Spec #137: per-Series poll failure state, completion hint, and outbound owner notification (#174)

Implements spec #137 (spec 4 of 4 from wayfinder map #114). Closes #137. Tickets: #164, #165, #166, #167, #168, #169, #170, #171, #172, #173 — all closed, landed on this branch. ## Summary - #164/#168: sixth outcome word `not_found`; per-Site completed marker predicate. - #165/#169: `poll_failures` row is the failure state; the pass remembers a Site-reported completion. - #166/#171: two new admin filters (`failing`, `unverified`); outbound owner notification + stall condition. - #167/#170: a failure names itself on the Series page; the completion hint reaches the owner and decides nothing. - #172: the other three fault conditions (no-browser-route, sidecar-down, adapter-broken) feeding the notifier. - #173: the landing verdict line shares the same `latest.FaultsFrom` judgement the notifier uses, so the page and the push cannot disagree. `cd backend && go test ./...` green on the merged branch (8 packages). Reviewed-on: #174 Co-authored-by: Sulthan Zaki <sultankiki05@gmail.com> Co-committed-by: Sulthan Zaki <sultankiki05@gmail.com>
2026-08-23 11:31:10 +07:00
parent 8e4fa6448e
commit e93e79c1bb
31 changed files with 3745 additions and 176 deletions
@@ -22,10 +22,10 @@ type latestChapter struct {

 // site answers the fixed questions every series-page read asks of its Site
 // (ADR-0009): the host its addresses must carry, how to find the Latest
-// Chapter and the Cover address in a body, and — for a Site behind a
-// JavaScript challenge — how to read its payload from a cleared tab. One
-// entry describes everything about one Site, and nowhere else gets to compare
-// the site string.
+// Chapter and the Cover address in a body, whether the Site calls the work
+// completed, and — for a Site behind a JavaScript challenge — how to read its
+// payload from a cleared tab. One entry describes everything about one Site,
+// and nowhere else gets to compare the site string.
 type site struct {
 	// Host is the exact hostname a series_url for this Site must carry.
 	Host string
@@ -33,6 +33,10 @@ type site struct {
 	LatestChapter func(seriesURL, body string) (latestChapter, bool)
 	// Cover finds the Cover address in a fetched body.
 	Cover func(seriesURL, body string) (string, bool)
+	// Completed reports whether this body carries the Site's own completed
+	// value. False for a body that carries any other value, and false for a
+	// failed extraction — never an error and never a third state.
+	Completed func(seriesURL, body string) bool
 	// Rest is how long a Series of this Site rests between Polls.
 	Rest time.Duration
 	// Gap is the Lane's strictest pace: at least one second must pass between
@@ -299,34 +303,42 @@ func kaganeCoverURL(body string) string {
 	return ""
 }

-func comixCoverURL(seriesURL, body string) string {
+// comixDetailQuery returns the ["manga","detail","<id>"] query entry of
+// comix's initial-data JSON, or nil. The cover and completed reads share the
+// scoped lookup so a "recommended" strip entry can never contribute either
+// answer.
+func comixDetailQuery(seriesURL, body string) json.RawMessage {
 	id, ok := comixSeriesID(seriesURL)
 	if !ok {
-		return ""
+		return nil
 	}
 	data := comixInitialDataRe.FindStringSubmatch(body)
 	if data == nil {
-		return ""
+		return nil
 	}
 	var state struct {
 		Queries map[string]json.RawMessage `json:"queries"`
 	}
 	if err := json.Unmarshal([]byte(data[1]), &state); err != nil {
+		return nil
+	}
+	return state.Queries[`["manga","detail","`+id+`"]`]
+}
+
+func comixCoverURL(seriesURL, body string) string {
+	detail := comixDetailQuery(seriesURL, body)
+	if len(detail) == 0 {
 		return ""
 	}
-	raw := state.Queries[`["manga","detail","`+id+`"]`]
-	if len(raw) == 0 {
-		return ""
-	}
-	var detail struct {
+	var entry struct {
 		Poster struct {
 			Medium string `json:"medium"`
 		} `json:"poster"`
 	}
-	if err := json.Unmarshal(raw, &detail); err != nil {
+	if err := json.Unmarshal(detail, &entry); err != nil {
 		return ""
 	}
-	return publishedCoverURL(detail.Poster.Medium)
+	return publishedCoverURL(entry.Poster.Medium)
 }

 // ogImageCover reads the og:image metadata shared by asura, demonic and
@@ -360,6 +372,87 @@ func coverFrom(site, seriesURL, body string) (string, bool) {
 	return "", false
 }

