feat(extract): implement pdf behind the [extract] extra with pdfplumber

Order G2a. Populates the optional `[extract]` extra for the first time with
one parser, `pdfplumber>=0.11.10,<0.12` (MIT), and wires `pdf` through it.
The default install is untouched: exactly one runtime dependency, stdlib
otherwise, enforced by test_packaging.py.

The gate for `pdf` becomes an import probe rather than a frozenset membership
test, exactly as extract.py's docstring had promised. The rejection does not
change: without the extra, `pdf` still raises `extractor_extra_missing` with
the same message. That behaviour is asserted UNCONDITIONALLY via a sys.modules
monkeypatch, so it holds on machines where the parser is installed too — a
skip would have preserved nothing there. Verified in a clean venv without the
extra: 589 passed, 7 skipped; with it, 596 passed.

`docx`/`xlsx` are unchanged and still fail fast — the extra names exactly what
it ships.

The parser choice was forced by measurement, not preference (b73dd9d,
docs/2026-08-21-g2-pdf-extraction-measurement.md): on a real requirement table
pdfplumber keeps 4 of 4 rows with label and value on one line, where pypdf,
pdfminer.six and pymupdf each keep 0 of 4. pymupdf is additionally out on
licence (AGPL-3.0), which an MIT package must not push onto a consumer.

Three facts from that measurement are now carried in code rather than in a
report:

- Extracted text is pinned to an exact transitive parser version
  (pdfplumber pins pdfminer.six==20260107; date-stamped, no stability
  contract). tests/test_extract.py freezes the expected text of a committed
  hand-written fixture so a parser upgrade breaks something visible instead of
  drifting silently. Reasoning at the declaration site and in
  tests/fixtures/README.md.
- Determinism within a version is now held by a test, not only measured once.
- Drawn content does not survive extraction. Every pdf extraction emits the
  new `ExtractionWarning`: figures have no text to recover, so a bundle built
  from drawn documents is incomplete by construction. Stated categorically
  rather than detected — deciding "is there a figure here" is the layout
  heuristic G2b declined.

Two new error codes, both mirroring existing patterns: `extractor_empty_pdf`
(a scanned/image-only PDF, refused rather than persisted as an empty concept)
and `extractor_pdf_error` (parser failure wrapped, never leaked).

Structured table recovery (G2b) is NOT implemented and is documented as out of
scope: two independent parsers return the same wrong shape, so the breakage is
document geometry, not a library choice. PDFs enter as prose.

Also corrects an install promise this change would otherwise have published:
the README no longer presents a bare `pip install 'llm-ingestion-okf[extract]'`
as working, because the package is not on an index.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HtNhsdHnMGtMi7U2mvMU8z

tests/test_extract.py

@@ -9,9 +9,24 @@ call — it is pure, deterministic plumbing.
 
 from __future__ import annotations
 
+import importlib.util
+import sys
+from pathlib import Path
+
 import pytest
 
-from llm_ingestion_okf import ExtractionError, extract_text
+from llm_ingestion_okf import ExtractionError, ExtractionWarning, extract_text
+
+FIXTURES = Path(__file__).parent / "fixtures"
+
+# The parser-dependent tests below need the optional extra, so they are skipped
+# without it — an optional extra that forced its parser on every test run would
+# not be optional. The behaviour that must survive EITHER WAY is the rejection,
+# and that one is asserted unconditionally above via the import probe.
+requires_extract = pytest.mark.skipif(
+    importlib.util.find_spec("pdfplumber") is None,
+    reason="the optional [extract] extra is not installed",
+)
 
 # --- core extractors: happy path (a fixture per type) ---
 
@@ -74,11 +89,11 @@ def test_missing_extension_fails_fast() -> None:
     assert excinfo.value.code == "extractor_unknown"
 
 
-# --- fail-fast: [extract]-gated binary types without the extra ---
+# --- fail-fast: [extract]-gated binary types the extra ships no parser for ---
 
