Compare commits
8
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e614d39e06 | ||
|
|
edcfe9e9bc | ||
|
|
f1f975d281 | ||
|
|
ddd4bdc2ac | ||
|
|
1fff54769d | ||
|
|
0c3e82ca0a | ||
|
|
eedb110be5 | ||
|
|
febab3e45d |
@@ -4,6 +4,7 @@ import (
|
|||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"strings"
|
"strings"
|
||||||
|
"syscall"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
"github.com/stretchr/testify/assert"
|
"github.com/stretchr/testify/assert"
|
||||||
@@ -63,3 +64,13 @@ func TestStartupSymlinkCheckRefusesAnUnlistableBrainRoot(t *testing.T) {
|
|||||||
t.Cleanup(func() { _ = os.Chmod(brain, 0o755) })
|
t.Cleanup(func() { _ = os.Chmod(brain, 0o755) })
|
||||||
assert.Error(t, startupSymlinkCheck(brain))
|
assert.Error(t, startupSymlinkCheck(brain))
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// hyperguild#179: a FIFO in the brain is refused at startup with a clear
|
||||||
|
// message, instead of hanging or exiting later in a reader.
|
||||||
|
func TestStartupSymlinkCheckRefusesABrainWithAFIFO(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "classification.yaml"), 0o644))
|
||||||
|
err := startupSymlinkCheck(brain)
|
||||||
|
require.Error(t, err)
|
||||||
|
assert.Contains(t, err.Error(), "classification.yaml")
|
||||||
|
}
|
||||||
|
|||||||
+1
-1
@@ -68,7 +68,7 @@ require (
|
|||||||
github.com/segmentio/asm v1.2.0 // indirect
|
github.com/segmentio/asm v1.2.0 // indirect
|
||||||
golang.org/x/crypto v0.51.0 // indirect
|
golang.org/x/crypto v0.51.0 // indirect
|
||||||
golang.org/x/sync v0.21.0 // indirect
|
golang.org/x/sync v0.21.0 // indirect
|
||||||
golang.org/x/sys v0.45.0 // indirect
|
golang.org/x/sys v0.45.0
|
||||||
golang.org/x/text v0.39.0 // indirect
|
golang.org/x/text v0.39.0 // indirect
|
||||||
gopkg.in/yaml.v3 v3.0.1
|
gopkg.in/yaml.v3 v3.0.1
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -23,6 +23,13 @@ func TestReadNoteRefusesSymlinksAndSurvivesSwapRaces(t *testing.T) {
|
|||||||
_, body, _, err := api.ReadNote(brain, "wiki/w/facts/leak.md")
|
_, body, _, err := api.ReadNote(brain, "wiki/w/facts/leak.md")
|
||||||
assert.Error(t, err)
|
assert.Error(t, err)
|
||||||
assert.NotContains(t, body, brainfstest.Sentinel)
|
assert.NotContains(t, body, brainfstest.Sentinel)
|
||||||
|
// A link to a file elsewhere in the brain: os.Root allows it, only the
|
||||||
|
// regular-file check refuses it (hyperguild#171).
|
||||||
|
brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "inlink.md")))
|
||||||
|
_, body, _, err = api.ReadNote(brain, "wiki/w/facts/inlink.md")
|
||||||
|
assert.Error(t, err)
|
||||||
|
assert.NotContains(t, body, brainfstest.Sentinel)
|
||||||
|
|
||||||
p := filepath.Join(facts, "r.md")
|
p := filepath.Join(facts, "r.md")
|
||||||
require.NoError(t, os.WriteFile(p, []byte("---\nx: y\n---\ninside"), 0o644))
|
require.NoError(t, os.WriteFile(p, []byte("---\nx: y\n---\ninside"), 0o644))
|
||||||
@@ -39,5 +46,7 @@ func TestReadNoteRefusesSymlinksAndSurvivesSwapRaces(t *testing.T) {
|
|||||||
return s
|
return s
|
||||||
}
|
}
|
||||||
brainfstest.AssertNoLeak(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, read)
|
brainfstest.AssertNoLeak(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, read)
|
||||||
|
inBrain := brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
brainfstest.AssertNoLeakFrom(t, p, "---\nx: y\n---\ninside", inBrain, 1500*time.Millisecond, read)
|
||||||
brainfstest.AssertNoHang(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, 6*time.Second, func() { _ = read() })
|
brainfstest.AssertNoHang(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, 6*time.Second, func() { _ = read() })
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -3,15 +3,18 @@ package api
|
|||||||
import (
|
import (
|
||||||
"crypto/sha256"
|
"crypto/sha256"
|
||||||
"encoding/hex"
|
"encoding/hex"
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"strings"
|
"strings"
|
||||||
"time"
|
"time"
|
||||||
|
|
||||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||||
"github.com/mathiasbq/hyperguild/ingestion/internal/claim"
|
"github.com/mathiasbq/hyperguild/ingestion/internal/claim"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/notes"
|
||||||
)
|
)
|
||||||
|
|
||||||
// ContentHash returns the lowercase hex sha256 of b. It is the note's
|
// ContentHash returns the lowercase hex sha256 of b. It is the note's
|
||||||
@@ -91,14 +94,23 @@ func UpdateNote(brainDir string, opts UpdateNoteOptions) (relPath, contentHash,
|
|||||||
rel = filepath.ToSlash(rel)
|
rel = filepath.ToSlash(rel)
|
||||||
}
|
}
|
||||||
|
|
||||||
rel, abs, err := resolveWithin(brainDir, rel)
|
// The path is caller-supplied (brain_update): resolve it as brain_edit
|
||||||
|
// does, knowledge/ and wiki/ notes only, and read and rewrite it through
|
||||||
|
// the brain root, never through a symlink (hyperguild#169).
|
||||||
|
t, err := notes.Resolve(brainDir, rel, notes.ScopeNotes)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return "", "", "", err
|
return "", "", "", err
|
||||||
}
|
}
|
||||||
|
rel = t.Rel
|
||||||
prior, err := os.ReadFile(abs)
|
bfs, err := brainfs.Open(brainDir)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
if os.IsNotExist(err) {
|
return "", "", "", fmt.Errorf("open brain: %w", err)
|
||||||
|
}
|
||||||
|
defer func() { _ = bfs.Close() }()
|
||||||
|
|
||||||
|
prior, err := bfs.ReadRegular(rel)
|
||||||
|
if err != nil {
|
||||||
|
if errors.Is(err, fs.ErrNotExist) {
|
||||||
return "", "", "", fmt.Errorf("note %q does not exist: use brain_write to create", rel)
|
return "", "", "", fmt.Errorf("note %q does not exist: use brain_write to create", rel)
|
||||||
}
|
}
|
||||||
return "", "", "", fmt.Errorf("read target: %w", err)
|
return "", "", "", fmt.Errorf("read target: %w", err)
|
||||||
@@ -164,7 +176,7 @@ func UpdateNote(brainDir string, opts UpdateNoteOptions) (relPath, contentHash,
|
|||||||
return "", "", "", err
|
return "", "", "", err
|
||||||
}
|
}
|
||||||
out := []byte(stamped)
|
out := []byte(stamped)
|
||||||
if err := os.WriteFile(abs, out, 0o644); err != nil {
|
if err := bfs.WriteRegular(rel, out); err != nil {
|
||||||
return "", "", "", fmt.Errorf("write: %w", err)
|
return "", "", "", fmt.Errorf("write: %w", err)
|
||||||
}
|
}
|
||||||
return rel, ContentHash(out), priorHash, nil
|
return rel, ContentHash(out), priorHash, nil
|
||||||
|
|||||||
@@ -0,0 +1,36 @@
|
|||||||
|
package api_test
|
||||||
|
|
||||||
|
import (
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||||
|
)
|
||||||
|
|
||||||
|
// hyperguild#173: a directory symlink inside wiki/ that points elsewhere in
|
||||||
|
// the brain redirected brain_update's write (os.Root follows in-root
|
||||||
|
// intermediate symlinks). Every directory above the note must be real.
|
||||||
|
func TestUpdateNoteRefusesANoteBehindASymlinkedDirectory(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
victim := filepath.Join(brain, "raw", "facts", "v.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("---\ntitle: v\n---\nuntouched\n"), 0o644))
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w"), 0o755))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "facts"), filepath.Join(brain, "wiki", "w", "alias")))
|
||||||
|
|
||||||
|
_, _, _, err := api.UpdateNote(brain, api.UpdateNoteOptions{Path: "wiki/w/alias/v.md", Content: "replaced"})
|
||||||
|
assert.ErrorIs(t, err, brainfs.ErrNotRegular)
|
||||||
|
got, _ := os.ReadFile(victim)
|
||||||
|
assert.Contains(t, string(got), "untouched")
|
||||||
|
|
||||||
|
real := filepath.Join(brain, "wiki", "w", "facts", "r.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(real), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(real, []byte("---\ntitle: r\n---\nold\n"), 0o644))
|
||||||
|
_, _, _, err = api.UpdateNote(brain, api.UpdateNoteOptions{Path: "wiki/w/facts/r.md", Content: "new"})
|
||||||
|
require.NoError(t, err, "positive control: a note in a real directory is updated")
|
||||||
|
}
|
||||||
@@ -0,0 +1,112 @@
|
|||||||
|
package api_test
|
||||||
|
|
||||||
|
import (
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"sync"
|
||||||
|
"sync/atomic"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
|
||||||
|
)
|
||||||
|
|
||||||
|
// brain_update passed the caller's path through resolveWithin, a lexical
|
||||||
|
// containment check only: any file in the brain could be superseded
|
||||||
|
// (classification.yaml, raw/, sessions/), and a final symlink was written
|
||||||
|
// through. It now resolves like brain_edit: knowledge/ and wiki/ notes only,
|
||||||
|
// read and rewritten through the brain root.
|
||||||
|
func TestUpdateNoteRefusesPathsOutsideKnowledgeAndWikiNotes(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
files := map[string]string{
|
||||||
|
"classification.yaml": "levels: {}\n",
|
||||||
|
"raw/r.md": "raw\n",
|
||||||
|
"sessions/s.jsonl": "{}\n",
|
||||||
|
"wiki/w/facts/ok.md": "---\ntitle: ok\n---\nold\n",
|
||||||
|
"knowledge/k.md": "---\ntitle: k\n---\nold\n",
|
||||||
|
"wiki/w/facts/x.txt": "txt\n",
|
||||||
|
}
|
||||||
|
for rel, body := range files {
|
||||||
|
p := filepath.Join(brain, filepath.FromSlash(rel))
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(p), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(p, []byte(body), 0o644))
|
||||||
|
}
|
||||||
|
for _, rel := range []string{"classification.yaml", "raw/r.md", "sessions/s.jsonl", "wiki/w/facts/x.txt", "wiki/w/../../raw/r.md"} {
|
||||||
|
_, _, _, err := api.UpdateNote(brain, api.UpdateNoteOptions{Path: rel, Content: "replaced"})
|
||||||
|
assert.Error(t, err, rel)
|
||||||
|
}
|
||||||
|
for rel, body := range files {
|
||||||
|
if rel == "wiki/w/facts/ok.md" || rel == "knowledge/k.md" {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
got, err := os.ReadFile(filepath.Join(brain, filepath.FromSlash(rel)))
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, body, string(got), rel)
|
||||||
|
}
|
||||||
|
for _, rel := range []string{"wiki/w/facts/ok.md", "knowledge/k.md"} {
|
||||||
|
_, _, _, err := api.UpdateNote(brain, api.UpdateNoteOptions{Path: rel, Content: "new body"})
|
||||||
|
require.NoError(t, err, "positive control: %s", rel)
|
||||||
|
got, _ := os.ReadFile(filepath.Join(brain, filepath.FromSlash(rel)))
|
||||||
|
assert.Contains(t, string(got), "new body")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestUpdateNoteDoesNotWriteThroughASymlinkedNote(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
facts := filepath.Join(brain, "wiki", "w", "facts")
|
||||||
|
require.NoError(t, os.MkdirAll(facts, 0o755))
|
||||||
|
victim := filepath.Join(brain, "raw", "victim.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "victim.md"), filepath.Join(facts, "l.md")))
|
||||||
|
_, _, _, err := api.UpdateNote(brain, api.UpdateNoteOptions{Path: "wiki/w/facts/l.md", Content: "replaced"})
|
||||||
|
assert.Error(t, err)
|
||||||
|
got, _ := os.ReadFile(victim)
|
||||||
|
assert.Equal(t, "untouched\n", string(got))
|
||||||
|
}
|
||||||
|
|
||||||
|
// The note is swapped between a regular file and an in-brain symlink to a
|
||||||
|
// raw/ file while UpdateNote runs: the read and the write each refuse a
|
||||||
|
// symlink, so the raw/ file is never rewritten.
|
||||||
|
func TestUpdateNoteNeverRewritesASymlinkSwappedInForTheNote(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
facts := filepath.Join(brain, "wiki", "w", "facts")
|
||||||
|
require.NoError(t, os.MkdirAll(facts, 0o755))
|
||||||
|
victim := filepath.Join(brain, "raw", "victim.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
note := filepath.Join(facts, "n.md")
|
||||||
|
body := "---\ntitle: n\n---\nold\n"
|
||||||
|
require.NoError(t, os.WriteFile(note, []byte(body), 0o644))
|
||||||
|
|
||||||
|
var stop atomic.Bool
|
||||||
|
var wg sync.WaitGroup
|
||||||
|
wg.Add(1)
|
||||||
|
go func() {
|
||||||
|
defer wg.Done()
|
||||||
|
tmp := note + ".swap"
|
||||||
|
for i := 0; !stop.Load(); i++ {
|
||||||
|
_ = os.Remove(tmp)
|
||||||
|
if i%2 == 0 {
|
||||||
|
_ = os.WriteFile(tmp, []byte(body), 0o644)
|
||||||
|
} else {
|
||||||
|
_ = os.Symlink(filepath.Join("..", "..", "..", "raw", "victim.md"), tmp)
|
||||||
|
}
|
||||||
|
_ = os.Rename(tmp, note)
|
||||||
|
}
|
||||||
|
}()
|
||||||
|
ok := 0
|
||||||
|
for deadline := time.Now().Add(1500 * time.Millisecond); time.Now().Before(deadline); {
|
||||||
|
if _, _, _, err := api.UpdateNote(brain, api.UpdateNoteOptions{Path: "wiki/w/facts/n.md", Content: "new"}); err == nil {
|
||||||
|
ok++
|
||||||
|
}
|
||||||
|
}
|
||||||
|
stop.Store(true)
|
||||||
|
wg.Wait()
|
||||||
|
got, _ := os.ReadFile(victim)
|
||||||
|
assert.Equal(t, "untouched\n", string(got))
|
||||||
|
assert.Positive(t, ok, "positive control: some updates reach the regular note")
|
||||||
|
}
|
||||||
@@ -0,0 +1,125 @@
|
|||||||
|
package brain_test
|
||||||
|
|
||||||
|
import (
|
||||||
|
"fmt"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"syscall"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs/brainfstest"
|
||||||
|
)
|
||||||
|
|
||||||
|
// hyperguild#174 / #157 slice 5b: DetectTunnels walked wiki/ and opened
|
||||||
|
// every note with a blocking os.Open, so a FIFO named *.md anywhere under
|
||||||
|
// wiki/ hung every brain_write and brain_update (wikiUpkeep -> AutoTunnel),
|
||||||
|
// and a symlinked note's title became a tunnel candidate.
