Merge branch 'main' into fix-gzip

custom/conf/app.example.ini

@@ -1456,7 +1456,7 @@ LEVEL = Info
 ;; Batch size to send for batched queues
 ;BATCH_LENGTH = 20
 ;;
-;; Connection string for redis queues this will store the redis or redis-cluster connection string.
+;; Connection string for redis queues this will store the redis (or Redis cluster) connection string.
 ;; When `TYPE` is `persistable-channel`, this provides a directory for the underlying leveldb
 ;; or additional options of the form `leveldb://path/to/db?option=value&....`, and will override `DATADIR`.
 ;CONN_STR = "redis://127.0.0.1:6379/0"
@@ -1740,9 +1740,8 @@ LEVEL = Info
 ;; For "memory" only, GC interval in seconds, default is 60
 ;INTERVAL = 60
 ;;
-;; For "redis", "redis-cluster" and "memcache", connection host address
-;; redis: `redis://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s`
-;; redis-cluster: `redis+cluster://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s`
+;; For "redis" and "memcache", connection host address
+;; redis: `redis://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s` (or `redis+cluster://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s` for a Redis cluster)
 ;; memcache: `127.0.0.1:11211`
 ;; twoqueue: `{"size":50000,"recent_ratio":0.25,"ghost_ratio":0.5}` or `50000`
 ;HOST =
@@ -1772,15 +1771,14 @@ LEVEL = Info
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
-;; Either "memory", "file", "redis", "redis-cluster", "db", "mysql", "couchbase", "memcache" or "postgres"
+;; Either "memory", "file", "redis", "db", "mysql", "couchbase", "memcache" or "postgres"
 ;; Default is "memory". "db" will reuse the configuration in [database]
 ;PROVIDER = memory
 ;;
 ;; Provider config options
 ;; memory: doesn't have any config yet
 ;; file: session file path, e.g. `data/sessions`
-;; redis: `redis://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s`
-;; redis-cluster: `redis+cluster://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s`
+;; redis: `redis://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s` (or `redis+cluster://127.0.0.1:6379/0?pool_size=100&idle_timeout=180s` for a Redis cluster)
 ;; mysql: go-sql-driver/mysql dsn config string, e.g. `root:password@/session_table`
 ;PROVIDER_CONFIG = data/sessions ; Relative paths will be made absolute against _`AppWorkPath`_.
 ;;

docs/content/administration/config-cheat-sheet.en-us.md

@@ -492,7 +492,7 @@ Configuration at `[queue]` will set defaults for queues with overrides for indiv
 - `DATADIR`: **queues/common**: Base DataDir for storing level queues. `DATADIR` for individual queues can be set in `queue.name` sections. Relative paths will be made absolute against `%(APP_DATA_PATH)s`.
 - `LENGTH`: **100000**: Maximal queue size before channel queues block
 - `BATCH_LENGTH`: **20**: Batch data before passing to the handler
-- `CONN_STR`: **redis://127.0.0.1:6379/0**: Connection string for the redis queue type. For `redis-cluster` use `redis+cluster://127.0.0.1:6379/0`. Options can be set using query params. Similarly, LevelDB options can also be set using: **leveldb://relative/path?option=value** or **leveldb:///absolute/path?option=value**, and will override `DATADIR`
+- `CONN_STR`: **redis://127.0.0.1:6379/0**: Connection string for the redis queue type. If you're running a Redis cluster, use `redis+cluster://127.0.0.1:6379/0`. Options can be set using query params. Similarly, LevelDB options can also be set using: **leveldb://relative/path?option=value** or **leveldb:///absolute/path?option=value**, and will override `DATADIR`
 - `QUEUE_NAME`: **_queue**: The suffix for default redis and disk queue name. Individual queues will default to **`name`**`QUEUE_NAME` but can be overridden in the specific `queue.name` section.
 - `SET_NAME`: **_unique**: The suffix that will be added to the default redis and disk queue `set` name for unique queues. Individual queues will default to **`name`**`QUEUE_NAME`_`SET_NAME`_ but can be overridden in the specific `queue.name` section.
 - `MAX_WORKERS`: **(dynamic)**: Maximum number of worker go-routines for the queue. Default value is "CpuNum/2" clipped to between 1 and 10.
@@ -777,11 +777,11 @@ and
 
 ## Cache (`cache`)
 
-- `ADAPTER`: **memory**: Cache engine adapter, either `memory`, `redis`, `redis-cluster`, `twoqueue` or `memcache`. (`twoqueue` represents a size limited LRU cache.)
+- `ADAPTER`: **memory**: Cache engine adapter, either `memory`, `redis`, `twoqueue` or `memcache`. (`twoqueue` represents a size limited LRU cache.)
 - `INTERVAL`: **60**: Garbage Collection interval (sec), for memory and twoqueue cache only.
-- `HOST`: **_empty_**: Connection string for `redis`, `redis-cluster` and `memcache`. For `twoqueue` sets configuration for the queue.
+- `HOST`: **_empty_**: Connection string for `redis` and `memcache`. For `twoqueue` sets configuration for the queue.
   - Redis: `redis://:macaron@127.0.0.1:6379/0?pool_size=100&idle_timeout=180s`
-  - Redis-cluster `redis+cluster://:macaron@127.0.0.1:6379/0?pool_size=100&idle_timeout=180s`
+    - For a Redis cluster: `redis+cluster://:macaron@127.0.0.1:6379/0?pool_size=100&idle_timeout=180s`
   - Memcache: `127.0.0.1:9090;127.0.0.1:9091`
   - TwoQueue LRU cache: `{"size":50000,"recent_ratio":0.25,"ghost_ratio":0.5}` or `50000` representing the maximum number of objects stored in the cache.
 - `ITEM_TTL`: **16h**: Time to keep items in cache if not used, Setting it to -1 disables caching.
@@ -793,7 +793,7 @@ and
 
