"""Stage explicitly classified batteries from the EA September 2024 pipeline."""
from __future__ import annotations
import csv
import hashlib
import io
import math
from typing import Any
HEADERS = [
"Developer",
"Project",
"Fuel",
"Technology",
"Megawatts",
"Capacity factor",
"Approx annual gigawatt-hours",
"Earliest commissioning year",
"Status",
"Grid connected?",
"Island",
]
[docs]
def parse_nz_pipeline(content: bytes) -> list[dict[str, Any]]:
"""Keep row locators and dated planning stages; never infer storage MWh or COD.
No identities are merged. The 2024 file can contain superseded ratings,
multi-phase aggregates and projects already operating in newer sources.
"""
reader = csv.DictReader(io.StringIO(content.decode("utf-8-sig")))
if reader.fieldnames != HEADERS:
raise ValueError("Unreviewed NZ pipeline header")
result = []
seen = set()
for line, row in enumerate(reader, 2):
if None in row or any(v is None for v in row.values()):
raise ValueError(f"Malformed CSV row {line}")
if row["Technology"] != "Chemical battery energy storage system":
continue
if row["Fuel"] != "Electrical energy":
raise ValueError(f"Conflicting battery classification at row {line}")
identity = (row["Developer"], row["Project"])
if not all(identity) or identity in seen:
raise ValueError(f"Missing or duplicate candidate identity at row {line}")
seen.add(identity)
mw = float(row["Megawatts"])
if not math.isfinite(mw) or mw <= 0:
raise ValueError(f"Invalid battery MW at row {line}")
if row["Status"] not in {"Committed", "Actively pursued", "Other"}:
raise ValueError(f"Unreviewed planning status at row {line}")
year = int(row["Earliest commissioning year"])
if not 1900 <= year <= 2200 or row["Grid connected?"] not in {"Y", "N"}:
raise ValueError(f"Invalid planning year or grid flag at row {line}")
result.append(
{
"source_row": line,
"developer": identity[0],
"project": identity[1],
"power_mw": mw,
"earliest_commissioning_year": year,
"planning_status": row["Status"],
"grid_connected_flag": row["Grid connected?"],
"island": row["Island"],
"snapshot_date": "2024-09-12",
"source_sha256": hashlib.sha256(content).hexdigest(),
}
)
return result
[docs]
def parse_transpower_pipeline(content: bytes) -> list[dict[str, Any]]:
"""Stage October 2026 forward BESS rows, including unnamed rows for review.
This adapter grants no source reuse rights. Connection stages are never
physical construction/operating statuses; Max MW is not battery nameplate.
Completed-sheet reconciliation is deliberately outside this forward adapter.
"""
from datetime import datetime
from openpyxl import load_workbook
book = load_workbook(io.BytesIO(content), read_only=True, data_only=True)
expected = [
"Project ID",
"Parent Project ID",
"Customer",
"Project name",
"Region",
"Connection location (substation or circuit)",
"Max MW",
"Connection voltage",
"Technology",
"Transpower stage",
"Status Flag",
"Stage % complete",
"Status",
"Consented",
"Estimated connection livening date",
]
try:
sheet = book["Forward Pipeline"]
iterator = sheet.iter_rows(values_only=True)
if list(next(iterator)[:15]) != expected:
raise ValueError("Unreviewed Transpower header")
result = []
seen = set()
for line, values in enumerate(iterator, 2):
row = dict(zip(expected, values[:15], strict=True))
if row["Technology"] != "BESS":
continue
key = row["Project ID"]
if key is None or str(key) in seen:
raise ValueError(f"Missing or duplicate Transpower ID at row {line}")
seen.add(str(key))
for name, value in row.items():
if isinstance(value, datetime):
row[name] = value.date().isoformat()
row["Project ID"] = str(key)
parent = row["Parent Project ID"]
row["Parent Project ID"] = str(parent) if parent is not None else None
result.append(
{
"source_sheet": "Forward Pipeline",
"source_row": line,
"reported_fields": row,
"identity_review_required": not bool(row["Customer"] and row["Project name"]),
"source_sha256": hashlib.sha256(content).hexdigest(),
}
)
return result
finally:
book.close()