Compare commits
11
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
22d0653b61 | ||
|
|
1a2a93d2f4 | ||
|
|
77c44f298c | ||
|
|
f4636c7ef0 | ||
|
|
bd989f887f | ||
|
|
4770f97ffd | ||
|
|
ddd4bdc2ac | ||
|
|
1fff54769d | ||
|
|
0c3e82ca0a | ||
|
|
eedb110be5 | ||
|
|
febab3e45d |
@@ -17,6 +17,7 @@ import (
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/audit"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/capture"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/classification"
|
||||
@@ -89,11 +90,15 @@ func (s *claudeSink) Ingest(ctx context.Context, b claudewatcher.Batch) error {
|
||||
sb.WriteString("\n\n")
|
||||
}
|
||||
slug := "session-" + b.Host + "-" + b.SessionID
|
||||
dest := filepath.Join(s.brainDir, "archive", "claude-sessions", b.Host, slug+".md")
|
||||
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
||||
return fmt.Errorf("create claude-sessions archive dir: %w", err)
|
||||
dest := "archive/claude-sessions/" + b.Host + "/" + slug + ".md"
|
||||
// Written through the brain root, never through a symlinked directory
|
||||
// or file (hyperguild#158).
|
||||
bfs, err := brainfs.Open(s.brainDir)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(sb.String()), 0o644); err != nil {
|
||||
defer func() { _ = bfs.Close() }()
|
||||
if err := bfs.PutRegular(dest, []byte(sb.String())); err != nil {
|
||||
return fmt.Errorf("write claude session archive: %w", err)
|
||||
}
|
||||
s.logger.Debug("claude session archived (non-indexed)", "path", dest)
|
||||
|
||||
@@ -76,3 +76,27 @@ func TestAlertingWarnings(t *testing.T) {
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// hyperguild#158: the claude-session archive was written with os.MkdirAll +
|
||||
// os.WriteFile by path, so a symlinked archive directory redirected it.
|
||||
func TestClaudeSinkDoesNotWriteThroughASymlinkedArchiveDir(t *testing.T) {
|
||||
for name, mk := range map[string]func(t *testing.T, dir string) (link, target string){
|
||||
"outside": func(t *testing.T, _ string) (string, string) { o := t.TempDir(); return o, o },
|
||||
"in-brain": func(t *testing.T, dir string) (string, string) {
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
|
||||
return filepath.Join("..", "raw"), filepath.Join(dir, "raw")
|
||||
},
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
link, target := mk(t, dir)
|
||||
require.NoError(t, os.Symlink(link, filepath.Join(dir, "archive")))
|
||||
sink := &claudeSink{brainDir: dir, logger: slog.New(slog.NewTextHandler(os.Stderr, nil))}
|
||||
err := sink.Ingest(context.Background(), claudewatcher.Batch{Host: "koala", SessionID: "abc",
|
||||
Turns: []claudewatcher.Turn{{Type: "assistant", Content: "x"}}})
|
||||
assert.Error(t, err)
|
||||
ents, _ := os.ReadDir(target)
|
||||
assert.Empty(t, ents, "the archive was written at the link's target")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4,6 +4,7 @@ import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"syscall"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
@@ -63,3 +64,13 @@ func TestStartupSymlinkCheckRefusesAnUnlistableBrainRoot(t *testing.T) {
|
||||
t.Cleanup(func() { _ = os.Chmod(brain, 0o755) })
|
||||
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
|
||||
golang.org/x/crypto v0.51.0 // 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
|
||||
gopkg.in/yaml.v3 v3.0.1
|
||||
)
|
||||
|
||||
@@ -12,6 +12,7 @@ import (
|
||||
"time"
|
||||
|
||||
"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/pipeline"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/search"
|
||||
@@ -227,14 +228,22 @@ func writeHallNote(brainDir string, opts WriteNoteOptions) (string, error) {
|
||||
// The directory is created only once the note is known to be writable:
|
||||
// a refused write leaves nothing behind, not even an empty hall dir
|
||||
// (brain#21; provenance refusal joins the envelope refusal here).
|
||||
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
||||
return "", fmt.Errorf("create hall dir: %w", err)
|
||||
// Created through the brain root, never through a symlinked wing or
|
||||
// hall directory (hyperguild#188).
|
||||
rel, err := filepath.Rel(brainDir, dest)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("note path: %w", err)
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(final), 0o644); err != nil {
|
||||
rel = filepath.ToSlash(rel)
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
defer func() { _ = bfs.Close() }()
|
||||
if err := bfs.PutRegular(rel, []byte(final)); err != nil {
|
||||
return "", fmt.Errorf("write: %w", err)
|
||||
}
|
||||
rel, _ := filepath.Rel(brainDir, dest)
|
||||
return filepath.ToSlash(rel), nil
|
||||
return rel, nil
|
||||
}
|
||||
|
||||
// scalarValues flattens frontmatter fields to key -> scalar value for
|
||||
|
||||
@@ -127,18 +127,18 @@ func PromoteNote(brainDir string, opts PromoteOptions) (string, error) {
|
||||
}
|
||||
fm.set("promoted_at", now)
|
||||
|
||||
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
||||
return "", fmt.Errorf("create wing dir: %w", err)
|
||||
}
|
||||
// Write-then-delete: the source survives any write failure.
|
||||
// Write-then-delete: the source survives any write failure. Both go
|
||||
// through the brain root (hyperguild#188).
|
||||
promoted, err := StampProvenance(fm.render()+body, opts.Origin, opts.WrittenBy)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(promoted), 0o644); err != nil {
|
||||
// Created with O_EXCL: a note that appeared after the collision check
|
||||
// above is never overwritten.
|
||||
if err := createBrainFile(brainDir, dest, []byte(promoted)); err != nil {
|
||||
return "", fmt.Errorf("write promoted note: %w", err)
|
||||
}
|
||||
if err := os.Remove(src); err != nil {
|
||||
if err := removeBrainFile(brainDir, src); err != nil {
|
||||
return "", fmt.Errorf("promoted note written but source removal failed: %w", err)
|
||||
}
|
||||
|
||||
@@ -196,14 +196,12 @@ func RejectNote(brainDir string, opts RejectOptions) (string, error) {
|
||||
fm.set("reject_reason", opts.Reason)
|
||||
}
|
||||
|
||||
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
||||
return "", fmt.Errorf("create rejected dir: %w", err)
|
||||
}
|
||||
// Write-then-delete: the source survives any write failure.
|
||||
if err := os.WriteFile(dest, []byte(fm.render()+body), 0o644); err != nil {
|
||||
// Write-then-delete: the source survives any write failure. Both go
|
||||
// through the brain root (hyperguild#188).
|
||||
if err := createBrainFile(brainDir, dest, []byte(fm.render()+body)); err != nil {
|
||||
return "", fmt.Errorf("write rejected note: %w", err)
|
||||
}
|
||||
if err := os.Remove(src); err != nil {
|
||||
if err := removeBrainFile(brainDir, src); err != nil {
|
||||
return "", fmt.Errorf("rejected note written but source removal failed: %w", err)
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,87 @@
|
||||
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"
|
||||
)
|
||||
|
||||
// hyperguild#188: promote and reject wrote the destination with
|
||||
// os.MkdirAll + os.WriteFile by path, so a symlinked wing (promote) or a
|
||||
// symlinked raw/rejected (reject) redirected the note; the raw source was
|
||||
// then removed.
|
||||
func TestPromoteAndRejectRefuseASymlinkedDestinationDirectory(t *testing.T) {
|
||||
brain := t.TempDir()
|
||||
outside := t.TempDir()
|
||||
raw := filepath.Join(brain, "raw")
|
||||
require.NoError(t, os.MkdirAll(raw, 0o755))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(raw, "2026-10-05-n.md"), []byte("---\ntitle: n\n---\nbody\n"), 0o644))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki"), 0o755))
|
||||
require.NoError(t, os.Symlink(outside, filepath.Join(brain, "wiki", "lw")))
|
||||
require.NoError(t, os.Symlink(outside, filepath.Join(raw, "rejected")))
|
||||
|
||||
_, err := api.PromoteNote(brain, api.PromoteOptions{Filename: "2026-10-05-n.md", Wing: "lw", Hall: "facts"})
|
||||
assert.Error(t, err)
|
||||
_, err = api.RejectNote(brain, api.RejectOptions{Filename: "2026-10-05-n.md"})
|
||||
assert.Error(t, err)
|
||||
ents, _ := os.ReadDir(outside)
|
||||
assert.Empty(t, ents, "a note was written outside the brain")
|
||||
_, err = os.Stat(filepath.Join(raw, "2026-10-05-n.md"))
|
||||
assert.NoError(t, err, "the raw source is kept when the write is refused")
|
||||
|
||||
require.NoError(t, os.Remove(filepath.Join(raw, "rejected")))
|
||||
_, err = api.PromoteNote(brain, api.PromoteOptions{Filename: "2026-10-05-n.md", Wing: "w", Hall: "facts"})
|
||||
require.NoError(t, err, "positive control: promote into a real wing")
|
||||
}
|
||||
|
||||
// StampProvenanceFile read and rewrote the note by path (provenance.ApplyFile).
|
||||
func TestStampProvenanceFileRefusesANoteBehindASymlinkedDirectory(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")))
|
||||
assert.Error(t, api.StampProvenanceFile(brain, "wiki/w/alias/v.md", "static", "x"))
|
||||
got, _ := os.ReadFile(victim)
|
||||
assert.Equal(t, "---\ntitle: v\n---\nuntouched\n", string(got))
|
||||
|
||||
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---\nbody\n"), 0o644))
|
||||
require.NoError(t, api.StampProvenanceFile(brain, "wiki/w/facts/r.md", "static", "x"), "positive control")
|
||||
got, _ = os.ReadFile(real)
|
||||
assert.Contains(t, string(got), "written_by: x")
|
||||
}
|
||||
|
||||
// The same through an in-brain symlinked wing and raw/rejected, which
|
||||
// os.Root alone would follow.
|
||||
func TestPromoteAndRejectRefuseAnInBrainSymlinkedDestinationDirectory(t *testing.T) {
|
||||
brain := t.TempDir()
|
||||
raw := filepath.Join(brain, "raw")
|
||||
require.NoError(t, os.MkdirAll(raw, 0o755))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(raw, "2026-10-05-n.md"), []byte("---\ntitle: n\n---\nbody\n"), 0o644))
|
||||
target := filepath.Join(brain, "archive")
|
||||
require.NoError(t, os.MkdirAll(target, 0o755))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki"), 0o755))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "archive"), filepath.Join(brain, "wiki", "lw")))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "archive"), filepath.Join(raw, "rejected")))
|
||||
|
||||
_, err := api.PromoteNote(brain, api.PromoteOptions{Filename: "2026-10-05-n.md", Wing: "lw", Hall: "facts"})
|
||||
assert.Error(t, err)
|
||||
_, err = api.RejectNote(brain, api.RejectOptions{Filename: "2026-10-05-n.md"})
|
||||
assert.Error(t, err)
|
||||
ents, _ := os.ReadDir(target)
|
||||
assert.Empty(t, ents, "a note was written at the in-brain link's target")
|
||||
_, err = os.Stat(filepath.Join(raw, "2026-10-05-n.md"))
|
||||
assert.NoError(t, err, "the raw source is kept")
|
||||
|
||||
require.NoError(t, os.Remove(filepath.Join(raw, "rejected")))
|
||||
_, err = api.RejectNote(brain, api.RejectOptions{Filename: "2026-10-05-n.md"})
|
||||
require.NoError(t, err, "positive control: reject into a real raw/rejected")
|
||||
}
|
||||
@@ -1,6 +1,10 @@
|
||||
package api
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"path/filepath"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/provenance"
|
||||
)
|
||||
|
||||
@@ -11,11 +15,61 @@ func StampProvenance(content, origin, writtenBy string) (string, error) {
|
||||
return provenance.Apply(content, provenance.Stamp{Origin: origin, WrittenBy: writtenBy})
|
||||
}
|
||||
|
||||
// StampProvenanceFile applies StampProvenance to a brain-relative note path.
