This is the piece that turns a Pre-Publish-Prüfung into an actual
archived, provable record instead of a one-off form response.
extract.Client.Extract now returns Result{Facts, RawJSON} instead of
just Facts — RawJSON is the model's exact, unmodified JSON, which is
what belongs in extraction.payload (the audit trail), not a re-encoded
view through our own Facts struct. extract.ParsePayload reconstructs
Facts from a stored payload later, reusing the same parsing/validation
path Extract uses (including the enum guard), so a previously-saved
extraction can be read back exactly as it would have been the first
time.
internal/dossier.BuildContent no longer requires AssetHash: most checks
right now are caption-only (no image/video upload wired yet), and
inventing a placeholder hash for a nonexistent asset would itself be an
integrity problem in an evidence tool. Content shows "kein Asset
hinterlegt" instead.
internal/web gains a narrow Store interface (mirroring the Extractor
pattern — only the methods these handlers use, not the full
*store.Store) so its test suite stays network/DB-free via an in-memory
fake:
- POST /pruefen persists submission + extraction + findings and marks
the submission "checked". A needsClarification result persists the
extraction (there's something worth keeping) but no findings and no
status change, and the template omits the archive option entirely.
- POST /veroeffentlichen re-derives Facts from the stored payload, hashes
the canonical submission+facts+findings metadata, gets an RFC-3161
timestamp, generates the PDF dossier to disk, and persists the
evidence_package row before marking the submission "published".
- GET /dossier/{id} serves the generated PDF.
Tested end-to-end offline: a fake Timestamper builds a real, structurally
valid self-signed RFC-3161 response so the full check→archive→download
flow runs against an in-memory store, verifying the downloaded bytes are
an actual PDF and the dossier file lands on disk — without hitting a
real database, TSA, or the Claude API.
cmd/deklarix/main.go now wires store.Store, evidence.NewHTTPTimestamper
(TSA_URL, default FreeTSA), and DOSSIER_DIR (default "dossiers") into
web.NewServer alongside the extractor and rule set.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
226 lines
7.2 KiB
Go
226 lines
7.2 KiB
Go
package extract_test
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/netcell-it/deklarix/internal/extract"
|
|
"github.com/netcell-it/deklarix/internal/rules"
|
|
)
|
|
|
|
// toolUseResponse baut eine minimale Anthropic-Messages-API-Antwort mit
|
|
// genau einem tool_use-Block, wie sie extract.Client erwartet.
|
|
func toolUseResponse(t *testing.T, toolName string, args any) []byte {
|
|
t.Helper()
|
|
input, err := json.Marshal(args)
|
|
if err != nil {
|
|
t.Fatalf("marshal args: %v", err)
|
|
}
|
|
body := map[string]any{
|
|
"content": []map[string]any{
|
|
{"type": "tool_use", "name": toolName, "input": json.RawMessage(input)},
|
|
},
|
|
}
|
|
data, err := json.Marshal(body)
|
|
if err != nil {
|
|
t.Fatalf("marshal response: %v", err)
|
|
}
|
|
return data
|
|
}
|
|
|
|
func newTestClient(t *testing.T, handler http.HandlerFunc) *extract.Client {
|
|
t.Helper()
|
|
server := httptest.NewServer(handler)
|
|
t.Cleanup(server.Close)
|
|
c, err := extract.NewClient("test-key", extract.WithBaseURL(server.URL))
