Add paddock briefing RSS backend spike

This commit is contained in:
2026-05-25 12:02:18 -04:00
parent 79b0b9f469
commit 84a8827244
12 changed files with 804 additions and 2 deletions

260
internal/news/news.go Normal file
View File

@@ -0,0 +1,260 @@
package news
import (
"context"
"encoding/xml"
"fmt"
"io"
"net/http"
"net/url"
"sort"
"strings"
"time"
)
const UserAgent = "box-box/phase-19b-rss-spike"
// Source describes a feed that can be fetched and normalized.
type Source struct {
ID string
Name string
URL string
Category string
}
// Item is the normalized shape consumed by storage and API layers.
type Item struct {
Source string
Title string
URL string
PublishedAt time.Time
Summary string
Category string
FetchedAt time.Time
}
// DefaultSources are free RSS/Atom feeds worth using for the Paddock Briefing spike.
var DefaultSources = []Source{
{ID: "fia", Name: "FIA", URL: "https://www.fia.com/rss/news", Category: "official"},
{ID: "bbc-f1", Name: "BBC Sport F1", URL: "https://feeds.bbci.co.uk/sport/formula1", Category: "news"},
{ID: "autosport-f1", Name: "Autosport F1", URL: "https://www.autosport.com/rss/f1/news/", Category: "news"},
{ID: "racefans-f1", Name: "RaceFans F1", URL: "https://www.racefans.net/category/f1-news/feed/", Category: "news"},
{ID: "guardian-f1", Name: "Guardian Formula One", URL: "https://www.theguardian.com/sport/formulaone/rss", Category: "news"},
{ID: "racer-f1", Name: "RACER F1", URL: "https://racer.com/f1/feed", Category: "news"},
{ID: "f1-youtube", Name: "Formula 1 YouTube", URL: "https://www.youtube.com/feeds/videos.xml?channel_id=UCB_qr75-ydFVKSF9Dmo6izg", Category: "video"},
}
// Fetch retrieves and parses one RSS or Atom feed with the provided HTTP client.
func Fetch(ctx context.Context, client *http.Client, source Source) ([]Item, error) {
if client == nil {
client = &http.Client{Timeout: 10 * time.Second}
}
req, err := http.NewRequestWithContext(ctx, http.MethodGet, source.URL, nil)
if err != nil {
return nil, err
}
req.Header.Set("User-Agent", UserAgent)
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("fetch %s: status %d", source.ID, resp.StatusCode)
}
return Parse(source, resp.Body, time.Now().UTC())
}
// Parse normalizes RSS 2.0 or Atom XML into Items.
func Parse(source Source, r io.Reader, fetchedAt time.Time) ([]Item, error) {
payload, err := io.ReadAll(io.LimitReader(r, 2<<20))
if err != nil {
return nil, err
}
var rss rssFeed
if err := xml.Unmarshal(payload, &rss); err == nil && len(rss.Channel.Items) > 0 {
return normalizeRSS(source, rss.Channel.Items, fetchedAt), nil
}
var atom atomFeed
if err := xml.Unmarshal(payload, &atom); err != nil {
return nil, err
}
if len(atom.Entries) == 0 {
return nil, fmt.Errorf("parse %s: no RSS items or Atom entries found", source.ID)
}
return normalizeAtom(source, atom.Entries, fetchedAt), nil
}
// DeduplicateByURL keeps the newest instance of each canonical URL.
func DeduplicateByURL(items []Item) []Item {
byURL := make(map[string]Item, len(items))
for _, item := range items {
key := canonicalURL(item.URL)
if key == "" {
continue
}
item.URL = key
if existing, ok := byURL[key]; !ok || item.PublishedAt.After(existing.PublishedAt) {
byURL[key] = item
}
}
out := make([]Item, 0, len(byURL))
for _, item := range byURL {
out = append(out, item)
}
sort.Slice(out, func(i, j int) bool {
return out[i].PublishedAt.After(out[j].PublishedAt)
})
return out
}
