poimen-memory/tests/it_entity_linking_5_1.rs

//! Integration Tests for Phase 5.1: Entity Linking
//!
//! Tests entity linking capabilities:
//! - Mention linking to existing entities
//! - Alias detection
//! - Entity merge suggestions
//! - Coreference clustering

#[cfg(test)]
mod tests {
    /// Test: Mention link structure
    #[test]
    fn test_mention_link_basic() {
        let mention_text = "Kubernetes";
        let entity_id = "e1";
        let confidence = 0.95;
        
        assert!(!mention_text.is_empty());
        assert_eq!(entity_id, "e1");
        assert!(confidence > 0.9);
    }

    /// Test: Mention link with offsets
    #[test]
    fn test_mention_link_offsets() {
        let start = 0;
        let end = 10;
        
        assert_eq!(end - start, 10);
    }

    /// Test: Link reason - semantic
    #[test]
    fn test_link_reason_semantic() {
        let reason = "SemanticMatch";
        assert_eq!(reason, "SemanticMatch");
    }

    /// Test: Link reason - lexical
    #[test]
    fn test_link_reason_lexical() {
        let reason = "LexicalMatch";
        assert_eq!(reason, "LexicalMatch");
    }

    /// Test: Link reason - alias
    #[test]
    fn test_link_reason_alias() {
        let reason = "AliasMatch";
        assert_eq!(reason, "AliasMatch");
    }

    /// Test: Link reason - acronym
    #[test]
    fn test_link_reason_acronym() {
        let reason = "AcronymMatch";
        assert_eq!(reason, "AcronymMatch");
    }

    /// Test: Link reason - partial
    #[test]
    fn test_link_reason_partial() {
        let reason = "PartialMatch";
        assert_eq!(reason, "PartialMatch");
    }

    /// Test: Alias suggestion structure
    #[test]
    fn test_alias_suggestion_basic() {
        let canonical = "Kubernetes";
        let alias = "k8s";
        let confidence = 0.95;
        
        assert_eq!(canonical, "Kubernetes");
        assert_eq!(alias, "k8s");
        assert!(confidence > 0.9);
    }

    /// Test: Alias with frequency
    #[test]
    fn test_alias_with_frequency() {
        let frequency = 5;
        let confidence = 0.95;
        
        assert!(frequency > 0);
        assert!(confidence > 0.5);
    }

    /// Test: Merge suggestion structure
    #[test]
    fn test_merge_suggestion_basic() {
        let entity1 = "Kubernetes";
        let entity2 = "K8s";
        let confidence = 0.85;
        
        assert_ne!(entity1, entity2);
        assert!(confidence > 0.8);
    }

    /// Test: Merge suggestion with reasons
    #[test]
    fn test_merge_suggestion_reasons() {
        let reasons = vec!["Acronym match".to_string()];
        assert_eq!(reasons.len(), 1);
    }

    /// Test: Merge suggestion multiple reasons
    #[test]
    fn test_merge_suggestion_multiple_reasons() {
        let reasons = vec![
            "Acronym match".to_string(),
            "Common relations".to_string(),
        ];
        assert_eq!(reasons.len(), 2);
    }

    /// Test: Coreference cluster structure
    #[test]
    fn test_coreference_cluster_basic() {
        let entity_id = "e1";
        let mention_count = 3;
        
        assert!(!entity_id.is_empty());
        assert!(mention_count > 0);
    }

    /// Test: Coreference cluster mentions
    #[test]
    fn test_coreference_cluster_mentions() {
        let mentions = vec!["Kubernetes".to_string(), "k8s".to_string(), "K8s".to_string()];
        assert_eq!(mentions.len(), 3);
    }

    /// Test: Coreference cluster confidence
    #[test]
    fn test_coreference_cluster_confidence() {
        let confidence = 0.85;
        assert!(confidence >= 0.0 && confidence <= 1.0);
    }

    /// Test: Entity linker initialization
    #[test]
    fn test_entity_linker_pool() {
        let pool_exists = true;
        assert!(pool_exists);
    }

