@ijonis/geo-lint 0.1.4 → 0.2.0

package/dist/index.d.cts

@@ -161,6 +161,10 @@ interface GeoConfig {
     genericAuthorNames?: string[];
     /** MDX component tags allowed in markdown (not flagged by inline-html rule) */
     allowedHtmlTags?: string[];
+    /** Organization sameAs URLs for entity verification (LinkedIn, GitHub, Wikidata QID, etc.) */
+    organizationSameAs?: string[];
+    /** URL patterns identifying service pages (e.g. ['/services/', '/leistungen/']) */
+    servicePagePatterns?: string[];
 }
 /** Internationalization configuration */
 interface I18nConfig {
@@ -169,6 +173,13 @@ interface I18nConfig {
     /** Default locale — maps to hreflang x-default. Must be in locales array */
     defaultLocale: string;
 }
+/** Technical site-level configuration */
+interface TechnicalConfig {
+    /** Declared feed URLs (e.g. ['/feed.xml', '/rss.xml']) */
+    feedUrls?: string[];
+    /** Path to llms.txt file (e.g. '/llms.txt') */
+    llmsTxtUrl?: string;
+}
 /** User-facing configuration (partial, with defaults applied) */
 interface GeoLintUserConfig {
     /** Canonical site URL, e.g. 'https://example.com' (required) */
@@ -189,6 +200,8 @@ interface GeoLintUserConfig {
     geo?: Partial<GeoConfig>;
     /** Internationalization configuration */
     i18n?: Partial<I18nConfig>;
+    /** Technical site-level configuration */
+    technical?: Partial<TechnicalConfig>;
     /** Rule severity overrides: 'off' disables a rule */
     rules?: Record<string, 'error' | 'warning' | 'off'>;
     /** Threshold overrides */
@@ -227,6 +240,8 @@ interface GeoLintConfig {
     excludeCategories: string[];
     geo: GeoConfig;
     i18n: I18nConfig;
+    /** Technical site-level configuration */
+    technical: TechnicalConfig;
     rules: Record<string, 'error' | 'warning' | 'off'>;
     thresholds: ThresholdConfig;
 }
@@ -299,4 +314,4 @@ declare function lint(options?: LintOptions): Promise<number>;
  */
 declare function lintQuiet(options?: LintOptions): Promise<LintResult[]>;
 
-export { type ContentAdapter, type ContentItem, type ContentPathConfig, type ContentType, type ExtractedImage, type ExtractedLink, type GeoConfig, type GeoLintConfig, type GeoLintUserConfig, type GlobalRule, type Heading, type I18nConfig, type LintOptions, type LintResult, type Rule, type RuleContext, type Severity, type ThresholdConfig, createAdapter, defineConfig, lint, lintQuiet, loadContentItems };
+export { type ContentAdapter, type ContentItem, type ContentPathConfig, type ContentType, type ExtractedImage, type ExtractedLink, type GeoConfig, type GeoLintConfig, type GeoLintUserConfig, type GlobalRule, type Heading, type I18nConfig, type LintOptions, type LintResult, type Rule, type RuleContext, type Severity, type TechnicalConfig, type ThresholdConfig, createAdapter, defineConfig, lint, lintQuiet, loadContentItems };

package/dist/index.d.ts

@@ -161,6 +161,10 @@ interface GeoConfig {
     genericAuthorNames?: string[];
     /** MDX component tags allowed in markdown (not flagged by inline-html rule) */
     allowedHtmlTags?: string[];
+    /** Organization sameAs URLs for entity verification (LinkedIn, GitHub, Wikidata QID, etc.) */
+    organizationSameAs?: string[];
+    /** URL patterns identifying service pages (e.g. ['/services/', '/leistungen/']) */
+    servicePagePatterns?: string[];
 }
 /** Internationalization configuration */
 interface I18nConfig {
@@ -169,6 +173,13 @@ interface I18nConfig {
     /** Default locale — maps to hreflang x-default. Must be in locales array */
     defaultLocale: string;
 }
+/** Technical site-level configuration */
+interface TechnicalConfig {
+    /** Declared feed URLs (e.g. ['/feed.xml', '/rss.xml']) */
+    feedUrls?: string[];
+    /** Path to llms.txt file (e.g. '/llms.txt') */
+    llmsTxtUrl?: string;
+}
 /** User-facing configuration (partial, with defaults applied) */
 interface GeoLintUserConfig {
     /** Canonical site URL, e.g. 'https://example.com' (required) */
@@ -189,6 +200,8 @@ interface GeoLintUserConfig {
     geo?: Partial<GeoConfig>;
     /** Internationalization configuration */
     i18n?: Partial<I18nConfig>;
+    /** Technical site-level configuration */
+    technical?: Partial<TechnicalConfig>;
     /** Rule severity overrides: 'off' disables a rule */
     rules?: Record<string, 'error' | 'warning' | 'off'>;
     /** Threshold overrides */
@@ -227,6 +240,8 @@ interface GeoLintConfig {
     excludeCategories: string[];
     geo: GeoConfig;
     i18n: I18nConfig;
+    /** Technical site-level configuration */
+    technical: TechnicalConfig;
     rules: Record<string, 'error' | 'warning' | 'off'>;
     thresholds: ThresholdConfig;
 }
@@ -299,4 +314,4 @@ declare function lint(options?: LintOptions): Promise<number>;
  */
 declare function lintQuiet(options?: LintOptions): Promise<LintResult[]>;
 