type rssFeed struct {
Channel struct {
Items []rssItem `xml:"item"`
} `xml:"channel"`
}
type rssItem struct {
Title string `xml:"title"`
Link string `xml:"link"`
GUID string `xml:"guid"`
PubDate string `xml:"pubDate"`
Description string `xml:"description"`
Categories []string `xml:"category"`
}
type atomFeed struct {
Entries []atomEntry `xml:"entry"`
}
type atomEntry struct {
Title string `xml:"title"`
ID string `xml:"id"`
Updated string `xml:"updated"`
Published string `xml:"published"`
Summary string `xml:"summary"`
Content string `xml:"content"`
Links []atomLink `xml:"link"`
Categories []struct {
Term string `xml:"term,attr"`
Label string `xml:"label,attr"`
} `xml:"category"`
}
type atomLink struct {
Href string `xml:"href,attr"`
Rel string `xml:"rel,attr"`
}
func normalizeRSS(source Source, raw []rssItem, fetchedAt time.Time) []Item {
items := make([]Item, 0, len(raw))
for _, entry := range raw {
link := strings.TrimSpace(entry.Link)
if link == "" {
link = strings.TrimSpace(entry.GUID)
}
items = append(items, Item{
Source: source.ID,
Title: cleanText(entry.Title),
URL: link,
PublishedAt: parseFeedTime(entry.PubDate),
Summary: cleanText(entry.Description),
Category: firstNonEmpty(entry.Categories, source.Category),
FetchedAt: fetchedAt,
})
}
return DeduplicateByURL(items)
}
func normalizeAtom(source Source, raw []atomEntry, fetchedAt time.Time) []Item {
items := make([]Item, 0, len(raw))
for _, entry := range raw {
category := source.Category
if len(entry.Categories) > 0 {
category = firstNonEmpty([]string{entry.Categories[0].Label, entry.Categories[0].Term}, source.Category)
}
items = append(items, Item{
Source: source.ID,
Title: cleanText(entry.Title),
URL: atomEntryURL(entry),
PublishedAt: parseFeedTime(firstNonEmpty([]string{entry.Published, entry.Updated}, "")),
Summary: cleanText(firstNonEmpty([]string{entry.Summary, entry.Content}, "")),
Category: category,
FetchedAt: fetchedAt,
})
}
return DeduplicateByURL(items)
}
func atomEntryURL(entry atomEntry) string {
for _, link := range entry.Links {
if link.Rel == "" || link.Rel == "alternate" {
return strings.TrimSpace(link.Href)
}
}
if len(entry.Links) > 0 {
return strings.TrimSpace(entry.Links[0].Href)
}
return strings.TrimSpace(entry.ID)
}
func parseFeedTime(value string) time.Time {
value = strings.TrimSpace(value)
if value == "" {
return time.Time{}
}
layouts := []string{
time.RFC1123Z,
time.RFC1123,
time.RFC3339,
time.RFC3339Nano,
"Mon, 02 Jan 2006 15:04:05 -0700",
"Mon, 2 Jan 2006 15:04:05 -0700",
}
for _, layout := range layouts {
if ts, err := time.Parse(layout, value); err == nil {
return ts.UTC()
}
}
return time.Time{}
}
func cleanText(value string) string {
value = strings.TrimSpace(value)
value = strings.ReplaceAll(value, "\n", " ")
value = strings.ReplaceAll(value, "\t", " ")
return strings.Join(strings.Fields(value), " ")
}
func firstNonEmpty(values []string, fallback string) string {
for _, value := range values {
if strings.TrimSpace(value) != "" {
return strings.TrimSpace(value)
}
}
return fallback
}
func canonicalURL(raw string) string {
raw = strings.TrimSpace(raw)
if raw == "" {
return ""
}
parsed, err := url.Parse(raw)
if err != nil || parsed.Scheme == "" || parsed.Host == "" {
return raw
}
parsed.Fragment = ""
q := parsed.Query()
for key := range q {
if strings.HasPrefix(strings.ToLower(key), "utm_") {
q.Del(key)
}
}
parsed.RawQuery = q.Encode()
return parsed.String()
}

