Bound the access log line against client-chosen text (closes #146)

The access log wrote one INFO line per request carrying
r.URL.String(). Registered with Use, it runs ahead of the route
limiter, so a client flooding the unauthenticated receiver with
invented paths wrote attacker-chosen text of attacker-chosen length
into the operator's log, one line per request.

3xx and 4xx responses now log the chi route pattern in place of the
concrete URL, and the fixed literal "(unmatched)" when routing matched
nothing at all. One line per request is retained, so real traffic
stays observable and rate accounting still works, but the line's
content is now bounded by the service's own route table. The pattern
is only populated after routing, so it is read in the deferred part of
the handler rather than before next.ServeHTTP.

The route pattern alone does not close the hole, because it leaves two
other ways for a request to choose the size of the line it writes.

The query string is one: /.well-known/healthcheck and /s/* answer 200
to anyone with no rate limiter in front of them, and /pages/login
behind only the login limiter, so appending 8 KB after the '?' bought
the same amplification as an invented 404 path. The branches that keep
the concrete URL now log the path only, with the query replaced by the
fixed marker "?(redacted)". Nothing debuggable is lost: `page`, on the
authenticated pagination links, is the only query parameter this
service reads.

The headers are the other: useragent and referer are logged on every
line, including the correctly redacted ones, so an 8 KB User-Agent
plus an 8 KB Referer produced a 24 KB line whose url field read
"(unmatched)". Each field a client supplies is now truncated rather
than dropped -- a truncated User-Agent is still worth reading -- to
512 bytes for url, useragent and referer, 128 for request_id (chi
passes an inbound X-Request-Id header straight through), and 32 for
method, which Go accepts as any token up to the header size limit.
Truncation also drops invalid UTF-8, which a JSON encoder would
otherwise expand six-fold past the budget.

A complete line is now at most 2,560 bytes, which the tests assert
against a request carrying 8 KB in the query and 8 KB in each of three
headers, and which the README states so an operator can size log
storage against it.

.dockerignore

@@ -3,11 +3,6 @@
 # stage of the Dockerfile.
 .git/
 bin/
-# Third-party browser assets are fetched and hash-verified inside the build by
-# script/fetch-assets. Excluding any host copy keeps a developer's working tree
-# from supplying the bytes that get shipped. The script and its
-# static/vendor.sha256 manifest stay in the context.
-static/js/alpine.min.js
 *.md
 LICENSE
 .editorconfig

.gitignore

@@ -45,8 +45,3 @@ temp/
 
 # CI cache barrier, written into the build context by the check workflow
 .ci-fingerprint 
-
-# Third-party browser assets, fetched and hash-verified by
-# script/fetch-assets against static/vendor.sha256. Not committed:
-# REPO_POLICIES.md forbids minified bundles in version control.
-/static/js/alpine.min.js 

Dockerfile

@@ -32,7 +32,7 @@ FROM golang:1.26.1-bookworm@sha256:4465644228bc2857a954b092167e12aa59c006a349228
 # Depend on lint stage passing
 COPY --from=lint /src/go.sum /dev/null
 
-RUN apt-get update && apt-get install -y --no-install-recommends make curl ca-certificates && rm -rf /var/lib/apt/lists/*
+RUN apt-get update && apt-get install -y --no-install-recommends make && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /build
 
@@ -44,14 +44,6 @@ RUN go mod download
 # the lint stage above.
 COPY . .
 
-# Fetch the third-party browser assets the UI serves. They are not committed
-# (REPO_POLICIES.md forbids minified bundles in version control) and
-# .dockerignore keeps any host copy out of the build context, so this step is
-# the only way they enter the image. Each download is checked against a
-# hardcoded sha256 and the build fails on mismatch; make test re-checks the
-# hashes against the bytes go:embed actually put in the binary.
-RUN script/fetch-assets
-
 # Run tests and build
 RUN make test
 RUN make build

Makefile

@@ -1,4 +1,4 @@
-.PHONY: bootstrap setup assets test lint fmt fmt-check check build run dev deps docker clean hooks css
+.PHONY: bootstrap setup test lint fmt fmt-check check build run dev deps docker clean hooks css
 
