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
use std::io;
use common::BinarySerializable;
use crate::directory::FileSlice;
use crate::positions::PositionReader;
use crate::postings::{BlockSegmentPostings, SegmentPostings, TermInfo};
use crate::schema::{IndexRecordOption, Term};
use crate::termdict::TermDictionary;
/// The inverted index reader is in charge of accessing
/// the inverted index associated with a specific field.
///
/// # Note
///
/// It is safe to delete the segment associated with
/// an `InvertedIndexReader`. As long as it is open,
/// the [`FileSlice`] it is relying on should
/// stay available.
///
/// `InvertedIndexReader` are created by calling
/// [`SegmentReader::inverted_index()`](crate::SegmentReader::inverted_index).
pub struct InvertedIndexReader {
termdict: TermDictionary,
postings_file_slice: FileSlice,
positions_file_slice: FileSlice,
record_option: IndexRecordOption,
total_num_tokens: u64,
}
impl InvertedIndexReader {
#[allow(clippy::needless_pass_by_value)] // for symmetry
pub(crate) fn new(
termdict: TermDictionary,
postings_file_slice: FileSlice,
positions_file_slice: FileSlice,
record_option: IndexRecordOption,
) -> io::Result<InvertedIndexReader> {
let (total_num_tokens_slice, postings_body) = postings_file_slice.split(8);
let total_num_tokens = u64::deserialize(&mut total_num_tokens_slice.read_bytes()?)?;
Ok(InvertedIndexReader {
termdict,
postings_file_slice: postings_body,
positions_file_slice,
record_option,
total_num_tokens,
})
}
/// Creates an empty `InvertedIndexReader` object, which
/// contains no terms at all.
pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
InvertedIndexReader {
termdict: TermDictionary::empty(),
postings_file_slice: FileSlice::empty(),
positions_file_slice: FileSlice::empty(),
record_option,
total_num_tokens: 0u64,
}
}
/// Returns the term info associated with the term.
pub fn get_term_info(&self, term: &Term) -> io::Result<Option<TermInfo>> {
self.termdict.get(term.value_bytes())
}
/// Return the term dictionary datastructure.
pub fn terms(&self) -> &TermDictionary {
&self.termdict
}
/// Resets the block segment to another position of the postings
/// file.
///
/// This is useful for enumerating through a list of terms,
/// and consuming the associated posting lists while avoiding
/// reallocating a [`BlockSegmentPostings`].
///
/// # Warning
///
/// This does not reset the positions list.
pub fn reset_block_postings_from_terminfo(
&self,
term_info: &TermInfo,
block_postings: &mut BlockSegmentPostings,
) -> io::Result<()> {
let postings_slice = self
.postings_file_slice
.slice(term_info.postings_range.clone());
let postings_bytes = postings_slice.read_bytes()?;
block_postings.reset(term_info.doc_freq, postings_bytes)?;
Ok(())
}
/// Returns a block postings given a `Term`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
pub fn read_block_postings(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<BlockSegmentPostings>> {
self.get_term_info(term)?
.map(move |term_info| self.read_block_postings_from_terminfo(&term_info, option))
.transpose()
}
/// Returns a block postings given a `term_info`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
pub fn read_block_postings_from_terminfo(
&self,
term_info: &TermInfo,
requested_option: IndexRecordOption,
) -> io::Result<BlockSegmentPostings> {
let postings_data = self
.postings_file_slice
.slice(term_info.postings_range.clone());
BlockSegmentPostings::open(
term_info.doc_freq,
postings_data,
self.record_option,
requested_option,
)
}
/// Returns a posting object given a `term_info`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
pub fn read_postings_from_terminfo(
&self,
term_info: &TermInfo,
option: IndexRecordOption,
) -> io::Result<SegmentPostings> {
let block_postings = self.read_block_postings_from_terminfo(term_info, option)?;
let position_reader = {
if option.has_positions() {
let positions_data = self
.positions_file_slice
.read_bytes_slice(term_info.positions_range.clone())?;
let position_reader = PositionReader::open(positions_data)?;
Some(position_reader)
} else {
None
}
};
Ok(SegmentPostings::from_block_postings(
block_postings,
position_reader,
))
}
/// Returns the total number of tokens recorded for all documents
/// (including deleted documents).
pub fn total_num_tokens(&self) -> u64 {
self.total_num_tokens
}
/// Returns the segment postings associated with the term, and with the given option,
/// or `None` if the term has never been encountered and indexed.
///
/// If the field was not indexed with the indexing options that cover
/// the requested options, the returned [`SegmentPostings`] the method does not fail
/// and returns a `SegmentPostings` with as much information as possible.
