feat: extraccion masiva footprint_aurgi (41 funcs + 4 types + stack Docker geo)

Extrae al registry funciones del proyecto interno footprint_aurgi:
- core (6): slugify_ascii, normalize_for_join, cp_provincia_es, infer_provincia_from_cp, safe_read_csv_fallback, csv_to_parquet_duckdb
- geo puras (7): haversine_km, point_in_ring, point_in_polygon, point_in_polygons_bbox, polygon_bbox, extent_with_padding, distance_bucket
- geo I/O (4): load_geojson_polygons, load_boundary_gdf, add_basemap_osm, add_basemap_with_timeout
- valhalla client (4): valhalla_route, valhalla_isochrone, valhalla_isochrones_async, valhalla_matrix_1_to_n
- datascience stats (7): trimmed_mean, geometric_mean, detect_distribution_type, best_central_tendency, summary_stats, kde_density_levels, alpha_shape_concave_hull
- datascience fuzzy (3): fuzzy_merge_adaptive (rapidfuzz), words_to_dataset, remove_words_from_column
- datascience viz (2): plot_kde_2d, plot_heatmap_log
- infra (4): compress_pdf_ghostscript, render_table_page_pdfpages, add_header_logo, osm2pgsql_ingest
- pipelines (4): setup_geo_stack_docker, compute_centers_reachability, generate_isochrones_by_zone, count_points_per_zone
- types geo (4): LonLat, BBox, IsochroneRequest, Centro

Incluye:
- apps/footprint_geo_stack/ (PostGIS + Martin + Valhalla via docker-compose)
- 131/132 tests pasan (1 skip esperado: osm2pgsql en PATH)
- Issue tracker dev/issues/0052-footprint-aurgi-extraction.md
- Atribucion uniforme: source_repo internal:footprint_aurgi, source_license internal-aurgi
- Build con 9 agentes en paralelo (8 wave 1 + 1 wave 2 pipelines)

Tambien commitea trabajo previo no commiteado: aggregate_extraction_results, chunk_with_overlap, clean_pdf_text, merge_entity_aliases, extract_graph_gliner2, extract_relations_mrebel, extract_triples_spacy_es, gliner2/mrebel/marianmt/rebel/spacy_es load_model, parse_rebel_output, translate_es_to_en, issue 0050/0051.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

python/functions/infra/tests/test_add_header_logo.py

@@ -0,0 +1,45 @@
+"""Tests para add_header_logo."""
+from __future__ import annotations
+
+from pathlib import Path
+
+import matplotlib
+matplotlib.use("Agg")
+import numpy as np
+import pytest
+
+
+def test_figura_nueva_con_imagen_zeros_no_lanza_excepcion():
+    """figura nueva con imagen zeros no lanza excepcion"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.add_header_logo import add_header_logo
+    import matplotlib.pyplot as plt
+
+    fig, ax = plt.subplots(figsize=(11.69, 8.27))
+    image = np.zeros((50, 200, 3), dtype=np.uint8)
+
+    # Should not raise
+    add_header_logo(fig, image)
+    plt.close(fig)
+
+
+def test_axes_de_logo_tiene_axis_off():
+    """axes de logo tiene axis off"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.add_header_logo import add_header_logo
+    import matplotlib.pyplot as plt
+
+    fig, ax = plt.subplots(figsize=(11.69, 8.27))
+    initial_axes_count = len(fig.axes)
+    image = np.zeros((10, 10, 3), dtype=np.uint8)
+
+    add_header_logo(fig, image, x=0.88, y=0.905, width=0.08, height=0.08)
+
+    # A new axes should have been added
+    assert len(fig.axes) == initial_axes_count + 1
+    logo_ax = fig.axes[-1]
+    # axis("off") disables both x and y axis visibility
+    assert not logo_ax.axison
+    plt.close(fig)

