feat(pipeline): add CanonicalizeLinks — convert [[Display Name]] to [[slug|Display Name]]

ingestion/internal/pipeline/links.go

@@ -0,0 +1,70 @@
+// ingestion/internal/pipeline/links.go
+package pipeline
+
+import (
+	"fmt"
+	"path/filepath"
+	"regexp"
+	"strings"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+// plainLinkRE matches [[Display Name]] — wikilinks without a slug pipe.
+// It does NOT match [[slug|Display]] (those already have a pipe).
+var plainLinkRE = regexp.MustCompile(`\[\[([^\]|]+)\]\]`)
+
+// CanonicalizeLinks converts [[Display Name]] wikilinks to [[slug|Display Name]]
+// using a title→slug map built from the inventory and current batch.
+// Unknown titles are left as-is and returned as warnings.
+func CanonicalizeLinks(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entry) ([]wiki.Page, []string) {
+	titleToSlug := buildTitleMap(pages, inventory)
+
+	var allWarnings []string
+	out := make([]wiki.Page, len(pages))
+	for i, p := range pages {
+		newContent, warnings := canonicalizeContent(p.Content, titleToSlug)
+		p.Content = newContent
+		out[i] = p
+		allWarnings = append(allWarnings, warnings...)
+	}
+	return out, allWarnings
+}
+
+// buildTitleMap builds a lowercase-title → slug map from inventory and current batch.
+// Current batch entries take precedence over inventory (they may be updates).
+func buildTitleMap(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entry) map[string]string {
+	m := make(map[string]string)
+	for _, entries := range inventory {
+		for _, e := range entries {
+			m[strings.ToLower(e.Title)] = e.Slug
+		}
+	}
+	// Current batch overrides inventory
+	for _, p := range pages {
+		title := extractTitle(p.Content)
+		slug := strings.TrimSuffix(filepath.Base(p.Path), ".md")
+		if title != "" && slug != "" {
+			m[strings.ToLower(title)] = slug
+		}
+	}
+	return m
+}
+
+func canonicalizeContent(content string, titleToSlug map[string]string) (string, []string) {
+	var warnings []string
+	result := plainLinkRE.ReplaceAllStringFunc(content, func(match string) string {
+		sub := plainLinkRE.FindStringSubmatch(match)
+		if len(sub) < 2 {
+			return match
+		}
+		displayName := sub[1]
+		slug, ok := titleToSlug[strings.ToLower(displayName)]
+		if !ok {
+			warnings = append(warnings, fmt.Sprintf("unknown wikilink: [[%s]]", displayName))
+			return match
+		}
+		return "[[" + slug + "|" + displayName + "]]"
+	})
+	return result, warnings
+}