|
||||
// StampProvenanceFile applies StampProvenance to a brain-relative note path,
|
||||
// read and rewritten through the brain root (hyperguild#158).
|
||||
func StampProvenanceFile(brainDir, relPath, origin, writtenBy string) error {
|
||||
_, abs, err := resolveWithin(brainDir, relPath)
|
||||
rel, _, err := resolveWithin(brainDir, relPath)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
return provenance.ApplyFile(abs, provenance.Stamp{Origin: origin, WrittenBy: writtenBy})
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
defer func() { _ = bfs.Close() }()
|
||||
b, err := bfs.ReadRegular(rel)
|
||||
if err != nil {
|
||||
return fmt.Errorf("read for provenance: %w", err)
|
||||
}
|
||||
out, err := provenance.Apply(string(b), provenance.Stamp{Origin: origin, WrittenBy: writtenBy})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if out == string(b) {
|
||||
return nil
|
||||
}
|
||||
if err := bfs.WriteRegular(rel, []byte(out)); err != nil {
|
||||
return fmt.Errorf("write provenance: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// createBrainFile creates the file at abs (inside brainDir) through the
|
||||
// brain root and fails if anything is already there.
|
||||
func createBrainFile(brainDir, abs string, data []byte) error {
|
||||
rel, err := filepath.Rel(brainDir, abs)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
defer func() { _ = bfs.Close() }()
|
||||
return bfs.CreateRegular(filepath.ToSlash(rel), data)
|
||||
}
|
||||
|
||||
// removeBrainFile removes the file at abs (inside brainDir) through the
|
||||
// brain root.
|
||||
func removeBrainFile(brainDir, abs string) error {
|
||||
rel, err := filepath.Rel(brainDir, abs)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
defer func() { _ = bfs.Close() }()
|
||||
return bfs.Remove(filepath.ToSlash(rel))
|
||||
}
|
||||
|
||||
@@ -23,6 +23,13 @@ func TestReadNoteRefusesSymlinksAndSurvivesSwapRaces(t *testing.T) {
|
||||
_, body, _, err := api.ReadNote(brain, "wiki/w/facts/leak.md")
|
||||
assert.Error(t, err)
|
||||
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")
|
||||
require.NoError(t, os.WriteFile(p, []byte("---\nx: y\n---\ninside"), 0o644))
|
||||
@@ -39,5 +46,7 @@ func TestReadNoteRefusesSymlinksAndSurvivesSwapRaces(t *testing.T) {
|
||||
return s
|
||||
}
|
||||
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() })
|
||||
}
|
||||
|
||||
@@ -3,15 +3,18 @@ package api
|
||||
import (
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"errors"
|
||||
"fmt"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"io/fs"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"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/notes"
|
||||
)
|
||||
|
||||
// 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, 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 {
|
||||
return "", "", "", err
|
||||
}
|
||||
|
||||
prior, err := os.ReadFile(abs)
|
||||
rel = t.Rel
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
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("read target: %w", err)
|
||||
@@ -164,7 +176,7 @@ func UpdateNote(brainDir string, opts UpdateNoteOptions) (relPath, contentHash,
|
||||
return "", "", "", err
|
||||
}
|
||||
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 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 +1,34 @@
|
||||
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"
|
||||
)
|
||||
|
||||
// hyperguild#178: an unreadable directory under wiki/ made the link check
|
||||
// fail and brain_write refuse the note, losing the learning. The note is now
|
||||
// written with its links as given.
|
||||
func TestWriteNoteKeepsTheLearningWhenTheLinkCheckCannotIndex(t *testing.T) {
|
||||
if os.Geteuid() == 0 {
|
||||
t.Skip("root ignores directory permissions")
|
||||
}
|
||||
brain := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w", "facts"), 0o755))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "w", "facts", "real.md"), []byte("x"), 0o644))
|
||||
locked := filepath.Join(brain, "wiki", "other", "locked")
|
||||
require.NoError(t, os.MkdirAll(locked, 0o755))
|
||||
require.NoError(t, os.Chmod(locked, 0o000))
|
||||
t.Cleanup(func() { _ = os.Chmod(locked, 0o755) })
|
||||
|
||||
rel, err := api.WriteNote(brain, api.WriteNoteOptions{Wing: "w", Hall: "facts", Filename: "n", Content: "learning [[real]] and [[gone]]"})
|
||||
require.NoError(t, err)
|
||||
got, err := os.ReadFile(filepath.Join(brain, filepath.FromSlash(rel)))
|
||||
require.NoError(t, err)
|
||||
assert.Contains(t, string(got), "[[gone]]", "links kept as given when the index is partial")
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
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"
|
||||
)
|
||||
|
||||
// hyperguild#188: brain_write created a new note with os.MkdirAll +
|
||||
// os.WriteFile by path, so a symlinked wing directory redirected the note
|
||||
// elsewhere in the brain or outside it.
|
||||
func TestWriteNoteRefusesASymlinkedWing(t *testing.T) {
|
||||
for name, target := range map[string]func(t *testing.T, brain string) string{
|
||||
"in-brain": func(t *testing.T, brain string) string {
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(brain, "raw"), 0o755))
|
||||
return filepath.Join("..", "raw")
|
||||
},
|
||||
"outside": func(t *testing.T, _ string) string { return t.TempDir() },
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
brain := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki"), 0o755))
|
||||
link := target(t, brain)
|
||||
require.NoError(t, os.Symlink(link, filepath.Join(brain, "wiki", "lw")))
|
||||
_, err := api.WriteNote(brain, api.WriteNoteOptions{Wing: "lw", Hall: "facts", Filename: "n", Content: "learning"})
|
||||
assert.Error(t, err)
|
||||
resolved := link
|
||||
if !filepath.IsAbs(resolved) {
|
||||
resolved = filepath.Join(brain, "wiki", link)
|
||||
}
|
||||
_, serr := os.Stat(filepath.Join(resolved, "facts"))
|
||||
assert.True(t, os.IsNotExist(serr), "a hall was created at the link's target")
|
||||
|
||||
_, err = api.WriteNote(brain, api.WriteNoteOptions{Wing: "w", Hall: "facts", Filename: "n", Content: "learning"})
|
||||
require.NoError(t, err, "positive control: a real wing is written")
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -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")
|
||||
}
|
||||
@@ -7,8 +7,6 @@ import (
|
||||
"fmt"
|
||||
"io"
|
||||
"io/fs"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
@@ -32,7 +30,6 @@ func BuildWingIndex(brainDir, wing string) error {
|
||||
if w == "" {
|
||||
return fmt.Errorf("invalid wing %q", wing)
|
||||
}
|
||||
wingDir := filepath.Join(brainDir, "wiki", w)
|
||||
// Listed and read through the brain root (hyperguild#157): a wing or
|
||||
// hall that is a symlink is not followed, and notes are regular files.
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
@@ -63,8 +60,9 @@ func BuildWingIndex(brainDir, wing string) error {
|
||||
fmt.Fprintf(&b, "| %s | [%s](%s/%s.md) | %s |\n", e.Hall, e.Title, e.Hall, e.Slug, e.Created)
|
||||
}
|
||||
|
||||
dest := filepath.Join(wingDir, "_index.md")
|
||||
return os.WriteFile(dest, []byte(b.String()), 0o644)
|
||||
// Written through the brain root, never through a symlinked _index.md
|
||||
// (hyperguild#158).
|
||||
return bfs.PutRegular("wiki/"+w+"/_index.md", []byte(b.String()))
|
||||
}
|
||||
|
||||
// BuildAllWingIndexes regenerates _index.md for every wing under brain/wiki/.
|
||||
@@ -116,23 +114,6 @@ func collectWingEntries(bfs *brainfs.Brain, wingRel string) ([]noteEntry, error)
|
||||
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,
|
||||
// regular files only (hyperguild#157).
|
||||
func readTitleAndCreatedIn(bfs *brainfs.Brain, rel, slug string) (string, string) {
|
||||
|
||||
@@ -47,7 +47,12 @@ var (
|
||||
func StripUnresolvedLinks(brainDir, content string) (string, []string, error) {
|
||||
index, err := entryIndex(brainDir)
|
||||
if err != nil {
|
||||
return "", nil, err
|
||||
// A partial index cannot tell an invented link from one into the
|
||||
// part it could not read, so unwrap nothing, and do not refuse the
|
||||
// write either: this runs before every brain_write, and a refused
|
||||
// write is a lost learning (hyperguild#178).
|
||||
slog.Warn("link check skipped: cannot index the brain", "err", err)
|
||||
return content, nil, nil
|
||||
}
|
||||
if len(index) == 0 {
|
||||
return content, nil, nil
|
||||
|
||||
@@ -0,0 +1,41 @@
|
||||
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"
|
||||
)
|
||||
|
||||
// hyperguild#178: StripUnresolvedLinks runs before every brain_write and
|
||||
// brain_update. An unreadable directory under knowledge/ or wiki/ made it
|
||||
// error, the write was refused and the learning lost. When the link index
|
||||
// cannot be built, the content is now returned unchanged (no link is
|
||||
// unwrapped, none is invented) and no error stops the write.
|
||||
func TestStripUnresolvedLinksKeepsContentWhenTheIndexCannotBeBuilt(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", "real.md"), []byte("x"), 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) })
|
||||
|
||||
in := "learning [[real]] and [[gone]]"
|
||||
out, unlinked, err := brain.StripUnresolvedLinks(b, in)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, in, out, "content unchanged: no link unwrapped on a partial index")
|
||||
assert.Empty(t, unlinked)
|
||||
|
||||
require.NoError(t, os.Chmod(locked, 0o755))
|
||||
out, _, err = brain.StripUnresolvedLinks(b, in)
|
||||
require.NoError(t, err)
|
||||
assert.NotContains(t, out, "[[gone]]", "positive control: with a readable tree the strip runs")
|
||||
}
|
||||
@@ -2,11 +2,15 @@ package brain
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"io/fs"
|
||||
"path"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
)
|
||||
|
||||
// seeAlsoHeader is the markdown heading used to group cross-wing links.
|
||||
@@ -36,24 +40,29 @@ type TunnelCandidate struct {
|
||||
// A note's title is read from YAML frontmatter `title:`; failing that,
|
||||
// the filename slug (sans `.md`, hyphens → spaces) is used.