 
-@pytest.mark.parametrize("name", ["doc.pdf", "doc.docx", "sheet.xlsx"])
-def test_optional_type_without_extra_fails_fast(name: str) -> None:
+@pytest.mark.parametrize("name", ["doc.docx", "sheet.xlsx"])
+def test_optional_type_without_a_parser_fails_fast(name: str) -> None:
     with pytest.raises(ExtractionError) as excinfo:
         extract_text(name, b"binary")
     assert excinfo.value.code == "extractor_extra_missing"
@@ -87,6 +102,80 @@ def test_optional_type_without_extra_fails_fast(name: str) -> None:
     assert "extract" in str(excinfo.value)
 
 
+def test_pdf_without_the_extra_installed_keeps_the_same_rejection(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """The gate became an import probe; the rejection did not change.
+
+    Setting the module to None in sys.modules is what CPython treats as a
+    failed import, so this exercises the uninstalled path REGARDLESS of
+    whether the extra is installed in the running environment — a skip would
+    have preserved nothing on the machine where the parser is present.
+    """
+    monkeypatch.setitem(sys.modules, "pdfplumber", None)
+    with pytest.raises(ExtractionError) as excinfo:
+        extract_text("doc.pdf", b"%PDF-1.4")
+    assert excinfo.value.code == "extractor_extra_missing"
+    assert "extract" in str(excinfo.value)
+
+
+# --- pdf: the [extract] parser (pdfplumber) ---
+
+# The expected text is frozen against a committed fixture ON PURPOSE. Extraction
+# is deterministic within a parser version and NOT guaranteed across one
+# (pdfplumber pins pdfminer.six==20260107 exactly; pdfminer.six ships
+# date-stamped releases with no stability contract). This literal is what makes
+# a parser upgrade break something visible instead of drifting silently.
+KRAV_TEXT = "Krav til helning på utkilingen\n60 og 70 1:15"
+
+
+@requires_extract
+def test_pdf_extracts_text_with_label_and_value_on_one_line() -> None:
+    data = (FIXTURES / "two-line-krav.pdf").read_bytes()
+    with pytest.warns(ExtractionWarning):
+        assert extract_text("krav.pdf", data) == KRAV_TEXT
+
+
+@requires_extract
+def test_pdf_extraction_is_byte_stable_across_calls() -> None:
+    """Determinism is a promise this library already makes; hold it here too."""
+    data = (FIXTURES / "two-line-krav.pdf").read_bytes()
+    with pytest.warns(ExtractionWarning):
+        first = extract_text("krav.pdf", data)
+        second = extract_text("krav.pdf", data)
+    assert first == second
+
+
+@requires_extract
+def test_pdf_extraction_warns_that_drawn_content_is_not_recovered() -> None:
+    """Figures are vector drawings: only the caption survives leg 2.
+
+    Categorically true of text extraction, so it is stated as a warning on
+    every PDF rather than guessed at per document — detecting "is there a
+    figure here" would be exactly the layout heuristic this order declined.
+    """
+    data = (FIXTURES / "two-line-krav.pdf").read_bytes()
+    with pytest.warns(ExtractionWarning, match="figures"):
+        extract_text("krav.pdf", data)
+
+
+@requires_extract
+def test_pdf_with_no_text_layer_fails_fast() -> None:
+    """A scanned PDF yields nothing; an empty concept would be a silent skip."""
+    data = (FIXTURES / "no-text-layer.pdf").read_bytes()
+    with pytest.raises(ExtractionError) as excinfo:
+        extract_text("scan.pdf", data)
+    assert excinfo.value.code == "extractor_empty_pdf"
+
+
+@requires_extract
+def test_corrupt_pdf_fails_fast_typed() -> None:
+    """Never a leaked pdfminer exception — the "always typed" doctrine holds."""
+    with pytest.raises(ExtractionError) as excinfo:
+        extract_text("broken.pdf", b"not a pdf at all")
+    assert excinfo.value.code == "extractor_pdf_error"
+
+
 # --- fail-fast: corrupt (non-UTF-8) bytes on a text type ---