Expose SCD XML structure outline

plugins/1c/parser/scd_payload.py

@@ -75,22 +75,20 @@ def query_without_line_comments(text: str) -> str:
 def node_path(root: ET.Element, target: ET.Element) -> str:
     """Produce a stable, human-readable evidence path without XML prefixes."""
 
-    def visit(node: ET.Element, prefix: str) -> str | None:
-        name = local_name(node.tag)
-        current = f"{prefix}/{name}" if prefix else f"/{name}"
+    def visit(node: ET.Element, current: str) -> str | None:
         if node is target:
             return current
         positions: dict[str, int] = {}
         for child in node:
             child_name = local_name(child.tag)
             positions[child_name] = positions.get(child_name, 0) + 1
-            child_prefix = f"{current}[{positions[child_name]}]"
-            found = visit(child, child_prefix)
+            suffix = f"[{positions[child_name]}]" if positions[child_name] > 1 else ""
+            found = visit(child, f"{current}/{child_name}{suffix}")
             if found:
                 return found
         return None
 
-    return visit(root, "") or "/"
+    return visit(root, f"/{local_name(root.tag)}[1]") or "/"
 
 
 def xml_from_scd_payload(data: bytes) -> tuple[ET.Element | None, dict[str, Any]]:
@@ -184,6 +182,21 @@ def inspect_scd_payload(data: bytes, *, sections: list[str] | None = None) -> di
             "container": {**container, "code": "SCD_SCHEMA_NODE_NOT_FOUND"},
             "sections": {name: [] for name in requested},
         }
+    # Keep a complete, evidence-backed map of the XML shape alongside the
+    # curated semantic sections below.  1C releases and SCD variants may add
+    # nodes that this adapter does not yet assign a business meaning to.  A
+    # tag/count/path outline makes those nodes visible to callers without
+    # guessing that (for example) a form property is a dataset or layout.
+    top_level_counts: dict[str, int] = {}
+    top_level_paths: dict[str, list[str]] = {}
+    for child in schema:
+        tag = local_name(child.tag)
+        top_level_counts[tag] = top_level_counts.get(tag, 0) + 1
+        top_level_paths.setdefault(tag, []).append(node_path(schema, child))
+    xml_tag_counts: dict[str, int] = {}
+    for node in schema.iter():
+        tag = local_name(node.tag)
+        xml_tag_counts[tag] = xml_tag_counts.get(tag, 0) + 1
     node_names = {
         "parameters": {"parameter"},
         "datasets": {"dataSet"},
@@ -220,6 +233,14 @@ def inspect_scd_payload(data: bytes, *, sections: list[str] | None = None) -> di
             query_references.append({"dataset": dataset.get("name"), "parameters": references})
     analysis = {
         "kind": "raw_query_parameter_token_scan",
+        "schema_outline": {
+            "kind": "exact_xml_tag_inventory",
+            "top_level": [
+                {"tag": tag, "count": top_level_counts[tag], "paths": top_level_paths[tag]}
+                for tag in sorted(top_level_counts, key=str.casefold)
+            ],
+            "all_tag_counts": dict(sorted(xml_tag_counts.items(), key=lambda item: item[0].casefold())),
+        },
         "declared_parameters": declared,
         "query_parameter_references": query_references,
         "referenced_not_declared_in_schema": sorted(