|
||||
func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
||||
wikiDir := filepath.Join(brainDir, "wiki")
|
||||
if _, err := os.Stat(wikiDir); os.IsNotExist(err) {
|
||||
// Walked and read through the brain root, regular files only
|
||||
// (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
|
||||
} else if err != nil {
|
||||
return nil, fmt.Errorf("stat wiki: %w", err)
|
||||
}
|
||||
|
||||
lowerContent := strings.ToLower(content)
|
||||
|
||||
var out []TunnelCandidate
|
||||
err := filepath.WalkDir(wikiDir, func(path string, d os.DirEntry, err error) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if d.IsDir() || !strings.HasSuffix(path, ".md") || d.Name() == "_index.md" {
|
||||
var walkErr error
|
||||
err = bfs.WalkRegular("wiki", func(rel string) error {
|
||||
name := path.Base(rel)
|
||||
if !strings.HasSuffix(name, ".md") || name == "_index.md" {
|
||||
return nil
|
||||
}
|
||||
title, _ := readTitleAndCreated(path, strings.TrimSuffix(d.Name(), ".md"))
|
||||
title, _ := readTitleAndCreatedIn(bfs, rel, strings.TrimSuffix(name, ".md"))
|
||||
title = strings.TrimSpace(title)
|
||||
if title == "" {
|
||||
return nil
|
||||
@@ -75,17 +84,25 @@ func DetectTunnels(brainDir, content string) ([]TunnelCandidate, error) {
|
||||
if idx == -1 {
|
||||
return nil
|
||||
}
|
||||
rel, err := filepath.Rel(brainDir, path)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
out = append(out, TunnelCandidate{
|
||||
TargetPath: filepath.ToSlash(rel),
|
||||
TargetPath: rel,
|
||||
MatchedTerm: title,
|
||||
Exact: isWholeWord(haystack, idx, len(needle)),
|
||||
})
|
||||
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 {
|
||||
return nil, err
|
||||
}
|
||||
@@ -158,35 +175,23 @@ func logFuzzyCandidates(brainDir, sourcePath string, cs []TunnelCandidate) error
|
||||
if len(cs) == 0 {
|
||||
return nil
|
||||
}
|
||||
rawDir := filepath.Join(brainDir, "raw")
|
||||
if err := os.MkdirAll(rawDir, 0o755); err != nil {
|
||||
return err
|
||||
}
|
||||
stamp := time.Now().UTC().Format("2006-01-02")
|
||||
path := filepath.Join(rawDir, "tunnel-candidates-"+stamp+".md")
|
||||
existed := fileExists(path)
|
||||
f, err := os.OpenFile(path, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
|
||||
// Appended through the brain root, never through a symlinked raw/ or
|
||||
// log file (hyperguild#158).
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = f.Close() }()
|
||||
if !existed {
|
||||
if _, err := f.WriteString("# Tunnel candidates " + stamp + "\n\nFuzzy cross-wing matches surfaced by AutoTunnel. Review and promote to a tunnel via `brain_tunnel` if relevant.\n\n"); err != nil {
|
||||
return err
|
||||
return fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
defer func() { _ = bfs.Close() }()
|
||||
stamp := time.Now().UTC().Format("2006-01-02")
|
||||
rel := "raw/tunnel-candidates-" + stamp + ".md"
|
||||
var buf strings.Builder
|
||||
if _, err := bfs.Lstat(rel); errors.Is(err, fs.ErrNotExist) {
|
||||
buf.WriteString("# Tunnel candidates " + stamp + "\n\nFuzzy cross-wing matches surfaced by AutoTunnel. Review and promote to a tunnel via `brain_tunnel` if relevant.\n\n")
|
||||
}
|
||||
for _, c := range cs {
|
||||
line := fmt.Sprintf("- `%s` ↔ `%s` (term: %q)\n", sourcePath, c.TargetPath, c.MatchedTerm)
|
||||
if _, err := f.WriteString(line); err != nil {
|
||||
return err
|
||||
fmt.Fprintf(&buf, "- `%s` ↔ `%s` (term: %q)\n", sourcePath, c.TargetPath, c.MatchedTerm)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func fileExists(p string) bool {
|
||||
_, err := os.Stat(p)
|
||||
return err == nil
|
||||
return bfs.AppendRegular(rel, []byte(buf.String()))
|
||||
}
|
||||
|
||||
// WriteTunnel appends a bidirectional wikilink between sourcePath and
|
||||
@@ -197,6 +202,12 @@ func fileExists(p string) bool {
|
||||
// section headers. Rejects same-wing pairs (a tunnel is by definition
|
||||
// cross-wing) and missing notes.
|
||||
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)
|
||||
if err != nil {
|
||||
return fmt.Errorf("source: %w", err)
|
||||
@@ -209,20 +220,50 @@ func WriteTunnel(brainDir, sourcePath, targetPath string) error {
|
||||
return fmt.Errorf("tunnel must cross wings; got both in %q", srcWing)
|
||||
}
|
||||
|
||||
srcFull := filepath.Join(brainDir, filepath.FromSlash(sourcePath))
|
||||
tgtFull := filepath.Join(brainDir, filepath.FromSlash(targetPath))
|
||||
if _, err := os.Stat(srcFull); err != nil {
|
||||
// Both notes are read and rewritten through the brain root, regular
|
||||
// files only: brain_tunnel passes caller-supplied paths, and the brain is
|
||||
// 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)
|
||||
}
|
||||
if _, err := os.Stat(tgtFull); err != nil {
|
||||
tgtContent, err := bfs.ReadRegular(targetPath)
|
||||
if err != nil {
|
||||
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)
|
||||
}
|
||||
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)
|
||||
} 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
|
||||
}
|
||||
@@ -248,16 +289,13 @@ func wingOf(relPath string) (string, error) {
|
||||
return parts[1], nil
|
||||
}
|
||||
|
||||
// appendSeeAlso inserts `- [[link]]` under the file's See also section,
|
||||
// creating the section if absent. No-op when the link is already present.
|
||||
func appendSeeAlso(filePath, link string) error {
|
||||
content, err := os.ReadFile(filePath)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
// withSeeAlso returns content with `- [[link]]` under its See also section,
|
||||
// creating the section if absent. changed is false when the link is already
|
||||
// present.
|
||||
func withSeeAlso(content []byte, link string) (out []byte, changed bool, err error) {
|
||||
wikilink := "[[" + link + "]]"
|
||||
if strings.Contains(string(content), wikilink) {
|
||||
return nil
|
||||
return content, false, nil
|
||||
}
|
||||
|
||||
bullet := "- " + wikilink
|
||||
@@ -266,8 +304,7 @@ func appendSeeAlso(filePath, link string) error {
|
||||
// No section yet — append a fresh one. Always emit a trailing
|
||||
// newline so subsequent appends don't merge into the previous line.
|
||||
trimmed := strings.TrimRight(string(content), "\n")
|
||||
out := trimmed + "\n\n" + seeAlsoHeader + "\n\n" + bullet + "\n"
|
||||
return os.WriteFile(filePath, []byte(out), 0o644)
|
||||
return []byte(trimmed + "\n\n" + seeAlsoHeader + "\n\n" + bullet + "\n"), true, nil
|
||||
}
|
||||
|
||||
// Section exists — splice the bullet in just before the next `## `
|
||||
@@ -293,12 +330,11 @@ func appendSeeAlso(filePath, link string) error {
|
||||
b.WriteByte('\n')
|
||||
}
|
||||
if err := scanner.Err(); err != nil {
|
||||
return err
|
||||
return nil, false, err
|
||||
}
|
||||
if !inserted {
|
||||
// section was the last thing in the file — just append bullet
|
||||
out := strings.TrimRight(b.String(), "\n") + "\n" + bullet + "\n"
|
||||
return os.WriteFile(filePath, []byte(out), 0o644)
|
||||
return []byte(strings.TrimRight(b.String(), "\n") + "\n" + bullet + "\n"), true, nil
|
||||
}
|
||||
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")
|
||||
}
|
||||
@@ -0,0 +1,52 @@
|
||||
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"
|
||||
)
|
||||
|
||||
// hyperguild#158: BuildWingIndex wrote wiki/<wing>/_index.md with
|
||||
// os.WriteFile, so a symlinked _index.md was written through.
|
||||
func TestBuildWingIndexDoesNotWriteThroughASymlinkedIndex(t *testing.T) {
|
||||
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", "n.md"), []byte("---\ntitle: zqn\n---\n"), 0o644))
|
||||
victim := filepath.Join(b, "raw", "v.md")
|
||||
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "v.md"), filepath.Join(b, "wiki", "w", "_index.md")))
|
||||
assert.Error(t, brain.BuildWingIndex(b, "w"))
|
||||
got, _ := os.ReadFile(victim)
|
||||
assert.Equal(t, "untouched", string(got))
|
||||
|
||||
require.NoError(t, os.Remove(filepath.Join(b, "wiki", "w", "_index.md")))
|
||||
require.NoError(t, brain.BuildWingIndex(b, "w"), "positive control")
|
||||
idx, _ := os.ReadFile(filepath.Join(b, "wiki", "w", "_index.md"))
|
||||
assert.Contains(t, string(idx), "zqn")
|
||||
}
|
||||
|
||||
// AutoTunnel's fuzzy-candidate log appended to raw/tunnel-candidates-*.md
|
||||
// with os.OpenFile, so a symlinked raw/ (or log file) was written through.
|
||||
func TestAutoTunnelDoesNotAppendTheCandidateLogThroughASymlinkedRaw(t *testing.T) {
|
||||
b := t.TempDir()
|
||||
outside := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "a", "facts"), 0o755))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "b", "facts"), 0o755))
|
||||
// "zq widget" matches as a substring of "zq widgets", a fuzzy candidate.
|
||||
require.NoError(t, os.WriteFile(filepath.Join(b, "wiki", "b", "facts", "t.md"), []byte("---\ntitle: Zq Widget\n---\n"), 0o644))
|
||||
require.NoError(t, os.Symlink(outside, filepath.Join(b, "raw")))
|
||||
_ = brain.AutoTunnel(b, "wiki/a/facts/s.md", "about zq widgets")
|
||||
ents, _ := os.ReadDir(outside)
|
||||
assert.Empty(t, ents, "the candidate log was written outside the brain")
|
||||
|
||||
require.NoError(t, os.Remove(filepath.Join(b, "raw")))
|
||||
require.NoError(t, brain.AutoTunnel(b, "wiki/a/facts/s.md", "about zq widgets"))
|
||||
logs, _ := filepath.Glob(filepath.Join(b, "raw", "tunnel-candidates-*.md"))
|
||||
assert.Len(t, logs, 1, "positive control: the fuzzy candidate is logged in the real raw/")
|
||||
}
|
||||
@@ -104,6 +104,17 @@ func (b *Brain) ReadDirRegular(relDir string) ([]string, error) {
|
||||
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) {
|
||||
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
|
||||
// directory, by name. Every component of relDir must be a real directory
|
||||
// (ErrNotRegular otherwise); symlinks to directories are left out.