 # Default target
 .DEFAULT_GOAL := check
@@ -9,9 +9,6 @@ bootstrap:
 setup:
 	@script/setup
 
-assets:
-	@script/fetch-assets
-
 test:
 	@script/test
 

README.md

@@ -40,7 +40,6 @@ make docker
 ```bash
 make bootstrap  # Install all dependencies (idempotent)
 make setup      # Bootstrap + install git pre-commit hook
-make assets     # Fetch + verify third-party browser assets
 make fmt        # Format code (gofmt + goimports)
 make lint       # Run golangci-lint
 make test       # Run tests with race detection
@@ -248,8 +247,6 @@ them. We provide:
 - `script/setup` — make a fresh clone ready for development
   (bootstrap, then install-precommit)
 - `script/projectname` — output the project name ("webhooker")
-- `script/fetch-assets` — download the third-party browser assets into
-  `static/`, verifying each against its pinned sha256
 - `script/test` — run the test suite
 - `script/lint` — run golangci-lint
 - `script/fmt` — format all code (writes)
@@ -263,27 +260,6 @@ them. We provide:
 - `script/install-precommit` — install the git pre-commit hook that
   runs `script/precommit`
 
-## Third-party browser assets
-
-The web UI serves one third-party script, Alpine.js. It is **not** committed:
-a minified bundle in the tree is unreviewable, and `REPO_POLICIES.md` bars
-both committed build artifacts and unpinned external references.
-
-Instead `script/fetch-assets` downloads it from a pinned URL, checks the
-download against a hardcoded sha256, and installs it under `static/`. The
-sha256 of every installed asset is recorded in `static/vendor.sha256`, and
-`static/vendor_test.go` re-hashes the bytes `go:embed` put in the binary
-against that manifest — so the pin is enforced on what actually ships, not
-merely written down. Any mismatch fails the build.
-
-`make bootstrap` runs the fetch for local development, and the Dockerfile
-runs it in the build stage; `.gitignore` and `.dockerignore` keep the
-artifact out of both the repo and the build context.
-
-To move to a new version: update the version, URL, and tarball sha256 in
-`script/fetch-assets` and the asset sha256 in `static/vendor.sha256`, then
-run `make assets && make check`.
-
 ## Rationale
 
 Webhook integrations between services are inherently fragile. The
@@ -956,33 +932,12 @@ The remaining client-supplied fields are truncated rather than dropped,
 each to a fixed budget: 512 bytes for `url`, `useragent` and `referer`,
 128 for `request_id` (chi passes an inbound `X-Request-Id` header
 through), and 32 for `method`. A truncated `User-Agent` is still worth
-reading; an absent one is not. A cut value ends in `[truncated]`, which
-is charged on top of the budget rather than inside it.
-
-Each budget is spent in _encoded_ bytes, not in the bytes the client
-sent. The log handler escapes a quotation mark, a backslash and a tab
-to two bytes each and a non-printable rune to six, and Go's header
-parser accepts all of them in a header value, so a budget counted raw
-would buy a field twice its nominal size — and the line, not the
-header, is what an operator has to store. Plain ASCII encodes one byte
-for one, so a real browser's `User-Agent` still fits whole; a value
-built out of escapes keeps a proportionally shorter prefix, which is
-the right trade.
-
-Net: **one `INFO` line per request, of at most 2,560 bytes.** That
-ceiling is arithmetic, not an observation: 3 × (512 + 11) for `url`,
-`useragent` and `referer`, plus 128 + 11 for `request_id`, plus 32 + 11
-for `method`, plus a 336-byte fixed portion (the field names, the
-punctuation, both timestamps at their longest, an IPv6 `remoteIP` with
-a zone, the status and the latency) — 2,087 bytes, stated at 2,560 so
