audit(xaml): emit the Phase-2 facts layer (xaml-facts.json)

.github/workflows/ci.yml

@@ -62,6 +62,7 @@ jobs:
           python audit/aggregate/score.py --selftest
           python audit/aggregate/report.py --selftest
           python audit/static/tools/xaml_check.py --selftest
+          python audit/static/tools/xaml_facts.py --selftest
           python audit/static/run_static.py --selftest
           python audit/runtime/ingest.py --selftest
 

audit/README.md

@@ -48,6 +48,7 @@ audit/
       owncheck.py    # build-free runner: own-check.sh --format sarif  (needs dotnet)
       codeql.sh      # build-free runner: CodeQL build-mode=none, security-and-quality
       xaml_check.py  # build-free runner: markup-only XAML perf/lifetime pass (stdlib XML, no SDK)
+      xaml_facts.py  # XAML facts extractor (resource graph + binding facts) -> xaml-facts.json (Phase-2 seam)
       roslyn_pack.ps1 # build-required runner (local Windows): NetAnalyzers/Roslynator/... 
       infersharp.sh  # build-required runner: Infer# over built binaries
     inject/          # OwnAudit.Directory.Build.props/.targets (analyzer injection, gated)
@@ -110,6 +111,7 @@ python audit/aggregate/normalize.py --selftest
 python audit/aggregate/score.py --selftest
 python audit/aggregate/report.py --selftest
 python audit/static/tools/xaml_check.py --selftest   # XAML rules + line preservation + SARIF round-trip
+python audit/static/tools/xaml_facts.py --selftest   # XAML facts: binding parser + resource graph
 python audit/static/run_static.py --selftest   # full pipeline end-to-end on fixtures
 ```
 
@@ -133,7 +135,11 @@ python audit/static/run_static.py --selftest   # full pipeline end-to-end on fix
   Freezable duplication). This makes category 8 (broken virtualization) statically
   covered, not NO-TOOL. Design + the full rule catalogue, phasing, and the Phase-2
   binding-path join: [`../docs/notes/xaml-analyzer-design.md`](../docs/notes/xaml-analyzer-design.md).
-  Phase 2 (Roslyn-linked XAML2xx) and Phase 3 (runtime correlation) are deferred.
+- **XAML Phase-2 seam — done:** `static/tools/xaml_facts.py` emits `xaml-facts.json` (resource graph
+  + binding facts: parsed binding paths / converters / handlers + the file's `x:Class`) from the same
+  parsed tree, in an OwnIR-parallel envelope. This is the structured input the binding-path join reads
+  next to the `OwnSharp.Extractor` OwnIR facts. The join itself (Roslyn-linked XAML2xx) and Phase 3
+  (runtime correlation) remain deferred.
 - **Runtime (Phase 2) — started:** the runtime→pipeline bridge (`runtime/ingest.py`,
   CI-gated), the leak-harness scenario schema + one scenario, runtime rule mappings
   in the taxonomy (categories 2/3/4/11), and the C# leak-harness skeleton. See

audit/static/tools/xaml_check.py

@@ -643,17 +643,24 @@ def _rule_layout_transform(root: Node, avalonia: bool) -> list[XamlFinding]:
 ]
 
 
+def analyze_root(root: Node) -> list[XamlFinding]:
+    """All Phase-1 rules over an already-parsed tree. Split out from ``analyze_text``
+    so a caller (e.g. ``run_xaml_check``) can parse a file once and feed the same
+    tree to both the rules and the facts extractor (``xaml_facts``)."""
+    avalonia = _is_avalonia(root)
+    out: list[XamlFinding] = []
+    for rule in RULES:
+        out.extend(rule(root, avalonia))
+    return out
+
+
 def analyze_text(text: str | bytes) -> list[XamlFinding]:
     """All Phase-1 rules over one markup document (``str`` or raw ``bytes``).
     Malformed markup -> no findings."""
     root = parse_xaml(text)
     if root is None:
         return []
-    avalonia = _is_avalonia(root)
-    out: list[XamlFinding] = []
-    for rule in RULES:
-        out.extend(rule(root, avalonia))
-    return out
+    return analyze_root(root)
 
 
 def _to_sarif(results: list[tuple[str, XamlFinding]]) -> dict[str, Any]:
@@ -679,11 +686,19 @@ def _to_sarif(results: list[tuple[str, XamlFinding]]) -> dict[str, Any]:
 
 
 def run_xaml_check(target: str, out_dir: Path) -> dict[str, Any]:
-    """Scan every ``.xaml`` / ``.axaml`` under ``target`` and write SARIF to
-    ``out_dir/xaml-check.sarif``. Always best-effort: a missing target or zero
-    markup files yields ``available=False`` with a reason, never a crash."""
+    """Scan every ``.xaml`` / ``.axaml`` under ``target`` and write two artifacts to
+    ``out_dir``: ``xaml-check.sarif`` (the Phase-1 rule findings, into the audit
+    pipeline) and ``xaml-facts.json`` (the structured resource-graph + binding facts
+    for the Phase-2 binding-path join — see ``xaml_facts``). Each file is parsed once
+    and the same tree feeds both the rules and the facts extractor. Always
+    best-effort: a missing target or zero markup files yields ``available=False`` with
+    a reason, never a crash."""
+    # Local import keeps the module pair decoupled (xaml_facts imports from here).
+    from xaml_facts import document_facts, module_facts
+
     out_dir.mkdir(parents=True, exist_ok=True)
     sarif_path = out_dir / "xaml-check.sarif"
+    facts_path = out_dir / "xaml-facts.json"
     status: dict[str, Any] = {"tool": "xaml", "tier": "build-free",
                               "available": False, "sarif": None, "reason": ""}
 
@@ -698,6 +713,7 @@ def run_xaml_check(target: str, out_dir: Path) -> dict[str, Any]:
         return status
 
     results: list[tuple[str, XamlFinding]] = []
+    documents: list[dict[str, Any]] = []
     scanned = 0
     for fp in files:
         try:
@@ -709,12 +725,27 @@ def run_xaml_check(target: str, out_dir: Path) -> dict[str, Any]:
             continue
         scanned += 1
         rel = fp.relative_to(root).as_posix()
-        for f in analyze_text(data):
+        tree = parse_xaml(data)
+        if tree is None:
+            continue  # malformed markup: skipped (no findings, no facts)
+        for f in analyze_root(tree):
             results.append((rel, f))
+        documents.append(document_facts(tree, rel))
 
-    sarif_path.write_text(json.dumps(_to_sarif(results), indent=2), encoding="utf-8")
-    status.update(available=True, sarif=str(sarif_path),
-                  findings=len(results), files_scanned=scanned)
+    facts = module_facts(documents, module=Path(target).name or "target")
+    try:
+        # Best-effort to the end: a permission/disk error on the artifact writes is
+        # recorded as a tier reason, not raised — the same never-crash contract as a
+        # missing target or absent SDK.
+        sarif_path.write_text(json.dumps(_to_sarif(results), indent=2), encoding="utf-8")
+        facts_path.write_text(json.dumps(facts, indent=2), encoding="utf-8")
+    except OSError as exc:
+        status["reason"] = f"failed to write XAML artifacts: {exc}"
+        return status
+    status.update(available=True, sarif=str(sarif_path), facts=str(facts_path),
+                  findings=len(results), files_scanned=scanned,
+                  bindings=sum(len(d["bindings"]) for d in documents),
+                  resources=sum(len(d["resources"]) for d in documents))
     return status