/ Check-in [60de1594]
Login
SQLite training in Houston TX on 2019-11-05 (details)
Part of the 2019 Tcl Conference

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Bias the fts5 snippet() function to return snippets that look like they start at the start of sentences.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fts5-snippet-bias
Files: files | file ages | folders
SHA1: 60de159476edbd48dc363f7f77f09c32ea68422f
User & Date: dan 2016-08-17 19:05:12
Context
2016-08-18
14:47
Adjust some tests to account for recent changes to the fts5 snippet function. check-in: 184ecbe9 user: dan tags: fts5-snippet-bias
2016-08-17
19:05
Bias the fts5 snippet() function to return snippets that look like they start at the start of sentences. check-in: 60de1594 user: dan tags: fts5-snippet-bias
11:14
Fix a problem in the fts5 snippet() auxiliary function. check-in: a861713c user: dan tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to ext/fts5/fts5_aux.c.

241
242
243
244
245
246
247













































































































248
249
250
251
252
253
254
...
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
...
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376

377
378
379
380
381
382
383
  if( rc!=SQLITE_OK ){
    sqlite3_result_error_code(pCtx, rc);
  }
}
/*
** End of highlight() implementation.
**************************************************************************/














































































































/*
** Implementation of snippet() function.
*/
static void fts5SnippetFunction(
  const Fts5ExtensionApi *pApi,   /* API offered by current FTS version */
  Fts5Context *pFts,              /* First arg to pass to pApi functions */
................................................................................
  int nToken;                     /* 5th argument to snippet() */
  int nInst = 0;                  /* Number of instance matches this row */
  int i;                          /* Used to iterate through instances */
  int nPhrase;                    /* Number of phrases in query */
  unsigned char *aSeen;           /* Array of "seen instance" flags */
  int iBestCol;                   /* Column containing best snippet */
  int iBestStart = 0;             /* First token of best snippet */
  int iBestLast;                  /* Last token of best snippet */
  int nBestScore = 0;             /* Score of best snippet */
  int nColSize = 0;               /* Total size of iBestCol in tokens */



  if( nVal!=5 ){
    const char *zErr = "wrong number of arguments to function snippet()";
    sqlite3_result_error(pCtx, zErr, -1);
    return;
  }


  memset(&ctx, 0, sizeof(HighlightContext));
  iCol = sqlite3_value_int(apVal[0]);
  ctx.zOpen = (const char*)sqlite3_value_text(apVal[1]);
  ctx.zClose = (const char*)sqlite3_value_text(apVal[2]);
  zEllips = (const char*)sqlite3_value_text(apVal[3]);
  nToken = sqlite3_value_int(apVal[4]);
  iBestLast = nToken-1;

  iBestCol = (iCol>=0 ? iCol : 0);
  nPhrase = pApi->xPhraseCount(pFts);
  aSeen = sqlite3_malloc(nPhrase);
  if( aSeen==0 ){
    rc = SQLITE_NOMEM;
  }

  if( rc==SQLITE_OK ){
    rc = pApi->xInstCount(pFts, &nInst);
  }


















  for(i=0; rc==SQLITE_OK && i<nInst; i++){
    int ip, iSnippetCol, iStart;

    memset(aSeen, 0, nPhrase);
    rc = pApi->xInst(pFts, i, &ip, &iSnippetCol, &iStart);
    if( rc==SQLITE_OK && (iCol<0 || iSnippetCol==iCol) ){





      int nScore = 1000;
      int iLast = iStart - 1 + pApi->xPhraseSize(pFts, ip);
      int j;
      aSeen[ip] = 1;

      for(j=i+1; rc==SQLITE_OK && j<nInst; j++){
        int ic; int io; int iFinal;
        rc = pApi->xInst(pFts, j, &ip, &ic, &io);
        iFinal = io + pApi->xPhraseSize(pFts, ip) - 1;
        if( rc==SQLITE_OK && ic==iSnippetCol && iLast<iStart+nToken ){
          nScore += aSeen[ip] ? 1000 : 1;
          aSeen[ip] = 1;
          if( iFinal>iLast ) iLast = iFinal;




