compass_teams_nhs/internal/parse/calendar.go

package parse

import (
	"fmt"
	"regexp"
	"strconv"
	"strings"
	"time"
)

// calendarPxPerHour is the Compass week-grid scale: the day gutter is 1200px
// tall for 24 hours, so 50px is one hour. The event's top offset is therefore
// the authoritative hour; the printed "6:00" prefix is 12-hour and ambiguous.
const calendarPxPerHour = 50.0

var (
	// calendarDayCol matches the day column id, for example
	// calendar-manager-week-bd-day-col-20261016.
	calendarDayCol = regexp.MustCompile(`calendar-manager-week-bd-day-col-(\d{8})`)
	// calendarTop matches the top offset in an event's inline style.
	calendarTop = regexp.MustCompile(`top:\s*([0-9.]+)px`)
	// clockPrefix matches the leading "8:55: " of an event label.
	clockPrefix = regexp.MustCompile(`^(\d{1,2}):(\d{2}):\s*(.*)$`)
	// periodLabel matches the period part of a lesson label: "5", "C" or
	// "RLE GROUP D".
	periodLabel = regexp.MustCompile(`^(\d{1,2}|[A-Z]|RLE GROUP [A-Z])$`)
)

// parseCalendar parses the week calendar into event items. It fails loudly when
// the page has no calendar grid (FR-12).
func parseCalendar(child string, page Page, loc *time.Location) ([]Item, error) {
	items, found, err := extractCalendar(child, page, loc)
	if err != nil {
		return nil, err
	}
	if !found {
		return nil, fmt.Errorf("parse: %s: no calendar grid found in %s (layout changed or fetch failed)", child, page.Slug)
	}
	return items, nil
}

// extractCalendar returns the calendar events in one page. found reports whether
// the page carried a week grid at all.
func extractCalendar(child string, page Page, loc *time.Location) (items []Item, found bool, err error) {
	root := parseHTML(page.HTML)

	dayCols := findAll(root, func(n *node) bool {
		return n.Tag == "div" && calendarDayCol.MatchString(n.Attrs["id"])
	})
	events := findAll(root, func(n *node) bool {
		return n.Tag == "div" && n.hasClassPart("calendar-manager-week-bd-evt-")
	})
	found = len(dayCols) > 0 || len(events) > 0
	if !found {
		return nil, false, nil
	}

	for _, ev := range events {
		it, ok, err := eventItem(child, ev, page, loc)
		if err != nil {
			return nil, false, err
		}
		if ok {
			items = append(items, it)
		}
	}
	return items, true, nil
}

func eventItem(child string, ev *node, page Page, loc *time.Location) (Item, bool, error) {
	labelSpan := find(ev, func(n *node) bool { return n.hasClass("ext-evt-bd") })
	if labelSpan == nil {
		return Item{}, false, nil // not an event body
	}
	label := collapse(labelSpan.Text())
	if label == "" {
		return Item{}, false, nil
	}

	day := nearest(ev, func(n *node) bool {
		return n.Tag == "div" && calendarDayCol.MatchString(n.Attrs["id"])
	})
	if day == nil {
		return Item{}, false, fmt.Errorf("parse: %s: event %q has no day column", page.Slug, label)
	}
	m := calendarDayCol.FindStringSubmatch(day.Attrs["id"])
	date, err := time.ParseInLocation("20060102", m[1], loc)
	if err != nil {
		return Item{}, false, fmt.Errorf("parse: %s: event %q: bad day column %q", page.Slug, label, day.Attrs["id"])
	}

	topMatch := calendarTop.FindStringSubmatch(ev.Attrs["style"])
	if topMatch == nil {
		return Item{}, false, fmt.Errorf("parse: %s: event %q has no top offset", page.Slug, label)
	}
	topPx, err := strconv.ParseFloat(topMatch[1], 64)
	if err != nil {
		return Item{}, false, fmt.Errorf("parse: %s: event %q: bad top offset %q", page.Slug, label, topMatch[1])
	}

	// The hour comes from the grid offset; the minutes come from the label.
	hour := int(topPx / calendarPxPerHour)
	minute := 0
	title := label
	if cm := clockPrefix.FindStringSubmatch(label); cm != nil {
		if v, err := strconv.Atoi(cm[2]); err == nil {
			minute = v
		}
		title = strings.TrimSpace(cm[3])
	}
	if hour < 0 || hour > 23 || minute < 0 || minute > 59 {
		return Item{}, false, fmt.Errorf("parse: %s: event %q: bad time %02d:%02d", page.Slug, label, hour, minute)
	}
	at := time.Date(date.Year(), date.Month(), date.Day(), hour, minute, 0, 0, loc)

	subject, teacher, body := splitEvent(label, title)

	url := page.URL
	if url == "" {
		url = compassHost + "/Organise/Calendar/"
	}

	return Item{
		Child:       child,
		Source:      SourceCompass,
		Type:        TypeEvent,
		Subject:     subject,
		Teacher:     teacher,
		Title:       title,
		Body:        body,
		DueAt:       &at,
		URL:         url,
		SourcePage:  page.Slug,
		ExternalRef: dedupeKey(at.Format(time.RFC3339), title),
		Importance:  importanceNormal,
	}, true, nil
}

// splitEvent breaks a calendar label into subject, teacher and body. A lesson
// label is "5 - 11HLEGB5 - D8 - LHT"; a school event is
// "End of Year Senior Music Concert - HALL (...) - KSH, CFR, ...".
func splitEvent(label, title string) (subject, teacher, body string) {
	parts := splitDash(title)
	if len(parts) >= 2 && periodLabel.MatchString(parts[0]) {
		for _, p := range parts[1:] {
			if subject == "" && classCode.MatchString(p) {
				subject = p
			}
		}
		if !classCode.MatchString(parts[0]) {
			teacher = parts[len(parts)-1]
		}
	}
	body = label
	if teacher != "" {
		body = label + "\nTeacher(s): " + teacher
	}
	return subject, teacher, body
}

// splitDash splits on " - " and trims each part.
func splitDash(s string) []string {
	raw := strings.Split(s, " - ")
	out := make([]string, 0, len(raw))
	for _, p := range raw {
		out = append(out, strings.TrimSpace(p))
	}
	return out
}