feat: add XML auto-fix and improve validator accuracy

- Add autoFixXml() to automatically repair common XML issues:
  - CDATA wrapper removal
  - Duplicate attribute removal
  - Unescaped & and < character escaping
  - Invalid entity reference fixing
  - Unclosed tag completion
  - Nested mxCell flattening
  - Duplicate ID renaming

- Improve validateMxCellStructure() with DOM + regex approach:
  - Use DOMParser for syntax error detection (94% recall)
  - Add regex checks for edge cases
  - Stateful parser for handling > in attribute values

- Integrate validateAndFixXml() in chat-message-display and diagram-context
  - Auto-repair invalid XML before loading
  - Log fixes applied for debugging

Metrics: 99.77% accuracy, 94.06% recall, 94.4% auto-fix success rate
This commit is contained in:
dayuan.jiang
2025-12-13 15:00:28 +09:00
parent e321ba7959
commit 4b838fd6d5
3 changed files with 682 additions and 128 deletions

View File

@@ -29,11 +29,7 @@ import {
ReasoningTrigger,
} from "@/components/ai-elements/reasoning"
import { ScrollArea } from "@/components/ui/scroll-area"
import {
convertToLegalXml,
replaceNodes,
validateMxCellStructure,
} from "@/lib/utils"
import { convertToLegalXml, replaceNodes, validateAndFixXml } from "@/lib/utils"
import ExamplePanel from "./chat-example-panel"
import { CodeBlock } from "./code-block"
@@ -312,15 +308,24 @@ export function ChatMessageDisplay({
`<mxfile><diagram name="Page-1" id="page-1"><mxGraphModel><root><mxCell id="0"/><mxCell id="1" parent="0"/></root></mxGraphModel></diagram></mxfile>`
const replacedXML = replaceNodes(baseXML, convertedXml)
const validationError = validateMxCellStructure(replacedXML)
if (!validationError) {
// Validate and auto-fix the XML
const validation = validateAndFixXml(replacedXML)
if (validation.valid) {
previousXML.current = convertedXml
// Use fixed XML if available, otherwise use original
const xmlToLoad = validation.fixed || replacedXML
if (validation.fixes.length > 0) {
console.log(
"[ChatMessageDisplay] Auto-fixed XML issues:",
validation.fixes,
)
}
// Skip validation in loadDiagram since we already validated above
onDisplayChart(replacedXML, true)
onDisplayChart(xmlToLoad, true)
} else {
console.error(
"[ChatMessageDisplay] XML validation failed:",
validationError,
validation.error,
)
// Only show toast if this is the final XML (not during streaming)
if (showToast) {