test(witness): the JSON role map sees mml:math and figcaption (H3, red)

PM measured it on N200 Vegbygging:2024: 74 `mml:math` carrying 2 811
characters and 49 `figcaption`, and the witness counted 0 and 0. Two
independent causes and both are in this red:

- `count_sts_xml` takes every tag through `_local`, which strips a
  Clark-notation namespace AND a prefix; `count_sts_json` compared the
  raw string, so `mml:math` never reached `tag == "math"`.
- the publisher's JSON puts a figure's caption in `figcaption` under
  the `graphic`, not in the `fig/caption` NISO-STS writes. Measured
  over the eight deliveries on this machine: 430 `figcaption`.

Three tests. The JSON half of `sts-rikt.xml`'s family carries both
shapes as a committed fixture; the real N200 carries PM's four numbers
and skips where the corpus is absent; and the known-negative for
stripping a prefix is N101's 574 `tbx:` tags, whose local names name
no role -- a generalising rule measured against what it must NOT take.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

tests/fixtures/accounting/witness/sts-mml-and-figcaption.twin.json

@@ -0,0 +1,37 @@
+{
+ "productInfo": {"meta": {"productTitle": "Formula and figure caption"}},
+ "standardContent": {
+  "id": null, "tag": "#document", "a": {},
+  "c": [
+   {"e": 1, "t": null, "x": {"id": null, "tag": "standard", "a": {}, "c": [
+     {"e": 1, "t": null, "x": {"id": null, "tag": "body", "a": {}, "c": [
+       {"e": 1, "t": null, "x": {"id": null, "tag": "sec", "a": {}, "c": [
+         {"e": 1, "t": null, "x": {"id": null, "tag": "title", "a": {}, "c": [
+           {"e": 2, "t": "Vegdekker", "x": null}
+         ]}},
+         {"e": 1, "t": null, "x": {"id": null, "tag": "p", "a": {}, "c": [
+           {"e": 2, "t": "Kravet regnes som ", "x": null},
+           {"e": 1, "t": null, "x": {"id": null, "tag": "inline-formula", "a": {}, "c": [
+             {"e": 1, "t": null, "x": {"id": null, "tag": "mml:math", "a": {}, "c": [
+               {"e": 2, "t": "IRI < 2", "x": null}
+             ]}}
+           ]}}
+         ]}},
+         {"e": 1, "t": null, "x": {"id": null, "tag": "fig", "a": {}, "c": [
+           {"e": 1, "t": null, "x": {"id": null, "tag": "graphic", "a": {"href": "figur-85-1.png"}, "c": [
+             {"e": 1, "t": null, "x": {"id": null, "tag": "figcaption", "a": {}, "c": [
+               {"e": 1, "t": null, "x": {"id": null, "tag": "graphic-caption-label", "a": {}, "c": [
+                 {"e": 2, "t": "Figur 85-1", "x": null}
+               ]}},
+               {"e": 1, "t": null, "x": {"id": null, "tag": "graphic-caption-title", "a": {}, "c": [
+                 {"e": 2, "t": "Maalepunkter langs vegbanen.", "x": null}
+               ]}}
+             ]}}
+           ]}}
+         ]}}
+       ]}}
+     ]}}
+   ]}}
+  ]
+ }
+}

tests/test_accounting_gate.py

@@ -350,6 +350,45 @@ def test_the_sts_witness_counts_citations_formulas_and_figure_captions() -> None
         assert inventory.elements[role] > 0, role
 
 
+def test_the_json_role_map_reads_a_prefixed_tag_and_the_publishers_figcaption() -> None:
+    """H3, measured by PM on N200 2026-09-18: the delivery carries 74
+    `mml:math` and 49 `figcaption`, and the witness counted 0 and 0.
+
+    `count_sts_xml` takes every tag through `_local`, which strips both a
+    Clark-notation namespace and a prefix; `count_sts_json` compared the RAW
+    string, so `mml:math` never reached `tag == "math"`. And the publisher's
+    JSON puts a figure's caption in `figcaption` under the `graphic`, not in
+    the `fig/caption` NISO-STS writes -- measured over the eight deliveries on
+    this machine: 430 `figcaption`, 0 of them under a `caption`.
+
+    The fixture is the JSON half of `sts-rikt.xml`'s family, and both halves
+    of the defect are in it."""
+    twin = gate.FIXTURES / "witness" / "sts-mml-and-figcaption.twin.json"
+    counts = witness.count_sts_json(twin.read_bytes()).counts
+    assert counts["math"] == 1
+    assert counts["figure_caption"] == 1
+
+
+def test_a_prefixed_tag_that_names_no_role_stays_uncounted() -> None:
+    """The known-negative for stripping the prefix: N101 ships 574 `tbx:`
+    tags, and not one of their local names is a role. A rule that generalises
+    is measured against what it must NOT take."""
+    for tag in ("tbx:term", "tbx:definition", "tbx:note", "tbx:termEntry"):
+        assert witness._sts_role_json(witness._local(tag), "sec", "body") is None
+
+
+@pytest.mark.skipif(not gate.N200_DEFAULT.is_file(), reason="N200 is not on this machine")
+def test_the_json_role_map_counts_n200s_own_formulas_and_figure_captions() -> None:
+    """The same defect on the delivery it was found in, with PM's numbers.
+    Skipped where the corpus is absent, and then this file's own fixture is
+    the only thing holding the rule -- which is why both exist."""
+    counts = witness.count_sts_json(gate.N200_DEFAULT.read_bytes()).counts
+    assert counts["math"] == 74
+    assert counts["figure_caption"] == 49
+    assert counts["citation"] == 194
+    assert counts["figure"] == 49
+
+
 def test_the_two_sts_role_maps_are_written_twice_and_not_shared() -> None:
     """M-2: both STS witnesses went through ONE `_sts_role`, so row 5 could
     never see a hole in it. Two maps, each written for its own delivery."""