Improve issue search (#2387)

* Improve issue indexer

* Fix new issue sqlite bug

* Different test indexer paths for each db

* Add integration indexer paths to make clean

2 files changed, 176 insertions, 4 deletions

diff --git a/modules/indexer/indexer.go b/modules/indexer/indexer.go
index 2b7b76f7f2..5ee813412d 100644
--- a/modules/indexer/indexer.go
+++ b/modules/indexer/indexer.go
@@ -5,10 +5,39 @@
 package indexer
 
 import (
-	"code.gitea.io/gitea/models"
+	"fmt"
+	"strconv"
+
+	"github.com/blevesearch/bleve"
+	"github.com/blevesearch/bleve/search/query"
 )
 
-// NewContext start indexer service
-func NewContext() {
-	models.InitIssueIndexer()
+// indexerID a bleve-compatible unique identifier for an integer id
+func indexerID(id int64) string {
+	return strconv.FormatInt(id, 36)
+}
+
+// idOfIndexerID the integer id associated with an indexer id
+func idOfIndexerID(indexerID string) (int64, error) {
+	id, err := strconv.ParseInt(indexerID, 36, 64)
+	if err != nil {
+		return 0, fmt.Errorf("Unexpected indexer ID %s: %v", indexerID, err)
+	}
+	return id, nil
+}
+
+// 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
 }
diff --git a/modules/indexer/issue.go b/modules/indexer/issue.go
new file mode 100644
index 0000000000..2503a78825
--- /dev/null
+++ b/modules/indexer/issue.go
@@ -0,0 +1,143 @@
+// Copyright 2017 The Gitea Authors. All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package indexer
+
+import (
+	"os"
+
+	"code.gitea.io/gitea/modules/log"
+	"code.gitea.io/gitea/modules/setting"
+
+	"github.com/blevesearch/bleve"
+	"github.com/blevesearch/bleve/analysis/analyzer/custom"
+	"github.com/blevesearch/bleve/analysis/token/lowercase"
+	"github.com/blevesearch/bleve/analysis/token/unicodenorm"
+	"github.com/blevesearch/bleve/analysis/tokenizer/unicode"
+)
+
+// issueIndexer (thread-safe) index for searching issues
+var issueIndexer bleve.Index
+
+// IssueIndexerData data stored in the issue indexer
+type IssueIndexerData struct {
+	RepoID   int64
+	Title    string
+	Content  string
+	Comments []string
+}
+
+// IssueIndexerUpdate an update to the issue indexer
+type IssueIndexerUpdate struct {
+	IssueID int64
+	Data    *IssueIndexerData
+}
+
+const issueIndexerAnalyzer = "issueIndexer"
+
+// InitIssueIndexer initialize issue indexer
+func InitIssueIndexer(populateIndexer func() error) {
+	_, err := os.Stat(setting.Indexer.IssuePath)
+	if err != nil {
+		if os.IsNotExist(err) {
+			if err = createIssueIndexer(); err != nil {
+				log.Fatal(4, "CreateIssuesIndexer: %v", err)
+			}
+			if err = populateIndexer(); err != nil {
+				log.Fatal(4, "PopulateIssuesIndex: %v", err)
+			}
+		} else {
+			log.Fatal(4, "InitIssuesIndexer: %v", err)
+		}
+	} else {
+		issueIndexer, err = bleve.Open(setting.Indexer.IssuePath)
+		if err != nil {
+			log.Error(4, "Unable to open issues indexer (%s)."+
+				" If the error is due to incompatible versions, try deleting the indexer files;"+
+				" gitea will recreate them with the appropriate version the next time it runs."+
+				" Deleting the indexer files will not result in loss of data.",
+				setting.Indexer.IssuePath)
+			log.Fatal(4, "InitIssuesIndexer, open index: %v", err)
+		}
+	}
+}
+
+// createIssueIndexer create an issue indexer if one does not already exist
+func createIssueIndexer() error {
+	mapping := bleve.NewIndexMapping()
+	docMapping := bleve.NewDocumentMapping()
+
+	docMapping.AddFieldMappingsAt("RepoID", bleve.NewNumericFieldMapping())
+
+	textFieldMapping := bleve.NewTextFieldMapping()
+	docMapping.AddFieldMappingsAt("Title", textFieldMapping)
+	docMapping.AddFieldMappingsAt("Content", textFieldMapping)
+	docMapping.AddFieldMappingsAt("Comments", textFieldMapping)
+
+	const unicodeNormNFC = "unicodeNormNFC"
+	if err := mapping.AddCustomTokenFilter(unicodeNormNFC, map[string]interface{}{
+		"type": unicodenorm.Name,
+		"form": unicodenorm.NFC,
+	}); err != nil {
+		return err
+	} else if err = mapping.AddCustomAnalyzer(issueIndexerAnalyzer, map[string]interface{}{
+		"type":          custom.Name,
+		"char_filters":  []string{},
+		"tokenizer":     unicode.Name,
+		"token_filters": []string{unicodeNormNFC, lowercase.Name},
+	}); err != nil {
+		return err
+	}
+
+	mapping.DefaultAnalyzer = issueIndexerAnalyzer
+	mapping.AddDocumentMapping("issues", docMapping)
+
+	var err error
+	issueIndexer, err = bleve.New(setting.Indexer.IssuePath, mapping)
+	return err
+}
+
+// UpdateIssue update the issue indexer
+func UpdateIssue(update IssueIndexerUpdate) error {
+	return issueIndexer.Index(indexerID(update.IssueID), update.Data)
+}
+
+// BatchUpdateIssues perform a batch update of the issue indexer
+func BatchUpdateIssues(updates ...IssueIndexerUpdate) error {
+	batch := issueIndexer.NewBatch()
+	for _, update := range updates {
+		err := batch.Index(indexerID(update.IssueID), update.Data)
+		if err != nil {
+			return err
+		}
+	}
+	return issueIndexer.Batch(batch)
+}
+
+// SearchIssuesByKeyword searches for issues by given conditions.
+// Returns the matching issue IDs
+func SearchIssuesByKeyword(repoID int64, keyword string) ([]int64, error) {
+	indexerQuery := bleve.NewConjunctionQuery(
+		numericEqualityQuery(repoID, "RepoID"),
+		bleve.NewDisjunctionQuery(
+			newMatchPhraseQuery(keyword, "Title", issueIndexerAnalyzer),
+			newMatchPhraseQuery(keyword, "Content", issueIndexerAnalyzer),
+			newMatchPhraseQuery(keyword, "Comments", issueIndexerAnalyzer),
+		))
+	search := bleve.NewSearchRequestOptions(indexerQuery, 2147483647, 0, false)
+
+	result, err := issueIndexer.Search(search)
+	if err != nil {
+		return nil, err
+	}
+
+	issueIDs := make([]int64, len(result.Hits))
+	for i, hit := range result.Hits {
+		issueIDs[i], err = idOfIndexerID(hit.ID)
+		if err != nil {
+			return nil, err
+		}
+	}
+	return issueIDs, nil
+}