|
|
if err != nil {
|
|
t.Fatalf("NewClient: %v", err)
|
|
}
|
|
return c
|
|
}
|
|
|
|
func TestNewClientRejectsEmptyAPIKey(t *testing.T) {
|
|
if _, err := extract.NewClient(""); err == nil {
|
|
t.Fatal("expected error for empty apiKey, got nil")
|
|
}
|
|
}
|
|
|
|
func TestExtractRejectsEmptyInput(t *testing.T) {
|
|
called := false
|
|
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
|
|
called = true
|
|
})
|
|
_, err := c.Extract(context.Background(), extract.Input{Platform: "instagram"})
|
|
if err == nil {
|
|
t.Fatal("expected error for empty caption+image, got nil")
|
|
}
|
|
if called {
|
|
t.Fatal("expected no HTTP call for invalid input, but the server was called")
|
|
}
|
|
}
|
|
|
|
func TestExtractSuccess(t *testing.T) {
|
|
var gotBody map[string]any
|
|
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
|
|
if r.URL.Path != "/v1/messages" {
|
|
t.Errorf("unexpected path: %s", r.URL.Path)
|
|
}
|
|
if got := r.Header.Get("x-api-key"); got != "test-key" {
|
|
t.Errorf("x-api-key = %q, want test-key", got)
|
|
}
|
|
if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
|
|
t.Fatalf("decode request body: %v", err)
|
|
}
|
|
w.WriteHeader(http.StatusOK)
|
|
w.Write(toolUseResponse(t, "extrahiere_fakten", map[string]any{
|
|
"gegenleistung": "bezahlt",
|
|
"kennzeichnung_vorhanden": true,
|
|
"kennzeichnung_wortlaut": "Werbung",
|
|
"kennzeichnung_vor_kuerzung": false,
|
|
}))
|
|
})
|
|
|
|
got, err := c.Extract(context.Background(), extract.Input{
|
|
Platform: "instagram",
|
|
Jurisdiction: "DE",
|
|
Caption: "Schaut euch dieses Produkt an! Werbung wegen ...",
|
|
ImageMediaType: "image/jpeg",
|
|
ImageData: []byte("fake-jpeg-bytes"),
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("Extract: %v", err)
|
|
}
|
|
|
|
want := rules.Facts{
|
|
Platform: "instagram",
|
|
Jurisdiction: "DE",
|
|
Consideration: rules.ConsiderationPaid,
|
|
DisclosurePresent: true,
|
|
DisclosureWording: "Werbung",
|
|
DisclosureBeforeCut: false,
|
|
}
|
|
if got.Facts != want {
|
|
t.Fatalf("Extract().Facts = %+v, want %+v", got.Facts, want)
|
|
}
|
|
var rawArgs map[string]any
|
|
if err := json.Unmarshal(got.RawJSON, &rawArgs); err != nil {
|
|
t.Fatalf("RawJSON does not parse as JSON: %v", err)
|
|
}
|
|
if rawArgs["gegenleistung"] != "bezahlt" {
|
|
t.Fatalf("RawJSON = %s, expected it to contain the model's raw field names", got.RawJSON)
|
|
}
|
|
|
|
toolChoice, _ := gotBody["tool_choice"].(map[string]any)
|
|
if toolChoice["name"] != "extrahiere_fakten" {
|
|
t.Errorf("tool_choice.name = %v, want extrahiere_fakten", toolChoice["name"])
|
|
}
|
|
if gotBody["system"] == nil || gotBody["system"] == "" {
|
|
t.Error("expected a non-empty system prompt in the request")
|
|
}
|
|
}
|
|
|
|
func TestExtractPassesThroughUnclear(t *testing.T) {
|
|
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
|
|
w.WriteHeader(http.StatusOK)
|
|
w.Write(toolUseResponse(t, "extrahiere_fakten", map[string]any{
|
|
"gegenleistung": "unklar",
|
|
"kennzeichnung_vorhanden": false,
|
|
"kennzeichnung_wortlaut": "",
|
|
"kennzeichnung_vor_kuerzung": false,
|
|
}))
|
|
})
|
|
|
|
got, err := c.Extract(context.Background(), extract.Input{Platform: "tiktok", Caption: "..."})
|
|
if err != nil {
|
|
t.Fatalf("Extract: %v", err)
|
|
}
|
|