-the figure has headroom. `internal/middleware/accesslog_test.go`
-asserts it against 8 KB of client-chosen text in the path, in the
-query, and in each of `User-Agent`, `Referer` and `X-Request-Id`,
-including cases built from the characters the handler escapes, and
-against the widest line the service can be made to write: a 5xx that
-keeps its concrete path while all three header fields are also at their
-budget. Measured over a real connection, that line is 1,972 bytes.
+reading; an absent one is not. A cut value ends in `[truncated]`.
 
+Net: **one `INFO` line per request, of at most 2,560 bytes** —
+`internal/middleware/accesslog_test.go` asserts that ceiling against a
+request carrying an 8 KB query, an 8 KB `User-Agent`, an 8 KB `Referer`
+and an 8 KB `X-Request-Id`, which together produce a 1,460-byte line.
 Multiply that ceiling by the request rate to size log storage. Note
 that the rate is not bounded by the limits above on every route:
 `/.well-known/healthcheck` and `/s/*` sit behind no limiter, so there

internal/middleware/accesslog_test.go

@@ -35,8 +35,7 @@ const maxLineBytes = 1024
 // maxCappedLineBytes bounds a single access log line when every
 // client-supplied field arrives oversized and is truncated to its
 // budget. This is the number the README quotes as the per-line cost an
-// operator sizes log storage against, and it is a bound on the
-// ENCODED line, which is what the operator's disk holds.
+// operator sizes log storage against.
 const maxCappedLineBytes = 2560
 
 // oversizedSegmentBytes is the length of the single attacker-chosen
@@ -119,16 +118,12 @@ func accessLogRouter(m *middleware.Middleware) *chi.Mux {
 		})
 	})
 
-	boom := func(w http.ResponseWriter, _ *http.Request) {
-		http.Error(w, "boom", http.StatusInternalServerError)
-	}
-
-	router.Get("/boom", boom)
-	// The 5xx branch keeps the concrete path, so it needs a route that
-	// answers 500 to a path of the client's choosing: that is where the
-	// url field and the header fields are both at their budget on the
-	// same line.
-	router.Get("/boom/*", boom)
+	router.Get(
+		"/boom",
+		func(w http.ResponseWriter, _ *http.Request) {
+			http.Error(w, "boom", http.StatusInternalServerError)
+		},
+	)
 
 	return router
 }
@@ -288,41 +283,22 @@ func TestAccessLog_UnroutablePathsLogFixedLiteral(t *testing.T) {
 	)
 }
 
-// oversizedValue builds an 8 KB header value out of repetitions of ch,
-// with the tail marker at its end.
-//
-// The leading 'x' is load-bearing for tab: net/textproto strips leading
-// and trailing whitespace from a header value, so a value that were
-// nothing but tabs would arrive empty over a real connection and the
-// case would prove nothing.
-func oversizedValue(ch string) string {
-	return "x" + strings.Repeat(ch, oversizedSegmentBytes) + tailMarker
-}
+// TestAccessLog_LineSizeDoesNotTrackInputSize drives 8 KB of
+// client-chosen text at the access log through each part of the
+// request that reaches it, and holds the resulting line to a fixed
+// bound in every case.
+func TestAccessLog_LineSizeDoesNotTrackInputSize(t *testing.T) {
+	t.Parallel()
 
-// oversizedHeaders fills every client-supplied header the access log
-// reads with the same value.
-func oversizedHeaders(value string) map[string]string {
-	return map[string]string{
-		"User-Agent":   value,
-		"Referer":      value,
-		"X-Request-Id": value,
-	}
-}
+	oversized := strings.Repeat("h", oversizedSegmentBytes) + tailMarker
 
-// sizeCase is one way of pointing 8 KB of client-chosen text at the
-// access log.
-type sizeCase struct {
-	target     string
-	headers    map[string]string
-	wantStatus int
-	wantURL    string
-	bound      int
-}
-
-// lineSizeCases enumerates every part of a request that reaches the
