Files
opencloud/services/search/pkg/bleve/backend.go

258 lines
7.0 KiB
Go

package bleve
import (
"context"
"math"
"time"
"github.com/blevesearch/bleve/v2"
"github.com/blevesearch/bleve/v2/search/query"
storageProvider "github.com/cs3org/go-cs3apis/cs3/storage/provider/v1beta1"
"github.com/opencloud-eu/reva/v2/pkg/errtypes"
"github.com/opencloud-eu/reva/v2/pkg/storagespace"
"github.com/opencloud-eu/reva/v2/pkg/utils"
"google.golang.org/protobuf/types/known/timestamppb"
"github.com/opencloud-eu/opencloud/pkg/kql"
"github.com/opencloud-eu/opencloud/pkg/log"
"github.com/opencloud-eu/opencloud/services/search/pkg/search"
searchMessage "github.com/opencloud-eu/opencloud/protogen/gen/opencloud/messages/search/v0"
searchService "github.com/opencloud-eu/opencloud/protogen/gen/opencloud/services/search/v0"
searchQuery "github.com/opencloud-eu/opencloud/services/search/pkg/query"
)
const defaultBatchSize = 50
var _ search.Engine = (*Backend)(nil) // ensure Backend implements Engine
type Backend struct {
index bleve.Index
queryCreator searchQuery.Creator[query.Query]
log log.Logger
}
func NewBackend(index bleve.Index, queryCreator searchQuery.Creator[query.Query], log log.Logger) *Backend {
return &Backend{
index: index,
queryCreator: queryCreator,
log: log,
}
}
// Search executes a search request operation within the index.
// Returns a SearchIndexResponse object or an error.
func (b *Backend) Search(_ context.Context, sir *searchService.SearchIndexRequest) (*searchService.SearchIndexResponse, error) {
createdQuery, err := b.queryCreator.Create(sir.Query)
if err != nil {
if kql.IsValidationError(err) {
return nil, errtypes.BadRequest(err.Error())
}
return nil, err
}
q := bleve.NewConjunctionQuery(
// Skip documents that have been marked as deleted
&query.BoolFieldQuery{
Bool: false,
FieldVal: "Deleted",
},
createdQuery,
)
if sir.Ref != nil {
q.Conjuncts = append(
q.Conjuncts,
&query.TermQuery{
FieldVal: "RootID",
Term: storagespace.FormatResourceID(
&storageProvider.ResourceId{
StorageId: sir.Ref.GetResourceId().GetStorageId(),
SpaceId: sir.Ref.GetResourceId().GetSpaceId(),
OpaqueId: sir.Ref.GetResourceId().GetOpaqueId(),
},
),
},
)
// Scope below the space root: restrict at query level so totals and
// paging respect the path too. Path is a case-preserving keyword
// (paths act as references, /Foo and /foo are distinct), so the exact
// folder or the folder prefix matches all of, and only, the scope.
