thermograph/frontend/server/internal/contentdata/loader_test.go

112 lines
3.1 KiB
Go
Raw Normal View History

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).
2026-07-24 00:49:49 +00:00
package contentdata
import (
"os"
"path/filepath"
"testing"
)
func writeContent(t *testing.T, name, body string) string {
t.Helper()
dir := t.TempDir()
if err := os.WriteFile(filepath.Join(dir, name), []byte(body), 0o644); err != nil {
t.Fatal(err)
}
return dir
}
func TestLoadGlossaryOrderAndLookup(t *testing.T) {
dir := writeContent(t, "glossary.yaml", `
terms:
- slug: b-term
term: B
short: short b
body: |-
Body <b>b</b> with {base} link.
- slug: a-term
term: A
short: short a
body: body a
`)
g, err := LoadGlossary(dir)
if err != nil {
t.Fatalf("LoadGlossary: %v", err)
}
// File order, not alphabetical — the index page renders in this order.
if len(g.Terms) != 2 || g.Terms[0].Slug != "b-term" || g.Terms[1].Slug != "a-term" {
t.Errorf("order wrong: %+v", g.Terms)
}
e, ok := g.Get("b-term")
if !ok || e.Term != "B" || e.Body != "Body <b>b</b> with {base} link." {
t.Errorf("Get(b-term) = %+v, %v", e, ok)
}
if _, ok := g.Get("missing"); ok {
t.Error("Get(missing) should report not-found")
}
}
func TestLoadGlossaryFailsLoud(t *testing.T) {
cases := map[string]string{
"empty terms": "terms: []\n",
"missing field": "terms:\n- slug: x\n term: X\n short: s\n", // no body
"missing slug": "terms:\n- term: X\n short: s\n body: b\n",
"duplicate slug": "terms:\n- {slug: x, term: X, short: s, body: b}\n- {slug: x, term: Y, short: s, body: b}\n",
"empty required": "terms:\n- {slug: x, term: X, short: '', body: b}\n", // falsy value fails, like the Python's `not entry.get(f)`
}
for name, body := range cases {
if _, err := LoadGlossary(writeContent(t, "glossary.yaml", body)); err == nil {
t.Errorf("%s: expected an error", name)
}
}
}
func TestLoadPages(t *testing.T) {
dir := writeContent(t, "pages.yaml", `
pages:
about:
title: "About | X"
description: >-
Folded
description.
`)
p, err := LoadPages(dir)
if err != nil {
t.Fatalf("LoadPages: %v", err)
}
if p["about"].Title != "About | X" || p["about"].Description != "Folded description." {
t.Errorf("pages = %+v", p)
}
if _, err := LoadPages(writeContent(t, "pages.yaml", "pages: {}\n")); err == nil {
t.Error("empty pages mapping should fail loud")
}
if _, err := LoadPages(writeContent(t, "pages.yaml", "pages:\n about: {title: T}\n")); err == nil {
t.Error("missing description should fail loud")
}
}
// Smoke-check against the real committed content files (frontend/content/),
// when present — the same files the Python loader validated at import.
func TestLoadRealContentFiles(t *testing.T) {
dir := filepath.Join("..", "..", "..", "content")
if _, err := os.Stat(filepath.Join(dir, "glossary.yaml")); err != nil {
t.Skipf("real content dir not available: %v", err)
}
g, err := LoadGlossary(dir)
if err != nil {
t.Fatalf("LoadGlossary(real): %v", err)
}
if len(g.Terms) == 0 {
t.Error("real glossary should have terms")
}
p, err := LoadPages(dir)
if err != nil {
t.Fatalf("LoadPages(real): %v", err)
}
for _, key := range []string{"about", "privacy", "hub", "glossary_index"} {
if _, ok := p[key]; !ok {
t.Errorf("real pages.yaml missing key %q (content.py reads it)", key)
}
}
}