View File

@@ -0,0 +1,72 @@
package news
import (
"strings"
"testing"
"time"
)
func TestParseRSSDeduplicatesByURL(t *testing.T) {
fixture := `<?xml version="1.0"?>
<rss version="2.0">
<channel>
<item>
<title>First story</title>
<link>https://example.com/f1/story?utm_source=rss</link>
<pubDate>Mon, 25 May 2026 10:00:00 GMT</pubDate>
<description>Latest from the paddock</description>
<category>Formula 1</category>
</item>
<item>
<title>Duplicate story newer</title>
<link>https://example.com/f1/story</link>
<pubDate>Mon, 25 May 2026 11:00:00 GMT</pubDate>
<description>Updated headline</description>
</item>
</channel>
</rss>`
source := Source{ID: "example", Category: "news"}
items, err := Parse(source, strings.NewReader(fixture), time.Unix(100, 0).UTC())
if err != nil {
t.Fatalf("Parse() error = %v", err)
}
if len(items) != 1 {
t.Fatalf("items len = %d, want 1", len(items))
}
if items[0].Title != "Duplicate story newer" {
t.Fatalf("title = %q, want newer duplicate", items[0].Title)
}
if items[0].URL != "https://example.com/f1/story" {
t.Fatalf("url = %q, want canonical URL", items[0].URL)
}
if items[0].PublishedAt.IsZero() {
t.Fatal("PublishedAt was not parsed")
}
}
func TestParseAtom(t *testing.T) {
fixture := `<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<entry>
<title>Formula 1 video</title>
<link rel="alternate" href="https://www.youtube.com/watch?v=abc123"/>
<published>2026-05-25T12:30:00Z</published>
<summary>Highlights from the weekend</summary>
<category term="video"/>
</entry>
</feed>`
source := Source{ID: "f1-youtube", Category: "video"}
items, err := Parse(source, strings.NewReader(fixture), time.Unix(200, 0).UTC())
if err != nil {
t.Fatalf("Parse() error = %v", err)
}
if len(items) != 1 {
t.Fatalf("items len = %d, want 1", len(items))
}
if items[0].Source != "f1-youtube" || items[0].Category != "video" {
t.Fatalf("item = %+v, want source/category preserved", items[0])
}
if items[0].URL != "https://www.youtube.com/watch?v=abc123" {
t.Fatalf("url = %q, want alternate link", items[0].URL)
}
}

51
internal/query/news.go Normal file
View File

@@ -0,0 +1,51 @@
package query
import (
"time"
"github.com/AmanTahiliani/box-box/internal/store"
)
// NewsItem is the frontend-facing cached briefing shape.
type NewsItem struct {
Source string `json:"source"`
Title string `json:"title"`
URL string `json:"url"`
PublishedAt *time.Time `json:"published_at,omitempty"`
Summary string `json:"summary,omitempty"`
Category string `json:"category,omitempty"`
FetchedAt time.Time `json:"fetched_at"`
}
// ListNews returns cached briefing items.
func (s *Service) ListNews(limit int, source string) ([]NewsItem, error) {
rows, err := s.store.ListNewsItems(limit, source)
if err != nil {
return nil, err
}
out := make([]NewsItem, 0, len(rows))
for _, row := range rows {
out = append(out, NewsItem{
Source: row.Source,
Title: row.Title,
URL: row.URL,
PublishedAt: row.PublishedAt,
Summary: row.Summary,
Category: row.Category,
FetchedAt: row.FetchedAt,
})
}
return out, nil
}
func NewsItemToStore(item NewsItem) store.NewsItem {
return store.NewsItem{
URL: item.URL,
Source: item.Source,
Title: item.Title,
PublishedAt: item.PublishedAt,
Summary: item.Summary,
Category: item.Category,
FetchedAt: item.FetchedAt,
}
}

