ingestion/internal/brain/index.go

@@ -2,12 +2,18 @@ package brain
 
 import (
 	"bufio"
+	"bytes"
+	"errors"
 	"fmt"
+	"io"
+	"io/fs"
 	"os"
 	"path/filepath"
 	"sort"
 	"strings"
 	"time"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
 )
 
 // noteEntry is one row in a Wing _index.md.
@@ -27,13 +33,18 @@ func BuildWingIndex(brainDir, wing string) error {
 		return fmt.Errorf("invalid wing %q", wing)
 	}
 	wingDir := filepath.Join(brainDir, "wiki", w)
-	if _, err := os.Stat(wingDir); os.IsNotExist(err) {
+	// 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)
+	if err != nil {
+		return fmt.Errorf("open brain: %w", err)
+	}
+	defer func() { _ = bfs.Close() }()
+	if _, err := bfs.Lstat("wiki/" + w); errors.Is(err, fs.ErrNotExist) {
 		return nil
-	} else if err != nil {
-		return fmt.Errorf("stat wing: %w", err)
 	}
 
-	entries, err := collectWingEntries(wingDir)
+	entries, err := collectWingEntries(bfs, "wiki/"+w)
 	if err != nil {
 		return err
 	}
@@ -58,51 +69,47 @@ func BuildWingIndex(brainDir, wing string) error {
 
 // BuildAllWingIndexes regenerates _index.md for every wing under brain/wiki/.
 func BuildAllWingIndexes(brainDir string) error {
-	wikiDir := filepath.Join(brainDir, "wiki")
+	bfs, err := brainfs.Open(brainDir)
-	ents, err := os.ReadDir(wikiDir)
+	if err != nil {
-	if os.IsNotExist(err) {
+		return fmt.Errorf("open brain: %w", err)
+	}
+	wings, err := bfs.ReadDirDirs("wiki")
+	_ = bfs.Close()
+	if errors.Is(err, fs.ErrNotExist) {
 		return nil
 	}
 	if err != nil {
 		return fmt.Errorf("read wiki: %w", err)
 	}
-	for _, e := range ents {
+	for _, w := range wings {
-		if !e.IsDir() {
+		if err := BuildWingIndex(brainDir, w); err != nil {
-			continue
+			return fmt.Errorf("index %s: %w", w, err)
-		}
-		if err := BuildWingIndex(brainDir, e.Name()); err != nil {
-			return fmt.Errorf("index %s: %w", e.Name(), err)
 		}
 	}
 	return nil
 }
 
-func collectWingEntries(wingDir string) ([]noteEntry, error) {
+func collectWingEntries(bfs *brainfs.Brain, wingRel string) ([]noteEntry, error) {
 	var out []noteEntry
-	ents, err := os.ReadDir(wingDir)
+	halls, err := bfs.ReadDirDirs(wingRel)
 	if err != nil {
 		return nil, fmt.Errorf("read wing: %w", err)
 	}
-	for _, hallEnt := range ents {
+	for _, hall := range halls {
-		if !hallEnt.IsDir() {
-			continue
-		}
-		hall := hallEnt.Name()
 		if !IsValidHall(hall) {
 			continue
 		}
-		hallDir := filepath.Join(wingDir, hall)
+		hallRel := wingRel + "/" + hall
-		notes, err := os.ReadDir(hallDir)
+		names, err := bfs.ReadDirRegular(hallRel)
 		if err != nil {
 			return nil, fmt.Errorf("read hall %s: %w", hall, err)
 		}
-		for _, n := range notes {
+		for _, name := range names {
-			if n.IsDir() || !strings.HasSuffix(n.Name(), ".md") || n.Name() == "_index.md" {
+			if !strings.HasSuffix(name, ".md") || name == "_index.md" {
 				continue
 			}
-			slug := strings.TrimSuffix(n.Name(), ".md")
+			slug := strings.TrimSuffix(name, ".md")
-			full := filepath.Join(hallDir, n.Name())
+			title, created := readTitleAndCreatedIn(bfs, hallRel+"/"+name, slug)
-			title, created := readTitleAndCreated(full, slug)
 			out = append(out, noteEntry{Hall: hall, Slug: slug, Title: title, Created: created})
 		}
 	}
@@ -117,9 +124,40 @@ func readTitleAndCreated(path, slug string) (string, string) {
 		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
+}
 
