,CAAC,CAAC;QACtD,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAEf,MAAM,UAAU,GAAG,gBAAgB;YACjC,CAAC,CAAC,UAAU,CAAC,CAAC,KAAK,GAAG,CAAC,aAAa,CAAC,CAAC,KAAK,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,SAC5D,CAAC,CAAC,KAAK,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAC7B,iBAAiB;YACnB,CAAC,CAAC,gBAAgB,CAAC,CAAC,KAAK,eAAe,CAAC;QAC3C,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,iBAAiB,MAAM,CAAC,CAAC,qBAAqB,GAAG,UAAU,EAAE,CAAC,CAAC;QACjF,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAEf,IAAI,MAAM,EAAE,CAAC;YACX,KAAK,CAAC,IAAI,CAAC,MAAM,MAAM,GAAG,CAAC,CAAC;YAC5B,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACjB,CAAC;QAED,IAAI,CAAC,CAAC,iBAAiB,EAAE,CAAC;YACxB,MAAM,OAAO,GAAG,gBAAgB,CAAC,CAAC,CAAC,0BAA0B,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC;YAC7E,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC,iBAAiB,GAAG,OAAO,IAAI,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;QAC/E,CAAC;aAAM,CAAC;YACN,KAAK,CAAC,IAAI,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,CAAC;QAChC,CAAC;QACD,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACjB,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,YAAY,CAAC,UAA0B;IAC9C,MAAM,IAAI,GAAa,EAAE,CAAC;IAC1B,MAAM,KAAK,GAAyC;QAClD,WAAW;QACX,iBAAiB;QACjB,UAAU;QACV,MAAM;KACP,CAAC;IACF,KAAK,MAAM,GAAG,IAAI,KAAK,EAAE,CAAC;QACxB,MAAM,IAAI,GAA8B,UAAU,CAAC,GAAG,CAAC,CAAC;QACxD,IAAI,CAAC,IAAI;YAAE,SAAS;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK,cAAc,CAAC,GAAG,CAAC,MAAM,IAAI,CAAC,KAAK,MAAM,IAAI,CAAC,MAAM,IAAI,CAAC,CAAC;IAC3E,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED,MAAM,UAAU,cAAc,CAC5B,OAAqB,EACrB,QAAgC;IAEhC,MAAM,KAAK,GAAa,EAAE,CAAC;IAE3B,KAAK,CAAC,IAAI,CAAC,mBAAmB,CAAC,CAAC;IAChC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACf,KAAK,CAAC,IAAI,CACR,gBAAgB,aAAa,CAAC,OAAO,CAAC,OAAO,CAAC,IAAI,aAAa,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CACnF,CAAC;IACF,mEAAmE;IACnE,6DAA6D;IAC7D,MAAM,OAAO,GAAG,aAAa,CAAC,OAAO,CAAC,kBAAkB,CAAC,CAAC;IAC1D,IAAI,OAAO;QAAE,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IACjC,KAAK,CAAC,IAAI,CAAC,aAAa,OAAO,CAAC,IAAI,0BAA0B,CAAC,CAAC;IAChE,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACf,KAAK,CAAC,IAAI,CAAC,iBAAiB,OAAO,CAAC,QAAQ,EAAE,CAAC,CAAC;IAChD,KAAK,CAAC,IAAI,CAAC,uBAAuB,OAAO,CAAC,SAAS,EAAE,CAAC,CAAC;IAEvD,IAAI,OAAO,CAAC,gBAAgB,EAAE,CAAC;QAC7B,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACf,KAAK,CAAC,IAAI,CACR,2FAA2F,CAC5F,CAAC;IACJ,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACf,KAAK,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC;IAC5B,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACf,KAAK,CAAC,IAAI,CAAC,+BAA+B,CAAC,CAAC;IAC5C,KAAK,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC;IAC5B,KAAK,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,OAAO,CAAC,UAAU,CAAC,CAAC,CAAC;IAChD,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAEf,oBAAoB;IACpB,MAAM,KAAK,GAAG,OAAO,CAAC,WAAW,EAAE,UAAU,CAAC;IAC9C,IAAI,KAAK,EAAE,CAAC;QACV,KAAK,CAAC,IAAI,CACR,WAAW,KAAK,CAAC,OAAO,cAAc,KAAK,CAAC,UAAU,iBAAiB,KAAK,CAAC,OAAO,YAAY,CACjG,CAAC;QACF,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACjB,CAAC;IAED,gBAAgB;IAChB,KAAK,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,CAAC;IACjE,KAAK,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,YAAY,EAAE,OAAO,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,CAAC;IACpE,KAAK,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,eAAe,EAAE,OAAO,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,CAAC;IAE3E,yBAAyB;IACzB,IAAI,OAAO,CAAC,MAAM,EAAE,CAAC;QACnB,KAAK,CAAC,IAAI,CAAC,oBAAoB,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC;IACnD,CAAC;IAED,4BAA4B;IAC5B,OAAO,KAAK,CAAC,MAAM,GAAG,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC;QAC1D,KAAK,CAAC,GAAG,EAAE,CAAC;IACd,CAAC;IACD,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC1B,CAAC;AAED,qEAAqE;AACrE,OAAO,EAAE,UAAU,EAAE,CAAC"}
|
|
@@ -0,0 +1,108 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Page-skip detection helpers used by the auditor pipeline (v0.4.1+).