|
||||
@@ -125,9 +136,170 @@ func (b *Brain) ReadDirDirs(relDir string) ([]string, error) {
|
||||
return names, nil
|
||||
}
|
||||
|
||||
// PutRegular creates or replaces a regular file at a brain-relative path,
|
||||
// for creating writes (hyperguild#188, #158). Missing parent directories are
|
||||
// created one component at a time through the root, and every existing
|
||||
// component must be a real directory, so a symlinked directory cannot
|
||||
// redirect the write elsewhere in the brain or outside it. An existing file
|
||||
// is replaced only if it is regular (WriteRegular's checks); a new file is
|
||||
// created with O_EXCL and confirmed to be the file that was opened. A
|
||||
// directory swapped in after the checks is the #167 residual.
|
||||
func (b *Brain) PutRegular(rel string, data []byte) error {
|
||||
if err := cleanRel(rel); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := b.mkdirReal(path.Dir(rel)); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := b.root.Lstat(rel); err == nil {
|
||||
return b.WriteRegular(rel, data)
|
||||
} else if !errors.Is(err, fs.ErrNotExist) {
|
||||
return err
|
||||
}
|
||||
return b.createNew(rel, data)
|
||||
}
|
||||
|
||||
// CreateRegular creates a new regular file at a brain-relative path, with
|
||||
// PutRegular's parent rules, and fails with fs.ErrExist if anything is
|
||||
// already there: for writers that must never overwrite (promote, reject).
|
||||
func (b *Brain) CreateRegular(rel string, data []byte) error {
|
||||
if err := cleanRel(rel); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := b.mkdirReal(path.Dir(rel)); err != nil {
|
||||
return err
|
||||
}
|
||||
return b.createNew(rel, data)
|
||||
}
|
||||
|
||||
// createNew creates rel with O_EXCL and writes data only after confirming
|
||||
// the path is the regular file it created.
|
||||
func (b *Brain) createNew(rel string, data []byte) error {
|
||||
f, err := b.root.OpenFile(rel, os.O_WRONLY|os.O_CREATE|os.O_EXCL|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0o644)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = f.Close() }()
|
||||
hfi, herr := f.Stat()
|
||||
lfi, lerr := b.root.Lstat(rel)
|
||||
if herr != nil || lerr != nil || !lfi.Mode().IsRegular() || !os.SameFile(lfi, hfi) {
|
||||
return fmt.Errorf("%s: changed while creating: %w", rel, ErrNotRegular)
|
||||
}
|
||||
if _, err := f.Write(data); err != nil {
|
||||
return err
|
||||
}
|
||||
return f.Close()
|
||||
}
|
||||
|
||||
// AppendRegular appends data to a regular file at a brain-relative path,
|
||||
// creating it (and missing parent directories, as PutRegular does) if it is
|
||||
// absent. It writes only after confirming the path is the regular file it
|
||||
// opened, so a final symlink or special file, or one swapped in, is refused.
|
||||
func (b *Brain) AppendRegular(rel string, data []byte) error {
|
||||
if err := cleanRel(rel); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := b.mkdirReal(path.Dir(rel)); err != nil {
|
||||
return err
|
||||
}
|
||||
if fi, err := b.root.Lstat(rel); err == nil && !fi.Mode().IsRegular() {
|
||||
return fmt.Errorf("%s: %w", rel, ErrNotRegular)
|
||||
} else if err != nil && !errors.Is(err, fs.ErrNotExist) {
|
||||
return err
|
||||
}
|
||||
f, err := b.root.OpenFile(rel, os.O_WRONLY|os.O_APPEND|os.O_CREATE|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0o644)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = f.Close() }()
|
||||
hfi, herr := f.Stat()
|
||||
lfi, lerr := b.root.Lstat(rel)
|
||||
if herr != nil || lerr != nil || !lfi.Mode().IsRegular() || !os.SameFile(lfi, hfi) {
|
||||
return fmt.Errorf("%s: changed while opening: %w", rel, ErrNotRegular)
|
||||
}
|
||||
if _, err := f.Write(data); err != nil {
|
||||
return err
|
||||
}
|
||||
return f.Close()
|
||||
}
|
||||
|
||||
// Remove removes the file at a clean brain-relative path through the root,
|
||||
// refusing a path behind a symlinked directory. A final symlink is removed
|
||||
// itself, never its target.
|
||||
func (b *Brain) Remove(rel string) error {
|
||||
if err := b.RealParent(rel); err != nil {
|
||||
return err
|
||||
}
|
||||
return b.root.Remove(rel)
|
||||
}
|
||||
|
||||
// RealParent returns ErrNotRegular unless rel is clean and every directory
|
||||
// above it is a real directory, for writers that do their own I/O (an atomic
|
||||
// rename) but must not be redirected by a symlinked directory.
|
||||
func (b *Brain) RealParent(rel string) error {
|
||||
if err := cleanRel(rel); err != nil {
|
||||
return err
|
||||
}
|
||||
return b.realDir(path.Dir(rel))
|
||||
}
|
||||
|
||||
// PutFile opens the brain dir as a root and calls PutRegular, for one-off
|
||||
// writers that hold no Brain.
|
||||
func PutFile(brainDir, rel string, data []byte) error {
|
||||
b, err := Open(brainDir)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = b.Close() }()
|
||||
return b.PutRegular(rel, data)
|
||||
}
|
||||
|
||||
// AppendFile opens the brain dir as a root and calls AppendRegular.
|
||||
func AppendFile(brainDir, rel string, data []byte) error {
|
||||
b, err := Open(brainDir)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = b.Close() }()
|
||||
return b.AppendRegular(rel, data)
|
||||
}
|
||||
|
||||
// mkdirReal makes sure every component of rel exists as a real directory,
|
||||
// creating missing ones through the root; an existing component that is
|
||||
// not a real directory is ErrNotRegular.
|
||||
func (b *Brain) mkdirReal(rel string) error {
|
||||
if rel == "." {
|
||||
return nil
|
||||
}
|
||||
prefix := ""
|
||||
for _, part := range strings.Split(rel, "/") {
|
||||
prefix = path.Join(prefix, part)
|
||||
fi, err := b.root.Lstat(prefix)
|
||||
if errors.Is(err, fs.ErrNotExist) {
|
||||
if err := b.root.Mkdir(prefix, 0o755); err != nil && !errors.Is(err, fs.ErrExist) {
|
||||
return err
|
||||
}
|
||||
fi, err = b.root.Lstat(prefix)
|
||||
}
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if !fi.IsDir() {
|
||||
return fmt.Errorf("%s: component %s is not a directory: %w", rel, prefix, ErrNotRegular)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// ReadRegular reads a brain-relative path, refusing anything that is not a
|
||||
// regular file, both before the open and on the opened handle.
|
||||
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)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
@@ -154,6 +326,12 @@ func (b *Brain) readOpened(rel string) ([]byte, error) { return b.readOpenedMax(
|
||||
// ReadRegularMax is ReadRegular with a size limit, checked on the opened
|
||||
// handle before reading (max < 0 means no limit).
|
||||
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)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
@@ -249,3 +427,51 @@ func (b *Brain) WalkRegular(relDir string, fn func(rel string) error, onErr func
|
||||
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
|
||||
// brain between the Lstat and the open: os.Root follows in-root links, so
|
||||
// only comparing the two (os.SameFile) refuses it.
|
||||
func TestReadRegularNeverReturnsAnInBrainFileSwappedInBehindASymlink(t *testing.T) {
|
||||
func TestReadRegularDoesNotReturnAnInBrainFileSwappedInBehindASymlink(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "s.md"), []byte("zqsamefilesentinel"), 0o644))
|
||||
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")
|
||||
}
|
||||
|
||||
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) {
|
||||
dir := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "a", "real"), 0o755))
|
||||
@@ -280,3 +326,223 @@ func TestReadDirDirsListsOnlyRealSubdirsAndRefusesSymlinkedComponents(t *testing
|
||||
_, err = b.ReadDirDirs("alias")
|
||||
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))
|
||||
}
|
||||
|
||||
// hyperguild#188: PutRegular creates or replaces a regular file through the
|
||||
// root. Missing parent directories are created; an existing component that
|
||||
// is not a real directory, a final symlink or special file, and an unclean
|
||||
// path are refused, and nothing is created at a link's target.
|
||||
func TestPutRegularCreatesOrReplacesOnlyThroughRealDirectories(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
outside := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "inwing")))
|
||||
require.NoError(t, os.Symlink(outside, filepath.Join(dir, "wiki", "outwing")))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki", "w"), 0o755))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "v.md"), filepath.Join(dir, "wiki", "w", "link.md")))
|
||||
require.NoError(t, syscall.Mkfifo(filepath.Join(dir, "wiki", "w", "f.md"), 0o644))
|
||||
b, err := Open(dir)
|
||||
require.NoError(t, err)
|
||||
defer func() { _ = b.Close() }()
|
||||
|
||||
for _, rel := range []string{"wiki/inwing/facts/n.md", "wiki/outwing/facts/n.md", "wiki/w/link.md", "wiki/w/f.md", "wiki/w/../../raw/v.md", "/abs.md"} {
|
||||
assert.ErrorIs(t, b.PutRegular(rel, []byte("x")), ErrNotRegular, rel)
|
||||
}
|
||||
ents, _ := os.ReadDir(outside)
|
||||
assert.Empty(t, ents, "nothing created outside the brain")
|
||||
_, err = os.Stat(filepath.Join(dir, "raw", "facts"))
|
||||
assert.True(t, os.IsNotExist(err), "nothing created through the in-brain link")
|
||||
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
|
||||
assert.Equal(t, "untouched", string(got))
|
||||
|
||||
require.NoError(t, b.PutRegular("wiki/new/facts/n.md", []byte("one")), "positive control: create with missing parents")
|
||||
got, _ = os.ReadFile(filepath.Join(dir, "wiki", "new", "facts", "n.md"))
|
||||
assert.Equal(t, "one", string(got))
|
||||
require.NoError(t, b.PutRegular("wiki/new/facts/n.md", []byte("two")), "positive control: replace")
|
||||
got, _ = os.ReadFile(filepath.Join(dir, "wiki", "new", "facts", "n.md"))
|
||||
assert.Equal(t, "two", string(got))
|
||||
}
|
||||
|
||||
func TestAppendRegularCreatesOrAppendsOnlyThroughRealDirectories(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
outside := 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.Symlink(outside, filepath.Join(dir, "outdir")))
|
||||
require.NoError(t, os.Symlink("raw", filepath.Join(dir, "indir")))
|
||||
require.NoError(t, os.Symlink(filepath.Join("raw", "v.md"), filepath.Join(dir, "log.md")))
|
||||
require.NoError(t, syscall.Mkfifo(filepath.Join(dir, "f.md"), 0o644))
|
||||
b, err := Open(dir)
|
||||
require.NoError(t, err)
|
||||
defer func() { _ = b.Close() }()
|
||||
|
||||
for _, rel := range []string{"outdir/l.md", "indir/v.md", "log.md", "f.md", "raw/../log.md"} {
|
||||
assert.ErrorIs(t, b.AppendRegular(rel, []byte("x")), ErrNotRegular, rel)
|
||||
}
|
||||
ents, _ := os.ReadDir(outside)
|
||||
assert.Empty(t, ents)
|
||||
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
|
||||
assert.Equal(t, "untouched", string(got))
|
||||
|
||||
require.NoError(t, b.AppendRegular("logs/a.md", []byte("one\n")), "positive control: create")
|
||||
require.NoError(t, b.AppendRegular("logs/a.md", []byte("two\n")), "positive control: append")
|
||||
got, _ = os.ReadFile(filepath.Join(dir, "logs", "a.md"))
|
||||
assert.Equal(t, "one\ntwo\n", string(got))
|
||||
}
|
||||
|
||||
func TestRealParentRefusesASymlinkedDirectoryOrUncleanPath(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
|
||||
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() }()
|
||||
assert.ErrorIs(t, b.RealParent("wiki/alias/x.md"), ErrNotRegular)
|
||||
assert.ErrorIs(t, b.RealParent("wiki/../raw/x.md"), ErrNotRegular)
|
||||
assert.NoError(t, b.RealParent("wiki/x.md"), "positive control")
|
||||
}
|
||||
|
||||
// cleanRel must refuse an unclean path on its own: here the ".." resolves,
|
||||
// after a symlinked directory, to a real regular file, so only the clean
|
||||
// check stands between the call and that file.