-	title, created := "", ""
+// readTitleAndCreatedIn is readTitleAndCreated through the brain root,
-	scanner := bufio.NewScanner(f)
+// regular files only (hyperguild#157).
+func readTitleAndCreatedIn(bfs *brainfs.Brain, rel, slug string) (string, string) {
+	content, err := bfs.ReadRegular(rel)
+	if err != nil {
+		return slug, ""
+	}
+	title, created := parseTitleAndCreated(bytes.NewReader(content))
+	if created == "" {
+		if info, err := bfs.Lstat(rel); err == nil {
+			created = info.ModTime().UTC().Format("2006-01-02")
+		}
+	}
+	return titleOrSlug(title, slug), created
+}
+
+func titleOrSlug(title, slug string) string {
+	if title == "" {
+		return strings.ReplaceAll(slug, "-", " ")
+	}
+	return title
+}
+
+func parseTitleAndCreated(r io.Reader) (title, created string) {
+	scanner := bufio.NewScanner(r)
 	inFrontmatter := false
 	for scanner.Scan() {
 		line := scanner.Text()
@@ -149,13 +187,5 @@ func readTitleAndCreated(path, slug string) (string, string) {
 			}
 		}
 	}
-	if title == "" {
-		title = strings.ReplaceAll(slug, "-", " ")
-	}
-	if created == "" {
-		if info, err := os.Stat(path); err == nil {
-			created = info.ModTime().UTC().Format("2006-01-02")
-		}
-	}
 	return title, created
 }

