compass_teams_nhs/internal/parse/news.go

package parse

import (
	"fmt"
	"strings"
	"time"
)

// newsTimeLayout is the aria-label format on the feed timestamp, for example
// "14/10/2026 09:00 AM".
const newsTimeLayout = "02/01/2006 03:04 PM"

// parseNews parses the home-page news feed into message items. It fails loudly
// when the page carries neither the feed toolbar nor a post, so a login or
// challenge page is never mistaken for "no news" (FR-12).
func parseNews(child string, page Page, loc *time.Location) ([]Item, error) {
	items, found, err := extractNews(child, page, loc)
	if err != nil {
		return nil, err
	}
	if !found {
		return nil, fmt.Errorf("parse: %s: no news feed or posts found in %s (layout changed or fetch failed)", child, page.Slug)
	}
	return items, nil
}

// extractNews returns news posts from the home page. found reports whether the
// feed was present at all.
func extractNews(child string, page Page, loc *time.Location) (items []Item, found bool, err error) {
	root := parseHTML(page.HTML)

	toolbar := find(root, func(n *node) bool {
		return strings.EqualFold(n.Attrs["data-testid"], "feed-toolbar")
	})
	cards := findAll(root, func(n *node) bool { return n.hasClass("MuiCardContent-root") })
	found = toolbar != nil || len(cards) > 0
	if !found {
		return nil, false, nil
	}

	for _, card := range cards {
		titleNode := find(card, func(n *node) bool { return n.hasClassPart("postTitle") })
		if titleNode == nil {
			continue // not a news post
		}
		title := collapse(titleNode.Text())
		if title == "" {
			continue
		}

		var body string
		if b := find(card, func(n *node) bool { return n.hasClassPart("froala-viewer") }); b != nil {
			body = b.Text()
		}

		var author string
		if a := find(card, func(n *node) bool { return n.hasClassPart("MuiTypography-dialogMdStrong") }); a != nil {
			author = collapse(a.Text())
		}

		var posted *time.Time
		if t := find(card, func(n *node) bool {
			return n.hasClassPart("MuiTypography-dialogSmStrong") && n.hasAttr("aria-label")
		}); t != nil {
			raw := strings.TrimSpace(t.Attrs["aria-label"])
			parsed, perr := time.ParseInLocation(newsTimeLayout, raw, loc)
			if perr != nil {
				return nil, false, fmt.Errorf("parse: %s: news %q: unrecognised posted time %q", page.Slug, title, raw)
			}
			posted = &parsed
		}

		pageURL := page.URL
		if pageURL == "" {
			pageURL = compassHost + "/"
		}
		ref := dedupeKey(author, title, relativeOrISO(posted))

		items = append(items, Item{
			Child:       child,
			Source:      SourceCompass,
			Type:        TypeMessage,
			Teacher:     author, // messages carry the author, not a teacher
			Title:       title,
			Body:        body,
			DueAt:       posted,
			URL:         pageURL,
			SourcePage:  page.Slug,
			ExternalRef: ref,
			Importance:  importanceNormal,
		})
	}
	return items, true, nil
}

// relativeOrISO renders a posted time for the dedupe key.
func relativeOrISO(t *time.Time) string {
	if t == nil {
		return ""
	}
	return t.Format(time.RFC3339)
}