 ## Session (`session`)
 
-- `PROVIDER`: **memory**: Session engine provider \[memory, file, redis, redis-cluster, db, mysql, couchbase, memcache, postgres\]. Setting `db` will reuse the configuration in `[database]`
+- `PROVIDER`: **memory**: Session engine provider \[memory, file, redis, db, mysql, couchbase, memcache, postgres\]. Setting `db` will reuse the configuration in `[database]`
 - `PROVIDER_CONFIG`: **data/sessions**: For file, the root path; for db, empty (database config will be used); for others, the connection string. Relative paths will be made absolute against _`AppWorkPath`_.
 - `COOKIE_SECURE`:**_empty_**: `true` or `false`. Enable this to force using HTTPS for all session access. If not set, it defaults to `true` if the ROOT_URL is an HTTPS URL.
 - `COOKIE_NAME`: **i\_like\_gitea**: The name of the cookie used for the session ID.

modules/indexer/code/bleve/bleve.go

@@ -39,8 +39,6 @@ import (
 const (
 	unicodeNormalizeName = "unicodeNormalize"
 	maxBatchSize         = 16
-	// fuzzyDenominator determines the levenshtein distance per each character of a keyword
-	fuzzyDenominator = 4
 )
 
 func addUnicodeNormalizeTokenFilter(m *mapping.IndexMappingImpl) error {
@@ -245,7 +243,7 @@ func (b *Indexer) Search(ctx context.Context, opts *internal.SearchOptions) (int
 	phraseQuery.Analyzer = repoIndexerAnalyzer
 	keywordQuery = phraseQuery
 	if opts.IsKeywordFuzzy {
-		phraseQuery.Fuzziness = len(opts.Keyword) / fuzzyDenominator
+		phraseQuery.Fuzziness = inner_bleve.GuessFuzzinessByKeyword(opts.Keyword)
 	}
 
 	if len(opts.RepoIDs) > 0 {

modules/indexer/internal/bleve/util.go

@@ -47,3 +47,15 @@ func openIndexer(path string, latestVersion int) (bleve.Index, int, error) {
 
 	return index, 0, nil
 }
+
+func GuessFuzzinessByKeyword(s string) int {
+	// according to https://github.com/blevesearch/bleve/issues/1563, the supported max fuzziness is 2
+	// magic number 4 was chosen to determine the levenshtein distance per each character of a keyword
+	// BUT, when using CJK (eg: `갃갃갃` `啊啊啊`), it mismatches a lot.
+	for _, r := range s {
+		if r >= 128 {
+			return 0
+		}
+	}
+	return min(2, len(s)/4)
+}

modules/indexer/issues/bleve/bleve.go

@@ -35,11 +35,7 @@ func addUnicodeNormalizeTokenFilter(m *mapping.IndexMappingImpl) error {
 	})
 }
 
-const (
-	maxBatchSize = 16
-	// fuzzyDenominator determines the levenshtein distance per each character of a keyword
-	fuzzyDenominator = 4
-)
+const maxBatchSize = 16
 
 // IndexerData an update to the issue indexer
 type IndexerData internal.IndexerData
@@ -162,7 +158,7 @@ func (b *Indexer) Search(ctx context.Context, options *internal.SearchOptions) (
 	if options.Keyword != "" {
 		fuzziness := 0
 		if options.IsFuzzyKeyword {
-			fuzziness = len(options.Keyword) / fuzzyDenominator
+			fuzziness = inner_bleve.GuessFuzzinessByKeyword(options.Keyword)
 		}
 
 		queries = append(queries, bleve.NewDisjunctionQuery([]query.Query{

routers/web/repo/search.go

@@ -28,6 +28,7 @@ func Search(ctx *context.Context) {
 	ctx.Data["Language"] = language
 	ctx.Data["IsFuzzy"] = isFuzzy
 	ctx.Data["PageIsViewCode"] = true
+	ctx.Data["IsRepoIndexerEnabled"] = setting.Indexer.RepoIndexerEnabled
 
 	if keyword == "" {
 		ctx.HTML(http.StatusOK, tplSearch)
@@ -86,7 +87,6 @@ func Search(ctx *context.Context) {
 		}
 	}
 
-	ctx.Data["IsRepoIndexerEnabled"] = setting.Indexer.RepoIndexerEnabled
 	ctx.Data["Repo"] = ctx.Repo.Repository
 	ctx.Data["SearchResults"] = searchResults
 	ctx.Data["SearchResultLanguages"] = searchResultLanguages