nitrite 0.4.0

An embedded NoSQL document database for Rust with collections, repositories, indexing, and ACID transactions
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
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266

use crate::{
    collection::{Document, NitriteId},
    errors::NitriteResult,
    store::{NitriteMap, NitriteMapProvider},
    Value,
};

pub(crate) struct IndexedStream {
    nitrite_map: NitriteMap,
    id_set: Vec<NitriteId>,
    current: usize,
}

impl IndexedStream {
    pub fn new(nitrite_map: NitriteMap, id_set: Vec<NitriteId>) -> Self {
        IndexedStream {
            nitrite_map,
            id_set,
            current: 0,
        }
    }
}

impl Iterator for IndexedStream {
    type Item = NitriteResult<Document>;

    fn next(&mut self) -> Option<Self::Item> {
        let id_set_len = self.id_set.len();
        loop {
            // Bounds check with early exit
            if self.current >= id_set_len {
                log::debug!("IndexedStream::next - exhausted all {} ids", id_set_len);
                return None;
            }

            let id = &self.id_set[self.current];
            self.current += 1;
            
            log::debug!("IndexedStream::next - looking up id: {:?}", id);
            
            // Inline the match for better branch prediction
            match self.nitrite_map.get(&Value::NitriteId(*id)) {
                Ok(Some(value)) => {
                    // Direct as_document() check without nested match
                    if let Some(doc) = value.as_document() {
                        log::debug!("IndexedStream::next - found document");
                        return Some(Ok(doc.clone()));
                    } else {
                        log::warn!("Data corruption: Expected Document in indexed stream, found {:?}", value);
                        // continue loop to next id
                    }
                }
                Ok(None) => {
                    log::debug!("IndexedStream::next - id not found in map");
                    // continue to next id
                }
                Err(e) => {
                    return Some(Err(e));
                }
            }
        }
    }
}

#[cfg(test)]
mod tests {
    use super::*;
    use crate::collection::Document;
    use crate::nitrite_config::NitriteConfig;
    use crate::store::NitriteStoreProvider;
    use crate::Value;

    fn create_nitrite_map() -> NitriteMap {
        let config = NitriteConfig::default();
        config.auto_configure().expect("Failed to auto configure");
        config.initialize().expect("Failed to initialize");
        let store = config.nitrite_store().expect("Failed to get store");
        
        store.open_map("test").expect("Failed to open map")
    }

    fn create_document(id: &str) -> Document {
        let mut doc = Document::new();
        doc.put("id", id).expect("Failed to put value");
        doc
    }

    #[test]
    fn test_indexed_stream_with_matching_document() {
        let map = create_nitrite_map();
        let mut doc = create_document("1");
        let id = doc.id().expect("Failed to get id");
        map.put(Value::NitriteId(id), Value::from(doc.clone()))
            .unwrap();

        let id_set = vec![id];
        let mut indexed_stream = IndexedStream::new(map.clone(), id_set);

        let result = indexed_stream.next().unwrap().unwrap();
        assert_eq!(result.get("id").unwrap().as_string().unwrap(), "1");
        assert!(indexed_stream.next().is_none());
    }

    #[test]
    fn test_indexed_stream_with_no_matching_document() {
        let map = create_nitrite_map();
        let id_set = vec![NitriteId::new()];
        let mut indexed_stream = IndexedStream::new(map, id_set);

        assert!(indexed_stream.next().is_none());
    }

    #[test]
    fn test_indexed_stream_with_multiple_documents() {
        let map = create_nitrite_map();
        let mut doc1 = create_document("1");
        let id1 = doc1.id().expect("Failed to get id");
        let mut doc2 = create_document("2");
        let id2 = doc2.id().expect("Failed to get id");
        map.put(Value::NitriteId(id1), Value::from(doc1.clone()))
            .unwrap();
        map.put(Value::NitriteId(id2), Value::from(doc2.clone()))
            .unwrap();

        let id_set = vec![id1, id2];
        let mut indexed_stream = IndexedStream::new(map, id_set);

        let result1 = indexed_stream.next().unwrap().unwrap();
        assert!(
            result1.get("id").unwrap().as_string().unwrap() == "1"
                || result1.get("id").unwrap().as_string().unwrap() == "2"
        );

        let result2 = indexed_stream.next().unwrap().unwrap();
        assert!(
            result2.get("id").unwrap().as_string().unwrap() == "1"
                || result2.get("id").unwrap().as_string().unwrap() == "2"
        );

        assert!(indexed_stream.next().is_none());
    }

    // as_document().unwrap() error handling tests
    #[test]
    fn test_indexed_stream_with_corrupted_document_type() {
        // Test that IndexedStream handles non-Document values gracefully
        // instead of panicking with as_document().unwrap()
        let map = create_nitrite_map();
        let id = NitriteId::new();
        
