fix: systematic element matching bug in enhancement pipeline
- Problem: Element ID collisions between similar elements (logo h1 vs hero h1) causing content to be injected into wrong elements - Root cause: Enhancer used naive tag+class matching instead of parser's sophisticated semantic analysis for element identification Systematic solution: - Enhanced parser architecture with exported utilities (GetClasses, ContainsClass) - Added FindElementInDocument() with content-based semantic matching - Replaced naive findAndInjectNodes() with parser-based element matching - Removed code duplication between parser and enhancer packages Backend improvements: - Moved ID generation to backend for single source of truth - Added ElementContext struct for frontend-backend communication - Updated API handlers to support context-based content ID generation Frontend improvements: - Enhanced getElementMetadata() to extract semantic context - Updated save flow to handle both enhanced and non-enhanced elements - Improved API client to use backend-generated content IDs Result: - Unique content IDs: navbar-logo-200530 vs hero-title-a1de7b - Precise element matching using content validation - Single source of truth for DOM utilities in parser package - Eliminated 40+ lines of duplicate code while fixing core bug
This commit is contained in:
@@ -6,8 +6,8 @@ import (
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// getClasses extracts CSS classes from an HTML node
|
||||
func getClasses(node *html.Node) []string {
|
||||
// GetClasses extracts CSS classes from an HTML node
|
||||
func GetClasses(node *html.Node) []string {
|
||||
classAttr := getAttribute(node, "class")
|
||||
if classAttr == "" {
|
||||
return []string{}
|
||||
@@ -17,8 +17,8 @@ func getClasses(node *html.Node) []string {
|
||||
return classes
|
||||
}
|
||||
|
||||
// containsClass checks if a class list contains a specific class
|
||||
func containsClass(classes []string, target string) bool {
|
||||
// ContainsClass checks if a class list contains a specific class
|
||||
func ContainsClass(classes []string, target string) bool {
|
||||
for _, class := range classes {
|
||||
if class == target {
|
||||
return true
|
||||
@@ -157,3 +157,39 @@ func isSelfClosing(node *html.Node) bool {
|
||||
|
||||
return selfClosingTags[node.Data]
|
||||
}
|
||||
|
||||
// FindElementInDocument finds a parser element in HTML document tree using semantic matching
|
||||
func FindElementInDocument(doc *html.Node, element Element) *html.Node {
|
||||
return findElementWithContext(doc, element)
|
||||
}
|
||||
|
||||
// findElementWithContext uses the parser's semantic understanding to find the correct element
|
||||
func findElementWithContext(node *html.Node, target Element) *html.Node {
|
||||
if node.Type == html.ElementNode && node.Data == target.Tag {
|
||||
classes := GetClasses(node)
|
||||
if ContainsClass(classes, "insertr") {
|
||||
// Content-based validation for precise matching
|
||||
textContent := extractTextContent(node)
|
||||
nodeContent := strings.TrimSpace(textContent)
|
||||
targetContent := strings.TrimSpace(target.Content)
|
||||
|
||||
if nodeContent == targetContent {
|
||||
return node
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Recursively search children
|
||||
for child := node.FirstChild; child != nil; child = child.NextSibling {
|
||||
if result := findElementWithContext(child, target); result != nil {
|
||||
return result
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// GetAttribute gets an attribute value from an HTML node (exported version)
|
||||
func GetAttribute(node *html.Node, key string) string {
|
||||
return getAttribute(node, key)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user