Source code for energy_data_retrieval.pv_catalogue.cesena
"""Stage geometry-free Valle del Savio ground-PV inventory features for review."""
from __future__ import annotations
import json
import math
import re
from typing import TypedDict
from .sam import verify_sha256
LAYER = "Cesena:OD_VG_FOTOVOLTAICO_SDO_preview"
FIELDS = {"OBJECTID", "TIPO_AUTO", "POSIZ", "ANNO", "POTENZA", "U_M_POT", "COMUNE"}
[docs]
class CesenaGroundPvObservation(TypedDict):
"""Source feature fields with the reported kW basis left unspecified."""
object_id: int
source_type: str
municipality_code: str
reported_year: int | None
power_native: str | None
reported_kw_ac_dc_unspecified: float | None
[docs]
def read_cesena_ground_pv_page(
content: bytes,
*,
sha256: str,
offset: int,
limit: int,
) -> tuple[int, list[CesenaGroundPvObservation]]:
"""Read a bounded WFS 2.0 page of the published ground-PV layer projection.
Project FIELDS, sort by OBJECTID ascending and filter POSIZ to A TERRA.
Source feature IDs and years do not establish plant identity or operation.
The service includes municipality codes outside Cesena. Keep them literal.
"""
if len(content) > 1_000_000 or offset < 0 or not 1 <= limit <= 100:
raise ValueError("Outside bounded Cesena page scope")
verify_sha256(content, sha256)
page = json.loads(content)
if not isinstance(page, dict) or page.get("type") != "FeatureCollection":
raise ValueError("Invalid Cesena feature collection")
total = page.get("numberMatched")
returned = page.get("numberReturned")
features = page.get("features")
if (
type(total) is not int
or total < 0
or page.get("totalFeatures") != total
or type(returned) is not int
or not isinstance(features, list)
or returned != len(features)
or returned != min(limit, max(0, total - offset))
):
raise ValueError("Cesena page counts do not match scope")
rows: list[CesenaGroundPvObservation] = []
previous = 0
for feature in features:
if (
not isinstance(feature, dict)
or feature.get("type") != "Feature"
or "geometry" not in feature
or feature["geometry"] is not None
):
raise ValueError("Geometry-free Cesena feature required")
row = feature.get("properties")
if not isinstance(row, dict) or row.keys() != FIELDS:
raise ValueError("Cesena projected fields changed")
identifier = row["OBJECTID"]
if (
type(identifier) is not int
or identifier <= previous
or feature.get("id") != f"{LAYER.split(':')[1]}.{identifier}"
):
raise ValueError("Invalid, unsorted or duplicate Cesena feature ID")
previous = identifier
source_type = row["TIPO_AUTO"]
code = row["COMUNE"]
year = row["ANNO"]
if (
row["POSIZ"] != "A TERRA"
or source_type not in ("UFFICIO", "SITONLINE", "CATASTO")
or not isinstance(code, str)
or re.fullmatch(r"[A-Z][0-9]{3}", code) is None
or (year is not None and (type(year) is not int or not 1900 <= year <= 2100))
or row["U_M_POT"] != "KW"
):
raise ValueError("Cesena technology-layer attributes or units changed")
native = row["POTENZA"]
power = None
if native is not None:
if (
not isinstance(native, str)
or re.fullmatch(r"[0-9]+(?:,[0-9]+)?", native.strip()) is None
):
raise ValueError("Ambiguous Cesena power literal")
power = float(native.strip().replace(",", "."))
if not math.isfinite(power):
raise ValueError("Nonfinite Cesena power")
rows.append(
{
"object_id": identifier,
"source_type": source_type,
"municipality_code": code,
"reported_year": year,
"power_native": native,
"reported_kw_ac_dc_unspecified": power,
}
)
return total, rows