ingestion/internal/brain/index_root_test.go

@@ -0,0 +1,132 @@
+package brain_test
+
+import (
+	"os"
+	"path/filepath"
+	"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"
+)
+
+func readIndex(t *testing.T, brainDir, wing string) string {
+	t.Helper()
+	b, _ := os.ReadFile(filepath.Join(brainDir, "wiki", wing, "_index.md"))
+	return string(b)
+}
+
+// hyperguild#157 slice 5: BuildWingIndex listed wiki/<wing>/<hall>/ with
+// os.ReadDir and opened each note by path, so a symlinked note put the
+// target's title into _index.md, and a FIFO hung the index build.
+func TestBuildWingIndexRefusesSymlinkedNotesAndSurvivesSwapRaces(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\n---\n"), 0o644))
+	require.NoError(t, os.Symlink(brainfstest.Outside(t), filepath.Join(facts, "leak.md")))
+	inBrain := brainfstest.WriteSentinelAt(t, filepath.Join(b, "raw", "s.md"))
+	require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "inlink.md")))
+
+	require.NoError(t, brain.BuildWingIndex(b, "w"))
+	idx := readIndex(t, b, "w")
+	assert.Contains(t, idx, "zqinside", "positive control")
+	assert.NotContains(t, idx, brainfstest.Sentinel)
+	assert.NotContains(t, idx, "leak")
+	assert.NotContains(t, idx, "inlink")
+
+	p := filepath.Join(facts, "r.md")
+	read := func() string {
+		_ = brain.BuildWingIndex(b, "w")
+		return readIndex(t, b, "w")
+	}
+	brainfstest.AssertNoLeak(t, p, "---\ntitle: zqinside\n---\n", 1500*time.Millisecond, read)
+	brainfstest.AssertNoLeakFrom(t, p, "---\ntitle: zqinside\n---\n", inBrain, 1500*time.Millisecond, read)
+	brainfstest.AssertNoHang(t, p, "---\ntitle: zqinside\n---\n", 1500*time.Millisecond, 6*time.Second, func() { _ = read() })
+}
+
+// A symlinked hall is skipped while a real hall next to it is indexed; a
+// symlinked wing is refused and nothing is written into its target.
+func TestBuildWingIndexSkipsASymlinkedHallAndRefusesASymlinkedWing(t *testing.T) {
+	b := t.TempDir()
+	require.NoError(t, os.MkdirAll(filepath.Join(b, "raw", "facts"), 0o755))
+	require.NoError(t, os.WriteFile(filepath.Join(b, "raw", "facts", "r.md"), []byte("---\ntitle: zqrawonly\n---\n"), 0o644))
+	require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "w", "decisions"), 0o755))
+	require.NoError(t, os.WriteFile(filepath.Join(b, "wiki", "w", "decisions", "d.md"), []byte("---\ntitle: zqrealhall\n---\n"), 0o644))
+	require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "facts"), filepath.Join(b, "wiki", "w", "facts")))
+	require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(b, "wiki", "alias")))
+
+	require.NoError(t, brain.BuildWingIndex(b, "w"))
+	idx, err := os.ReadFile(filepath.Join(b, "wiki", "w", "_index.md"))
+	require.NoError(t, err, "the wing index is written")
+	assert.Contains(t, string(idx), "zqrealhall", "the real hall is indexed")
+	assert.NotContains(t, string(idx), "zqrawonly", "the symlinked hall is not")
+
+	assert.Error(t, brain.BuildWingIndex(b, "alias"))
+	_, err = os.Stat(filepath.Join(b, "raw", "_index.md"))
+	assert.True(t, os.IsNotExist(err), "an index was written into the symlinked wing's target")
+}
+
+// BuildAllWingIndexes indexes the real wings and skips a symlinked one.
+func TestBuildAllWingIndexesSkipsASymlinkedWing(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: zqrealwing\n---\n"), 0o644))
+	require.NoError(t, os.MkdirAll(filepath.Join(b, "raw", "facts"), 0o755))
+	require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(b, "wiki", "alias")))
+
+	require.NoError(t, brain.BuildAllWingIndexes(b))
+	idx, err := os.ReadFile(filepath.Join(b, "wiki", "w", "_index.md"))
+	require.NoError(t, err)
+	assert.Contains(t, string(idx), "zqrealwing")
+	_, err = os.Stat(filepath.Join(b, "raw", "_index.md"))
+	assert.True(t, os.IsNotExist(err))
+}
+
+// A link to a symlinked note does not resolve: only regular files count as
+// entries, so StripUnresolvedLinks unwraps it.
+func TestStripUnresolvedLinksDoesNotCountASymlinkedNoteAsAnEntry(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, "real.md"), []byte("x"), 0o644))
+	brainfstest.WriteSentinelAt(t, filepath.Join(b, "raw", "s.md"))
+	require.NoError(t, os.Symlink(filepath.Join("..", "..", "..", "raw", "s.md"), filepath.Join(facts, "ghost.md")))
+	out, unlinked, err := brain.StripUnresolvedLinks(b, "see [[real]] and [[ghost]]")
+	require.NoError(t, err)
+	assert.Contains(t, out, "[[real]]", "positive control")
+	assert.NotContains(t, out, "[[ghost]]")
+	assert.Contains(t, unlinked, "ghost")
+}
+
+// A linked tree (knowledge/ or wiki/) that is not a real directory is
+// skipped, not an error: StripUnresolvedLinks runs before every brain_write,
+// and an error there loses the learning.
+func TestStripUnresolvedLinksSkipsALinkedTreeThatIsNotARealDirectory(t *testing.T) {
+	for name, mk := range map[string]func(t *testing.T, b string){
+		"symlink to an in-brain dir": func(t *testing.T, b string) {
+			require.NoError(t, os.MkdirAll(filepath.Join(b, "raw", "k"), 0o755))
+			require.NoError(t, os.Symlink(filepath.Join("raw", "k"), filepath.Join(b, "knowledge")))
+		},
+		"dangling symlink": func(t *testing.T, b string) {
+			require.NoError(t, os.Symlink("nowhere", filepath.Join(b, "knowledge")))
+		},
+		"regular file": func(t *testing.T, b string) {
+			require.NoError(t, os.WriteFile(filepath.Join(b, "knowledge"), []byte("x"), 0o644))
+		},
+	} {
+		t.Run(name, func(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", "real.md"), []byte("x"), 0o644))
+			mk(t, b)
+			out, _, err := brain.StripUnresolvedLinks(b, "learning [[real]] and [[gone]]")
+			require.NoError(t, err)
+			assert.Contains(t, out, "[[real]]", "links into wiki/ still resolve")
+			assert.NotContains(t, out, "[[gone]]")
+		})
+	}
+}

ingestion/internal/brain/linkcheck.go

@@ -1,12 +1,16 @@
 package brain
 
 import (
+	"errors"
 	"fmt"
-	"os"
+	"io/fs"
-	"path/filepath"
+	"log/slog"
+	"path"
 	"regexp"
 	"sort"
 	"strings"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
 )
 
