rlucene 0.1.0-alpha.3

A Rust port of Apache Lucene, a full-text search engine 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
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
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

use crate::core::analysis::reader::StringReader;
use crate::core::analysis::token_stream::TokenStream;
use crate::core::document::document::Document;
use crate::core::document::field::{Field, FieldBase, Store};
use crate::core::document::field_type::FieldType;
use crate::core::document::fields::{FieldTokenStreamEnum, Fields};
use crate::core::document::stored_field::StoredField;
use crate::core::document::string_field::StringField;
use crate::core::document::string_field::TYPE_STORED as STRING_TYPE_STORED;
use crate::core::document::text_field::TextField;
use crate::core::index::BytesRefValue;
use crate::test_framework::core::util::lucene_test_case::{
  new_directory_shared, new_searcher_with_reader, random,
};

use crate::core::index::index_options::IndexOptions;
use crate::core::index::index_reader::IndexReader;
use crate::core::index::indexable_field::IndexableField;
use crate::core::index::indexable_field_type::IndexableFieldType;
use crate::core::index::stored_fields::StoredFields;
use crate::core::index::term::Term;
use crate::core::search::index_searcher::{self, IndexSearcher};
use crate::core::search::phrase_query::PhraseQuery;
use crate::core::search::score_doc::ScoreDocLike;
use crate::core::search::term_query::TermQuery;
use crate::core::search::top_docs::TopDocsLike;
use crate::core::util::error::lucene_error::{LuceneError, LuceneErrorKind, Result};
use crate::test_framework::core::analysis::mock_tokenizer::MockTokenizer;
use crate::test_framework::core::index::random_index_writer::RandomIndexWriter;

#[allow(dead_code)] // for quick search
struct TestDocument;

/// Tests the [`Document::remove_field`] method for a brand-new [`Document`]
/// that has not been indexed yet.
///
/// # Errors
/// - Returns an error if execution fails.
#[test]
fn test_binary_field() -> Result<()> {
  let binary_val = "this text will be stored as a byte array in the index";
  let binary_val2 = "this text will be also stored as a byte array in the index";

  let mut doc = Document::new();

  let mut ft = FieldType::new();
  ft.set_stored(true)?;
  let ft_arc = ft;

  let string_fld = Field::from_string("string", binary_val, ft_arc.clone())?;
  let binary_fld = StoredField::from_binary("binary", binary_val.as_bytes().to_vec())?;
  let binary_fld2 = StoredField::from_binary("binary", binary_val2.as_bytes().to_vec())?;

  assert!(binary_fld.binary_value()?.is_some());
  assert!(string_fld.field_type().stored());
  assert_eq!(binary_fld.field_type().index_options(), &IndexOptions::None);
  doc.add(binary_fld);
  doc.add(string_fld);

  assert_eq!(doc.get_fields().len(), 2);

  match doc.get_binary_value("binary")? {
    Some(bf) => {
      let bf_value = bf.as_bytes_ref().utf8_to_string()?.to_owned();
      assert_eq!(bf_value, binary_val);
    },
    None => {
      unreachable!()
    },
  }
  match doc.get("string")? {
    Some(sf) => {
      assert_eq!(sf.as_ref(), binary_val);
    },
    None => {
      unreachable!()
    },
  }

  doc.add(binary_fld2);
  assert_eq!(doc.get_fields().len(), 3);

  let binary_tests = doc.get_binary_values("binary")?;
  assert_eq!(binary_tests.len(), 2);

  let binary_test = binary_tests[0].as_bytes_ref().utf8_to_string()?.to_owned();
  let binary_test2 = binary_tests[1].as_bytes_ref().utf8_to_string()?.to_owned();

  assert_ne!(binary_test, binary_test2);
  assert_eq!(binary_test, binary_val);
  assert_eq!(binary_test2, binary_val2);
  doc.remove_field("string");
  assert_eq!(doc.get_fields().len(), 2);
  doc.remove_fields("binary");
  assert_eq!(doc.get_fields().len(), 0);
  Ok(())
}
/// Tests the [`Document::remove_field`] method for a brand-new [`Document`]
/// that has not been indexed yet.
///
/// # Errors
/// - Returns an error if execution fails.
#[test]
fn test_remove_for_new_document() -> Result<()> {
  let mut doc = make_document_with_fields()?;
  assert_eq!(10, doc.get_fields().len());