-// access log, at 8 KB apiece.
-func lineSizeCases() map[string]sizeCase {
-	cases := map[string]sizeCase{
+	tests := map[string]struct {
+		target     string
+		headers    map[string]string
+		wantStatus int
+		wantURL    string
+		bound      int
+	}{
 		"oversized path segment": {
 			target: "/webhook/" + attackerMarker +
 				strings.Repeat("x", oversizedSegmentBytes),
@@ -344,73 +320,19 @@ func lineSizeCases() map[string]sizeCase {
 		// These reach the line on every request, including one whose
 		// url field is correctly redacted.
 		"oversized headers": {
-			target:     "/" + attackerMarker,
-			headers:    oversizedHeaders(oversizedValue("h")),
+			target: "/" + attackerMarker,
+			headers: map[string]string{
+				"User-Agent":   oversized,
+				"Referer":      oversized,
+				"X-Request-Id": oversized,
+			},
 			wantStatus: http.StatusNotFound,
 			wantURL:    unmatchedRouteLiteral,
 			bound:      maxCappedLineBytes,
 		},
 	}
 
-	// The url field on a 5xx keeps the concrete path, so it reaches its
-	// own budget on the same line as the three header fields. That is
-	// the widest line the service can be made to write.
-	longPath := "/boom/" + strings.Repeat("x", oversizedSegmentBytes)
-	wantLongURL := longPath[:maxFieldBytes] + truncationSuffix
-
-	// escapeChars are the bytes Go's header parser accepts in a header
-	// value and the log handler then escapes, one byte in and two or
-	// more out. A budget counted in raw bytes lets any of them buy a
-	// field twice its nominal size, so every one of them gets a case.
-	escapeChars := map[string]string{
-		"quote":     `"`,
-		"backslash": `\`,
-		"tab":       "\t",
-	}
-
-	for kind, char := range escapeChars {
-		fill := oversizedValue(char)
-
-		cases["oversized "+kind+" headers"] = sizeCase{
-			target:     "/" + attackerMarker,
-			headers:    oversizedHeaders(fill),
-			wantStatus: http.StatusNotFound,
-			wantURL:    unmatchedRouteLiteral,
-			bound:      maxCappedLineBytes,
-		}
-
-		cases["oversized "+kind+" headers with a 5xx concrete url"] =
-			sizeCase{
-				target:     longPath,
-				headers:    oversizedHeaders(fill),
-				wantStatus: http.StatusInternalServerError,
-				wantURL:    wantLongURL,
-				bound:      maxCappedLineBytes,
-			}
-	}
-
-	return cases
-}
-
-// TestAccessLog_LineSizeDoesNotTrackInputSize drives 8 KB of
-// client-chosen text at the access log through each part of the
-// request that reaches it, and holds the resulting line to a fixed
-// bound in every case.
-//
-// The bound is on the ENCODED line, so the cases built out of
-// characters the handler escapes are the ones that matter: a budget
-// spent in raw bytes passes every plain-ASCII case here and still
-// writes a line half again as long as the stated ceiling.
-func TestAccessLog_LineSizeDoesNotTrackInputSize(t *testing.T) {
-	t.Parallel()
-
-	require.Equal(
-		t, middleware.MaxAccessLogLineBytes, maxCappedLineBytes,
-		"the README quotes this ceiling and the middleware derives "+
-			"it; they have to agree",
-	)
-
-	for name, tc := range lineSizeCases() {
+	for name, tc := range tests {
 		t.Run(name, func(t *testing.T) {
 			t.Parallel()
 
@@ -453,12 +375,18 @@ func TestAccessLog_OversizedHeadersKeepATruncatedPrefix(t *testing.T) {
 	m, buf := capturingMiddleware(t)
 	router := accessLogRouter(m)
 
+	oversized := strings.Repeat("h", oversizedSegmentBytes) + tailMarker
+
 	assert.Equal(
 		t,
 		http.StatusNotFound,
 		getWithHeaders(
 			t, router, "/nope",
-			oversizedHeaders(oversizedValue("h")),
+			map[string]string{
+				"User-Agent":   oversized,
+				"Referer":      oversized,
+				"X-Request-Id": oversized,
+			},
 		),
 	)
 

internal/middleware/middleware.go

