-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathisr.cpp
More file actions
618 lines (509 loc) · 16.2 KB
/
Copy pathisr.cpp
File metadata and controls
618 lines (509 loc) · 16.2 KB
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
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
#include <climits>
#include "isr.h"
#include "../index/index.h"
// ISR
Location ISR::GetStartLocation() // -> return start
{
return start;
}
Location ISR::GetEndLocation() // -> return end
{
return end;
}
size_t ISR::GetMatchingDoc() // return result
{
return matchingDocument;
}
unsigned ISR::GetDocumentCount()
{
return postingList->documentCount;
}
unsigned ISR::GetNumberOfOccurrences()
{
return postingList->posts;
}
const SerialPost *ISR::GetCurrentPost()
{
return curr;
}
void ISR::SetCurrentPost( const SerialPost *p )
{
curr = p;
}
void ISR::SetPostingList( const SerialPostingList *pl )
{
postingList = pl;
}
// ISRWord
const SerialPost *ISRWord::Next( )
{
// do a next on the term, then return match
return Seek( start + 1 );
}
const SerialPost *ISRWord::Seek ( Location target )
{
// Seek ISR to the first occurrence beginning at the target location
// use synchronization point
uint8_t highBits = target >> 56;
// std::cout << (int)highBits << std::endl;
size_t idx = 0;
while (highBits > 0) {
highBits >>= 1;
idx++;
}
if (idx >= postingList->seekIndex)
return nullptr;
const std::pair<size_t, size_t> *p = postingList->getSeekPair( idx );
size_t offset = p->first;
size_t actualLocation = p->second;
// std::cout << "offset: " << offset << " actual loc: " << actualLocation << std::endl;
// seek from synchronization point to target
// if using seek table
while ( actualLocation < target )
{
if ( offset + 1 < postingList->posts ) // TODO: check
{
const SerialPost *data = postingList->getPost(offset+1);
try {
actualLocation += GetCustomUtf8(reinterpret_cast<const Utf8 *>(data));
offset ++;
} catch (std::runtime_error &e) {
return nullptr;
}
}
else
{
// reach the end and no match, return nullptr
return nullptr;
}
}
// update start location
start = actualLocation;
// std::cout << "offset: " << offset << " actual loc: " << actualLocation << std::endl;
// std::cout << "data 2: " << offset << std::endl;
curr = postingList->getPost(offset);
// std::cout << "test\n";
// TODO: update end(?)
// update end of document
// std::cout << "doc end start loc: " << EndDoc->GetStartLocation() << std::endl;
if ( actualLocation > EndDoc->GetStartLocation( ) || actualLocation < EndDoc->GetStartLocation() - EndDoc->GetDocumentLength() ) {
// std::cout << "docend seek\n";
EndDoc->Seek( actualLocation );
}
// std::cout << "end if\n";
matchingDocument = EndDoc->GetMatchingDoc();
return curr;
}
const SerialPost *ISRWord::NextDocument( )
{
// Seek ISR to the first occurrence just past the end of this document
return Seek( EndDoc->GetStartLocation( ) + 1 );
}
// ISREndDoc
Location ISREndDoc::GetStartLocation() // -> return start
{
return start;
}
Location ISREndDoc::GetEndLocation() // -> return end
{
return end;
}
size_t ISREndDoc::GetMatchingDoc() // return result
{
return matchingDocument;
}
const SerialPost *ISREndDoc::GetCurrentPost()
{
return curr;
}
void ISREndDoc::SetCurrentPost( const SerialPost *p )
{
curr = p;
}
void ISREndDoc::SetPostingList( const SerialPostingList *pl )
{
postingList = pl;
}
const SerialPost *ISREndDoc::Seek ( Location target )
{