  doc.remove_fields("keyword");
  assert_eq!(8, doc.get_fields().len());

  doc.remove_fields("doesnotexists"); // removing non-existing fields is
  doc.remove_fields("keyword"); // removing a field more than once
  assert_eq!(8, doc.get_fields().len());

  doc.remove_field("text");
  assert_eq!(7, doc.get_fields().len());

  doc.remove_field("text");
  assert_eq!(6, doc.get_fields().len());

  doc.remove_field("text");
  assert_eq!(6, doc.get_fields().len());

  doc.remove_field("doesnotexists"); // removing non-existing fields is
  assert_eq!(6, doc.get_fields().len());

  doc.remove_fields("unindexed");
  assert_eq!(4, doc.get_fields().len());

  doc.remove_fields("unstored");
  assert_eq!(2, doc.get_fields().len());

  doc.remove_fields("doesnotexists"); // removing non-existing fields is
  assert_eq!(2, doc.get_fields().len());

  doc.remove_fields("indexed_not_tokenized");
  assert_eq!(0, doc.get_fields().len());

  Ok(())
}
#[test]
fn test_constructor_exceptions() -> Result<()> {
  let mut ft = FieldType::new();
  ft.set_stored(true)?;
  Field::from_string("name", "value", ft.clone())?;

  StringField::from_string("name", "value", Store::No)?;

  let ft_invalid = FieldType::new();
  let result = Field::from_string("name", "value", ft_invalid);
  assert!(matches!(
    result.as_ref().map_err(LuceneError::kind),
    Err(LuceneErrorKind::IllegalArgument(_))
  ));

  let mut random = random();
  let dir = new_directory_shared(&mut random)?;
  let writer = RandomIndexWriter::new(&mut random, dir.clone())?;

  Field::from_string("name", "value", ft.clone())?;

  let mut doc = Document::new();
  let mut ft2 = FieldType::new();
  ft2.set_stored(true)?;
  ft2.set_store_term_vectors(true)?;
  doc.add(Field::from_string("name", "value", ft2)?);

  let result = writer.add_document(&mut random, doc);
  assert!(matches!(
    result.as_ref().map_err(LuceneError::kind),
    Err(LuceneErrorKind::IllegalArgument(_))
  ));

  writer.close(&mut random)?;
  Ok(())
}

#[test]
fn test_clear_document() -> Result<()> {
  let mut doc = make_document_with_fields()?;
  assert_eq!(doc.get_fields().len(), 10);
  doc.clear();
  assert_eq!(doc.get_fields().len(), 0);
  Ok(())
}

#[test]
#[ignore = "Java-only: Document::get_fields returns an immutable Rust slice by type"]
fn test_get_fields_immutable() -> Result<()> {
  test_not_required_in_rust_lucene!();
}

#[test]
fn test_get_values_for_new_document() -> Result<()> {
  do_assert(&make_document_with_fields()?, false)
}
#[test]
fn test_get_values_for_indexed_document() -> Result<()> {
  let mut random = random();
  let dir = new_directory_shared(&mut random)?;

  let writer = RandomIndexWriter::new(&mut random, dir.clone())?;
  writer.add_document(&mut random, make_document_with_fields()?)?;

  let reader = writer.get_reader(&mut random)?;
  let searcher = index_searcher::from_reader(reader)?;

  // search for something that does exist
  let query = TermQuery::new(Term::from_text("keyword", "test1"));

  // ensure that queries return expected results without DateFilter first
  let top_docs = searcher.search(query, 1000)?;
  let hits = top_docs.score_docs();
  assert_eq!(hits.len(), 1);

  let doc = searcher.stored_fields()?.document(hits[0].doc())?;

  do_assert(&doc, true)?;

  writer.close(&mut random)?;

