hyperguild/ingestion/internal/brain/index.go

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.
type noteEntry struct {
	Hall    string
	Slug    string
	Title   string
	Created string
}

// BuildWingIndex regenerates brain/wiki/<wing>/_index.md as a Map of
// Content listing every note in that wing with its Hall and creation
// date. Returns nil if the wing directory does not exist.
func BuildWingIndex(brainDir, wing string) error {
	w := Sanitise(wing)
	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)
	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
	}

	entries, err := collectWingEntries(bfs, "wiki/"+w)
	if err != nil {
		return err
	}
	sort.Slice(entries, func(i, j int) bool {
		if entries[i].Hall != entries[j].Hall {
			return entries[i].Hall < entries[j].Hall
		}
		return entries[i].Slug < entries[j].Slug
	})

	var b strings.Builder
	fmt.Fprintf(&b, "# %s\n\n", w)
	b.WriteString("| Hall | Note | Created |\n")
	b.WriteString("|------|------|---------|\n")
	for _, e := range entries {
		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)
}

// BuildAllWingIndexes regenerates _index.md for every wing under brain/wiki/.
func BuildAllWingIndexes(brainDir string) error {
	bfs, err := brainfs.Open(brainDir)
	if err != nil {
		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 _, w := range wings {
		if err := BuildWingIndex(brainDir, w); err != nil {
			return fmt.Errorf("index %s: %w", w, err)
		}
	}
	return nil
}

func collectWingEntries(bfs *brainfs.Brain, wingRel string) ([]noteEntry, error) {
	var out []noteEntry
	halls, err := bfs.ReadDirDirs(wingRel)
	if err != nil {
		return nil, fmt.Errorf("read wing: %w", err)
	}
	for _, hall := range halls {
		if !IsValidHall(hall) {
			continue
		}
		hallRel := wingRel + "/" + hall
		names, err := bfs.ReadDirRegular(hallRel)
		if err != nil {
			return nil, fmt.Errorf("read hall %s: %w", hall, err)
		}
		for _, name := range names {
			if !strings.HasSuffix(name, ".md") || name == "_index.md" {
				continue
			}
			slug := strings.TrimSuffix(name, ".md")
			title, created := readTitleAndCreatedIn(bfs, hallRel+"/"+name, slug)
			out = append(out, noteEntry{Hall: hall, Slug: slug, Title: title, Created: created})
		}
	}
	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) {
	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()
		if strings.TrimSpace(line) == "---" {
			if !inFrontmatter {
				inFrontmatter = true
				continue
			}
			break
		}
		if !inFrontmatter {
			continue
		}
		key, val, ok := strings.Cut(line, ":")
		if !ok {
			continue
		}
		v := strings.Trim(strings.TrimSpace(val), `"'`)
		switch strings.TrimSpace(key) {
		case "title":
			title = v
		case "created_at":
			if t, err := time.Parse(time.RFC3339, v); err == nil {
				created = t.UTC().Format("2006-01-02")
			} else {
				created = v
			}
		}
	}
	return title, created
}