// Seek ISR to the first occurrence beginning at the target location
// use synchronization point
uint8_t highBits = target >> 56;
size_t idx = 0;
while (highBits > 0) {
highBits >>= 1;
idx++;
}
if (idx >= postingList->seekIndex)
return nullptr;
const std::pair<size_t, size_t> *p = postingList->getSeekPair( idx );
size_t offset = p->first;
size_t actualLocation = p->second;
// std::cout << "eod high bit: " << idx << " offset: " << offset << " actual location: " << actualLocation << "\n";
// std::cout << "number of eod: " << postingList->posts << "\n";
// seek from synchronization point to target
while ( actualLocation < target )
{
if ( offset + 1 < postingList->posts )
{
// actualLocation += GetCustomUtf8((*list)[offset+1].getData());
try {
size_t delta = GetCustomUtf8(reinterpret_cast<const Utf8*>(postingList->getPost(offset+1)));
SetDocumentLength(delta);
actualLocation += delta;
offset ++;
matchingDocument = offset; // set doc id of this document
} catch (std::runtime_error &e) {
return nullptr;
}
}
else
return nullptr;
}
// update start location
start = actualLocation;
curr = postingList->getPost(offset);
matchingDocument = offset;
return curr;
}
const SerialPost *ISREndDoc::NextDocument( )
{
// Seek ISR to the first occurrence just past the end of this document
return Seek( start + 1 );
}
const SerialPost *ISREndDoc::Next()
{
return Seek( start + 1 );
}
// set document, title, url lengths
void ISREndDoc::SetDocumentLength(size_t length)
{
documentLength = length;
}
void ISREndDoc::SetTitleLength(size_t length)
{
titleLength = length;
}
void ISREndDoc::SetUrlLength(size_t length)
{
urlLength = length;
}
// get document, title, url lengths
size_t ISREndDoc::GetDocumentLength()
{
return documentLength;
}
size_t ISREndDoc::GetTitleLength()
{
return titleLength;
}
size_t ISREndDoc::GetUrlLength()
{
return urlLength;
}
// ISRContainer
// Do Open ISR in index ( including assign Contained and Excluded )
// ISRContainer::ISRContainer( unsigned int countContained, unsigned int countExcluded )
// : CountContained( countContained ), CountExcluded( countExcluded )
// {
// // set ISR
// if ( CountContained > 0 )
// {
// Contained = new ISR*[CountContained];
// for ( unsigned int i = 0; i < CountContained; i ++ )
// Contained[ i ] = new ISR( );
// }
// if ( CountExcluded > 0 )
// {
// Excluded = new ISR*[countExcluded];
// for ( unsigned int i = 0; i < countExcluded; i ++ )
// Excluded[ i ] = new ISR( );
// }
// EndDoc = new ISREndDoc( );
// }
// ISRContainer::~ISRContainer( )
// {
// for ( int i = 0; i < CountContained; i ++ )
// delete Contained[ i ];
// delete[ ] Contained;
// for ( int i = 0; i < CountExcluded; i ++ )
// delete Excluded[ i ];
// delete[ ] Excluded;
// delete EndDoc;
// }
const SerialPost *ISRContainer::Seek( Location target )
{
bool found = false;
while ( !found )
{
// seek all the included ISRs to the first occurrence beginning at the target location
nearestStartLocation = INT_MAX;
farthestStartLocation = 0;
for (int i = 0; i < CountContained; i++)
{
const SerialPost *result = Contained[ i ]->Seek( target );
if ( result == nullptr )
return nullptr; // if any ISR reaches the end, there is no match
// update nearest and farthest terms
Location loc = Contained[ i ]->GetStartLocation();
if ( loc < nearestStartLocation )
{
nearestContained = i;
nearestStartLocation = loc;
}
if ( loc > farthestStartLocation )
{
farthestContained = i;
farthestStartLocation = loc;
}