|
|
3
|
+
*
|
|
4
|
+
* Five policy filters live here, each gated by an AuditOption:
|
|
5
|
+
* - `detectNoindex(page)` honours `<meta name="robots" content="noindex">`
|
|
6
|
+
* and `X-Robots-Tag: noindex` HTTP headers. The site owner already told
|
|
7
|
+
* Google not to index these pages — auditing them produces noise the
|
|
8
|
+
* reader can't act on.
|
|
9
|
+
* - `detectAuthPage(page)` heuristically classifies pages as
|
|
10
|
+
* login / signup / password-reset based on three signals (password input
|
|
11
|
+
* in a thin body, title matches the auth regex, H1 matches the auth
|
|
12
|
+
* regex). Two signals are required for a positive verdict, which keeps
|
|
13
|
+
* the false-positive rate low: a marketing landing page with a single
|
|
14
|
+
* password input or a single auth-shaped heading won't trip it.
|
|
15
|
+
* - `detectBoilerplatePage(page)` (v0.4.2) flags cookie / legal / consent /
|
|
16
|
+
* imprint pages. A single signal is enough because the patterns are
|
|
17
|
+
* anchored + specific (the title or H1 matches the whole-string compliance
|
|
18
|
+
* regex, or the URL path is one of the well-known compliance slugs).
|
|
19
|
+
* - `detectSearchResultPage(page)` (v0.4.2) flags pages that look like
|
|
20
|
+
* internal search-result URLs (query parameter `q` / `query` / `search` /
|
|
21
|
+
* `s` / `keyword`, or path under `/search`). Per Google's own guidance
|
|
22
|
+
* these should be noindex'd — auditing them generates noise.
|
|
23
|
+
* - `detectEmptyBodyPage(page)` (v0.4.2) flags un-hydrated SPA shells:
|
|
24
|
+
* body text < 100 chars, script tags present, and no substantive
|
|
25
|
+
* `<noscript>` fallback. These fail every content rule but the underlying
|
|
26
|
+
* fix is server-side rendering, not content quality.
|
|
27
|
+
*
|
|
28
|
+
* All functions are pure and synchronous so they can be called inside the
|
|
29
|
+
* `parsedPages` map step without disrupting the existing pipeline shape.
|
|
30
|
+
*/
|
|
31
|
+
import type { ParsedPage } from "./types.js";
|
|
32
|
+
/**
|
|
33
|
+
* Returns true when the page is explicitly noindex'd via either the parsed
|
|
34
|
+
* `<meta name="robots">` content or the `X-Robots-Tag` HTTP response header.
|
|
35
|
+
* Match is case-insensitive and substring-based to tolerate combined
|
|
36
|
+
* directives like `"noindex, nofollow"` or `"index, noindex"` (the latter is
|
|
37
|
+
* a common bug — `noindex` wins per spec).
|
|
38
|
+
*/
|
|
39
|
+
export declare function detectNoindex(page: ParsedPage): boolean;
|
|
40
|
+
export interface AuthDetectionResult {
|
|
41
|
+
isAuth: boolean;
|
|
42
|
+
signals: Array<"password-input" | "auth-title" | "auth-h1">;
|
|
43
|
+
}
|
|
44
|
+
/**
|
|
45
|
+
* Heuristic auth-page detection. Returns `isAuth: true` when 2+ signals
|
|
46
|
+
* fire (high confidence). Single-signal pages return `isAuth: false` but
|
|
47
|
+
* still expose the signal list for diagnostics — useful for tracking
|
|
48
|
+
* borderline cases that might warrant a manual config exclude.
|
|
49
|
+
*/
|
|
50
|
+
export declare function detectAuthPage(page: ParsedPage): AuthDetectionResult;
|
|
51
|
+
export interface BoilerplateDetectionResult {
|
|
52
|
+
isBoilerplate: boolean;
|
|
53
|
+
signals: Array<"boilerplate-title" | "boilerplate-h1" | "boilerplate-url">;
|
|
54
|
+
}
|
|
55
|
+
/**
|
|
56
|
+
* Heuristic boilerplate-page detection. Single-signal trigger (1+ = positive)
|
|
57
|
+
* because the patterns are anchored and specific — a marketing page that
|
|
58
|
+
* merely mentions "privacy" in its body won't fire any signal. Cookie / legal
|
|
59
|
+
* / consent / imprint pages exist for compliance, never as SEO targets, so
|
|
60
|
+
* auditing them produces routine findings the user already knows about.
