5aa9e95468
index id's are now opaque (until finally returned to top-level user)
- the TermFieldDoc's returned by TermFieldReader no longer contain doc id
- instead they return an opaque IndexInternalID
- items returned are still in the "natural index order"
- but that is no longer guaranteed to be "doc id order"
- correct behavior requires that they all follow the same order
- but not any particular order
- new API FinalizeDocID which converts index internal ID's to public string ID
- APIs used internally which previously took doc id now take IndexInternalID
- that is DocumentFieldTerms() and DocumentFieldTermsForFields()
- however, APIs that are used externally do not reflect this change
- that is Document()
- DocumentIDReader follows the same changes, but this is less obvious
- behavior clarified, used to iterate doc ids, BUT NOT in doc id order
- method STILL available to iterate doc ids in range
- but again, you won't get them in any meaningful order
- new method to iterate actual doc ids from list of possible ids
- this was introduced to make the DocIDSearcher continue working
searchers now work with the new opaque index internal doc ids
- they return new DocumentMatchInternal (which does not have string ID)
scorerers also work with these opaque index internal doc ids
- they return DocumentMatchInternal (which does not have string ID)
collectors now also perform a final step of converting the final result
- they STILL return traditional DocumentMatch (with string ID)
- but they now also require an IndexReader (so that they can do the conversion)
126 lines
3.4 KiB
Go
126 lines
3.4 KiB
Go
// Copyright (c) 2014 Couchbase, Inc.
|
|
// Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file
|
|
// except in compliance with the License. You may obtain a copy of the License at
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
// Unless required by applicable law or agreed to in writing, software distributed under the
|
|
// License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
|
|
// either express or implied. See the License for the specific language governing permissions
|
|
// and limitations under the License.
|
|
|
|
package searchers
|
|
|
|
import (
|
|
"github.com/blevesearch/bleve/index"
|
|
"github.com/blevesearch/bleve/search"
|
|
)
|
|
|
|
type FuzzySearcher struct {
|
|
indexReader index.IndexReader
|
|
term string
|
|
prefix int
|
|
fuzziness int
|
|
field string
|
|
explain bool
|
|
searcher *DisjunctionSearcher
|
|
}
|
|
|
|
func NewFuzzySearcher(indexReader index.IndexReader, term string, prefix, fuzziness int, field string, boost float64, explain bool) (*FuzzySearcher, error) {
|
|
prefixTerm := ""
|
|
for i, r := range term {
|
|
if i < prefix {
|
|
prefixTerm += string(r)
|
|
}
|
|
}
|
|
|
|
candidateTerms, err := findFuzzyCandidateTerms(indexReader, &term, fuzziness, field, prefixTerm)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
// enumerate all the terms in the range
|
|
qsearchers := make([]search.Searcher, 0, len(candidateTerms))
|
|
|
|
for _, cterm := range candidateTerms {
|
|
qsearcher, err := NewTermSearcher(indexReader, cterm, field, boost, explain)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
qsearchers = append(qsearchers, qsearcher)
|
|
}
|
|
|
|
// build disjunction searcher of these ranges
|
|
searcher, err := NewDisjunctionSearcher(indexReader, qsearchers, 0, explain)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
return &FuzzySearcher{
|
|
indexReader: indexReader,
|
|
term: term,
|
|
prefix: prefix,
|
|
fuzziness: fuzziness,
|
|
field: field,
|
|
explain: explain,
|
|
searcher: searcher,
|
|
}, nil
|
|
}
|
|
|
|
func findFuzzyCandidateTerms(indexReader index.IndexReader, term *string, fuzziness int, field, prefixTerm string) (rv []string, err error) {
|
|
rv = make([]string, 0)
|
|
var fieldDict index.FieldDict
|
|
if len(prefixTerm) > 0 {
|
|
fieldDict, err = indexReader.FieldDictPrefix(field, []byte(prefixTerm))
|
|
} else {
|
|
fieldDict, err = indexReader.FieldDict(field)
|
|
}
|
|
defer func() {
|
|
if cerr := fieldDict.Close(); cerr != nil && err == nil {
|
|
err = cerr
|
|
}
|
|
}()
|
|
|
|
// enumerate terms and check levenshtein distance
|
|
tfd, err := fieldDict.Next()
|
|
for err == nil && tfd != nil {
|
|
ld, exceeded := search.LevenshteinDistanceMax(term, &tfd.Term, fuzziness)
|
|
if !exceeded && ld <= fuzziness {
|
|
rv = append(rv, tfd.Term)
|
|
if tooManyClauses(len(rv)) {
|
|
return rv, tooManyClausesErr()
|
|
}
|
|
}
|
|
tfd, err = fieldDict.Next()
|
|
}
|
|
|
|
return rv, err
|
|
}
|
|
|
|
func (s *FuzzySearcher) Count() uint64 {
|
|
return s.searcher.Count()
|
|
}
|
|
|
|
func (s *FuzzySearcher) Weight() float64 {
|
|
return s.searcher.Weight()
|
|
}
|
|
|
|
func (s *FuzzySearcher) SetQueryNorm(qnorm float64) {
|
|
s.searcher.SetQueryNorm(qnorm)
|
|
}
|
|
|
|
func (s *FuzzySearcher) Next(preAllocated *search.DocumentMatchInternal) (*search.DocumentMatchInternal, error) {
|
|
return s.searcher.Next(preAllocated)
|
|
|
|
}
|
|
|
|
func (s *FuzzySearcher) Advance(ID index.IndexInternalID, preAllocated *search.DocumentMatchInternal) (*search.DocumentMatchInternal, error) {
|
|
return s.searcher.Advance(ID, preAllocated)
|
|
}
|
|
|
|
func (s *FuzzySearcher) Close() error {
|
|
return s.searcher.Close()
|
|
}
|
|
|
|
func (s *FuzzySearcher) Min() int {
|
|
return 0
|
|
}
|