Spec #164: A sixth outcome word: not_found splits out of errors

backend/internal/latest/poller.go

@@ -273,7 +273,8 @@ const (
 // (issue #141). The classification the read already makes is counted, never a
 // second taxonomy: refused is the Site holding a challenge, unreachable the
 // browser interrupting, noChapter a 200 with real HTML but no chapter links,
-// unfetchable the host pin or a missing fetcher, and errors everything else.
+// unfetchable the host pin or a missing fetcher, notFound a 4xx other than
+// the 403 refusal — the page is gone — and errors everything else.
 type readOutcome int
 
 const (
@@ -283,14 +284,15 @@ const (
 	outcomeNoChapter
 	outcomeUnfetchable
 	outcomeError
+	outcomeNotFound
 )
 
-// outcomeCounts are the five named outcome counts of one pass. A success
-// count is derived, never stored: checked minus the four, with unreachable
-// excluded because the sidecar-loss path returns before the checked counter
-// increments (issue #141).
+// outcomeCounts are the six named outcome counts of one pass. A success
+// count is derived, never stored: checked minus the five named failures,
+// with unreachable excluded because the sidecar-loss path returns before the
+// checked counter increments (issue #141).
 type outcomeCounts struct {
-	refused, unreachable, noChapter, unfetchable, errors int
+	refused, unreachable, noChapter, unfetchable, errors, notFound int
 }
 
 func (c *outcomeCounts) add(o readOutcome) {
@@ -303,6 +305,8 @@ func (c *outcomeCounts) add(o readOutcome) {
 		c.noChapter++
 	case outcomeUnfetchable:
 		c.unfetchable++
+	case outcomeNotFound:
+		c.notFound++
 	case outcomeError:
 		c.errors++
 	}
@@ -517,6 +521,7 @@ func (p *Poller) recordPass(rec passRecord, fig passFigures) {
 		Unreachable: rec.counts.unreachable,
 		NoChapter:   rec.counts.noChapter,
 		Unfetchable: rec.counts.unfetchable,
+		NotFound:    rec.counts.notFound,
 		Errors:      rec.counts.errors,
 	}
 	if row.GapMS == 0 {
@@ -612,8 +617,8 @@ func maxSeriesWait(due []store.Series, now time.Time, rest time.Duration) time.D
 // the poller is a best-effort enhancement, and no single bad series may stall a
 // Lane or take down the process. The returned outcome classifies the read for
 // the pass row (issue #141), so the Lane can count a refusal, a lost browser,
-// a chapter-less page, an unfetchable address or a transport error without
-// re-deriving the taxonomy.
+// a chapter-less page, an unfetchable address, a missing page or a transport
+// error without re-deriving the taxonomy.
 func (p *Poller) checkOne(ctx context.Context, sr store.Series) (outcome readOutcome) {
 	defer func() {
 		if r := recover(); r != nil {
@@ -657,6 +662,10 @@ func (p *Poller) checkOne(ctx context.Context, sr store.Series) (outcome readOut
 		if errors.Is(err, errBrowserInterrupted) {
 			return outcomeUnreachable
 		}
+		if errors.Is(err, errNotFound) {
+			log.Printf("latest poll %q: page not found: %v", sr.Key(), err)
+			return outcomeNotFound
+		}
 		return outcomeError
 	}
 	// A legacy cover source is healed independently of the page read.