Fix personnel extraction + header bugs on real Polres Cimahi sprint

This fixes 4 bugs found on a real Polres Cimahi SPRIN PDF:

1. satuan_penerbit captured the generic 'KEPOLISIAN NEGARA REPUBLIK
   INDONESIA' letterhead line instead of the most-specific issuing unit
   (e.g. RESOR CIMAHI / SEKTOR PADALARANG). Reworked find_satuan to
   scan for each level independently and return the deepest available.

2. find_dasar_list dropped numbered items when OCR put the marker on
   its own line ("1.\n Undang-Undang ..."). Refactored into
   _collect_numbered_section that buffers a bare-number line and uses
   the next non-empty line as the body. Also reused for the new
   find_untuk_list which extracts the previously-empty 'untuk' bullets.

3. find_perihal returned None for documents that use 'Pertimbangan'
   (very common in Polres-level sprint), forcing the LLM to guess.
   Added a regex fallback that picks up the first line under a
   'Pertimbangan' label so we keep extraction deterministic.

4. Personnel rows were emitted with only nama populated when
   PP-Structure detected a table but the column mapper degraded.
   Added a text-based fallback (extract_personnel_from_text) that
   scans raw OCR for <rank> + <8-digit NRP> patterns. Triggered when
   the PP-Structure result has fewer than 30% rank/NRP-bearing rows.
   Reviewed by raising the new PERSONNEL_TEXT_FALLBACK flag.

5. Validation now flags rows with neither pangkat nor nrp as
   INCOMPLETE_PERSONNEL_ROW, so the document routes to needs_review
   even when individual nrp/pangkat checks pass on empty values.

6. Added 'BRIGPOL' as a variant of BRIGADIR (seen in real scans).

Tests: 229 (was 203) — 26 new tests covering the regex fixes,
text-based personnel extractor, low-quality detector, validator
behaviour, and orchestrator wiring of the fallback path.

Co-Authored-By: adrian kuman firmansah <adriancuman@gmail.com>

tests/unit/test_orchestrator_llm.py

@@ -169,3 +169,92 @@ def test_orchestrator_marks_unavailable_when_llm_returns_none(
     out = run_pipeline(b"%PDF-1.4\n%fake")
     assert ReviewFlag.LLM_UNAVAILABLE in out.result.review_flags
     assert ReviewFlag.LLM_FALLBACK not in out.result.review_flags
+
+
+def test_orchestrator_uses_text_fallback_when_pp_structure_yields_only_names(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """When PP-Structure produces low-quality rows (e.g. only ``nama`` filled),
+    the orchestrator must run the text fallback against the raw OCR text and
+    raise the ``personnel_text_fallback`` flag.
+    """
+    monkeypatch.setenv("LLM_ENABLED", "false")
+    from ocr_sprint.config import get_settings
+
+    get_settings.cache_clear()
+
+    raw_text = (
+        "DAFTAR PERSONIL\n"
+        "1.\n"
+        "SRI WAHYUNI\n"
+        "AIPTU / 75070328\n"
+        "INTELKAM POLRES CIMAHI\n"
+        "2.\n"
+        "AGUNG LUKMAN\n"
+        "BRIPTU / 99030245\n"
+        "SAT INTELKAM\n"
+    )
+
+    # PP-Structure 'succeeded' but emitted name-only rows (the bug we saw on
+    # the real Polres Cimahi document).
+    from ocr_sprint.schemas.personnel import PersonnelEntry
+
+    pp_structure_low_quality = [
+        PersonnelEntry(nama="SRI WAHYUNI"),
+        PersonnelEntry(nama="AGUNG LUKMAN"),
+    ]
+    _stub_pipeline_stages(
+        monkeypatch,
+        raw_text=raw_text,
+        regex_header=HeaderFields(
+            nomor_sprint="Sprin/1/I/2025",
+            tanggal=date(2025, 1, 1),
+            satuan_penerbit="Polres Cimahi",
+            perihal="ok",
+            dasar=["UU 2/2002"],
+        ),
+    )
+    # Override extract_personnel to return the broken PP-Structure rows.
+    monkeypatch.setattr(orch_module, "extract_personnel", lambda _t: pp_structure_low_quality)
+
+    out = run_pipeline(b"%PDF-1.4\n%fake")
+    assert ReviewFlag.PERSONNEL_TEXT_FALLBACK in out.result.review_flags
+    # Fallback rows must carry pangkat + nrp (the whole point of the path).
+    assert all(r.pangkat and r.nrp for r in out.result.personel)
+    assert {r.pangkat for r in out.result.personel} == {"AIPTU", "BRIPTU"}
+
+
+def test_orchestrator_keeps_pp_structure_rows_when_quality_is_high(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Healthy PP-Structure output (rank+nrp present on most rows) must NOT
+    be replaced by the text fallback.
+    """
+    monkeypatch.setenv("LLM_ENABLED", "false")
+    from ocr_sprint.config import get_settings
+
+    get_settings.cache_clear()
+
+    from ocr_sprint.schemas.personnel import PersonnelEntry
+
+    healthy = [
+        PersonnelEntry(pangkat="AIPTU", nrp="11111111", nama="A"),
+        PersonnelEntry(pangkat="BRIPTU", nrp="22222222", nama="B"),
+        PersonnelEntry(pangkat="BRIPDA", nrp="33333333", nama="C"),
+    ]
+    _stub_pipeline_stages(
+        monkeypatch,
+        raw_text="ignored — should not be parsed",
+        regex_header=HeaderFields(
+            nomor_sprint="Sprin/1/I/2025",
+            tanggal=date(2025, 1, 1),
+            satuan_penerbit="Polres X",
+            perihal="ok",
+            dasar=["UU 2/2002"],
+        ),
+    )
+    monkeypatch.setattr(orch_module, "extract_personnel", lambda _t: healthy)
+
+    out = run_pipeline(b"%PDF-1.4\n%fake")
+    assert ReviewFlag.PERSONNEL_TEXT_FALLBACK not in out.result.review_flags
+    assert [r.nrp for r in out.result.personel] == ["11111111", "22222222", "33333333"]