View File

@@ -0,0 +1,24 @@
CREATE TABLE IF NOT EXISTS news_sources (
source TEXT PRIMARY KEY,
name TEXT NOT NULL,
feed_url TEXT NOT NULL,
category TEXT,
enabled INTEGER NOT NULL DEFAULT 1,
fetched_at INTEGER,
expires_at INTEGER,
updated_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS news_items (
url TEXT PRIMARY KEY,
source TEXT NOT NULL,
title TEXT NOT NULL,
published_at INTEGER,
summary TEXT,
category TEXT,
fetched_at INTEGER NOT NULL,
FOREIGN KEY (source) REFERENCES news_sources(source)
);
CREATE INDEX IF NOT EXISTS idx_news_items_published ON news_items (published_at DESC);
CREATE INDEX IF NOT EXISTS idx_news_items_source_published ON news_items (source, published_at DESC);

View File

@@ -28,6 +28,29 @@ type IngestionRun struct {
SummaryJSON string
}
// NewsSource stores RSS/Atom feed metadata for local-first briefing reads.
type NewsSource struct {
Source string
Name string
FeedURL string
Category string
Enabled bool
FetchedAt *time.Time
ExpiresAt *time.Time
UpdatedAt time.Time
}
// NewsItem stores a normalized feed item deduplicated by URL.
type NewsItem struct {
URL string
Source string
Title string
PublishedAt *time.Time
Summary string
Category string
FetchedAt time.Time
}
// Meeting is a race weekend record.
type Meeting struct {
MeetingKey int

134
internal/store/news.go Normal file
View File

@@ -0,0 +1,134 @@
package store
import (
"database/sql"
"fmt"
"time"
)
// UpsertNewsSource inserts or updates RSS/Atom feed metadata.
func (s *Store) UpsertNewsSource(src NewsSource) error {
updatedAt := src.UpdatedAt
if updatedAt.IsZero() {
updatedAt = time.Now().UTC()
}
_, err := s.db.Exec(`
INSERT INTO news_sources (
source, name, feed_url, category, enabled, fetched_at, expires_at, updated_at
) VALUES (?, ?, ?, ?, ?, ?, ?, ?)
ON CONFLICT(source) DO UPDATE SET
name = excluded.name,
feed_url = excluded.feed_url,
category = excluded.category,
enabled = excluded.enabled,
fetched_at = excluded.fetched_at,
expires_at = excluded.expires_at,
updated_at = excluded.updated_at
`,
src.Source,
src.Name,
src.FeedURL,
nullString(src.Category),
boolInt(src.Enabled),
nullableTime(src.FetchedAt),
nullableTime(src.ExpiresAt),
updatedAt.Unix(),
)
if err != nil {
return fmt.Errorf("upsert news source: %w", err)
}
return nil
}
// UpsertNewsItem inserts or updates a normalized feed item.
func (s *Store) UpsertNewsItem(item NewsItem) error {
_, err := s.db.Exec(`
INSERT INTO news_items (
url, source, title, published_at, summary, category, fetched_at
) VALUES (?, ?, ?, ?, ?, ?, ?)
ON CONFLICT(url) DO UPDATE SET
source = excluded.source,
title = excluded.title,
published_at = excluded.published_at,
summary = excluded.summary,
category = excluded.category,
fetched_at = excluded.fetched_at
`,
item.URL,
item.Source,
item.Title,
nullableTime(item.PublishedAt),
nullString(item.Summary),
nullString(item.Category),
item.FetchedAt.Unix(),
)
if err != nil {
return fmt.Errorf("upsert news item: %w", err)
}
return nil
}
// ListNewsItems returns newest cached news items, optionally filtered by source.
func (s *Store) ListNewsItems(limit int, source string) ([]NewsItem, error) {
if limit <= 0 || limit > 100 {
limit = 25
}
query := `
SELECT url, source, title, published_at, summary, category, fetched_at
FROM news_items
`
var args []any
if source != "" {
query += ` WHERE source = ?`
args = append(args, source)
}
query += ` ORDER BY COALESCE(published_at, fetched_at) DESC, fetched_at DESC LIMIT ?`
args = append(args, limit)
rows, err := s.db.Query(query, args...)
if err != nil {
return nil, err
}
defer rows.Close()
var out []NewsItem
for rows.Next() {
var item NewsItem
var published sql.NullInt64
var summary, category sql.NullString
var fetched int64
if err := rows.Scan(
&item.URL,
&item.Source,
&item.Title,
&published,
&summary,
&category,
&fetched,
); err != nil {
return nil, err
}
item.PublishedAt = nullTimePtr(published)
item.Summary = summary.String
item.Category = category.String
item.FetchedAt = time.Unix(fetched, 0).UTC()
out = append(out, item)
}
return out, rows.Err()
}
func nullableTime(v *time.Time) any {
if v == nil || v.IsZero() {
return nil
}
return v.Unix()
}
func nullTimePtr(v sql.NullInt64) *time.Time {
if !v.Valid {
return nil
}
t := time.Unix(v.Int64, 0).UTC()
return &t
}

