2024-11-04 17:10:50 +08:00

223 lines
7.7 KiB
Go

// Copyright 2024 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package bleve
import (
"context"
"code.gitea.io/gitea/modules/indexer/conversations/internal"
indexer_internal "code.gitea.io/gitea/modules/indexer/internal"
inner_bleve "code.gitea.io/gitea/modules/indexer/internal/bleve"
"github.com/blevesearch/bleve/v2"
"github.com/blevesearch/bleve/v2/analysis/analyzer/custom"
"github.com/blevesearch/bleve/v2/analysis/token/camelcase"
"github.com/blevesearch/bleve/v2/analysis/token/lowercase"
"github.com/blevesearch/bleve/v2/analysis/token/unicodenorm"
"github.com/blevesearch/bleve/v2/analysis/tokenizer/unicode"
"github.com/blevesearch/bleve/v2/mapping"
"github.com/blevesearch/bleve/v2/search/query"
)
const (
conversationIndexerAnalyzer = "conversationIndexer"
conversationIndexerDocType = "conversationIndexerDocType"
conversationIndexerLatestVersion = 4
)
const unicodeNormalizeName = "unicodeNormalize"
func addUnicodeNormalizeTokenFilter(m *mapping.IndexMappingImpl) error {
return m.AddCustomTokenFilter(unicodeNormalizeName, map[string]any{
"type": unicodenorm.Name,
"form": unicodenorm.NFC,
})
}
const maxBatchSize = 16
// IndexerData an update to the conversation indexer
type IndexerData internal.IndexerData
// Type returns the document type, for bleve's mapping.Classifier interface.
func (i *IndexerData) Type() string {
return conversationIndexerDocType
}
// generateConversationIndexMapping generates the bleve index mapping for conversations
func generateConversationIndexMapping() (mapping.IndexMapping, error) {
mapping := bleve.NewIndexMapping()
docMapping := bleve.NewDocumentMapping()
numericFieldMapping := bleve.NewNumericFieldMapping()
numericFieldMapping.Store = false
numericFieldMapping.IncludeInAll = false
docMapping.AddFieldMappingsAt("repo_id", numericFieldMapping)
textFieldMapping := bleve.NewTextFieldMapping()
textFieldMapping.Store = false
textFieldMapping.IncludeInAll = false
boolFieldMapping := bleve.NewBooleanFieldMapping()
boolFieldMapping.Store = false
boolFieldMapping.IncludeInAll = false
numberFieldMapping := bleve.NewNumericFieldMapping()
numberFieldMapping.Store = false
numberFieldMapping.IncludeInAll = false
docMapping.AddFieldMappingsAt("is_public", boolFieldMapping)
docMapping.AddFieldMappingsAt("title", textFieldMapping)
docMapping.AddFieldMappingsAt("content", textFieldMapping)
docMapping.AddFieldMappingsAt("comments", textFieldMapping)
docMapping.AddFieldMappingsAt("is_pull", boolFieldMapping)
docMapping.AddFieldMappingsAt("is_closed", boolFieldMapping)
docMapping.AddFieldMappingsAt("label_ids", numberFieldMapping)
docMapping.AddFieldMappingsAt("no_label", boolFieldMapping)
docMapping.AddFieldMappingsAt("milestone_id", numberFieldMapping)
docMapping.AddFieldMappingsAt("project_id", numberFieldMapping)
docMapping.AddFieldMappingsAt("project_board_id", numberFieldMapping)
docMapping.AddFieldMappingsAt("poster_id", numberFieldMapping)
docMapping.AddFieldMappingsAt("assignee_id", numberFieldMapping)
docMapping.AddFieldMappingsAt("mention_ids", numberFieldMapping)
docMapping.AddFieldMappingsAt("reviewed_ids", numberFieldMapping)
docMapping.AddFieldMappingsAt("review_requested_ids", numberFieldMapping)
docMapping.AddFieldMappingsAt("subscriber_ids", numberFieldMapping)
docMapping.AddFieldMappingsAt("updated_unix", numberFieldMapping)
docMapping.AddFieldMappingsAt("created_unix", numberFieldMapping)
docMapping.AddFieldMappingsAt("deadline_unix", numberFieldMapping)
docMapping.AddFieldMappingsAt("comment_count", numberFieldMapping)
if err := addUnicodeNormalizeTokenFilter(mapping); err != nil {
return nil, err
} else if err = mapping.AddCustomAnalyzer(conversationIndexerAnalyzer, map[string]any{
"type": custom.Name,
"char_filters": []string{},
