fix(api,watcher,server): reject moves non-markdown untouched; read caps; BOM; strict routing flag (review of #211, pass 2)
CI / Lint / Test / Vet (pull_request) Successful in 1m2s
CI / Mirror to GitHub (pull_request) Skipped

- brain_reject on a parked pdf/txt moves the bytes; it no longer prepends YAML
- raw/ notes are read through a cap (readCapped); an endless reader test fails
  instead of exhausting memory
- a byte-order mark no longer hides a note's wing: key
- INGEST_WING_ROUTING is parsed strictly; a typo stops the server rather than
  leaving routing silently off
- tests for the reserved-wing check in every disguise (Sources, sources., ...)
Mutation-checked.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-20 20:49:10 +02:00
co-authored by Claude Sonnet 5.5
parent 6f5fb481ad
commit 49286ba8b8
8 changed files with 152 additions and 11 deletions
@@ -1,8 +1,10 @@
package api
import (
"errors"
"os"
"path/filepath"
"strings"
"testing"
"github.com/stretchr/testify/assert"
@@ -124,3 +126,67 @@ func TestPromoteNote_OnlyMarkdownCanBePromoted(t *testing.T) {
_, statErr := os.Stat(filepath.Join(dir, "raw", "needs-review", "paper.pdf"))
assert.NoError(t, statErr, "refused, untouched")
}
// brain.Sanitise normalises case, trailing dots and separators; the reserved-name
// check must look at the normalised name or "Sources" and "sources." walk past it.
func TestPromoteNote_ReservedWingNamesAreRefusedInEveryDisguise(t *testing.T) {
for _, w := range []string{"Sources", "sources.", "SOURCES ", "Entities/", "concepts\\", " wiki "} {
t.Run(w, func(t *testing.T) {
dir := t.TempDir()
writeRaw(t, dir, "a.md", "top")
_, err := PromoteNote(dir, PromoteOptions{Filename: "a.md", Wing: w, Hall: "facts"})
assert.Error(t, err)
_, statErr := os.Stat(filepath.Join(dir, "raw", "a.md"))
assert.NoError(t, statErr, "refused, untouched")
})
}
}
// Reject moves the bytes; it must not prepend frontmatter to a pdf or txt.
func TestRejectNote_AParkedNonMarkdownFileIsMovedUntouched(t *testing.T) {
dir := t.TempDir()
pdf := "%PDF-1.4\r\n\x00\xff binary \r\n"
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw", "needs-review"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "needs-review", "paper.pdf"), []byte(pdf), 0o644))
rel, err := RejectNote(dir, RejectOptions{Filename: "paper.pdf", Reason: "not relevant"})
require.NoError(t, err)
got, err := os.ReadFile(filepath.Join(dir, rel))
require.NoError(t, err)
assert.Equal(t, pdf, string(got), "byte for byte")
_, statErr := os.Stat(filepath.Join(dir, "raw", "needs-review", "paper.pdf"))
assert.ErrorIs(t, statErr, os.ErrNotExist)
}
func TestReadRawNote_IsBoundedByTheCap(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(dir, "big.md"), []byte(strings.Repeat("x", 200)), 0o644))
root, err := os.OpenRoot(dir)
require.NoError(t, err)
defer func() { _ = root.Close() }()
prev := maxRawNoteBytes
maxRawNoteBytes = 100
t.Cleanup(func() { maxRawNoteBytes = prev })
_, _, err = readRawNote(root, "big.md")
require.Error(t, err)
assert.Contains(t, err.Error(), "exceeds")
}
type endless struct{ n int64 }
func (e *endless) Read(p []byte) (int, error) {
if e.n > 8<<20 { // a regression fails the test instead of exhausting memory
return 0, errors.New("endless reader drained")
}
e.n += int64(len(p))
return len(p), nil
}
func TestReadCapped_StopsAtTheCap(t *testing.T) {
e := &endless{}
_, err := readCapped(e, 1000)
require.Error(t, err)
assert.Contains(t, err.Error(), "exceeds")
assert.LessOrEqual(t, e.n, int64(1000+1+32*1024), "pulled far more than the cap: %d", e.n)
}