stam-tools 0.15.2

Command-line tools for working with stand-off annotations on text (STAM)
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

use stam::*;
use std::collections::BTreeSet;

#[derive(Copy, Clone, Debug, PartialEq)]
pub enum SplitMode {
    Retain,
    Delete,
}

pub fn split<'a>(
    store: &'a mut AnnotationStore,
    queries: Vec<Query<'a>>,
    mode: SplitMode,
    verbose: bool,
) {
    let mut split_annotations: BTreeSet<AnnotationHandle> = BTreeSet::new();
    let mut split_resources: BTreeSet<TextResourceHandle> = BTreeSet::new();
    let mut split_datasets: BTreeSet<AnnotationDataSetHandle> = BTreeSet::new();
    for (i, query) in queries.into_iter().enumerate() {
        eprintln!("Running query #{}...", i + 1);
        let iter = store.query(query).expect("query failed");
        for resultrow in iter {
            if let Ok(result) = resultrow.get_by_name_or_last(Some("split")) {
                match result {
                    QueryResultItem::None => {}
                    QueryResultItem::Annotation(annotation) => {
                        split_annotations.insert(annotation.handle());
                    }
                    QueryResultItem::TextResource(resource) => {
                        split_resources.insert(resource.handle());
                    }
                    QueryResultItem::AnnotationDataSet(dataset) => {
                        split_datasets.insert(dataset.handle());
                    }
                    _ => {
                        eprintln!("Error: Obtained result type is invalid for split, only ANNOTATION, RESOURCE and DATASET work.");
                    }
                }
            }
        }
    }
    eprintln!(
        "Gathered {} annotations, {} resources, {} datasets",
        split_annotations.len(),
        split_resources.len(),
        split_datasets.len()
    );

    match mode {
        SplitMode::Delete => {
            //split_* sets contains resources to delete
            if !split_resources.is_empty() {
                for resource in split_resources {
                    if verbose {
                        eprintln!("removing resource...");
                    }
                    let _ = store.remove_resource(resource); //we can just ignore handle error at this point
                }
            }
            if !split_datasets.is_empty() {
                for dataset in split_datasets {
                    if verbose {
                        eprintln!("removing dataset...");
                    }
                    let _ = store.remove_dataset(dataset); //we can just ignore handle error at this point
                }
            }
            if !split_annotations.is_empty() {
                for annotation in split_annotations {
                    if verbose {
                        eprintln!("removing annotation...");
                    }
                    let _ = store.remove_annotation(annotation); //we can just ignore handle error at this point
                }
            }
        }
        SplitMode::Retain => {
            //split_* sets contains resources to retain
            if !split_resources.is_empty() {
                for resource in 0..store.resources_len() {
                    let resource = TextResourceHandle::new(resource);
                    if store.has(resource) && !split_resources.contains(&resource) {
                        if verbose {
                            eprintln!("removing resource #{}...", resource.as_usize());
                        }
                        let _ = store.remove_resource(resource); //we can just ignore handle error at this point
                    }
                }
            }
            if !split_datasets.is_empty() {
                for dataset in 0..store.datasets_len() {
                    let dataset = AnnotationDataSetHandle::new(dataset);
                    if store.has(dataset) && !split_datasets.contains(&dataset) {
                        if verbose {
                            eprintln!("removing dataset #{}...", dataset.as_usize());
                        }
                        let _ = store.remove_dataset(dataset); //we can just ignore handle error at this point
                    }
                }
            }
            if !split_annotations.is_empty() {
                for annotation in 0..store.annotations_len() {
                    let annotation = AnnotationHandle::new(annotation);
                    if store.has(annotation) && !split_annotations.contains(&annotation) {
                        if verbose {
                            eprintln!("removing annotation #{}...", annotation.as_usize());
                        }
                        let _ = store.remove_annotation(annotation); //we can just ignore handle error at this point
                    }
                }
            }
        }
    }
}