@@ -8,8 +8,6 @@ import (
 	"net/http"
 	"strings"
 	"time"
-	"unicode"
-	"unicode/utf8"
 
 	basicauth "github.com/99designs/basicauth-go"
 	"github.com/go-chi/chi"
@@ -45,12 +43,8 @@ const (
 
 	// maxLogFieldBytes bounds each access log field whose value the
 	// client supplies outright: the URL, the User-Agent and the
-	// Referer. The budget is spent in ENCODED bytes (see
-	// truncateLogField), so 512 still holds a real browser's User-Agent
-	// whole — those are plain ASCII, which encodes one byte for one —
-	// while a value built from characters the encoder escapes keeps a
-	// shorter prefix. That is the intended trade: 500 quotation marks
-	// are not a debugging asset.
+	// Referer. 512 bytes holds a real browser's User-Agent whole, so a
+	// truncated one is still worth having.
 	maxLogFieldBytes = 512
 
 	// maxLogRequestIDBytes bounds the request id, which is also
@@ -66,34 +60,8 @@ const (
 	maxLogMethodBytes = 32
 
 	// truncationMarker is appended to any field the access log cut, so
-	// a short value and a truncated one cannot be confused. It is
-	// charged on top of the budget, not inside it.
+	// a short value and a truncated one cannot be confused.
 	truncationMarker = "[truncated]"
-
-	// MaxAccessLogLineBytes is the ceiling on one JSON access log line,
-	// and the number an operator multiplies by the request rate to size
-	// log storage. It is not an observation of a sample: it is the sum
-	// of the budgets above, each of which truncateLogField enforces in
-	// ENCODED bytes, plus the part of the line no client can influence.
-	//
-	//	url, useragent, referer   3*(512+11) = 1569
-	//	request_id                    128+11 =  139
-	//	method                         32+11 =   43
-	//	fixed portion                        =  336
-	//	                                        ----
-	//	                                        2087
-	//
-	// The fixed portion is the JSON punctuation, the field names, the
-	// level and the message, both timestamps at their longest, an IPv6
-	// remoteIP with a zone, a three-digit status and a full-width int64
-	// latency. Stated at 2560 so the figure carries headroom rather
-	// than sitting on the arithmetic.
-	//
-	// The tty text handler in internal/logger is covered by the same
-	// figure: encodedLogFieldBytes charges the worse of the two
-	// handlers' escapes, and the text handler's fixed portion is the
-	// smaller of the two.
-	MaxAccessLogLineBytes = 2560
 )
 
 //nolint:revive // MiddlewareParams is a standard fx naming convention.
@@ -163,95 +131,19 @@ func (lrw *loggingResponseWriter) WriteHeader(code int) {
 	lrw.ResponseWriter.WriteHeader(code)
 }
 
-// encodedLogFieldBytes is what r costs on the line once the log
-// handler has escaped it, taking the worse of the two handlers
-// internal/logger configures.
+// truncateLogField caps s at maxBytes, marking the value when it cuts.
 //
-// slog's JSON handler escapes quote, backslash, newline, carriage
-// return and tab to two bytes each, and every other C0 control plus
-// LINE SEPARATOR and PARAGRAPH SEPARATOR to a six-byte \u escape. Its
-// text handler quotes with strconv.Quote, which spells any
-// non-printable rune the same six-byte way. Both pass printable runes
-// through as their own UTF-8, so unicode.IsPrint separates the two
-// cases for either handler. Go's header parser accepts quote,
-// backslash, tab and non-printable multi-byte runes in a header value,
-// so every one of these is reachable from a request.
-func encodedLogFieldBytes(r rune) int {
-	const (
-		// A backslash and the character itself.
-		shortEscapeBytes = 2
-		// \uXXXX, which is also the width of \u00XX.
-		escapedRuneBytes = 6
-	)
-
-	switch {
