mirror of
https://github.com/hanzoai/team.git
synced 2026-09-30 01:57:35 +00:00
zeekay
8feb24ea1f
The server module named github.com/hanzoai/team/server/v8 — a path that resolves to the retired workspace's repository, not this one — while server/public still published github.com/mattermost/mattermost/server/public. Both are github.com/hanzoteam/server/... now, which is where this code actually lives. That second half is what made the binary unbootable. Upstream's public path stayed claimed by upstream, mattermost-plugin-ai imported it, and the build linked public/model twice; public/plugin's gob.Register then ran twice under one name and panicked at init, before main. Reverting the rename traded the brand for a working binary. Rebranding the plugin alongside it needs no such trade: the agents fork is github.com/hanzoteam/agents/v2 against our public module, so no module named mattermost/mattermost is in the graph at all. Measured: `go list -deps ./cmd/mattermost` names exactly one public/model, and it is ours.
121 lines
3.1 KiB
Go
121 lines
3.1 KiB
Go
// Copyright (c) 2015-present Mattermost, Inc. All Rights Reserved.
|
|
// See LICENSE.txt for license information.
|
|
|
|
package docextractor
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"io/fs"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
|
|
"github.com/mholt/archives"
|
|
|
|
"github.com/hanzoteam/server/server/v8/channels/utils"
|
|
)
|
|
|
|
type archiveExtractor struct {
|
|
SubExtractor Extractor
|
|
}
|
|
|
|
func (ae *archiveExtractor) Name() string {
|
|
return "archiveExtractor"
|
|
}
|
|
|
|
func (ae *archiveExtractor) Match(filename string) bool {
|
|
_, _, err := archives.Identify(context.Background(), filename, nil)
|
|
return err == nil
|
|
}
|
|
|
|
// getExtAlsoTarGz returns the extension of the given file name, special casing .tar.gz.
|
|
func getExtAlsoTarGz(name string) string {
|
|
if strings.HasSuffix(name, ".tar.gz") {
|
|
return ".tar.gz"
|
|
}
|
|
|
|
return filepath.Ext(name)
|
|
}
|
|
|
|
func (ae *archiveExtractor) Extract(ctx context.Context, name string, r io.ReadSeeker, maxFileSize int64) (string, error) {
|
|
// MM-65701: Skip 7zip files due to OOM vulnerability in bodgit/sevenzip library
|
|
match, _ := (archives.SevenZip{}).Match(context.Background(), name, r)
|
|
_, _ = r.Seek(0, io.SeekStart) // Reset reader position after Match reads from stream
|
|
if match.ByName || match.ByStream {
|
|
return "", nil
|
|
}
|
|
|
|
ext := getExtAlsoTarGz(name)
|
|
|
|
// Create a temporary file, using `*` control the random component while preserving the extension.
|
|
f, err := os.CreateTemp("", "archiver-*"+ext)
|
|
if err != nil {
|
|
return "", fmt.Errorf("error creating temporary file: %v", err)
|
|
}
|
|
defer os.Remove(f.Name())
|
|
|
|
_, err = io.Copy(f, r)
|
|
f.Close()
|
|
if err != nil {
|
|
return "", fmt.Errorf("error copying data into temporary file: %v", err)
|
|
}
|
|
|
|
var text strings.Builder
|
|
fsys, err := archives.FileSystem(context.Background(), f.Name(), nil)
|
|
if err != nil {
|
|
return "", fmt.Errorf("error creating file system: %w", err)
|
|
}
|
|
|
|
err = fs.WalkDir(fsys, ".", func(path string, d fs.DirEntry, err error) error {
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if d.IsDir() {
|
|
return nil
|
|
}
|
|
|
|
text.WriteString(path + " ")
|
|
if ae.SubExtractor != nil {
|
|
filename := filepath.Base(path)
|
|
filename = strings.ReplaceAll(filename, "-", " ")
|
|
filename = strings.ReplaceAll(filename, ".", " ")
|
|
filename = strings.ReplaceAll(filename, ",", " ")
|
|
|
|
file, err := fsys.Open(path)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
defer file.Close()
|
|
|
|
// Limit the size of decompressed archive entries to prevent
|
|
// memory exhaustion from zip bombs or other malicious archives.
|
|
var reader io.Reader = file
|
|
if maxFileSize > 0 {
|
|
reader = utils.NewLimitedReaderWithError(file, maxFileSize)
|
|
}
|
|
|
|
data, err := io.ReadAll(reader)
|
|
if err != nil {
|
|
return fmt.Errorf("error reading archive entry %s: %w", path, err)
|
|
}
|
|
|
|
subtext, extractErr := ae.SubExtractor.Extract(ctx, filename, bytes.NewReader(data), maxFileSize)
|
|
if extractErr == nil {
|
|
text.WriteString(subtext + " ")
|
|
} else if errors.Is(extractErr, context.Canceled) || errors.Is(extractErr, context.DeadlineExceeded) {
|
|
return fmt.Errorf("error extracting %q: %w", filename, extractErr)
|
|
}
|
|
}
|
|
return nil
|
|
})
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
|
|
return text.String(), nil
|
|
}
|