content tests are three-valued: unknown when unreadable or read in part

1 files changed, 7 insertions, 2 deletions

diff --git a/internal/engine/facts.go b/internal/engine/facts.go
index ccdf18d..c510b20 100644
--- a/internal/engine/facts.go
+++ b/internal/engine/facts.go
@@ -118,6 +118,7 @@ type facts struct {
 
 	contentDone bool            // extraction was attempted
 	contentErr  error           // why it failed
+	partialErr  error           // extract.ErrPartial: a keyword not found may be in the unread part
 	answers     map[string]bool // by cond.KeywordKey, once extracted
 }
 
@@ -171,7 +172,7 @@ func (f *facts) ContentContains(opt cond.Options, keywords []string) (int, error
 			return i, nil
 		}
 	}
-	return -1, nil
+	return -1, f.partialErr
 }
 
 // extract reads the file's text and answers every keyword of the directory,
@@ -180,6 +181,10 @@ func (f *facts) extract(opt cond.Options, keywords []string) {
 	f.contentDone = true
 	text, err := f.run.e.Extract.Text(f.run.ctx, f.file.Path, f.file.Size, f.run.d.Settings.MaxRead)
 	switch {
+	case errors.Is(err, extract.ErrPartial):
+		// Partly read: the keywords found in it are answered; one not found
+		// is unknown (ContentContains), and nothing is cached (plan 11).
+		f.partialErr = err
 	case errors.Is(err, extract.ErrUnsupported):
 		// A format with no text cannot contain a keyword: every answer is
 		// no, with no warning, and the answers are cached like any other
@@ -203,7 +208,7 @@ func (f *facts) extract(opt cond.Options, keywords []string) {
 		}
 		f.answers[k.Key()] = strings.Contains(t, k.Norm)
 	}
-	if id, ok := f.cacheID(); ok {
+	if id, ok := f.cacheID(); ok && f.partialErr == nil {
 		f.run.cache.Store(id, f.answers)
 	}
 }