|
|
61
|
+
*/
|
|
62
|
+
export declare function detectBoilerplatePage(page: ParsedPage): BoilerplateDetectionResult;
|
|
63
|
+
/**
|
|
64
|
+
* Returns true when the URL has search-result hallmarks: a recognised search
|
|
65
|
+
* query parameter (`?q=`, `?query=`, `?search=`, `?s=`, `?keyword=`) or a
|
|
66
|
+
* pathname of `/search` or starting with `/search/`. Returns false for
|
|
67
|
+
* unparseable URLs (e.g. filesystem paths from local directory audits).
|
|
68
|
+
*/
|
|
69
|
+
export declare function detectSearchResultPage(page: ParsedPage): boolean;
|
|
70
|
+
export interface EmptyBodyDetectionResult {
|
|
71
|
+
isEmpty: boolean;
|
|
72
|
+
reason?: string;
|
|
73
|
+
}
|
|
74
|
+
/**
|
|
75
|
+
* Heuristic detection of un-hydrated SPA shells. Three conditions must hold:
|
|
76
|
+
* 1. `contentText` (post-render-or-parse body text) trimmed < 100 chars
|
|
77
|
+
* 2. The HTML contains at least one `<script src=...>` tag (script-driven)
|
|
78
|
+
* 3. No substantive `<noscript>` fallback (combined noscript content
|
|
79
|
+
* <= 200 chars). A page with a long noscript block is doing
|
|
80
|
+
* progressive enhancement, not failing — don't flag it.
|
|
81
|
+
*
|
|
82
|
+
* Returns `{ isEmpty: true, reason: "spa-shell" }` when all three hold.
|
|
83
|
+
*/
|
|
84
|
+
export declare function detectEmptyBodyPage(page: ParsedPage): EmptyBodyDetectionResult;
|
|
85
|
+
/**
|
|
86
|
+
* Combined skip decision for the auditor pipeline. Returns the reason string
|
|
87
|
+
* to surface in `summary.skippedUrls` diagnostics, or `null` when the page
|
|
88
|
+
* should be audited normally. Order matters — the priority is:
|
|
89
|
+
* `noindex` > `auth-detected` > `boilerplate` > `search-result` > `spa-shell`.
|
|
90
|
+
*
|
|
91
|
+
* - `noindex` first: the site-owner-declared signal beats every heuristic.
|
|
92
|
+
* - `auth-detected` next: a confirmed auth surface wins over generic
|
|
93
|
+
* boilerplate / search / shell heuristics.
|
|
94
|
+
* - `boilerplate` next: a clearly compliance-page-shaped URL beats the
|
|
95
|
+
* generic search/shell signals.
|
|
96
|
+
* - `search-result` next: explicit search hallmarks beat the empty-body
|
|
97
|
+
* fallback (a search page MAY be a SPA but the better label is "search").
|
|
98
|
+
* - `spa-shell` last: the most generic "we couldn't audit this" reason.
|
|
99
|
+
*/
|
|
100
|
+
export interface PageSkipOptions {
|
|
101
|
+
respectNoindex: boolean;
|
|
102
|
+
skipDetectedAuth: boolean;
|
|
103
|
+
skipBoilerplate: boolean;
|
|
104
|
+
skipSearchPages: boolean;
|
|
105
|
+
skipEmptyBody: boolean;
|
|
106
|
+
}
|
|
107
|
+
export declare function pageSkipReason(page: ParsedPage, options: PageSkipOptions): "noindex" | "auth-detected" | "boilerplate" | "search-result" | "spa-shell" | null;
|
|
108
|
+
//# sourceMappingURL=page-filter.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"page-filter.d.ts","sourceRoot":"","sources":["../src/page-filter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAEH,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAE7C;;;;;;GAMG;AACH,wBAAgB,aAAa,CAAC,IAAI,EAAE,UAAU,GAAG,OAAO,CAIvD;AA6BD,MAAM,WAAW,mBAAmB;IAClC,MAAM,EAAE,OAAO,CAAC;IAChB,OAAO,EAAE,KAAK,CAAC,gBAAgB,GAAG,YAAY,GAAG,SAAS,CAAC,CAAC;CAC7D;AAED;;;;;GAKG;AACH,wBAAgB,cAAc,CAAC,IAAI,EAAE,UAAU,GAAG,mBAAmB,CAqBpE;AAkBD,MAAM,WAAW,0BAA0B;IACzC,aAAa,EAAE,OAAO,CAAC;IACvB,OAAO,EAAE,KAAK,CAAC,mBAAmB,GAAG,gBAAgB,GAAG,iBAAiB,CAAC,CAAC;CAC5E;AAED;;;;;;GAMG;AACH,wBAAgB,qBAAqB,CAAC,IAAI,EAAE,UAAU,GAAG,0BAA0B,CAyBlF;AASD;;;;;GAKG;AACH,wBAAgB,sBAAsB,CAAC,IAAI,EAAE,UAAU,GAAG,OAAO,CAgBhE;AAED,MAAM,WAAW,wBAAwB;IACvC,OAAO,EAAE,OAAO,CAAC;IACjB,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED;;;;;;;;;GASG;AACH,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,UAAU,GAAG,wBAAwB,CAoB9E;AAED;;;;;;;;;;;;;;GAcG;AACH,MAAM,WAAW,eAAe;IAC9B,cAAc,EAAE,OAAO,CAAC;IACxB,gBAAgB,EAAE,OAAO,CAAC;IAC1B,eAAe,EAAE,OAAO,CAAC;IACzB,eAAe,EAAE,OAAO,CAAC;IACzB,aAAa,EAAE,OAAO,CAAC;CACxB;AAED,wBAAgB,cAAc,CAC5B,IAAI,EAAE,UAAU,EAChB,OAAO,EAAE,eAAe,GACvB,SAAS,GAAG,eAAe,GAAG,aAAa,GAAG,eAAe,GAAG,WAAW,GAAG,IAAI,CAOpF"}
|
|
@@ -0,0 +1,207 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Page-skip detection helpers used by the auditor pipeline (v0.4.1+).
