mirror of
https://codeberg.org/forgejo/forgejo.git
synced 2024-11-11 12:21:16 +01:00
375fd15fbf
Refactor `modules/indexer` to make it more maintainable. And it can be easier to support more features. I'm trying to solve some of issue searching, this is a precursor to making functional changes. Current supported engines and the index versions: | engines | issues | code | | - | - | - | | db | Just a wrapper for database queries, doesn't need version | - | | bleve | The version of index is **2** | The version of index is **6** | | elasticsearch | The old index has no version, will be treated as version **0** in this PR | The version of index is **1** | | meilisearch | The old index has no version, will be treated as version **0** in this PR | - | ## Changes ### Split Splited it into mutiple packages ```text indexer ├── internal │ ├── bleve │ ├── db │ ├── elasticsearch │ └── meilisearch ├── code │ ├── bleve │ ├── elasticsearch │ └── internal └── issues ├── bleve ├── db ├── elasticsearch ├── internal └── meilisearch ``` - `indexer/interanal`: Internal shared package for indexer. - `indexer/interanal/[engine]`: Internal shared package for each engine (bleve/db/elasticsearch/meilisearch). - `indexer/code`: Implementations for code indexer. - `indexer/code/internal`: Internal shared package for code indexer. - `indexer/code/[engine]`: Implementation via each engine for code indexer. - `indexer/issues`: Implementations for issues indexer. ### Deduplication - Combine `Init/Ping/Close` for code indexer and issues indexer. - ~Combine `issues.indexerHolder` and `code.wrappedIndexer` to `internal.IndexHolder`.~ Remove it, use dummy indexer instead when the indexer is not ready. - Duplicate two copies of creating ES clients. - Duplicate two copies of `indexerID()`. ### Enhancement - [x] Support index version for elasticsearch issues indexer, the old index without version will be treated as version 0. - [x] Fix spell of `elastic_search/ElasticSearch`, it should be `Elasticsearch`. - [x] Improve versioning of ES index. We don't need `Aliases`: - Gitea does't need aliases for "Zero Downtime" because it never delete old indexes. - The old code of issues indexer uses the orignal name to create issue index, so it's tricky to convert it to an alias. - [x] Support index version for meilisearch issues indexer, the old index without version will be treated as version 0. - [x] Do "ping" only when `Ping` has been called, don't ping periodically and cache the status. - [x] Support the context parameter whenever possible. - [x] Fix outdated example config. - [x] Give up the requeue logic of issues indexer: When indexing fails, call Ping to check if it was caused by the engine being unavailable, and only requeue the task if the engine is unavailable. - It is fragile and tricky, could cause data losing (It did happen when I was doing some tests for this PR). And it works for ES only. - Just always requeue the failed task, if it caused by bad data, it's a bug of Gitea which should be fixed. --------- Co-authored-by: Giteabot <teabot@gitea.io>
187 lines
5.7 KiB
Go
187 lines
5.7 KiB
Go
// Copyright 2018 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package bleve
|
|
|
|
import (
|
|
"context"
|
|
|
|
indexer_internal "code.gitea.io/gitea/modules/indexer/internal"
|
|
inner_bleve "code.gitea.io/gitea/modules/indexer/internal/bleve"
|
|
"code.gitea.io/gitea/modules/indexer/issues/internal"
|
|
|
|
"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 (
|
|
issueIndexerAnalyzer = "issueIndexer"
|
|
issueIndexerDocType = "issueIndexerDocType"
|
|
issueIndexerLatestVersion = 2
|
|
)
|
|
|
|
// numericEqualityQuery a numeric equality query for the given value and field
|
|
func numericEqualityQuery(value int64, field string) *query.NumericRangeQuery {
|
|
f := float64(value)
|
|
tru := true
|
|
q := bleve.NewNumericRangeInclusiveQuery(&f, &f, &tru, &tru)
|
|
q.SetField(field)
|
|
return q
|
|
}
|
|
|
|
func newMatchPhraseQuery(matchPhrase, field, analyzer string) *query.MatchPhraseQuery {
|
|
q := bleve.NewMatchPhraseQuery(matchPhrase)
|
|
q.FieldVal = field
|
|
q.Analyzer = analyzer
|
|
return q
|
|
}
|
|
|
|
const unicodeNormalizeName = "unicodeNormalize"
|
|
|
|
func addUnicodeNormalizeTokenFilter(m *mapping.IndexMappingImpl) error {
|
|
return m.AddCustomTokenFilter(unicodeNormalizeName, map[string]interface{}{
|
|
"type": unicodenorm.Name,
|
|
"form": unicodenorm.NFC,
|
|
})
|
|
}
|
|
|
|
const maxBatchSize = 16
|
|
|
|
// IndexerData an update to the issue indexer
|
|
type IndexerData internal.IndexerData
|
|
|
|
// Type returns the document type, for bleve's mapping.Classifier interface.