        }
      }










      if( rc==SQLITE_OK && nScore>nBestScore ){

        iBestCol = iSnippetCol;
        iBestStart = iStart;
        iBestLast = iLast;
        nBestScore = nScore;


      }
    }
  }

  if( rc==SQLITE_OK ){
    rc = pApi->xColumnSize(pFts, iBestCol, &nColSize);
  }
  if( rc==SQLITE_OK ){
    rc = pApi->xColumnText(pFts, iBestCol, &ctx.zIn, &ctx.nIn);
  }
  if( ctx.zIn ){
    if( rc==SQLITE_OK ){
      rc = fts5CInstIterInit(pApi, pFts, iBestCol, &ctx.iter);
    }

    if( (iBestStart+nToken-1)>iBestLast ){
      iBestStart -= (iBestStart+nToken-1-iBestLast) / 2;
    }
    if( iBestStart+nToken>nColSize ){
      iBestStart = nColSize - nToken;
    }
    if( iBestStart<0 ) iBestStart = 0;

    ctx.iRangeStart = iBestStart;
    ctx.iRangeEnd = iBestStart + nToken - 1;

    if( iBestStart>0 ){
      fts5HighlightAppend(&rc, &ctx, zEllips, -1);
    }

................................................................................
      rc = pApi->xTokenize(pFts, ctx.zIn, ctx.nIn, (void*)&ctx,fts5HighlightCb);
    }
    if( ctx.iRangeEnd>=(nColSize-1) ){
      fts5HighlightAppend(&rc, &ctx, &ctx.zIn[ctx.iOff], ctx.nIn - ctx.iOff);
    }else{
      fts5HighlightAppend(&rc, &ctx, zEllips, -1);
    }

    if( rc==SQLITE_OK ){
      sqlite3_result_text(pCtx, (const char*)ctx.zOut, -1, SQLITE_TRANSIENT);
    }else{
      sqlite3_result_error_code(pCtx, rc);
    }
    sqlite3_free(ctx.zOut);
  }
  sqlite3_free(aSeen);

}

/************************************************************************/

/*
** The first time the bm25() function is called for a query, an instance
** of the following structure is allocated and populated.







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







 







<


>
>







>






<







<



>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
<
>
|
<
<
>
>
>
>
>
|
<
<
<

|
<
<
<
<
<
<
<
>
>
>
>



>
>
>
>
>
>
>
>
>
|
>
|
|
<
<
>
>




<
<
<








<
<
<
<
<
<
<
<







 







|
|
|
|
|
|
|
<

>







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
...
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
...
484
485
486
487
488
489
490
491
492
493
494
495
496
497

498
499
500
501
502
503
504
505
506
  if( rc!=SQLITE_OK ){
    sqlite3_result_error_code(pCtx, rc);
  }
}
/*
** End of highlight() implementation.
**************************************************************************/

/*
** Context object passed to the fts5SentenceFinderCb() function.
*/
typedef struct Fts5SFinder Fts5SFinder;
struct Fts5SFinder {
  int iPos;                       /* Current token position */
  int nFirstAlloc;                /* Allocated size of aFirst[] */
  int nFirst;                     /* Number of entries in aFirst[] */
  int *aFirst;                    /* Array of first token in each sentence */
  const char *zDoc;               /* Document being tokenized */
};

/*
** Add an entry to the Fts5SFinder.aFirst[] array. Grow the array if
** necessary. Return SQLITE_OK if successful, or SQLITE_NOMEM if an
** error occurs.
*/
static int fts5SentenceFinderAdd(Fts5SFinder *p, int iAdd){
  if( p->nFirstAlloc==p->nFirst ){
    int nNew = p->nFirstAlloc ? p->nFirstAlloc*2 : 64;
    int *aNew;

    aNew = (int*)sqlite3_realloc(p->aFirst, nNew*sizeof(int));
    if( aNew==0 ) return SQLITE_NOMEM;
    p->aFirst = aNew;
    p->nFirstAlloc = nNew;
  }
  p->aFirst[p->nFirst++] = iAdd;
  return SQLITE_OK;
}