-	case r == '"' || r == '\\' || r == '\n' || r == '\r' || r == '\t':
-		return shortEscapeBytes
-	case !unicode.IsPrint(r):
-		return escapedRuneBytes
-	default:
-		return utf8.RuneLen(r)
-	}
-}
-
-// truncateLogField caps s at maxBytes of ENCODED output, marking the
-// value when it cuts.
-//
-// Budgeting raw bytes would not bound the line. Escaping only ever
-// grows a value, so a raw budget spent on characters the encoder
-// escapes buys a field several times its nominal size — and the line
-// is the thing an operator is told to multiply by their request rate.
-// Charging each rune what it will actually cost is what makes
-// MaxAccessLogLineBytes true rather than merely larger. The visible
-// consequence is that an escape-heavy value keeps a shorter prefix
-// than a plain one, which is the correct trade.
-//
-// The result is always valid UTF-8. A cut on a byte boundary can split
-// a multi-byte rune, and a header can carry bytes that were never
-// valid UTF-8 to begin with; both are dropped rather than kept, since
-// an encoder would otherwise spend six bytes replacing each one.
+// The result is always valid UTF-8: a byte-boundary cut can split a
+// multi-byte rune, and a header can carry bytes that were never valid
+// UTF-8 to begin with, either of which a JSON encoder expands to six
+// bytes apiece. Dropping them keeps the encoded field inside the same
+// budget as the raw one.
 func truncateLogField(s string, maxBytes int) string {
-	// No rune encodes to fewer bytes than it occupies, so nothing past
-	// maxBytes raw can fit the budget. Slicing first bounds the scan
-	// below to the budget rather than to the size of the header the
-	// client sent.
-	window, cut := s, false
-	if len(window) > maxBytes {
-		window, cut = window[:maxBytes], true
+	if len(s) <= maxBytes {
+		return strings.ToValidUTF8(s, "")
 	}
 
-	var (
-		kept  strings.Builder
-		spent int
-	)
-
-	for i := 0; i < len(window); {
-		r, size := utf8.DecodeRuneInString(window[i:])
-		if r == utf8.RuneError && size == 1 {
-			i += size
-
-			continue
-		}
-
-		cost := encodedLogFieldBytes(r)
-		if spent+cost > maxBytes {
-			cut = true
-
-			break
-		}
-
-		spent += cost
-
-		kept.WriteString(window[i : i+size])
-
-		i += size
-	}
-
-	if !cut {
-		return kept.String()
-	}
-
-	return kept.String() + truncationMarker
+	return strings.ToValidUTF8(s[:maxBytes], "") + truncationMarker
 }
 
 // concreteLogURL renders the request's own URL for the access log

internal/server/static_assets_test.go

@@ -1,50 +0,0 @@
-package server_test
-
-import (
-	"net/http"
-	"regexp"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"sneak.berlin/go/webhooker/templates"
-)
-
-// TestBaseTemplateScriptsAreServed walks every /s/ script the base
-// template loads on each page and fetches it through the real router.
-// Alpine.js is fetched at build time rather than committed, so nothing
-// in the repo guarantees it is present: this is the check that the page
-// still gets the JavaScript it asks for.
-func TestBaseTemplateScriptsAreServed(t *testing.T) {
-	t.Parallel()
-
-	// scriptSrc matches the src of every <script> tag pointing at the
-	// /s/ static mount.
-	scriptSrc := regexp.MustCompile(`<script[^>]+src="(/s/[^"]+)"`)
-
-	base, err := templates.Templates.ReadFile("base.html")
-	require.NoError(t, err)
-
-	matches := scriptSrc.FindAllStringSubmatch(string(base), -1)
-	require.NotEmpty(t, matches, "base.html should load scripts from /s/")
-
-	env := newTestEnv(t)
-
-	for _, m := range matches {
-		src := m[1]
-		t.Run(src, func(t *testing.T) {
-			t.Parallel()
-
-			w := env.get(src, nil)
-
-			require.Equalf(
-				t, http.StatusOK, w.Code,
-				"base.html loads %s but the server does not serve it", src,
