PyCS/labels/flat_moth_label_provider/lepiforum_reader.py

#!/usr/bin/env python
if __name__ != '__main__': raise Exception("Do not import me!")

import csv
import json

from argparse import ArgumentParser
from collections import namedtuple

columns = ["KR-Nr.", "Überfamilie", "Familie", "Unterfamilie", "Tribus", "Gattung", "Art", "Seltenheit"]
Row = namedtuple("Row", "kr superfamily family subfamily tribus genus species rarity")


class ClassName(namedtuple("ClassName", "genus species")):
	__slots__ = ()
	alt = {
		"mesapamea_spec": "mesapamea_secalis",
		"amphipyra_pyramidea_-_berberea": "amphipyra_pyramidea",
		"aplocera_plagiata_-_efformata": "aplocera_plagiata",
		"chlroclystis_v-ata": "chloroclystis_v-ata",
		"epirrita_autumnata_-_dilutata_-_christyi": "epirrita_autumnata",
		"noctua_janthina_-_janthe": "noctua_janthina",
		"oligia_latruncula_-_strigilis_-_versicolor": "oligia_latruncula",
		"thera_variata_-_britannica": "thera_variata"
	}

	@classmethod
	def new(cls, name_string: str):
		name_string = name_string.strip()

		name_string = cls.alt.get(name_string, name_string)
		genus, _, spec = name_string.partition("_")
		return cls(genus, spec)


def main(args):
	global columns

	with open(args.class_names) as f:
		class_names = list(map(ClassName.new, f))

	with open(args.csv_file, newline="") as f:
		reader = csv.DictReader(f, delimiter="\t")
		rows = [Row(*[row[col] for col in columns]) for row in reader]

	not_mapped = []
	mapping = {}
	for i, name in enumerate(class_names):
		mapped = False

		for row in rows:
			if name.genus == row.genus.lower() and name.species == row.species.lower():
				mapped = True
				mapping[i] = dict(class_name="_".join(name), **row._asdict())
				continue

		if not mapped:
			not_mapped.append(name)

	with open(args.output, "w") as f:
		json.dump(mapping, f, indent=2)


parser = ArgumentParser()
parser.add_argument("csv_file")
parser.add_argument("class_names")
parser.add_argument("--output", default="mapping.json")

main(parser.parse_args())