spark-server/internal/module/squarebot/logic/rss.go

package logic

import (
	"context"
	"encoding/xml"
	"fmt"
	"html"
	"io"
	"net/http"
	"net/url"
	"regexp"
	"strings"
	"time"
	"unicode/utf8"
)

const (
	rssMaxBody  = 2 << 20
	rssTimeout  = 20 * time.Second
	summaryRunes = 280
)

// FeedItem is one public RSS/Atom entry (title + summary + link).
type FeedItem struct {
	Title   string
	Summary string
	Link    string
	Source  string
}

type rssFeed struct {
	Channel struct {
		Title string    `xml:"title"`
		Items []rssItem `xml:"item"`
	} `xml:"channel"`
}

type rssItem struct {
	Title       string `xml:"title"`
	Link        string `xml:"link"`
	Description string `xml:"description"`
	GUID        string `xml:"guid"`
}

type atomFeed struct {
	Title   string      `xml:"title"`
	Entries []atomEntry `xml:"entry"`
}

type atomEntry struct {
	Title   string     `xml:"title"`
	Summary string     `xml:"summary"`
	Content string     `xml:"content"`
	Links   []atomLink `xml:"link"`
	ID      string     `xml:"id"`
}

type atomLink struct {
	Href string `xml:"href,attr"`
	Rel  string `xml:"rel,attr"`
}

var tagRe = regexp.MustCompile(`(?s)<[^>]*>`)

// FetchFeed loads and parses a public RSS 2.0 or Atom URL.
func FetchFeed(ctx context.Context, client *http.Client, feedURL string) ([]FeedItem, error) {
	feedURL = strings.TrimSpace(feedURL)
	if feedURL == "" {
		return nil, fmt.Errorf("empty feed url")
	}
	if client == nil {
		client = &http.Client{Timeout: rssTimeout}
	}
	req, err := http.NewRequestWithContext(ctx, http.MethodGet, feedURL, nil)
	if err != nil {
		return nil, err
	}
	req.Header.Set("User-Agent", "SparkIM-SquareBot/1.0 (+https://spark.wyrs365.com)")
	req.Header.Set("Accept", "application/rss+xml, application/atom+xml, application/xml, text/xml, */*")
	resp, err := client.Do(req)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()
	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
		return nil, fmt.Errorf("feed status %d", resp.StatusCode)
	}
	body, err := io.ReadAll(io.LimitReader(resp.Body, rssMaxBody))
	if err != nil {
		return nil, err
	}
	return parseFeed(body, feedURL)
}

func parseFeed(body []byte, feedURL string) ([]FeedItem, error) {
	var rss rssFeed
	if err := xml.Unmarshal(body, &rss); err == nil && len(rss.Channel.Items) > 0 {
		src := strings.TrimSpace(rss.Channel.Title)
		out := make([]FeedItem, 0, len(rss.Channel.Items))
		for _, it := range rss.Channel.Items {
			link := firstNonEmpty(strings.TrimSpace(it.Link), strings.TrimSpace(it.GUID))
			item := FeedItem{
				Title:   cleanText(it.Title),
				Summary: cleanText(it.Description),
				Link:    normalizeURL(link),
				Source:  src,
			}
			if item.Title == "" || item.Link == "" {
				continue
			}
			out = append(out, item)
		}
		if len(out) > 0 {
			return out, nil
		}
	}
	var atom atomFeed
	if err := xml.Unmarshal(body, &atom); err != nil {
		return nil, fmt.Errorf("parse feed %s: %w", feedURL, err)
	}
	src := cleanText(atom.Title)
	out := make([]FeedItem, 0, len(atom.Entries))
	for _, e := range atom.Entries {
		link := atomBestLink(e.Links)
		if link == "" {
			link = strings.TrimSpace(e.ID)
		}
		sum := firstNonEmpty(e.Summary, e.Content)
		item := FeedItem{
			Title:   cleanText(e.Title),
			Summary: cleanText(sum),
			Link:    normalizeURL(link),
			Source:  src,
		}
		if item.Title == "" || item.Link == "" {
			continue
		}
		out = append(out, item)
	}
	if len(out) == 0 {
		return nil, fmt.Errorf("empty feed %s", feedURL)
	}
	return out, nil
}

func atomBestLink(links []atomLink) string {
	var alt, self, any string
	for _, l := range links {
		href := strings.TrimSpace(l.Href)
		if href == "" {
			continue
		}
		any = href
		switch strings.ToLower(strings.TrimSpace(l.Rel)) {
		case "", "alternate":
			if alt == "" {
				alt = href
			}
		case "self":
			if self == "" {
				self = href
			}
		}
	}
	return firstNonEmpty(alt, self, any)
}

func FormatPostText(item FeedItem) string {
	title := strings.TrimSpace(item.Title)
	sum := truncateRunes(strings.TrimSpace(item.Summary), summaryRunes)
	link := strings.TrimSpace(item.Link)
	src := strings.TrimSpace(item.Source)
	var b strings.Builder
	if src != "" {
		b.WriteString(src)
		b.WriteString("\n")
	}
	b.WriteString(title)
	if sum != "" && !strings.EqualFold(sum, title) {
		b.WriteString("\n\n")
		b.WriteString(sum)
	}
	b.WriteString("\n\n")
	b.WriteString(link)
	text := strings.TrimSpace(b.String())
	return truncateRunes(text, 1000)
}

func cleanText(s string) string {
	s = html.UnescapeString(s)
	s = tagRe.ReplaceAllString(s, " ")
	s = strings.Join(strings.Fields(s), " ")
	return strings.TrimSpace(s)
}

func truncateRunes(s string, max int) string {
	if max <= 0 || utf8.RuneCountInString(s) <= max {
		return s
	}
	runes := []rune(s)
	return string(runes[:max-1]) + "…"
}

func normalizeURL(raw string) string {
	raw = strings.TrimSpace(raw)
	if raw == "" {
		return ""
	}
	u, err := url.Parse(raw)
	if err != nil || u.Scheme == "" || u.Host == "" {
		return ""
	}
	scheme := strings.ToLower(u.Scheme)
	if scheme != "http" && scheme != "https" {
		return ""
	}
	u.Fragment = ""
	return u.String()
}

func firstNonEmpty(vals ...string) string {
	for _, v := range vals {
		if strings.TrimSpace(v) != "" {
			return strings.TrimSpace(v)
		}
	}
	return ""
}