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
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
/*
 * 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::codecs::DefaultStoredFieldsFormat;
use crate::core::codecs::stored_fields_format::StoredFieldsFormat;
use crate::core::codecs::stored_fields_reader::StoredFieldsReader;
use crate::core::index::codec_reader::CodecReader;
use crate::core::index::field_info::FieldInfo;
use crate::core::index::field_infos::FieldInfos;
use crate::core::index::merge_state::SharedDocMap;
use crate::core::index::merge_state::{DocMap, MergeState};
use crate::core::index::stored_field_visitor::{Status, StoredFieldVisitor};
use crate::core::index::stored_fields::StoredFields;
use crate::core::index::{BytesRef, DocIDMerger, Sub, SubBase, of};
use crate::core::search::doc_id_set_iterator::NO_MORE_DOCS;
use crate::core::store::DataInput;
use crate::core::store::directory::Directory;
use crate::core::util::access::ByteSource;
use crate::core::util::accountable::Accountable;
use crate::core::util::close::Closeable;
use crate::core::util::error::lucene_error::{LuceneError, Result};

/// Codec API for writing stored fields:
///
/// 1. For every document,
///    [`start_document`](StoredFieldsWriter::start_document) is called,
///    informing the Codec that a new document has started.
/// 2. `write_field_*` is called for each field in the document.
/// 3. After all documents have been written,
///    [`finish`](StoredFieldsWriter::finish) is called for
///    verification/sanity-checks.
/// 4. Finally, the writer is closed.
pub trait StoredFieldsWriter: Accountable + Closeable {
  /// Called before writing the stored fields of the document.
  /// `write_field` will be called for each stored field.
  /// This is called even if the document has no stored fields.
  fn start_document(&mut self) -> Result<()>;

  /// Called when a document and all its fields have been added.
  fn finish_document(&mut self) -> Result<()> {
    Ok(())
  }

  /// Writes a stored `i32` value.
  fn write_field_i32(&mut self, field_info: &FieldInfo, value: i32) -> Result<()>;

  /// Writes a stored `i64` value.
  fn write_field_i64(&mut self, field_info: &FieldInfo, value: i64) -> Result<()>;

  /// Writes a stored `f32` value.
  fn write_field_f32(&mut self, field_info: &FieldInfo, value: f32) -> Result<()>;

  /// Writes a stored `f64` value.
  fn write_field_f64(&mut self, field_info: &FieldInfo, value: f64) -> Result<()>;

  /// Writes a stored binary value from a [`DataInput`] and a `length`.
  fn write_field_with_input<DI>(
    &mut self,
    field_info: &FieldInfo,
    input: &mut DI,
    length: usize,
  ) -> Result<()>
  where
    DI: DataInput,
  {
    if length == 0 {
      let mut bytes = Vec::new();
      input.read_bytes(&mut bytes, 0, 0)?;
      return self.write_field_bytes(field_info, &BytesRef::from_slice(bytes, 0, 0));
    }
    let bytes = input.get_bytes(length)?;
    self.write_field_bytes(
      field_info,
      &BytesRef {
        bytes: bytes.as_ref(),
        offset: 0,
        length,
      },
    )
  }

  /// Writes a stored binary value.
  /// Implementations that retain the bytes beyond this call must copy them.
  fn write_field_bytes<B>(&mut self, field_info: &FieldInfo, value: &BytesRef<B>) -> Result<()>
  where
    B: ByteSource;

  /// Writes a stored string value.
  fn write_field_str(&mut self, field_info: &FieldInfo, value: &str) -> Result<()>;

  /**
   * Called before `Drop`, passing in the number of documents that were
   * written. Note that this is intentionally redundant (equivalent to
   * the number of calls to
   * [`start_document`](StoredFieldsWriter::start_document),
   * but a codec should check that this is the case to detect the runtime bug
   * described in LUCENE-1282.
   */
  fn finish<D>(&mut self, num_docs: i32, dir: &D) -> Result<()>
  where
    D: Directory;