}
for ( int i = 0; i < CountExcluded; i ++ )
Excluded[ i ]->Seek( target );
Location docEnd, docBegin;
while ( true )
{
// move the document end ISR to just past the furthest contained ISR
const SerialPost *result = EndDoc->Seek( Contained[ farthestContained ]->GetStartLocation( ) + 1 );
if ( result == nullptr )
return nullptr; // if any ISR reaches the end, there is no match
// calculate document begin location
docEnd = EndDoc->GetStartLocation( );
docBegin = docEnd - EndDoc->GetDocumentLength( );
// seek all the other contained terms to past the document begin
bool allWithinDoc = true;
nearestStartLocation = INT_MAX;
farthestStartLocation = 0;
for ( int i = 0; i < CountContained; i ++ )
{
const SerialPost *result = Contained[ i ]->Seek( docBegin );
if ( result == nullptr )
return nullptr; // if any ISR reaches the end, there is no match
// update nearest and farthest terms
Location loc = Contained[ i ]->GetStartLocation();
if ( loc < nearestStartLocation )
{
nearestContained = i;
nearestStartLocation = loc;
}
if ( loc > farthestStartLocation )
{
farthestContained = i;
farthestStartLocation = loc;
}
if ( Contained[ i ]->GetStartLocation() > docEnd )
allWithinDoc = false; // not in this document
}
// if all ISRs within the document, break the loop
if ( allWithinDoc )
break;
}
// seek all the excluded ISRs to the first occurrence beginning at the document begin location
found = true;
for ( int i = 0; i < CountExcluded; i ++ )
{
const SerialPost *result = Excluded[ i ]->Seek( docBegin );
if ( result != nullptr && Excluded[ i ]->GetStartLocation() < docEnd ) // if any excluded ISR falls within the document
{
// reset the target to one past the end of the document
target = docEnd + 1;
found = false;
break;
}
}
}
// find document
matchingDocument = EndDoc->GetMatchingDoc();
return Contained[0]->GetCurrentPost(); // return something, not nullptr
}
const SerialPost *ISRContainer::Next( )
{
return Seek( Contained[ nearestContained ]->GetStartLocation( ) + 1 );
}
const SerialPost *ISRContainer::NextDocument()
{
return Seek( EndDoc->GetStartLocation( ) + 1 );
}
// ISRAnd
const SerialPost *ISRAnd::Seek( Location target )
{
// Seek all the ISRs to the first occurrence beginning at the target location.
nearestStartLocation = INT_MAX;
farthestStartLocation = 0;
for ( int i = 0; i < NumberOfTerms; i ++ )
{
const SerialPost *result = Terms[ i ]->Seek( target );
if ( result == nullptr )
return nullptr; // if any ISR reaches the end, there is no match
// update nearest and farthest terms
Location loc = Terms[ i ]->GetStartLocation();
if ( loc < nearestStartLocation )
{
nearestTerm = i;
nearestStartLocation = loc;
}
if ( loc > farthestStartLocation )
{
farthestTerm = i;
farthestStartLocation = loc;
}
}
Location docEnd, docBegin;
while ( true )
{
// move the document end ISR to just past the farthest word ISR
const SerialPost *result = EndDoc->Seek( Terms[ farthestTerm ]->GetStartLocation( ) + 1 );
if ( result == nullptr )
return nullptr; // if any ISR reaches the end, there is no match
// calculate document begin location
docEnd = EndDoc->GetStartLocation( );
docBegin = docEnd - EndDoc->GetDocumentLength( );
// seek all the other terms to past the document begin
bool allWithinDoc = true;
nearestStartLocation = INT_MAX;
farthestStartLocation = 0;
for ( int i = 0; i < NumberOfTerms; i ++ )
{
const SerialPost *result = Terms[ i ]->Seek( docBegin );
if ( result == nullptr ) {
