Initial commit: knox knowledge index

internal/ingest/ingest.go

@@ -0,0 +1,57 @@
+package ingest
+
+import (
+	"crypto/sha256"
+	"encoding/json"
+	"fmt"
+)
+
+type IngestResult struct {
+	Fingerprint     string
+	SourceID        string
+	SourcePath      string
+	Project         string
+	ContentType     string
+	Title           string
+	Summary         string
+	CreatedAt       string
+	LineStart       int
+	LineEnd         int
+	Confidence      float64
+	IngesterVersion string
+	Provenance      map[string]any
+}
+
+type Ingester interface {
+	SourceID() string
+	Ingest(path string) (*IngestResult, error)
+}
+
+func Fingerprint(data []byte) string {
+	h := sha256.Sum256(data)
+	return fmt.Sprintf("%x", h[:16])
+}
+
+func FingerprintWithMeta(data []byte, meta map[string]string) string {
+	h := sha256.New()
+	h.Write(data)
+	enc := json.NewEncoder(h)
+	_ = enc.Encode(meta)
+	return fmt.Sprintf("%x", h.Sum(nil)[:16])
+}
+
+func ProvenanceJSON(m map[string]any) string {
+	b, err := json.Marshal(m)
+	if err != nil {
+		return "{}"
+	}
+	return string(b)
+}
+
+func truncate(s string, n int) string {
+	runes := []rune(s)
+	if len(runes) <= n {
+		return s
+	}
+	return string(runes[:n]) + "..."
+}