indexflow-seo 0.1.2

High-performance Technical SEO quality gate & GEO (Generative Engine Optimization) auditor for modern search engines and AI crawlers
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223

//! # indexflow-seo
//!
//! A high-performance, lightweight Technical SEO quality gate & GEO (Generative Engine Optimization) auditor.
//!
//! ## Features
//! - Zero-dependency HTML evaluation (HTTP Status, Canonical, noindex, Title, H1, Meta Description)
//! - JSON-LD (Schema.org) structured data extraction and entity mapping (`@graph`, array `@type`)
//! - OpenGraph & Twitter Card social meta parsing
//! - AI Search Engine Bot directive auditing (GPTBot, Perplexity, Claude, Google-Extended)
//! - Non-redirecting fast HTTP prober client (Redirects treated as gate issues)

pub mod canonical;
pub mod evaluator;
pub mod extractor;
pub mod models;

#[cfg(feature = "probe")]
pub mod probe;

pub use canonical::{canonical_matches_page, normalize_url};
pub use evaluator::evaluate_html;
pub use extractor::{decode_basic_entities, inspect_html};
pub use models::*;

#[cfg(feature = "probe")]
pub use probe::SeoProbeClient;

#[cfg(test)]
mod tests {
    use super::*;

    const SAMPLE_HTML_FULL: &str = r#"<!DOCTYPE html>
    <html lang="en">
    <head>
      <meta charset="UTF-8">
      <title>Rust Monolith Guide &amp; SEO Best Practices</title>
      <meta name="description" content="A complete technical SEO guide for modern Rust developers." />
      <meta name="robots" content="index, follow" />
      <link rel="canonical" href="https://example.com/guide" />
      <link rel="alternate" hreflang="zh" href="https://example.com/zh/guide" />
      <link rel="alternate" hreflang="en" href="https://example.com/guide" />
      
      <!-- Social Metadata -->
      <meta property="og:title" content="Rust Monolith Guide" />
      <meta property="og:description" content="Social preview description." />
      <meta property="og:type" content="article" />
      <meta property="og:image" content="https://example.com/cover.jpg" />
      <meta name="twitter:card" content="summary_large_image" />
      
      <!-- AI Bot Directives -->
      <meta name="gptbot" content="noindex" />
      <meta name="perplexitybot" content="index" />
      
      <!-- JSON-LD Schema.org -->
      <script type="application/ld+json">
      {
        "@context": "https://schema.org",
        "@type": "Article",
        "headline": "Rust Monolith Guide",
        "author": {
          "@type": "Person",
          "name": "IndexFlow Team"
        }
      }
      </script>
      <script type="application/ld+json">
      {
        "@context": "https://schema.org",
        "@type": "FAQPage",
        "mainEntity": []
      }
      </script>
    </head>
    <body>
      <h1>Complete Rust Guide</h1>
      <p>Body paragraph</p>
    </body>
    </html>"#;

    #[test]
    fn test_full_inspection_pass() {
        let res = evaluate_html("https://example.com/guide", 200, 32, None, SAMPLE_HTML_FULL);

        assert!(res.passed);
        assert_eq!(res.block_reason, None);
        assert_eq!(res.http_status, Some(200));
        assert_eq!(
            res.page_title.as_deref(),
            Some("Rust Monolith Guide & SEO Best Practices")
        );
        assert_eq!(
            res.meta_description.as_deref(),
            Some("A complete technical SEO guide for modern Rust developers.")
        );
        assert_eq!(res.h1_content.as_deref(), Some("Complete Rust Guide"));
        assert_eq!(res.h1_count, 1);
        assert!(res.has_canonical);
        assert_eq!(res.canonical_url.as_deref(), Some("https://example.com/guide"));
        assert!(!res.has_noindex);
        assert!(!res.has_nofollow);
        assert_eq!(res.hreflang.len(), 2);

        assert_eq!(res.opengraph.title.as_deref(), Some("Rust Monolith Guide"));
        assert_eq!(res.opengraph.og_type.as_deref(), Some("article"));
        assert_eq!(res.opengraph.image.as_deref(), Some("https://example.com/cover.jpg"));
        assert_eq!(res.twitter_card.card.as_deref(), Some("summary_large_image"));

        assert!(res.ai_directives.gptbot_blocked);
        assert!(!res.ai_directives.perplexity_blocked);

        assert_eq!(res.json_ld.len(), 2);
        assert_eq!(
            res.schema_types(),
            vec!["Article".to_string(), "FAQPage".to_string()]
        );
    }

