Source code for energy_data_retrieval.wind_catalogue.oem_tables

"""Stage visually reviewed OEM columns with explicit revision and unit boundaries.

This is a transcription adapter, not OCR. Original bytes must match the review;
model lists are copied from table headers, never expanded from platform ranges.
"""

from __future__ import annotations

import copy
import hashlib
import math
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 = ("windey_english_brochure_202206",)
SCALARS = (
    "rated_power_kw",
    "rotor_diameter_m",
    "blade_length_m",
    "blade_count",
    "cut_in_m_s",
    "rated_wind_speed_m_s",
)


[docs] def stage_tables( review: dict[str, Any], original: bytes, existing: list[dict[str, Any]], *, now: str ) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]: """Return new models and explicit holds for existing configurations. Generator RPM is never rotor RPM, converter kVA is never turbine kW, and option ranges never become a scalar or a synthetic configuration. Existing identities require a separate revision review before enrichment. """ if hashlib.sha256(original).hexdigest() != review["sha256"]: raise ValueError("Original OEM checksum mismatch") if not review.get("revision") or not review.get("source_id"): raise ValueError("OEM revision and source are required") prior = {(r.get("manufacturer"), r.get("model")) for r in existing} result, ledger = [], [] seen: set[str] = set() pages: set[int] = set() for table in review["tables"]: page = table["pdf_page"] if type(page) is not int or page < 1 or page in pages: raise ValueError("Duplicate or invalid OEM page") pages.add(page) models = [c["model"] for c in table["columns"]] if not models or models != table["expected_models"]: raise ValueError("Incomplete or reordered OEM columns") for column, raw in enumerate(table["columns"], 1): model = raw["model"] if not model or model in seen: raise ValueError("Duplicate or missing exact model") seen.add(model) for field in SCALARS: value = raw[field] if type(value) not in (int, float) or not math.isfinite(value) or value <= 0: raise ValueError("Invalid explicit OEM scalar") # Component ratings have their own units and boundaries. Validate # optional observations without promoting them to turbine scalars. for field in ( "generator_power_kw", "generator_voltage_v", "generator_rated_speed_rpm", "single_blade_mass_t", "hub_mass_t", "nacelle_mass_t", ): value = raw.get(field) if value is not None and ( type(value) not in (int, float) or not math.isfinite(value) or value <= 0 ): raise ValueError("Invalid OEM component quantity") for field, size in ( ("converter_power_kva_grid_turbine", 2), ("converter_current_a_grid_turbine", 2), ("hub_dimensions_m", 3), ("nacelle_dimensions_m", 3), ): values = raw.get(field) if values is not None and ( not isinstance(values, list) or len(values) != size or any( type(v) not in (int, float) or not math.isfinite(v) or v <= 0 for v in values ) ): raise ValueError("Invalid OEM component vector") for field in ( "cut_out_range_m_s", "hub_height_range_m", "converter_frequency_range_hz", ): values = raw[field] if ( len(values) != 2 or any(type(v) not in (int, float) or not math.isfinite(v) for v in values) or not 0 < values[0] <= values[1] ): raise ValueError("Invalid OEM option range") locator = ( f"PDF page {page}; printed {table['printed_pages']}; model column {column}: {model}" ) if ("Windey", model) in prior: ledger.append( dict( model=model, decision="existing_revision_review", locator=locator, observation=raw, ) ) continue variant = review["revision"] ext = dict( oem_table_observations=[ dict( source_id=review["source_id"], locator=locator, revision=variant, values=copy.deepcopy(raw), ) ], air_density_kg_m3=None, operating_mode=None, restart_speed_m_s=None, certification_identifier=None, warranty_years=None, design_life_years=None, numerical_curves=None, exact_component_models=None, installed_project_configuration=None, completeness=( "Partial published configuration; ranges are options, not installed values" ), performance_status="OEM specifications; not independently validated performance", ) values = dict( record_id=stable_id("equipment", "Windey", model, variant), entity_type="equipment", record_scope="model", name=f"Windey {model}", manufacturer="Windey", model=model, variant=variant, source_revision=variant, equipment_category="wind_turbine", capacity_scope=( "Exact brochure model; installed revision and project application unknown" ), rated_power_conditions=( "OEM nominal turbine rating; density and operating mode unspecified" ), extensions_json=canonical_json(ext), **{k: raw[k] for k in SCALARS}, notes=( "Original units retained in dated table observation. " "No independent performance validation." ), ) row = evidence_record(values, source_id=review["source_id"], now=now, locator=locator) result.append(row) ledger.append( dict(model=model, record_id=row["record_id"], decision="addition", locator=locator) ) return result, ledger