        // Insert a corrupted value (non-Document) into the map
        map.put(Value::NitriteId(id), Value::String("not a document".to_string()))
            .unwrap();

        let id_set = vec![id];
        let mut indexed_stream = IndexedStream::new(map, id_set);

        // Should skip corrupted entry and return None instead of panicking
        assert!(indexed_stream.next().is_none());
    }

    #[test]
    fn test_indexed_stream_gracefully_handles_mixed_types() {
        // Test that IndexedStream can iterate through mixed valid and invalid entries
        let map = create_nitrite_map();
        
        let mut doc = create_document("valid");
        let valid_id = doc.id().expect("Failed to get id");
        map.put(Value::NitriteId(valid_id), Value::from(doc))
            .unwrap();
        
        let invalid_id = NitriteId::new();
        map.put(Value::NitriteId(invalid_id), Value::I32(42))
            .unwrap();

        let id_set = vec![valid_id, invalid_id];
        let mut indexed_stream = IndexedStream::new(map, id_set);

        // Should return the valid document
        let result = indexed_stream.next();
        assert!(result.is_some());
        if let Some(Ok(doc)) = result {
            assert_eq!(doc.get("id").unwrap().as_string().unwrap(), "valid");
        }

        // The invalid entry should be skipped
        assert!(indexed_stream.next().is_none());
    }

    #[test]
    fn bench_indexed_stream_iteration() {
        let map = create_nitrite_map();
        let mut id_set = Vec::new();
        
        for i in 0..100 {
            let mut doc = create_document(&i.to_string());
            let id = doc.id().expect("Failed to get id");
            map.put(Value::NitriteId(id), Value::from(doc))
                .unwrap();
            id_set.push(id);
        }

        let start = std::time::Instant::now();
        for _ in 0..10 {
            let indexed_stream = IndexedStream::new(map.clone(), id_set.clone());
            let count = indexed_stream.count();
            assert_eq!(count, 100);
        }
        let elapsed = start.elapsed();

        println!("Indexed stream iteration (10x 100 docs): {:?} ({:.3}µs per iteration)", 
                 elapsed,
                 elapsed.as_micros() as f64 / 10.0);
    }

    #[test]
    fn bench_indexed_stream_with_sparse_ids() {
        let map = create_nitrite_map();
        let mut id_set = Vec::new();
        
        // Insert 100 documents
        for i in 0..100 {
            let mut doc = create_document(&i.to_string());
            let id = doc.id().expect("Failed to get id");
            map.put(Value::NitriteId(id), Value::from(doc))
                .unwrap();
            id_set.push(id);
        }
        
        // But only reference 10 of them in the stream
        let sparse_ids: Vec<_> = id_set.iter().step_by(10).cloned().collect();

        let start = std::time::Instant::now();
        for _ in 0..100 {
            let indexed_stream = IndexedStream::new(map.clone(), sparse_ids.clone());
            let count = indexed_stream.count();
            assert_eq!(count, 10);
        }
        let elapsed = start.elapsed();

        println!("Indexed stream with sparse IDs (100x 10 docs from 100): {:?} ({:.3}µs per iteration)", 
                 elapsed,
                 elapsed.as_micros() as f64 / 100.0);
    }

    #[test]
    fn bench_indexed_stream_single_lookup() {
        let map = create_nitrite_map();
        let mut doc = create_document("single");
        let id = doc.id().expect("Failed to get id");
        map.put(Value::NitriteId(id), Value::from(doc))
            .unwrap();

        let start = std::time::Instant::now();
        for _ in 0..1000 {
            let indexed_stream = IndexedStream::new(map.clone(), vec![id]);
            let count = indexed_stream.count();
            assert_eq!(count, 1);
        }
        let elapsed = start.elapsed();

        println!("Indexed stream single lookup (1000 iterations): {:?} ({:.3}µs per lookup)", 
                 elapsed,
                 elapsed.as_micros() as f64 / 1000.0);
    }
}