    #[test]
    fn test_gate_block_http_non_200() {
        let res = evaluate_html(
            "https://example.com/404",
            404,
            15,
            None,
            "<html><head><title>Not Found</title></head></html>",
        );
        assert!(!res.passed);
        assert_eq!(res.block_reason.as_deref(), Some("HTTP 404"));
    }

    #[test]
    fn test_gate_block_meta_noindex() {
        let html = r#"<html><head><title>Draft Page</title><meta name="robots" content="noindex, nofollow" /></head></html>"#;
        let res = evaluate_html("https://example.com/draft", 200, 20, None, html);
        assert!(!res.passed);
        assert!(res.has_noindex);
        assert!(res.has_nofollow);
        assert_eq!(
            res.block_reason.as_deref(),
            Some("noindex directive present")
        );
    }

    #[test]
    fn test_gate_block_x_robots_tag_header() {
        let html = r#"<html><head><title>Valid Title</title></head></html>"#;
        let res = evaluate_html(
            "https://example.com/page",
            200,
            20,
            Some("noindex, noarchive"),
            html,
        );
        assert!(!res.passed);
        assert!(res.has_noindex);
        assert_eq!(
            res.block_reason.as_deref(),
            Some("noindex directive present")
        );
    }

    #[test]
    fn test_gate_block_missing_title() {
        let html = r#"<html><head><meta name="description" content="No title here" /></head><body><h1>Hello</h1></body></html>"#;
        let res = evaluate_html("https://example.com/no-title", 200, 20, None, html);
        assert!(!res.passed);
        assert_eq!(res.block_reason.as_deref(), Some("Missing <title> tag"));
    }

    #[test]
    fn test_gate_block_canonical_mismatch() {
        let html = r#"<html><head><title>Duplicate Post</title><link rel="canonical" href="https://example.com/original-post" /></head></html>"#;
        let res = evaluate_html("https://example.com/duplicate-post", 200, 20, None, html);
        assert!(!res.passed);
        assert_eq!(
            res.block_reason.as_deref(),
            Some("Canonical URL mismatch: https://example.com/original-post")
        );
    }

    #[test]
    fn test_canonical_fuzzy_match() {
        assert!(canonical_matches_page(
            "https://example.com/blog/post-1/",
            "https://example.com/blog/post-1"
        ));
        assert!(canonical_matches_page(
            "https://example.com:443/blog/post-1",
            "https://example.com/blog/post-1"
        ));
        assert!(canonical_matches_page(
            "https://example.com/blog/post-1",
            "/blog/post-1"
        ));
        assert!(!canonical_matches_page(
            "https://example.com/blog/post-1",
            "https://example.com/blog/other"
        ));
    }

    #[test]
    fn test_entity_decoding() {
        assert_eq!(
            decode_basic_entities("Tom &amp; Jerry &#39;Special&#39;"),
            "Tom & Jerry 'Special'"
        );
        assert_eq!(
            decode_basic_entities("&lt;div&gt;&quot;Hello&quot;&nbsp;World&lt;/div&gt;"),
            "<div>\"Hello\"\u{a0}World</div>"
        );
    }

    #[test]
    fn nested_person_type_is_not_promoted_as_page_schema() {
        // The Article block also contains an author Person. schema_types walks
        // only @type / @graph, not arbitrary nested objects — Person stays out.
        let res = evaluate_html("https://example.com/guide", 200, 1, None, SAMPLE_HTML_FULL);
        assert_eq!(
            res.schema_types(),
            vec!["Article".to_string(), "FAQPage".to_string()]
        );
    }
}