test(extract): reach extra-missing through the import probe

Both tests reached `extractor_extra_missing` through a `.docx`/`.xlsx`
filename, which works only while `_UNPARSED_OPTIONAL_EXTENSIONS` is non-empty.
Those types are about to gain a converter, which empties the set and makes the
membership branch unreachable -- the tests would have gone red for the right
reason at the worst moment, mid-series.

Repointed both at the import probe, the mechanism the pdf gate already uses and
the one path that stays reachable however many types gain parsers.

Measured negative control: without the probe the same call raises
`extractor_pdf_error`, so the probe is load-bearing and the test can still fail.

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

tests/test_error_codes.py

@@ -12,6 +12,7 @@ import hashlib
 import importlib.util
 import json
 import sqlite3
+import sys
 import urllib.error
 from pathlib import Path
 from typing import Any
@@ -344,12 +345,14 @@ def test_extractor_unknown() -> None:
     assert code_of(excinfo) == "extractor_unknown"
 
 
-def test_extractor_extra_missing() -> None:
-    # `docx` rather than `pdf`: the extra now ships a pdf parser, so the type
-    # that still has none is what proves this code is reachable. The pdf
-    # import-probe path is covered in tests/test_extract.py.
+def test_extractor_extra_missing(monkeypatch: pytest.MonkeyPatch) -> None:
+    # The import probe rather than a suffix: `docx` proved this code reachable
+    # only while the extra shipped no parser for it. Once it gains a converter,
+    # `_UNPARSED_OPTIONAL_EXTENSIONS` empties and the membership branch becomes
+    # unreachable — the probe is the path that survives.
+    monkeypatch.setitem(sys.modules, "pdfplumber", None)
     with pytest.raises(ExtractionError) as excinfo:
-        extract_text("doc.docx", b"binary")
+        extract_text("report.pdf", b"%PDF-1.4")
     assert code_of(excinfo) == "extractor_extra_missing"
 
 

tests/test_extract.py

@@ -89,13 +89,27 @@ def test_missing_extension_fails_fast() -> None:
     assert excinfo.value.code == "extractor_unknown"
 
 
-# --- fail-fast: [extract]-gated binary types the extra ships no parser for ---
+# --- fail-fast: an [extract]-gated type without the extra installed ---
 
 
-@pytest.mark.parametrize("name", ["doc.docx", "sheet.xlsx"])
-def test_optional_type_without_a_parser_fails_fast(name: str) -> None:
+def test_optional_type_without_the_extra_fails_fast(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """`extractor_extra_missing` reached through the import probe, not a suffix set.
+
+    This test used to reach the code through a `.docx` or `.xlsx` filename,
+    which sat in `_UNPARSED_OPTIONAL_EXTENSIONS` because the extra shipped no
+    parser for those types. That set is on its way to empty: once those types gain a converter,
+    a membership test can no longer raise this code at all, and a test pinned
+    to it would go red for the right reason at the worst moment.
+
+    The import probe is the durable path — it is how the gate actually works
+    (`extract.py`'s `_extract_pdf`), and it stays reachable no matter how many
+    types gain parsers.
+    """
+    monkeypatch.setitem(sys.modules, "pdfplumber", None)
     with pytest.raises(ExtractionError) as excinfo:
-        extract_text(name, b"binary")
+        extract_text("report.pdf", b"%PDF-1.4")
     assert excinfo.value.code == "extractor_extra_missing"
     # The error names the extra so the operator knows the remedy — never a
     # silent skip, never a bundled parser in core.