"tokenizer": unicode.Name,
"token_filters": []string{unicodeNormalizeName, camelcase.Name, lowercase.Name},
}); err != nil {
return nil, err
}
mapping.DefaultAnalyzer = conversationIndexerAnalyzer
mapping.AddDocumentMapping(conversationIndexerDocType, docMapping)
mapping.AddDocumentMapping("_all", bleve.NewDocumentDisabledMapping())
mapping.DefaultMapping = bleve.NewDocumentDisabledMapping() // disable default mapping, avoid indexing unexpected structs
return mapping, nil
}
var _ internal.Indexer = &Indexer{}
// Indexer implements Indexer interface
type Indexer struct {
inner *inner_bleve.Indexer
indexer_internal.Indexer // do not composite inner_bleve.Indexer directly to avoid exposing too much
}
// NewIndexer creates a new bleve local indexer
func NewIndexer(indexDir string) *Indexer {
inner := inner_bleve.NewIndexer(indexDir, conversationIndexerLatestVersion, generateConversationIndexMapping)
return &Indexer{
Indexer: inner,
inner: inner,
}
}
// Index will save the index data
func (b *Indexer) Index(_ context.Context, conversations ...*internal.IndexerData) error {
batch := inner_bleve.NewFlushingBatch(b.inner.Indexer, maxBatchSize)
for _, conversation := range conversations {
if err := batch.Index(indexer_internal.Base36(conversation.ID), (*IndexerData)(conversation)); err != nil {
return err
}
}
return batch.Flush()
}
// Delete deletes indexes by ids
func (b *Indexer) Delete(_ context.Context, ids ...int64) error {
batch := inner_bleve.NewFlushingBatch(b.inner.Indexer, maxBatchSize)
for _, id := range ids {
if err := batch.Delete(indexer_internal.Base36(id)); err != nil {
return err
}
}
return batch.Flush()
}
// Search searches for conversations by given conditions.
// Returns the matching conversation IDs
func (b *Indexer) Search(ctx context.Context, options *internal.SearchOptions) (*internal.SearchResult, error) {
var queries []query.Query
if options.Keyword != "" {
fuzziness := 0
if options.IsFuzzyKeyword {
fuzziness = inner_bleve.GuessFuzzinessByKeyword(options.Keyword)
}
queries = append(queries, bleve.NewDisjunctionQuery([]query.Query{
inner_bleve.MatchPhraseQuery(options.Keyword, "title", conversationIndexerAnalyzer, fuzziness),
inner_bleve.MatchPhraseQuery(options.Keyword, "content", conversationIndexerAnalyzer, fuzziness),
inner_bleve.MatchPhraseQuery(options.Keyword, "comments", conversationIndexerAnalyzer, fuzziness),
}...))
}
if len(options.RepoIDs) > 0 || options.AllPublic {
var repoQueries []query.Query
for _, repoID := range options.RepoIDs {
repoQueries = append(repoQueries, inner_bleve.NumericEqualityQuery(repoID, "repo_id"))
}
if options.AllPublic {
repoQueries = append(repoQueries, inner_bleve.BoolFieldQuery(true, "is_public"))
}
queries = append(queries, bleve.NewDisjunctionQuery(repoQueries...))
}
if options.UpdatedAfterUnix.Has() || options.UpdatedBeforeUnix.Has() {
queries = append(queries, inner_bleve.NumericRangeInclusiveQuery(
options.UpdatedAfterUnix,
options.UpdatedBeforeUnix,
"updated_unix"))
}
var indexerQuery query.Query = bleve.NewConjunctionQuery(queries...)
if len(queries) == 0 {
indexerQuery = bleve.NewMatchAllQuery()
}
skip, limit := indexer_internal.ParsePaginator(options.Paginator)
search := bleve.NewSearchRequestOptions(indexerQuery, limit, skip, false)
if options.SortBy == "" {
options.SortBy = internal.SortByCreatedAsc
}
search.SortBy([]string{string(options.SortBy), "-_id"})
result, err := b.inner.Indexer.SearchInContext(ctx, search)
if err != nil {
return nil, err
}
ret := &internal.SearchResult{
Total: int64(result.Total),
Hits: make([]internal.Match, 0, len(result.Hits)),
}
for _, hit := range result.Hits {
id, err := indexer_internal.ParseBase36(hit.ID)
if err != nil {
return nil, err
}
ret.Hits = append(ret.Hits, internal.Match{
ID: id,
})
}
return ret, nil
}