|
|
3
|
+
*
|
|
4
|
+
* Five policy filters live here, each gated by an AuditOption:
|
|
5
|
+
* - `detectNoindex(page)` honours `<meta name="robots" content="noindex">`
|
|
6
|
+
* and `X-Robots-Tag: noindex` HTTP headers. The site owner already told
|
|
7
|
+
* Google not to index these pages — auditing them produces noise the
|
|
8
|
+
* reader can't act on.
|
|
9
|
+
* - `detectAuthPage(page)` heuristically classifies pages as
|
|
10
|
+
* login / signup / password-reset based on three signals (password input
|
|
11
|
+
* in a thin body, title matches the auth regex, H1 matches the auth
|
|
12
|
+
* regex). Two signals are required for a positive verdict, which keeps
|
|
13
|
+
* the false-positive rate low: a marketing landing page with a single
|
|
14
|
+
* password input or a single auth-shaped heading won't trip it.
|
|
15
|
+
* - `detectBoilerplatePage(page)` (v0.4.2) flags cookie / legal / consent /
|
|
16
|
+
* imprint pages. A single signal is enough because the patterns are
|
|
17
|
+
* anchored + specific (the title or H1 matches the whole-string compliance
|
|
18
|
+
* regex, or the URL path is one of the well-known compliance slugs).
|
|
19
|
+
* - `detectSearchResultPage(page)` (v0.4.2) flags pages that look like
|
|
20
|
+
* internal search-result URLs (query parameter `q` / `query` / `search` /
|
|
21
|
+
* `s` / `keyword`, or path under `/search`). Per Google's own guidance
|
|
22
|
+
* these should be noindex'd — auditing them generates noise.
|
|
23
|
+
* - `detectEmptyBodyPage(page)` (v0.4.2) flags un-hydrated SPA shells:
|
|
24
|
+
* body text < 100 chars, script tags present, and no substantive
|
|
25
|
+
* `<noscript>` fallback. These fail every content rule but the underlying
|
|
26
|
+
* fix is server-side rendering, not content quality.
|
|
27
|
+
*
|
|
28
|
+
* All functions are pure and synchronous so they can be called inside the
|
|
29
|
+
* `parsedPages` map step without disrupting the existing pipeline shape.
|
|
30
|
+
*/
|
|
31
|
+
/**
|
|
32
|
+
* Returns true when the page is explicitly noindex'd via either the parsed
|
|
33
|
+
* `<meta name="robots">` content or the `X-Robots-Tag` HTTP response header.
|
|
34
|
+
* Match is case-insensitive and substring-based to tolerate combined
|
|
35
|
+
* directives like `"noindex, nofollow"` or `"index, noindex"` (the latter is
|
|
36
|
+
* a common bug — `noindex` wins per spec).
|
|
37
|
+
*/
|
|
38
|
+
export function detectNoindex(page) {
|
|
39
|
+
const metaRobots = (page.robotsMeta ?? "").toLowerCase();
|
|
40
|
+
const xRobots = (page.httpMeta?.xRobotsTag ?? "").toLowerCase();
|
|
41
|
+
return metaRobots.includes("noindex") || xRobots.includes("noindex");
|
|
42
|
+
}
|
|
43
|
+
/**
|
|
44
|
+
* Auth-shaped page title pattern, applied AFTER stripping the brand suffix.
|
|
45
|
+
* Matches "Sign in", "Sign-In", "Log in", "Log-Out", "Register", "Sign up",
|
|
46
|
+
* "Forgot password", "Reset password", "Create account", "Verify email" and
|
|
47
|
+
* common variants. Case-insensitive; whole-string match (anchored).
|
|
48
|
+
*/
|
|
49
|
+
const AUTH_TITLE_REGEX = /^(sign[-\s]?in|sign[-\s]?up|sign[-\s]?out|log[-\s]?in|log[-\s]?out|register|forgot[-\s]password|reset[-\s]password|create[-\s](?:an[-\s])?account|verify[-\s](?:your[-\s])?email|two[-\s]?factor|account[-\s]recovery)$/i;
|
|
50
|
+
/**
|
|
51
|
+
* Common brand-suffix separators. We split on the FIRST occurrence and keep
|
|
52
|
+
* everything before it — typical pattern is `Sign in | MyApp` or
|
|
53
|
+
* `Sign in - MyApp` or `Sign in · MyApp`. Without this strip, the regex
|
|
54
|
+
* would never match because the title would be `Sign in | MyApp`, not just
|
|
55
|
+
* `Sign in`.