  /// Merges in the stored fields from the readers in `merge_state`. The
  /// default implementation skips over deleted documents, and uses
  /// [`start_document`](StoredFieldsWriter::start_document), `write_field_*`,
  /// and [`finish`](StoredFieldsWriter::finish), returning the number of
  /// documents that were written. Implementations can provide this
  /// method for more sophisticated merging (bulk-byte copying, etc.).
  fn merge<D, D1, CR>(&mut self, merge_state: &mut MergeState<D, CR>, dir: &D1) -> Result<i32>
  where
    D1: Directory,
    CR: CodecReader,
    Self: Sized,
  {
    StoredFieldsWriterDefaults::merge(self, merge_state, dir)
  }
}

pub struct StoredFieldsWriterDefaults;

impl StoredFieldsWriterDefaults {
  pub fn merge<W, D, D1, CR>(
    writer: &mut W,
    merge_state: &mut MergeState<D, CR>,
    dir: &D1,
  ) -> Result<i32>
  where
    W: StoredFieldsWriter,
    D1: Directory,
    CR: CodecReader,
  {
    let mut subs = Vec::with_capacity(merge_state.stored_fields_readers.len());

    for i in 0..merge_state.stored_fields_readers.len() {
      {
        let reader = match merge_state.stored_fields_readers[i] {
          Some(ref mut r) => r,
          _ => {
            return Err(LuceneError::illegal_state(
              "Expected Lucene90CompressingStoredFieldsReader",
            ));
          },
        };
        reader.check_integrity()?;
      }
      let visitor = MergeVisitor::new(
        merge_state.merge_field_infos.as_ref(),
        merge_state.field_infos[i].as_ref(),
      )?;

      subs.push(Sub::new(StoredFieldsMergeSub::new(
        visitor,
        merge_state.doc_map(i),
        i,
        merge_state.max_docs[i],
      )));
    }

    let mut doc_count = 0;
    let mut doc_id_merger = of(subs, merge_state.needs_index_sort)?;

    while let Some(sub_idx) = doc_id_merger.next()? {
      let sub = &mut doc_id_merger.get_subs_mut()[sub_idx];
      debug_assert_eq!(sub.mapped_doc_id, doc_count);

      writer.start_document()?;
      let reader = match merge_state.stored_fields_readers[sub.sub.reader_index] {
        Some(ref mut r) => r,
        _ => {
          return Err(LuceneError::illegal_state(
            "Expected Lucene90CompressingStoredFieldsReader",
          ));
        },
      };
      reader.document_with_visitor(sub.sub.doc_id, &mut sub.sub.visitor, Some(&mut *writer))?;
      writer.finish_document()?;
      doc_count += 1;
    }

    writer.finish(doc_count, dir)?;
    Ok(doc_count)
  }
}
pub type DefaultStoredFieldsWriter<D> =
  <DefaultStoredFieldsFormat as StoredFieldsFormat>::StoredFieldsWriter<D>;
struct StoredFieldsMergeSub<'a, DM> {
  pub reader_index: usize,
  pub max_doc: i32,
  pub visitor: MergeVisitor<'a>,
  pub doc_id: i32,
  pub doc_map: SharedDocMap<DM>,
}

impl<'a, DM> StoredFieldsMergeSub<'a, DM> {
  fn new(
    visitor: MergeVisitor<'a>,
    doc_map: SharedDocMap<DM>,
    reader_index: usize,
    max_doc: i32,
  ) -> Self {
    Self {
      reader_index,
      max_doc,
      visitor,
      doc_id: -1,
      doc_map,
    }
  }
}
impl<DM> SubBase for StoredFieldsMergeSub<'_, DM>
where
  DM: DocMap,
{
  fn next_doc(&mut self) -> Result<i32> {
    self.doc_id += 1;
    if self.doc_id == self.max_doc {
      Ok(NO_MORE_DOCS)
    } else {
      Ok(self.doc_id)
    }
  }

  type DocMap = DM;

