fix(ingestion): brain/raw/ readers go through an os.Root; symlinks are inert (#153) (#156)

Co-authored-by: Mathias <mthbqv@gmail.com>

ingestion/internal/extract/extract.go

@@ -3,8 +3,10 @@ package extract
 
 import (
 	"fmt"
+	"io"
 	"os"
 	"strings"
+	"syscall"
 )
 
 // Text reads the file at path and returns its plain-text content.
@@ -41,3 +43,70 @@ 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 := OpenRegular(r, 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)
+	}
+}
+
+// OpenRegular opens rel inside r and returns it only if the OPENED handle is
+// a regular file. The open is non-blocking, so a FIFO swapped in after an
+// Lstat (PR #156 review: it hung open(2) forever) is refused promptly rather
+// than stalling the reader. Callers keep their Lstat check, which refuses
+// symlinks outright; this closes the race between that check and the open.
+func OpenRegular(r *os.Root, rel string) (*os.File, os.FileInfo, error) {
+	f, err := r.OpenFile(rel, os.O_RDONLY|syscall.O_NONBLOCK, 0)
+	if err != nil {
+		return nil, nil, err
+	}
+	fi, err := f.Stat()
+	if err != nil {
+		_ = f.Close()
+		return nil, nil, err
+	}
+	if !fi.Mode().IsRegular() {
+		_ = f.Close()
+		return nil, nil, fmt.Errorf("%s: not a regular file", rel)
+	}
+	return f, fi, nil
+}