SQLite

abuse_err:
  Tcl_AppendResult(interp, "sqlite3_create_function abused test failed", 
                   (char*)0);
  return TCL_ERROR;
}


/*
** SQLite user defined function to use with matchinfo() to calculate the
** relevancy of an FTS match. The value returned is the relevancy score
** (a real value greater than or equal to zero). A larger value indicates 
** a more relevant document.
**
** The overall relevancy returned is the sum of the relevancies of each 
** column value in the FTS table. The relevancy of a column value is the
** sum of the following for each reportable phrase in the FTS query:
**
**   (<hit count> / <global hit count>) * <column weight>
**
** where <hit count> is the number of instances of the phrase in the
** column value of the current row and <global hit count> is the number
** of instances of the phrase in the same column of all rows in the FTS
** table. The <column weight> is a weighting factor assigned to each
** column by the caller (see below).
**
** The first argument to this function must be the return value of the FTS 
** matchinfo() function. Following this must be one argument for each column 
** of the FTS table containing a numeric weight factor for the corresponding 
** column. Example:
**
**     CREATE VIRTUAL TABLE documents USING fts3(title, content)
**
** The following query returns the docids of documents that match the full-text
** query <query> sorted from most to least relevant. When calculating
** relevance, query term instances in the 'title' column are given twice the
** weighting of those in the 'content' column.
**
**     SELECT docid FROM documents 
**     WHERE documents MATCH <query> 
**     ORDER BY rank(matchinfo(documents), 1.0, 0.5) DESC
*/
static void rankfunc(sqlite3_context *pCtx, int nVal, sqlite3_value **apVal){
  int *aMatchinfo;                /* Return value of matchinfo() */
  int nMatchinfo;                 /* Number of elements in aMatchinfo[] */
  int nCol = 0;                   /* Number of columns in the table */
  int nPhrase = 0;                /* Number of phrases in the query */
  int iPhrase;                    /* Current phrase */
  double score = 0.0;             /* Value to return */

  assert( sizeof(int)==4 );

  /* Check that the number of arguments passed to this function is correct.
  ** If not, jump to wrong_number_args. Set aMatchinfo to point to the array
  ** of unsigned integer values returned by FTS function matchinfo. Set
  ** nPhrase to contain the number of reportable phrases in the users full-text
  ** query, and nCol to the number of columns in the table. Then check that the
  ** size of the matchinfo blob is as expected. Return an error if it is not.
  */
  if( nVal<1 ) goto wrong_number_args;
  aMatchinfo = (unsigned int *)sqlite3_value_blob(apVal[0]);
  nMatchinfo = sqlite3_value_bytes(apVal[0]) / sizeof(int);
  if( nMatchinfo>=2 ){
    nPhrase = aMatchinfo[0];
    nCol = aMatchinfo[1];
  }
  if( nMatchinfo!=(2+3*nCol*nPhrase) ){
    sqlite3_result_error(pCtx,
        "invalid matchinfo blob passed to function rank()", -1);
    return;
  }
  if( nVal!=(1+nCol) ) goto wrong_number_args;

  /* Iterate through each phrase in the users query. */
  for(iPhrase=0; iPhrase<nPhrase; iPhrase++){
    int iCol;                     /* Current column */

    /* Now iterate through each column in the users query. For each column,
    ** increment the relevancy score by:
    **
    **   (<hit count> / <global hit count>) * <column weight>
    **
    ** aPhraseinfo[] points to the start of the data for phrase iPhrase. So
    ** the hit count and global hit counts for each column are found in 
    ** aPhraseinfo[iCol*3] and aPhraseinfo[iCol*3+1], respectively.
    */
    int *aPhraseinfo = &aMatchinfo[2 + iPhrase*nCol*3];
    for(iCol=0; iCol<nCol; iCol++){
      int nHitCount = aPhraseinfo[3*iCol];
      int nGlobalHitCount = aPhraseinfo[3*iCol+1];
      double weight = sqlite3_value_double(apVal[iCol+1]);
      if( nHitCount>0 ){
        score += ((double)nHitCount / (double)nGlobalHitCount) * weight;
      }
    }
  }

  sqlite3_result_double(pCtx, score);
  return;

