From 1f97acc1bfe604d46629328a5398ca7c2b1c91fc Mon Sep 17 00:00:00 2001
From: Joakim <joakim@jnss.me>
Date: Wed, 3 Sep 2025 12:23:20 +0200
Subject: [PATCH] Implement hash-based content ID generation

- Replace content text sampling with SHA1 content hashing
- Generate IDs with format: context-purpose-hash (e.g., services-text-0d96da)
- Achieve content independence: IDs stable when text changes
- Maintain semantic meaning through context and purpose components
- Support disposable development IDs with production stability
---
 insertr-cli/pkg/parser/id_generator.go | 34 +++++++++-----------------
 1 file changed, 12 insertions(+), 22 deletions(-)

diff --git a/insertr-cli/pkg/parser/id_generator.go b/insertr-cli/pkg/parser/id_generator.go
index 73632ca..932ed22 100644
--- a/insertr-cli/pkg/parser/id_generator.go
+++ b/insertr-cli/pkg/parser/id_generator.go
@@ -25,9 +25,9 @@ func NewIDGenerator() *IDGenerator {
 func (g *IDGenerator) Generate(node *html.Node) string {
 	context := g.getSemanticContext(node)
 	purpose := g.getPurpose(node)
-	content := g.getContentSample(node)
+	contentHash := g.getContentHash(node)
 
-	baseID := g.createBaseID(context, purpose, content)
+	baseID := g.createBaseID(context, purpose, contentHash)
 	return g.ensureUnique(baseID)
 }
 
@@ -111,27 +111,19 @@ func (g *IDGenerator) getPurpose(node *html.Node) string {
 	}
 }
 
-// getContentSample gets a sample of content for ID generation
-func (g *IDGenerator) getContentSample(node *html.Node) string {
+// getContentHash creates a short hash of the content for ID generation
+func (g *IDGenerator) getContentHash(node *html.Node) string {
 	text := extractTextContent(node)
 
-	// Clean and normalize text
-	text = strings.ToLower(text)
-	text = regexp.MustCompile(`[^a-z0-9\s]+`).ReplaceAllString(text, "")
-	text = regexp.MustCompile(`\s+`).ReplaceAllString(text, " ")
-	text = strings.TrimSpace(text)
+	// Create hash of the text content
+	hash := fmt.Sprintf("%x", sha1.Sum([]byte(text)))
 
-	// Take first few words
-	words := strings.Fields(text)
-	if len(words) > 3 {
-		words = words[:3]
-	}
-
-	return strings.Join(words, "-")
+	// Return first 6 characters for brevity
+	return hash[:6]
 }
 
 // createBaseID creates the base ID from components
-func (g *IDGenerator) createBaseID(context, purpose, content string) string {
+func (g *IDGenerator) createBaseID(context, purpose, contentHash string) string {
 	parts := []string{}
 
 	// Add context if meaningful
@@ -142,10 +134,8 @@ func (g *IDGenerator) createBaseID(context, purpose, content string) string {
 	// Add purpose
 	parts = append(parts, purpose)
 
-	// Add content sample if available and meaningful
-	if content != "" && content != purpose {
-		parts = append(parts, content)
-	}
+	// Always add content hash for uniqueness
+	parts = append(parts, contentHash)
 
 	baseID := strings.Join(parts, "-")
 
@@ -155,7 +145,7 @@ func (g *IDGenerator) createBaseID(context, purpose, content string) string {
 
 	// Ensure it's not empty
 	if baseID == "" {
-		baseID = "content"
+		baseID = fmt.Sprintf("content-%s", contentHash)
 	}
 
 	return baseID