mathiasandClaude Opus 5.5
c7a6429bae
graphsync.IndexDoc/BackfillFromBrainDir and wiki.LoadInventory/ RebuildIndex read notes by path (os.ReadFile, os.Open, os.ReadDir + open). A symlinked note put the target's title, aliases and wikilinks into the knowledge graph, the wiki inventory (and the LLM prompts built from it) and wiki/index.md; a FIFO hung each read. - graphsync: IndexDoc and the backfill read through brainfs; the backfill walks with WalkRegular, skips a missing root and aborts on any other walk error, including a symlinked root. - wiki: LoadInventory lists type dirs with the new brainfs.ReadDirRegular (every component a real dir, regular files only) and reads frontmatter through the root; a symlinked type dir is an error. RebuildIndex reads first sentences through the root. - brainfstest's outside file now carries the sentinel in frontmatter title and aliases, a heading and a wikilink, so extractors that ignore the body are tested too. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
99 lines
2.4 KiB
Go
99 lines
2.4 KiB
Go
// ingestion/internal/wiki/inventory.go
|
|
package wiki
|
|
|
|
import (
|
|
"bufio"
|
|
"bytes"
|
|
"errors"
|
|
"fmt"
|
|
"io/fs"
|
|
"strings"
|
|
|
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
|
)
|
|
|
|
// LoadInventory walks brain/wiki/ and returns all pages grouped by type.
|
|
// Missing subdirectories are silently skipped. Pages are listed and read
|
|
// through the brain root, regular files only (hyperguild#157); a type
|
|
// directory that is a symlink is an error.
|
|
func LoadInventory(brainDir string) (map[PageType][]Entry, error) {
|
|
result := map[PageType][]Entry{
|
|
PageTypeConcept: {},
|
|
PageTypeEntity: {},
|
|
PageTypeSource: {},
|
|
}
|
|
bfs, err := brainfs.Open(brainDir)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("open brain: %w", err)
|
|
}
|
|
defer func() { _ = bfs.Close() }()
|
|
for pt := range result {
|
|
dir := "wiki/" + string(pt)
|
|
names, err := bfs.ReadDirRegular(dir)
|
|
if errors.Is(err, fs.ErrNotExist) {
|
|
continue
|
|
}
|
|
if err != nil {
|
|
return nil, fmt.Errorf("read dir %s: %w", dir, err)
|
|
}
|
|
for _, name := range names {
|
|
if !strings.HasSuffix(name, ".md") {
|
|
continue
|
|
}
|
|
slug := strings.TrimSuffix(name, ".md")
|
|
title, aliases := readFrontmatter(bfs, dir+"/"+name, slug)
|
|
result[pt] = append(result[pt], Entry{Slug: slug, Title: title, Aliases: aliases, Type: pt})
|
|
}
|
|
}
|
|
return result, nil
|
|
}
|
|
|
|
// readFrontmatter extracts title and aliases from YAML frontmatter.
|
|
// Falls back to slug for title and empty aliases on any error.
|
|
func readFrontmatter(bfs *brainfs.Brain, rel, fallbackSlug string) (title string, aliases []string) {
|
|
title = fallbackSlug
|
|
content, err := bfs.ReadRegular(rel)
|
|
if err != nil {
|
|
return
|
|
}
|
|
|
|
scanner := bufio.NewScanner(bytes.NewReader(content))
|
|
inFM := false
|
|
inAliases := false
|
|
for scanner.Scan() {
|
|
line := scanner.Text()
|
|
if strings.TrimSpace(line) == "---" {
|
|
if !inFM {
|
|
inFM = true
|
|
continue
|
|
}
|
|
break // end of frontmatter
|
|
}
|
|
if !inFM {
|
|
continue
|
|
}
|
|
|
|
// Detect alias list items (lines starting with " - ").
|
|
if inAliases {
|
|
trimmed := strings.TrimSpace(line)
|
|
if strings.HasPrefix(trimmed, "- ") {
|
|
aliases = append(aliases, strings.TrimPrefix(trimmed, "- "))
|
|
continue
|
|
}
|
|
inAliases = false // end of alias block
|
|
}
|
|
|
|
key, val, ok := strings.Cut(line, ":")
|
|
if !ok {
|
|
continue
|
|
}
|
|
switch strings.TrimSpace(key) {
|
|
case "title":
|
|
title = strings.Trim(strings.TrimSpace(val), `"'`)
|
|
case "aliases":
|
|
inAliases = true
|
|
}
|
|
}
|
|
return
|
|
}
|