lunr.Index.prototype.query = function()

in miredot/lib/lunr/js/lunr.js [1756:1923]

• 77 lines of code
• 12 McCabe index (conditional complexity)

lunr.Index.prototype.query = function (fn) {
  // for each query clause
  // * process terms
  // * expand terms from token set
  // * find matching documents and metadata
  // * get document vectors
  // * score documents

  var query = new lunr.Query(this.fields),
      matchingFields = Object.create(null),
      queryVectors = Object.create(null),
      termFieldCache = Object.create(null)

  fn.call(query, query)

  for (var i = 0; i < query.clauses.length; i++) {
    /*
     * Unless the pipeline has been disabled for this term, which is
     * the case for terms with wildcards, we need to pass the clause
     * term through the search pipeline. A pipeline returns an array
     * of processed terms. Pipeline functions may expand the passed
     * term, which means we may end up performing multiple index lookups
     * for a single query term.
     */
    var clause = query.clauses[i],
        terms = null

    if (clause.usePipeline) {
      terms = this.pipeline.runString(clause.term)
    } else {
      terms = [clause.term]
    }

    for (var m = 0; m < terms.length; m++) {
      var term = terms[m]

      /*
       * Each term returned from the pipeline needs to use the same query
       * clause object, e.g. the same boost and or edit distance. The
       * simplest way to do this is to re-use the clause object but mutate
       * its term property.
       */
      clause.term = term

      /*
       * From the term in the clause we create a token set which will then
       * be used to intersect the indexes token set to get a list of terms
       * to lookup in the inverted index
       */
      var termTokenSet = lunr.TokenSet.fromClause(clause),
          expandedTerms = this.tokenSet.intersect(termTokenSet).toArray()

      for (var j = 0; j < expandedTerms.length; j++) {
        /*
         * For each term get the posting and termIndex, this is required for
         * building the query vector.
         */
        var expandedTerm = expandedTerms[j],
            posting = this.invertedIndex[expandedTerm],
            termIndex = posting._index

        for (var k = 0; k < clause.fields.length; k++) {
          /*
           * For each field that this query term is scoped by (by default
           * all fields are in scope) we need to get all the document refs
           * that have this term in that field.
           *
           * The posting is the entry in the invertedIndex for the matching
           * term from above.
           */
          var field = clause.fields[k],
              fieldPosting = posting[field],
              matchingDocumentRefs = Object.keys(fieldPosting),
              termField = expandedTerm + "/" + field

          /*
           * To support field level boosts a query vector is created per
           * field. This vector is populated using the termIndex found for
           * the term and a unit value with the appropriate boost applied.
           *
           * If the query vector for this field does not exist yet it needs
           * to be created.
           */
          if (queryVectors[field] === undefined) {
            queryVectors[field] = new lunr.Vector
          }

          /*
           * Using upsert because there could already be an entry in the vector
           * for the term we are working with. In that case we just add the scores
           * together.
           */
          queryVectors[field].upsert(termIndex, 1 * clause.boost, function (a, b) { return a + b })

          /**
           * If we've already seen this term, field combo then we've already collected
           * the matching documents and metadata, no need to go through all that again
           */
          if (termFieldCache[termField]) {
            continue
          }

          for (var l = 0; l < matchingDocumentRefs.length; l++) {
            /*
             * All metadata for this term/field/document triple
             * are then extracted and collected into an instance
             * of lunr.MatchData ready to be returned in the query
             * results
             */
            var matchingDocumentRef = matchingDocumentRefs[l],
                matchingFieldRef = new lunr.FieldRef (matchingDocumentRef, field),
                metadata = fieldPosting[matchingDocumentRef],
                fieldMatch

            if ((fieldMatch = matchingFields[matchingFieldRef]) === undefined) {
              matchingFields[matchingFieldRef] = new lunr.MatchData (expandedTerm, field, metadata)
            } else {
              fieldMatch.add(expandedTerm, field, metadata)
            }

          }

          termFieldCache[termField] = true
        }
      }
    }
  }

  var matchingFieldRefs = Object.keys(matchingFields),
      results = [],
      matches = Object.create(null)

  for (var i = 0; i < matchingFieldRefs.length; i++) {
    /*
     * Currently we have document fields that match the query, but we
     * need to return documents. The matchData and scores are combined
     * from multiple fields belonging to the same document.
     *
     * Scores are calculated by field, using the query vectors created
     * above, and combined into a final document score using addition.
     */
    var fieldRef = lunr.FieldRef.fromString(matchingFieldRefs[i]),
        docRef = fieldRef.docRef,
        fieldVector = this.fieldVectors[fieldRef],
        score = queryVectors[fieldRef.fieldName].similarity(fieldVector),
        docMatch

    if ((docMatch = matches[docRef]) !== undefined) {
      docMatch.score += score
      docMatch.matchData.combine(matchingFields[fieldRef])
    } else {
      var match = {
        ref: docRef,
        score: score,
        matchData: matchingFields[fieldRef]
      }
      matches[docRef] = match
      results.push(match)
    }
  }

  /*
   * Sort the results objects by score, highest first.
   */
  return results.sort(function (a, b) {
    return b.score - a.score
  })
}