    /// Test: Mention extraction from text
    #[test]
    fn test_mention_extraction_capitalized() {
        let text = "Kubernetes is a platform";
        let mention = "Kubernetes";
        
        assert!(text.contains(mention));
    }

    /// Test: Mention extraction multiword
    #[test]
    fn test_mention_extraction_multiword() {
        let text = "Google Cloud Platform provides services";
        let mention = "Cloud";
        
        assert!(text.contains(mention));
    }

    /// Test: Acronym detection k8s
    #[test]
    fn test_acronym_k8s() {
        let acronym = "k8s";
        let full = "Kubernetes";
        
        assert_ne!(acronym, full);
        assert!(full.to_lowercase().starts_with("k"));
    }

    /// Test: String similarity exact match
    #[test]
    fn test_similarity_exact() {
        let s1 = "Kubernetes";
        let s2 = "Kubernetes";
        
        assert_eq!(s1, s2);
    }

    /// Test: String similarity case insensitive
    #[test]
    fn test_similarity_case_insensitive() {
        let s1 = "Kubernetes";
        let s2 = "kubernetes";
        
        assert_eq!(s1.to_lowercase(), s2.to_lowercase());
    }

    /// Test: String similarity substring
    #[test]
    fn test_similarity_substring() {
        let s1 = "Kubernetes";
        let s2 = "Kubernetes Platform";
        
        assert!(s2.contains(s1));
    }

    /// Test: Edit distance same
    #[test]
    fn test_edit_distance_same() {
        let s1 = "test";
        let s2 = "test";
        
        assert_eq!(s1, s2);
    }

    /// Test: Edit distance one change
    #[test]
    fn test_edit_distance_one_char() {
        let s1 = "test";
        let s2 = "text";
        
        assert_ne!(s1, s2);
        assert!(s1.len() == s2.len());
    }

    /// Test: Edit distance typo
    #[test]
    fn test_edit_distance_typo() {
        let s1 = "Kubernetes";
        let s2 = "Kubenetes";
        
        assert_ne!(s1, s2);
    }

    /// Test: Link entities request validation
    #[test]
    fn test_link_entities_request_valid() {
        let project = "poimen";
        let text = "Kubernetes is great";
        
        assert!(!project.is_empty());
        assert!(!text.is_empty());
        assert!(text.len() < 10000);
    }

    /// Test: Link entities request empty text
    #[test]
    fn test_link_entities_request_empty_text() {
        let text = "";
        assert!(text.is_empty());
    }

    /// Test: Link entities request too long
    #[test]
    fn test_link_entities_request_too_long() {
        let text = "x".repeat(10001);
        assert!(text.len() > 10000);
    }

    /// Test: Detect aliases request valid
    #[test]
    fn test_detect_aliases_request_valid() {
        let entity_id = "e1";
        let entity_name = "Kubernetes";
        let samples = vec!["k8s is great".to_string()];
        
        assert!(!entity_id.is_empty());
        assert!(!entity_name.is_empty());
        assert!(!samples.is_empty());
    }

    /// Test: Detect aliases empty samples
    #[test]
    fn test_detect_aliases_empty_samples() {
        let samples: Vec<String> = vec![];
        assert!(samples.is_empty());
    }

    /// Test: Suggest merges threshold valid
    #[test]
    fn test_suggest_merges_threshold_valid() {
        let threshold = 0.8;
        assert!(threshold >= 0.0 && threshold <= 1.0);
    }

    /// Test: Suggest merges threshold too low
    #[test]
    fn test_suggest_merges_threshold_too_low() {
        let threshold = -0.1;
        assert!(threshold < 0.0);
    }

    /// Test: Suggest merges threshold too high
    #[test]
    fn test_suggest_merges_threshold_too_high() {
        let threshold = 1.5;
        assert!(threshold > 1.0);
    }

    /// Test: Coreference detection request valid
    #[test]
    fn test_coreferences_request_valid() {
        let texts = vec!["Kubernetes is great".to_string()];
        assert!(!texts.is_empty());
    }

    /// Test: Coreference detection empty texts
    #[test]
    fn test_coreferences_request_empty() {
        let texts: Vec<String> = vec![];
        assert!(texts.is_empty());
    }

