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- [x] Fix outdated example config.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>
		
	
			
		
			
				
	
	
		
			136 lines
		
	
	
		
			3.4 KiB
		
	
	
	
		
			Go
		
	
	
	
	
	
			
		
		
	
	
			136 lines
		
	
	
		
			3.4 KiB
		
	
	
	
		
			Go
		
	
	
	
	
	
| // Copyright 2017 The Gitea Authors. All rights reserved.
 | |
| // SPDX-License-Identifier: MIT
 | |
| 
 | |
| package code
 | |
| 
 | |
| import (
 | |
| 	"bytes"
 | |
| 	"context"
 | |
| 	"strings"
 | |
| 
 | |
| 	"code.gitea.io/gitea/modules/highlight"
 | |
| 	"code.gitea.io/gitea/modules/indexer/code/internal"
 | |
| 	"code.gitea.io/gitea/modules/timeutil"
 | |
| 	"code.gitea.io/gitea/modules/util"
 | |
| )
 | |
| 
 | |
| // Result a search result to display
 | |
| type Result struct {
 | |
| 	RepoID         int64
 | |
| 	Filename       string
 | |
| 	CommitID       string
 | |
| 	UpdatedUnix    timeutil.TimeStamp
 | |
| 	Language       string
 | |
| 	Color          string
 | |
| 	LineNumbers    []int
 | |
| 	FormattedLines string
 | |
| }
 | |
| 
 | |
| type SearchResultLanguages = internal.SearchResultLanguages
 | |
| 
 | |
| func indices(content string, selectionStartIndex, selectionEndIndex int) (int, int) {
 | |
| 	startIndex := selectionStartIndex
 | |
| 	numLinesBefore := 0
 | |
| 	for ; startIndex > 0; startIndex-- {
 | |
| 		if content[startIndex-1] == '\n' {
 | |
| 			if numLinesBefore == 1 {
 | |
| 				break
 | |
| 			}
 | |
| 			numLinesBefore++
 | |
| 		}
 | |
| 	}
 | |
| 
 | |
| 	endIndex := selectionEndIndex
 | |
| 	numLinesAfter := 0
 | |
| 	for ; endIndex < len(content); endIndex++ {
 | |
| 		if content[endIndex] == '\n' {
 | |
| 			if numLinesAfter == 1 {
 | |
| 				break
 | |
| 			}
 | |
| 			numLinesAfter++
 | |
| 		}
 | |
| 	}
 | |
| 
 | |
| 	return startIndex, endIndex
 | |
| }
 | |
| 
 | |
| func writeStrings(buf *bytes.Buffer, strs ...string) error {
 | |
| 	for _, s := range strs {
 | |
| 		_, err := buf.WriteString(s)
 | |
| 		if err != nil {
 | |
| 			return err
 | |
| 		}
 | |
| 	}
 | |
| 	return nil
 | |
| }
 | |
| 
 | |
| func searchResult(result *internal.SearchResult, startIndex, endIndex int) (*Result, error) {
 | |
| 	startLineNum := 1 + strings.Count(result.Content[:startIndex], "\n")
 | |
| 
 | |
| 	var formattedLinesBuffer bytes.Buffer
 | |
| 
 | |
| 	contentLines := strings.SplitAfter(result.Content[startIndex:endIndex], "\n")
 | |
| 	lineNumbers := make([]int, len(contentLines))
 | |
| 	index := startIndex
 | |
| 	for i, line := range contentLines {
 | |
| 		var err error
 | |
| 		if index < result.EndIndex &&
 | |
| 			result.StartIndex < index+len(line) &&
 | |
| 			result.StartIndex < result.EndIndex {
 | |
| 			openActiveIndex := util.Max(result.StartIndex-index, 0)
 | |
| 			closeActiveIndex := util.Min(result.EndIndex-index, len(line))
 | |
| 			err = writeStrings(&formattedLinesBuffer,
 | |
| 				line[:openActiveIndex],
 | |
| 				line[openActiveIndex:closeActiveIndex],
 | |
| 				line[closeActiveIndex:],
 | |
| 			)
 | |
| 		} else {
 | |
| 			err = writeStrings(&formattedLinesBuffer,
 | |
| 				line,
 | |
| 			)
 | |
| 		}
 | |
| 		if err != nil {
 | |
| 			return nil, err
 | |
| 		}
 | |
| 
 | |
| 		lineNumbers[i] = startLineNum + i
 | |
| 		index += len(line)
 | |
| 	}
 | |
| 
 | |
| 	highlighted, _ := highlight.Code(result.Filename, "", formattedLinesBuffer.String())
 | |
| 
 | |
| 	return &Result{
 | |
| 		RepoID:         result.RepoID,
 | |
| 		Filename:       result.Filename,
 | |
| 		CommitID:       result.CommitID,
 | |
| 		UpdatedUnix:    result.UpdatedUnix,
 | |
| 		Language:       result.Language,
 | |
| 		Color:          result.Color,
 | |
| 		LineNumbers:    lineNumbers,
 | |
| 		FormattedLines: highlighted,
 | |
| 	}, nil
 | |
| }
 | |
| 
 | |
| // PerformSearch perform a search on a repository
 | |
| func PerformSearch(ctx context.Context, repoIDs []int64, language, keyword string, page, pageSize int, isMatch bool) (int, []*Result, []*internal.SearchResultLanguages, error) {
 | |
| 	if len(keyword) == 0 {
 | |
| 		return 0, nil, nil, nil
 | |
| 	}
 | |
| 
 | |
| 	total, results, resultLanguages, err := (*globalIndexer.Load()).Search(ctx, repoIDs, language, keyword, page, pageSize, isMatch)
 | |
| 	if err != nil {
 | |
| 		return 0, nil, nil, err
 | |
| 	}
 | |
| 
 | |
| 	displayResults := make([]*Result, len(results))
 | |
| 
 | |
| 	for i, result := range results {
 | |
| 		startIndex, endIndex := indices(result.Content, result.StartIndex, result.EndIndex)
 | |
| 		displayResults[i], err = searchResult(result, startIndex, endIndex)
 | |
| 		if err != nil {
 | |
| 			return 0, nil, nil, err
 | |
| 		}
 | |
| 	}
 | |
| 	return int(total), displayResults, resultLanguages, nil
 | |
| }
 |