|
||||
func TestAppendRegularRefusesAnUncleanPathThatResolvesToARealFile(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw", "keep"), 0o755))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
|
||||
require.NoError(t, os.Symlink(filepath.Join("raw", "keep"), filepath.Join(dir, "indir")))
|
||||
b, err := Open(dir)
|
||||
require.NoError(t, err)
|
||||
defer func() { _ = b.Close() }()
|
||||
assert.ErrorIs(t, b.AppendRegular("indir/../v.md", []byte("x")), ErrNotRegular)
|
||||
assert.ErrorIs(t, b.PutRegular("indir/../v.md", []byte("x")), ErrNotRegular)
|
||||
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
|
||||
assert.Equal(t, "untouched", string(got))
|
||||
}
|
||||
|
||||
func TestRemoveRefusesAPathBehindASymlinkedDirectoryAndRemovesOnlyTheLink(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("keep"), 0o644))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "alias")))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "raw", "v.md"), filepath.Join(dir, "wiki", "link.md")))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "wiki", "n.md"), []byte("n"), 0o644))
|
||||
b, err := Open(dir)
|
||||
require.NoError(t, err)
|
||||
defer func() { _ = b.Close() }()
|
||||
|
||||
assert.ErrorIs(t, b.Remove("wiki/alias/v.md"), ErrNotRegular)
|
||||
_, err = os.Stat(filepath.Join(dir, "raw", "v.md"))
|
||||
assert.NoError(t, err, "the file behind the symlinked directory is kept")
|
||||
require.NoError(t, b.Remove("wiki/link.md"))
|
||||
_, err = os.Stat(filepath.Join(dir, "raw", "v.md"))
|
||||
assert.NoError(t, err, "removing a final symlink never removes its target")
|
||||
require.NoError(t, b.Remove("wiki/n.md"), "positive control")
|
||||
_, err = os.Stat(filepath.Join(dir, "wiki", "n.md"))
|
||||
assert.True(t, os.IsNotExist(err))
|
||||
}
|
||||
|
||||
// CreateRegular is the only write path for promote and reject: it creates
|
||||
// missing parents through the root, refuses an in-brain symlinked parent and
|
||||
// an unclean path, and never replaces anything already there (fs.ErrExist,
|
||||
// content unchanged), including a dangling link.
|
||||
func TestCreateRegularCreatesOnlyNewFilesThroughRealDirectories(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw", "keep"), 0o755))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "inwing")))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
|
||||
require.NoError(t, os.Symlink(filepath.Join("raw", "keep"), filepath.Join(dir, "indir")))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(dir, "wiki", "exists.md"), []byte("original"), 0o644))
|
||||
require.NoError(t, os.Symlink("nowhere.md", filepath.Join(dir, "wiki", "dangling.md")))
|
||||
b, err := Open(dir)
|
||||
require.NoError(t, err)
|
||||
defer func() { _ = b.Close() }()
|
||||
|
||||
assert.ErrorIs(t, b.CreateRegular("wiki/inwing/facts/n.md", []byte("x")), ErrNotRegular)
|
||||
_, err = os.Stat(filepath.Join(dir, "raw", "facts"))
|
||||
assert.True(t, os.IsNotExist(err), "nothing created through the in-brain link")
|
||||
assert.ErrorIs(t, b.CreateRegular("indir/../v.md", []byte("x")), ErrNotRegular)
|
||||
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
|
||||
assert.Equal(t, "untouched", string(got))
|
||||
|
||||
assert.ErrorIs(t, b.CreateRegular("wiki/exists.md", []byte("x")), fs.ErrExist)
|
||||
got, _ = os.ReadFile(filepath.Join(dir, "wiki", "exists.md"))
|
||||
assert.Equal(t, "original", string(got))
|
||||
assert.ErrorIs(t, b.CreateRegular("wiki/dangling.md", []byte("x")), fs.ErrExist)
|
||||
_, err = os.Stat(filepath.Join(dir, "wiki", "nowhere.md"))
|
||||
assert.True(t, os.IsNotExist(err), "nothing created at the dangling link's target")
|
||||
|
||||
require.NoError(t, b.CreateRegular("wiki/new/facts/n.md", []byte("one")), "positive control: create with missing parents")
|
||||
got, _ = os.ReadFile(filepath.Join(dir, "wiki", "new", "facts", "n.md"))
|
||||
assert.Equal(t, "one", string(got))
|
||||
}
|
||||
|
||||
// On Linux a backslash is an ordinary filename byte, not a separator, so a
|
||||
// name containing one stays a single in-root component (hyperguild#158: the
|
||||
// watcher retried such a note forever while cleanRel refused it).
|
||||
func TestReadAndPutRegularTreatABackslashAsAFilenameByte(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
b, err := Open(dir)
|
||||
require.NoError(t, err)
|
||||
defer func() { _ = b.Close() }()
|
||||
require.NoError(t, b.PutRegular(`a\..\b.md`, []byte("x")))
|
||||
got, err := os.ReadFile(filepath.Join(dir, `a\..\b.md`))
|
||||
require.NoError(t, err, "the name was not kept as one component")
|
||||
assert.Equal(t, "x", string(got))
|
||||
got, err = b.ReadRegular(`a\..\b.md`)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "x", string(got))
|
||||
}
|
||||
|
||||
@@ -1,8 +1,10 @@
|
||||
// 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
|
||||
// FIFO (with a writer held open) into a path while a reader under test loops.
|
||||
// It observes two things: no sentinel byte from the outside file reaches the
|
||||
// reader's output, and the reader returns within a timeout. It does not cover
|
||||
// tests: it keeps swapping a regular note, a symlink to a sentinel target file
|
||||
// (outside the brain, or inside it for hyperguild#171), or a FIFO (with a
|
||||
// writer held open) into a path while a reader under test loops.
|
||||
// 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.
|
||||
package brainfstest
|
||||
|
||||
@@ -18,7 +20,7 @@ import (
|
||||
"time"
|
||||
)
|
||||
|
||||
// Sentinel marks the outside file's contents.
|
||||
// Sentinel marks the target file's contents.
|
||||
const Sentinel = "zqbrainfssentinelonefiftyseven"
|
||||
|
||||
// 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 {
|
||||
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 {
|
||||
t.Fatalf("no symlink was swapped into %s in %d iterations: the race did not run", path, iters)
|
||||
|
||||
@@ -16,9 +16,10 @@
|
||||
package classification
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"io/fs"
|
||||
"strings"
|
||||
|
||||
"gopkg.in/yaml.v3"
|
||||
@@ -110,9 +111,20 @@ type rawConfig struct {
|
||||
func Load(brainDir string) (*Config, error) {
|
||||
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 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 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")
|
||||
}
|
||||
@@ -88,7 +88,6 @@ func TestNoPackageReferencesExtractTextOutsideExtract(t *testing.T) {
|
||||
// osOpenAllowed names the functions in guarded files that may call os.Open*
|
||||
// on a path that is not a raw/ read.
|
||||
var osOpenAllowed = map[string]bool{
|
||||
"internal/watcher/watcher.go:appendWatcherLog": true, // ingest log append, not a raw/ read
|
||||
// Text reads by path; outside this package only TextIn's temp copy reaches
|
||||
// it (TestNoPackageReferencesExtractTextOutsideExtract enforces that).
|
||||
"internal/extract/extract.go:Text": true,
|
||||
|
||||
@@ -21,6 +21,11 @@ func TestReadExcerptRefusesSymlinksAndSurvivesSwapRaces(t *testing.T) {
|
||||
require.NoError(t, os.MkdirAll(facts, 0o755))
|
||||
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)
|
||||
// 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")
|
||||
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 {
|
||||
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() {
|
||||
_ = readExcerpt(brain, "wiki/w/facts/r.md", 500)
|
||||
})
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
package notes
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// hyperguild#188/#173: brain_edit's atomic rename must not be redirected by
|
||||
// a symlinked directory inside the brain.
|
||||
func TestEditRefusesANoteBehindASymlinkedDirectory(t *testing.T) {
|
||||
b := t.TempDir()
|
||||
// Edit refuses a tree that is not the sync source before any path
|
||||
// check, so the test needs a .git to reach the symlink refusal.
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(b, ".git"), 0o755))
|
||||
victim := filepath.Join(b, "raw", "facts", "v.md")
|
||||
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||
require.NoError(t, os.WriteFile(victim, []byte("old text\n"), 0o644))
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "w"), 0o755))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "facts"), filepath.Join(b, "wiki", "w", "alias")))
|
||||
_, err := Edit(b, "wiki/w/alias/v.md", "old text", "new text", ScopeNotes)
|
||||
assert.Error(t, err)
|
||||
got, _ := os.ReadFile(victim)
|
||||
assert.Equal(t, "old text\n", string(got))
|
||||
|
||||
real := filepath.Join(b, "wiki", "w", "facts", "r.md")
|
||||
require.NoError(t, os.MkdirAll(filepath.Dir(real), 0o755))
|
||||
require.NoError(t, os.WriteFile(real, []byte("old text\n"), 0o644))
|
||||
_, err = Edit(b, "wiki/w/facts/r.md", "old text", "new text", ScopeNotes)
|
||||
require.NoError(t, err, "positive control: a note in a real directory is edited")
|
||||
got, _ = os.ReadFile(real)
|
||||
assert.Equal(t, "new text\n", string(got))
|
||||
}
|
||||
@@ -38,3 +38,31 @@ func TestReadScopedRefusesANoteOverMaxNoteBytes(t *testing.T) {
|
||||
_, err := ReadScoped(brain, "wiki/w/facts/big.md", ScopeNotes)
|
||||
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)
|
||||
}
|
||||
|
||||
@@ -3,9 +3,10 @@ package pipeline
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"io/fs"
|
||||
"strings"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
|
||||
@@ -23,10 +24,16 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
|
||||
return 0, fmt.Errorf("load inventory: %w", err)
|
||||
}
|
||||
|
||||
sourcesDir := filepath.Join(brainDir, "wiki", "sources")
|
||||
entries, err := os.ReadDir(sourcesDir)
|
||||
// Listed and read through the brain root, regular files only
|
||||
// (hyperguild#157).
