bench-forgejo/modules/indexer/code/repo.go

258 lines
7 KiB
Go
Raw Normal View History

// 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 code
import (
"strings"
"sync"
"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/tokenizer/unicode"
"github.com/blevesearch/bleve/search/query"
2018-02-05 23:59:17 +05:30
"github.com/ethantkoenig/rupture"
)
2018-02-05 23:59:17 +05:30
const (
repoIndexerAnalyzer = "repoIndexerAnalyzer"
repoIndexerDocType = "repoIndexerDocType"
repoIndexerLatestVersion = 4
2018-02-05 23:59:17 +05:30
)
type bleveIndexerHolder struct {
index bleve.Index
mutex sync.RWMutex
cond *sync.Cond
}
func newBleveIndexerHolder() *bleveIndexerHolder {
b := &bleveIndexerHolder{}
b.cond = sync.NewCond(b.mutex.RLocker())
return b
}
func (r *bleveIndexerHolder) set(index bleve.Index) {
r.mutex.Lock()
defer r.mutex.Unlock()
r.index = index
r.cond.Broadcast()
}
func (r *bleveIndexerHolder) get() bleve.Index {
r.mutex.RLock()
defer r.mutex.RUnlock()
if r.index == nil {
r.cond.Wait()
}
return r.index
}
// repoIndexer (thread-safe) index for repository contents
var indexerHolder = newBleveIndexerHolder()
// RepoIndexerOp type of operation to perform on repo indexer
type RepoIndexerOp int
const (
// RepoIndexerOpUpdate add/update a file's contents
RepoIndexerOpUpdate = iota
// RepoIndexerOpDelete delete a file
RepoIndexerOpDelete
)
// RepoIndexerData data stored in the repo indexer
type RepoIndexerData struct {
RepoID int64
Content string
}
2018-02-05 23:59:17 +05:30
// Type returns the document type, for bleve's mapping.Classifier interface.
func (d *RepoIndexerData) Type() string {
return repoIndexerDocType
}
// RepoIndexerUpdate an update to the repo indexer
type RepoIndexerUpdate struct {
Filepath string
Op RepoIndexerOp
Data *RepoIndexerData
}
2018-02-05 23:59:17 +05:30
// AddToFlushingBatch adds the update to the given flushing batch.
func (update RepoIndexerUpdate) AddToFlushingBatch(batch rupture.FlushingBatch) error {
id := filenameIndexerID(update.Data.RepoID, update.Filepath)
switch update.Op {
case RepoIndexerOpUpdate:
return batch.Index(id, update.Data)
case RepoIndexerOpDelete:
2018-02-05 23:59:17 +05:30
return batch.Delete(id)
default:
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Error("Unrecognized repo indexer op: %d", update.Op)
}
return nil
}
// initRepoIndexer initialize repo indexer
func initRepoIndexer(populateIndexer func() error) {
indexer, err := openIndexer(setting.Indexer.RepoPath, repoIndexerLatestVersion)
if err != nil {
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Fatal("InitRepoIndexer: %v", err)
2018-02-05 23:59:17 +05:30
}
if indexer != nil {
indexerHolder.set(indexer)
2018-02-05 23:59:17 +05:30
return
}
if err = createRepoIndexer(setting.Indexer.RepoPath, repoIndexerLatestVersion); err != nil {
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Fatal("CreateRepoIndexer: %v", err)
2018-02-05 23:59:17 +05:30
}
if err = populateIndexer(); err != nil {
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Fatal("PopulateRepoIndex: %v", err)
}
}
// createRepoIndexer create a repo indexer if one does not already exist
func createRepoIndexer(path string, latestVersion int) error {
docMapping := bleve.NewDocumentMapping()
2018-02-05 23:59:17 +05:30
numericFieldMapping := bleve.NewNumericFieldMapping()
numericFieldMapping.IncludeInAll = false
docMapping.AddFieldMappingsAt("RepoID", numericFieldMapping)
textFieldMapping := bleve.NewTextFieldMapping()
2018-02-05 23:59:17 +05:30
textFieldMapping.IncludeInAll = false
docMapping.AddFieldMappingsAt("Content", textFieldMapping)
mapping := bleve.NewIndexMapping()
