Initial commit: knox knowledge index

internal/ingest/skills.go

@@ -0,0 +1,135 @@
+package ingest
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+)
+
+var _ Ingester = (*SkillsIngester)(nil)
+
+type SkillsIngester struct {
+	Version string
+}
+
+func NewSkillsIngester() *SkillsIngester {
+	return &SkillsIngester{Version: "skills-index/v1"}
+}
+
+func (s *SkillsIngester) SourceID() string { return "skills-catalog" }
+
+func (s *SkillsIngester) Ingest(path string) (*IngestResult, error) {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("read skill: %w", err)
+	}
+	if len(data) < 20 {
+		return nil, nil
+	}
+
+	content := string(data)
+	title := extractSkillName(content, path)
+	summary := extractSkillSummary(content)
+	tags := extractSkillTags(content)
+	projects := extractProjects(tags)
+	createdAt := extractCreatedAt(content)
+
+	fp := FingerprintWithMeta(data, map[string]string{
+		"source": "skills-catalog",
+		"title":  title,
+	})
+
+	return &IngestResult{
+		Fingerprint:     fp,
+		SourceID:        s.SourceID(),
+		SourcePath:      path,
+		Project:         projects,
+		ContentType:     ".md",
+		Title:           title,
+		Summary:         summary,
+		CreatedAt:       createdAt,
+		LineStart:       0,
+		LineEnd:         len(strings.Split(content, "\n")),
+		Confidence:      0.9,
+		IngesterVersion: s.Version,
+		Provenance: map[string]any{
+			"skill_name": title,
+			"tags":       tags,
+			"line_count": len(strings.Split(content, "\n")),
+		},
+	}, nil
+}
+
+func extractSkillName(content, path string) string {
+	base := filepath.Base(filepath.Dir(path))
+	if base != "" && base != "." && base != "/" {
+		return base
+	}
+	return strings.TrimSuffix(filepath.Base(path), ".md")
+}
+
+func extractSkillSummary(content string) string {
+	for _, line := range strings.Split(content, "\n") {
+		trimmed := strings.TrimSpace(line)
+		if strings.HasPrefix(trimmed, "description:") {
+			desc := strings.TrimSpace(trimmed[len("description:"):])
+			if len(desc) > 200 {
+				desc = desc[:200] + "..."
+			}
+			return desc
+		}
+	}
+	for _, line := range strings.Split(content, "\n") {
+		trimmed := strings.TrimSpace(line)
+		if strings.HasPrefix(trimmed, "# ") {
+			continue
+		}
+		if trimmed != "" && !strings.HasPrefix(trimmed, "---") {
+			return truncate(trimmed, 200)
+		}
+	}
+	return ""
+}
+
+func extractSkillTags(content string) []string {
+	for _, line := range strings.Split(content, "\n") {
+		trimmed := strings.TrimSpace(line)
+		if strings.HasPrefix(trimmed, "tags:") {
+			raw := strings.TrimSpace(trimmed[len("tags:"):])
+			raw = strings.Trim(raw, "\"[]")
+			var tags []string
+			for _, t := range strings.Split(raw, ",") {
+				t = strings.TrimSpace(t)
+				t = strings.Trim(t, "\" ")
+				if t != "" {
+					tags = append(tags, t)
+				}
+			}
+			return tags
+		}
+	}
+	return nil
+}
+
+func extractProjects(tags []string) string {
+	for _, t := range tags {
+		if strings.HasPrefix(t, "scope:project:") {
+			return strings.TrimPrefix(t, "scope:project:")
+		}
+		if strings.HasPrefix(t, "scope:machine:") {
+			return "[machine]"
+		}
+	}
+	return ""
+}
+
+func extractCreatedAt(content string) string {
+	for _, line := range strings.Split(content, "\n") {
+		trimmed := strings.TrimSpace(line)
+		if strings.HasPrefix(trimmed, "created_at:") || strings.HasPrefix(trimmed, "updated_at:") {
+			return strings.TrimSpace(trimmed[strings.Index(trimmed, ":")+1:])
+		}
+	}
+	return ""
+}