|
||||||
|
func TestDetectTunnelsReturnsPromptlyWithAFIFOUnderWikiWithAndWithoutAWriter(t *testing.T) {
|
||||||
|
for _, withWriter := range []bool{false, true} {
|
||||||
|
t.Run(fmt.Sprintf("writer=%v", withWriter), func(t *testing.T) {
|
||||||
|
b := t.TempDir()
|
||||||
|
facts := filepath.Join(b, "wiki", "w", "facts")
|
||||||
|
require.NoError(t, os.MkdirAll(facts, 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(facts, "ok.md"), []byte("---\ntitle: Zqinside Phrase\n---\n"), 0o644))
|
||||||
|
fifo := filepath.Join(facts, "f.md")
|
||||||
|
require.NoError(t, syscall.Mkfifo(fifo, 0o644))
|
||||||
|
if withWriter {
|
||||||
|
// A writer held open: a reader that opens the FIFO gets no
|
||||||
|
// EOF and parks, unless the FIFO is never opened.
|
||||||
|
w, err := os.OpenFile(fifo, os.O_RDWR, 0)
|
||||||
|
require.NoError(t, err)
|
||||||
|
t.Cleanup(func() { _ = w.Close() })
|
||||||
|
}
|
||||||
|
done := make(chan []brain.TunnelCandidate, 1)
|
||||||
|
go func() {
|
||||||
|
cs, _ := brain.DetectTunnels(b, "text mentioning zqinside phrase here")
|
||||||
|
done <- cs
|
||||||
|
}()
|
||||||
|
select {
|
||||||
|
case cs := <-done:
|
||||||
|
assert.Contains(t, fmt.Sprintf("%+v", cs), "Zqinside Phrase", "positive control")
|
||||||
|
case <-time.After(3 * time.Second):
|
||||||
|
if r, err := os.OpenFile(fifo, os.O_WRONLY|syscall.O_NONBLOCK, 0); err == nil {
|
||||||
|
_ = r.Close()
|
||||||
|
}
|
||||||
|
t.Fatal("DetectTunnels blocked on a FIFO")
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestDetectTunnelsRefusesSymlinkedNotesAndSurvivesSwapRaces(t *testing.T) {
|
||||||
|
b := t.TempDir()
|
||||||
|
facts := filepath.Join(b, "wiki", "w", "facts")
|
||||||
|
require.NoError(t, os.MkdirAll(facts, 0o755))
|
||||||
|
// The static note's title differs from the raced note's, so the
|
||||||
|
// harness's "inside was read" floor can only be met by reading r.md.
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(facts, "ok.md"), []byte("---\ntitle: Zqstatic Words\n---\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink(brainfstest.Outside(t), filepath.Join(facts, "out.md")))
|
||||||
|
inBrain := brainfstest.WriteSentinelAt(t, filepath.Join(b, "raw", "s.md"))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "in.md")))
|
||||||
|
content := "zqstatic words, zqinside phrase and " + brainfstest.Sentinel
|
||||||
|
|
||||||
|
cs, err := brain.DetectTunnels(b, content)
|
||||||
|
require.NoError(t, err)
|
||||||
|
got := fmt.Sprintf("%+v", cs)
|
||||||
|
assert.Contains(t, got, "Zqstatic Words", "positive control")
|
||||||
|
assert.NotContains(t, got, brainfstest.Sentinel)
|
||||||
|
|
||||||
|
p := filepath.Join(facts, "r.md")
|
||||||
|
read := func() string {
|
||||||
|
cs, _ := brain.DetectTunnels(b, content)
|
||||||
|
return fmt.Sprintf("%+v", cs)
|
||||||
|
}
|
||||||
|
brainfstest.AssertNoLeak(t, p, "---\ntitle: Zqinside Phrase\n---\n", 1500*time.Millisecond, read)
|
||||||
|
brainfstest.AssertNoLeakFrom(t, p, "---\ntitle: Zqinside Phrase\n---\n", inBrain, 1500*time.Millisecond, read)
|
||||||
|
}
|
||||||
|
|
||||||
|
// A wiki/ that is not a real directory yields no candidates and no error:
|
||||||
|
// AutoTunnel runs inside brain_write.
|
||||||
|
func TestDetectTunnelsSkipsAWikiThatIsNotARealDirectory(t *testing.T) {
|
||||||
|
b := t.TempDir()
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(b, "raw", "w", "facts"), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(b, "raw", "w", "facts", "r.md"), []byte("---\ntitle: Zqrawonly Phrase\n---\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink("raw", filepath.Join(b, "wiki")))
|
||||||
|
cs, err := brain.DetectTunnels(b, "zqrawonly phrase")
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Empty(t, cs)
|
||||||
|
}
|
||||||
|
|
||||||
|
// An unreadable directory under wiki/ is a walk error and DetectTunnels
|
||||||
|
// reports it, as filepath.WalkDir did; it is not silently dropped.
|
||||||
|
func TestDetectTunnelsReportsAnUnreadableDirectoryUnderWiki(t *testing.T) {
|
||||||
|
if os.Geteuid() == 0 {
|
||||||
|
t.Skip("root ignores directory permissions")
|
||||||
|
}
|
||||||
|
b := t.TempDir()
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "w", "facts"), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(b, "wiki", "w", "facts", "ok.md"), []byte("---\ntitle: Zqinside Phrase\n---\n"), 0o644))
|
||||||
|
locked := filepath.Join(b, "wiki", "other", "locked")
|
||||||
|
require.NoError(t, os.MkdirAll(locked, 0o755))
|
||||||
|
require.NoError(t, os.Chmod(locked, 0o000))
|
||||||
|
t.Cleanup(func() { _ = os.Chmod(locked, 0o755) })
|
||||||
|
_, err := brain.DetectTunnels(b, "zqinside phrase")
|
||||||
|
assert.ErrorIs(t, err, os.ErrPermission)
|
||||||
|
}
|
||||||
|
|
||||||
|
// _index.md files are generated, not notes: their title never becomes a
|
||||||
|
// candidate.
|
||||||
|
func TestDetectTunnelsSkipsIndexFiles(t *testing.T) {
|
||||||
|
b := t.TempDir()
|
||||||
|
w := filepath.Join(b, "wiki", "w")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(w, "facts"), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(w, "_index.md"), []byte("---\ntitle: Zqindex Words\n---\n"), 0o644))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(w, "facts", "ok.md"), []byte("---\ntitle: Zqinside Phrase\n---\n"), 0o644))
|
||||||
|
cs, err := brain.DetectTunnels(b, "zqindex words and zqinside phrase")
|
||||||
|
require.NoError(t, err)
|
||||||
|
got := fmt.Sprintf("%+v", cs)
|
||||||
|
assert.Contains(t, got, "Zqinside Phrase", "positive control")
|
||||||
|
assert.NotContains(t, got, "Zqindex")
|
||||||
|
}
|
||||||
@@ -116,23 +116,6 @@ func collectWingEntries(bfs *brainfs.Brain, wingRel string) ([]noteEntry, error)
|
|||||||
return out, nil
|
return out, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// readTitleAndCreated reads YAML frontmatter for title + created_at; falls
|
|
||||||
// back to slug and file mtime when absent.
|
|
||||||
func readTitleAndCreated(path, slug string) (string, string) {
|
|
||||||
f, err := os.Open(path)
|
|
||||||
if err != nil {
|
|
||||||
return slug, ""
|
|
||||||
}
|
|
||||||
defer func() { _ = f.Close() }()
|
|
||||||
title, created := parseTitleAndCreated(f)
|
|
||||||
if created == "" {
|
|
||||||
if info, err := os.Stat(path); err == nil {
|
|
||||||
created = info.ModTime().UTC().Format("2006-01-02")
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return titleOrSlug(title, slug), created
|
|
||||||
}
|
|
||||||
|
|
||||||
// readTitleAndCreatedIn is readTitleAndCreated through the brain root,
|
// readTitleAndCreatedIn is readTitleAndCreated through the brain root,
|
||||||
// regular files only (hyperguild#157).
|
// regular files only (hyperguild#157).
|
||||||
func readTitleAndCreatedIn(bfs *brainfs.Brain, rel, slug string) (string, string) {
|
func readTitleAndCreatedIn(bfs *brainfs.Brain, rel, slug string) (string, string) {
|
||||||
|
|||||||
@@ -2,11 +2,16 @@ package brain
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"bufio"
|
"bufio"
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
|
"path"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"strings"
|
"strings"
|
||||||
"time"
|
"time"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||||
)
|
)
|
||||||
|
|
||||||
// seeAlsoHeader is the markdown heading used to group cross-wing links.
|
// seeAlsoHeader is the markdown heading used to group cross-wing links.
|
||||||
@@ -36,24 +41,29 @@ type TunnelCandidate struct {
|
|||||||
// A note's title is read from YAML frontmatter `title:`; failing that,
|
// A note's title is read from YAML frontmatter `title:`; failing that,
|
||||||
// the filename slug (sans `.md`, hyphens → spaces) is used.
|
// the filename slug (sans `.md`, hyphens → spaces) is used.
|
||||||
func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
||||||
wikiDir := filepath.Join(brainDir, "wiki")
|
// Walked and read through the brain root, regular files only
|
||||||
if _, err := os.Stat(wikiDir); os.IsNotExist(err) {
|
// (hyperguild#174, #157): this runs inside every brain_write, so a FIFO
|
||||||
|
// must not block it and a symlinked note's title must not become a
|
||||||
|
// candidate.
|
||||||
|
bfs, err := brainfs.Open(brainDir)
|
||||||
|
if err != nil {
|
||||||
|
return nil, fmt.Errorf("open brain: %w", err)
|
||||||
|
}
|
||||||
|
defer func() { _ = bfs.Close() }()
|
||||||
|
if _, err := bfs.Lstat("wiki"); errors.Is(err, fs.ErrNotExist) {
|
||||||
return nil, nil
|
return nil, nil
|
||||||
} else if err != nil {
|
|
||||||
return nil, fmt.Errorf("stat wiki: %w", err)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
lowerContent := strings.ToLower(content)
|
lowerContent := strings.ToLower(content)
|
||||||
|
|
||||||
var out []TunnelCandidate
|
var out []TunnelCandidate
|
||||||
err := filepath.WalkDir(wikiDir, func(path string, d os.DirEntry, err error) error {
|
var walkErr error
|
||||||
if err != nil {
|
err = bfs.WalkRegular("wiki", func(rel string) error {
|
||||||
return err
|
name := path.Base(rel)
|
||||||
}
|
if !strings.HasSuffix(name, ".md") || name == "_index.md" {
|
||||||
if d.IsDir() || !strings.HasSuffix(path, ".md") || d.Name() == "_index.md" {
|
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
title, _ := readTitleAndCreated(path, strings.TrimSuffix(d.Name(), ".md"))
|
title, _ := readTitleAndCreatedIn(bfs, rel, strings.TrimSuffix(name, ".md"))
|
||||||
title = strings.TrimSpace(title)
|
title = strings.TrimSpace(title)
|
||||||
if title == "" {
|
if title == "" {
|
||||||
return nil
|
return nil
|
||||||
@@ -75,17 +85,25 @@ func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
|||||||
if idx == -1 {
|
if idx == -1 {
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
rel, err := filepath.Rel(brainDir, path)
|
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
out = append(out, TunnelCandidate{
|
out = append(out, TunnelCandidate{
|
||||||
TargetPath: filepath.ToSlash(rel),
|
TargetPath: rel,
|
||||||
MatchedTerm: title,
|
MatchedTerm: title,
|
||||||
Exact: isWholeWord(haystack, idx, len(needle)),
|
Exact: isWholeWord(haystack, idx, len(needle)),
|
||||||
})
|
})
|
||||||
return nil
|
return nil
|
||||||
|
}, func(rel string, err error) {
|
||||||
|
// A wiki/ that is not a real directory yields no candidates, as
|
||||||
|
// filepath.WalkDir did; other walk errors still abort.
|
||||||
|
if rel == "wiki" && errors.Is(err, brainfs.ErrNotRegular) {
|
||||||
|
return
|
||||||
|
}
|
||||||
|
if walkErr == nil {
|
||||||
|
walkErr = fmt.Errorf("%s: %w", rel, err)
|
||||||
|
}
|
||||||
})
|
})
|
||||||
|
if err == nil {
|
||||||
|
err = walkErr
|
||||||
|
}
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
@@ -197,6 +215,12 @@ func fileExists(p string) bool {
|
|||||||
// section headers. Rejects same-wing pairs (a tunnel is by definition
|
// section headers. Rejects same-wing pairs (a tunnel is by definition
|
||||||
// cross-wing) and missing notes.
|
// cross-wing) and missing notes.
|
||||||
func WriteTunnel(brainDir, sourcePath, targetPath string) error {
|
func WriteTunnel(brainDir, sourcePath, targetPath string) error {
|
||||||
|
if err := checkNotePath(sourcePath); err != nil {
|
||||||
|
return fmt.Errorf("source: %w", err)
|
||||||
|
}
|
||||||
|
if err := checkNotePath(targetPath); err != nil {
|
||||||
|
return fmt.Errorf("target: %w", err)
|
||||||
|
}
|
||||||
srcWing, err := wingOf(sourcePath)
|
srcWing, err := wingOf(sourcePath)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return fmt.Errorf("source: %w", err)
|
return fmt.Errorf("source: %w", err)
|
||||||
@@ -209,20 +233,50 @@ func WriteTunnel(brainDir, sourcePath, targetPath string) error {
|
|||||||
return fmt.Errorf("tunnel must cross wings; got both in %q", srcWing)
|
return fmt.Errorf("tunnel must cross wings; got both in %q", srcWing)
|
||||||
}
|
}
|
||||||
|
|
||||||
srcFull := filepath.Join(brainDir, filepath.FromSlash(sourcePath))
|
// Both notes are read and rewritten through the brain root, regular
|
||||||
tgtFull := filepath.Join(brainDir, filepath.FromSlash(targetPath))
|
// files only: brain_tunnel passes caller-supplied paths, and the brain is
|
||||||
if _, err := os.Stat(srcFull); err != nil {
|
// a Syncthing folder that can hold symlinks.
|
||||||
|
bfs, err := brainfs.Open(brainDir)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("open brain: %w", err)
|
||||||
|
}
|
||||||
|
defer func() { _ = bfs.Close() }()
|
||||||
|
srcContent, err := bfs.ReadRegular(sourcePath)
|
||||||
|
if err != nil {
|
||||||
return fmt.Errorf("source note: %w", err)
|
return fmt.Errorf("source note: %w", err)
|
||||||
}
|
}
|
||||||
if _, err := os.Stat(tgtFull); err != nil {
|
tgtContent, err := bfs.ReadRegular(targetPath)
|
||||||
|
if err != nil {
|
||||||
return fmt.Errorf("target note: %w", err)
|
return fmt.Errorf("target note: %w", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
if err := appendSeeAlso(srcFull, wikilinkOf(targetPath)); err != nil {
|
if out, changed, err := withSeeAlso(srcContent, wikilinkOf(targetPath)); err != nil {
|
||||||
|
return fmt.Errorf("update source: %w", err)
|
||||||
|
} else if changed {
|
||||||
|
if err := bfs.WriteRegular(sourcePath, out); err != nil {
|
||||||
return fmt.Errorf("update source: %w", err)
|
return fmt.Errorf("update source: %w", err)
|
||||||
}
|
}
|
||||||
if err := appendSeeAlso(tgtFull, wikilinkOf(sourcePath)); err != nil {
|
}
|
||||||
|
if out, changed, err := withSeeAlso(tgtContent, wikilinkOf(sourcePath)); err != nil {
|
||||||
return fmt.Errorf("update target: %w", err)
|
return fmt.Errorf("update target: %w", err)
|
||||||
|
} else if changed {
|
||||||
|
if err := bfs.WriteRegular(targetPath, out); err != nil {
|
||||||
|
return fmt.Errorf("update target: %w", err)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// checkNotePath accepts only a clean, local wiki/<wing>/<hall>/.../<slug>.md
|
||||||
|
// path: no "." or ".." segments, no empty segments, no leading slash.