if got.Facts.Consideration != rules.ConsiderationUnclear {
|
|
t.Fatalf("Consideration = %q, want unklar", got.Facts.Consideration)
|
|
}
|
|
}
|
|
|
|
func TestExtractRejectsInvalidConsiderationValue(t *testing.T) {
|
|
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
|
|
w.WriteHeader(http.StatusOK)
|
|
w.Write(toolUseResponse(t, "extrahiere_fakten", map[string]any{
|
|
"gegenleistung": "vielleicht", // nicht im Enum
|
|
"kennzeichnung_vorhanden": false,
|
|
"kennzeichnung_wortlaut": "",
|
|
"kennzeichnung_vor_kuerzung": false,
|
|
}))
|
|
})
|
|
|
|
if _, err := c.Extract(context.Background(), extract.Input{Platform: "instagram", Caption: "x"}); err == nil {
|
|
t.Fatal("expected error for out-of-enum gegenleistung value, got nil")
|
|
}
|
|
}
|
|
|
|
func TestExtractRejectsMissingToolUseBlock(t *testing.T) {
|
|
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
|
|
w.WriteHeader(http.StatusOK)
|
|
w.Write([]byte(`{"content":[{"type":"text","text":"kein tool_use hier"}]}`))
|
|
})
|
|
|
|
if _, err := c.Extract(context.Background(), extract.Input{Platform: "instagram", Caption: "x"}); err == nil {
|
|
t.Fatal("expected error when response has no tool_use block, got nil")
|
|
}
|
|
}
|
|
|
|
func TestExtractRejectsMalformedToolInput(t *testing.T) {
|
|
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
|
|
w.WriteHeader(http.StatusOK)
|
|
w.Write([]byte(`{"content":[{"type":"tool_use","name":"extrahiere_fakten","input":"not-an-object"}]}`))
|
|
})
|
|
|
|
if _, err := c.Extract(context.Background(), extract.Input{Platform: "instagram", Caption: "x"}); err == nil {
|
|
t.Fatal("expected error for malformed tool input, got nil")
|
|
}
|
|
}
|
|
|
|
func TestParsePayloadRoundTrip(t *testing.T) {
|
|
payload := []byte(`{"gegenleistung":"sachbezug","kennzeichnung_vorhanden":true,"kennzeichnung_wortlaut":"Anzeige","kennzeichnung_vor_kuerzung":true}`)
|
|
|
|
facts, err := extract.ParsePayload(payload, "tiktok", "DE")
|
|
if err != nil {
|
|
t.Fatalf("ParsePayload: %v", err)
|
|
}
|
|
|
|
want := rules.Facts{
|
|
Platform: "tiktok",
|
|
Jurisdiction: "DE",
|
|
Consideration: rules.ConsiderationInKind,
|
|
DisclosurePresent: true,
|
|
DisclosureWording: "Anzeige",
|
|
DisclosureBeforeCut: true,
|
|
}
|
|
if facts != want {
|
|
t.Fatalf("ParsePayload() = %+v, want %+v", facts, want)
|
|
}
|
|
}
|
|
|
|
func TestParsePayloadRejectsInvalidConsideration(t *testing.T) {
|
|
payload := []byte(`{"gegenleistung":"vielleicht","kennzeichnung_vorhanden":false,"kennzeichnung_wortlaut":"","kennzeichnung_vor_kuerzung":false}`)
|
|
if _, err := extract.ParsePayload(payload, "tiktok", "DE"); err == nil {
|
|
t.Fatal("expected error for out-of-enum stored payload, got nil")
|
|
}
|
|
}
|
|
|
|
func TestExtractPropagatesAPIError(t *testing.T) {
|
|
c := newTestClient(t, func(w http.ResponseWriter, r *http.Request) {
|
|
w.WriteHeader(http.StatusTooManyRequests)
|
|
w.Write([]byte(`{"error":{"type":"rate_limit_error","message":"too many requests"}}`))
|
|
})
|
|
|
|
_, err := c.Extract(context.Background(), extract.Input{Platform: "instagram", Caption: "x"})
|
|
if err == nil {
|
|
t.Fatal("expected error for non-200 status, got nil")
|
|
}
|
|
if got := err.Error(); !strings.Contains(got, "too many requests") {
|
|
t.Fatalf("error %q does not mention API message", got)
|
|
}
|
|
}
|