if requestedPath := utils.MakeRelativePath(sir.Ref.Path); requestedPath != "." {
q.Conjuncts = append(q.Conjuncts, query.NewDisjunctionQuery([]query.Query{
&query.TermQuery{FieldVal: "Path", Term: requestedPath},
&query.PrefixQuery{FieldVal: "Path", Prefix: requestedPath + "/"},
}))
}
}
bleveReq := bleve.NewSearchRequest(q)
bleveReq.Highlight = bleve.NewHighlight()
switch {
case sir.PageSize == -1:
bleveReq.Size = math.MaxInt
case sir.PageSize == 0:
bleveReq.Size = 200
default:
bleveReq.Size = int(sir.PageSize)
}
bleveReq.Fields = []string{"*"}
res, err := b.index.Search(bleveReq)
if err != nil {
return nil, err
}
matches := make([]*searchMessage.Match, 0, len(res.Hits))
totalMatches := res.Total
for _, hit := range res.Hits {
rootID, err := storagespace.ParseID(getFieldValue[string](hit.Fields, "RootID"))
if err != nil {
return nil, err
}
rID, err := storagespace.ParseID(getFieldValue[string](hit.Fields, "ID"))
if err != nil {
return nil, err
}
pID, _ := storagespace.ParseID(getFieldValue[string](hit.Fields, "ParentID"))
match := &searchMessage.Match{
Score: float32(hit.Score),
Entity: &searchMessage.Entity{
Ref: &searchMessage.Reference{
ResourceId: resourceIDtoSearchID(rootID),
Path: getFieldValue[string](hit.Fields, "Path"),
},
Id: resourceIDtoSearchID(rID),
Name: getFieldValue[string](hit.Fields, "Name"),
ParentId: resourceIDtoSearchID(pID),
Size: uint64(getFieldValue[float64](hit.Fields, "Size")),
Type: uint64(getFieldValue[float64](hit.Fields, "Type")),
MimeType: getFieldValue[string](hit.Fields, "MimeType"),
Deleted: getFieldValue[bool](hit.Fields, "Deleted"),
Tags: getFieldSliceValue[string](hit.Fields, "Tags"),
Favorites: getFieldSliceValue[string](hit.Fields, "Favorites"),
Highlights: getFragmentValue(hit.Fragments, "Content", 0),
Audio: hitToFacet[searchMessage.Audio](hit.Fields, "audio"),
Image: hitToFacet[searchMessage.Image](hit.Fields, "image"),
Location: hitToFacet[searchMessage.GeoCoordinates](hit.Fields, "location"),
Photo: hitToFacet[searchMessage.Photo](hit.Fields, "photo"),
Video: hitToFacet[searchMessage.Video](hit.Fields, "video"),
MotionPhoto: hitToFacet[searchMessage.MotionPhoto](hit.Fields, "motionPhoto"),
LivePhoto: hitToFacet[searchMessage.LivePhoto](hit.Fields, "livePhoto"),
},
}
if mtime, err := time.Parse(time.RFC3339, getFieldValue[string](hit.Fields, "Mtime")); err == nil {
match.Entity.LastModifiedTime = &timestamppb.Timestamp{Seconds: mtime.Unix(), Nanos: int32(mtime.Nanosecond())}
}
matches = append(matches, match)
}
return &searchService.SearchIndexResponse{
Matches: matches,
TotalMatches: int32(totalMatches),
}, nil
}
func (b *Backend) DocCount() (uint64, error) {
return b.index.DocCount()
}
func (b *Backend) Upsert(id string, r search.Resource) error {
batch, err := b.NewBatch(defaultBatchSize)
if err != nil {
return err
}
if err := batch.Upsert(id, r); err != nil {
return err
}
return batch.Push()
}
func (b *Backend) Move(id, parentID, targetPath string) error {
batch, err := b.NewBatch(defaultBatchSize)
if err != nil {
return err
}
if err := batch.Move(id, parentID, targetPath); err != nil {
return err
}
return batch.Push()
}
func (b *Backend) Delete(id string) error {
batch, err := b.NewBatch(defaultBatchSize)
if err != nil {
return err
}
if err := batch.Delete(id); err != nil {
return err
}
return batch.Push()
}
func (b *Backend) Restore(id string) error {
batch, err := b.NewBatch(defaultBatchSize)
if err != nil {
return err
}
if err := batch.Restore(id); err != nil {
return err
}
return batch.Push()
}
func (b *Backend) Purge(id string, onlyDeleted bool) error {
batch, err := b.NewBatch(defaultBatchSize)
if err != nil {
return err
}
if err := batch.Purge(id, onlyDeleted); err != nil {
return err
}
return batch.Push()
}
func (b *Backend) PurgeSpace(rootID string) error {
for {
req := bleve.NewSearchRequest(&query.TermQuery{FieldVal: "RootID", Term: rootID})
req.Size = defaultBatchSize
res, err := b.index.Search(req)
if err != nil {
return err
}
if res.Hits.Len() == 0 {
return nil
}
batch := b.index.NewBatch()
for _, hit := range res.Hits {
batch.Delete(hit.ID)
}
if err := b.index.Batch(batch); err != nil {
return err
}
}
}
func (b *Backend) NewBatch(size int) (search.BatchOperator, error) {
return NewBatch(b.index, size)
}