Classify appearance templates by XML root

plugins/1c/connector/adapter_1c_server.py

@@ -172,7 +172,7 @@ ONEC_TEMPLATE_PLATFORM_TYPES = [
         "xml_type": "DataCompositionAppearanceTemplate",
         "decoder": "data_composition_appearance",
         "status": "not_implemented",
-        "aliases": ["МакетОформленияКомпоновкиДанных", "DataCompositionAppearanceTemplate"],
+        "aliases": ["МакетОформленияКомпоновкиДанных", "DataCompositionAppearanceTemplate", "AppearanceTemplate"],
     },
     {
         "id": "external_component",
@@ -4087,6 +4087,7 @@ def declared_template_platform_type_from_part(part: dict[str, Any]) -> dict[str,
             classification.get("template_type"),
             classification.get("platform_type_id"),
             classification.get("platform_type"),
+            classification.get("xml_root"),
         ]
     )
     candidates.extend(classification.get("strings_sample") or [])
@@ -4101,7 +4102,7 @@ def template_type_candidates_from_features(features: dict[str, Any], content_par
     candidates: list[dict[str, Any]] = []
     declared = normalize_onec_template_platform_type(features.get("declared_platform_type_id") or features.get("declared_platform_type"))
     if declared:
-        declared.update({"confidence": "high", "evidence": ["TemplateType metadata"]})
+        declared.update({"confidence": "high", "evidence": [str(features.get("declared_platform_type_evidence") or "TemplateType metadata")]})
         candidates.append(declared)
 
     def append_candidate(candidate: dict[str, Any]) -> None:
@@ -4140,6 +4141,14 @@ def public_template_summary(
         (template_type for template_type in (declared_template_platform_type_from_part(part) for part in parts) if template_type),
         None,
     )
+    declared_type_evidence = "TemplateType metadata"
+    if any(
+        normalize_onec_template_platform_type(
+            ((part.get("classification") or {}).get("xml_root") if isinstance(part.get("classification"), dict) else None)
+        )
+        for part in parts
+    ):
+        declared_type_evidence = "payload XML root"
     features = {
         "tabular_document": any(((part.get("features") or {}).get("tabular_document")) for part in content_parts),
         "html": any(((part.get("features") or {}).get("html")) for part in content_parts),
@@ -4149,6 +4158,7 @@ def public_template_summary(
                 "declared_platform_type": declared_platform_type.get("name"),
                 "declared_platform_type_id": declared_platform_type.get("id"),
                 "declared_platform_xml_type": declared_platform_type.get("xml_type"),
+                "declared_platform_type_evidence": declared_type_evidence,
             }
             if declared_platform_type
             else {}

plugins/1c/parser/cas_payload.py

@@ -7,6 +7,9 @@ import hashlib
 import re
 from typing import Any
 
+
+XML_ROOT_RE = re.compile(r"^\s*(?:<\?xml[^>]*>\s*)?<([A-Za-z_][\w.-]*(?::[A-Za-z_][\w.-]*)?)\b")
+
 from .payload import collect_strings, decode_payload_lossless, encode_text, parse_brace_text, root_signature, scalar
 
 
@@ -483,6 +486,11 @@ def classify_payload(data: bytes, *, include_text: bool = False, include_tree: b
                 stream["text"] = declared_prefix["text"]
                 stream["text_preview"] = str(declared_prefix["text"] or "").replace("\x00", "")[:500]
     text = decoded.get("text")
+    xml_root = None
+    if isinstance(text, str):
+        match = XML_ROOT_RE.match(text.lstrip("\ufeff"))
+        if match:
+            xml_root = match.group(1).rsplit(":", 1)[-1]
     tree = None
     root = None
     base64_decoded: list[dict[str, Any]] = []
@@ -505,6 +513,7 @@ def classify_payload(data: bytes, *, include_text: bool = False, include_tree: b
         "sha1": sha1_hex(data),
         "payload_sha1": sha1_hex(bytes(payload)),
         "markers": markers,
+        **({"xml_root": xml_root} if xml_root else {}),
         "root": root,
         "role": classify_role(root_marker, markers, text, stream_blocks, base64_decoded),
         "strings_sample": strings_sample,

tests/1c/test_payload_codec.py

@@ -6949,6 +6949,16 @@ def test_public_template_summary_uses_declared_template_type_alias() -> None:
     assert summary["template_type_candidates"][0]["confidence"] == "high"
 
 
+def test_public_template_summary_recognizes_live_appearance_xml_root() -> None:
+    summary = adapter_server.public_template_summary(
+        [{"role": "content", "classification": {"xml_root": "AppearanceTemplate"}, "features": {}}]
+    )
+
+    assert summary["platform_type"] == "Макет оформления компоновки данных"
+    assert summary["template_type_candidates"][0]["id"] == "data_composition_appearance_template"
+    assert summary["template_type_candidates"][0]["evidence"] == ["payload XML root"]
+
+
 def test_moxel_template_artifact_kind_tracks_coordinate_hint_schema() -> None:
     assert adapter_server.MOXEL_TEMPLATE_ARTIFACT_KIND == "template_part_moxel_v11"