///
/// For instance, requesting [`IndexRecordOption::WithFreqs`] for a
/// [`TextOptions`](crate::schema::TextOptions) that does not index position
/// will return a [`SegmentPostings`] with `DocId`s and frequencies.
pub fn read_postings(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<SegmentPostings>> {
self.get_term_info(term)?
.map(move |term_info| self.read_postings_from_terminfo(&term_info, option))
.transpose()
}
pub(crate) fn read_postings_no_deletes(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<SegmentPostings>> {
self.get_term_info(term)?
.map(|term_info| self.read_postings_from_terminfo(&term_info, option))
.transpose()
}
/// Returns the number of documents containing the term.
pub fn doc_freq(&self, term: &Term) -> io::Result<u32> {
Ok(self
.get_term_info(term)?
.map(|term_info| term_info.doc_freq)
.unwrap_or(0u32))
}
}
#[cfg(feature = "quickwit")]
impl InvertedIndexReader {
pub(crate) async fn get_term_info_async(&self, term: &Term) -> io::Result<Option<TermInfo>> {
self.termdict.get_async(term.value_bytes()).await
}
/// Returns a block postings given a `Term`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
pub async fn warm_postings(&self, term: &Term, with_positions: bool) -> io::Result<()> {
let term_info_opt: Option<TermInfo> = self.get_term_info_async(term).await?;
if let Some(term_info) = term_info_opt {
self.postings_file_slice
.read_bytes_slice_async(term_info.postings_range.clone())
.await?;
if with_positions {
self.positions_file_slice
.read_bytes_slice_async(term_info.positions_range.clone())
.await?;
}
}
Ok(())
}
/// Returns a block postings given a `Term` asynchronously.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings_async()`] instead.
pub async fn read_block_postings_async(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<BlockSegmentPostings>> {
match self.get_term_info_async(term).await? {
None => None,
Some(term_info) => Some(
self.read_block_postings_from_terminfo_async(&term_info, option)
.await,
),
}
.transpose()
}
pub(crate) async fn read_postings_no_deletes_async(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<SegmentPostings>> {
match self.get_term_info_async(term).await? {
None => None,
Some(term_info) => Some(
self.read_postings_from_terminfo_async(&term_info, option)
.await,
),
}
.transpose()
}
/// Returns a posting object given a `term_info` asynchronously.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings_async()`] instead.
pub async fn read_postings_from_terminfo_async(
&self,
term_info: &TermInfo,
option: IndexRecordOption,
) -> io::Result<SegmentPostings> {
let block_postings = self
.read_block_postings_from_terminfo_async(term_info, option)
.await?;
let position_reader = {
if option.has_positions() {
let positions_data = self
.positions_file_slice
.read_bytes_slice_async(term_info.positions_range.clone())
.await?;
let position_reader = PositionReader::open(positions_data)?;
Some(position_reader)
} else {
None
}
};
Ok(SegmentPostings::from_block_postings(
block_postings,
position_reader,
))
}
/// Returns a block postings given a `term_info` asynchronously.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings_async()`] instead.
pub async fn read_block_postings_from_terminfo_async(
&self,
term_info: &TermInfo,
requested_option: IndexRecordOption,
) -> io::Result<BlockSegmentPostings> {
let postings_data = self
.postings_file_slice
.slice(term_info.postings_range.clone());
BlockSegmentPostings::open_async(
term_info.doc_freq,
postings_data,
self.record_option,
requested_option,
)
.await
}
/// Returns the segment postings associated with the term asynchronously, and with the given
/// option, or `None` if the term has never been encountered and indexed.
///
/// If the field was not indexed with the indexing options that cover
/// the requested options, the returned [`SegmentPostings`] the method does not fail
/// and returns a `SegmentPostings` with as much information as possible.
///
/// For instance, requesting [`IndexRecordOption::WithFreqs`] for a
/// [`TextOptions`](crate::schema::TextOptions) that does not index position
/// will return a [`SegmentPostings`] with `DocId`s and frequencies.
pub async fn read_postings_async(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<SegmentPostings>> {
match self.get_term_info(term)? {
None => None,
Some(term_info) => Some(
self.read_postings_from_terminfo_async(&term_info, option)
.await,
),
}
.transpose()
}
/// Read the block postings for all terms.
/// This method is for an advanced usage only.
///
/// If you know which terms to pre-load, prefer using [`Self::warm_postings`] instead.
pub async fn warm_postings_full(&self, with_positions: bool) -> io::Result<()> {
self.postings_file_slice.read_bytes_async().await?;
if with_positions {
self.positions_file_slice.read_bytes_async().await?;
}
Ok(())
}
/// Returns the number of documents containing the term asynchronously.
pub async fn doc_freq_async(&self, term: &Term) -> io::Result<u32> {
Ok(self
.get_term_info_async(term)
.await?
.map(|term_info| term_info.doc_freq)
.unwrap_or(0u32))
}
}