    /// Test: Link success rate calculation
    #[test]
    fn test_link_success_rate() {
        let linked = 8;
        let unlinked = 2;
        let total = linked + unlinked;
        let rate = linked as f32 / total as f32;
        
        assert_eq!(rate, 0.8);
    }

    /// Test: Link success rate all linked
    #[test]
    fn test_link_success_rate_all() {
        let linked = 10;
        let total = 10;
        let rate = linked as f32 / total as f32;
        
        assert_eq!(rate, 1.0);
    }

    /// Test: Link success rate none linked
    #[test]
    fn test_link_success_rate_none() {
        let linked = 0;
        let total = 10;
        let rate = if total > 0 {
            linked as f32 / total as f32
        } else {
            0.0
        };
        
        assert_eq!(rate, 0.0);
    }

    /// Test: Mention link response structure
    #[test]
    fn test_link_response_structure() {
        let links_count = 5;
        let unlinked_count = 2;
        let total = links_count + unlinked_count;
        
        assert_eq!(total, 7);
    }

    /// Test: Alias response structure
    #[test]
    fn test_alias_response_structure() {
        let alias_count = 3;
        let entity_name = "Kubernetes";
        
        assert!(alias_count > 0);
        assert!(!entity_name.is_empty());
    }

    /// Test: Merge response structure
    #[test]
    fn test_merge_response_structure() {
        let suggestion_count = 5;
        let project = "poimen";
        
        assert!(suggestion_count > 0);
        assert_eq!(project, "poimen");
    }

    /// Test: Coreference response structure
    #[test]
    fn test_coreference_response_structure() {
        let cluster_count = 3;
        let total_mentions = 12;
        
        assert!(cluster_count > 0);
        assert!(total_mentions > 0);
    }

    /// Test: Multiple mentions in single text
    #[test]
    fn test_multiple_mentions_composition() {
        let entities = vec!["Kubernetes", "Docker", "Prometheus"];
        let mention_count = entities.len();
        
        assert_eq!(mention_count, 3);
    }

    /// Test: Linking with high confidence
    #[test]
    fn test_linking_high_confidence() {
        let confidence = 0.95;
        let threshold = 0.9;
        
        assert!(confidence > threshold);
    }

    /// Test: Linking below confidence threshold
    #[test]
    fn test_linking_low_confidence() {
        let confidence = 0.65;
        let threshold = 0.7;
        
        assert!(confidence < threshold);
    }

    /// Test: Merge candidate filtering by threshold
    #[test]
    fn test_merge_threshold_filtering() {
        let similarity = 0.75;
        let threshold = 0.8;
        
        assert!(similarity < threshold);
    }

    /// Test: Coreference from multiple texts
    #[test]
    fn test_coreference_multiple_texts() {
        let texts = vec![
            "Kubernetes is great".to_string(),
            "k8s simplifies deployment".to_string(),
            "Kubernetes powers modern infrastructure".to_string(),
        ];
        
        assert_eq!(texts.len(), 3);
    }

    /// Test: Serialization of mention link
    #[test]
    fn test_mention_link_serializable() {
        let mention_text = "Kubernetes";
        let json_text = "\"Kubernetes\"";
        
        assert!(json_text.contains(mention_text));
    }

    /// Test: Serialization of alias suggestion
    #[test]
    fn test_alias_suggestion_serializable() {
        let canonical = "Kubernetes";
        let alias = "k8s";
        
        assert_ne!(canonical, alias);
    }

    /// Test: Serialization of merge suggestion
    #[test]
    fn test_merge_suggestion_serializable() {
        let entity1 = "Kubernetes";
        let entity2 = "K8s";
        
        assert_ne!(entity1, entity2);
    }

    /// Test: Rate limiting applies to synthesis
    #[test]
    fn test_synthesis_rate_limiting() {
        let max_per_hour = 100;
        let requests = 50;
        
        assert!(requests < max_per_hour);
    }

    /// Test: Processing time tracking
    #[test]
    fn test_process_time_tracked() {
        let process_time_ms = 150;
        
        assert!(process_time_ms > 0);
    }

    /// Test: Entity linking with mixed case
    #[test]
    fn test_entity_linking_mixed_case() {
        let canonical = "Kubernetes";
        let mention = "KUBERNETES";
        
        assert_eq!(canonical.to_lowercase(), mention.to_lowercase());
    }

    /// Test: Alias detection frequency threshold
    #[test]
    fn test_alias_frequency_threshold() {
        let frequency = 2;
        let min_frequency = 1;
        
        assert!(frequency > min_frequency);
    }
}