|
||||||
|
func checkNotePath(p string) error {
|
||||||
|
if p == "" || path.Clean(p) != p || !filepath.IsLocal(p) || !strings.HasSuffix(p, ".md") {
|
||||||
|
return fmt.Errorf("not a clean wiki note path: %q", p)
|
||||||
|
}
|
||||||
|
for _, part := range strings.Split(p, "/") {
|
||||||
|
if part == "" || part == "." || part == ".." {
|
||||||
|
return fmt.Errorf("not a clean wiki note path: %q", p)
|
||||||
|
}
|
||||||
}
|
}
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
@@ -248,16 +302,13 @@ func wingOf(relPath string) (string, error) {
|
|||||||
return parts[1], nil
|
return parts[1], nil
|
||||||
}
|
}
|
||||||
|
|
||||||
// appendSeeAlso inserts `- [[link]]` under the file's See also section,
|
// withSeeAlso returns content with `- [[link]]` under its See also section,
|
||||||
// creating the section if absent. No-op when the link is already present.
|
// creating the section if absent. changed is false when the link is already
|
||||||
func appendSeeAlso(filePath, link string) error {
|
// present.
|
||||||
content, err := os.ReadFile(filePath)
|
func withSeeAlso(content []byte, link string) (out []byte, changed bool, err error) {
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
wikilink := "[[" + link + "]]"
|
wikilink := "[[" + link + "]]"
|
||||||
if strings.Contains(string(content), wikilink) {
|
if strings.Contains(string(content), wikilink) {
|
||||||
return nil
|
return content, false, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
bullet := "- " + wikilink
|
bullet := "- " + wikilink
|
||||||
@@ -266,8 +317,7 @@ func appendSeeAlso(filePath, link string) error {
|
|||||||
// No section yet — append a fresh one. Always emit a trailing
|
// No section yet — append a fresh one. Always emit a trailing
|
||||||
// newline so subsequent appends don't merge into the previous line.
|
// newline so subsequent appends don't merge into the previous line.
|
||||||
trimmed := strings.TrimRight(string(content), "\n")
|
trimmed := strings.TrimRight(string(content), "\n")
|
||||||
out := trimmed + "\n\n" + seeAlsoHeader + "\n\n" + bullet + "\n"
|
return []byte(trimmed + "\n\n" + seeAlsoHeader + "\n\n" + bullet + "\n"), true, nil
|
||||||
return os.WriteFile(filePath, []byte(out), 0o644)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Section exists — splice the bullet in just before the next `## `
|
// Section exists — splice the bullet in just before the next `## `
|
||||||
@@ -293,12 +343,11 @@ func appendSeeAlso(filePath, link string) error {
|
|||||||
b.WriteByte('\n')
|
b.WriteByte('\n')
|
||||||
}
|
}
|
||||||
if err := scanner.Err(); err != nil {
|
if err := scanner.Err(); err != nil {
|
||||||
return err
|
return nil, false, err
|
||||||
}
|
}
|
||||||
if !inserted {
|
if !inserted {
|
||||||
// section was the last thing in the file — just append bullet
|
// section was the last thing in the file — just append bullet
|
||||||
out := strings.TrimRight(b.String(), "\n") + "\n" + bullet + "\n"
|
return []byte(strings.TrimRight(b.String(), "\n") + "\n" + bullet + "\n"), true, nil
|
||||||
return os.WriteFile(filePath, []byte(out), 0o644)
|
|
||||||
}
|
}
|
||||||
return os.WriteFile(filePath, []byte(b.String()), 0o644)
|
return []byte(b.String()), true, nil
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,38 @@
|
|||||||
|
package brain_test
|
||||||
|
|
||||||
|
import (
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||||
|
)
|
||||||
|
|
||||||
|
// hyperguild#173: brain_tunnel's write followed a directory symlink inside
|
||||||
|
// wiki/ that points elsewhere in the brain.
|
||||||
|
func TestWriteTunnelRefusesATargetBehindASymlinkedDirectory(t *testing.T) {
|
||||||
|
b := t.TempDir()
|
||||||
|
src := filepath.Join(b, "wiki", "a", "facts", "s.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(src), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(src, []byte("x\n"), 0o644))
|
||||||
|
victim := filepath.Join(b, "raw", "facts", "v.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "b"), 0o755))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "facts"), filepath.Join(b, "wiki", "b", "facts")))
|
||||||
|
|
||||||
|
assert.ErrorIs(t, brain.WriteTunnel(b, "wiki/a/facts/s.md", "wiki/b/facts/v.md"), brainfs.ErrNotRegular)
|
||||||
|
got, _ := os.ReadFile(victim)
|
||||||
|
assert.Equal(t, "untouched\n", string(got))
|
||||||
|
got, _ = os.ReadFile(src)
|
||||||
|
assert.Equal(t, "x\n", string(got), "the source is not rewritten either")
|
||||||
|
|
||||||
|
real := filepath.Join(b, "wiki", "c", "facts", "t.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(real), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(real, []byte("t\n"), 0o644))
|
||||||
|
require.NoError(t, brain.WriteTunnel(b, "wiki/a/facts/s.md", "wiki/c/facts/t.md"), "positive control: a tunnel between real directories is written")
|
||||||
|
}
|
||||||
@@ -0,0 +1,141 @@
|
|||||||
|
package brain_test
|
||||||
|
|
||||||
|
import (
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"strings"
|
||||||
|
"sync"
|
||||||
|
"sync/atomic"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
|
||||||
|
)
|
||||||
|
|
||||||
|
// brain_tunnel passes caller-supplied source and target paths to WriteTunnel,
|
||||||
|
// which checked only "wiki/<wing>/..." and then joined them onto the brain
|
||||||
|
// dir: ".." segments resolved outside the brain and appendSeeAlso rewrote the
|
||||||
|
// file there.
|
||||||
|
func TestWriteTunnelRefusesATargetThatTraversesOutOfTheBrain(t *testing.T) {
|
||||||
|
brain0 := t.TempDir()
|
||||||
|
src := filepath.Join(brain0, "wiki", "a", "facts", "s.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(src), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(src, []byte("---\ntitle: S\n---\nbody\n"), 0o644))
|
||||||
|
victim := filepath.Join(t.TempDir(), "victim.md")
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
|
||||||
|
up := strings.Repeat("../", strings.Count(filepath.Clean(brain0), "/")+3)
|
||||||
|
target := "wiki/b/x/" + up + strings.TrimPrefix(victim, "/")
|
||||||
|
err := brain.WriteTunnel(brain0, "wiki/a/facts/s.md", target)
|
||||||
|
assert.Error(t, err)
|
||||||
|
got, rerr := os.ReadFile(victim)
|
||||||
|
require.NoError(t, rerr)
|
||||||
|
assert.Equal(t, "untouched\n", string(got), "a file outside the brain was modified")
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWriteTunnelRefusesUncleanOrNonWikiPaths(t *testing.T) {
|
||||||
|
brain0 := t.TempDir()
|
||||||
|
for _, p := range []string{"wiki/a/facts/s.md", "wiki/b/facts/t.md", "wiki/b/facts/t.txt", "raw/r.md"} {
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(filepath.Join(brain0, p)), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain0, p), []byte("x\n"), 0o644))
|
||||||
|
}
|
||||||
|
for _, target := range []string{
|
||||||
|
"wiki/b/facts/../../../raw/r.md",
|
||||||
|
"wiki/b/./facts/t.md",
|
||||||
|
"wiki/b//facts/t.md",
|
||||||
|
"/wiki/b/facts/t.md",
|
||||||
|
"wiki/b/facts/t.txt",
|
||||||
|
"wiki/b/facts/",
|
||||||
|
} {
|
||||||
|
assert.Error(t, brain.WriteTunnel(brain0, "wiki/a/facts/s.md", target), target)
|
||||||
|
}
|
||||||
|
for _, p := range []string{"raw/r.md", "wiki/b/facts/t.txt"} {
|
||||||
|
got, err := os.ReadFile(filepath.Join(brain0, p))
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "x\n", string(got), p)
|
||||||
|
}
|
||||||
|
require.NoError(t, brain.WriteTunnel(brain0, "wiki/a/facts/s.md", "wiki/b/facts/t.md"), "positive control")
|
||||||
|
got, err := os.ReadFile(filepath.Join(brain0, "wiki", "b", "facts", "t.md"))
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Contains(t, string(got), "[[a/facts/s]]")
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWriteTunnelDoesNotWriteThroughASymlinkedNote(t *testing.T) {
|
||||||
|
brain0 := t.TempDir()
|
||||||
|
src := filepath.Join(brain0, "wiki", "a", "facts", "s.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(src), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(src, []byte("x\n"), 0o644))
|
||||||
|
tdir := filepath.Join(brain0, "wiki", "b", "facts")
|
||||||
|
require.NoError(t, os.MkdirAll(tdir, 0o755))
|
||||||
|
victim := filepath.Join(t.TempDir(), "victim.md")
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink(victim, filepath.Join(tdir, "t.md")))
|
||||||
|
assert.Error(t, brain.WriteTunnel(brain0, "wiki/a/facts/s.md", "wiki/b/facts/t.md"))
|
||||||
|
got, err := os.ReadFile(victim)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "untouched\n", string(got))
|
||||||
|
|
||||||
|
// The same with a link to a file elsewhere in the brain, which os.Root
|
||||||
|
// would follow.
|
||||||
|
inVictim := filepath.Join(brain0, "raw", "v.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(inVictim), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(inVictim, []byte("untouched\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "v.md"), filepath.Join(tdir, "u.md")))
|
||||||
|
assert.Error(t, brain.WriteTunnel(brain0, "wiki/a/facts/s.md", "wiki/b/facts/u.md"))
|
||||||
|
got, err = os.ReadFile(inVictim)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "untouched\n", string(got))
|
||||||
|
got, err = os.ReadFile(src)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "x\n", string(got), "the source is not touched when the target is refused")
|
||||||
|
}
|
||||||
|
|
||||||
|
// The target is swapped between a regular note and a symlink to an in-brain
|
||||||
|
// file outside wiki/ while WriteTunnel runs: the read and the write each
|
||||||
|
// refuse a symlink, so the other file is never rewritten.
|
||||||
|
func TestWriteTunnelNeverRewritesASymlinkSwappedInForTheTarget(t *testing.T) {
|
||||||
|
brain0 := t.TempDir()
|
||||||
|
src := filepath.Join(brain0, "wiki", "a", "facts", "s.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(src), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(src, []byte("x\n"), 0o644))
|
||||||
|
tdir := filepath.Join(brain0, "wiki", "b", "facts")
|
||||||
|
require.NoError(t, os.MkdirAll(tdir, 0o755))
|
||||||
|
victim := filepath.Join(brain0, "raw", "victim.md")
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
tgt := filepath.Join(tdir, "t.md")
|
||||||
|
require.NoError(t, os.WriteFile(tgt, []byte("t\n"), 0o644))
|
||||||
|
|
||||||
|
var stop atomic.Bool
|
||||||
|
var wg sync.WaitGroup
|
||||||
|
wg.Add(1)
|
||||||
|
go func() {
|
||||||
|
defer wg.Done()
|
||||||
|
tmp := tgt + ".swap"
|
||||||
|
for i := 0; !stop.Load(); i++ {
|
||||||
|
_ = os.Remove(tmp)
|
||||||
|
if i%2 == 0 {
|
||||||
|
_ = os.WriteFile(tmp, []byte("t\n"), 0o644)
|
||||||
|
} else {
|
||||||
|
_ = os.Symlink(filepath.Join("..", "..", "..", "raw", "victim.md"), tmp)
|
||||||
|
}
|
||||||
|
_ = os.Rename(tmp, tgt)
|
||||||
|
}
|
||||||
|
}()
|
||||||
|
ok := 0
|
||||||
|
for deadline := time.Now().Add(1500 * time.Millisecond); time.Now().Before(deadline); {
|
||||||
|
if brain.WriteTunnel(brain0, "wiki/a/facts/s.md", "wiki/b/facts/t.md") == nil {
|
||||||
|
ok++
|
||||||
|
}
|
||||||
|
_ = os.WriteFile(src, []byte("x\n"), 0o644)
|
||||||
|
}
|
||||||
|
stop.Store(true)
|
||||||
|
wg.Wait()
|
||||||
|
got, err := os.ReadFile(victim)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "untouched\n", string(got), "the swapped-in symlink's target was rewritten")
|
||||||
|
assert.Positive(t, ok, "positive control: some tunnels were written to the regular target")
|
||||||
|
}
|
||||||
@@ -104,6 +104,17 @@ func (b *Brain) ReadDirRegular(relDir string) ([]string, error) {
|
|||||||
return names, nil
|
return names, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// cleanRel refuses a path that is not clean and local. realDir checks the
|
||||||
|
// cleaned parent, so the I/O must use that same path: os.Root resolves ".."
|
||||||
|
// after following a symlink, and a ".." after a symlinked directory would
|
||||||
|
// otherwise pass the check and redirect the read or write.
|
||||||
|
func cleanRel(rel string) error {
|
||||||
|
if rel == "" || path.Clean(rel) != rel || !filepath.IsLocal(rel) || strings.Contains(rel, "\\") {
|
||||||
|
return fmt.Errorf("%q: not a clean brain-relative path: %w", rel, ErrNotRegular)
|
||||||
|
}
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
// ReadDirDirs lists the real subdirectories directly in a brain-relative
|
// ReadDirDirs lists the real subdirectories directly in a brain-relative
|
||||||
// directory, by name. Every component of relDir must be a real directory
|
// directory, by name. Every component of relDir must be a real directory
|
||||||
// (ErrNotRegular otherwise); symlinks to directories are left out.
|
// (ErrNotRegular otherwise); symlinks to directories are left out.
|
||||||
@@ -128,6 +139,12 @@ func (b *Brain) ReadDirDirs(relDir string) ([]string, error) {
|
|||||||
// ReadRegular reads a brain-relative path, refusing anything that is not a
|
// ReadRegular reads a brain-relative path, refusing anything that is not a
|
||||||
// regular file, both before the open and on the opened handle.
|
// regular file, both before the open and on the opened handle.
|
||||||
func (b *Brain) ReadRegular(rel string) ([]byte, error) {
|
func (b *Brain) ReadRegular(rel string) ([]byte, error) {
|
||||||
|
if err := cleanRel(rel); err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
if err := b.realDir(path.Dir(rel)); err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
fi, err := b.root.Lstat(rel)
|
fi, err := b.root.Lstat(rel)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
@@ -154,6 +171,12 @@ func (b *Brain) readOpened(rel string) ([]byte, error) { return b.readOpenedMax(
|
|||||||
// ReadRegularMax is ReadRegular with a size limit, checked on the opened
|
// ReadRegularMax is ReadRegular with a size limit, checked on the opened
|
||||||
// handle before reading (max < 0 means no limit).
