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

mod collector_cache;
mod custom_serializer;
mod default_tokenizers;
mod fruit_extractors;
mod index_holder;
mod index_registry;
mod index_writer_holder;
pub mod merge_policies;
pub mod queries;
mod query_parser;
mod segment_attributes;
mod snippet_generator;
mod summa_document;
pub mod tokenizers;

pub use custom_serializer::NamedFieldDocument;
pub use default_tokenizers::{default_tokenizers, STOP_WORDS};
pub use fruit_extractors::{build_fruit_extractor, FruitExtractor, IntermediateExtractionResult};
pub use index_holder::{cleanup_index, IndexHolder};
pub use index_registry::IndexRegistry;
pub use index_writer_holder::IndexWriterHolder;
pub use query_parser::{MorphologyManager, ProtoQueryParser, QueryParser, QueryParserError};
pub use segment_attributes::SummaSegmentAttributes;
pub use summa_document::{DocumentParsingError, SummaDocument};

pub mod test_utils {
    use std::default::Default;
    use std::sync::atomic::{AtomicI64, Ordering};

    use itertools::Itertools;
    use rand::rngs::SmallRng;
    use rand::{Rng, SeedableRng};
    use serde_json::json;
    use tantivy::doc;
    use tantivy::schema::{IndexRecordOption, JsonObjectOptions, Schema, TextFieldIndexing, TextOptions, FAST, INDEXED, STORED};

    use crate::components::SummaDocument;

    pub fn create_test_schema() -> Schema {
        let mut schema_builder = Schema::builder();

        schema_builder.add_i64_field("id", FAST | INDEXED | STORED);
        schema_builder.add_i64_field("issued_at", FAST | INDEXED | STORED);
        schema_builder.add_text_field(
            "title",
            TextOptions::default().set_stored().set_indexing_options(
                TextFieldIndexing::default()
                    .set_tokenizer("summa")
                    .set_index_option(IndexRecordOption::WithFreqsAndPositions),
            ),
        );
        schema_builder.add_text_field(
            "body",
            TextOptions::default().set_stored().set_indexing_options(
                TextFieldIndexing::default()
                    .set_tokenizer("summa")
                    .set_index_option(IndexRecordOption::WithFreqsAndPositions),
            ),
        );
        schema_builder.add_text_field(
            "tags",
            TextOptions::default()
                .set_stored()
                .set_indexing_options(TextFieldIndexing::default().set_tokenizer("summa").set_index_option(IndexRecordOption::Basic)),
        );
        schema_builder.add_json_field(
            "metadata",
            JsonObjectOptions::default()
                .set_stored()
                .set_indexing_options(
                    TextFieldIndexing::default()
                        .set_tokenizer("summa_without_stop_words")
                        .set_index_option(IndexRecordOption::Basic),
                )
                .set_expand_dots_enabled(),
        );
        schema_builder.add_text_field(
            "extra",
            TextOptions::default().set_stored().set_indexing_options(
                TextFieldIndexing::default()
                    .set_tokenizer("summa")
                    .set_index_option(IndexRecordOption::WithFreqsAndPositions),
            ),
        );
        schema_builder.add_text_field(
            "concepts",
            TextOptions::default().set_stored().set_indexing_options(
                TextFieldIndexing::default()
                    .set_tokenizer("summa_dict")
                    .set_index_option(IndexRecordOption::WithFreqsAndPositions),
            ),
        );
        schema_builder.build()
    }

    #[inline]
    fn generate_term(rng: &mut SmallRng, prefix: &str, power: usize) -> String {
        if power > 0 {
            format!("{}{}", prefix, rng.gen_range(0..power))
        } else {
            prefix.to_string()
        }
    }

    #[inline]
    fn generate_sentence(rng: &mut SmallRng, prefix: &str, power: usize, length: usize) -> String {
        (0..length).map(|_| generate_term(rng, prefix, power)).join(" ")
    }

    pub fn generate_document<'a>(
        doc_id: Option<i64>,
        rng: &mut SmallRng,
        schema: &Schema,
        title_prefix: &'a str,
        title_power: usize,
        body_prefix: &'a str,
        body_power: usize,
        tag_prefix: &'a str,
        tag_power: usize,
    ) -> SummaDocument<'a> {
        static DOC_ID: AtomicI64 = AtomicI64::new(1);

        let issued_at = 1674041452i64 - rng.gen_range(100..1000);
        let doc_id = doc_id.unwrap_or_else(|| DOC_ID.fetch_add(1, Ordering::SeqCst));

        SummaDocument::TantivyDocument(doc!(
            schema.get_field("id").expect("no expected field") => doc_id,
            schema.get_field("title").expect("no expected field") => generate_sentence(rng, title_prefix, title_power, 3),
            schema.get_field("body").expect("no expected field") => generate_sentence(rng, body_prefix, body_power, 50),
            schema.get_field("tags").expect("no expected field") => generate_sentence(rng, tag_prefix, tag_power, 5),
            schema.get_field("issued_at").expect("no expected field") => issued_at,
            schema.get_field("metadata").expect("no expected field") => json!({"id": doc_id}),
        ))
    }

    pub fn generate_unique_document<'a>(schema: &'a Schema, title: &'a str) -> SummaDocument<'a> {
        generate_document(None, &mut SmallRng::seed_from_u64(42), schema, title, 0, "body", 1000, "tag", 100)
    }

    pub fn generate_documents(schema: &Schema, n: usize) -> Vec<SummaDocument> {
        let mut rng = SmallRng::seed_from_u64(42);
        (0..n)
            .map(|_| generate_document(None, &mut rng, schema, "title", 100, "body", 1000, "tag", 10))
            .collect()
    }

    pub fn generate_documents_with_doc_id_gen_and_rng<'a>(doc_id_gen: AtomicI64, rng: &mut SmallRng, schema: &'a Schema, n: usize) -> Vec<SummaDocument<'a>> {
        (0..n)
            .map(|_| {
                generate_document(
                    Some(doc_id_gen.fetch_add(1, Ordering::SeqCst)),
                    rng,
                    schema,
                    "title",
                    100,
                    "body",
                    1000,
                    "tag",
                    10,
                )
            })
            .collect()
    }
}