egutierrez
dabc945eda
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>
69 lines
2.3 KiB
Python
69 lines
2.3 KiB
Python
"""Traduce texto espanol a ingles usando MarianMT, frase a frase."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
from typing import Any
|
|
|
|
# Patron de split por oraciones: punto, exclamacion, interrogacion seguidos de espacio.
|
|
_SENTENCE_RE = re.compile(r"(?<=[.!?])\s+")
|
|
|
|
|
|
def translate_es_to_en(
|
|
text: str,
|
|
tokenizer: Any,
|
|
model: Any,
|
|
max_length: int = 512,
|
|
num_beams: int = 4,
|
|
) -> str:
|
|
"""Translate Spanish text to English, sentence by sentence.
|
|
|
|
Splits the input on sentence boundaries (after ``.``, ``!``, ``?``),
|
|
translates each sentence independently, and rejoins with a single space.
|
|
Processing sentence by sentence preserves proper nouns (names, companies,
|
|
locations) better than passing the full paragraph in a single call, because
|
|
the translation model can focus on shorter context windows.
|
|
|
|
Args:
|
|
text: Spanish text to translate. Can be a single sentence or a
|
|
multi-sentence paragraph.
|
|
tokenizer: MarianMT tokenizer loaded with ``marianmt_es_en_load_model``.
|
|
model: MarianMT model loaded with ``marianmt_es_en_load_model``.
|
|
max_length: Maximum token length for each sentence during tokenization
|
|
and generation. Sentences longer than this are truncated.
|
|
num_beams: Number of beams for beam search. Higher = better quality,
|
|
slower. Default 4 is a good tradeoff.
|
|
|
|
Returns:
|
|
Translated English text. Sentences joined with a single space.
|
|
Returns an empty string if ``text`` is empty or whitespace-only.
|
|
|
|
Raises:
|
|
RuntimeError: if model.generate fails (propagated from transformers).
|
|
"""
|
|
if not text or not text.strip():
|
|
return ""
|
|
|
|
sentences = _SENTENCE_RE.split(text.strip())
|
|
sentences = [s.strip() for s in sentences if s.strip()]
|
|
if not sentences:
|
|
return ""
|
|
|
|
translated_parts: list[str] = []
|
|
for sentence in sentences:
|
|
inputs = tokenizer(
|
|
sentence,
|
|
return_tensors="pt",
|
|
max_length=max_length,
|
|
truncation=True,
|
|
)
|
|
generated = model.generate(
|
|
**inputs,
|
|
num_beams=num_beams,
|
|
max_length=max_length,
|
|
)
|
|
decoded = tokenizer.decode(generated[0], skip_special_tokens=True)
|
|
translated_parts.append(decoded.strip())
|
|
|
|
return " ".join(translated_parts)
|