fix(ingestion): every brain/raw/ reader goes through an os.Root; symlinks are inert
raw/ is writable via Syncthing (a sendreceive folder shared with flamingo, symlinks synced) and by the brain CronJobs, and several readers followed symlinks out of it: - /pending and brain_pending showed a symlink target's contents; brain_promote would copy it into wiki/ (then brain-sync to Gitea); brain_reject would copy it into raw/rejected/. - The watcher, which needs no API call at all, ingested symlinked files (WalkDir yields them; extract.Text followed them). Not in the issue; found while fixing it. - Ingest checked a path then reopened it by name (TOCTOU). OpenRawRoot opens brain/raw as an os.Root and refuses a raw/ that is itself a symlink. ListPending, PromoteNote and RejectNote read through it and refuse anything not a regular file. extract.TextIn reads through a root (temp copy for pdf/docmark); /ingest-path, brain_ingest and the watcher use it, and the watcher archives via the root too, so a file swapped for a symlink after a check still cannot lead out. Refs #153 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -3,6 +3,7 @@ package extract
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
"strings"
|
||||
)
|
||||
@@ -41,3 +42,48 @@ func fileExt(path string) string {
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// TextIn is Text for a file read through an os.Root (hyperguild#153): the
|
||||
// read cannot leave the root, so a path checked earlier cannot be swapped
|
||||
// for a symlink pointing elsewhere before it is read. Formats that need an
|
||||
// external tool (pdf, docmark) are copied to a temp file from the handle
|
||||
// opened through the root, then extracted from the copy.
|
||||
func TextIn(r *os.Root, rel string) (string, error) {
|
||||
fi, err := r.Lstat(rel)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("stat %s: %w", rel, err)
|
||||
}
|
||||
if !fi.Mode().IsRegular() {
|
||||
return "", fmt.Errorf("%s: not a regular file", rel)
|
||||
}
|
||||
f, err := r.Open(rel)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("open %s: %w", rel, err)
|
||||
}
|
||||
defer func() { _ = f.Close() }()
|
||||
ext := strings.ToLower(fileExt(rel))
|
||||
switch ext {
|
||||
case ".md", ".txt":
|
||||
b, err := io.ReadAll(f)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("read %s: %w", rel, err)
|
||||
}
|
||||
return string(b), nil
|
||||
case ".pdf", ".docx", ".xlsx", ".pptx", ".png", ".jpg", ".jpeg":
|
||||
tmp, err := os.CreateTemp("", "ingest-*"+ext)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("temp copy: %w", err)
|
||||
}
|
||||
defer func() { _ = os.Remove(tmp.Name()) }()
|
||||
if _, err := io.Copy(tmp, f); err != nil {
|
||||
_ = tmp.Close()
|
||||
return "", fmt.Errorf("copy %s: %w", rel, err)
|
||||
}
|
||||
if err := tmp.Close(); err != nil {
|
||||
return "", fmt.Errorf("copy %s: %w", rel, err)
|
||||
}
|
||||
return Text(tmp.Name())
|
||||
default:
|
||||
return "", fmt.Errorf("unsupported file extension: %s", ext)
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user