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
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, fmt.Errorf("read sources dir: %w", err)
|
||||
@@ -37,20 +44,20 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
|
||||
// get both refs merged before a single write.
|
||||
pending := make(map[string]wiki.Page)
|
||||
|
||||
for _, e := range entries {
|
||||
for _, name := range names {
|
||||
if ctx.Err() != nil {
|
||||
return 0, ctx.Err()
|
||||
}
|
||||
if e.IsDir() || !strings.HasSuffix(e.Name(), ".md") {
|
||||
if !strings.HasSuffix(name, ".md") {
|
||||
continue
|
||||
}
|
||||
|
||||
b, err := os.ReadFile(filepath.Join(sourcesDir, e.Name()))
|
||||
b, err := bfs.ReadRegular("wiki/sources/" + name)
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
sourceContent := string(b)
|
||||
sourceSlug := strings.TrimSuffix(e.Name(), ".md")
|
||||
sourceSlug := strings.TrimSuffix(name, ".md")
|
||||
sourceTitle := extractTitle(sourceContent)
|
||||
if sourceTitle == "" {
|
||||
sourceTitle = sourceSlug
|
||||
@@ -70,7 +77,7 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
|
||||
// Start from already-accumulated version if we've seen this page.
|
||||
page, seen := pending[relPath]
|
||||
if !seen {
|
||||
raw, err := os.ReadFile(filepath.Join(brainDir, filepath.FromSlash(relPath)))
|
||||
raw, err := bfs.ReadRegular(relPath)
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
@@ -81,8 +88,7 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
|
||||
}
|
||||
|
||||
for relPath, page := range pending {
|
||||
dest := filepath.Join(brainDir, filepath.FromSlash(relPath))
|
||||
if err := os.WriteFile(dest, []byte(page.Content), 0o644); err != nil {
|
||||
if err := bfs.PutRegular(relPath, []byte(page.Content)); err != nil {
|
||||
return 0, fmt.Errorf("write %s: %w", relPath, err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -5,9 +5,10 @@ import (
|
||||
"context"
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"io/fs"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
@@ -125,11 +126,7 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
|
||||
var written []string
|
||||
for _, page := range merged {
|
||||
if !dryRun {
|
||||
dest := filepath.Join(brainDir, filepath.FromSlash(page.Path))
|
||||
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
|
||||
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 {
|
||||
return Result{}, err
|
||||
}
|
||||
@@ -147,7 +144,9 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
|
||||
if err != nil {
|
||||
return Result{}, fmt.Errorf("stamp %s: %w", page.Path, err)
|
||||
}
|
||||
if err := os.WriteFile(dest, []byte(stamped), 0o644); err != nil {
|
||||
// Written through the brain root, never through a symlinked
|
||||
// directory or page (hyperguild#158).
|
||||
if err := writeBrainFile(brainDir, page.Path, []byte(stamped)); err != nil {
|
||||
return Result{}, fmt.Errorf("write %s: %w", page.Path, err)
|
||||
}
|
||||
}
|
||||
@@ -188,14 +187,38 @@ func hashBody(content string) string {
|
||||
|
||||
// readSourcePage returns the full on-disk content of the source page at
|
||||
// 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 {
|
||||
raw, err := os.ReadFile(filepath.Join(brainDir, "wiki", "sources", sourceSlug+".md"))
|
||||
raw, err := readBrainFile(brainDir, "wiki/sources/"+sourceSlug+".md")
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
return string(raw)
|
||||
}
|
||||
|
||||
// writeBrainFile creates or replaces one brain-relative file through the
|
||||
// brain root (hyperguild#158).
|
||||
func writeBrainFile(brainDir, rel string, data []byte) error {
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = bfs.Close() }()
|
||||
return bfs.PutRegular(rel, data)
|
||||
}
|
||||
|
||||
// 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
|
||||
// wrote, or "" when there is no such page or no such field.
|
||||
//
|
||||
@@ -230,10 +253,10 @@ func storedSourceHash(brainDir, sourceSlug string) string {
|
||||
// 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
|
||||
// field today.
|
||||
func reviseOrCreate(dest string, page wiki.Page) (string, []string, error) {
|
||||
existing, err := os.ReadFile(dest)
|
||||
func reviseOrCreate(brainDir string, page wiki.Page) (string, []string, error) {
|
||||
existing, err := readBrainFile(brainDir, page.Path)
|
||||
switch {
|
||||
case os.IsNotExist(err):
|
||||
case errors.Is(err, fs.ErrNotExist):
|
||||
return page.Content, nil, nil
|
||||
case err != nil:
|
||||
return "", nil, fmt.Errorf("read existing %s: %w", page.Path, err)
|
||||
@@ -267,7 +290,7 @@ See brain/schema.md for the full schema.
|
||||
`
|
||||
|
||||
func loadSchema(brainDir string) string {
|
||||
b, err := os.ReadFile(filepath.Join(brainDir, "schema.md"))
|
||||
b, err := readBrainFile(brainDir, "schema.md")
|
||||
if err != nil {
|
||||
return defaultSchema
|
||||
}
|
||||
|
||||
@@ -2,7 +2,6 @@
|
||||
package pipeline
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"strings"
|
||||
@@ -53,8 +52,7 @@ func injectSourceRefs(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entr
|
||||
if !ok {
|
||||
continue
|
||||
}
|
||||
diskPath := filepath.Join(brainDir, "wiki", string(pt), slug+".md")
|
||||
b, err := os.ReadFile(diskPath)
|
||||
b, err := readBrainFile(brainDir, "wiki/"+string(pt)+"/"+slug+".md")
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
|
||||
@@ -0,0 +1,217 @@
|
||||
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)
|
||||
}
|
||||
|
||||
// hyperguild#158: BackfillRefs read a regular concept page, a symlink could
|
||||
// be swapped in, and os.WriteFile then followed it and overwrote the link's
|
||||
// target. The target is not restored between rounds here, so any
|
||||
// write-through shows.
|
||||
func TestBackfillRefsNeverWritesThroughAPageSwappedForASymlink(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")
|
||||
require.NoError(t, os.WriteFile(target, []byte("untouched"), 0o644))
|
||||
inside := "---\ntitle: C\n---\nbody\n"
|
||||
require.NoError(t, os.WriteFile(page, []byte(inside), 0o644))
|
||||
brainfstest.StartSwap(t, page, inside, target, false)
|
||||
ok := 0
|
||||
for deadline := time.Now().Add(2 * time.Second); time.Now().Before(deadline); {
|
||||
if _, err := BackfillRefs(context.Background(), brain); err == nil {
|
||||
ok++
|
||||
}
|
||||
}
|
||||
got, _ := os.ReadFile(target)
|
||||
assert.Equal(t, "untouched", string(got), "BackfillRefs wrote through a swapped-in symlink")
|
||||
assert.Positive(t, ok, "positive control: some backfills ran")
|
||||
}
|
||||
|
||||
// hyperguild#158: buildAndWrite wrote each page with os.WriteFile by path, so
|
||||
// a page read as regular and swapped for a symlink before the write was
|
||||
// written through. The target is not restored between rounds, so any
|
||||
// write-through shows.
|
||||
func TestBuildAndWriteNeverWritesThroughAPageSwappedForASymlink(t *testing.T) {
|
||||
brain := t.TempDir()
|
||||
mkdirs(t, brain, "wiki/sources", "wiki/concepts", "wiki/entities", "raw")
|
||||
page := filepath.Join(brain, "wiki", "concepts", "zq-concept.md")
|
||||
target := filepath.Join(brain, "raw", "secret.md")
|
||||
require.NoError(t, os.WriteFile(target, []byte("untouched"), 0o644))
|
||||
inside := "---\ntitle: Zq Concept\n---\nbody\n"
|
||||
require.NoError(t, os.WriteFile(page, []byte(inside), 0o644))
|
||||
pages := []RawPage{{Title: "Zq Concept", Type: "concept", Content: "## About\n\nmore\n"}}
|
||||
brainfstest.StartSwap(t, page, inside, target, false)
|
||||
ok := 0
|
||||
for deadline := time.Now().Add(2 * time.Second); time.Now().Before(deadline); {
|
||||
if _, err := RunRaw(context.Background(), brain, "zq source", pages, false); err == nil {
|
||||
ok++
|
||||
}
|
||||
}
|
||||
got, _ := os.ReadFile(target)
|
||||
assert.Equal(t, "untouched", string(got), "buildAndWrite wrote through a swapped-in symlink")
|
||||
assert.Positive(t, ok, "positive control: some runs returned without error")
|
||||
}
|
||||
@@ -28,7 +28,6 @@ import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
@@ -102,25 +101,6 @@ func Apply(content string, s Stamp) (string, error) {
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// ApplyFile applies the stamp to the note at absPath in place.
|
||||
func ApplyFile(absPath string, s Stamp) error {
|
||||
b, err := os.ReadFile(absPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("read for provenance: %w", err)
|
||||
}
|
||||
out, err := Apply(string(b), s)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if out == string(b) {
|
||||
return nil
|
||||
}
|
||||
if err := os.WriteFile(absPath, []byte(out), 0o644); err != nil {
|
||||
return fmt.Errorf("write provenance: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// plainGroups keeps the provably plain key groups of a frontmatter block.
|
||||
func plainGroups(block string) string {
|
||||
lines := strings.Split(strings.TrimSuffix(block, "\n"), "\n")
|
||||
|
||||
@@ -12,6 +12,8 @@ import (
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"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
|
||||
@@ -189,3 +191,49 @@ func TestHydrateRefusesASymlink(t *testing.T) {
|
||||
assert.Error(t, err)
|
||||
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"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"syscall"
|
||||
"time"
|
||||
)
|
||||
|
||||
@@ -42,16 +44,63 @@ type Attempt struct {
|
||||
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.
|
||||
// The open does not follow a final symlink.
|
||||
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)
|
||||
}
|
||||
path := filepath.Join(sessionsDir, sessionID+".jsonl")
|
||||
f, err := os.OpenFile(path, os.O_CREATE|os.O_APPEND|os.O_WRONLY, 0o644)
|
||||
// The sessions dir itself must be a real directory, not a symlink that
|
||||
// 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 {
|
||||
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)
|
||||
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.
|
||||
func Read(sessionsDir, sessionID string) ([]Entry, error) {
|
||||
if err := checkID(sessionID); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
path := filepath.Join(sessionsDir, sessionID+".jsonl")
|
||||
f, err := os.Open(path)
|
||||
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 {
|
||||
Symlinks []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.
|
||||
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
|
||||
// a name containing a newline cannot blur two findings together.
