Compare commits

..

2 Commits

Author SHA1 Message Date
477ff660c2 Merge pull request 'embed blogs.json instead of fetching it at runtime' (#2) from clawbot/hnblogs:issue-1-embed-blogs-json into main
Reviewed-on: #2
2026-09-05 06:41:55 +02:00
7e1b010c4f embed blogs.json instead of fetching it at runtime (closes #1)
The dataset is vendored as blogs.json and compiled in with go:embed, so
the package does no network I/O on any code path.

FetchBlogs is removed rather than kept as a no-op wrapper, since nothing
is fetched any more: GetBlogs decodes the embedded bytes on first call
and memoizes the result, and RandomBlog, RandomBlogs and NthBlog go
through it. Callers of FetchBlogs have to switch to GetBlogs.

make update-data refreshes the vendored copy from the BlogsURL constant,
downloading to a temporary file and replacing blogs.json only once that
file parses as a non-empty JSON array of blog entries, so a
complete-but-wrong response cannot overwrite the good dataset. A test
walks the dependency graph of the non-test build and fails if any net/*
package is reachable.

Model: opus-5
2026-09-05 04:37:58 +00:00
4 changed files with 46 additions and 34 deletions

View File

@@ -23,13 +23,19 @@ lint:
# Refresh the vendored dataset from the BlogsURL constant in hnblogs.go, which
# is the single source of truth for the upstream location. The download lands
# on a temporary file and only replaces blogs.json once it is complete, so an
# interrupted fetch cannot leave a truncated dataset committed.
# on a temporary file and only replaces blogs.json once it has been checked to
# be a non-empty JSON array of blog entries, so neither an interrupted transfer
# nor a complete-but-wrong response (an error page, a redirect landing page)
# can overwrite the good dataset.
update-data:
@command -v jq >/dev/null || { echo "update-data requires jq" >&2; exit 1; }
@url=$$(sed -n 's/^const BlogsURL = "\(.*\)"$$/\1/p' hnblogs.go); \
test -n "$$url" || { echo "could not parse BlogsURL from hnblogs.go" >&2; exit 1; }; \
echo "fetching $$url"; \
echo "downloading $$url"; \
curl -fsSL "$$url" -o blogs.json.tmp
@test -s blogs.json.tmp || { echo "downloaded dataset is empty" >&2; rm -f blogs.json.tmp; exit 1; }
@jq -e 'type == "array" and length > 0 and all(.[]; type == "object" and has("url"))' \
blogs.json.tmp >/dev/null 2>&1 \
|| { echo "download is not a non-empty JSON array of blog entries; blogs.json left unchanged" >&2; \
rm -f blogs.json.tmp; exit 1; }
mv blogs.json.tmp blogs.json
$(MAKE) test

View File

@@ -16,9 +16,9 @@ the package with `go:embed`. The library performs no network I/O: importing it
does not reach out to anything, results do not change under a caller between
runs of the same build, and `go test` works offline.
`FetchBlogs` keeps its name and its `sync.Once` memoization, but on first call
it decodes the embedded bytes rather than issuing an HTTP request. Its error
return is now only reachable if the committed `blogs.json` is malformed.
`GetBlogs` decodes the embedded bytes on first call and memoizes the result;
every other accessor goes through it. Its error return is only reachable if the
committed `blogs.json` is malformed.
The trade-off is that the dataset is a build-time artifact: it is roughly 8 MB
of JSON, it lands in every binary that links the package, and it is only as
@@ -31,10 +31,12 @@ make update-data
```
That target reads the upstream location from the `BlogsURL` constant in
`hnblogs.go` — the single source of truth — downloads to a temporary file,
replaces `blogs.json` only once the download completes, and then runs the test
suite against the new data. Commit the resulting `blogs.json` to publish the
update.
`hnblogs.go` — the single source of truth — and downloads it to a temporary
file. It replaces `blogs.json` only once that file parses as a non-empty JSON
array of blog entries, so a response that arrives complete but is not the
dataset leaves the vendored copy untouched. It then runs the test suite
against the new data. Requires `curl` and `jq`. Commit the resulting
`blogs.json` to publish the update.
## Development
@@ -44,4 +46,4 @@ make lint
make docker
```
`make docker` runs lint and tests in containers, matching CI.
`make docker` runs lint and tests in containers.

