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",