|
|
func (i *IndexerData) Type() string {
|
|
return issueIndexerDocType
|
|
}
|
|
|
|
// generateIssueIndexMapping generates the bleve index mapping for issues
|
|
func generateIssueIndexMapping() (mapping.IndexMapping, error) {
|
|
mapping := bleve.NewIndexMapping()
|
|
docMapping := bleve.NewDocumentMapping()
|
|
|
|
numericFieldMapping := bleve.NewNumericFieldMapping()
|
|
numericFieldMapping.IncludeInAll = false
|
|
docMapping.AddFieldMappingsAt("RepoID", numericFieldMapping)
|
|
|
|
textFieldMapping := bleve.NewTextFieldMapping()
|
|
textFieldMapping.Store = false
|
|
textFieldMapping.IncludeInAll = false
|
|
docMapping.AddFieldMappingsAt("Title", textFieldMapping)
|
|
docMapping.AddFieldMappingsAt("Content", textFieldMapping)
|
|
docMapping.AddFieldMappingsAt("Comments", textFieldMapping)
|
|
|
|
if err := addUnicodeNormalizeTokenFilter(mapping); err != nil {
|
|
return nil, err
|
|
} else if err = mapping.AddCustomAnalyzer(issueIndexerAnalyzer, map[string]interface{}{
|
|
"type": custom.Name,
|
|
"char_filters": []string{},
|
|
"tokenizer": unicode.Name,
|
|
"token_filters": []string{unicodeNormalizeName, camelcase.Name, lowercase.Name},
|
|
}); err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
mapping.DefaultAnalyzer = issueIndexerAnalyzer
|
|
mapping.AddDocumentMapping(issueIndexerDocType, docMapping)
|
|
mapping.AddDocumentMapping("_all", bleve.NewDocumentDisabledMapping())
|
|
|
|
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, issueIndexerLatestVersion, generateIssueIndexMapping)
|
|
return &Indexer{
|
|
Indexer: inner,
|
|
inner: inner,
|
|
}
|
|
}
|
|
|
|
// Index will save the index data
|
|
func (b *Indexer) Index(_ context.Context, issues []*internal.IndexerData) error {
|
|
batch := inner_bleve.NewFlushingBatch(b.inner.Indexer, maxBatchSize)
|
|
for _, issue := range issues {
|
|
if err := batch.Index(indexer_internal.Base36(issue.ID), struct {
|
|
RepoID int64
|
|
Title string
|
|
Content string
|
|
Comments []string
|
|
}{
|
|
RepoID: issue.RepoID,
|
|
Title: issue.Title,
|
|
Content: issue.Content,
|
|
Comments: issue.Comments,
|
|
}); 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 issues by given conditions.
|
|
// Returns the matching issue IDs
|
|
func (b *Indexer) Search(ctx context.Context, keyword string, repoIDs []int64, limit, start int) (*internal.SearchResult, error) {
|
|
var repoQueriesP []*query.NumericRangeQuery
|
|
for _, repoID := range repoIDs {
|
|
repoQueriesP = append(repoQueriesP, numericEqualityQuery(repoID, "RepoID"))
|
|
}
|
|
repoQueries := make([]query.Query, len(repoQueriesP))
|
|
for i, v := range repoQueriesP {
|
|
repoQueries[i] = query.Query(v)
|
|
}
|
|
|
|
indexerQuery := bleve.NewConjunctionQuery(
|
|
bleve.NewDisjunctionQuery(repoQueries...),
|
|
bleve.NewDisjunctionQuery(
|
|
newMatchPhraseQuery(keyword, "Title", issueIndexerAnalyzer),
|
|
newMatchPhraseQuery(keyword, "Content", issueIndexerAnalyzer),
|
|
newMatchPhraseQuery(keyword, "Comments", issueIndexerAnalyzer),
|
|
))
|
|
search := bleve.NewSearchRequestOptions(indexerQuery, limit, start, false)
|
|
search.SortBy([]string{"-_score"})
|
|
|
|
result, err := b.inner.Indexer.SearchInContext(ctx, search)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
ret := internal.SearchResult{
|
|
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
|
|
}
|