return nullptr; // if any ISR reaches the end, there is no match
}
// update nearest and farthest terms
Location loc = Terms[ i ]->GetStartLocation();
if ( loc < nearestStartLocation )
{
nearestTerm = i;
nearestStartLocation = loc;
}
if ( loc > farthestStartLocation )
{
farthestTerm = i;
farthestStartLocation = loc;
}
if ( Terms[ i ]->GetStartLocation() > docEnd )
allWithinDoc = false; // not in this document
}
// if all ISRs within the document, break the loop
if ( allWithinDoc )
break;
}
// find document
matchingDocument = EndDoc->GetMatchingDoc();
return Terms[0]->GetCurrentPost(); // return something, not nullptr
}
const SerialPost *ISRAnd::Next()
{
return Seek( nearestStartLocation + 1 );
}
const SerialPost *ISRAnd::NextDocument()
{
return Seek( EndDoc->GetStartLocation( ) + 1 );
}
// ISROr
const SerialPost *ISROr::Seek( Location target )
{
nearestStartLocation = INT_MAX;
// nearestEndLocation = 0;
bool flag = false; // if all terms reach the end, return nullptr
for ( int i = 0; i < NumberOfTerms; i ++ )
{
if ( Terms[ i ] != nullptr )
{
const SerialPost *result = Terms[ i ] -> Seek(target);
if ( result )
{
flag = true;
Location loc = Terms[ i ]->GetStartLocation();
if ( loc <= nearestStartLocation )
{
nearestTerm = i;
nearestStartLocation = loc;
}
}
}
}
if ( !flag )
return nullptr;
matchingDocument = Terms[ nearestTerm ] -> GetMatchingDoc();
EndDoc->Seek(Terms[nearestTerm]->EndDoc->GetStartLocation() - 1);
return Terms[nearestTerm]->GetCurrentPost();
}
const SerialPost *ISROr::NextDocument()
{
return Seek( EndDoc->GetStartLocation( ) + 1 );
}
const SerialPost *ISROr::Next()
{
return Seek( nearestStartLocation + 1 );
}
Location ISROr::GetStartLocation()
{
return nearestStartLocation;
}
Location ISROr::GetEndLocation()
{
return nearestEndLocation;
}
// ISRPhrase
const SerialPost *ISRPhrase::Seek( Location target )
{
nearestStartLocation = INT_MAX;
nearestEndLocation = 0;
for (int i = 0; i < NumberOfTerms; i++)
{
const SerialPost *result = Terms[ i ]->Seek(target);
if ( result == nullptr )
return nullptr;
Location loc = Terms[ i ]->GetStartLocation();
if (loc < nearestStartLocation)
{
nearestStartLocation = loc;
nearestTerm = i;
}
if (loc > nearestEndLocation)
{
nearestEndLocation = loc;
farthestTerm = i;
}
}
// 1, 5;3, 6;2, 7
// next: new target = neareststartloc + 1
// neareststartloc:
// std::cout<<"nearestStartLocation: "<<nearestStartLocation<<std::endl;
// std::cout << Terms[0]->GetStartLocation() << std::endl;
// std::cout << Terms[1]->GetStartLocation() << std::endl;
for ( int i = 1; i < NumberOfTerms; i ++ )
{
if (Terms[i]->GetStartLocation() != Terms[i - 1]->GetStartLocation() + 1 )
return Next();
}
Location docEnd, docBegin;
const SerialPost *result = EndDoc->Seek(Terms[farthestTerm]->GetStartLocation() + 1);
if ( result == nullptr )
return nullptr;
docEnd = EndDoc->GetStartLocation( );
docBegin = docEnd - EndDoc->GetDocumentLength( );
bool allWithinDoc = true;
for (unsigned i = 0; i < NumberOfTerms; ++i)
{
if (Terms[i]->GetStartLocation() < docBegin || Terms[i]->GetStartLocation() > docEnd)
{
allWithinDoc = false;
break;
}
}
if (allWithinDoc)
{
matchingDocument = EndDoc->GetMatchingDoc();
return Terms[0]->GetCurrentPost();
}
else
return Next();
}
const SerialPost *ISRPhrase::Next()
{
return Seek( nearestStartLocation + 1 );
}
const SerialPost *ISRPhrase::NextDocument()
{
return Seek( EndDoc->GetStartLocation( ) + 1 );
}