feat(pipeline): inject source back-references into concept and entity pages

ingestion/internal/pipeline/refs.go

@@ -0,0 +1,115 @@
+// ingestion/internal/pipeline/refs.go
+package pipeline
+
+import (
+	"os"
+	"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 strings.HasPrefix(p.Path, "wiki/sources/") &&
+			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 !strings.HasPrefix(p.Path, "wiki/sources/") {
+			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
+		}
+		diskPath := filepath.Join(brainDir, "wiki", string(pt), slug+".md")
+		b, err := os.ReadFile(diskPath)
+		if err != nil {
+			continue
+		}
+		page := wiki.Page{
+			Path:    "wiki/" + string(pt) + "/" + slug + ".md",
+			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 strings.HasPrefix(p.Path, "wiki/sources/") {
+			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
+}