thermograph/frontend/server/main.go
Emi Griffith 9eecfc8eef
All checks were successful
PR build (required check) / changes (pull_request) Successful in 6s
secrets-guard / encrypted (pull_request) Successful in 7s
PR build (required check) / build-backend (pull_request) Has been skipped
shell-lint / shellcheck (pull_request) Successful in 7s
PR build (required check) / validate-observability (pull_request) Has been skipped
PR build (required check) / build-frontend (pull_request) Successful in 1m0s
PR build (required check) / gate (pull_request) Successful in 2s
frontend: rewrite the SSR content service in Go
Ports frontend/ (Jinja2/FastAPI, ~1180 LOC) to Go with html/template.
No climate math, no DB, no auth here -- every route fetches from the
backend's /content/* API, so this is I/O-bound glue with no hard-porting
wall; the risk was always in reproducing the rendering exactly, not the
language.

Verified with a golden-HTML diff, not just unit tests: both the Python
original and the Go rewrite were run against the same committed fixtures
(frontend/tests/fixtures/) and every one of the 11 routes compared
byte-for-byte. The only surviving differences after that process are
insignificant inter-tag whitespace and one attribute where Go's stricter
escaper HTML-encodes an apostrophe Jinja left literal (functionally
identical in every browser) -- confirmed programmatically by normalizing
whitespace and unescaping before diffing, not by eyeballing.

That process caught defects unit tests alone would have missed, because
map[string]any has no compile-time field check:

- Render-context keys were snake_case throughout (content.py's Jinja
  convention, ported verbatim) while the templates -- written
  independently -- read PascalCase fields. A missing map key doesn't
  error in html/template, it silently renders empty, so this was invisible
  in every status code and every "it built" signal: title, meta
  description, canonical URL, OpenGraph tags, the homepage's entire ranked
  list, and the brand-tag/nav-active state were all blank across every
  page. Fixed by renaming every key to match each template's own header
  comment (the authoritative per-page field contract) and, where an
  API struct's exported fields already matched what a template needed
  (contentapi.CityInfo, Crumb, HomeRanked, HubCountry, ...), passing the
  struct straight through instead of hand-rewrapping it in a map --
  removes a whole layer of future drift risk, not just this instance of it.
- Three pages 500'd outright: `.ToolHref` needed a fully-composed href
  string, not the bare "lat,lon" fragment the handlers were building; the
  all-time-records table needed the raw contentapi.AllTimeRecords struct,
  not a re-wrapped map.
- JSON-LD was being double-encoded: `<script type="application/ld+json">`
  is JAVASCRIPT context to html/template's contextual escaper regardless
  of the script's `type` attribute, so a template.HTML-typed value placed
  there gets re-escaped as a quoted JS string instead of emitted raw --
  the entire structured-data payload shipped as a JSON string containing
  JSON, which no crawler would parse as the intended object. Needed
  template.JS instead, the type that actually means "trusted JS source."
  The glossary term page's JSON-LD was simply never built at all (the
  Jinja original assembled it inline in the template rather than through
  content.py's context dict, and that got lost in translation) -- added.
- html/template silently strips literal HTML comments AND JavaScript
  comments from the parsed output (verified in isolation, zero template
  actions involved) -- confirmed as real engine behavior, not a bug in
  either port, so both need a FuncMap function returning template.HTML /
  template.JS respectively to survive parsing rather than a literal
  `<!-- -->` or `//` in the template source.

Packaging: multi-stage Go build, final image alpine (not distroless -- the
Swarm stack's env-entrypoint.sh shim needs bash), 187MB -> 22.6MB. Two
defects caught before they reached a host:
- The Swarm stack overrides `entrypoint:` with no `command:`, which drops
  the image's own CMD entirely (Docker/Swarm semantics, not merged) --
  env-entrypoint.sh then fell through to its hardcoded `exec uvicorn
  app:app` fallback, which doesn't exist in this image. Every deploy
  would have exited 127. Fixed with an explicit `command:` on the stack's
  frontend service, and corrected the shim's stale comment claiming CMD
  passes through automatically.
- `COPY --chown=thermograph` resolves the group by NAME at copy time;
  Alpine's `adduser -S` with no `-G` doesn't create a same-named group, so
  the classic (non-BuildKit) Docker builder -- which this CI runner falls
  back to, since it installs plain `docker.io` with no buildx plugin --
  failed outright. Fixed with an explicit group and numeric --chown.

Verification: go build/vet/test -race clean across all packages; the
Docker image builds and passes its embedded go test step under both
BuildKit and the classic builder; shellcheck 0 findings on the one script
touched; rebased onto current main (the ERA5 lake stack landed on both
main and dev during this work -- confirmed additive, no overlap with
frontend/daemon).
2026-07-23 17:51:31 -07:00

