Finalize SPC outlook feature addition and clean up implemented roadmap documentation

internal/providers/spc/discussion.go

@@ -13,6 +13,8 @@ var (
 	preBlockRE    = regexp.MustCompile(`(?is)<pre\b[^>]*>(.*?)</pre>`)
 	tagRE         = regexp.MustCompile(`(?is)<[^>]+>`)
 	updatedRE     = regexp.MustCompile(`(?im)^\s*Updated:\s*(.+?)\s*$`)
+	pageUpdatedRE = regexp.MustCompile(`(?i)\bUpdated:\s*((?:\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z)|(?:[A-Z][a-z]{2}\s+[A-Z][a-z]{2}\s+\d{1,2}\s+\d{2}:\d{2}:\d{2}\s+UTC\s+\d{4})|(?:\d{4}\s+UTC\s+[A-Z][a-z]{2}\s+[A-Z][a-z]{2}\s+\d{1,2}\s+\d{4})|(?:\d{4}Z\s+[A-Z][a-z]{2}\s+[A-Z][a-z]{2}\s+\d{1,2}\s+\d{4}))`)
+	productCodeRE = regexp.MustCompile(`(?i)^SPC\s+AC\s+\d+\s*$`)
 	sectionRE     = regexp.MustCompile(`^\s*\.\.\.[A-Z0-9 /-]+\.{3}\s*$`)
 )
 
@@ -41,6 +43,20 @@ func ExtractProductText(rawHTML string) (string, error) {
 	return "", fmt.Errorf("no useful pre block found")
 }
 
+// ParseDiscussionHTML extracts SPC product text and page-level metadata from a
+// print-page HTML document.
+func ParseDiscussionHTML(rawHTML string) (DiscussionText, error) {
+	text, err := ExtractProductText(rawHTML)
+	if err != nil {
+		return DiscussionText{}, err
+	}
+	parsed := ParseDiscussionText(text)
+	if updatedAt := ParsePageUpdatedTimestamp(rawHTML); updatedAt != nil {
+		parsed.UpdatedAt = updatedAt
+	}
+	return parsed, nil
+}
+
 // ParseDiscussionText extracts common SPC narrative metadata from cleaned
 // product text.
 func ParseDiscussionText(text string) DiscussionText {
@@ -55,6 +71,19 @@ func ParseDiscussionText(text string) DiscussionText {
 	}
 }
 
+// ParsePageUpdatedTimestamp parses the page-level Updated row from an SPC print
+// page. SPC currently places this outside the product <pre> block.
+func ParsePageUpdatedTimestamp(rawHTML string) *time.Time {
+	text := cleanHTMLText(rawHTML)
+	text = strings.ReplaceAll(text, "\u00a0", " ")
+	text = strings.Join(strings.Fields(text), " ")
+	match := pageUpdatedRE.FindStringSubmatch(text)
+	if len(match) != 2 {
+		return nil
+	}
+	return parseUpdatedValue(match[1])
+}
+
 // ParseUpdatedTimestamp parses an SPC print-page Updated line when present.
 func ParseUpdatedTimestamp(text string) *time.Time {
 	match := updatedRE.FindStringSubmatch(normalizeNewlines(text))
@@ -68,7 +97,7 @@ func ParseUpdatedTimestamp(text string) *time.Time {
 func ParseProductTitle(text string) string {
 	for _, line := range strings.Split(normalizeNewlines(text), "\n") {
 		line = strings.TrimSpace(line)
-		if line == "" || strings.HasPrefix(line, "Updated:") {
+		if line == "" || strings.HasPrefix(line, "Updated:") || productCodeRE.MatchString(line) {
 			continue
 		}
 		return line
@@ -142,6 +171,7 @@ func parseUpdatedValue(value string) *time.Time {
 		return t
 	}
 	for _, layout := range []string{
+		"Mon Jan 2 15:04:05 UTC 2006",
 		"1504 UTC Mon Jan 2 2006",
 		"1504Z Mon Jan 2 2006",
 		"3:04 PM UTC Mon Jan 2 2006",

internal/providers/spc/discussion_test.go

@@ -22,18 +22,19 @@ func TestExtractProductTextCleansPreBlock(t *testing.T) {
 	if !strings.Contains(got, "Day 1 Convective Outlook") {
 		t.Fatalf("ExtractProductText() missing headline: %q", got)
 	}
+	if !strings.HasPrefix(got, "SPC AC 111234") {
+		t.Fatalf("ExtractProductText() = %q, want product code prefix", got)
+	}
 	if strings.HasPrefix(got, "\n") || strings.HasSuffix(got, "\n") {
 		t.Fatalf("ExtractProductText() retained surrounding blank lines: %q", got)
 	}
 }
 