  fn get_doc_map(&self) -> Result<&Self::DocMap> {
    Ok(self.doc_map.as_ref())
  }
}
/// A visitor that adds every field it sees.
#[derive(Default, Clone)]
pub(crate) struct MergeVisitor<'a> {
  remapper: Option<&'a FieldInfos>,
}
impl<'a> MergeVisitor<'a> {
  pub(crate) fn new(
    merge_field_infos: &'a FieldInfos,
    reader_field_infos: &FieldInfos,
  ) -> Result<Self> {
    for fi in reader_field_infos {
      match merge_field_infos.field_info_by_number(fi.number)? {
        Some(other) if other.name == fi.name => {},
        _ => {
          return Ok(Self {
            remapper: Some(merge_field_infos),
          });
        },
      }
    }
    Ok(Self { remapper: None })
  }
  fn remap<'b>(&'b self, field: &'b FieldInfo) -> Result<&'b FieldInfo> {
    if let Some(remapper) = self.remapper {
      // field numbers are not aligned, we need to remap to the new field
      // number
      match remapper.field_info_by_name(&field.name)? {
        Some(new_field) => Ok(new_field),
        None => Err(LuceneError::illegal_state(format!(
          "FieldInfo not found in remapper with filed_name: {}",
          field.name
        ))),
      }
    } else {
      Ok(field)
    }
  }
}
impl StoredFieldVisitor for MergeVisitor<'_> {
  fn binary_field_with_input<S, DI>(
    &mut self,
    field_info: &FieldInfo,
    input: &mut DI,
    length: usize,
    writer: Option<&mut S>,
  ) -> Result<()>
  where
    S: StoredFieldsWriter,
    DI: DataInput,
  {
    let writer =
      writer.ok_or_else(|| LuceneError::illegal_state("StoredFieldsWriter is required"))?;
    writer.write_field_with_input(self.remap(field_info)?, input, length)
  }

  fn binary_field<S>(
    &mut self,
    field_info: &FieldInfo,
    value: std::borrow::Cow<'_, [u8]>,
    writer: Option<&mut S>,
  ) -> Result<()>
  where
    S: StoredFieldsWriter,
  {
    let writer =
      writer.ok_or_else(|| LuceneError::illegal_state("StoredFieldsWriter is required"))?;
    writer.write_field_bytes(
      self.remap(field_info)?,
      &BytesRef {
        bytes: value.as_ref(),
        offset: 0,
        length: value.len(),
      },
    )
  }

  fn string_field<S>(
    &mut self,
    field_info: &FieldInfo,
    value: std::borrow::Cow<'_, str>,
    writer: Option<&mut S>,
  ) -> Result<()>
  where
    S: StoredFieldsWriter,
  {
    let writer =
      writer.ok_or_else(|| LuceneError::illegal_state("StoredFieldsWriter is required"))?;
    writer.write_field_str(self.remap(field_info)?, &value)
  }

  fn int_field<S>(
    &mut self,
    field_info: &FieldInfo,
    value: i32,
    writer: Option<&mut S>,
  ) -> Result<()>
  where
    S: StoredFieldsWriter,
  {
    let writer =
      writer.ok_or_else(|| LuceneError::illegal_state("StoredFieldsWriter is required"))?;
    writer.write_field_i32(self.remap(field_info)?, value)
  }

  fn long_field<S>(
    &mut self,
    field_info: &FieldInfo,
    value: i64,
    writer: Option<&mut S>,
  ) -> Result<()>
  where
    S: StoredFieldsWriter,
  {
    let writer =
      writer.ok_or_else(|| LuceneError::illegal_state("StoredFieldsWriter is required"))?;
    writer.write_field_i64(self.remap(field_info)?, value)
  }

  fn float_field<S>(
    &mut self,
    field_info: &FieldInfo,
    value: f32,
    writer: Option<&mut S>,
  ) -> Result<()>
  where
    S: StoredFieldsWriter,
  {
    let writer =
      writer.ok_or_else(|| LuceneError::illegal_state("StoredFieldsWriter is required"))?;
    writer.write_field_f32(self.remap(field_info)?, value)
  }

  fn double_field<S>(
    &mut self,
    field_info: &FieldInfo,
    value: f64,
    writer: Option<&mut S>,
  ) -> Result<()>
  where
    S: StoredFieldsWriter,
  {
    let writer =
      writer.ok_or_else(|| LuceneError::illegal_state("StoredFieldsWriter is required"))?;
    writer.write_field_f64(self.remap(field_info)?, value)
  }