if err := addUnicodeNormalizeTokenFilter(mapping); err != nil {
return err
} else if err := mapping.AddCustomAnalyzer(repoIndexerAnalyzer, map[string]interface{}{
"type": custom.Name,
"char_filters": []string{},
"tokenizer": unicode.Name,
"token_filters": []string{unicodeNormalizeName, lowercase.Name},
}); err != nil {
return err
}
mapping.DefaultAnalyzer = repoIndexerAnalyzer
2018-02-05 23:59:17 +05:30
mapping.AddDocumentMapping(repoIndexerDocType, docMapping)
mapping.AddDocumentMapping("_all", bleve.NewDocumentDisabledMapping())
indexer, err := bleve.New(path, mapping)
if err != nil {
return err
}
indexerHolder.set(indexer)
return rupture.WriteIndexMetadata(path, &rupture.IndexMetadata{
Version: latestVersion,
})
}
func filenameIndexerID(repoID int64, filename string) string {
return indexerID(repoID) + "_" + filename
}
func filenameOfIndexerID(indexerID string) string {
index := strings.IndexByte(indexerID, '_')
if index == -1 {
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Error("Unexpected ID in repo indexer: %s", indexerID)
}
return indexerID[index+1:]
}
// RepoIndexerBatch batch to add updates to
2018-02-05 23:59:17 +05:30
func RepoIndexerBatch() rupture.FlushingBatch {
return rupture.NewFlushingBatch(indexerHolder.get(), maxBatchSize)
}
// deleteRepoFromIndexer delete all of a repo's files from indexer
func deleteRepoFromIndexer(repoID int64) error {
query := numericEqualityQuery(repoID, "RepoID")
searchRequest := bleve.NewSearchRequestOptions(query, 2147483647, 0, false)
result, err := indexerHolder.get().Search(searchRequest)
if err != nil {
return err
}
batch := RepoIndexerBatch()
for _, hit := range result.Hits {
2018-02-05 23:59:17 +05:30
if err = batch.Delete(hit.ID); err != nil {
return err
}
}
return batch.Flush()
}
// RepoSearchResult result of performing a search in a repo
type RepoSearchResult struct {
RepoID int64
StartIndex int
EndIndex int
Filename string
Content string
}
// SearchRepoByKeyword searches for files in the specified repo.
// Returns the matching file-paths
func SearchRepoByKeyword(repoIDs []int64, keyword string, page, pageSize int) (int64, []*RepoSearchResult, error) {
phraseQuery := bleve.NewMatchPhraseQuery(keyword)
phraseQuery.FieldVal = "Content"
phraseQuery.Analyzer = repoIndexerAnalyzer
var indexerQuery query.Query
if len(repoIDs) > 0 {
var repoQueries = make([]query.Query, 0, len(repoIDs))
for _, repoID := range repoIDs {
repoQueries = append(repoQueries, numericEqualityQuery(repoID, "RepoID"))
}
indexerQuery = bleve.NewConjunctionQuery(
bleve.NewDisjunctionQuery(repoQueries...),
phraseQuery,
)
} else {
indexerQuery = phraseQuery
}
from := (page - 1) * pageSize
searchRequest := bleve.NewSearchRequestOptions(indexerQuery, pageSize, from, false)
searchRequest.Fields = []string{"Content", "RepoID"}
searchRequest.IncludeLocations = true
result, err := indexerHolder.get().Search(searchRequest)
if err != nil {
return 0, nil, err
}
searchResults := make([]*RepoSearchResult, len(result.Hits))
for i, hit := range result.Hits {
var startIndex, endIndex int = -1, -1
for _, locations := range hit.Locations["Content"] {
location := locations[0]
locationStart := int(location.Start)
locationEnd := int(location.End)
if startIndex < 0 || locationStart < startIndex {
startIndex = locationStart
}
if endIndex < 0 || locationEnd > endIndex {
endIndex = locationEnd
}
}
searchResults[i] = &RepoSearchResult{
RepoID: int64(hit.Fields["RepoID"].(float64)),
StartIndex: startIndex,
EndIndex: endIndex,
Filename: filenameOfIndexerID(hit.ID),
Content: hit.Fields["Content"].(string),
}
}
return int64(result.Total), searchResults, nil
}