-func TestParseDiscussionTextExtractsHeadlineSummaryAndUpdated(t *testing.T) {
-	text, err := ExtractProductText(string(readTestFile(t, "day1_prt.html")))
+func TestParseDiscussionHTMLExtractsHeadlineSummaryAndUpdated(t *testing.T) {
+	got, err := ParseDiscussionHTML(string(readTestFile(t, "day1_prt.html")))
 	if err != nil {
-		t.Fatalf("ExtractProductText() error = %v", err)
+		t.Fatalf("ParseDiscussionHTML() error = %v", err)
 	}
-
-	got := ParseDiscussionText(text)
 	if got.ProductTitle != "Day 1 Convective Outlook" {
 		t.Fatalf("ProductTitle = %q", got.ProductTitle)
 	}
@@ -47,27 +48,37 @@ func TestParseDiscussionTextExtractsHeadlineSummaryAndUpdated(t *testing.T) {
 	if !strings.Contains(got.Discussion, "...DISCUSSION...") {
 		t.Fatalf("Discussion missing full text: %q", got.Discussion)
 	}
+	if !strings.HasPrefix(got.Discussion, "SPC AC 111234") {
+		t.Fatalf("Discussion = %q, want product code prefix", got.Discussion)
+	}
 	wantUpdated := time.Date(2026, 6, 11, 12, 45, 0, 0, time.UTC)
 	if got.UpdatedAt == nil || !got.UpdatedAt.Equal(wantUpdated) {
 		t.Fatalf("UpdatedAt = %v, want %s", got.UpdatedAt, wantUpdated)
 	}
 }
 
+func TestParseProductTitleSkipsSPCProductCode(t *testing.T) {
+	got := ParseProductTitle("SPC AC 101959\nDay 1 Convective Outlook\nNWS Storm Prediction Center Norman OK")
+	if got != "Day 1 Convective Outlook" {
+		t.Fatalf("ParseProductTitle() = %q, want Day 1 Convective Outlook", got)
+	}
+}
+
 func TestParseDiscussionTextPreservesCorrectionMarker(t *testing.T) {
-	text, err := ExtractProductText(string(readTestFile(t, "day2_prt_corr.html")))
+	got, err := ParseDiscussionHTML(string(readTestFile(t, "day2_prt_corr.html")))
 	if err != nil {
-		t.Fatalf("ExtractProductText() error = %v", err)
+		t.Fatalf("ParseDiscussionHTML() error = %v", err)
 	}
 
-	got := ParseDiscussionText(text)
 	if !strings.Contains(got.Headline, "CORR 1") {
 		t.Fatalf("Headline = %q, want correction marker", got.Headline)
 	}
 	if !strings.Contains(got.Discussion, "CORR 1") {
 		t.Fatalf("Discussion = %q, want correction marker", got.Discussion)
 	}
-	if got.UpdatedAt != nil {
-		t.Fatalf("UpdatedAt = %v, want nil", got.UpdatedAt)
+	wantUpdated := time.Date(2026, 6, 11, 17, 30, 0, 0, time.UTC)
+	if got.UpdatedAt == nil || !got.UpdatedAt.Equal(wantUpdated) {
+		t.Fatalf("UpdatedAt = %v, want %s", got.UpdatedAt, wantUpdated)
 	}
 }
 
@@ -88,3 +99,11 @@ func TestParseUpdatedTimestampAcceptsSPCUTCFormat(t *testing.T) {
 		t.Fatalf("ParseUpdatedTimestamp() = %v, want %s", got, want)
 	}
 }
+
+func TestParsePageUpdatedTimestampAcceptsLiveSPCShape(t *testing.T) {
+	got := ParsePageUpdatedTimestamp(string(readTestFile(t, "day3_prt.html")))
+	want := time.Date(2026, 6, 11, 20, 0, 0, 0, time.UTC)
+	if got == nil || !got.Equal(want) {
+		t.Fatalf("ParsePageUpdatedTimestamp() = %v, want %s", got, want)
+	}
+}

internal/providers/spc/testdata/day1_prt.html

@@ -2,11 +2,14 @@
 <html>
 <head><title>Day 1 Convective Outlook</title></head>
 <body>
+<table>
+<tr><td align="center" class="rpttext" nowrap>Updated:&nbsp;Thu Jun 11 12:45:00 UTC 2026&nbsp;(<a href="archive/day1-geojson.zip">geojson</a>)</td></tr>
+</table>
 <pre>
 <script>window.bad = "<b>ignore me</b>";</script>
+SPC AC 111234
 Day 1 Convective Outlook
 NWS Storm Prediction Center Norman OK
-Updated: 2026-06-11T12:45:00Z
 
 ...SUMMARY...
 Severe thunderstorms are possible across parts of the central Plains

internal/providers/spc/testdata/day2_prt_corr.html

@@ -1,7 +1,11 @@
 <!doctype html>
 <html>
 <body>
+<table>
+<tr><td class="rpttext">Updated:&nbsp;Thu Jun 11 17:30:00 UTC 2026&nbsp;</td></tr>
+</table>
 <pre>
+SPC AC 111730
 Day 2 Convective Outlook CORR 1
 NWS Storm Prediction Center Norman OK
 

internal/providers/spc/testdata/day3_prt.html

@@ -1,10 +1,13 @@
 <!doctype html>
 <html>
 <body>
+<table>
+<tr><td class="rpttext">Updated:&nbsp;Thu Jun 11 20:00:00 UTC 2026&nbsp;</td></tr>
+</table>
 <pre>
+SPC AC 112000
 Day 3 Convective Outlook
 NWS Storm Prediction Center Norman OK
-Updated: 2026-06-11T20:00:00Z
 
 ...SUMMARY...
 A corridor of strong to severe storms may develop near a frontal zone.