3 files changed, 14 insertions, 4 deletions
diff --git a/internal/extract/extract.go b/internal/extract/extract.go
index 7e3adec..0843c42 100644
--- a/internal/extract/extract.go
+++ b/internal/extract/extract.go
@@ -23,6 +23,11 @@ var (
 	// ErrUnsupported is returned when the format carries no text krino
 	// knows how to extract.
 	ErrUnsupported = errors.New("no text in this format")
+	// ErrPartial wraps the error of a document read only in part (an
+	// archive entry that would not open or parse). Text returns the text it
+	// did read along with it: a keyword found there is found, but one not
+	// found may be in the part that could not be read (plan 11).
+	ErrPartial = errors.New("part of it could not be read")
 	// ErrTooLarge is returned when the file is larger than the configured
 	// max-read; nothing is read in that case.
 	ErrTooLarge = errors.New("larger than max-read")
diff --git a/internal/extract/zipxml.go b/internal/extract/zipxml.go
index 1b3ba82..3b59d3a 100644
--- a/internal/extract/zipxml.go
+++ b/internal/extract/zipxml.go
@@ -102,8 +102,11 @@ func zipText(ctx context.Context, path, ext string, maxRead int64) (string, erro
 		}
 		b.WriteByte('\n')
 	}
-	if !wroteText && firstErr != nil {
-		return "", firstErr
+	if firstErr != nil {
+		if !wroteText {
+			return "", firstErr
+		}
+		return b.String(), fmt.Errorf("%w: %w", ErrPartial, firstErr)
 	}
 	return b.String(), nil
 }
diff --git a/internal/extract/zipxml_test.go b/internal/extract/zipxml_test.go
index 14ead80..30a4cf9 100644
--- a/internal/extract/zipxml_test.go
+++ b/internal/extract/zipxml_test.go
@@ -138,8 +138,10 @@ func TestZipLenientOnMalformedEntry(t *testing.T) {
 		"word/document.xml": `<w:document xmlns:w="w"><w:body><w:p><w:r><w:t>good body text</w:t></w:r></w:p></w:body></w:document>`,
 		"word/footer1.xml":  `<w:ftr xmlns:w="w"><w:p><w:r><w:t>broken</w:t></w:r></w:p></w:xyz>`,
 	}), 0)
-	if err != nil {
-		t.Fatalf("good entry alongside a malformed one: %v", err)
+	// Partly read: the text is kept, and ErrPartial says some of it is
+	// missing, so a keyword not found in it is unknown (plan 11).
+	if !errors.Is(err, ErrPartial) {
+		t.Fatalf("good entry alongside a malformed one: err %v, want ErrPartial", err)
 	}
 	if !strings.Contains(got, "good body text") {
 		t.Errorf("text from the good entry was discarded: %q", got)