/*
** This function is an xTokenize() callback used by the auxiliary snippet()
** function. Its job is to identify tokens that are the first in a sentence.
** For each such token, an entry is added to the SFinder.aFirst[] array.
*/
static int fts5SentenceFinderCb(
  void *pContext,                 /* Pointer to HighlightContext object */
  int tflags,                     /* Mask of FTS5_TOKEN_* flags */
  const char *pToken,             /* Buffer containing token */
  int nToken,                     /* Size of token in bytes */
  int iStartOff,                  /* Start offset of token */
  int iEndOff                     /* End offset of token */
){
  int rc = SQLITE_OK;

  if( (tflags & FTS5_TOKEN_COLOCATED)==0 ){
    Fts5SFinder *p = (Fts5SFinder*)pContext;
    if( p->iPos>0 ){
      int i;
      char c = 0;
      for(i=iStartOff-1; i>=0; i--){
        c = p->zDoc[i];
        if( c!=' ' && c!='\t' && c!='\n' && c!='\r' ) break;
      }
      if( i!=iStartOff-1 && (c=='.' || c==':') ){
        rc = fts5SentenceFinderAdd(p, p->iPos);
      }
    }else{
      rc = fts5SentenceFinderAdd(p, 0);
    }
    p->iPos++;
  }
  return rc;
}

static int fts5SnippetScore(
  const Fts5ExtensionApi *pApi,   /* API offered by current FTS version */
  Fts5Context *pFts,              /* First arg to pass to pApi functions */
  int nDocsize,                   /* Size of column in tokens */
  unsigned char *aSeen,           /* Array with one element per query phrase */
  int iCol,                       /* Column to score */
  int iPos,                       /* Starting offset to score */
  int nToken,                     /* Max tokens per snippet */
  int *pnScore,                   /* OUT: Score */
  int *piPos                      /* OUT: Adjusted offset */
){
  int rc;
  int i;
  int ip = 0;
  int ic = 0;
  int iOff = 0;
  int iFirst = -1;
  int nInst;
  int nScore = 0;

  rc = pApi->xInstCount(pFts, &nInst);
  for(i=0; i<nInst && rc==SQLITE_OK; i++){
    rc = pApi->xInst(pFts, i, &ip, &ic, &iOff);
    if( rc==SQLITE_OK && ic==iCol && iOff>=iPos && iOff<(iPos+nToken) ){
      nScore += (aSeen[ip] ? 1 : 1000);
      aSeen[ip] = 1;
      if( iFirst<0 ) iFirst = iOff;
    }
  }

  *pnScore = nScore;
  if( piPos ){
    int iLast = iOff + pApi->xPhraseSize(pFts, ip);
    int iAdj = iFirst - (nToken - (iLast-iFirst)) / 2;

    if( (iAdj+nToken)>nDocsize ) iAdj = nDocsize - nToken;
    if( iAdj<0 ) iAdj = 0;
    *piPos = iAdj;
  }

  return rc;
}

/*
** Implementation of snippet() function.
*/
static void fts5SnippetFunction(
  const Fts5ExtensionApi *pApi,   /* API offered by current FTS version */
  Fts5Context *pFts,              /* First arg to pass to pApi functions */
................................................................................
  int nToken;                     /* 5th argument to snippet() */
  int nInst = 0;                  /* Number of instance matches this row */
  int i;                          /* Used to iterate through instances */
  int nPhrase;                    /* Number of phrases in query */
  unsigned char *aSeen;           /* Array of "seen instance" flags */
  int iBestCol;                   /* Column containing best snippet */
  int iBestStart = 0;             /* First token of best snippet */

  int nBestScore = 0;             /* Score of best snippet */
  int nColSize = 0;               /* Total size of iBestCol in tokens */
  Fts5SFinder sFinder;            /* Used to find the beginnings of sentences */
  int nCol;

  if( nVal!=5 ){
    const char *zErr = "wrong number of arguments to function snippet()";
    sqlite3_result_error(pCtx, zErr, -1);
    return;
  }