  Ok(())
}

#[test]
fn test_get_values() -> Result<()> {
  let doc = make_document_with_fields()?;

  let keyword_values = doc.get_values("keyword")?;
  assert!(
    keyword_values
      .iter()
      .map(|s| s.as_ref())
      .eq(["test1", "test2"]),
    "unexpected keyword values: {keyword_values:?}"
  );

  let text_values = doc.get_values("text")?;
  assert!(
    text_values
      .iter()
      .map(|s| s.as_ref())
      .eq(["test1", "test2"]),
    "unexpected text values: {text_values:?}"
  );

  let unindexed_values = doc.get_values("unindexed")?;
  assert!(
    unindexed_values
      .iter()
      .map(|s| s.as_ref())
      .eq(["test1", "test2"]),
    "unexpected unindexed values: {unindexed_values:?}"
  );

  let nope_values = doc.get_values("nope")?;
  assert!(nope_values.is_empty());

  Ok(())
}
#[test]
fn test_position_increment_multi_fields() -> Result<()> {
  let mut random = random();
  let dir = new_directory_shared(&mut random)?;

  let writer = RandomIndexWriter::new(&mut random, dir.clone())?;
  writer.add_document(&mut random, make_document_with_fields()?)?;

  let reader = writer.get_reader(&mut random)?;
  let searcher = new_searcher_with_reader(reader)?;

  let query = PhraseQuery::from_terms(0, "indexed_not_tokenized", ["test1", "test2"])?;

  let top_docs = searcher.search(query, 1000)?;
  let hits = top_docs.score_docs();
  assert_eq!(1, hits.len());

  let doc = searcher.stored_fields()?.document(hits[0].doc)?;
  do_assert(&doc, true)?;

  writer.close(&mut random)?;
  Ok(())
}

fn make_document_with_fields() -> Result<Document> {
  let mut doc = Document::new();
  let mut stored = FieldType::new();
  stored.set_stored(true)?;
  let mut indexed_not_tokenized = FieldType::new();
  indexed_not_tokenized.set_index_options(IndexOptions::DocsAndFreqsAndPositions)?;
  indexed_not_tokenized.set_tokenized(false)?;
  doc.add(StringField::from_string("keyword", "test1", Store::Yes)?);
  doc.add(StringField::from_string("keyword", "test2", Store::Yes)?);
  doc.add(TextField::from_string("text", "test1", Store::Yes)?);
  doc.add(TextField::from_string("text", "test2", Store::Yes)?);
  doc.add(Field::from_string("unindexed", "test1", stored.clone())?);
  doc.add(Field::from_string("unindexed", "test2", stored.clone())?);
  doc.add(TextField::from_string("unstored", "test1", Store::No)?);
  doc.add(TextField::from_string("unstored", "test2", Store::No)?);
  doc.add(Field::from_string(
    "indexed_not_tokenized",
    "test1",
    indexed_not_tokenized.clone(),
  )?);
  doc.add(Field::from_string(
    "indexed_not_tokenized",
    "test2",
    indexed_not_tokenized.clone(),
  )?);
  Ok(doc)
}

fn do_assert(doc: &Document, from_index: bool) -> Result<()> {
  let keyword_field_values = doc.get_fields_with_name("keyword");
  let text_field_values = doc.get_fields_with_name("text");
  let unindexed_field_values = doc.get_fields_with_name("unindexed");
  let unstored_field_values = doc.get_fields_with_name("unstored");

  assert_eq!(keyword_field_values.len(), 2);
  assert_eq!(text_field_values.len(), 2);
  assert_eq!(unindexed_field_values.len(), 2);
  // this test cannot work for documents retrieved from the index
  // since unstored fields will obviously not be returned
  if !from_index {
    assert_eq!(unstored_field_values.len(), 2);
  }

  assert_eq!(
    keyword_field_values[0].string_value()?.unwrap().as_ref(),
    "test1"
  );
  assert_eq!(
    keyword_field_values[1].string_value()?.unwrap().as_ref(),
    "test2"
  );
  assert_eq!(
    text_field_values[0].string_value()?.unwrap().as_ref(),
    "test1"
  );
  assert_eq!(
    text_field_values[1].string_value()?.unwrap().as_ref(),
    "test2"
  );
  assert_eq!(
    unindexed_field_values[0].string_value()?.unwrap().as_ref(),
    "test1"
  );
  assert_eq!(
    unindexed_field_values[1].string_value()?.unwrap().as_ref(),
    "test2"
  );
  // this test cannot work for documents retrieved from the index
  // since unstored fields will obviously not be returned
  if !from_index {
    assert_eq!(
      unstored_field_values[0].string_value()?.unwrap().as_ref(),
      "test1"
    );
    assert_eq!(
      unstored_field_values[1].string_value()?.unwrap().as_ref(),
      "test2"
    );
  }