-			)
-			assert.NotEmptyf(
-				t, w.Body.Bytes(), "%s is served but empty", src,
-			)
-		})
-	}
-}

script/bootstrap

@@ -5,8 +5,7 @@
 # or apk (detected in that order); assumes NOTHING is present (not git,
 # make, or go). golangci-lint is packaged in nix, brew, and apk; on apt
 # it is installed from a hash-verified GitHub release archive (never
-# curl | sh). Finishes by running script/fetch-assets, which installs the
-# hash-pinned third-party browser assets the repo does not commit.
+# curl | sh).
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
@@ -116,11 +115,6 @@ main() {
 
     go mod download
 
-    # Third-party browser assets are not committed; fetch and verify them
-    # so a fresh clone can build and test.
-    if missing curl; then pkg_install curl curl curl curl; fi
-    "$ROOT/script/fetch-assets"
-
     echo "bootstrap complete"
 }
 

script/fetch-assets

@@ -1,104 +0,0 @@
-#!/bin/sh
-# script/fetch-assets: download the third-party browser assets the web UI
-# ships and install them under static/. Minified bundles are not committed
-# (REPO_POLICIES.md: no build artifacts in version control), so the build
-# fetches them here. Every download is verified against a hardcoded sha256
-# before it is installed, and any mismatch aborts. Idempotent: an asset
-# already present with its pinned hash is left alone.
-set -eu
-
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
-
-# The sha256 of each installed asset lives in static/vendor.sha256, in
-# sha256sum(1) format, with paths relative to static/. That file is the
-# single source of truth: this script verifies against it, and
-# static/vendor_test.go asserts the bytes embedded into the binary match
-# it, so the hash cannot rot into a value nothing checks.
-MANIFEST="static/vendor.sha256"
-
-# Alpine.js 3.14.9, 2026-08-17. Fetched from registry.npmjs.org, the
-# publisher of record; the jsDelivr and unpkg copies are mirrors of this
-# same tarball. dist/cdn.min.js is the browser build Alpine publishes for
-# a <script> tag.
-ALPINE_VERSION="3.14.9"
-ALPINE_URL="https://registry.npmjs.org/alpinejs/-/alpinejs-${ALPINE_VERSION}.tgz"
-# sha256 of alpinejs-3.14.9.tgz
-ALPINE_TARBALL_SHA256="97dad7c0c81e659cfc8e7700055da9770f8186187cb9a8a76efb57e00d5ce52a"
-ALPINE_MEMBER="package/dist/cdn.min.js"
-ALPINE_DEST="js/alpine.min.js"
-
-sha256_of() {
-    if command -v sha256sum >/dev/null 2>&1; then
-        sha256sum "$1" | cut -d' ' -f1
-    else
-        shasum -a 256 "$1" | cut -d' ' -f1
-    fi
-}
-
-# expected_sha256 <path-relative-to-static>
-expected_sha256() {
-    awk -v want="$1" '$2 == want { print $1; found = 1 }
-        END { if (!found) exit 1 }' "$ROOT/$MANIFEST"
-}
-
-# verify <file> <expected-sha256> <what>
-verify() {
-    actual="$(sha256_of "$1")"
-    if [ "$actual" != "$2" ]; then
-        echo "fetch-assets: sha256 mismatch for $3" >&2
-        echo "  expected: $2" >&2
-        echo "  actual:   $actual" >&2
-        exit 1
-    fi
-}
-
-# up_to_date <path-relative-to-static> <expected-sha256>
-up_to_date() {
-    [ -f "$ROOT/static/$1" ] || return 1
-    [ "$(sha256_of "$ROOT/static/$1")" = "$2" ]
-}
-
-fetch_alpine() {
-    want="$(expected_sha256 "$ALPINE_DEST")"
-
-    if up_to_date "$ALPINE_DEST" "$want"; then
-        echo "fetch-assets: static/$ALPINE_DEST already at $want"
-        return 0
-    fi
-
-    echo "fetch-assets: fetching Alpine.js $ALPINE_VERSION from $ALPINE_URL"
-    tmp="$(mktemp -d)"
-    trap 'rm -rf "$tmp"' EXIT INT TERM
-    curl -fsSL -o "$tmp/alpine.tgz" "$ALPINE_URL"
-    verify "$tmp/alpine.tgz" "$ALPINE_TARBALL_SHA256" "alpinejs-${ALPINE_VERSION}.tgz"
-    tar -xzOf "$tmp/alpine.tgz" "$ALPINE_MEMBER" >"$tmp/alpine.min.js"
