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>
2026-05-04 23:35:22 +02:00
parent f73ea072bd
commit faac610745
193 changed files with 13146 additions and 3 deletions
@@ -0,0 +1,63 @@
+"""Compress a PDF file in-place using Ghostscript."""
+from __future__ import annotations
+
+import shutil
+import subprocess
+import tempfile
+from pathlib import Path
+
+
+def compress_pdf_ghostscript(
+    pdf_path: "str | Path",
+    quality: str = "screen",
+) -> bool:
+    """Compress a PDF in-place using Ghostscript.
+
+    Runs gs with downsampling (96 dpi color/gray, 200 dpi mono). Replaces the
+    original file only when the compressed output is strictly smaller. Returns
+    True if the file was replaced, False if gs is not available, the file does
+    not exist, compression failed, or the output was not smaller.
+
+    Args:
+        pdf_path: Path to the PDF file to compress (modified in-place on success).
+        quality: Ghostscript PDFSETTINGS profile. One of "screen", "ebook",
+                 "printer", "prepress".
+
+    Returns:
+        True if the file was compressed and replaced, False otherwise.
+    """
+    path = Path(pdf_path)
+    gs = shutil.which("gs")
+    if not gs or not path.exists():
+        return False
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        compressed = Path(tmpdir) / "compressed.pdf"
+        cmd = [
+            gs,
+            "-sDEVICE=pdfwrite",
+            "-dCompatibilityLevel=1.4",
+            f"-dPDFSETTINGS=/{quality}",
+            "-dDownsampleColorImages=true",
+            "-dDownsampleGrayImages=true",
+            "-dDownsampleMonoImages=true",
+            "-dColorImageResolution=96",
+            "-dGrayImageResolution=96",
+            "-dMonoImageResolution=200",
+            "-dNOPAUSE",
+            "-dQUIET",
+            "-dBATCH",
+            f"-sOutputFile={compressed}",
+            str(path),
+        ]
+        try:
+            subprocess.run(cmd, check=True, capture_output=True)
+        except subprocess.CalledProcessError:
+            return False
+
+        if compressed.exists() and compressed.stat().st_size < path.stat().st_size:
+            import shutil as _sh
+            _sh.copy2(str(compressed), str(path))
+            return True
+
+    return False