 // wikilinkRE matches [[target]] and [[target|Display Text]].
@@ -98,29 +102,40 @@ var linkedTrees = []string{"knowledge", "wiki"}
 // one the audit will also resolve.
 func entryIndex(brainDir string) (map[string]struct{}, error) {
 	index := map[string]struct{}{}
+	// Walked through the brain root (hyperguild#157): only regular files
+	// count as entries, so a symlinked .md name cannot make a link resolve.
+	bfs, err := brainfs.Open(brainDir)
+	if err != nil {
+		return nil, fmt.Errorf("open brain: %w", err)
+	}
+	defer func() { _ = bfs.Close() }()
 	for _, dir := range linkedTrees {
-		root := filepath.Join(brainDir, dir)
+		if _, err := bfs.Lstat(dir); errors.Is(err, fs.ErrNotExist) {
-		if _, err := os.Stat(root); os.IsNotExist(err) {
 			continue
-		} else if err != nil {
-			return nil, fmt.Errorf("stat %s: %w", dir, err)
 		}
-		err := filepath.WalkDir(root, func(path string, d os.DirEntry, err error) error {
+		var walkErr error
-			if err != nil {
+		err := bfs.WalkRegular(dir, func(rel string) error {
-				return err
+			if !strings.HasSuffix(rel, ".md") {
-			}
-			if d.IsDir() || !strings.HasSuffix(path, ".md") {
 				return nil
 			}
-			rel, err := filepath.Rel(brainDir, path)
+			index[strings.TrimSuffix(path.Base(rel), ".md")] = struct{}{}
-			if err != nil {
-				return err
-			}
-			rel = filepath.ToSlash(rel)
-			index[strings.TrimSuffix(filepath.Base(rel), ".md")] = struct{}{}
 			index[strings.TrimPrefix(strings.TrimSuffix(rel, ".md"), "wiki/")] = struct{}{}
 			return nil
+		}, func(rel string, err error) {
+			// A linked tree that is not a real directory (a symlink, a
+			// file) is skipped, as filepath.WalkDir did: this runs before
+			// every brain_write, and an error here loses the learning.
+			if rel == dir && errors.Is(err, brainfs.ErrNotRegular) {
+				slog.Warn("link check: skipping a linked tree that is not a real directory", "dir", dir)
+				return
+			}
+			if walkErr == nil {
+				walkErr = fmt.Errorf("%s: %w", rel, err)
+			}
 		})
+		if err == nil {
+			err = walkErr
+		}
 		if err != nil {
 			return nil, fmt.Errorf("walk %s: %w", dir, err)
 		}

ingestion/internal/brainfs/brainfs.go

@@ -104,6 +104,27 @@ func (b *Brain) ReadDirRegular(relDir string) ([]string, error) {
 	return names, 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.
+func (b *Brain) ReadDirDirs(relDir string) ([]string, error) {
+	relDir = filepath.ToSlash(relDir)
+	if err := b.realDir(relDir); err != nil {
+		return nil, err
+	}
+	ents, err := fs.ReadDir(b.root.FS(), relDir)
+	if err != nil {
+		return nil, err
+	}
+	var names []string
+	for _, e := range ents {
+		if e.Type().IsDir() {
+			names = append(names, e.Name())
+		}
+	}
+	return names, 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) {

ingestion/internal/brainfs/brainfs_test.go

@@ -262,3 +262,21 @@ func TestReadRegularNeverReturnsAnInBrainFileSwappedInBehindASymlink(t *testing.
 	assert.Zero(t, leaks)
 	assert.Positive(t, ok, "positive control: the regular file is read")
 }
+
+func TestReadDirDirsListsOnlyRealSubdirsAndRefusesSymlinkedComponents(t *testing.T) {
+	dir := t.TempDir()
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "a", "real"), 0o755))
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "other"), 0o755))
+	require.NoError(t, os.Symlink(filepath.Join("..", "other"), filepath.Join(dir, "a", "linked")))
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "a", "f.md"), []byte("f"), 0o644))
+	require.NoError(t, os.Symlink("a", filepath.Join(dir, "alias")))
+	b, err := Open(dir)
+	require.NoError(t, err)
+	defer func() { _ = b.Close() }()
+
+	names, err := b.ReadDirDirs("a")
+	require.NoError(t, err)
+	assert.Equal(t, []string{"real"}, names)
+	_, err = b.ReadDirDirs("alias")
+	assert.ErrorIs(t, err, ErrNotRegular)
+}