  fn needs_field<S>(&mut self, _field_info: &FieldInfo, _writer: Option<&mut S>) -> Result<Status>
  where
    S: StoredFieldsWriter,
  {
    Ok(Status::Yes)
  }
}

pub enum StoredFieldsWriterEnum2<A, B> {
  A(A),
  B(B),
}

impl<A, B> Closeable for StoredFieldsWriterEnum2<A, B>
where
  A: Closeable,
  B: Closeable,
{
  fn close(&mut self) -> Result<()> {
    match self {
      Self::A(inner) => inner.close(),
      Self::B(inner) => inner.close(),
    }
  }
}

impl<A, B> Accountable for StoredFieldsWriterEnum2<A, B>
where
  A: Accountable,
  B: Accountable,
{
  fn ram_bytes_used(&self) -> Result<i64> {
    match self {
      Self::A(inner) => inner.ram_bytes_used(),
      Self::B(inner) => inner.ram_bytes_used(),
    }
  }
}

impl<A, B> StoredFieldsWriter for StoredFieldsWriterEnum2<A, B>
where
  A: StoredFieldsWriter,
  B: StoredFieldsWriter,
{
  fn start_document(&mut self) -> Result<()> {
    match self {
      Self::A(inner) => inner.start_document(),
      Self::B(inner) => inner.start_document(),
    }
  }

  fn finish_document(&mut self) -> Result<()> {
    match self {
      Self::A(inner) => inner.finish_document(),
      Self::B(inner) => inner.finish_document(),
    }
  }

  fn write_field_i32(&mut self, field_info: &FieldInfo, value: i32) -> Result<()> {
    match self {
      Self::A(inner) => inner.write_field_i32(field_info, value),
      Self::B(inner) => inner.write_field_i32(field_info, value),
    }
  }

  fn write_field_i64(&mut self, field_info: &FieldInfo, value: i64) -> Result<()> {
    match self {
      Self::A(inner) => inner.write_field_i64(field_info, value),
      Self::B(inner) => inner.write_field_i64(field_info, value),
    }
  }

  fn write_field_f32(&mut self, field_info: &FieldInfo, value: f32) -> Result<()> {
    match self {
      Self::A(inner) => inner.write_field_f32(field_info, value),
      Self::B(inner) => inner.write_field_f32(field_info, value),
    }
  }

  fn write_field_f64(&mut self, field_info: &FieldInfo, value: f64) -> Result<()> {
    match self {
      Self::A(inner) => inner.write_field_f64(field_info, value),
      Self::B(inner) => inner.write_field_f64(field_info, value),
    }
  }

  fn write_field_with_input<DI>(
    &mut self,
    field_info: &FieldInfo,
    input: &mut DI,
    length: usize,
  ) -> Result<()>
  where
    DI: DataInput,
  {
    match self {
      Self::A(inner) => inner.write_field_with_input(field_info, input, length),
      Self::B(inner) => inner.write_field_with_input(field_info, input, length),
    }
  }

  fn write_field_bytes<S>(&mut self, field_info: &FieldInfo, value: &BytesRef<S>) -> Result<()>
  where
    S: ByteSource,
  {
    match self {
      Self::A(inner) => inner.write_field_bytes(field_info, value),
      Self::B(inner) => inner.write_field_bytes(field_info, value),
    }
  }

  fn write_field_str(&mut self, field_info: &FieldInfo, value: &str) -> Result<()> {
    match self {
      Self::A(inner) => inner.write_field_str(field_info, value),
      Self::B(inner) => inner.write_field_str(field_info, value),
    }
  }

  fn finish<D>(&mut self, num_docs: i32, dir: &D) -> Result<()>
  where
    D: Directory,
  {
    match self {
      Self::A(inner) => inner.finish(num_docs, dir),
      Self::B(inner) => inner.finish(num_docs, dir),
    }
  }

  fn merge<D, D1, CR>(&mut self, merge_state: &mut MergeState<D, CR>, dir: &D1) -> Result<i32>
  where
    D1: Directory,
    CR: CodecReader,
  {
    match self {
      Self::A(inner) => inner.merge(merge_state, dir),
      Self::B(inner) => inner.merge(merge_state, dir),
    }
  }
}