hyperguild/ingestion/internal/pipeline/refs.go

// ingestion/internal/pipeline/refs.go
package pipeline

import (
	"path/filepath"
	"regexp"
	"strings"

	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
)

var wikilinkRE = regexp.MustCompile(`\[\[([^|\]]+)\|`)

// injectSourceRefs finds the source page in the proposed batch, extracts its
// wikilinks, and injects a back-reference into every linked concept or entity page.
// Pages that exist on disk but are not in the current batch are loaded and
// appended so they will be updated on write.
func injectSourceRefs(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entry, brainDir string) []wiki.Page {
	sourceSlug, sourceTitle, found := findSourcePage(pages)
	if !found {
		return pages
	}

	var sourceContent string
	for _, p := range pages {
		if isSourcePath(p.Path) &&
			strings.TrimSuffix(filepath.Base(p.Path), ".md") == sourceSlug {
			sourceContent = p.Content
			break
		}
	}

	linkedSlugs := extractWikilinks(sourceContent)
	sourceRef := "- [[" + sourceSlug + "|" + sourceTitle + "]]"

	bySlug := make(map[string]int, len(pages))
	for i, p := range pages {
		if !isSourcePath(p.Path) {
			bySlug[strings.TrimSuffix(filepath.Base(p.Path), ".md")] = i
		}
	}

	for slug := range linkedSlugs {
		if slug == sourceSlug {
			continue
		}
		if idx, ok := bySlug[slug]; ok {
			pages[idx] = addSourceRef(pages[idx], sourceRef)
			continue
		}
		pt, ok := findInInventory(slug, inventory)
		if !ok {
			continue
		}
		path := entryPath(slug, pt, inventory)
		b, err := readBrainFile(brainDir, path)
		if err != nil {
			continue
		}
		page := wiki.Page{
			Path:    path,
			Content: string(b),
		}
		pages = append(pages, addSourceRef(page, sourceRef))
	}

	return pages
}

// addSourceRef injects sourceRef into the ## Sources bullet section of page
// using wiki.Merge, which deduplicates bullets automatically.
func addSourceRef(page wiki.Page, sourceRef string) wiki.Page {
	patch := wiki.Page{
		Path:    page.Path,
		Content: "\n## Sources\n\n" + sourceRef + "\n",
	}
	return wiki.Merge(page, patch)
}

// extractWikilinks returns the set of slugs referenced as [[slug|...]] in content.
func extractWikilinks(content string) map[string]bool {
	slugs := make(map[string]bool)
	for _, m := range wikilinkRE.FindAllStringSubmatch(content, -1) {
		slugs[m[1]] = true
	}
	return slugs
}

// findSourcePage returns the slug and title of the first wiki/sources/ page in pages.
func findSourcePage(pages []wiki.Page) (slug, title string, found bool) {
	for _, p := range pages {
		if isSourcePath(p.Path) {
			slug = strings.TrimSuffix(filepath.Base(p.Path), ".md")
			title = extractTitle(p.Content)
			if title == "" {
				title = slug
			}
			return slug, title, true
		}
	}
	return "", "", false
}

// findInInventory returns the PageType for a slug if it appears in the inventory.
func findInInventory(slug string, inventory map[wiki.PageType][]wiki.Entry) (wiki.PageType, bool) {
	for pt, entries := range inventory {
		for _, e := range entries {
			if e.Slug == slug {
				return pt, true
			}
		}
	}
	return "", false
}

// isSourcePath reports whether path is a source page in either layout:
// wiki/sources/<slug>.md or wiki/<wing>/sources/<slug>.md.
func isSourcePath(path string) bool {
	parts := strings.Split(filepath.ToSlash(path), "/")
	switch {
	case len(parts) == 3 && parts[0] == "wiki" && parts[1] == "sources":
		return true
	case len(parts) == 4 && parts[0] == "wiki" && parts[2] == "sources":
		return true
	}
	return false
}

// entryPath is the brain-relative path of an inventory page: the recorded Path
// for a wing-layout entry, else the retired wiki/<type>/<slug>.md.
func entryPath(slug string, pt wiki.PageType, inventory map[wiki.PageType][]wiki.Entry) string {
	for _, e := range inventory[pt] {
		if e.Slug == slug && e.Path != "" {
			return e.Path
		}
	}
	return "wiki/" + string(pt) + "/" + slug + ".md"
}