  Ok(())
}
#[test]
fn test_field_set_value() -> Result<()> {
  let mut random = random();
  let dir = new_directory_shared(&mut random)?;

  let mut doc = Document::new();
  doc.add(StringField::from_string("id", "id1", Store::Yes)?);
  doc.add(StringField::from_string("keyword", "test", Store::Yes)?);

  let writer = RandomIndexWriter::new(&mut random, dir.clone())?;
  writer.add_document(&mut random, &mut doc)?;

  match doc.get_field_mut("id") {
    Some(Fields::String(field)) => field.set_string_value("id2")?,
    _ => panic!("expected string field"),
  }
  writer.add_document(&mut random, &mut doc)?;

  match doc.get_field_mut("id") {
    Some(Fields::String(field)) => field.set_string_value("id3")?,
    _ => panic!("expected string field"),
  }
  writer.add_document(&mut random, &mut doc)?;

  let reader = writer.get_reader(&mut random)?;
  let searcher = index_searcher::from_reader(reader)?;

  let query = TermQuery::new(Term::from_text("keyword", "test"));
  // ensure that queries return expected results without DateFilter first
  let top_docs = searcher.search(query, 1000)?;
  let hits = top_docs.score_docs();
  assert_eq!(hits.len(), 3);

  let mut stored_fields = searcher.stored_fields()?;

  let mut result = 0;
  #[allow(clippy::needless_range_loop)]
  for i in 0..3 {
    let doc2 = stored_fields.document(hits[i].doc())?;

    let f = doc2
      .get_field("id")
      .ok_or_else(|| LuceneError::illegal_state("missing id field"))?;

    let string_value = f.string_value()?.unwrap();
    let val = string_value.as_ref();

    match val {
      "id1" => result |= 1,
      "id2" => result |= 2,
      "id3" => result |= 4,
      _ => return Err(LuceneError::illegal_state("unexpected id field")),
    }
  }

  writer.close(&mut random)?;

  assert_eq!(7, result, "did not see all IDs");
  Ok(())
}

#[test]
fn test_invalid_fields() -> Result<()> {
  let random = random();
  let mut tokenizer = MockTokenizer::new(random);
  tokenizer.set_reader(StringReader::new("").into())?;
  assert!(matches!(
    (Field::from_token_stream(
      "foo",
      FieldTokenStreamEnum::custom(tokenizer),
      STRING_TYPE_STORED.clone(),
    ))
    .as_ref()
    .map_err(LuceneError::kind),
    Err(LuceneErrorKind::IllegalArgument(_))
  ));
  Ok(())
}

#[test]
fn test_numeric_field_as_string() -> Result<()> {
  // build document
  let mut doc = Document::new();
  doc.add(StoredField::from_i32("int", 5)?);
  assert_eq!("5", doc.get("int")?.unwrap().as_ref());
  assert_eq!(None, doc.get("somethingElse")?);

  doc.add(StoredField::from_i32("int", 4)?);

  let values = doc.get_values("int")?;
  assert!(values.iter().map(|v| v.as_ref()).eq(["5", "4"]));

  // index it
  let mut random = random();
  let dir = new_directory_shared(&mut random)?;
  let iw = RandomIndexWriter::new(&mut random, dir.clone())?;
  iw.add_document(&mut random, doc)?;

  let ir = iw.get_reader(&mut random)?;
  let sdoc = ir.stored_fields()?.document(0)?;

  assert_eq!("5", sdoc.get("int")?.unwrap().as_ref());
  assert_eq!(None, sdoc.get("somethingElse")?);

  let svalues = sdoc.get_values("int")?;
  assert!(svalues.iter().map(|v| v.as_ref()).eq(["5", "4"]));

  iw.close(&mut random)?;
  Ok(())
}