-export { type ContentAdapter, type ContentItem, type ContentPathConfig, type ContentType, type ExtractedImage, type ExtractedLink, type GeoConfig, type GeoLintConfig, type GeoLintUserConfig, type GlobalRule, type Heading, type I18nConfig, type LintOptions, type LintResult, type Rule, type RuleContext, type Severity, type ThresholdConfig, createAdapter, defineConfig, lint, lintQuiet, loadContentItems };
+export { type ContentAdapter, type ContentItem, type ContentPathConfig, type ContentType, type ExtractedImage, type ExtractedLink, type GeoConfig, type GeoLintConfig, type GeoLintUserConfig, type GlobalRule, type Heading, type I18nConfig, type LintOptions, type LintResult, type Rule, type RuleContext, type Severity, type TechnicalConfig, type ThresholdConfig, createAdapter, defineConfig, lint, lintQuiet, loadContentItems };

package/dist/index.js

@@ -147,7 +147,13 @@ var DEFAULT_CONFIG = {
       "Tabs",
       "Tab"
     ],
-    enabledContentTypes: ["blog"]
+    enabledContentTypes: ["blog"],
+    organizationSameAs: [],
+    servicePagePatterns: []
+  },
+  technical: {
+    feedUrls: [],
+    llmsTxtUrl: ""
   },
   i18n: {
     locales: ["de", "en"],
@@ -222,12 +228,18 @@ function mergeWithDefaults(user) {
       acronymAllowlist: user.geo?.acronymAllowlist ?? DEFAULT_CONFIG.geo.acronymAllowlist,
       vagueHeadings: user.geo?.vagueHeadings ?? DEFAULT_CONFIG.geo.vagueHeadings,
       genericAuthorNames: user.geo?.genericAuthorNames ?? DEFAULT_CONFIG.geo.genericAuthorNames,
-      allowedHtmlTags: user.geo?.allowedHtmlTags ?? DEFAULT_CONFIG.geo.allowedHtmlTags
+      allowedHtmlTags: user.geo?.allowedHtmlTags ?? DEFAULT_CONFIG.geo.allowedHtmlTags,
+      organizationSameAs: user.geo?.organizationSameAs ?? DEFAULT_CONFIG.geo.organizationSameAs,
+      servicePagePatterns: user.geo?.servicePagePatterns ?? DEFAULT_CONFIG.geo.servicePagePatterns
     },
     i18n: {
       locales: user.i18n?.locales ?? DEFAULT_CONFIG.i18n.locales,
       defaultLocale: user.i18n?.defaultLocale ?? DEFAULT_CONFIG.i18n.defaultLocale
     },
+    technical: {
+      feedUrls: user.technical?.feedUrls ?? DEFAULT_CONFIG.technical.feedUrls,
+      llmsTxtUrl: user.technical?.llmsTxtUrl ?? DEFAULT_CONFIG.technical.llmsTxtUrl
+    },
     rules: { ...DEFAULT_CONFIG.rules, ...user.rules ?? {} },
     thresholds: {
       title: { ...DEFAULT_CONFIG.thresholds.title, ...user.thresholds?.title ?? {} },
@@ -2578,12 +2590,72 @@ var datasetSchemaReadiness = {
     return results;
   }
 };
-var schemaRules = [
+var MIN_SAMEAS_ENTRIES = 2;
+function createSchemaSameAsRule(organizationSameAs) {
+  let hasFired = false;
+  return {
+    name: "seo-schema-sameas-incomplete",
+    severity: "warning",
+    category: "seo",
+    fixStrategy: "Add social profiles (LinkedIn, GitHub, Twitter), Wikidata QID, and Crunchbase URL to Organization schema sameAs array",
+    run: (_item) => {
+      if (hasFired) return [];
+      hasFired = true;
+      if (!organizationSameAs || organizationSameAs.length === 0) return [];
+      if (organizationSameAs.length < MIN_SAMEAS_ENTRIES) {
+        return [
+          {
+            file: "_site",
+            field: "schema",
+            rule: "seo-schema-sameas-incomplete",
+            severity: "warning",
+            message: `Organization sameAs has ${organizationSameAs.length} entry \u2014 include at least ${MIN_SAMEAS_ENTRIES} for entity verification`,
+            suggestion: "AI models use sameAs to verify entity identity. Include at least LinkedIn + one other profile (GitHub, Wikidata QID, Crunchbase)."
+          }
+        ];
+      }
+      return [];
+    }
+  };
+}
+function createServicePageSchemaRule(servicePagePatterns) {
+  return {
+    name: "seo-service-page-no-schema",
+    severity: "warning",
+    category: "seo",
+    fixStrategy: "Add Service structured data (JSON-LD) to service pages with name, description, provider, and areaServed.",
+    run: (item) => {
+      if (!servicePagePatterns || servicePagePatterns.length === 0) return [];
+      const matchesPattern = servicePagePatterns.some(
+        (pattern) => item.permalink.includes(pattern)
+      );
+      if (!matchesPattern) return [];
+      return [
+        {
+          file: getDisplayPath(item),
+          field: "schema",
+          rule: "seo-service-page-no-schema",
+          severity: "warning",
+          message: `Service page "${item.permalink}" should have Service structured data`,
+          suggestion: 'Service pages need schema markup to appear in AI answers for "[service] provider in [city]" queries. Add Service JSON-LD with name, description, provider, and areaServed.'
+        }
+      ];
+    }
+  };
+}
+var schemaStaticRules = [
   blogMissingSchemaFields,
   faqpageSchemaReadiness,
   breadcrumblistSchemaReadiness,
   datasetSchemaReadiness
 ];
+function createSchemaRules(geo) {
+  return [
+    ...schemaStaticRules,
+    createSchemaSameAsRule(geo.organizationSameAs),
+    createServicePageSchemaRule(geo.servicePagePatterns)
+  ];
+}
 