  /* Jump here if the wrong number of arguments are passed to this function */
wrong_number_args:
  sqlite3_result_error(pCtx, "wrong number of arguments to function rank()", -1);
}

static int SQLITE_TCLAPI install_fts3_rank_function(
  void * clientData,
  Tcl_Interp *interp,
  int objc,
  Tcl_Obj *CONST objv[]
){
  extern int getDbPointer(Tcl_Interp*, const char*, sqlite3**);
  sqlite3 *db;

  if( objc!=2 ){
    Tcl_WrongNumArgs(interp, 1, objv, "DB");
    return TCL_ERROR;
  }

  if( getDbPointer(interp, Tcl_GetString(objv[1]), &db) ) return TCL_ERROR;
  sqlite3_create_function(db, "rank", -1, SQLITE_UTF8, 0, rankfunc, 0, 0);
  return TCL_OK;
}


/*
** Register commands with the TCL interpreter.
*/
int Sqlitetest_func_Init(Tcl_Interp *interp){
  static struct {
     char *zName;
     Tcl_ObjCmdProc *xProc;
  } aObjCmd[] = {
     { "autoinstall_test_functions",    autoinstall_test_funcs },
     { "abuse_create_function",         abuse_create_function  },
     { "install_fts3_rank_function",    install_fts3_rank_function  },
  };
  int i;
  extern int Md5_Register(sqlite3 *, char **, const sqlite3_api_routines *);

  for(i=0; i<sizeof(aObjCmd)/sizeof(aObjCmd[0]); i++){
    Tcl_CreateObjCommand(interp, aObjCmd[i].zName, aObjCmd[i].xProc, 0, 0);
  }

# 2017 October 7
#
# The author disclaims copyright to this source code.  In place of
# a legal notice, here is a blessing:
#
#    May you do good and not evil.
#    May you find forgiveness for yourself and forgive others.
#    May you share freely, never taking more than you give.
#
#*************************************************************************
# This file implements regression tests for SQLite library.  The
# focus of this script is testing the FTS3 module.
#

set testdir [file dirname $argv0]
source $testdir/tester.tcl
set testprefix fts3expr5

# If SQLITE_ENABLE_FTS3 is defined, omit this file.
ifcapable !fts3 {
  finish_test
  return
}

install_fts3_rank_function db
do_execsql_test 1.0 {
  CREATE VIRTUAL TABLE t1 USING fts3(a, b);
  INSERT INTO t1 VALUES('one two', 'one');
  INSERT INTO t1 VALUES('one two', 'three');
  INSERT INTO t1 VALUES('one two', 'two');
}

do_execsql_test 1.1 {
  SELECT * FROM t1 WHERE t1 MATCH 'one' 
  ORDER BY rank(matchinfo(t1), 1.0, 1.0) DESC, rowid
} {
  {one two} one
  {one two} three
  {one two} two
}

do_execsql_test 1.2 {
  SELECT * FROM t1 WHERE t1 MATCH 'two' 
  ORDER BY rank(matchinfo(t1), 1.0, 1.0) DESC, rowid
} {
  {one two} two
  {one two} one
  {one two} three
}

do_catchsql_test 1.3 {
  SELECT * FROM t1 ORDER BY rank(matchinfo(t1), 1.0, 1.0) DESC, rowid
} {1 {invalid matchinfo blob passed to function rank()}}

do_catchsql_test 1.4 {
  SELECT * FROM t1 ORDER BY rank(x'0000000000000000') DESC, rowid
} {0 {{one two} one {one two} three {one two} two}}

do_catchsql_test 1.5 {
  SELECT * FROM t1 ORDER BY rank(x'0100000001000000') DESC, rowid
} {1 {invalid matchinfo blob passed to function rank()}}

finish_test