forgejo/modules/indexer/code/git.go
Jason Song 375fd15fbf
Refactor indexer (#25174)
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>
2023-06-23 12:37:56 +00:00

168 lines
4.9 KiB
Go

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package code
import (
"context"
"strconv"
"strings"
repo_model "code.gitea.io/gitea/models/repo"
"code.gitea.io/gitea/modules/git"
"code.gitea.io/gitea/modules/indexer/code/internal"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/setting"
)
func getDefaultBranchSha(ctx context.Context, repo *repo_model.Repository) (string, error) {
stdout, _, err := git.NewCommand(ctx, "show-ref", "-s").AddDynamicArguments(git.BranchPrefix + repo.DefaultBranch).RunStdString(&git.RunOpts{Dir: repo.RepoPath()})
if err != nil {
return "", err
}
return strings.TrimSpace(stdout), nil
}
// getRepoChanges returns changes to repo since last indexer update
func getRepoChanges(ctx context.Context, repo *repo_model.Repository, revision string) (*internal.RepoChanges, error) {
status, err := repo_model.GetIndexerStatus(ctx, repo, repo_model.RepoIndexerTypeCode)
if err != nil {
return nil, err
}
if len(status.CommitSha) == 0 {
return genesisChanges(ctx, repo, revision)
}
return nonGenesisChanges(ctx, repo, revision)
}
func isIndexable(entry *git.TreeEntry) bool {
if !entry.IsRegular() && !entry.IsExecutable() {
return false
}
name := strings.ToLower(entry.Name())
for _, g := range setting.Indexer.ExcludePatterns {
if g.Match(name) {
return false
}
}
for _, g := range setting.Indexer.IncludePatterns {
if g.Match(name) {
return true
}
}
return len(setting.Indexer.IncludePatterns) == 0
}
// parseGitLsTreeOutput parses the output of a `git ls-tree -r --full-name` command
func parseGitLsTreeOutput(stdout []byte) ([]internal.FileUpdate, error) {
entries, err := git.ParseTreeEntries(stdout)
if err != nil {
return nil, err
}
idxCount := 0
updates := make([]internal.FileUpdate, len(entries))
for _, entry := range entries {
if isIndexable(entry) {
updates[idxCount] = internal.FileUpdate{
Filename: entry.Name(),
BlobSha: entry.ID.String(),
Size: entry.Size(),
Sized: true,
}
idxCount++
}
}
return updates[:idxCount], nil
}
// genesisChanges get changes to add repo to the indexer for the first time
func genesisChanges(ctx context.Context, repo *repo_model.Repository, revision string) (*internal.RepoChanges, error) {
var changes internal.RepoChanges
stdout, _, runErr := git.NewCommand(ctx, "ls-tree", "--full-tree", "-l", "-r").AddDynamicArguments(revision).RunStdBytes(&git.RunOpts{Dir: repo.RepoPath()})
if runErr != nil {
return nil, runErr
}
var err error
changes.Updates, err = parseGitLsTreeOutput(stdout)
return &changes, err
}
// nonGenesisChanges get changes since the previous indexer update
func nonGenesisChanges(ctx context.Context, repo *repo_model.Repository, revision string) (*internal.RepoChanges, error) {
diffCmd := git.NewCommand(ctx, "diff", "--name-status").AddDynamicArguments(repo.CodeIndexerStatus.CommitSha, revision)
stdout, _, runErr := diffCmd.RunStdString(&git.RunOpts{Dir: repo.RepoPath()})
if runErr != nil {
// previous commit sha may have been removed by a force push, so
// try rebuilding from scratch
log.Warn("git diff: %v", runErr)
if err := (*globalIndexer.Load()).Delete(ctx, repo.ID); err != nil {
return nil, err
}
return genesisChanges(ctx, repo, revision)
}
var changes internal.RepoChanges
var err error
updatedFilenames := make([]string, 0, 10)
for _, line := range strings.Split(stdout, "\n") {
line = strings.TrimSpace(line)
if len(line) == 0 {
continue
}
fields := strings.Split(line, "\t")
if len(fields) < 2 {
log.Warn("Unparseable output for diff --name-status: `%s`)", line)
continue
}
filename := fields[1]
if len(filename) == 0 {
continue
} else if filename[0] == '"' {
filename, err = strconv.Unquote(filename)
if err != nil {
return nil, err
}
}
switch status := fields[0][0]; status {
case 'M', 'A':
updatedFilenames = append(updatedFilenames, filename)
case 'D':
changes.RemovedFilenames = append(changes.RemovedFilenames, filename)
case 'R', 'C':
if len(fields) < 3 {
log.Warn("Unparseable output for diff --name-status: `%s`)", line)
continue
}
dest := fields[2]
if len(dest) == 0 {
log.Warn("Unparseable output for diff --name-status: `%s`)", line)
continue
}
if dest[0] == '"' {
dest, err = strconv.Unquote(dest)
if err != nil {
return nil, err
}
}
if status == 'R' {
changes.RemovedFilenames = append(changes.RemovedFilenames, filename)
}
updatedFilenames = append(updatedFilenames, dest)
default:
log.Warn("Unrecognized status: %c (line=%s)", status, line)
}
}
cmd := git.NewCommand(ctx, "ls-tree", "--full-tree", "-l").AddDynamicArguments(revision).
AddDashesAndList(updatedFilenames...)
lsTreeStdout, _, err := cmd.RunStdBytes(&git.RunOpts{Dir: repo.RepoPath()})
if err != nil {
return nil, err
}
changes.Updates, err = parseGitLsTreeOutput(lsTreeStdout)
return &changes, err
}