View File

@@ -14,8 +14,8 @@ import (
"sync"
)
// BlogsURL is the upstream source of blogs.json. It is not fetched at runtime;
// it documents where "make update-data" pulls the vendored copy from.
// BlogsURL is the upstream source of blogs.json. Nothing reads it at runtime;
// it documents where "make update-data" downloads the vendored copy from.
const BlogsURL = "https://raw.githubusercontent.com/surprisetalk/blogs.hn/main/blogs.json"
// blogsJSON is the vendored dataset, refreshed by "make update-data".
@@ -39,13 +39,13 @@ type Blog struct {
Desc string `json:"desc"`
}
// FetchBlogs returns the embedded list of blogs, decoding it on first call and
// GetBlogs returns the embedded list of blogs, decoding it on first call and
// memoizing the result for subsequent calls.
//
// Despite the name it performs no I/O: the data is compiled into the binary, so
// the only error it can return is a malformed embedded blogs.json, which would
// mean the committed dataset is broken.
func FetchBlogs() ([]Blog, error) {
// It performs no I/O: the data is compiled into the binary, so the only error
// it can return is a malformed embedded blogs.json, which would mean the
// committed dataset is broken.
func GetBlogs() ([]Blog, error) {
once.Do(func() {
var decoded []Blog
if err := json.Unmarshal(blogsJSON, &decoded); err != nil {
@@ -59,11 +59,6 @@ func FetchBlogs() ([]Blog, error) {
return blogs, loadError
}
// GetBlogs returns the memoized list of blogs.
func GetBlogs() ([]Blog, error) {
return FetchBlogs()
}
// RandomBlog returns a random blog from the list of blogs.
func RandomBlog() (Blog, error) {
blogs, err := GetBlogs()

View File

@@ -1,14 +1,15 @@
package hnblogs
import (
"bytes"
"encoding/json"
"go/build"
"os/exec"
"strings"
"testing"
)
func TestFetchBlogs(t *testing.T) {
blogs, err := FetchBlogs()
func TestGetBlogs(t *testing.T) {
blogs, err := GetBlogs()
if err != nil {
t.Fatalf("Expected no error, got %v", err)
}
@@ -39,17 +40,25 @@ func TestEmbeddedDataIsUsable(t *testing.T) {
}
// TestNoRuntimeNetworkImports is the regression guard for the reason this data
// is embedded: the package must not reach the network on any code path. A
// transport dependency reintroduced in non-test code fails here.
// is embedded: the package must not reach the network on any code path. It
// walks the whole dependency graph of the non-test build rather than the direct
// import list, so a net/* package reached through an intermediate import fails
// here too. Test-only imports are outside that graph, which is why this test
// may use os/exec itself.
func TestNoRuntimeNetworkImports(t *testing.T) {
pkg, err := build.ImportDir(".", 0)
cmd := exec.Command("go", "list", "-deps", ".")
var stderr bytes.Buffer
cmd.Stderr = &stderr
out, err := cmd.Output()
if err != nil {
t.Fatalf("Failed to inspect package imports: %v", err)
t.Fatalf("Failed to list package dependencies: %v\n%s", err, stderr.String())
}
for _, imported := range pkg.Imports {
if imported == "net" || strings.HasPrefix(imported, "net/") {
t.Fatalf("Package must not perform network I/O, but imports %q", imported)
for _, dep := range strings.Fields(string(out)) {
if dep == "net" || strings.HasPrefix(dep, "net/") {
t.Fatalf("Package must not perform network I/O, but depends on %q", dep)
}
}
}