|
// handle before reading (max < 0 means no limit).
|
||||||
func (b *Brain) ReadRegularMax(rel string, max int64) ([]byte, error) {
|
func (b *Brain) ReadRegularMax(rel string, max int64) ([]byte, error) {
|
||||||
|
if err := cleanRel(rel); err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
if err := b.realDir(path.Dir(rel)); err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
fi, err := b.root.Lstat(rel)
|
fi, err := b.root.Lstat(rel)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
@@ -249,3 +272,51 @@ func (b *Brain) WalkRegular(relDir string, fn func(rel string) error, onErr func
|
|||||||
return fn(p)
|
return fn(p)
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// WriteRegular replaces the contents of an existing regular file at a
|
||||||
|
// brain-relative path. It never creates a file and never writes through a
|
||||||
|
// final symlink: os.Root.OpenFile follows an in-root final symlink even with
|
||||||
|
// O_NOFOLLOW (verified on go1.27), so the path is Lstat-ed through the root
|
||||||
|
// first and the opened handle must be that same file (os.SameFile), which
|
||||||
|
// also catches a swap between the two. O_NONBLOCK keeps a FIFO from blocking
|
||||||
|
// the open. Every directory above the file must be a real directory
|
||||||
|
// (hyperguild#173); a directory swapped in after that check is the #167
|
||||||
|
// residual.
|
||||||
|
func (b *Brain) WriteRegular(rel string, data []byte) error {
|
||||||
|
if err := cleanRel(rel); err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
// Every directory above the file must be real: os.Root follows an
|
||||||
|
// in-brain intermediate symlink, which would redirect the write
|
||||||
|
// elsewhere in the brain (hyperguild#173). A swap after this check is
|
||||||
|
// the #167 residual.
|
||||||
|
if err := b.realDir(path.Dir(rel)); err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
lfi, err := b.root.Lstat(rel)
|
||||||
|
if err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
if !lfi.Mode().IsRegular() {
|
||||||
|
return fmt.Errorf("%s: %w", rel, ErrNotRegular)
|
||||||
|
}
|
||||||
|
f, err := b.root.OpenFile(rel, os.O_WRONLY|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0)
|
||||||
|
if err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
defer func() { _ = f.Close() }()
|
||||||
|
fi, err := f.Stat()
|
||||||
|
if err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
if !fi.Mode().IsRegular() || !os.SameFile(lfi, fi) {
|
||||||
|
return fmt.Errorf("%s: changed while opening: %w", rel, ErrNotRegular)
|
||||||
|
}
|
||||||
|
if err := f.Truncate(0); err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
if _, err := f.Write(data); err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
return f.Close()
|
||||||
|
}
|
||||||
|
|||||||
@@ -218,7 +218,7 @@ func TestReadDirRegularListsOnlyRegularFilesAndRefusesSymlinkedComponents(t *tes
|
|||||||
// A final component swapped for a symlink to another regular file in the
|
// A final component swapped for a symlink to another regular file in the
|
||||||
// brain between the Lstat and the open: os.Root follows in-root links, so
|
// brain between the Lstat and the open: os.Root follows in-root links, so
|
||||||
// only comparing the two (os.SameFile) refuses it.
|
// only comparing the two (os.SameFile) refuses it.
|
||||||
func TestReadRegularNeverReturnsAnInBrainFileSwappedInBehindASymlink(t *testing.T) {
|
func TestReadRegularDoesNotReturnAnInBrainFileSwappedInBehindASymlink(t *testing.T) {
|
||||||
dir := t.TempDir()
|
dir := t.TempDir()
|
||||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "s.md"), []byte("zqsamefilesentinel"), 0o644))
|
require.NoError(t, os.WriteFile(filepath.Join(dir, "s.md"), []byte("zqsamefilesentinel"), 0o644))
|
||||||
p := filepath.Join(dir, "r.md")
|
p := filepath.Join(dir, "r.md")
|
||||||
@@ -263,6 +263,52 @@ func TestReadRegularNeverReturnsAnInBrainFileSwappedInBehindASymlink(t *testing.
|
|||||||
assert.Positive(t, ok, "positive control: the regular file is read")
|
assert.Positive(t, ok, "positive control: the regular file is read")
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestWriteRegularRefusesFinalSymlinksFIFOsEscapesAndMissingFilesAndRewritesRegularFiles(t *testing.T) {
|
||||||
|
dir := t.TempDir()
|
||||||
|
outside := filepath.Join(t.TempDir(), "o.md")
|
||||||
|
require.NoError(t, os.WriteFile(outside, []byte("untouched"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink(outside, filepath.Join(dir, "l.md")))
|
||||||
|
require.NoError(t, syscall.Mkfifo(filepath.Join(dir, "f.md"), 0o644))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(dir, "n.md"), []byte("old content"), 0o644))
|
||||||
|
b, err := Open(dir)
|
||||||
|
require.NoError(t, err)
|
||||||
|
defer func() { _ = b.Close() }()
|
||||||
|
|
||||||
|
assert.Error(t, b.WriteRegular("l.md", []byte("x")))
|
||||||
|
got, _ := os.ReadFile(outside)
|
||||||
|
assert.Equal(t, "untouched", string(got))
|
||||||
|
|
||||||
|
// A symlink to another file inside the brain: os.Root would allow it,
|
||||||
|
// only O_NOFOLLOW refuses it.
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(dir, "in.md"), []byte("inside"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink("in.md", filepath.Join(dir, "il.md")))
|
||||||
|
assert.Error(t, b.WriteRegular("il.md", []byte("x")))
|
||||||
|
got, _ = os.ReadFile(filepath.Join(dir, "in.md"))
|
||||||
|
assert.Equal(t, "inside", string(got))
|
||||||
|
|
||||||
|
// A reader held open, so a non-blocking write open would succeed. The
|
||||||
|
// Lstat type check refuses the FIFO first; the handle check and
|
||||||
|
// O_NONBLOCK matter only if it is swapped in after the Lstat.
|
||||||
|
r, err := os.OpenFile(filepath.Join(dir, "f.md"), os.O_RDONLY|syscall.O_NONBLOCK, 0)
|
||||||
|
require.NoError(t, err)
|
||||||
|
defer func() { _ = r.Close() }()
|
||||||
|
done := make(chan error, 1)
|
||||||
|
go func() { done <- b.WriteRegular("f.md", []byte("x")) }()
|
||||||
|
select {
|
||||||
|
case err := <-done:
|
||||||
|
assert.Error(t, err)
|
||||||
|
case <-time.After(3 * time.Second):
|
||||||
|
t.Fatal("WriteRegular hung on a FIFO")
|
||||||
|
}
|
||||||
|
|
||||||
|
assert.Error(t, b.WriteRegular("../"+filepath.Base(filepath.Dir(outside))+"/o.md", []byte("x")))
|
||||||
|
assert.Error(t, b.WriteRegular("missing.md", []byte("x")), "does not create files")
|
||||||
|
|
||||||
|
require.NoError(t, b.WriteRegular("n.md", []byte("new")))
|
||||||
|
got, _ = os.ReadFile(filepath.Join(dir, "n.md"))
|
||||||
|
assert.Equal(t, "new", string(got), "truncated and rewritten")
|
||||||
|
}
|
||||||
|
|
||||||
func TestReadDirDirsListsOnlyRealSubdirsAndRefusesSymlinkedComponents(t *testing.T) {
|
func TestReadDirDirsListsOnlyRealSubdirsAndRefusesSymlinkedComponents(t *testing.T) {
|
||||||
dir := t.TempDir()
|
dir := t.TempDir()
|
||||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "a", "real"), 0o755))
|
require.NoError(t, os.MkdirAll(filepath.Join(dir, "a", "real"), 0o755))
|
||||||
@@ -280,3 +326,53 @@ func TestReadDirDirsListsOnlyRealSubdirsAndRefusesSymlinkedComponents(t *testing
|
|||||||
_, err = b.ReadDirDirs("alias")
|
_, err = b.ReadDirDirs("alias")
|
||||||
assert.ErrorIs(t, err, ErrNotRegular)
|
assert.ErrorIs(t, err, ErrNotRegular)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// hyperguild#173: a file reached through a symlinked directory inside the
|
||||||
|
// brain is refused for reads and writes, so a caller-supplied path cannot be
|
||||||
|
// redirected to another part of the brain.
|
||||||
|
func TestReadAndWriteRegularRefuseAFileBehindASymlinkedDirectory(t *testing.T) {
|
||||||
|
dir := t.TempDir()
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "alias")))
|
||||||
|
b, err := Open(dir)
|
||||||
|
require.NoError(t, err)
|
||||||
|
defer func() { _ = b.Close() }()
|
||||||
|
|
||||||
|
_, err = b.ReadRegular("wiki/alias/v.md")
|
||||||
|
assert.ErrorIs(t, err, ErrNotRegular)
|
||||||
|
_, err = b.ReadRegularMax("wiki/alias/v.md", 100)
|
||||||
|
assert.ErrorIs(t, err, ErrNotRegular)
|
||||||
|
assert.ErrorIs(t, b.WriteRegular("wiki/alias/v.md", []byte("x")), ErrNotRegular)
|
||||||
|
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
|
||||||
|
assert.Equal(t, "untouched", string(got))
|
||||||
|
got, err = b.ReadRegular("raw/v.md")
|
||||||
|
require.NoError(t, err, "positive control: the real path still reads")
|
||||||
|
assert.Equal(t, "untouched", string(got))
|
||||||
|
}
|
||||||
|
|
||||||
|
// realDir checks the cleaned parent, so the I/O must use that same clean
|
||||||
|
// path: os.Root resolves ".." after following a symlink, and a ".." placed
|
||||||
|
// after a symlinked directory would otherwise pass the check and redirect.
|
||||||
|
func TestReadAndWriteRegularRefuseAPathThatIsNotClean(t *testing.T) {
|
||||||
|
dir := t.TempDir()
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw", "facts"), 0o755))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "raw", "facts"), filepath.Join(dir, "wiki", "alias")))
|
||||||
|
b, err := Open(dir)
|
||||||
|
require.NoError(t, err)
|
||||||
|
defer func() { _ = b.Close() }()
|
||||||
|
|
||||||
|
for _, rel := range []string{"wiki/alias/../v.md", "./raw/v.md", "raw//v.md", "/raw/v.md"} {
|
||||||
|
got, err := b.ReadRegular(rel)
|
||||||
|
assert.ErrorIs(t, err, ErrNotRegular, rel)
|
||||||
|
assert.NotContains(t, string(got), "untouched", rel)
|
||||||
|
_, err = b.ReadRegularMax(rel, 100)
|
||||||
|
assert.ErrorIs(t, err, ErrNotRegular, rel)
|
||||||
|
assert.ErrorIs(t, b.WriteRegular(rel, []byte("OVERWRITTEN")), ErrNotRegular, rel)
|
||||||
|
}
|
||||||
|
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
|
||||||
|
assert.Equal(t, "untouched", string(got))
|
||||||
|
}
|
||||||
|
|||||||
@@ -1,8 +1,10 @@
|
|||||||
// Package brainfstest is the shared harness for hyperguild#157's swap-race
|
// Package brainfstest is the shared harness for hyperguild#157's swap-race
|
||||||
// tests: it keeps swapping a regular note, a symlink to an outside file, or a
|
// tests: it keeps swapping a regular note, a symlink to a sentinel target file
|
||||||
// FIFO (with a writer held open) into a path while a reader under test loops.
|
// (outside the brain, or inside it for hyperguild#171), or a FIFO (with a
|
||||||
// It observes two things: no sentinel byte from the outside file reaches the
|
// writer held open) into a path while a reader under test loops.
|
||||||
// reader's output, and the reader returns within a timeout. It does not cover
|
// It observes two things, over a sampled window only: no sentinel byte from
|
||||||
|
// the target reaches the reader's output, and the reader returns within a
|
||||||
|
// timeout. It does not cover
|
||||||
// hard links, other paths into the reader, or races it does not generate.
|
// hard links, other paths into the reader, or races it does not generate.
|
||||||
package brainfstest
|
package brainfstest
|
||||||
|
|
||||||
@@ -18,7 +20,7 @@ import (
|
|||||||
"time"
|
"time"
|
||||||
)
|
)
|
||||||
|
|
||||||
// Sentinel marks the outside file's contents.
|
// Sentinel marks the target file's contents.
|
||||||
const Sentinel = "zqbrainfssentinelonefiftyseven"
|
const Sentinel = "zqbrainfssentinelonefiftyseven"
|
||||||
|
|
||||||
// outsideContent carries Sentinel in every field a reader might extract: the
|
// outsideContent carries Sentinel in every field a reader might extract: the
|
||||||
@@ -141,7 +143,7 @@ func AssertNoLeakFrom(t testing.TB, path, inside, target string, d time.Duration
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
if leaks > 0 {
|
if leaks > 0 {
|
||||||
t.Fatalf("outside file leaked %d times in %d iterations", leaks, iters)
|
t.Fatalf("symlink target %s leaked %d times in %d iterations", target, leaks, iters)
|
||||||
}
|
}
|
||||||
if n := swaps.Load(); n == 0 {
|
if n := swaps.Load(); n == 0 {
|
||||||
t.Fatalf("no symlink was swapped into %s in %d iterations: the race did not run", path, iters)
|
t.Fatalf("no symlink was swapped into %s in %d iterations: the race did not run", path, iters)
|
||||||
|
|||||||
@@ -16,9 +16,10 @@
|
|||||||
package classification
|
package classification
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"os"
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||||
"path/filepath"
|
"io/fs"
|
||||||
"strings"
|
"strings"
|
||||||
|
|
||||||
"gopkg.in/yaml.v3"
|
"gopkg.in/yaml.v3"
|
||||||
@@ -110,9 +111,20 @@ type rawConfig struct {
|
|||||||
func Load(brainDir string) (*Config, error) {
|
func Load(brainDir string) (*Config, error) {
|
||||||
cfg := &Config{wings: map[string]Level{}, repos: map[string]Level{}}
|
cfg := &Config{wings: map[string]Level{}, repos: map[string]Level{}}
|
||||||
|
|
||||||
data, err := os.ReadFile(filepath.Join(brainDir, "classification.yaml"))
|
// Read through the brain root, regular files only (hyperguild#157): a
|
||||||
|
// symlinked or special file is not trusted as the config, which is a hard
|
||||||
|
// error like a malformed one.