|
|
56
|
+
*/
|
|
57
|
+
const BRAND_SEPARATORS = [" | ", " - ", " — ", " · ", " : ", " :: "];
|
|
58
|
+
function stripBrandSuffix(title) {
|
|
59
|
+
let cut = title.length;
|
|
60
|
+
for (const sep of BRAND_SEPARATORS) {
|
|
61
|
+
const idx = title.indexOf(sep);
|
|
62
|
+
if (idx >= 0 && idx < cut)
|
|
63
|
+
cut = idx;
|
|
64
|
+
}
|
|
65
|
+
return title.slice(0, cut).trim();
|
|
66
|
+
}
|
|
67
|
+
/**
|
|
68
|
+
* Heuristic auth-page detection. Returns `isAuth: true` when 2+ signals
|
|
69
|
+
* fire (high confidence). Single-signal pages return `isAuth: false` but
|
|
70
|
+
* still expose the signal list for diagnostics — useful for tracking
|
|
71
|
+
* borderline cases that might warrant a manual config exclude.
|
|
72
|
+
*/
|
|
73
|
+
export function detectAuthPage(page) {
|
|
74
|
+
const signals = [];
|
|
75
|
+
const wordCount = (page.contentText ?? "").split(/\s+/).filter(Boolean).length;
|
|
76
|
+
const h2Count = (page.headings?.h2 ?? []).length;
|
|
77
|
+
const hasPasswordInput = /<input\b[^>]*\btype\s*=\s*["']?password["']?/i.test(page.html ?? "");
|
|
78
|
+
if (hasPasswordInput && wordCount < 200 && h2Count < 3) {
|
|
79
|
+
signals.push("password-input");
|
|
80
|
+
}
|
|
81
|
+
const cleanedTitle = stripBrandSuffix(page.title ?? "");
|
|
82
|
+
if (cleanedTitle && AUTH_TITLE_REGEX.test(cleanedTitle)) {
|
|
83
|
+
signals.push("auth-title");
|
|
84
|
+
}
|
|
85
|
+
const firstH1 = (page.headings?.h1 ?? [])[0]?.trim() ?? "";
|
|
86
|
+
if (firstH1 && AUTH_TITLE_REGEX.test(firstH1)) {
|
|
87
|
+
signals.push("auth-h1");
|
|
88
|
+
}
|
|
89
|
+
return { isAuth: signals.length >= 2, signals };
|
|
90
|
+
}
|
|
91
|
+
/**
|
|
92
|
+
* Boilerplate (cookie / legal / consent / imprint) title and H1 pattern.
|
|
93
|
+
* Whole-string match (anchored), case-insensitive. Applied to the title
|
|
94
|
+
* AFTER stripping the brand suffix (`Privacy Policy | MyApp` → `Privacy`).
|
|
95
|
+
*/
|
|
96
|
+
const BOILERPLATE_TITLE_REGEX = /^(cookie|cookies|cookie[-\s]?policy|gdpr|ccpa|privacy|terms|terms[-\s](?:of[-\s])?(?:use|service|sale)|legal|disclaimer|impressum|imprint|do[-\s]not[-\s]sell|accessibility(?:[-\s]statement)?|copyright[-\s]notice)$/i;
|
|
97
|
+
/**
|
|
98
|
+
* Boilerplate URL pathname pattern. Matches `/cookies`, `/cookie-policy`,
|
|
99
|
+
* `/privacy`, `/terms/anything`, `/impressum`, etc. Anchored at path start
|
|
100
|
+
* so a marketing URL like `/blog/privacy-by-design` is NOT matched.
|
|
101
|
+
*/
|
|
102
|
+
const BOILERPLATE_URL_REGEX = /^\/(?:cookies?|cookie-policy|gdpr|ccpa|privacy|terms|legal|disclaimer|impressum|imprint|accessibility|do-not-sell|copyright)(?:\/.*)?$/i;
|
|
103
|
+
/**
|
|
104
|
+
* Heuristic boilerplate-page detection. Single-signal trigger (1+ = positive)
|
|
105
|
+
* because the patterns are anchored and specific — a marketing page that
|
|
106
|
+
* merely mentions "privacy" in its body won't fire any signal. Cookie / legal
|
|
107
|
+
* / consent / imprint pages exist for compliance, never as SEO targets, so
|
|
108
|
+
* auditing them produces routine findings the user already knows about.