+// asuraStatusRe matches the status value inside the escaped astro-island
+// props blob, in both the &quot; form the served document carries and the "
+// form a decoded copy would. "completed" is the only true value: "dropped"
+// is scanlation editorial (the work itself continues elsewhere) and hiatus is
+// its own value.
+var asuraStatusRe = regexp.MustCompile(`(?:&quot;|")status(?:&quot;|"):\[0,(?:&quot;|")completed(?:&quot;|")\]`)
+
+func asuraCompleted(_, body string) bool {
+	return asuraStatusRe.MatchString(body)
+}
+
+// demonicStatusRe matches the info block's status pair: a Status label <li>
+// immediately followed by the value <li>. The site's whole status vocabulary
+// is {Ongoing, Completed} (its advanced-search status filter), so the literal
+// Completed value is the entire signal.
+var demonicStatusRe = regexp.MustCompile(`<li[^>]*>\s*Status\s*</li>\s*<li[^>]*>\s*Completed\s*</li>`)
+
+func demonicCompleted(_, body string) bool {
+	return demonicStatusRe.MatchString(body)
+}
+
+// comixCompleted reads "status" from the scoped detail entry only;
+// "finished" is the completed value, and on_hiatus and discontinued are
+// distinct values.
+func comixCompleted(seriesURL, body string) bool {
+	detail := comixDetailQuery(seriesURL, body)
+	if len(detail) == 0 {
+		return false
+	}
+	var entry struct {
+		Status string `json:"status"`
+	}
+	if err := json.Unmarshal(detail, &entry); err != nil {
+		return false
+	}
+	return entry.Status == "finished"
+}
+
+// kaganeCompleted reads publication_status only: upload_status is the
+// release's state, and the two provably diverge ('Cause Calypso Can,
+// 2026-08-19: publication Ongoing, upload Hiatus), so a Completed upload
+// must never read as a Completed work.
+func kaganeCompleted(_, body string) bool {
+	var series struct {
+		PublicationStatus string `json:"publication_status"`
+	}
+	if err := json.Unmarshal([]byte(body), &series); err != nil {
+		return false
+	}
+	return series.PublicationStatus == "Completed"
+}
+
+// novelfullStatusRe matches the info panel's status link. The page's whole
+// status vocabulary is {Ongoing, Completed} (the "OnGoing" spelling aliases
+// "Ongoing" on the taxonomy), so the Completed href is the signal.
+var novelfullStatusRe = regexp.MustCompile(`href="/status/Completed"`)
+
+func novelfullCompleted(_, body string) bool {
+	return novelfullStatusRe.MatchString(body)
+}
+
+// lnwCompleted matches creativeWorkStatus in the head's JSON-LD block. The
+// whole body is scanned and the comment marker is not required, unlike
+// lnwLatestChapter: the status block sits ahead of the visitor-writable
+// thread, and hiatus maps to a distinct PotentialActionStatus value.
+var lnwStatusRe = regexp.MustCompile(`"creativeWorkStatus"\s*:\s*"https://schema\.org/CompletedActionStatus"`)
+
+func lnwCompleted(_, body string) bool {
+	return lnwStatusRe.MatchString(body)
+}
+
+// siteCompletedFrom reports whether the Site calls this work completed, via
+// the Site's registry entry. False for an unknown site, a challenge body and
+// a redesign alike: an absent hint, never a claim.
+func siteCompletedFrom(site, seriesURL, body string) bool {
+	if fn := sites[site].Completed; fn != nil {
+		return fn(seriesURL, body)
+	}
+	return false
+}
+
 // metaContent returns the content of the first <meta> whose attrName is
 // attrValue. It keeps scanning after an empty match so a later published cover
 // is not hidden by an empty tag.
@@ -449,6 +542,7 @@ var sites = map[string]site{
 		Host:          "asurascans.com",
 		LatestChapter: asuraLatestChapter,
 		Cover:         ogImageCover,
+		Completed:     asuraCompleted,
 		Rest:          defaultRest,
 		Gap:           defaultGap,
 	},
@@ -456,6 +550,7 @@ var sites = map[string]site{
 		Host:          "demonicscans.org",
 		LatestChapter: demonicLatestChapter,
 		Cover:         ogImageCover,
+		Completed:     demonicCompleted,
 		Rest:          defaultRest,
 		Gap:           defaultGap,
 	},
@@ -463,6 +558,7 @@ var sites = map[string]site{
 		Host:          "comix.to",
 		LatestChapter: comixLatestChapter,
 		Cover:         comixCoverEntry,
+		Completed:     comixCompleted,
 		Rest:          defaultRest,
 		Gap:           defaultGap,
 		Browser: &browserRead{
@@ -479,6 +575,7 @@ var sites = map[string]site{
 		Host:          "kagane.to",
 		LatestChapter: kaganeLatestChapter,
 		Cover:         kaganeCoverEntry,
+		Completed:     kaganeCompleted,
 		Rest:          defaultRest,
 		Gap:           defaultGap,
 		Browser: &browserRead{
@@ -493,6 +590,7 @@ var sites = map[string]site{
 		Host:          "novelfull.com",
 		LatestChapter: novelfullLatestChapter,
 		Cover:         novelfullCoverEntry,
+		Completed:     novelfullCompleted,
 		Rest:          defaultRest,
 		Gap:           defaultGap,
 		Browser: &browserRead{
@@ -507,6 +605,7 @@ var sites = map[string]site{
 		Host:          "lightnovelworld.net",
 		LatestChapter: lnwLatestChapter,
 		Cover:         ogImageCover,
+		Completed:     lnwCompleted,
 		Rest:          defaultRest,
 		Gap:           defaultGap,
 	},
@@ -524,6 +623,12 @@ func SiteNames() []string {
 	return names
 }

+// BrowserBackedSites is derived from the registry: the Sites whose pages are
+// read through the browser sidecar. Sorted so callers that range it (the
+// browser fetcher's dispatch) see a stable order instead of map-iteration
+// noise. Exported so the web layer shares the same set the poller does.
+func BrowserBackedSites() []string { return browserBackedSites() }
+
 // browserBackedSites is derived from the registry: the Sites whose pages are
 // read through the browser sidecar. Sorted so callers that range it (the
 // browser fetcher's dispatch) see a stable order instead of map-iteration