|
||||||
|
bfs, err := brainfs.Open(brainDir)
|
||||||
|
if errors.Is(err, fs.ErrNotExist) {
|
||||||
|
return cfg, nil
|
||||||
|
}
|
||||||
if err != nil {
|
if err != nil {
|
||||||
if os.IsNotExist(err) {
|
return nil, fmt.Errorf("open brain: %w", err)
|
||||||
|
}
|
||||||
|
defer func() { _ = bfs.Close() }()
|
||||||
|
data, err := bfs.ReadRegular("classification.yaml")
|
||||||
|
if err != nil {
|
||||||
|
if errors.Is(err, fs.ErrNotExist) {
|
||||||
return cfg, nil
|
return cfg, nil
|
||||||
}
|
}
|
||||||
return nil, fmt.Errorf("read classification.yaml: %w", err)
|
return nil, fmt.Errorf("read classification.yaml: %w", err)
|
||||||
|
|||||||
@@ -0,0 +1,46 @@
|
|||||||
|
package classification
|
||||||
|
|
||||||
|
import (
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"syscall"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
)
|
||||||
|
|
||||||
|
// hyperguild#157 slice 6: Load read classification.yaml with os.ReadFile. It
|
||||||
|
// sets the I1 sovereignty levels; a symlinked file must not be trusted as the
|
||||||
|
// config (a hard error, as for a malformed file), and a FIFO must not hang
|
||||||
|
// startup.
|
||||||
|
func TestLoadRefusesASymlinkedOrFIFOClassificationFile(t *testing.T) {
|
||||||
|
ok := t.TempDir()
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(ok, "classification.yaml"), []byte("wings:\n w: confidential\n"), 0o644))
|
||||||
|
_, err := Load(ok)
|
||||||
|
require.NoError(t, err, "positive control")
|
||||||
|
|
||||||
|
linked := t.TempDir()
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(linked, "real.yaml"), []byte("wings:\n w: public\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink("real.yaml", filepath.Join(linked, "classification.yaml")))
|
||||||
|
_, err = Load(linked)
|
||||||
|
assert.Error(t, err, "an in-brain symlink is not trusted as the config")
|
||||||
|
|
||||||
|
fifo := t.TempDir()
|
||||||
|
require.NoError(t, syscall.Mkfifo(filepath.Join(fifo, "classification.yaml"), 0o644))
|
||||||
|
w, err := os.OpenFile(filepath.Join(fifo, "classification.yaml"), os.O_RDWR, 0)
|
||||||
|
require.NoError(t, err)
|
||||||
|
defer func() { _ = w.Close() }()
|
||||||
|
done := make(chan error, 1)
|
||||||
|
go func() { _, err := Load(fifo); done <- err }()
|
||||||
|
select {
|
||||||
|
case err := <-done:
|
||||||
|
assert.Error(t, err)
|
||||||
|
case <-time.After(3 * time.Second):
|
||||||
|
t.Fatal("Load hung on a FIFO")
|
||||||
|
}
|
||||||
|
|
||||||
|
_, err = Load(t.TempDir())
|
||||||
|
assert.NoError(t, err, "an absent file is still not an error")
|
||||||
|
}
|
||||||
@@ -21,6 +21,11 @@ func TestReadExcerptRefusesSymlinksAndSurvivesSwapRaces(t *testing.T) {
|
|||||||
require.NoError(t, os.MkdirAll(facts, 0o755))
|
require.NoError(t, os.MkdirAll(facts, 0o755))
|
||||||
require.NoError(t, os.Symlink(brainfstest.Outside(t), filepath.Join(facts, "leak.md")))
|
require.NoError(t, os.Symlink(brainfstest.Outside(t), filepath.Join(facts, "leak.md")))
|
||||||
assert.NotContains(t, readExcerpt(brain, "wiki/w/facts/leak.md", 500), brainfstest.Sentinel)
|
assert.NotContains(t, readExcerpt(brain, "wiki/w/facts/leak.md", 500), brainfstest.Sentinel)
|
||||||
|
// A link to a file elsewhere in the brain: os.Root allows it, only the
|
||||||
|
// regular-file check refuses it (hyperguild#171).
|
||||||
|
inBrain := brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "inlink.md")))
|
||||||
|
assert.NotContains(t, readExcerpt(brain, "wiki/w/facts/inlink.md", 500), brainfstest.Sentinel)
|
||||||
|
|
||||||
p := filepath.Join(facts, "r.md")
|
p := filepath.Join(facts, "r.md")
|
||||||
require.NoError(t, os.WriteFile(p, []byte("---\nx: y\n---\ninside"), 0o644))
|
require.NoError(t, os.WriteFile(p, []byte("---\nx: y\n---\ninside"), 0o644))
|
||||||
@@ -28,6 +33,9 @@ func TestReadExcerptRefusesSymlinksAndSurvivesSwapRaces(t *testing.T) {
|
|||||||
brainfstest.AssertNoLeak(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, func() string {
|
brainfstest.AssertNoLeak(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, func() string {
|
||||||
return readExcerpt(brain, "wiki/w/facts/r.md", 500)
|
return readExcerpt(brain, "wiki/w/facts/r.md", 500)
|
||||||
})
|
})
|
||||||
|
brainfstest.AssertNoLeakFrom(t, p, "---\nx: y\n---\ninside", inBrain, 1500*time.Millisecond, func() string {
|
||||||
|
return readExcerpt(brain, "wiki/w/facts/r.md", 500)
|
||||||
|
})
|
||||||
brainfstest.AssertNoHang(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, 6*time.Second, func() {
|
brainfstest.AssertNoHang(t, p, "---\nx: y\n---\ninside", 1500*time.Millisecond, 6*time.Second, func() {
|
||||||
_ = readExcerpt(brain, "wiki/w/facts/r.md", 500)
|
_ = readExcerpt(brain, "wiki/w/facts/r.md", 500)
|
||||||
})
|
})
|
||||||
|
|||||||
@@ -38,3 +38,31 @@ func TestReadScopedRefusesANoteOverMaxNoteBytes(t *testing.T) {
|
|||||||
_, err := ReadScoped(brain, "wiki/w/facts/big.md", ScopeNotes)
|
_, err := ReadScoped(brain, "wiki/w/facts/big.md", ScopeNotes)
|
||||||
assert.ErrorIs(t, err, ErrTooLarge)
|
assert.ErrorIs(t, err, ErrTooLarge)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// hyperguild#171 (review of #172, finding 1): os.Root alone refuses links that
|
||||||
|
// leave the brain, so the outside-target race above stays green for a reader
|
||||||
|
// that skips brainfs's Lstat and SameFile checks. An in-brain target (raw/,
|
||||||
|
// outside ScopeNotes) is what tells them apart.
|
||||||
|
func TestReadScopedDoesNotReturnAnInBrainSymlinkTargetStaticallyOrDuringASampledSwapRace(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
facts := filepath.Join(brain, "wiki", "w", "facts")
|
||||||
|
require.NoError(t, os.MkdirAll(facts, 0o755))
|
||||||
|
target := brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "inlink.md")))
|
||||||
|
b, err := ReadScoped(brain, "wiki/w/facts/inlink.md", ScopeNotes)
|
||||||
|
assert.Error(t, err, "static in-brain link")
|
||||||
|
assert.NotContains(t, string(b), brainfstest.Sentinel, "static in-brain link")
|
||||||
|
|
||||||
|
p := filepath.Join(facts, "r.md")
|
||||||
|
require.NoError(t, os.WriteFile(p, []byte("inside"), 0o644))
|
||||||
|
b, err = ReadScoped(brain, "wiki/w/facts/r.md", ScopeNotes)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "inside", string(b), "positive control: a regular note reads")
|
||||||
|
|
||||||
|
read := func() string {
|
||||||
|
b, _ := ReadScoped(brain, "wiki/w/facts/r.md", ScopeNotes)
|
||||||
|
return string(b)
|
||||||
|
}
|
||||||
|
brainfstest.AssertNoLeakFrom(t, p, "inside", target, 1500*time.Millisecond, read)
|
||||||
|
}
|
||||||
|
|||||||
@@ -3,7 +3,10 @@ package pipeline
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||||
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"strings"
|
"strings"
|
||||||
@@ -23,10 +26,16 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
|
|||||||
return 0, fmt.Errorf("load inventory: %w", err)
|
return 0, fmt.Errorf("load inventory: %w", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
sourcesDir := filepath.Join(brainDir, "wiki", "sources")
|
// Listed and read through the brain root, regular files only
|
||||||
entries, err := os.ReadDir(sourcesDir)
|
// (hyperguild#157).
|
||||||
|
bfs, err := brainfs.Open(brainDir)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
if os.IsNotExist(err) {
|
return 0, fmt.Errorf("open brain: %w", err)
|
||||||
|
}
|
||||||
|
defer func() { _ = bfs.Close() }()
|
||||||
|
names, err := bfs.ReadDirRegular("wiki/sources")
|
||||||
|
if err != nil {
|
||||||
|
if errors.Is(err, fs.ErrNotExist) {
|
||||||
return 0, nil
|
return 0, nil
|
||||||
}
|
}
|
||||||
return 0, fmt.Errorf("read sources dir: %w", err)
|
return 0, fmt.Errorf("read sources dir: %w", err)
|
||||||
@@ -37,20 +46,20 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
|
|||||||
// get both refs merged before a single write.
|
// get both refs merged before a single write.
|
||||||
pending := make(map[string]wiki.Page)
|
pending := make(map[string]wiki.Page)
|
||||||
|
|
||||||
for _, e := range entries {
|
for _, name := range names {
|
||||||
if ctx.Err() != nil {
|
if ctx.Err() != nil {
|
||||||
return 0, ctx.Err()
|
return 0, ctx.Err()
|
||||||
}
|
}
|
||||||
if e.IsDir() || !strings.HasSuffix(e.Name(), ".md") {
|
if !strings.HasSuffix(name, ".md") {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
b, err := os.ReadFile(filepath.Join(sourcesDir, e.Name()))
|
b, err := bfs.ReadRegular("wiki/sources/" + name)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
sourceContent := string(b)
|
sourceContent := string(b)
|
||||||
sourceSlug := strings.TrimSuffix(e.Name(), ".md")
|
sourceSlug := strings.TrimSuffix(name, ".md")
|
||||||
sourceTitle := extractTitle(sourceContent)
|
sourceTitle := extractTitle(sourceContent)
|
||||||
if sourceTitle == "" {
|
if sourceTitle == "" {
|
||||||
sourceTitle = sourceSlug
|
sourceTitle = sourceSlug
|
||||||
@@ -70,7 +79,7 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
|
|||||||
// Start from already-accumulated version if we've seen this page.
|
// Start from already-accumulated version if we've seen this page.
|
||||||
page, seen := pending[relPath]
|
page, seen := pending[relPath]
|
||||||
if !seen {
|
if !seen {
|
||||||
raw, err := os.ReadFile(filepath.Join(brainDir, filepath.FromSlash(relPath)))
|
raw, err := bfs.ReadRegular(relPath)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -5,7 +5,10 @@ import (
|
|||||||
"context"
|
"context"
|
||||||
"crypto/sha256"
|
"crypto/sha256"
|
||||||
"encoding/hex"
|
"encoding/hex"
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||||
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"strings"
|
"strings"
|
||||||
@@ -129,7 +132,7 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
|
|||||||
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
||||||
return Result{}, fmt.Errorf("mkdir for %s: %w", page.Path, err)
|
return Result{}, fmt.Errorf("mkdir for %s: %w", page.Path, err)
|
||||||
}
|
}
|
||||||
content, conflicts, err := reviseOrCreate(dest, page)
|
content, conflicts, err := reviseOrCreate(brainDir, page)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return Result{}, err
|
return Result{}, err
|
||||||
}
|
}
|
||||||
@@ -188,14 +191,27 @@ func hashBody(content string) string {
|
|||||||
|
|
||||||
// readSourcePage returns the full on-disk content of the source page at
|
// readSourcePage returns the full on-disk content of the source page at
|
||||||
// wiki/sources/<sourceSlug>.md, or "" when it doesn't exist yet.
|
// wiki/sources/<sourceSlug>.md, or "" when it doesn't exist yet.
|
||||||
|
// It reads through the brain root, regular files only (hyperguild#157): the
|
||||||
|
// content goes into the LLM prompt.
|
||||||
func readSourcePage(brainDir, sourceSlug string) string {
|
func readSourcePage(brainDir, sourceSlug string) string {
|
||||||
raw, err := os.ReadFile(filepath.Join(brainDir, "wiki", "sources", sourceSlug+".md"))
|
raw, err := readBrainFile(brainDir, "wiki/sources/"+sourceSlug+".md")
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return ""
|
return ""
|
||||||
}
|
}
|
||||||
return string(raw)
|
return string(raw)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// readBrainFile reads one brain-relative file through the brain root,
|
||||||
|
// regular files only (hyperguild#157).
|
||||||
|
func readBrainFile(brainDir, rel string) ([]byte, error) {
|
||||||
|
bfs, err := brainfs.Open(brainDir)
|
||||||
|
if err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
defer func() { _ = bfs.Close() }()
|
||||||
|
return bfs.ReadRegular(rel)
|
||||||
|
}
|
||||||
|
|
||||||
// storedSourceHash reads source_hash from the source page a previous ingest
|
// storedSourceHash reads source_hash from the source page a previous ingest
|
||||||
// wrote, or "" when there is no such page or no such field.
|
// wrote, or "" when there is no such page or no such field.
|
||||||
//
|
//
|
||||||
@@ -230,10 +246,10 @@ func storedSourceHash(brainDir, sourceSlug string) string {
|
|||||||
// its first-ingest date on a revised page. Left deliberately — the alternative
|
// its first-ingest date on a revised page. Left deliberately — the alternative
|
||||||
// is this function editing frontmatter it does not own, and no lint reads that
|
// is this function editing frontmatter it does not own, and no lint reads that
|
||||||
// field today.
|
// field today.
|
||||||
func reviseOrCreate(dest string, page wiki.Page) (string, []string, error) {
|
func reviseOrCreate(brainDir string, page wiki.Page) (string, []string, error) {
|
||||||
existing, err := os.ReadFile(dest)
|
existing, err := readBrainFile(brainDir, page.Path)
|
||||||
switch {
|
switch {
|
||||||
case os.IsNotExist(err):
|
case errors.Is(err, fs.ErrNotExist):
|
||||||
return page.Content, nil, nil
|
return page.Content, nil, nil
|
||||||
case err != nil:
|
case err != nil:
|
||||||
return "", nil, fmt.Errorf("read existing %s: %w", page.Path, err)
|
return "", nil, fmt.Errorf("read existing %s: %w", page.Path, err)
|
||||||
@@ -267,7 +283,7 @@ See brain/schema.md for the full schema.
|
|||||||
`
|
`
|
||||||
|
|
||||||
func loadSchema(brainDir string) string {
|
func loadSchema(brainDir string) string {
|
||||||
b, err := os.ReadFile(filepath.Join(brainDir, "schema.md"))
|
b, err := readBrainFile(brainDir, "schema.md")
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return defaultSchema
|
return defaultSchema
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -2,7 +2,6 @@
|
|||||||
package pipeline
|
package pipeline
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"os"
|
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"regexp"
|
"regexp"
|
||||||
"strings"
|
"strings"
|
||||||
@@ -53,8 +52,7 @@ func injectSourceRefs(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entr
|
|||||||
if !ok {
|
if !ok {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
diskPath := filepath.Join(brainDir, "wiki", string(pt), slug+".md")
|
b, err := readBrainFile(brainDir, "wiki/"+string(pt)+"/"+slug+".md")
|
||||||
b, err := os.ReadFile(diskPath)
|
|
||||||
if err != nil {
|
if err != nil {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,167 @@
|
|||||||
|
package pipeline
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
"fmt"
|
||||||
|
"io"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"syscall"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs/brainfstest"
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
|
||||||
|
)
|
||||||
|
|
||||||
|
// hyperguild#157 slice 6: the pipeline read the source page, schema.md, the
|
||||||
|
// pages it revises and the pages it adds source refs to with os.ReadFile, so
|
||||||
|
// a symlinked file's content reached the LLM prompt and the written pages,
|
||||||
|
// and a FIFO hung the ingest.