|
|
109
|
+
*/
|
|
110
|
+
export function detectBoilerplatePage(page) {
|
|
111
|
+
const signals = [];
|
|
112
|
+
const cleanedTitle = stripBrandSuffix(page.title ?? "");
|
|
113
|
+
if (cleanedTitle && BOILERPLATE_TITLE_REGEX.test(cleanedTitle)) {
|
|
114
|
+
signals.push("boilerplate-title");
|
|
115
|
+
}
|
|
116
|
+
const firstH1 = (page.headings?.h1 ?? [])[0]?.trim() ?? "";
|
|
117
|
+
if (firstH1 && BOILERPLATE_TITLE_REGEX.test(firstH1)) {
|
|
118
|
+
signals.push("boilerplate-h1");
|
|
119
|
+
}
|
|
120
|
+
// URL pathname check. `page.url` may be a filesystem path on local audits,
|
|
121
|
+
// so wrap the URL parse in try/catch and skip the signal on failure.
|
|
122
|
+
try {
|
|
123
|
+
const pathname = new URL(page.url).pathname;
|
|
124
|
+
if (BOILERPLATE_URL_REGEX.test(pathname)) {
|
|
125
|
+
signals.push("boilerplate-url");
|
|
126
|
+
}
|
|
127
|
+
}
|
|
128
|
+
catch {
|
|
129
|
+
// unparseable URL (filesystem path); skip the URL signal
|
|
130
|
+
}
|
|
131
|
+
return { isBoilerplate: signals.length >= 1, signals };
|
|
132
|
+
}
|
|
133
|
+
/**
|
|
134
|
+
* Search-result query parameter names we treat as evidence of an internal
|
|
135
|
+
* search-result page. Compared case-insensitively against the URL's
|
|
136
|
+
* searchParams keys.
|
|
137
|
+
*/
|
|
138
|
+
const SEARCH_QUERY_PARAMS = new Set(["q", "query", "search", "s", "keyword"]);
|
|
139
|
+
/**
|
|
140
|
+
* Returns true when the URL has search-result hallmarks: a recognised search
|
|
141
|
+
* query parameter (`?q=`, `?query=`, `?search=`, `?s=`, `?keyword=`) or a
|
|
142
|
+
* pathname of `/search` or starting with `/search/`. Returns false for
|
|
143
|
+
* unparseable URLs (e.g. filesystem paths from local directory audits).
|
|
144
|
+
*/
|
|
145
|
+
export function detectSearchResultPage(page) {
|
|
146
|
+
let parsed;
|
|
147
|
+
try {
|
|
148
|
+
parsed = new URL(page.url);
|
|
149
|
+
}
|
|
150
|
+
catch {
|
|
151
|
+
return false;
|
|
152
|
+
}
|
|
153
|
+
for (const key of parsed.searchParams.keys()) {
|
|
154
|
+
if (SEARCH_QUERY_PARAMS.has(key.toLowerCase()))
|
|
155
|
+
return true;
|
|
156
|
+
}
|
|
157
|
+
const pathname = parsed.pathname;
|
|
158
|
+
if (pathname === "/search" || pathname.startsWith("/search/"))
|
|
159
|
+
return true;
|
|
160
|
+
return false;
|
|
161
|
+
}
|
|
162
|
+
/**
|
|
163
|
+
* Heuristic detection of un-hydrated SPA shells. Three conditions must hold:
|
|
164
|
+
* 1. `contentText` (post-render-or-parse body text) trimmed < 100 chars
|
|
165
|
+
* 2. The HTML contains at least one `<script src=...>` tag (script-driven)
|
|
166
|
+
* 3. No substantive `<noscript>` fallback (combined noscript content
|
|
167
|
+
* <= 200 chars). A page with a long noscript block is doing
|
|
168
|
+
* progressive enhancement, not failing — don't flag it.
|
|
169
|
+
*
|
|
170
|
+
* Returns `{ isEmpty: true, reason: "spa-shell" }` when all three hold.
|
|
171
|
+
*/
|
|
172
|
+
export function detectEmptyBodyPage(page) {
|
|
173
|
+
const bodyLen = (page.contentText ?? "").trim().length;
|
|
174
|
+
if (bodyLen >= 100)
|
|
175
|
+
return { isEmpty: false };
|
|
176
|
+
const html = page.html ?? "";
|
|
177
|
+
if (!/<script\s[^>]*src\s*=/i.test(html))
|
|
178
|
+
return { isEmpty: false };
|
|
179
|
+
// Sum the visible content length of every <noscript>...</noscript> block.
|
|
180
|
+
// If the site provides a substantive noscript fallback, it's a
|
|
181
|
+
// progressive-enhancement page, not a broken SPA shell.
