acorn-lib 0.1.62

ACORN library
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

//! Pure artifact discovery and grouping helpers.
use crate::schema::pid::{Identifier, PID};
use serde::{Deserialize, Serialize};
/// Candidate artifact record before standard-specific mapping
#[derive(Clone, Debug, Default, Deserialize, Eq, PartialEq, Serialize)]
pub struct ArtifactCandidate {
    /// Identifiers associated with this artifact
    pub identifiers: Vec<Identifier>,
    /// Resolver-proven canonical URL
    pub canonical_url: Option<String>,
    /// Enriched title
    pub title: Option<String>,
    /// Enriched author display names
    pub authors: Vec<String>,
}
/// Discover and normalize supported identifiers from prose or metadata text
pub fn discover_identifiers(content: &str) -> Vec<Identifier> {
    content
        .split_whitespace()
        .filter_map(|value| Identifier::new(value).normalize())
        .fold(Vec::new(), |mut identifiers, identifier| {
            if !identifiers.contains(&identifier) {
                identifiers.push(identifier);
            }
            identifiers
        })
}
/// Group artifacts only when canonical identifiers or enriched metadata prove equivalence
pub fn group_artifacts(candidates: Vec<ArtifactCandidate>) -> Vec<ArtifactCandidate> {
    candidates.into_iter().fold(Vec::<ArtifactCandidate>::new(), |mut grouped, candidate| {
        match grouped.iter_mut().find(|existing| same_artifact(existing, &candidate)) {
            | Some(existing) => {
                candidate.identifiers.into_iter().for_each(|identifier| {
                    if !existing.identifiers.contains(&identifier) {
                        existing.identifiers.push(identifier);
                    }
                });
                existing.identifiers.sort();
                if existing.canonical_url.is_none() {
                    existing.canonical_url = candidate.canonical_url;
                }
                if existing.title.is_none() {
                    existing.title = candidate.title;
                }
                if existing.authors.is_empty() {
                    existing.authors = candidate.authors;
                }
            }
            | None => grouped.push(candidate),
        }
        grouped
    })
}

fn same_artifact(left: &ArtifactCandidate, right: &ArtifactCandidate) -> bool {
    let canonical_match = left
        .identifiers
        .iter()
        .filter(|identifier| matches!(identifier.kind, PID::DOI | PID::URL))
        .any(|identifier| right.identifiers.contains(identifier))
        || left
            .canonical_url
            .as_ref()
            .zip(right.canonical_url.as_ref())
            .is_some_and(|(left, right)| left == right);
    let metadata_match = left
        .title
        .as_ref()
        .zip(right.title.as_ref())
        .filter(|(left, right)| normalized_text(left) == normalized_text(right))
        .is_some()
        && !left.authors.is_empty()
        && normalized_authors(&left.authors) == normalized_authors(&right.authors);
    canonical_match || metadata_match
}

fn normalized_text(value: &str) -> String {
    value.split_whitespace().collect::<Vec<_>>().join(" ").to_ascii_lowercase()
}

fn normalized_authors(values: &[String]) -> Vec<String> {
    let mut values = values.iter().map(|value| normalized_text(value)).collect::<Vec<_>>();
    values.sort();
    values
}

#[cfg(test)]
mod tests {
    #![allow(clippy::indexing_slicing, clippy::unwrap_used)]
    use super::*;
    #[test]
    fn identifier_hash_is_stable_and_short() {
        let identifier = Identifier::new("doi:10.1234/abc").normalize().unwrap();
        assert_eq!(identifier.identifier_hash().len(), 12);
        assert_eq!(identifier.identifier_hash(), identifier.identifier_hash());
    }
    #[test]
    fn discovers_supported_identifiers_without_duplicates() {
        let identifiers = discover_identifiers("Results: doi:10.1234/example and https://doi.org/10.1234/example plus https://example.org/artifact");
        assert_eq!(identifiers.len(), 2);
        assert_eq!(identifiers[0].kind, PID::DOI);
        assert_eq!(identifiers[1].kind, PID::URL);
    }

    #[test]
    fn groups_only_proven_equivalent_candidates() {
        let doi = Identifier::new("doi:10.1234/abc").normalize().unwrap();
        let url = Identifier::new("https://example.org/artifact").normalize().unwrap();
        let candidates = vec![
            ArtifactCandidate {
                identifiers: vec![doi.clone()],
                title: Some("A Result".to_string()),
                authors: vec!["Alice Example".to_string()],
                ..ArtifactCandidate::default()
            },
            ArtifactCandidate {
                identifiers: vec![doi, url],
                ..ArtifactCandidate::default()
            },
            ArtifactCandidate {
                identifiers: vec![Identifier::new("doi:10.9999/other").normalize().unwrap()],
                title: Some("A Different Result".to_string()),
                authors: vec!["Alice Example".to_string()],
                ..ArtifactCandidate::default()
            },
        ];
        let grouped = group_artifacts(candidates);
        assert_eq!(grouped.len(), 2);
        assert_eq!(grouped[0].identifiers.len(), 2);
    }
}