 // src/rules/keyword-coherence-rules.ts
 var MIN_SIGNIFICANT_WORDS = 2;
@@ -14615,6 +14687,58 @@ var geoMissingTldr = {
     return [];
   }
 };
+var ORG_AUTHOR_PATTERNS = [
+  /\bteam\b/i,
+  /\bredaktion\b/i,
+  /\beditorial\b/i,
+  /\beditors?\b/i,
+  /\bherausgeber\b/i,
+  /\bverlag\b/i,
+  /\bredaktionsteam\b/i
+];
+function createGeoAuthorNotPersonRule(brandName) {
+  return {
+    name: "geo-author-not-person",
+    severity: "warning",
+    category: "geo",
+    fixStrategy: "Replace organization name with individual author name. Use Person type in BlogPosting schema for stronger E-E-A-T signals.",
+    run: (item, context) => {
+      const geoTypes = context.geoEnabledContentTypes ?? ["blog"];
+      if (!geoTypes.includes(item.contentType)) return [];
+      if (!item.author || item.author.trim() === "") return [];
+      if (!brandName || brandName.trim() === "") return [];
+      const normalizedAuthor = item.author.trim().toLowerCase();
+      if (normalizedAuthor === brandName.trim().toLowerCase()) {
+        return [
+          {
+            file: getDisplayPath(item),
+            field: "author",
+            rule: "geo-author-not-person",
+            severity: "warning",
+            message: `Author "${item.author}" is the organization name \u2014 use a person's name instead`,
+            suggestion: "AI models cite named experts over faceless organizations. Use the actual author's name for stronger E-E-A-T signals."
+          }
+        ];
+      }
+      const matchesOrgPattern = ORG_AUTHOR_PATTERNS.some(
+        (pattern) => pattern.test(item.author)
+      );
+      if (matchesOrgPattern) {
+        return [
+          {
+            file: getDisplayPath(item),
+            field: "author",
+            rule: "geo-author-not-person",
+            severity: "warning",
+            message: `Author "${item.author}" appears to be an organization or team name`,
+            suggestion: "BlogPosting with author.@type: Person gets cited more than Organization. Use an individual person's name."
+          }
+        ];
+      }
+      return [];
+    }
+  };
+}
 var geoEeatStaticRules = [
   geoMissingSourceCitations,
   geoMissingExpertQuotes,
@@ -14627,7 +14751,8 @@ function createGeoEeatRules(geo) {
   return [
     ...geoEeatStaticRules,
     createGeoMissingAuthorRule(geo.genericAuthorNames ?? []),
-    createGeoHeadingTooVagueRule(geo.vagueHeadings ?? [])
+    createGeoHeadingTooVagueRule(geo.vagueHeadings ?? []),
+    createGeoAuthorNotPersonRule(geo.brandName)
   ];
 }
 
