Source code for energy_data_retrieval.wind_catalogue.blade_tables

"""Stage complete reviewed blade columns without inventing turbine compatibility."""

from __future__ import annotations

import hashlib
import json
import math
from datetime import date
from typing import Any

from energy_data_retrieval.pv_catalogue.catalogue import canonical_json

from .catalogue import stable_id
from .gppd import evidence_record

REFERENCE_IDS = (
    "crrc_times_blades_2x_20210722",
    "crrc_times_blades_3x_20220303",
    "crrc_times_blades_4x6x_20220303",
)


[docs] def stage_blade_table( review: dict[str, Any], original: bytes | None, existing: list[dict[str, Any]], *, now: str ) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]: """Keep repeated model names distinct only by explicitly printed configuration. A model's MW prefix is an application class, not a component electrical rating. Root pitch-circle diameter is not rotor diameter. Certification text is an OEM claim with no independently verified certificate, date or validity inferred. """ if original is None: if review.get("sha256") is not None or review.get("original_availability") != ( "unavailable_http_403_search_rendered_table_reviewed" ): raise ValueError("Unavailable original bytes require explicit acquisition status") elif hashlib.sha256(original).hexdigest() != review.get("sha256"): raise ValueError("Original blade table checksum mismatch") if not review.get("source_id") or not review.get("manufacturer") or not review.get("revision"): raise ValueError("Source, manufacturer and revision required") if date.fromisoformat(review["published_at"]) > date.fromisoformat(now[:10]): raise ValueError("Future publication") columns = review["columns"] expected = review["expected_configurations"] keys = [(c["model"], c["wind_class"], c["root_pitch_circle_diameter_m"]) for c in columns] if not keys or keys != [tuple(k) for k in expected] or len(keys) != len(set(keys)): raise ValueError("Incomplete, reordered or duplicate blade configuration partition") prior = {(r.get("manufacturer"), r.get("model")) for r in existing} records, ledger = [], [] for column, raw in enumerate(columns, 1): if set(raw) != { "model", "wind_class", "blade_length_m", "root_pitch_circle_diameter_m", "certification_claim_raw", }: raise ValueError("Only printed blade cells supported; no inferred turbine fields") if not raw["model"] or not raw["wind_class"]: raise ValueError("Exact model and explicit wind class required") for field in ("blade_length_m", "root_pitch_circle_diameter_m"): value = raw[field] if type(value) not in (int, float) or not math.isfinite(value) or value <= 0: raise ValueError("Positive finite blade geometry required") if raw["root_pitch_circle_diameter_m"] >= raw["blade_length_m"]: raise ValueError("Root pitch-circle diameter must be below blade length") claim = raw["certification_claim_raw"] if claim is not None and not isinstance(claim, str): raise ValueError("Certification claim must be text or null") locator = f"Section 2 product parameter table; model column {column}: {raw['model']}" if (review["manufacturer"], raw["model"]) in prior: ledger.append( dict(model=raw["model"], locator=locator, decision="existing_revision_review") ) continue variant = ( f"{review['revision']}; wind class {raw['wind_class']}; " f"root pitch-circle {raw['root_pitch_circle_diameter_m']:g} m" ) ext = dict( blade_table_observations=[ dict( source_id=review["source_id"], locator=locator, publication_date=review["published_at"], revision=review["revision"], original_cells=raw.copy(), original_units=dict(blade_length_m="m", root_pitch_circle_diameter_m="m"), normalization=( "Identity in metres; printed model and wind-class strings retained" ), ) ], root_pitch_circle_diameter_m=raw["root_pitch_circle_diameter_m"], wind_class_reported=raw["wind_class"], certification_claim=None if claim in {None, "", "/", "-"} else claim, certification_identifier=None, certification_validity=None, turbine_application=None, region=None, material_for_this_model=None, numerical_curves=None, completeness="Complete published table column; partial component specifications", performance_status="OEM specification claim; not independently validated performance", ) row = evidence_record( dict( record_id=stable_id("equipment", review["manufacturer"], raw["model"], variant), entity_type="equipment", record_scope="configuration", name=f"{review['manufacturer']} {raw['model']}", manufacturer=review["manufacturer"], model=raw["model"], variant=variant, equipment_category="blade", blade_length_m=raw["blade_length_m"], source_revision=review["revision"], extensions_json=canonical_json(ext), capacity_scope="Blade configuration; model MW prefix is not component rated power", notes=( "No exact turbine compatibility or project installation established. " "No rating, rotor diameter, certificate validity or material inferred. " "Blade-root pitch-circle diameter is retained only as component geometry." ), ), source_id=review["source_id"], now=now, locator=locator, ) evidence = json.loads(row["evidence_json"]) for value in evidence.values(): value.update(publication_date=review["published_at"], revision=review["revision"]) evidence["blade_length_m"].update(original_unit="m", normalization="identity") row["evidence_json"] = canonical_json(evidence) records.append(row) ledger.append( dict( model=raw["model"], variant=variant, record_id=row["record_id"], locator=locator, decision="addition", ) ) return records, ledger