|
||||||
|
|
||||||
|
func mkdirs(t *testing.T, brain string, dirs ...string) {
|
||||||
|
t.Helper()
|
||||||
|
for _, d := range dirs {
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(brain, filepath.FromSlash(d)), 0o755))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestReadSourcePageAndSchemaRefuseSymlinksAndSurviveSwapRaces(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
mkdirs(t, brain, "wiki/sources")
|
||||||
|
inBrain := brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "sources", "ok.md"), []byte("zqinside source"), 0o644))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "schema.md"), []byte("zqinside schema"), 0o644))
|
||||||
|
assert.Equal(t, "zqinside source", readSourcePage(brain, "ok"), "positive control")
|
||||||
|
assert.Equal(t, "zqinside schema", loadSchema(brain), "positive control")
|
||||||
|
|
||||||
|
require.NoError(t, os.Symlink(brainfstest.Outside(t), filepath.Join(brain, "wiki", "sources", "out.md")))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "s.md"), filepath.Join(brain, "wiki", "sources", "in.md")))
|
||||||
|
assert.NotContains(t, readSourcePage(brain, "out"), brainfstest.Sentinel)
|
||||||
|
assert.NotContains(t, readSourcePage(brain, "in"), brainfstest.Sentinel)
|
||||||
|
assert.NotContains(t, storedSourceHash(brain, "in"), brainfstest.Sentinel)
|
||||||
|
|
||||||
|
src := filepath.Join(brain, "wiki", "sources", "r.md")
|
||||||
|
read := func() string { return readSourcePage(brain, "r") }
|
||||||
|
brainfstest.AssertNoLeak(t, src, "zqinside", 1500*time.Millisecond, read)
|
||||||
|
brainfstest.AssertNoLeakFrom(t, src, "zqinside", inBrain, 1500*time.Millisecond, read)
|
||||||
|
brainfstest.AssertNoHang(t, src, "zqinside", 1500*time.Millisecond, 6*time.Second, func() { _ = read() })
|
||||||
|
|
||||||
|
schema := filepath.Join(brain, "schema.md")
|
||||||
|
rs := func() string { return loadSchema(brain) }
|
||||||
|
brainfstest.AssertNoLeakFrom(t, schema, "zqinside schema", inBrain, 1500*time.Millisecond, rs)
|
||||||
|
brainfstest.AssertNoHang(t, schema, "zqinside schema", 1500*time.Millisecond, 6*time.Second, func() { _ = rs() })
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestReviseOrCreateRefusesASymlinkedExistingPage(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
mkdirs(t, brain, "wiki/concepts")
|
||||||
|
brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "s.md"), filepath.Join(brain, "wiki", "concepts", "c.md")))
|
||||||
|
page := wiki.Page{Path: "wiki/concepts/c.md", Content: "---\ntitle: C\n---\nnew\n"}
|
||||||
|
out, _, err := reviseOrCreate(brain, page)
|
||||||
|
assert.Error(t, err)
|
||||||
|
assert.NotContains(t, out, brainfstest.Sentinel)
|
||||||
|
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "concepts", "d.md"), []byte("---\ntitle: D\n---\nzqold\n"), 0o644))
|
||||||
|
out, _, err = reviseOrCreate(brain, wiki.Page{Path: "wiki/concepts/d.md", Content: "---\ntitle: D\n---\nnew\n"})
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Contains(t, out, "zqold", "positive control: the existing page is read")
|
||||||
|
out, _, err = reviseOrCreate(brain, wiki.Page{Path: "wiki/concepts/new.md", Content: "fresh"})
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "fresh", out, "positive control: a missing page is created")
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestInjectSourceRefsDoesNotReadASymlinkedPage(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
mkdirs(t, brain, "wiki/concepts")
|
||||||
|
brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "s.md"), filepath.Join(brain, "wiki", "concepts", "c.md")))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "concepts", "d.md"), []byte("zqinside d"), 0o644))
|
||||||
|
inv := map[wiki.PageType][]wiki.Entry{wiki.PageTypeConcept: {
|
||||||
|
{Slug: "c", Type: wiki.PageTypeConcept}, {Slug: "d", Type: wiki.PageTypeConcept},
|
||||||
|
}}
|
||||||
|
src := wiki.Page{Path: "wiki/sources/src.md", Content: "---\ntitle: Src\n---\nsee [[c|C]] and [[d|D]]\n"}
|
||||||
|
out := injectSourceRefs([]wiki.Page{src}, inv, brain)
|
||||||
|
got := fmt.Sprintf("%+v", out)
|
||||||
|
assert.Contains(t, got, "zqinside d", "positive control")
|
||||||
|
assert.NotContains(t, got, brainfstest.Sentinel)
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestBackfillRefsSkipsSymlinkedSourcesAndPages(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
mkdirs(t, brain, "wiki/sources", "wiki/concepts", "raw")
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "concepts", "real.md"), []byte("---\ntitle: R\n---\nbody\n"), 0o644))
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "sources", "ok.md"), []byte("---\ntitle: zqinside\n---\n[[real|R]]\n"), 0o644))
|
||||||
|
// A source elsewhere in the brain whose title is the sentinel and which
|
||||||
|
// links the real concept with the [[slug|title]] form the pipeline follows.
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "raw", "src.md"),
|
||||||
|
[]byte("---\ntitle: "+brainfstest.Sentinel+"\n---\n[[real|R]]\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "src.md"), filepath.Join(brain, "wiki", "sources", "in.md")))
|
||||||
|
// A concept page linked by the regular source that is itself a symlink.
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "sources", "ok2.md"), []byte("---\ntitle: Two\n---\n[[lnk|L]]\n"), 0o644))
|
||||||
|
brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "page.md"))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "page.md"), filepath.Join(brain, "wiki", "concepts", "lnk.md")))
|
||||||
|
|
||||||
|
_, err := BackfillRefs(context.Background(), brain)
|
||||||
|
require.NoError(t, err)
|
||||||
|
b, _ := os.ReadFile(filepath.Join(brain, "wiki", "concepts", "real.md"))
|
||||||
|
assert.Contains(t, string(b), "zqinside", "positive control: the regular source's ref is added")
|
||||||
|
assert.NotContains(t, string(b), brainfstest.Sentinel, "a symlinked source's title was written as a ref")
|
||||||
|
raw, _ := os.ReadFile(filepath.Join(brain, "raw", "page.md"))
|
||||||
|
assert.NotContains(t, string(raw), "[[ok2", "the symlinked concept page's target was rewritten")
|
||||||
|
}
|
||||||
|
|
||||||
|
// A source swapped between a regular file and a symlink to an in-brain source
|
||||||
|
// whose title is the sentinel: the read refuses the swapped-in link, so the
|
||||||
|
// sentinel never lands in the concept page as a ref.
|
||||||
|
func TestBackfillRefsDoesNotWriteARefFromASourceSwappedInBehindASymlink(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
mkdirs(t, brain, "wiki/sources", "wiki/concepts", "raw")
|
||||||
|
realPage := filepath.Join(brain, "wiki", "concepts", "real.md")
|
||||||
|
target := filepath.Join(brain, "raw", "src.md")
|
||||||
|
require.NoError(t, os.WriteFile(target, []byte("---\ntitle: "+brainfstest.Sentinel+"\n---\n[[real|R]]\n"), 0o644))
|
||||||
|
src := filepath.Join(brain, "wiki", "sources", "r.md")
|
||||||
|
inside := "---\ntitle: zqinside\n---\n[[real|R]]\n"
|
||||||
|
read := func() string {
|
||||||
|
_ = os.WriteFile(realPage, []byte("---\ntitle: R\n---\nbody\n"), 0o644)
|
||||||
|
_, _ = BackfillRefs(context.Background(), brain)
|
||||||
|
b, _ := os.ReadFile(realPage)
|
||||||
|
return string(b)
|
||||||
|
}
|
||||||
|
require.NoError(t, os.WriteFile(src, []byte(inside), 0o644))
|
||||||
|
require.Contains(t, read(), "zqinside", "positive control")
|
||||||
|
brainfstest.AssertNoLeakFrom(t, src, inside, target, 1500*time.Millisecond, read)
|
||||||
|
}
|
||||||
|
|
||||||
|
// A concept page that is regular when the inventory lists it, then swapped
|
||||||
|
// for a symlink to an in-brain file before BackfillRefs reads it: only the
|
||||||
|
// page read's own check refuses it (a static symlink never gets this far,
|
||||||
|
// because LoadInventory does not list it).
|
||||||
|
func TestBackfillRefsDoesNotCopyAPageSwappedInBehindASymlink(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
mkdirs(t, brain, "wiki/sources", "wiki/concepts", "raw")
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "sources", "s.md"), []byte("---\ntitle: S\n---\n[[c|C]]\n"), 0o644))
|
||||||
|
page := filepath.Join(brain, "wiki", "concepts", "c.md")
|
||||||
|
target := filepath.Join(brain, "raw", "secret.md")
|
||||||
|
inside := "---\ntitle: C\n---\nzqinside\n"
|
||||||
|
read := func() string {
|
||||||
|
// The write path still follows a swapped-in link (#158) and can
|
||||||
|
// overwrite the target, so restore it each round.
|
||||||
|
_ = os.WriteFile(target, []byte("---\ntitle: X\n---\n"+brainfstest.Sentinel+"\n"), 0o644)
|
||||||
|
_, _ = BackfillRefs(context.Background(), brain)
|
||||||
|
f, err := os.OpenFile(page, os.O_RDONLY|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0)
|
||||||
|
if err != nil {
|
||||||
|
return ""
|
||||||
|
}
|
||||||
|
defer func() { _ = f.Close() }()
|
||||||
|
b, _ := io.ReadAll(f)
|
||||||
|
return string(b)
|
||||||
|
}
|
||||||
|
require.NoError(t, os.WriteFile(page, []byte(inside), 0o644))
|
||||||
|
require.Contains(t, read(), "[[s|S]]", "positive control: the regular page gets the source ref")
|
||||||
|
brainfstest.AssertNoLeakFrom(t, page, inside, target, 3*time.Second, read)
|
||||||
|
}
|
||||||
@@ -12,6 +12,8 @@ import (
|
|||||||
|
|
||||||
"github.com/stretchr/testify/assert"
|
"github.com/stretchr/testify/assert"
|
||||||
"github.com/stretchr/testify/require"
|
"github.com/stretchr/testify/require"
|
||||||
|
|
||||||
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs/brainfstest"
|
||||||
)
|
)
|
||||||
|
|
||||||
// hyperguild#157 option 1: search walked and read the brain by path, so a
|
// hyperguild#157 option 1: search walked and read the brain by path, so a
|
||||||
@@ -189,3 +191,49 @@ func TestHydrateRefusesASymlink(t *testing.T) {
|
|||||||
assert.Error(t, err)
|
assert.Error(t, err)
|
||||||
assert.NotContains(t, r.Excerpt, sentinel157)
|
assert.NotContains(t, r.Excerpt, sentinel157)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// hyperguild#171: os.Root refuses links that leave the brain on its own, so
|
||||||
|
// the outside-target cases above would stay green for a caller that read
|
||||||
|
// without brainfs's Lstat and SameFile checks. These targets are inside the
|
||||||
|
// brain (raw/, which is not a search root).
|
||||||
|
func inBrainTarget(t *testing.T, brain string) string {
|
||||||
|
t.Helper()
|
||||||
|
return brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestQueryDoesNotReturnAnInBrainSymlinkTargetDuringASampledSwapRace(t *testing.T) {
|
||||||
|
brain, facts, _ := searchBrain(t)
|
||||||
|
target := inBrainTarget(t, brain)
|
||||||
|
read := func() string {
|
||||||
|
// Both terms, so the regular note is a possible hit: a reader that
|
||||||
|
// never returns the inside note would pass vacuously (#177 floor).
|
||||||
|
rs, _ := Query(brain, QueryOptions{Query: brainfstest.Sentinel + " zqinside", Limit: 10})
|
||||||
|
s := ""
|
||||||
|
for _, r := range rs {
|
||||||
|
s += r.Title + r.Excerpt
|
||||||
|
}
|
||||||
|
return s
|
||||||
|
}
|
||||||
|
brainfstest.AssertNoLeakFrom(t, filepath.Join(facts, "r.md"), "# r\n\nzqinside", target, 1500*time.Millisecond, read)
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "inlink.md")))
|
||||||
|
assert.NotContains(t, read(), brainfstest.Sentinel, "static in-brain link")
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestHydrateRefusesAnInBrainSymlinkAndDoesNotReturnItsTargetDuringASampledSwapRace(t *testing.T) {
|
||||||
|
brain, facts, _ := searchBrain(t)
|
||||||
|
target := inBrainTarget(t, brain)
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "inlink.md")))
|
||||||
|
r, err := hydrate(brain, "wiki/w/facts/inlink.md")
|
||||||
|
assert.Error(t, err)
|
||||||
|
assert.NotContains(t, r.Excerpt+r.Title, brainfstest.Sentinel)
|
||||||
|
|
||||||
|
p := filepath.Join(facts, "r.md")
|
||||||
|
require.NoError(t, os.WriteFile(p, []byte("# r\n\nzqinside"), 0o644))
|
||||||
|
r, err = hydrate(brain, "wiki/w/facts/r.md")
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Contains(t, r.Excerpt, "zqinside", "positive control: a regular note hydrates")
|
||||||
|
brainfstest.AssertNoLeakFrom(t, p, "# r\n\nzqinside", target, 1500*time.Millisecond, func() string {
|
||||||
|
r, _ := hydrate(brain, "wiki/w/facts/r.md")
|
||||||
|
return r.Title + r.Excerpt
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|||||||
@@ -0,0 +1,177 @@
|
|||||||
|
package session
|
||||||
|
|
||||||
|
import (
|
||||||
|
"errors"
|
||||||
|
"fmt"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"sync/atomic"
|
||||||
|
"syscall"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
"golang.org/x/sys/unix"
|
||||||
|
)
|
||||||
|
|
||||||
|
// session_log passed the caller's session_id straight into
|
||||||
|
// filepath.Join(sessionsDir, id+".jsonl") and opened it O_CREATE|O_APPEND:
|
||||||
|
// path segments in the id created or appended files anywhere the pod could
|
||||||
|
// write. The id is now a plain name, and the open does not follow a final
|
||||||
|
// symlink.