-    verify "$tmp/alpine.min.js" "$want" "$ALPINE_MEMBER from alpinejs-${ALPINE_VERSION}.tgz"
-
-    mkdir -p "$(dirname "$ROOT/static/$ALPINE_DEST")"
-    cp "$tmp/alpine.min.js" "$ROOT/static/$ALPINE_DEST"
-    rm -rf "$tmp"
-    trap - EXIT INT TERM
-    echo "fetch-assets: installed static/$ALPINE_DEST ($want)"
-}
-
-# Re-check every manifest entry against what is now on disk, so an entry
-# no script installs fails loudly instead of passing silently.
-verify_manifest() {
-    while read -r want path; do
-        case "$want" in '' | '#'*) continue ;; esac
-        if [ ! -f "$ROOT/static/$path" ]; then
-            echo "fetch-assets: $MANIFEST lists static/$path, which is missing" >&2
-            exit 1
-        fi
-        verify "$ROOT/static/$path" "$want" "static/$path"
-    done <"$ROOT/$MANIFEST"
-}
-
-main() {
-    cd "$ROOT"
-    fetch_alpine
-    verify_manifest
-    echo "fetch-assets: all assets in $MANIFEST verified"
-}
-
-main "$@"

static/vendor.sha256

@@ -1 +0,0 @@
-3ed1eed252488921df65e363d6715deb04d7f92aaedb9e52199fdf73cb1e0ad3  js/alpine.min.js

static/vendor_test.go

@@ -1,92 +0,0 @@
-package static_test
-
-import (
-	"bufio"
-	"crypto/sha256"
-	"encoding/hex"
-	"os"
-	"strings"
-	"testing"
-
-	"github.com/stretchr/testify/require"
-
-	"sneak.berlin/go/webhooker/static"
-)
-
-const manifestPath = "vendor.sha256"
-
-// fetchHint is appended to every failure here: the assets the manifest
-// covers are fetched by the build, not committed, so a fresh clone that
-// has not run script/fetch-assets fails this test and should be told why.
-const fetchHint = "run `script/fetch-assets` (or `make assets`) to install " +
-	"the pinned third-party assets"
-
-// TestVendoredAssetsMatchManifest asserts that every asset listed in
-// static/vendor.sha256 is embedded in the binary with exactly the pinned
-// bytes. script/fetch-assets verifies the same hashes at download time;
-// this test verifies them again on what actually ships, so a build that
-// skipped, cached, or subverted the fetch cannot produce a binary serving
-// unpinned third-party JavaScript.
-func TestVendoredAssetsMatchManifest(t *testing.T) {
-	t.Parallel()
-
-	entries := readManifest(t)
-	require.NotEmpty(t, entries, "%s lists no assets", manifestPath)
-
-	for path, want := range entries {
-		t.Run(path, func(t *testing.T) {
-			t.Parallel()
-
-			data, err := static.Static.ReadFile(path)
-			require.NoErrorf(
-				t, err,
-				"%s is listed in %s but is not embedded; %s",
-				path, manifestPath, fetchHint,
-			)
-
-			sum := sha256.Sum256(data)
-			got := hex.EncodeToString(sum[:])
-			require.Equalf(
-				t, want, got,
-				"embedded %s does not match its pinned sha256 in %s; %s",
-				path, manifestPath, fetchHint,
-			)
-		})
-	}
-}
-
-// readManifest parses static/vendor.sha256, which is in sha256sum(1)
-// format with paths relative to static/.
-func readManifest(t *testing.T) map[string]string {
-	t.Helper()
-
-	f, err := os.Open(manifestPath)
-	require.NoError(t, err, "opening %s", manifestPath)
-
-	defer func() { require.NoError(t, f.Close()) }()
-
-	entries := make(map[string]string)
-	scanner := bufio.NewScanner(f)
-
-	for scanner.Scan() {
-		line := strings.TrimSpace(scanner.Text())
-		if line == "" || strings.HasPrefix(line, "#") {
-			continue
-		}
-
-		fields := strings.Fields(line)
-		require.Lenf(
-			t, fields, 2,
-			"%s: malformed entry %q, want \"<sha256>  <path>\"",
-			manifestPath, line,
-		)
-
-		sum, path := fields[0], fields[1]
-		require.Lenf(t, sum, 64, "%s: %q is not a sha256", manifestPath, sum)
-		entries[path] = sum
-	}
-
-	require.NoError(t, scanner.Err(), "reading %s", manifestPath)
-
-	return entries
-}