@@ -15616,6 +15741,68 @@ var contentQualityRules = [
   sentenceVariety
 ];
 
+// src/rules/technical-site-rules.ts
+function createNoFeedRule(feedUrls) {
+  let hasFired = false;
+  return {
+    name: "technical-no-feed",
+    severity: "warning",
+    category: "technical",
+    fixStrategy: "Add an RSS or JSON feed endpoint exposing blog posts with full content.",
+    run: (_item, _context) => {
+      if (hasFired) return [];
+      hasFired = true;
+      if (feedUrls === void 0) return [];
+      if (feedUrls.length === 0) {
+        return [
+          {
+            file: "_site",
+            field: "feed",
+            rule: "technical-no-feed",
+            severity: "warning",
+            message: "No RSS/Atom/JSON feed detected \u2014 AI systems lose a structured ingestion path",
+            suggestion: "Feeds provide a structured ingestion path for AI systems beyond crawler discovery. Add an RSS or JSON feed endpoint."
+          }
+        ];
+      }
+      return [];
+    }
+  };
+}
+function createNoLlmsTxtRule(llmsTxtUrl) {
+  let hasFired = false;
+  return {
+    name: "technical-no-llms-txt",
+    severity: "warning",
+    category: "technical",
+    fixStrategy: "Create a /llms.txt endpoint that maps your most important content for LLM consumption in Markdown format.",
+    run: (_item, _context) => {
+      if (hasFired) return [];
+      hasFired = true;
+      if (llmsTxtUrl === void 0) return [];
+      if (llmsTxtUrl.trim() === "") {
+        return [
+          {
+            file: "_site",
+            field: "llms-txt",
+            rule: "technical-no-llms-txt",
+            severity: "warning",
+            message: "No /llms.txt endpoint detected \u2014 missing the emerging standard for LLM content declaration",
+            suggestion: "llms.txt is the robots.txt equivalent for AI \u2014 trivial to add, future-proofs your site for LLM crawlers."
+          }
+        ];
+      }
+      return [];
+    }
+  };
+}
+function createTechnicalSiteRules(technical) {
+  return [
+    createNoFeedRule(technical.feedUrls),
+    createNoLlmsTxtRule(technical.llmsTxtUrl)
+  ];
+}
+
 // src/rules/index.ts
 function buildRules(config, linkExtractor) {
   const rules = [
@@ -15635,7 +15822,7 @@ function buildRules(config, linkExtractor) {
     ...createI18nRules(config.i18n),
     ...dateRules,
     ...config.categories.length > 0 ? createCategoryRules(config.categories) : [],
-    ...schemaRules,
+    ...createSchemaRules(config.geo),
     ...createGeoRules(config.geo),
     ...createGeoEeatRules(config.geo),
     ...geoStructureRules,
@@ -15643,7 +15830,8 @@ function buildRules(config, linkExtractor) {
     ...createGeoRagRules(config.geo),
     ...keywordCoherenceRules,
     ...createCanonicalRules(config.siteUrl),
-    ...contentQualityRules
+    ...contentQualityRules,
+    ...createTechnicalSiteRules(config.technical)
   ];
   return rules.map((rule) => applyRuleOverride(rule, config.rules));
 }
@@ -15832,8 +16020,7 @@ async function lint(options = {}) {
   } else {
     formatResults(results, lintableItems.length, excludedItems.length);
   }
-  const errorCount = results.filter((r) => r.severity === "error").length;
-  return errorCount > 0 ? 1 : 0;
+  return 0;
 }
 async function lintQuiet(options = {}) {
   const projectRoot = resolve2(options.projectRoot ?? process.cwd());