174 lines
5.6 KiB
Go

// thermograph-frontend: the SSR frontend service — server-rendered content
// pages (climate hub / per-city / month / records / glossary / about), the
// interactive tool's SPA shells, and every static asset. All climate data
// comes from the backend's content API over HTTP (internal/contentapi); this
// process holds no data of its own.
//
// Go port of app.py: configuration, the route wiring (internal/content for
// the content.py routes, internal/handlers for the SPA shells + static
// assets), and the process lifecycle uvicorn used to own (listen, access
// logs, graceful shutdown).
package main
import (
"context"
"errors"
"log/slog"
"mime"
"net"
"net/http"
"os"
"os/signal"
"syscall"
"time"
"thermograph/frontend/internal/config"
"thermograph/frontend/internal/content"
"thermograph/frontend/internal/contentapi"
"thermograph/frontend/internal/contentdata"
"thermograph/frontend/internal/handlers"
"thermograph/frontend/internal/render"
)
func main() {
logger := slog.New(slog.NewJSONHandler(os.Stdout, nil))
slog.SetDefault(logger)
// Fail loud at boot on bad configuration or content (missing backend URL,
// garbage TTL, malformed glossary/pages YAML) — the Python raised at
// import for the same cases: a missing backend URL or a bad content edit
// should break the boot, not silently 500 on the first request.
cfg, err := config.Load()
if err != nil {
fatal(logger, "config", err)
}
client := contentapi.New(contentapi.Options{
BaseURL: cfg.APIBaseInternal,
BasePrefix: cfg.Base, // backend runs under the same THERMOGRAPH_BASE
APIVersion: cfg.APIVersion,
TTL: cfg.SSRCacheTTL,
})
glossary, err := contentdata.LoadGlossary(cfg.ContentDir)
if err != nil {
fatal(logger, "glossary", err)
}
pages, err := contentdata.LoadPages(cfg.ContentDir)
if err != nil {
fatal(logger, "pages", err)
}
// Templates parse once, at boot, with the full FuncMap (html/template
// resolves function names at parse time) — the Go analogue of the Jinja
// environment's auto_reload=False.
engine, err := render.New(content.FuncMap(cfg))
if err != nil {
fatal(logger, "templates", err)
}
// The PWA manifest is served as a static file; register its media type so
// the file server labels it correctly (not in Go's default mime table).
if err := mime.AddExtensionType(".webmanifest", "application/manifest+json"); err != nil {
fatal(logger, "mime", err)
}
// app.py-layer routes: SPA shells + static assets + the bare-BASE redirect.
app := handlers.New(handlers.Options{
Base: cfg.Base,
StaticDir: cfg.StaticDir,
GoogleVerify: cfg.GoogleVerify,
BingVerify: cfg.BingVerify,
Log: logger,
})
// content.py-layer routes. content.New takes a *log.Logger; bridge it into
// slog so its lines (IndexNow boot warning, render failures) land on
// stdout structured like everything else.
contentHandlers, err := content.New(cfg, client, engine, glossary, pages,
slog.NewLogLogger(logger.Handler(), slog.LevelWarn))
if err != nil {
fatal(logger, "content", err)
}
mux := http.NewServeMux()
// Liveness probe: the process is up and serving. Deliberately does no I/O
// — no call to the backend — so it stays cheap and reliable for a tight
// healthcheck interval. Readiness (backend reachable) is a separate concern.
mux.HandleFunc("GET /healthz", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
_, _ = w.Write([]byte(`{"status":"ok"}`))
})
// Register order does not matter for precedence (most-specific pattern
// wins), but content registration performs the eager IndexNow key fetch —
// same point in boot as the Python's content.register(app). Its lazy
// fallback route needs the static handler to delegate non-key requests to.
contentHandlers.Register(mux, app.Static())
app.Register(mux)
srv := &http.Server{
Addr: net.JoinHostPort("", cfg.Port), // 0.0.0.0:PORT, like uvicorn --host 0.0.0.0
Handler: accessLog(logger, mux),
ReadHeaderTimeout: 10 * time.Second,
}
// Graceful shutdown on SIGINT/SIGTERM: stop accepting, drain in-flight
// requests, then exit — what uvicorn did for the Python process.
ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
defer stop()
errCh := make(chan error, 1)
go func() {
logger.Info("thermograph-frontend listening", "port", cfg.Port, "base", cfg.Base)
errCh <- srv.ListenAndServe()
}()
select {
case err := <-errCh:
if !errors.Is(err, http.ErrServerClosed) {
fatal(logger, "serve", err)
}
case <-ctx.Done():
shutdownCtx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
defer cancel()
if err := srv.Shutdown(shutdownCtx); err != nil {
logger.Error("shutdown", "err", err)
os.Exit(1)
}
logger.Info("shut down cleanly")
}
}
func fatal(logger *slog.Logger, stage string, err error) {
logger.Error(stage, "err", err)
os.Exit(1)
}
// accessLog is the uvicorn access log's replacement: one structured line per
// request on stdout.
func accessLog(logger *slog.Logger, next http.Handler) http.Handler {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
start := time.Now()
rec := &statusRecorder{ResponseWriter: w, status: http.StatusOK}
next.ServeHTTP(rec, r)
logger.Info("request",
"method", r.Method,
"path", r.URL.Path,
"status", rec.status,
"dur_ms", time.Since(start).Milliseconds(),
)
})
}
// statusRecorder captures the response status for the access log.
type statusRecorder struct {
http.ResponseWriter
status int
}
func (rec *statusRecorder) WriteHeader(status int) {
rec.status = status
rec.ResponseWriter.WriteHeader(status)
}