|
||||||
|
func TestAppendRefusesSessionIDsThatAreNotPlainNames(t *testing.T) {
|
||||||
|
root := t.TempDir()
|
||||||
|
dir := filepath.Join(root, "sessions")
|
||||||
|
for _, id := range []string{"../x", "a/b", "/abs", ".", "..", ".hidden", "", "a\\b", "a\x00b"} {
|
||||||
|
assert.Error(t, Append(dir, id, Entry{SessionID: id}), "%q", id)
|
||||||
|
}
|
||||||
|
ents, _ := os.ReadDir(root)
|
||||||
|
for _, e := range ents {
|
||||||
|
assert.Equal(t, "sessions", e.Name(), "nothing created beside the sessions dir")
|
||||||
|
}
|
||||||
|
for _, id := range []string{"1557b2e1-bf0d-5c4f-bbe3-0754d087e356", "_routing", "2026-05-05-infra.plan", "0"} {
|
||||||
|
require.NoError(t, Append(dir, id, Entry{SessionID: id}), "positive control: %q", id)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestAppendDoesNotWriteThroughASymlinkedLog(t *testing.T) {
|
||||||
|
root := t.TempDir()
|
||||||
|
dir := filepath.Join(root, "sessions")
|
||||||
|
require.NoError(t, os.MkdirAll(dir, 0o755))
|
||||||
|
victim := filepath.Join(root, "victim.md")
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "victim.md"), filepath.Join(dir, "s.jsonl")))
|
||||||
|
assert.Error(t, Append(dir, "s", Entry{SessionID: "s"}))
|
||||||
|
got, _ := os.ReadFile(victim)
|
||||||
|
assert.Equal(t, "untouched\n", string(got))
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestReadRefusesSessionIDsThatAreNotPlainNames(t *testing.T) {
|
||||||
|
root := t.TempDir()
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(root, "x.jsonl"), []byte(`{"session_id":"x"}`+"\n"), 0o644))
|
||||||
|
_, err := Read(filepath.Join(root, "sessions"), "../x")
|
||||||
|
assert.Error(t, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
// A name that starts plainly and then climbs out with ".." is exactly what the
|
||||||
|
// ban on "/" in the id's tail stops: filepath.Join cleans "a/../../x" to a
|
||||||
|
// path beside the sessions dir without needing sessions/a to exist. The
|
||||||
|
// assertion is on the refusal itself (ErrInvalidID), not on any error.
|
||||||
|
func TestAppendRefusesAnIDThatClimbsOutAfterAPlainPrefix(t *testing.T) {
|
||||||
|
root := t.TempDir()
|
||||||
|
dir := filepath.Join(root, "sessions")
|
||||||
|
require.NoError(t, os.MkdirAll(dir, 0o755))
|
||||||
|
for _, id := range []string{"a/../../escape", "a/../../../escape", "a/../b"} {
|
||||||
|
err := Append(dir, id, Entry{SessionID: id})
|
||||||
|
assert.ErrorIs(t, err, ErrInvalidID, "%q", id)
|
||||||
|
}
|
||||||
|
_, err := os.Lstat(filepath.Join(root, "escape.jsonl"))
|
||||||
|
assert.True(t, errors.Is(err, os.ErrNotExist), "nothing created beside the sessions dir")
|
||||||
|
_, err = os.Lstat(filepath.Join(dir, "b.jsonl"))
|
||||||
|
assert.True(t, errors.Is(err, os.ErrNotExist), "no in-dir alias created either")
|
||||||
|
}
|
||||||
|
|
||||||
|
// Append does no Lstat type check, so O_NONBLOCK is the only thing that keeps
|
||||||
|
// a FIFO named <id>.jsonl with no reader from blocking session_log forever.
|
||||||
|
func TestAppendReturnsPromptlyOnAFIFOLogWithNoReader(t *testing.T) {
|
||||||
|
dir := filepath.Join(t.TempDir(), "sessions")
|
||||||
|
require.NoError(t, os.MkdirAll(dir, 0o755))
|
||||||
|
fifo := filepath.Join(dir, "s.jsonl")
|
||||||
|
require.NoError(t, syscall.Mkfifo(fifo, 0o644))
|
||||||
|
done := make(chan error, 1)
|
||||||
|
go func() { done <- Append(dir, "s", Entry{SessionID: "s"}) }()
|
||||||
|
select {
|
||||||
|
case err := <-done:
|
||||||
|
assert.Error(t, err, "a FIFO with no reader is refused, not written")
|
||||||
|
case <-time.After(3 * time.Second):
|
||||||
|
// Unblock the stuck open so the goroutine and TempDir cleanup finish.
|
||||||
|
if r, err := os.OpenFile(fifo, os.O_RDONLY|syscall.O_NONBLOCK, 0); err == nil {
|
||||||
|
defer r.Close() //nolint:errcheck
|
||||||
|
}
|
||||||
|
<-done
|
||||||
|
t.Fatal("Append blocked on a FIFO log with no reader")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// hyperguild#173: session_log followed a symlinked sessions dir.
|
||||||
|
func TestAppendRefusesASymlinkedSessionsDir(t *testing.T) {
|
||||||
|
root := t.TempDir()
|
||||||
|
elsewhere := filepath.Join(root, "elsewhere")
|
||||||
|
require.NoError(t, os.MkdirAll(elsewhere, 0o755))
|
||||||
|
dir := filepath.Join(root, "sessions")
|
||||||
|
require.NoError(t, os.Symlink("elsewhere", dir))
|
||||||
|
assert.Error(t, Append(dir, "s", Entry{SessionID: "s"}))
|
||||||
|
ents, _ := os.ReadDir(elsewhere)
|
||||||
|
assert.Empty(t, ents, "a log was created through the symlinked dir")
|
||||||
|
}
|
||||||
|
|
||||||
|
// The sessions dir is swapped (RENAME_EXCHANGE) with a symlink to a
|
||||||
|
// directory outside the brain while Append runs. Append opens through an
|
||||||
|
// os.Root on the sessions dir's parent, so a swap can redirect it only
|
||||||
|
// inside that parent (the #167 residual), never outside it.
|
||||||
|
func TestAppendNeverCreatesALogOutsideTheParentUnderADirSwapRace(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
outside := t.TempDir()
|
||||||
|
dir := filepath.Join(brain, "sessions")
|
||||||
|
other := filepath.Join(brain, "sessions.link")
|
||||||
|
require.NoError(t, os.MkdirAll(dir, 0o755))
|
||||||
|
require.NoError(t, os.Symlink(outside, other))
|
||||||
|
var stop atomic.Bool
|
||||||
|
done := make(chan struct{})
|
||||||
|
go func() {
|
||||||
|
defer close(done)
|
||||||
|
for !stop.Load() {
|
||||||
|
_ = unix.Renameat2(unix.AT_FDCWD, dir, unix.AT_FDCWD, other, unix.RENAME_EXCHANGE)
|
||||||
|
}
|
||||||
|
}()
|
||||||
|
ok := 0
|
||||||
|
for i := 0; i < 20000; i++ {
|
||||||
|
if Append(dir, fmt.Sprintf("s%d", i), Entry{SessionID: "s"}) == nil {
|
||||||
|
ok++
|
||||||
|
}
|
||||||
|
}
|
||||||
|
stop.Store(true)
|
||||||
|
<-done
|
||||||
|
ents, _ := os.ReadDir(outside)
|
||||||
|
assert.Empty(t, ents, "logs were created outside the brain")
|
||||||
|
assert.Positive(t, ok, "positive control: appends to the real dir succeed")
|
||||||
|
}
|
||||||
|
|
||||||
|
// The log file is swapped between a regular file and a symlink to another
|
||||||
|
// file in the brain while Append runs: Append writes only after confirming
|
||||||
|
// the path is the regular file it opened, so the other file never grows.
|
||||||
|
func TestAppendNeverWritesThroughALogSwappedForASymlink(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
dir := filepath.Join(brain, "sessions")
|
||||||
|
require.NoError(t, os.MkdirAll(dir, 0o755))
|
||||||
|
victim := filepath.Join(brain, "victim.md")
|
||||||
|
require.NoError(t, os.WriteFile(victim, []byte("untouched\n"), 0o644))
|
||||||
|
log := filepath.Join(dir, "s.jsonl")
|
||||||
|
var stop atomic.Bool
|
||||||
|
done := make(chan struct{})
|
||||||
|
go func() {
|
||||||
|
defer close(done)
|
||||||
|
tmp := log + ".swap"
|
||||||
|
for i := 0; !stop.Load(); i++ {
|
||||||
|
_ = os.Remove(tmp)
|
||||||
|
if i%2 == 0 {
|
||||||
|
_ = os.WriteFile(tmp, nil, 0o644)
|
||||||
|
} else {
|
||||||
|
_ = os.Symlink(filepath.Join("..", "victim.md"), tmp)
|
||||||
|
}
|
||||||
|
_ = os.Rename(tmp, log)
|
||||||
|
}
|
||||||
|
}()
|
||||||
|
ok := 0
|
||||||
|
for i := 0; i < 20000; i++ {
|
||||||
|
if Append(dir, "s", Entry{SessionID: "s"}) == nil {
|
||||||
|
ok++
|
||||||
|
}
|
||||||
|
}
|
||||||
|
stop.Store(true)
|
||||||
|
<-done
|
||||||
|
got, _ := os.ReadFile(victim)
|
||||||
|
assert.Equal(t, "untouched\n", string(got), "a log line was written through the swapped-in symlink")
|
||||||
|
assert.Positive(t, ok, "positive control: appends to the regular log succeed")
|
||||||
|
}
|
||||||
@@ -9,6 +9,8 @@ import (
|
|||||||
"io/fs"
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
"regexp"
|
||||||
|
"syscall"
|
||||||
"time"
|
"time"
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -42,16 +44,63 @@ type Attempt struct {
|
|||||||
RunnerOutput string `json:"runner_output,omitempty"`
|
RunnerOutput string `json:"runner_output,omitempty"`
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// idPattern is a plain file name: session_log takes the id from the caller,
|
||||||
|
// and a path segment in it created or appended files anywhere the pod could
|
||||||
|
// write (hyperguild#169).
|
||||||
|
var idPattern = regexp.MustCompile(`^[A-Za-z0-9_][A-Za-z0-9._-]{0,127}$`)
|
||||||
|
|
||||||
|
// ErrInvalidID is returned when a session id is not a plain file name.
|
||||||
|
var ErrInvalidID = errors.New("session id is not a plain name")
|
||||||
|
|
||||||
|
func checkID(sessionID string) error {
|
||||||
|
if !idPattern.MatchString(sessionID) {
|
||||||
|
return fmt.Errorf("%w: %q", ErrInvalidID, sessionID)
|
||||||
|
}
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
// Append writes entry as a single JSON line to sessionsDir/{sessionID}.jsonl.
|
// Append writes entry as a single JSON line to sessionsDir/{sessionID}.jsonl.
|
||||||
|
// The open does not follow a final symlink.
|
||||||
func Append(sessionsDir, sessionID string, entry Entry) error {
|
func Append(sessionsDir, sessionID string, entry Entry) error {
|
||||||
if err := os.MkdirAll(sessionsDir, 0o755); err != nil {
|
if err := checkID(sessionID); err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
// Opened through an os.Root on the sessions dir's parent (the brain dir),
|
||||||
|
// so a sessions dir swapped for a symlink after the check below can
|
||||||
|
// redirect the log only inside that parent, never outside it (#173; the
|
||||||
|
// in-brain swap is the #167 residual).
|
||||||
|
parentDir, name := filepath.Dir(sessionsDir), filepath.Base(sessionsDir)
|
||||||
|
if err := os.MkdirAll(parentDir, 0o755); err != nil {
|
||||||
|
return fmt.Errorf("create sessions parent: %w", err)
|
||||||
|
}
|
||||||
|
root, err := os.OpenRoot(parentDir)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("open sessions parent: %w", err)
|
||||||
|
}
|
||||||
|
defer func() { _ = root.Close() }()
|
||||||
|
if err := root.Mkdir(name, 0o755); err != nil && !errors.Is(err, fs.ErrExist) {
|
||||||
return fmt.Errorf("create sessions dir: %w", err)
|
return fmt.Errorf("create sessions dir: %w", err)
|
||||||
}
|
}
|
||||||
path := filepath.Join(sessionsDir, sessionID+".jsonl")
|
// The sessions dir itself must be a real directory, not a symlink that
|
||||||
f, err := os.OpenFile(path, os.O_CREATE|os.O_APPEND|os.O_WRONLY, 0o644)
|
// redirects the log elsewhere (hyperguild#173).
|
||||||
|
if fi, err := root.Lstat(name); err != nil {
|
||||||
|
return fmt.Errorf("stat sessions dir: %w", err)
|
||||||
|
} else if !fi.IsDir() {
|
||||||
|
return fmt.Errorf("sessions dir %s is not a real directory", sessionsDir)
|
||||||
|
}
|
||||||
|
logRel := name + "/" + sessionID + ".jsonl"
|
||||||
|
f, err := root.OpenFile(logRel, os.O_CREATE|os.O_APPEND|os.O_WRONLY|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0o644)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return fmt.Errorf("open session log: %w", err)
|
return fmt.Errorf("open session log: %w", err)
|
||||||
}
|
}
|
||||||
|
// os.Root follows an in-root final symlink even with O_NOFOLLOW, so
|
||||||
|
// confirm, before writing, that the path is the regular file we opened.
|
||||||
|
hfi, herr := f.Stat()
|
||||||
|
lfi, lerr := root.Lstat(logRel)
|
||||||
|
if herr != nil || lerr != nil || !lfi.Mode().IsRegular() || !os.SameFile(lfi, hfi) {
|
||||||
|
_ = f.Close()
|
||||||
|
return fmt.Errorf("session log %s is not a regular file", logRel)
|
||||||
|
}
|
||||||
|
|
||||||
line, err := json.Marshal(entry)
|
line, err := json.Marshal(entry)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
@@ -70,6 +119,9 @@ func Append(sessionsDir, sessionID string, entry Entry) error {
|
|||||||
|
|
||||||
// Read returns all entries for sessionID. Returns empty slice if no log exists.
|
// Read returns all entries for sessionID. Returns empty slice if no log exists.
|
||||||
func Read(sessionsDir, sessionID string) ([]Entry, error) {
|
func Read(sessionsDir, sessionID string) ([]Entry, error) {
|
||||||
|
if err := checkID(sessionID); err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
path := filepath.Join(sessionsDir, sessionID+".jsonl")
|
path := filepath.Join(sessionsDir, sessionID+".jsonl")
|
||||||
f, err := os.Open(path)
|
f, err := os.Open(path)
|
||||||
if errors.Is(err, fs.ErrNotExist) {
|
if errors.Is(err, fs.ErrNotExist) {
|
||||||
|
|||||||
@@ -0,0 +1,104 @@
|
|||||||
|
package symlinkguard
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
"net"
|
||||||
|
"os"
|
||||||
|
"path/filepath"
|
||||||
|
"syscall"
|
||||||
|
"testing"
|
||||||
|
"time"
|
||||||
|
|
||||||
|
"github.com/stretchr/testify/assert"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
)
|
||||||
|
|
||||||
|
// hyperguild#179: the tripwire looked only for symlinks, so a FIFO (or
|
||||||
|
// socket) in the brain passed it. A FIFO at classification.yaml then made
|
||||||
|
// startup exit; at a note path it could hang readers that skip the handle
|
||||||
|
// check.
|
||||||
|
func TestScanReportsFIFOsAndSocketsAsSpecialFiles(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w"), 0o755))
|
||||||
|
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "classification.yaml"), 0o644))
|
||||||
|
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "wiki", "w", "f.md"), 0o644))
|
||||||
|
l, err := net.Listen("unix", filepath.Join(brain, "s.sock"))
|
||||||
|
require.NoError(t, err)
|
||||||
|
defer func() { _ = l.Close() }()
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "w", "n.md"), []byte("n"), 0o644))
|
||||||
|
|
||||||
|
r, err := Scan(brain)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, []string{"classification.yaml", "s.sock", "wiki/w/f.md"}, r.Special)
|
||||||
|
assert.False(t, r.Clean())
|
||||||
|
assert.Contains(t, r.String(), "special file")
|
||||||
|
}
|
||||||
|
|
||||||
|
// Watch removes a FIFO as it removes symlinks, and leaves a regular file
|
||||||
|
// (which Scan never reports) alone.