  nCol = pApi->xColumnCount(pFts);
  memset(&ctx, 0, sizeof(HighlightContext));
  iCol = sqlite3_value_int(apVal[0]);
  ctx.zOpen = (const char*)sqlite3_value_text(apVal[1]);
  ctx.zClose = (const char*)sqlite3_value_text(apVal[2]);
  zEllips = (const char*)sqlite3_value_text(apVal[3]);
  nToken = sqlite3_value_int(apVal[4]);


  iBestCol = (iCol>=0 ? iCol : 0);
  nPhrase = pApi->xPhraseCount(pFts);
  aSeen = sqlite3_malloc(nPhrase);
  if( aSeen==0 ){
    rc = SQLITE_NOMEM;
  }

  if( rc==SQLITE_OK ){
    rc = pApi->xInstCount(pFts, &nInst);
  }

  memset(&sFinder, 0, sizeof(Fts5SFinder));
  for(i=0; i<nCol; i++){
    if( iCol<0 || iCol==i ){
      int nDoc;
      int nDocsize;
      int ii;
      sFinder.iPos = 0;
      sFinder.nFirst = 0;
      rc = pApi->xColumnText(pFts, i, &sFinder.zDoc, &nDoc);
      if( rc!=SQLITE_OK ) break;
      rc = pApi->xTokenize(pFts, 
          sFinder.zDoc, nDoc, (void*)&sFinder,fts5SentenceFinderCb
      );
      if( rc!=SQLITE_OK ) break;
      rc = pApi->xColumnSize(pFts, i, &nDocsize);
      if( rc!=SQLITE_OK ) break;

      for(ii=0; rc==SQLITE_OK && ii<sFinder.nFirst; ii++){

        int nScore;
        memset(aSeen, 0, nPhrase);


        rc = fts5SnippetScore(pApi, pFts, nDocsize, aSeen, i, 
            sFinder.aFirst[ii], nToken, &nScore, 0
        );

        /* Bonus of 100 points for starting at the start of a sentence */
        nScore += 100;            




        if( rc==SQLITE_OK && nScore>nBestScore ){







          nBestScore = nScore;
          iBestCol = i;
          iBestStart = sFinder.aFirst[ii];
          nColSize = nDocsize;
        }
      }

      for(ii=0; rc==SQLITE_OK && ii<nInst; ii++){
        int ip, ic, io;
        int nScore;
        rc = pApi->xInst(pFts, ii, &ip, &ic, &io);
        if( ic!=i || rc!=SQLITE_OK ) continue;
        memset(aSeen, 0, nPhrase);
        rc = fts5SnippetScore(pApi, pFts, nDocsize, aSeen, i,
            io, nToken, &nScore, &io
        );
        if( rc==SQLITE_OK && nScore>nBestScore ){
          nBestScore = nScore;
          iBestCol = i;
          iBestStart = io;


          nColSize = nDocsize;
        }
      }
    }
  }




  if( rc==SQLITE_OK ){
    rc = pApi->xColumnText(pFts, iBestCol, &ctx.zIn, &ctx.nIn);
  }
  if( ctx.zIn ){
    if( rc==SQLITE_OK ){
      rc = fts5CInstIterInit(pApi, pFts, iBestCol, &ctx.iter);
    }









    ctx.iRangeStart = iBestStart;
    ctx.iRangeEnd = iBestStart + nToken - 1;

    if( iBestStart>0 ){
      fts5HighlightAppend(&rc, &ctx, zEllips, -1);
    }

................................................................................
      rc = pApi->xTokenize(pFts, ctx.zIn, ctx.nIn, (void*)&ctx,fts5HighlightCb);
    }
    if( ctx.iRangeEnd>=(nColSize-1) ){
      fts5HighlightAppend(&rc, &ctx, &ctx.zIn[ctx.iOff], ctx.nIn - ctx.iOff);
    }else{
      fts5HighlightAppend(&rc, &ctx, zEllips, -1);
    }
  }
  if( rc==SQLITE_OK ){
    sqlite3_result_text(pCtx, (const char*)ctx.zOut, -1, SQLITE_TRANSIENT);
  }else{
    sqlite3_result_error_code(pCtx, rc);
  }
  sqlite3_free(ctx.zOut);

  sqlite3_free(aSeen);
  sqlite3_free(sFinder.aFirst);
}

/************************************************************************/

/*
** The first time the bm25() function is called for a query, an instance
** of the following structure is allocated and populated.

