Files
Enterprise-Knowledge-Base/cli/cmd/search/docs_test.go
T
nullkey 1b20b06f5e feat(cli): --json field-select, --jq, auth token, doc --from-url
Output ergonomics:
- `--json` accepts a comma-separated field list (gh-parity); selects
  named keys from the per-command payload. Bare `--json` keeps the
  full shape.
- `--jq <expr>` evaluates a gojq expression over the JSON; pairs with
  `--json field-list` so projection runs before jq.
- `--version` is a global cobra flag in addition to the `version`
  subcommand; both render the same line.
- Per-command `--help` now renders the available JSON field list under
  "JSON fields available via `--json id,name,...`" (field-discovery
  parity with gh / kubectl `-o jsonpath`).

New commands:
- `auth token` — print the active context's credential to stdout for
  shell command substitution (`WEKNORA_TOKEN=$(weknora auth token)`).
  Default: raw secret, no trailing newline. `--json` emits
  `{token, mode, context}`.
- `doc upload --from-url <URL>` — ingest a remote URL via the SDK
  `CreateKnowledgeFromURL`. `--name` forwarded as `FileName` so the
  server's known-extension heuristic upgrades crawl-mode to
  file-download-mode where appropriate.

Includes the simplify post-review polish pass (field-filter unit
tests, --json/--jq compose check, agent_help copy fixes).
2026-05-15 12:03:56 +08:00

122 lines
4.2 KiB
Go

package search
import (
"context"
"encoding/json"
"errors"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
"github.com/Tencent/WeKnora/cli/internal/format"
"github.com/Tencent/WeKnora/cli/internal/iostreams"
sdk "github.com/Tencent/WeKnora/client"
)
// fakeDocsSearchSvc scripts paginated ListKnowledge responses. Pages are
// indexed 1-based; items keyed by page.
type fakeDocsSearchSvc struct {
pages map[int][]sdk.Knowledge
total int64
err error
calls []int // page numbers requested, for assertions
}
func (f *fakeDocsSearchSvc) ListKnowledge(_ context.Context, kbID string, page, pageSize int, tagID string) ([]sdk.Knowledge, int64, error) {
f.calls = append(f.calls, page)
if f.err != nil {
return nil, 0, f.err
}
return f.pages[page], f.total, nil
}
func TestDocsSearch_Substring(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeDocsSearchSvc{
pages: map[int][]sdk.Knowledge{
1: {
{ID: "d1", Title: "Q3 Forecast", FileName: "q3.pdf", UpdatedAt: mustTime(t, "2026-05-10T00:00:00Z")},
{ID: "d2", Title: "Random Notes", FileName: "notes.md", UpdatedAt: mustTime(t, "2026-05-12T00:00:00Z")},
{ID: "d3", Title: "Q3 retro", FileName: "retro.pdf", UpdatedAt: mustTime(t, "2026-05-11T00:00:00Z")},
},
},
total: 3,
}
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "q3", KBID: "kb1", Limit: 20}, nil, svc))
got := out.String()
assert.Contains(t, got, "d1")
assert.Contains(t, got, "d3")
assert.NotContains(t, got, "d2") // "Random Notes" doesn't contain q3
}
func TestDocsSearch_MatchesFileName(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeDocsSearchSvc{
pages: map[int][]sdk.Knowledge{1: {{ID: "d1", Title: "Untitled", FileName: "report.pdf"}}},
total: 1,
}
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "report", KBID: "kb1", Limit: 20}, nil, svc))
assert.Contains(t, out.String(), "d1")
}
func TestDocsSearch_PaginatesUntilTotal(t *testing.T) {
out, _ := iostreams.SetForTest(t)
page1 := make([]sdk.Knowledge, docsPageSize)
for i := range page1 {
page1[i] = sdk.Knowledge{ID: "p1", Title: "no match"}
}
page2 := []sdk.Knowledge{{ID: "found", Title: "needle here"}}
svc := &fakeDocsSearchSvc{
pages: map[int][]sdk.Knowledge{1: page1, 2: page2},
total: int64(docsPageSize) + 1,
}
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "needle", KBID: "kb1", Limit: 20}, nil, svc))
assert.Contains(t, out.String(), "found")
assert.Equal(t, []int{1, 2}, svc.calls, "must page past the first batch when no match on page 1")
}
func TestDocsSearch_StopsAtLimit(t *testing.T) {
_, _ = iostreams.SetForTest(t)
page1 := make([]sdk.Knowledge, 50)
for i := range page1 {
page1[i] = sdk.Knowledge{ID: "match", Title: "needle"}
}
svc := &fakeDocsSearchSvc{pages: map[int][]sdk.Knowledge{1: page1}, total: 1000}
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "needle", KBID: "kb1", Limit: 3}, nil, svc))
// Must not request page 2 because limit was hit mid-page.
assert.Equal(t, []int{1}, svc.calls)
}
func TestDocsSearch_JSON(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeDocsSearchSvc{
pages: map[int][]sdk.Knowledge{1: {{ID: "d1", Title: "match"}}},
total: 1,
}
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "match", KBID: "kb1", Limit: 20}, &cmdutil.JSONOptions{}, svc))
var env format.Envelope
require.NoError(t, json.Unmarshal(out.Bytes(), &env))
require.True(t, env.OK)
assert.Contains(t, out.String(), `"id":"d1"`)
}
func TestDocsSearch_NetworkError(t *testing.T) {
_, _ = iostreams.SetForTest(t)
svc := &fakeDocsSearchSvc{err: errors.New("HTTP error 404: kb not found")}
err := runDocsSearch(context.Background(), &DocsSearchOptions{Query: "x", KBID: "missing", Limit: 20}, nil, svc)
require.Error(t, err)
var typed *cmdutil.Error
require.ErrorAs(t, err, &typed)
assert.Equal(t, cmdutil.CodeResourceNotFound, typed.Code)
}
func mustTime(t *testing.T, s string) time.Time {
t.Helper()
v, err := time.Parse(time.RFC3339, s)
require.NoError(t, err)
return v
}