|
||||
@@ -59,6 +65,9 @@ func (r Result) String() string {
|
||||
if len(r.Symlinks) > 0 {
|
||||
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 {
|
||||
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 {
|
||||
return filepath.SkipDir
|
||||
}
|
||||
if d.Type()&os.ModeSymlink != 0 {
|
||||
switch {
|
||||
case d.Type()&os.ModeSymlink != 0:
|
||||
r.Symlinks = append(r.Symlinks, rel)
|
||||
case !d.IsDir() && !d.Type().IsRegular():
|
||||
r.Special = append(r.Special, rel)
|
||||
}
|
||||
return nil
|
||||
})
|
||||
sort.Strings(r.Symlinks)
|
||||
sort.Strings(r.Special)
|
||||
sort.Strings(r.Unreadable)
|
||||
if walkErr != nil {
|
||||
// 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",
|
||||
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 {
|
||||
reported = key
|
||||
if key != "" {
|
||||
slog.Error("brain symlink tripwire", "finding", key)
|
||||
q.push("brain symlink tripwire (hyperguild#157): " + key +
|
||||
". Readers may follow symlinks out of the brain; fix them.")
|
||||
q.push("brain symlink tripwire (hyperguild#157, #179): " + key +
|
||||
". 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()
|
||||
}
|
||||
|
||||
// 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
|
||||
// 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.
|
||||
|
||||
@@ -42,6 +42,11 @@ func TestSyncRefusesSymlinkedNotesAndSurvivesSwapRaces(t *testing.T) {
|
||||
brain := t.TempDir()
|
||||
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")))
|
||||
// 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{}
|
||||
store := &stubStore{}
|
||||
@@ -51,6 +56,7 @@ func TestSyncRefusesSymlinkedNotesAndSurvivesSwapRaces(t *testing.T) {
|
||||
assert.NotContains(t, emb.all(), brainfstest.Sentinel)
|
||||
for p := range store.upserts {
|
||||
assert.NotContains(t, p, "leak.md")
|
||||
assert.NotContains(t, p, "inlink.md")
|
||||
}
|
||||
|
||||
p := filepath.Join(brain, "knowledge", "r.md")
|
||||
@@ -61,6 +67,7 @@ func TestSyncRefusesSymlinkedNotesAndSurvivesSwapRaces(t *testing.T) {
|
||||
return e.all()
|
||||
}
|
||||
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() })
|
||||
}
|
||||
|
||||
|
||||
@@ -3,15 +3,18 @@ package watcher
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
"unicode"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/extract"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
|
||||
)
|
||||
@@ -109,14 +112,28 @@ func processDir(ctx context.Context, cfg Config, date string) []error {
|
||||
}
|
||||
|
||||
// Skip files that have already been processed or permanently failed.
|
||||
if _, err := os.Stat(path + ".processed"); err == nil {
|
||||
// Any entry at the marker path counts (Lstat, not Stat): a dangling
|
||||
// marker symlink made os.Stat report nothing and the note was
|
||||
// reprocessed every interval (hyperguild#158).
|
||||
if _, err := os.Lstat(path + ".processed"); err == nil {
|
||||
return nil
|
||||
}
|
||||
if _, err := os.Stat(path + ".failed"); err == nil {
|
||||
if _, err := os.Lstat(path + ".failed"); err == nil {
|
||||
return nil
|
||||
}
|
||||
// A note whose archive copy or marker was refused is not retried
|
||||
// until it changes: a refusal has no marker to stop the next round,
|
||||
// and each round can cost an LLM call (hyperguild#158).
|
||||
info, ierr := d.Info()
|
||||
if ierr == nil && refusedUnchanged(path, info) {
|
||||
return nil
|
||||
}
|
||||
|
||||
if err := processFile(ctx, cfg, root, rawDir, path, date); err != nil {
|
||||
if ierr == nil && errors.Is(err, brainfs.ErrNotRegular) {
|
||||
rememberRefused(path, info)
|
||||
slog.Error("watcher: note refused; not retried until it changes", "file", filepath.Base(path), "error", err)
|
||||
}
|
||||
errs = append(errs, fmt.Errorf("process %s: %w", filepath.Base(path), err))
|
||||
}
|
||||
return nil
|
||||
@@ -145,16 +162,15 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d
|
||||
|
||||
_, runErr := pipeline.Run(ctx, cfg.Pipeline, cfg.BrainDir, content, source, false)
|
||||
if runErr != nil {
|
||||
// Copy to failed/ and leave a .failed marker so we don't retry.
|
||||
failedDir := filepath.Join(cfg.BrainDir, "raw", "failed")
|
||||
if mkErr := os.MkdirAll(failedDir, 0o755); mkErr != nil {
|
||||
return fmt.Errorf("mkdir failed dir: %w", mkErr)
|
||||
}
|
||||
dest := filepath.Join(failedDir, filename)
|
||||
if cpErr := copyFromRoot(root, rel, dest); cpErr != nil {
|
||||
// Copy to failed/ and leave a .failed marker so we don't retry. Both
|
||||
// written through the brain root (hyperguild#158).
|
||||
if cpErr := copyFromRoot(root, rel, cfg.BrainDir, "raw/failed/"+filename); cpErr != nil {
|
||||
return fmt.Errorf("copy to failed: %w", cpErr)
|
||||
}
|
||||
if mkErr := os.WriteFile(path+".failed", []byte(runErr.Error()), 0o644); mkErr != nil {
|
||||
if mkErr := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".failed", []byte(runErr.Error())); mkErr != nil {
|
||||
if errors.Is(mkErr, brainfs.ErrNotRegular) {
|
||||
return fmt.Errorf("write .failed marker: %w", mkErr)
|
||||
}
|
||||
slog.Error("watcher: failed to write .failed marker", "error", mkErr)
|
||||
}
|
||||
|
||||
@@ -168,21 +184,21 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d
|
||||
}
|
||||
|
||||
// Copy to processed/YYYY-MM-DD/ and leave a .processed marker so we don't re-ingest.
|
||||
processedDir := filepath.Join(cfg.BrainDir, "raw", "processed", date)
|
||||
if err := os.MkdirAll(processedDir, 0o755); err != nil {
|
||||
return fmt.Errorf("mkdir processed dir: %w", err)
|
||||
}
|
||||
dest := filepath.Join(processedDir, filename)
|
||||
if _, err := os.Stat(dest); err == nil {
|
||||
// Written through the brain root (hyperguild#158).
|
||||
dest := "raw/processed/" + date + "/" + filename
|
||||
if _, err := os.Lstat(filepath.Join(cfg.BrainDir, filepath.FromSlash(dest))); err == nil {
|
||||
// Archive copy already exists; append timestamp to avoid overwriting.
|
||||
ext := filepath.Ext(filename)
|
||||
base := strings.TrimSuffix(filename, ext)
|
||||
dest = filepath.Join(processedDir, base+"-"+time.Now().UTC().Format("150405")+ext)
|
||||
dest = "raw/processed/" + date + "/" + base + "-" + time.Now().UTC().Format("150405") + ext
|
||||
}
|
||||
if err := copyFromRoot(root, rel, dest); err != nil {
|
||||
if err := copyFromRoot(root, rel, cfg.BrainDir, dest); err != nil {
|
||||
return fmt.Errorf("copy to processed: %w", err)
|
||||
}
|
||||
if err := os.WriteFile(path+".processed", []byte(date), 0o644); err != nil {
|
||||
if err := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".processed", []byte(date)); err != nil {
|
||||
if errors.Is(err, brainfs.ErrNotRegular) {
|
||||
return fmt.Errorf("write .processed marker: %w", err)
|
||||
}
|
||||
slog.Error("watcher: failed to write .processed marker", "error", err)
|
||||
}
|
||||
|
||||
@@ -190,6 +206,32 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d
|
||||
return nil
|
||||
}
|
||||
|
||||
// refused remembers notes whose archive copy or marker write was refused,
|
||||
// by path, with the size and mtime they had, for the life of the process.
|
||||
var refused sync.Map
|
||||
|
||||
type refusedStamp struct {
|
||||
size int64
|
||||
mtime time.Time
|
||||
}
|
||||
|
||||
func rememberRefused(path string, info os.FileInfo) {
|
||||
refused.Store(path, refusedStamp{size: info.Size(), mtime: info.ModTime()})
|
||||
}
|
||||
|
||||
func refusedUnchanged(path string, info os.FileInfo) bool {
|
||||
v, ok := refused.Load(path)
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
st := v.(refusedStamp)
|
||||
if st.size == info.Size() && st.mtime.Equal(info.ModTime()) {
|
||||
return true
|
||||
}
|
||||
refused.Delete(path)
|
||||
return false
|
||||
}
|
||||
|
||||
// deriveSource turns a filename into a human-readable source name.
|
||||
// "shape-up-book.md" → "Shape Up Book"
|
||||
func deriveSource(filename string) string {
|
||||
@@ -214,23 +256,22 @@ func appendWatcherLog(brainDir, filename string, runErr error, date string) erro
|
||||
entry := fmt.Sprintf("## %s — watcher error\n\n- **File:** %s\n- **Error:** %s\n\n",
|
||||
date, filename, runErr.Error())
|
||||
|
||||
logPath := filepath.Join(brainDir, "log.md")
|
||||
f, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open log: %w", err)
|
||||
}
|
||||
|
||||
if _, err = f.WriteString(entry); err != nil {
|
||||
f.Close() //nolint:errcheck
|
||||
if err := brainfs.AppendFile(brainDir, "log.md", []byte(entry)); err != nil {
|
||||
return fmt.Errorf("write log: %w", err)
|
||||
}
|
||||
return f.Close()
|
||||
return nil
|
||||
}
|
||||
|
||||
// putBrainFile creates or replaces a brain-relative file through the brain
|
||||
// root, never through a symlinked directory or file (hyperguild#158).
|
||||
func putBrainFile(brainDir, rel string, data []byte) error {
|
||||
return brainfs.PutFile(brainDir, rel, data)
|
||||
}
|
||||
|
||||
// copyFromRoot archives a raw/ file read through the root, refusing anything
|
||||
// that is not a regular file, so a swapped-in symlink cannot copy an outside
|
||||
// file into raw/processed/ or raw/failed/ (hyperguild#153).
|
||||
func copyFromRoot(root *os.Root, rel, dst string) error {
|
||||
func copyFromRoot(root *os.Root, rel, brainDir, dstRel string) error {
|
||||
fi, err := root.Lstat(rel)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -243,13 +284,9 @@ func copyFromRoot(root *os.Root, rel, dst string) error {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = in.Close() }()
|
||||
out, err := os.Create(dst)
|
||||
data, err := io.ReadAll(in)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := io.Copy(out, in); err != nil {
|
||||
_ = out.Close()
|
||||
return err
|
||||
}
|
||||
return out.Close()
|
||||
return putBrainFile(brainDir, dstRel, data)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,186 @@
|
||||
package watcher
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
|
||||
)
|
||||
|
||||
func okPipeline() pipeline.Config {
|
||||
return pipeline.Config{Complete: func(context.Context, string, string) (string, error) {
|
||||
b, _ := json.Marshal([]pipeline.RawPage{{Title: "X", Type: "source", Subtype: "article", Content: "## S\n\nx\n"}})
|
||||
return string(b), nil
|
||||
}, Schema: "# Schema"}
|
||||
}
|
||||
|
||||
func failingPipeline() pipeline.Config {
|
||||
return pipeline.Config{Complete: func(context.Context, string, string) (string, error) {
|
||||
return "", errors.New("model down")
|
||||
}, Schema: "# Schema"}
|
||||
}
|
||||
|
||||
// hyperguild#158: the watcher wrote the archive copy under raw/processed or
|
||||
// raw/failed, and its log.md entry, by path, so a symlinked archive
|
||||
// directory or log redirected the write elsewhere in the brain or outside
|
||||
// it. (A pre-planted marker symlink makes the watcher skip the note, so the
|
||||
// marker write itself is reachable only by a race.)