Changes to ext/fts5/test/fts5af.test.

55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
...
107
108
109
110
111
112
113




114
115
116
117
118
119
120
  } [list $res]


}


foreach {tn doc res} {

  1.1 {X o o o o o o} {[X] o o o o o o}
  1.2 {o X o o o o o} {o [X] o o o o o}
  1.3 {o o X o o o o} {o o [X] o o o o}
  1.4 {o o o X o o o} {o o o [X] o o o}
  1.5 {o o o o X o o} {o o o o [X] o o}
  1.6 {o o o o o X o} {o o o o o [X] o}
  1.7 {o o o o o o X} {o o o o o o [X]}
................................................................................
  7.3 {o o X o o X o o o} {...o [X] o o [X] o o...}
  7.4 {o o o X o o X o o} {...o [X] o o [X] o o}
  7.5 {o o o o X o o X o} {...o o [X] o o [X] o}
  7.6 {o o o o o X o o X} {...o o o [X] o o [X]}

  8.1 {o o o o X o o o o o o o o o o o o o o o o o o o o o X X X o o o}
      {...o o [X] [X] [X] o o...}




} {
  do_snippet_test 1.$tn $doc X $res
}

if {[detail_is_full]} {
  foreach {tn doc res} {
    1.1 {X Y o o o o o} {[X Y] o o o o o}







<







 







>
>
>
>







55
56
57
58
59
60
61

62
63
64
65
66
67
68
...
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
  } [list $res]


}


foreach {tn doc res} {

  1.1 {X o o o o o o} {[X] o o o o o o}
  1.2 {o X o o o o o} {o [X] o o o o o}
  1.3 {o o X o o o o} {o o [X] o o o o}
  1.4 {o o o X o o o} {o o o [X] o o o}
  1.5 {o o o o X o o} {o o o o [X] o o}
  1.6 {o o o o o X o} {o o o o o [X] o}
  1.7 {o o o o o o X} {o o o o o o [X]}
................................................................................
  7.3 {o o X o o X o o o} {...o [X] o o [X] o o...}
  7.4 {o o o X o o X o o} {...o [X] o o [X] o o}
  7.5 {o o o o X o o X o} {...o o [X] o o [X] o}
  7.6 {o o o o o X o o X} {...o o o [X] o o [X]}

  8.1 {o o o o X o o o o o o o o o o o o o o o o o o o o o X X X o o o}
      {...o o [X] [X] [X] o o...}
  8.2 {o o o o. X o o o o o o o o o o o o o o o o o o o o o X X X o o o} 
      {...[X] o o o o o o...}


} {
  do_snippet_test 1.$tn $doc X $res
}

if {[detail_is_full]} {
  foreach {tn doc res} {
    1.1 {X Y o o o o o} {[X Y] o o o o o}

Changes to ext/fts5/test/fts5unicode2.test.

156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
     the maximum x value.
  }
  3 "ROW" {
     ...returns the value of y on the same [row] that contains 
     the maximum x value.
  }
  4 "rollback" {
     ...[ROLLBACK]. Instead, the pending statement
     will return SQLITE_ABORT upon next access after the [ROLLBACK].
  }
  5 "rOllback" {
     ...[ROLLBACK]. Instead, the pending statement
     will return SQLITE_ABORT upon next access after the [ROLLBACK].
  }
  6 "lang*" {
     Added support for the FTS4 [languageid] option.
  }
} {
  do_test 2.$tn {







|



|







156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
     the maximum x value.
  }
  3 "ROW" {
     ...returns the value of y on the same [row] that contains 
     the maximum x value.
  }
  4 "rollback" {
     ...Instead, the pending statement
     will return SQLITE_ABORT upon next access after the [ROLLBACK].
  }
  5 "rOllback" {
     ...Instead, the pending statement
     will return SQLITE_ABORT upon next access after the [ROLLBACK].
  }
  6 "lang*" {
     Added support for the FTS4 [languageid] option.
  }
} {
  do_test 2.$tn {