mathiasandClaude Opus 5.5
21a53c4159
Both read a caller-chosen server path with extract.Text, so any file the pod could read (the ServiceAccount token, /etc/passwd) could be ingested into the brain and read back with brain_query. ResolveIngestPath resolves relative paths against brain/raw/ (the inbox the watcher already owns), evaluates symlinks, and refuses anything that lands outside. A directory ingest re-resolves every walked file, so a symlinked file inside raw/ cannot lead out. Existing ingest-path tests moved their fixtures under brain/raw/. Refs #149 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
63 lines
1.9 KiB
Go
63 lines
1.9 KiB
Go
// ingestion/internal/api/ingestpath_docmark_test.go
|
|
package api_test
|
|
|
|
import (
|
|
"bytes"
|
|
"encoding/json"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"os"
|
|
"path/filepath"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestIngestPath_DocxUnsupportedWhenDocmarkNotConfigured(t *testing.T) {
|
|
t.Setenv("DOCMARK_URL", "")
|
|
_, h := setup(t)
|
|
|
|
dir := t.TempDir()
|
|
f := filepath.Join(dir, "doc.docx")
|
|
require.NoError(t, os.WriteFile(f, []byte("fake docx"), 0o644))
|
|
|
|
body, _ := json.Marshal(map[string]any{"path": f, "source": "test-doc", "dry_run": true})
|
|
req := httptest.NewRequest(http.MethodPost, "/ingest-path", bytes.NewReader(body))
|
|
rec := httptest.NewRecorder()
|
|
|
|
h.IngestPath(rec, req)
|
|
|
|
assert.Equal(t, http.StatusBadRequest, rec.Code, rec.Body.String())
|
|
}
|
|
|
|
func TestIngestPath_DocxSupportedWhenDocmarkConfigured(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
w.Header().Set("Content-Type", "application/json")
|
|
_, _ = w.Write([]byte(`{"jsonrpc":"2.0","id":1,"result":{"content":[{"type":"text","text":"# Converted Doc"}]}}`))
|
|
}))
|
|
defer srv.Close()
|
|
t.Setenv("DOCMARK_URL", srv.URL+"/mcp")
|
|
t.Setenv("DOCMARK_BEARER_TOKEN", "tok")
|
|
|
|
brainDir, h := setup(t)
|
|
|
|
dir := filepath.Join(brainDir, "raw", "fixture") // ingest paths must live in brain/raw/ (#149)
|
|
require.NoError(t, os.MkdirAll(dir, 0o755))
|
|
f := filepath.Join(dir, "doc.docx")
|
|
require.NoError(t, os.WriteFile(f, []byte("fake docx"), 0o644))
|
|
|
|
body, _ := json.Marshal(map[string]any{"path": f, "source": "test-doc", "dry_run": true})
|
|
req := httptest.NewRequest(http.MethodPost, "/ingest-path", bytes.NewReader(body))
|
|
rec := httptest.NewRecorder()
|
|
|
|
h.IngestPath(rec, req)
|
|
|
|
require.Equal(t, http.StatusOK, rec.Code, rec.Body.String())
|
|
var resp map[string]any
|
|
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
|
|
pages, ok := resp["pages"].([]any)
|
|
require.True(t, ok)
|
|
assert.NotEmpty(t, pages)
|
|
}
|