View File

@@ -28,8 +28,8 @@ func TestOpenAppliesMigrations(t *testing.T) {
if err != nil {
t.Fatalf("SchemaVersion() error = %v", err)
}
if version != 2 {
t.Fatalf("SchemaVersion() = %d, want 2", version)
if version != 3 {
t.Fatalf("SchemaVersion() = %d, want 3", version)
}
tables := []string{
@@ -48,6 +48,8 @@ func TestOpenAppliesMigrations(t *testing.T) {
"race_control",
"weather",
"laps",
"news_sources",
"news_items",
}
for _, table := range tables {
var name string
@@ -84,6 +86,12 @@ func TestMigrationsAreIdempotent(t *testing.T) {
if count != 1 {
t.Fatalf("schema_migrations v2 count = %d, want 1", count)
}
if err := s.db.QueryRow(`SELECT COUNT(*) FROM schema_migrations WHERE version = 3`).Scan(&count); err != nil {
t.Fatalf("count schema_migrations v3: %v", err)
}
if count != 1 {
t.Fatalf("schema_migrations v3 count = %d, want 1", count)
}
}
func TestRawPayloadInsertAndRead(t *testing.T) {
@@ -597,6 +605,58 @@ func TestAnalyticsUpsertRead(t *testing.T) {
}
}
func TestNewsUpsertRead(t *testing.T) {
s := openTestStore(t)
now := time.Unix(1800000000, 0).UTC()
expires := now.Add(30 * time.Minute)
if err := s.UpsertNewsSource(NewsSource{
Source: "bbc-f1",
Name: "BBC Sport F1",
FeedURL: "https://feeds.bbci.co.uk/sport/formula1",
Category: "news",
Enabled: true,
FetchedAt: &now,
ExpiresAt: &expires,
UpdatedAt: now,
}); err != nil {
t.Fatalf("UpsertNewsSource() error = %v", err)
}
published := now.Add(-time.Hour)
item := NewsItem{
URL: "https://example.com/f1/story",
Source: "bbc-f1",
Title: "Paddock update",
PublishedAt: &published,
Summary: "Short briefing text",
Category: "news",
FetchedAt: now,
}
if err := s.UpsertNewsItem(item); err != nil {
t.Fatalf("UpsertNewsItem() error = %v", err)
}
updated := item
updated.Title = "Paddock update revised"
if err := s.UpsertNewsItem(updated); err != nil {
t.Fatalf("second UpsertNewsItem() error = %v", err)
}
items, err := s.ListNewsItems(10, "bbc-f1")
if err != nil {
t.Fatalf("ListNewsItems() error = %v", err)
}
if len(items) != 1 {
t.Fatalf("items len = %d, want 1", len(items))
}
if items[0].Title != updated.Title {
t.Fatalf("title = %q, want %q", items[0].Title, updated.Title)
}
if items[0].PublishedAt == nil || !items[0].PublishedAt.Equal(published) {
t.Fatalf("published_at = %v, want %v", items[0].PublishedAt, published)
}
}
func TestWithTxRollback(t *testing.T) {
s := openTestStore(t)