|
||||||
|
func TestWatchRemovesAFIFOAndLeavesAnUnreportedRegularFile(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
fifo := filepath.Join(brain, "f.md")
|
||||||
|
require.NoError(t, syscall.Mkfifo(fifo, 0o644))
|
||||||
|
regular := filepath.Join(brain, "n.md")
|
||||||
|
require.NoError(t, os.WriteFile(regular, []byte("n"), 0o644))
|
||||||
|
n := &recNotifier{}
|
||||||
|
ctx, cancel := context.WithCancel(context.Background())
|
||||||
|
defer cancel()
|
||||||
|
go Watch(ctx, brain, 10*time.Millisecond, n)
|
||||||
|
require.Eventually(t, func() bool {
|
||||||
|
_, err := os.Lstat(fifo)
|
||||||
|
return os.IsNotExist(err)
|
||||||
|
}, 2*time.Second, 10*time.Millisecond, "the FIFO is removed")
|
||||||
|
require.Eventually(t, func() bool { return n.count() >= 1 }, 2*time.Second, 10*time.Millisecond)
|
||||||
|
b, err := os.ReadFile(regular)
|
||||||
|
require.NoError(t, err)
|
||||||
|
assert.Equal(t, "n", string(b))
|
||||||
|
n.mu.Lock()
|
||||||
|
defer n.mu.Unlock()
|
||||||
|
assert.Contains(t, n.msgs[0], "f.md")
|
||||||
|
}
|
||||||
|
|
||||||
|
// removeSpecial re-checks the type: a path that is a regular file or a
|
||||||
|
// directory at the re-check is not removed. (A swap between the re-check and
|
||||||
|
// the unlink can still remove one; Linux has no conditional unlink. The same
|
||||||
|
// window exists in removeSymlinks.)
|
||||||
|
func TestRemoveSpecialRefusesRegularFilesAndDirectories(t *testing.T) {
|
||||||
|
brain := t.TempDir()
|
||||||
|
require.NoError(t, os.WriteFile(filepath.Join(brain, "n.md"), []byte("n"), 0o644))
|
||||||
|
require.NoError(t, os.MkdirAll(filepath.Join(brain, "d"), 0o755))
|
||||||
|
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "f.md"), 0o644))
|
||||||
|
removed, failed := removeSpecial(brain, []string{"n.md", "d", "f.md"})
|
||||||
|
assert.Equal(t, []string{"f.md"}, removed)
|
||||||
|
assert.Equal(t, []string{"n.md", "d"}, failed)
|
||||||
|
_, err := os.Stat(filepath.Join(brain, "n.md"))
|
||||||
|
assert.NoError(t, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
// A special file Watch cannot remove (its directory is read-only) stays
|
||||||
|
// reported: the persistent-finding alert names it.
|
||||||
|
func TestWatchReportsASpecialFileItCannotRemove(t *testing.T) {
|
||||||
|
if os.Geteuid() == 0 {
|
||||||
|
t.Skip("root ignores directory permissions")
|
||||||
|
}
|
||||||
|
brain := t.TempDir()
|
||||||
|
ro := filepath.Join(brain, "ro")
|
||||||
|
require.NoError(t, os.MkdirAll(ro, 0o755))
|
||||||
|
require.NoError(t, syscall.Mkfifo(filepath.Join(ro, "f.md"), 0o644))
|
||||||
|
require.NoError(t, os.Chmod(ro, 0o555))
|
||||||
|
t.Cleanup(func() { _ = os.Chmod(ro, 0o755) })
|
||||||
|
n := &recNotifier{}
|
||||||
|
ctx, cancel := context.WithCancel(context.Background())
|
||||||
|
defer cancel()
|
||||||
|
go Watch(ctx, brain, 10*time.Millisecond, n)
|
||||||
|
require.Eventually(t, func() bool { return n.count() >= 1 }, 2*time.Second, 10*time.Millisecond)
|
||||||
|
_, err := os.Lstat(filepath.Join(ro, "f.md"))
|
||||||
|
require.NoError(t, err, "the FIFO could not be removed")
|
||||||
|
n.mu.Lock()
|
||||||
|
defer n.mu.Unlock()
|
||||||
|
assert.Contains(t, n.msgs[0], "ro/f.md")
|
||||||
|
assert.Contains(t, n.msgs[0], "special file")
|
||||||
|
for _, m := range n.msgs {
|
||||||
|
assert.NotContains(t, m, "removed", "a file it could not remove was reported as removed")
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -46,10 +46,16 @@ type Notifier interface {
|
|||||||
type Result struct {
|
type Result struct {
|
||||||
Symlinks []string
|
Symlinks []string
|
||||||
Unreadable []string
|
Unreadable []string
|
||||||
|
// Special holds FIFOs, sockets and devices (hyperguild#179): a reader
|
||||||
|
// that opens one by path can hang, and a FIFO at classification.yaml
|
||||||
|
// stops startup.
|
||||||
|
Special []string
|
||||||
}
|
}
|
||||||
|
|
||||||
// Clean reports whether the scan found nothing to act on.
|
// Clean reports whether the scan found nothing to act on.
|
||||||
func (r Result) Clean() bool { return len(r.Symlinks) == 0 && len(r.Unreadable) == 0 }
|
func (r Result) Clean() bool {
|
||||||
|
return len(r.Symlinks) == 0 && len(r.Unreadable) == 0 && len(r.Special) == 0
|
||||||
|
}
|
||||||
|
|
||||||
// String describes the findings for a log line or alert. Paths are quoted, so
|
// String describes the findings for a log line or alert. Paths are quoted, so
|
||||||
// a name containing a newline cannot blur two findings together.
|
// a name containing a newline cannot blur two findings together.
|
||||||
@@ -59,6 +65,9 @@ func (r Result) String() string {
|
|||||||
if len(r.Symlinks) > 0 {
|
if len(r.Symlinks) > 0 {
|
||||||
parts = append(parts, fmt.Sprintf("%d symlink(s): %s", len(r.Symlinks), q(r.Symlinks)))
|
parts = append(parts, fmt.Sprintf("%d symlink(s): %s", len(r.Symlinks), q(r.Symlinks)))
|
||||||
}
|
}
|
||||||
|
if len(r.Special) > 0 {
|
||||||
|
parts = append(parts, fmt.Sprintf("%d special file(s) (FIFO, socket or device; delete them): %s", len(r.Special), q(r.Special)))
|
||||||
|
}
|
||||||
if len(r.Unreadable) > 0 {
|
if len(r.Unreadable) > 0 {
|
||||||
parts = append(parts, fmt.Sprintf("%d unreadable dir(s): %s", len(r.Unreadable), q(r.Unreadable)))
|
parts = append(parts, fmt.Sprintf("%d unreadable dir(s): %s", len(r.Unreadable), q(r.Unreadable)))
|
||||||
}
|
}
|
||||||
@@ -113,12 +122,16 @@ func Scan(brainDir string) (Result, error) {
|
|||||||
if d.IsDir() && p == rootGit {
|
if d.IsDir() && p == rootGit {
|
||||||
return filepath.SkipDir
|
return filepath.SkipDir
|
||||||
}
|
}
|
||||||
if d.Type()&os.ModeSymlink != 0 {
|
switch {
|
||||||
|
case d.Type()&os.ModeSymlink != 0:
|
||||||
r.Symlinks = append(r.Symlinks, rel)
|
r.Symlinks = append(r.Symlinks, rel)
|
||||||
|
case !d.IsDir() && !d.Type().IsRegular():
|
||||||
|
r.Special = append(r.Special, rel)
|
||||||
}
|
}
|
||||||
return nil
|
return nil
|
||||||
})
|
})
|
||||||
sort.Strings(r.Symlinks)
|
sort.Strings(r.Symlinks)
|
||||||
|
sort.Strings(r.Special)
|
||||||
sort.Strings(r.Unreadable)
|
sort.Strings(r.Unreadable)
|
||||||
if walkErr != nil {
|
if walkErr != nil {
|
||||||
// Only the root's own error reaches here (deeper errors are recorded
|
// Only the root's own error reaches here (deeper errors are recorded
|
||||||
@@ -182,14 +195,20 @@ func Watch(ctx context.Context, brainDir string, interval time.Duration, n Notif
|
|||||||
q.push(fmt.Sprintf("brain symlink tripwire (hyperguild#157): removed %d symlink(s) from the brain dir: %s",
|
q.push(fmt.Sprintf("brain symlink tripwire (hyperguild#157): removed %d symlink(s) from the brain dir: %s",
|
||||||
len(removed), Result{}.quoted(removed)))
|
len(removed), Result{}.quoted(removed)))
|
||||||
}
|
}
|
||||||
key = Result{Symlinks: failed, Unreadable: r.Unreadable}.String()
|
sRemoved, sFailed := removeSpecial(brainDir, r.Special)
|
||||||
|
if len(sRemoved) > 0 {
|
||||||
|
slog.Error("brain symlink tripwire removed special files", "count", len(sRemoved))
|
||||||
|
q.push(fmt.Sprintf("brain symlink tripwire (hyperguild#179): removed %d special file(s) (FIFO, socket or device) from the brain dir: %s",
|
||||||
|
len(sRemoved), Result{}.quoted(sRemoved)))
|
||||||
|
}
|
||||||
|
key = Result{Symlinks: failed, Unreadable: r.Unreadable, Special: sFailed}.String()
|
||||||
}
|
}
|
||||||
if key != reported {
|
if key != reported {
|
||||||
reported = key
|
reported = key
|
||||||
if key != "" {
|
if key != "" {
|
||||||
slog.Error("brain symlink tripwire", "finding", key)
|
slog.Error("brain symlink tripwire", "finding", key)
|
||||||
q.push("brain symlink tripwire (hyperguild#157): " + key +
|
q.push("brain symlink tripwire (hyperguild#157, #179): " + key +
|
||||||
". Readers may follow symlinks out of the brain; fix them.")
|
". Symlinks can lead readers out of the brain and special files can hang them; remove them.")
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -322,6 +341,40 @@ func permanent(err error) bool {
|
|||||||
return errors.As(err, &p) && p.Permanent()
|
return errors.As(err, &p) && p.Permanent()
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// removeSpecial unlinks each brain-relative FIFO, socket or device through
|
||||||
|
// an os.Root on the brain dir, after re-checking that it is still one: a
|
||||||
|
// path that is a regular file, a directory or a symlink at the re-check is
|
||||||
|
// left alone and reported as failed. The re-check narrows, but cannot close,
|
||||||
|
// the window before the unlink (Linux has no conditional unlink); the same
|
||||||
|
// window exists in removeSymlinks, and only a local writer can use it.
|
||||||
|
func removeSpecial(brainDir string, rels []string) (removed, failed []string) {
|
||||||
|
if len(rels) == 0 {
|
||||||
|
return nil, nil
|
||||||
|
}
|
||||||
|
resolved, err := filepath.EvalSymlinks(brainDir)
|
||||||
|
if err != nil {
|
||||||
|
return nil, rels
|
||||||
|
}
|
||||||
|
root, err := os.OpenRoot(resolved)
|
||||||
|
if err != nil {
|
||||||
|
return nil, rels
|
||||||
|
}
|
||||||
|
defer func() { _ = root.Close() }()
|
||||||
|
for _, rel := range rels {
|
||||||
|
fi, err := root.Lstat(rel)
|
||||||
|
if err != nil || fi.IsDir() || fi.Mode().IsRegular() || fi.Mode()&os.ModeSymlink != 0 {
|
||||||
|
failed = append(failed, rel)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
if err := root.Remove(rel); err != nil {
|
||||||
|
failed = append(failed, rel)
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
removed = append(removed, rel)
|
||||||
|
}
|
||||||
|
return removed, failed
|
||||||
|
}
|
||||||
|
|
||||||
// removeSymlinks unlinks each brain-relative symlink through an os.Root on
|
// removeSymlinks unlinks each brain-relative symlink through an os.Root on
|
||||||
// the brain dir, after re-checking it is still a symlink. Removing a symlink
|
// the brain dir, after re-checking it is still a symlink. Removing a symlink
|
||||||
// never touches its target. It returns what was removed and what was not.
|
// never touches its target. It returns what was removed and what was not.
|
||||||
|
|||||||
@@ -42,6 +42,11 @@ func TestSyncRefusesSymlinkedNotesAndSurvivesSwapRaces(t *testing.T) {
|
|||||||
brain := t.TempDir()
|
brain := t.TempDir()
|
||||||
writeNote(t, brain, "wiki/w/facts/ok.md", "inside note")
|
writeNote(t, brain, "wiki/w/facts/ok.md", "inside note")
|
||||||
require.NoError(t, os.Symlink(brainfstest.Outside(t), filepath.Join(brain, "wiki", "w", "facts", "leak.md")))
|
require.NoError(t, os.Symlink(brainfstest.Outside(t), filepath.Join(brain, "wiki", "w", "facts", "leak.md")))
|
||||||
|
// A link to a file elsewhere in the brain: os.Root allows it, only the
|
||||||
|
// regular-file checks refuse it (hyperguild#171). raw/ is not a scan root,
|
||||||
|
// so its sentinel can only arrive through the link.
|
||||||
|
inBrain := brainfstest.WriteSentinelAt(t, filepath.Join(brain, "raw", "s.md"))
|
||||||
|
require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(brain, "wiki", "w", "facts", "inlink.md")))
|
||||||
|
|
||||||
emb := &recordingEmbedder{}
|
emb := &recordingEmbedder{}
|
||||||
store := &stubStore{}
|
store := &stubStore{}
|
||||||
@@ -51,6 +56,7 @@ func TestSyncRefusesSymlinkedNotesAndSurvivesSwapRaces(t *testing.T) {
|
|||||||
assert.NotContains(t, emb.all(), brainfstest.Sentinel)
|
assert.NotContains(t, emb.all(), brainfstest.Sentinel)
|
||||||
for p := range store.upserts {
|
for p := range store.upserts {
|
||||||
assert.NotContains(t, p, "leak.md")
|
assert.NotContains(t, p, "leak.md")
|
||||||
|
assert.NotContains(t, p, "inlink.md")
|
||||||
}
|
}
|
||||||
|
|
||||||
p := filepath.Join(brain, "knowledge", "r.md")
|
p := filepath.Join(brain, "knowledge", "r.md")
|
||||||
@@ -61,6 +67,7 @@ func TestSyncRefusesSymlinkedNotesAndSurvivesSwapRaces(t *testing.T) {
|
|||||||
return e.all()
|
return e.all()
|
||||||
}
|
}
|
||||||
brainfstest.AssertNoLeak(t, p, "inside", 1500*time.Millisecond, sync)
|
brainfstest.AssertNoLeak(t, p, "inside", 1500*time.Millisecond, sync)
|
||||||
|
brainfstest.AssertNoLeakFrom(t, p, "inside", inBrain, 1500*time.Millisecond, sync)
|
||||||
brainfstest.AssertNoHang(t, p, "inside", 1500*time.Millisecond, 6*time.Second, func() { _ = sync() })
|
brainfstest.AssertNoHang(t, p, "inside", 1500*time.Millisecond, 6*time.Second, func() { _ = sync() })
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user