|
||||
func TestProcessDirDoesNotWriteThroughASymlinkedArchiveDir(t *testing.T) {
|
||||
for name, pcfg := range map[string]pipeline.Config{"processed": okPipeline(), "failed": failingPipeline()} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
outside := t.TempDir()
|
||||
victim := filepath.Join(brainDir, "wiki", "concepts", "v.md")
|
||||
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644))
|
||||
require.NoError(t, os.Symlink(outside, filepath.Join(brainDir, "raw", name)))
|
||||
_ = processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pcfg}, "2026-10-05")
|
||||
got, _ := os.ReadFile(victim)
|
||||
assert.Equal(t, "untouched", string(got))
|
||||
ents, _ := os.ReadDir(outside)
|
||||
assert.Empty(t, ents, "the archive copy was written outside the brain")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestProcessDirWritesMarkersAndArchiveInRealDirectories(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644))
|
||||
errs := processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: okPipeline()}, "2026-10-05")
|
||||
assert.Empty(t, errs)
|
||||
_, err := os.Stat(filepath.Join(brainDir, "raw", "n.md.processed"))
|
||||
assert.NoError(t, err, "positive control: marker written")
|
||||
_, err = os.Stat(filepath.Join(brainDir, "raw", "processed", "2026-10-05", "n.md"))
|
||||
assert.NoError(t, err, "positive control: archive copy written")
|
||||
}
|
||||
|
||||
// The log.md entry for a failed note is appended through the brain root: with
|
||||
// a real raw/failed (so the archive copy succeeds and the log is reached), a
|
||||
// symlinked log.md is not written through.
|
||||
func TestProcessDirDoesNotAppendTheLogThroughASymlink(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
victim := filepath.Join(brainDir, "wiki", "concepts", "v.md")
|
||||
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644))
|
||||
require.NoError(t, os.Symlink(filepath.Join("wiki", "concepts", "v.md"), filepath.Join(brainDir, "log.md")))
|
||||
_ = processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: failingPipeline()}, "2026-10-05")
|
||||
_, err := os.Stat(filepath.Join(brainDir, "raw", "failed", "n.md"))
|
||||
require.NoError(t, err, "positive control: the archive copy was written, so the log append was reached")
|
||||
got, _ := os.ReadFile(victim)
|
||||
assert.Equal(t, "untouched", string(got), "the log was appended through a symlink")
|
||||
}
|
||||
|
||||
// A marker path holding anything (here a dangling symlink) counts as a
|
||||
// marker: the note is skipped and nothing is created at the link's target.
|
||||
// (os.Stat followed the link, saw nothing, and processed the note again.)
|
||||
func TestProcessDirTreatsAnyEntryAtTheMarkerPathAsAMarker(t *testing.T) {
|
||||
for _, kind := range []string{"processed", "failed"} {
|
||||
t.Run(kind, func(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
outside := filepath.Join(t.TempDir(), "created")
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644))
|
||||
require.NoError(t, os.Symlink(outside, filepath.Join(brainDir, "raw", "n.md."+kind)))
|
||||
calls := 0
|
||||
cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{
|
||||
Complete: func(context.Context, string, string) (string, error) { calls++; return "[]", nil }, Schema: "# Schema"}}
|
||||
_ = processDir(context.Background(), cfg, "2026-10-05")
|
||||
assert.Zero(t, calls, "the note was processed despite an entry at its marker path")
|
||||
_, err := os.Lstat(outside)
|
||||
assert.True(t, os.IsNotExist(err), "a file was created at the marker link's target")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// The marker write itself is reachable while pipeline.Run is in flight
|
||||
// (in production, an LLM call): a link planted at the marker path then is
|
||||
// refused, and the note is remembered, so removing the link (as
|
||||
// symlinkguard does) does not make the watcher call the model again.
|
||||
func TestProcessDirRefusesAMarkerLinkPlantedDuringTheRunAndDoesNotRetry(t *testing.T) {
|
||||
for _, kind := range []string{"processed", "failed"} {
|
||||
for _, target := range []string{"outside", "in-brain"} {
|
||||
t.Run(kind+"/"+target, func(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
raw := filepath.Join(brainDir, "raw")
|
||||
marker := filepath.Join(raw, "n.md."+kind)
|
||||
require.NoError(t, os.WriteFile(filepath.Join(raw, "n.md"), []byte("note"), 0o644))
|
||||
// The in-brain target is relative, so os.Root itself would
|
||||
// follow it; only the regular-file check refuses it.
|
||||
victim := filepath.Join(raw, "victim")
|
||||
link := filepath.Join(t.TempDir(), "created")
|
||||
if target == "in-brain" {
|
||||
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
|
||||
link = "victim"
|
||||
}
|
||||
ok := okPipeline().Complete
|
||||
calls := 0
|
||||
cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{Schema: "# Schema",
|
||||
Complete: func(ctx context.Context, sys, user string) (string, error) {
|
||||
calls++
|
||||
require.NoError(t, os.Symlink(link, marker))
|
||||
if kind == "failed" {
|
||||
return "", errors.New("model down")
|
||||
}
|
||||
return ok(ctx, sys, user)
|
||||
}}}
|
||||
for i := 0; i < 3; i++ {
|
||||
errs := processDir(context.Background(), cfg, "2026-10-05")
|
||||
if i == 0 {
|
||||
require.NotEmpty(t, errs, "the planted link was not refused")
|
||||
}
|
||||
_ = os.Remove(marker)
|
||||
}
|
||||
assert.Equal(t, 1, calls, "the note was retried after its marker write was refused")
|
||||
if target == "in-brain" {
|
||||
got, err := os.ReadFile(victim)
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "untouched", string(got), "the marker was written through the link")
|
||||
} else {
|
||||
_, err := os.Lstat(link)
|
||||
assert.True(t, os.IsNotExist(err), "the marker was written through the link")
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A refused archive copy must not retry every interval: the note is
|
||||
// remembered and skipped until it changes (a symlinked raw/failed cost one
|
||||
// LLM call per round before).
|
||||
func TestProcessDirDoesNotRetryANoteWhoseArchiveCopyIsRefused(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644))
|
||||
require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brainDir, "raw", "failed")))
|
||||
calls := 0
|
||||
cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{
|
||||
Complete: func(context.Context, string, string) (string, error) { calls++; return "", errors.New("model down") }, Schema: "# Schema"}}
|
||||
for i := 0; i < 3; i++ {
|
||||
_ = processDir(context.Background(), cfg, "2026-10-05")
|
||||
}
|
||||
assert.Equal(t, 1, calls, "the refused note was retried every round")
|
||||
|
||||
// Once the note changes it is tried again.
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note, edited"), 0o644))
|
||||
future := time.Now().Add(2 * time.Second)
|
||||
require.NoError(t, os.Chtimes(filepath.Join(brainDir, "raw", "n.md"), future, future))
|
||||
_ = processDir(context.Background(), cfg, "2026-10-05")
|
||||
assert.Equal(t, 2, calls, "positive control: a changed note is tried again")
|
||||
}
|
||||
|
||||
// A note whose name has a backslash is legal on Linux and must be processed
|
||||
// (cleanRel refused it, so it was never archived or marked).
|
||||
func TestProcessDirProcessesANoteWithABackslashInItsName(t *testing.T) {
|
||||
brainDir := setupBrainDir(t)
|
||||
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "a\\b.md"), []byte("note"), 0o644))
|
||||
errs := processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: okPipeline()}, "2026-10-05")
|
||||
assert.Empty(t, errs)
|
||||
_, err := os.Stat(filepath.Join(brainDir, "raw", "a\\b.md.processed"))
|
||||
assert.NoError(t, err)
|
||||
}
|
||||
@@ -3,8 +3,6 @@ package wiki
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
@@ -50,8 +48,8 @@ func RebuildIndex(brainDir, date string) error {
|
||||
sb.WriteString("\n")
|
||||
}
|
||||
|
||||
dest := filepath.Join(brainDir, "wiki", "index.md")
|
||||
return os.WriteFile(dest, []byte(sb.String()), 0o644)
|
||||
// Written through the brain root, never through a symlink (#158).
|
||||
return bfs.PutRegular("wiki/index.md", []byte(sb.String()))
|
||||
}
|
||||
|
||||
// pageFirstSentence reads the page through the brain root, regular files
|
||||
|
||||
@@ -3,8 +3,7 @@ package wiki
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
"strings"
|
||||
)
|
||||
|
||||
@@ -27,14 +26,14 @@ func AppendLog(brainDir, source string, pages, warnings []string, date string) e
|
||||
}
|
||||
sb.WriteString("\n")
|
||||
|
||||
logPath := filepath.Join(brainDir, "log.md")
|
||||
f, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
|
||||
// Appended through the brain root, never through a symlink (#158).
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return fmt.Errorf("open log: %w", err)
|
||||
return fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
if _, err = f.WriteString(sb.String()); err != nil {
|
||||
f.Close() //nolint:errcheck
|
||||
defer func() { _ = bfs.Close() }()
|
||||
if err := bfs.AppendRegular("log.md", []byte(sb.String())); err != nil {
|
||||
return fmt.Errorf("write log: %w", err)
|
||||
}
|
||||
return f.Close()
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
package wiki
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// hyperguild#158: RebuildIndex wrote wiki/index.md and AppendLog appended
|
||||
// log.md with os.WriteFile / os.OpenFile, so a symlinked file was written
|
||||
// through.
|
||||
func TestRebuildIndexAndAppendLogDoNotWriteThroughSymlinks(t *testing.T) {
|
||||
b := t.TempDir()
|
||||
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "concepts"), 0o755))
|
||||
victim := filepath.Join(b, "raw", "v.md")
|
||||
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
|
||||
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
|
||||
require.NoError(t, os.Symlink(filepath.Join("..", "raw", "v.md"), filepath.Join(b, "wiki", "index.md")))
|
||||
require.NoError(t, os.Symlink(filepath.Join("raw", "v.md"), filepath.Join(b, "log.md")))
|
||||
|
||||
assert.Error(t, RebuildIndex(b, "2026-10-05"))
|
||||
assert.Error(t, AppendLog(b, "src", []string{"p"}, nil, "2026-10-05"))
|
||||
got, _ := os.ReadFile(victim)
|
||||
assert.Equal(t, "untouched", string(got))
|
||||
|
||||
require.NoError(t, os.Remove(filepath.Join(b, "wiki", "index.md")))
|
||||
require.NoError(t, os.Remove(filepath.Join(b, "log.md")))
|
||||
require.NoError(t, RebuildIndex(b, "2026-10-05"), "positive control")
|
||||
require.NoError(t, AppendLog(b, "src", []string{"p"}, nil, "2026-10-05"), "positive control")
|
||||
l, _ := os.ReadFile(filepath.Join(b, "log.md"))
|
||||
assert.Contains(t, string(l), "src")
|
||||
}
|
||||
Reference in New Issue
Block a user