View File

@@ -115,6 +115,24 @@ func (s *Server) handleSessions(w http.ResponseWriter, r *http.Request) {
writeJSON(w, sessions)
}
// --- /api/v1/news ---
func (s *Server) handleNews(w http.ResponseWriter, r *http.Request) {
if !s.hasLocalQuery() {
writeJSON(w, []query.NewsItem{})
return
}
limit, _ := strconv.Atoi(r.URL.Query().Get("limit"))
source := strings.TrimSpace(r.URL.Query().Get("source"))
items, err := s.query.ListNews(limit, source)
if err != nil {
writeError(w, err, http.StatusInternalServerError, false)
return
}
writeJSON(w, items)
}
// --- /api/v1/drivers ---
func (s *Server) handleDrivers(w http.ResponseWriter, r *http.Request) {

View File

@@ -192,6 +192,52 @@ func TestHandleSeasonsWithData(t *testing.T) {
}
}
func TestHandleNewsWithLocalData(t *testing.T) {
st := openTestStore(t)
now := time.Unix(1800000000, 0).UTC()
published := now.Add(-30 * time.Minute)
if err := st.UpsertNewsSource(store.NewsSource{
Source: "racefans-f1",
Name: "RaceFans F1",
FeedURL: "https://www.racefans.net/category/f1-news/feed/",
Category: "news",
Enabled: true,
UpdatedAt: now,
}); err != nil {
t.Fatalf("UpsertNewsSource() error = %v", err)
}
if err := st.UpsertNewsItem(store.NewsItem{
URL: "https://example.com/story",
Source: "racefans-f1",
Title: "RaceFans story",
PublishedAt: &published,
Summary: "Brief summary",
Category: "news",
FetchedAt: now,
}); err != nil {
t.Fatalf("UpsertNewsItem() error = %v", err)
}
srv := testServer(t, st)
req := httptest.NewRequest(http.MethodGet, "/api/v1/news?source=racefans-f1&limit=5", nil)
rec := httptest.NewRecorder()
srv.handleNews(rec, req)
if rec.Code != http.StatusOK {
t.Fatalf("status = %d, want 200", rec.Code)
}
var items []query.NewsItem
if err := json.Unmarshal(rec.Body.Bytes(), &items); err != nil {
t.Fatalf("decode response: %v", err)
}
if len(items) != 1 {
t.Fatalf("items len = %d, want 1", len(items))
}
if items[0].Source != "racefans-f1" || items[0].Title != "RaceFans story" {
t.Fatalf("items[0] = %+v, want seeded item", items[0])
}
}
func TestHandleWeekendNotFound(t *testing.T) {
st := openTestStore(t)
srv := testServer(t, st)

View File

@@ -64,6 +64,7 @@ func (s *Server) routes() (http.Handler, error) {
mux.HandleFunc("/api/v1/race-hub", s.handleRaceHub)
mux.HandleFunc("/api/v1/seasons", s.handleSeasons)
mux.HandleFunc("/api/v1/weekend", s.handleWeekend)
mux.HandleFunc("/api/v1/news", s.handleNews)
mux.HandleFunc("/api/v1/meetings", s.handleMeetings)
mux.HandleFunc("/api/v1/sessions", s.handleSessions)
mux.HandleFunc("/api/v1/drivers", s.handleDrivers)