|
|
182
|
+
let noscriptTextLen = 0;
|
|
183
|
+
const noscriptRe = /<noscript[^>]*>([\s\S]*?)<\/noscript>/gi;
|
|
184
|
+
let match;
|
|
185
|
+
while ((match = noscriptRe.exec(html)) !== null) {
|
|
186
|
+
noscriptTextLen += match[1].replace(/<[^>]+>/g, "").trim().length;
|
|
187
|
+
if (noscriptTextLen > 200)
|
|
188
|
+
break;
|
|
189
|
+
}
|
|
190
|
+
if (noscriptTextLen > 200)
|
|
191
|
+
return { isEmpty: false };
|
|
192
|
+
return { isEmpty: true, reason: "spa-shell" };
|
|
193
|
+
}
|
|
194
|
+
export function pageSkipReason(page, options) {
|
|
195
|
+
if (options.respectNoindex && detectNoindex(page))
|
|
196
|
+
return "noindex";
|
|
197
|
+
if (options.skipDetectedAuth && detectAuthPage(page).isAuth)
|
|
198
|
+
return "auth-detected";
|
|
199
|
+
if (options.skipBoilerplate && detectBoilerplatePage(page).isBoilerplate)
|
|
200
|
+
return "boilerplate";
|
|
201
|
+
if (options.skipSearchPages && detectSearchResultPage(page))
|
|
202
|
+
return "search-result";
|
|
203
|
+
if (options.skipEmptyBody && detectEmptyBodyPage(page).isEmpty)
|
|
204
|
+
return "spa-shell";
|
|
205
|
+
return null;
|
|
206
|
+
}
|
|
207
|
+
//# sourceMappingURL=page-filter.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"page-filter.js","sourceRoot":"","sources":["../src/page-filter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAIH;;;;;;GAMG;AACH,MAAM,UAAU,aAAa,CAAC,IAAgB;IAC5C,MAAM,UAAU,GAAG,CAAC,IAAI,CAAC,UAAU,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC;IACzD,MAAM,OAAO,GAAG,CAAC,IAAI,CAAC,QAAQ,EAAE,UAAU,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC;IAChE,OAAO,UAAU,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC;AACvE,CAAC;AAED;;;;;GAKG;AACH,MAAM,gBAAgB,GACpB,0NAA0N,CAAC;AAE7N;;;;;;GAMG;AACH,MAAM,gBAAgB,GAAG,CAAC,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM,CAAC,CAAC;AAErE,SAAS,gBAAgB,CAAC,KAAa;IACrC,IAAI,GAAG,GAAG,KAAK,CAAC,MAAM,CAAC;IACvB,KAAK,MAAM,GAAG,IAAI,gBAAgB,EAAE,CAAC;QACnC,MAAM,GAAG,GAAG,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;QAC/B,IAAI,GAAG,IAAI,CAAC,IAAI,GAAG,GAAG,GAAG;YAAE,GAAG,GAAG,GAAG,CAAC;IACvC,CAAC;IACD,OAAO,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;AACpC,CAAC;AAOD;;;;;GAKG;AACH,MAAM,UAAU,cAAc,CAAC,IAAgB;IAC7C,MAAM,OAAO,GAAmC,EAAE,CAAC;IAEnD,MAAM,SAAS,GAAG,CAAC,IAAI,CAAC,WAAW,IAAI,EAAE,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,MAAM,CAAC;IAC/E,MAAM,OAAO,GAAG,CAAC,IAAI,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC;IACjD,MAAM,gBAAgB,GAAG,+CAA+C,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC;IAC/F,IAAI,gBAAgB,IAAI,SAAS,GAAG,GAAG,IAAI,OAAO,GAAG,CAAC,EAAE,CAAC;QACvD,OAAO,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAC;IACjC,CAAC;IAED,MAAM,YAAY,GAAG,gBAAgB,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC;IACxD,IAAI,YAAY,IAAI,gBAAgB,CAAC,IAAI,CAAC,YAAY,CAAC,EAAE,CAAC;QACxD,OAAO,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;IAC7B,CAAC;IAED,MAAM,OAAO,GAAG,CAAC,IAAI,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC;IAC3D,IAAI,OAAO,IAAI,gBAAgB,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QAC9C,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IAC1B,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,IAAI,CAAC,EAAE,OAAO,EAAE,CAAC;AAClD,CAAC;AAED;;;;GAIG;AACH,MAAM,uBAAuB,GAC3B,wNAAwN,CAAC;AAE3N;;;;GAIG;AACH,MAAM,qBAAqB,GACzB,yIAAyI,CAAC;AAO5I;;;;;;GAMG;AACH,MAAM,UAAU,qBAAqB,CAAC,IAAgB;IACpD,MAAM,OAAO,GAA0C,EAAE,CAAC;IAE1D,MAAM,YAAY,GAAG,gBAAgB,CAAC,IAAI,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC;IACxD,IAAI,YAAY,IAAI,uBAAuB,CAAC,IAAI,CAAC,YAAY,CAAC,EAAE,CAAC;QAC