python/functions/infra/tests/test_compress_pdf_ghostscript.py

@@ -0,0 +1,62 @@
+"""Tests para compress_pdf_ghostscript."""
+from __future__ import annotations
+
+import shutil
+import tempfile
+from pathlib import Path
+
+import pytest
+
+
+def _make_simple_pdf(path: Path) -> None:
+    """Create a minimal valid PDF using fpdf2."""
+    try:
+        from fpdf import FPDF
+        pdf = FPDF()
+        pdf.add_page()
+        pdf.set_font("Helvetica", size=12)
+        pdf.cell(200, 10, text="Test PDF for ghostscript compression", ln=True)
+        pdf.output(str(path))
+    except ImportError:
+        # Fallback: write a minimal PDF manually
+        content = (
+            b"%PDF-1.4\n"
+            b"1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n"
+            b"2 0 obj\n<< /Type /Pages /Kids [3 0 R] /Count 1 >>\nendobj\n"
+            b"3 0 obj\n<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] >>\nendobj\n"
+            b"xref\n0 4\n0000000000 65535 f \n0000000009 00000 n \n"
+            b"0000000068 00000 n \n0000000125 00000 n \n"
+            b"trailer\n<< /Size 4 /Root 1 0 R >>\nstartxref\n210\n%%EOF\n"
+        )
+        path.write_bytes(content)
+
+
+def test_crea_pdf_temporal_y_comprime_retorna_bool_sin_excepcion():
+    """crea pdf temporal y comprime - retorna bool sin excepcion"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.compress_pdf_ghostscript import compress_pdf_ghostscript
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        pdf_path = Path(tmpdir) / "test.pdf"
+        _make_simple_pdf(pdf_path)
+        assert pdf_path.exists()
+        result = compress_pdf_ghostscript(pdf_path)
+        assert isinstance(result, bool)
+        # File must still exist regardless of whether compression happened
+        assert pdf_path.exists()
+
+
+def test_retorna_False_cuando_gs_no_esta_disponible(monkeypatch):
+    """retorna False cuando gs no esta disponible"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.compress_pdf_ghostscript import compress_pdf_ghostscript
+
+    monkeypatch.setattr("shutil.which", lambda x: None)
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        pdf_path = Path(tmpdir) / "test.pdf"
+        _make_simple_pdf(pdf_path)
+        result = compress_pdf_ghostscript(pdf_path)
+        assert result is False

python/functions/infra/tests/test_osm2pgsql_ingest.py

@@ -0,0 +1,38 @@
+"""Tests para osm2pgsql_ingest."""
+from __future__ import annotations
+
+import shutil
+import tempfile
+from pathlib import Path
+from unittest.mock import patch
+
+import pytest
+
+
+def test_lanza_FileNotFoundError_con_path_inexistente():
+    """lanza FileNotFoundError con path inexistente"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.osm2pgsql_ingest import osm2pgsql_ingest
+
+    with pytest.raises(FileNotFoundError):
+        osm2pgsql_ingest("/tmp/non_existent_file_that_does_not_exist.osm.pbf")
+
+
+def test_lanza_RuntimeError_si_osm2pgsql_no_esta_en_PATH():
+    """lanza RuntimeError si osm2pgsql no esta en PATH"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.osm2pgsql_ingest import osm2pgsql_ingest
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        pbf_path = Path(tmpdir) / "fake.osm.pbf"
+        # Create a dummy file so FileNotFoundError is not raised first
+        pbf_path.write_bytes(b"PBF")
+
+        # Skip test if osm2pgsql is actually in PATH (CI environment may have it)
+        if shutil.which("osm2pgsql") is not None:
+            pytest.skip("osm2pgsql is available in PATH; skipping RuntimeError test")
+
+        with pytest.raises(RuntimeError, match="osm2pgsql"):
+            osm2pgsql_ingest(pbf_path)

python/functions/infra/tests/test_render_table_page_pdfpages.py

@@ -0,0 +1,53 @@
+"""Tests para render_table_page_pdfpages."""
+from __future__ import annotations
+
+import tempfile
+from pathlib import Path
+
+import matplotlib
+matplotlib.use("Agg")
+import pytest
+
+
+def test_50_filas_con_max_rows_28_genera_2_paginas_en_pdf_no_vacio():
+    """50 filas con max_rows=28 genera 2 paginas en pdf no vacio"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.render_table_page_pdfpages import render_table_page_pdfpages
+    from matplotlib.backends.backend_pdf import PdfPages
+
+    rows = [[str(i), f"valor_{i}", f"extra_{i}"] for i in range(50)]
+    col_labels = ["ID", "Valor", "Extra"]
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        pdf_path = Path(tmpdir) / "test_table.pdf"
+        with PdfPages(str(pdf_path)) as pdf:
+            render_table_page_pdfpages(pdf, "Test Tabla", rows, col_labels, max_rows=28)
+
+        assert pdf_path.exists()
+        assert pdf_path.stat().st_size > 0
+
+        # Verify 2 pages were generated by reading PDF metadata
+        try:
+            from pypdf import PdfReader
+            reader = PdfReader(str(pdf_path))
+            assert len(reader.pages) == 2
+        except ImportError:
+            # If pypdf not available, just check file size
+            assert pdf_path.stat().st_size > 1000
+
+
+def test_0_filas_genera_1_pagina_vacia_sin_excepcion():
+    """0 filas genera 1 pagina vacia sin excepcion"""
+    import sys
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from infra.render_table_page_pdfpages import render_table_page_pdfpages
+    from matplotlib.backends.backend_pdf import PdfPages
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        pdf_path = Path(tmpdir) / "empty_table.pdf"
+        with PdfPages(str(pdf_path)) as pdf:
+            render_table_page_pdfpages(pdf, "Vacío", [], ["Col1", "Col2"])
+
+        assert pdf_path.exists()
+        assert pdf_path.stat().st_size > 0