feat(pipeline): add BuildPages — compute slugs/paths/frontmatter from RawPage

ingestion/internal/pipeline/build.go

@@ -0,0 +1,88 @@
+// ingestion/internal/pipeline/build.go
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+// BuildPages converts RawPages from the LLM into wiki.Pages with computed slugs,
+// paths, and YAML frontmatter. sourceSlug is the slug of the source being ingested
+// (derived from the filename, not the LLM title).
+func BuildPages(rawPages []RawPage, sourceSlug, date string) []wiki.Page {
+	out := make([]wiki.Page, 0, len(rawPages))
+	for _, rp := range rawPages {
+		out = append(out, buildPage(rp, sourceSlug, date))
+	}
+	return out
+}
+
+func buildPage(rp RawPage, sourceSlug, date string) wiki.Page {
+	var slug, dir string
+	switch rp.Type {
+	case "source":
+		slug = sourceSlug
+		dir = "wiki/sources"
+	case "concept":
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/concepts"
+	case "entity":
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/entities"
+	default:
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/" + rp.Type
+	}
+
+	path := dir + "/" + slug + ".md"
+	fm := buildFrontmatter(rp, date)
+
+	return wiki.Page{
+		Path:    path,
+		Content: fm + "\n" + rp.Content,
+	}
+}
+
+func buildFrontmatter(rp RawPage, date string) string {
+	var sb strings.Builder
+	sb.WriteString("---\n")
+	fmt.Fprintf(&sb, "title: %s\n", rp.Title)
+
+	switch rp.Type {
+	case "source":
+		subtype := rp.Subtype
+		if subtype == "" {
+			subtype = "article"
+		}
+		fmt.Fprintf(&sb, "type: %s\n", subtype)
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "date_ingested: %s\n", date)
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	case "concept":
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	case "entity":
+		if rp.Subtype != "" {
+			fmt.Fprintf(&sb, "type: %s\n", rp.Subtype)
+		}
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	default:
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	}
+
+	fmt.Fprintf(&sb, "aliases:\n  - %s\n", rp.Title)
+	sb.WriteString("---\n")
+	return sb.String()
+}