/D,OAAO,CAAC,IAAI,CAAC,mBAAmB,CAAC,CAAC;IACpC,CAAC;IAED,MAAM,OAAO,GAAG,CAAC,IAAI,CAAC,QAAQ,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC;IAC3D,IAAI,OAAO,IAAI,uBAAuB,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QACrD,OAAO,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAC;IACjC,CAAC;IAED,2EAA2E;IAC3E,qEAAqE;IACrE,IAAI,CAAC;QACH,MAAM,QAAQ,GAAG,IAAI,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC5C,IAAI,qBAAqB,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC;YACzC,OAAO,CAAC,IAAI,CAAC,iBAAiB,CAAC,CAAC;QAClC,CAAC;IACH,CAAC;IAAC,MAAM,CAAC;QACP,yDAAyD;IAC3D,CAAC;IAED,OAAO,EAAE,aAAa,EAAE,OAAO,CAAC,MAAM,IAAI,CAAC,EAAE,OAAO,EAAE,CAAC;AACzD,CAAC;AAED;;;;GAIG;AACH,MAAM,mBAAmB,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,EAAE,OAAO,EAAE,QAAQ,EAAE,GAAG,EAAE,SAAS,CAAC,CAAC,CAAC;AAE9E;;;;;GAKG;AACH,MAAM,UAAU,sBAAsB,CAAC,IAAgB;IACrD,IAAI,MAAW,CAAC;IAChB,IAAI,CAAC;QACH,MAAM,GAAG,IAAI,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IAC7B,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,KAAK,CAAC;IACf,CAAC;IAED,KAAK,MAAM,GAAG,IAAI,MAAM,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,CAAC;QAC7C,IAAI,mBAAmB,CAAC,GAAG,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC;YAAE,OAAO,IAAI,CAAC;IAC9D,CAAC;IAED,MAAM,QAAQ,GAAG,MAAM,CAAC,QAAQ,CAAC;IACjC,IAAI,QAAQ,KAAK,SAAS,IAAI,QAAQ,CAAC,UAAU,CAAC,UAAU,CAAC;QAAE,OAAO,IAAI,CAAC;IAE3E,OAAO,KAAK,CAAC;AACf,CAAC;AAOD;;;;;;;;;GASG;AACH,MAAM,UAAU,mBAAmB,CAAC,IAAgB;IAClD,MAAM,OAAO,GAAG,CAAC,IAAI,CAAC,WAAW,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,MAAM,CAAC;IACvD,IAAI,OAAO,IAAI,GAAG;QAAE,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC;IAE9C,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,IAAI,EAAE,CAAC;IAC7B,IAAI,CAAC,wBAAwB,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC;IAEpE,0EAA0E;IAC1E,+DAA+D;IAC/D,wDAAwD;IACxD,IAAI,eAAe,GAAG,CAAC,CAAC;IACxB,MAAM,UAAU,GAAG,yCAAyC,CAAC;IAC7D,IAAI,KAA6B,CAAC;IAClC,OAAO,CAAC,KAAK,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QAChD,eAAe,IAAI,KAAK,CAAC,CAAC,CAAE,CAAC,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,MAAM,CAAC;QACnE,IAAI,eAAe,GAAG,GAAG;YAAE,MAAM;IACnC,CAAC;IACD,IAAI,eAAe,GAAG,GAAG;QAAE,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC;IAErD,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,CAAC;AAChD,CAAC;AAyBD,MAAM,UAAU,cAAc,CAC5B,IAAgB,EAChB,OAAwB;IAExB,IAAI,OAAO,CAAC,cAAc,IAAI,aAAa,CAAC,IAAI,CAAC;QAAE,OAAO,SAAS,CAAC;IACpE,IAAI,OAAO,CAAC,gBAAgB,IAAI,cAAc,CAAC,IAAI,CAAC,CAAC,MAAM;QAAE,OAAO,eAAe,CAAC;IACpF,IAAI,OAAO,CAAC,eAAe,IAAI,qBAAqB,CAAC,IAAI,CAAC,CAAC,aAAa;QAAE,OAAO,aAAa,CAAC;IAC/F,IAAI,OAAO,CAAC,eAAe,IAAI,sBAAsB,CAAC,IAAI,CAAC;QAAE,OAAO,eAAe,CAAC;IACpF,IAAI,OAAO,CAAC,aAAa,IAAI,mBAAmB,CAAC,IAAI,CAAC,CAAC,OAAO;QAAE,OAAO,WAAW,CAAC;IACnF,OAAO,IAAI,CAAC;AACd,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"answer-first.d.ts","sourceRoot":"","sources":["../../../src/rules/aeo/answer-first.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,
|
|
1
|
+
{"version":3,"file":"answer-first.d.ts","sourceRoot":"","sources":["../../../src/rules/aeo/answer-first.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAc,iBAAiB,EAAE,UAAU,EAAE,UAAU,EAAE,MAAM,gBAAgB,CAAC;AAE5F,MAAM,WAAW,kBAAkB;IACjC,0FAA0F;IAC1F,sBAAsB,CAAC,EAAE,MAAM,CAAC;IAChC,iFAAiF;IACjF,qBAAqB,CAAC,EAAE,MAAM,CAAC;IAC/B,6DAA6D;IAC7D,cAAc,CAAC,EAAE,MAAM,CAAC;CACzB;AA6BD;;;;;GAKG;AACH,wBAAgB,qBAAqB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CA0D1D;AA8CD,wBAAgB,eAAe,CAC7B,KAAK,EAAE,UAAU,EAAE,EACnB,cAAc,EAAE,iBAAiB,EAAE,EACnC,OAAO,CAAC,EAAE,kBAAkB,GAC3B,UAAU,EAAE,CA4Ed"}
|