scripts.updatedata._update_municipalities_data() - Code Metrics - Inspection of "Merge branch 'master' of https://github.com/fabioc..." - fabiocaccamo/python-codicefiscale - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( d7a7a9...fa1f03 )

by Fabio

created 2022-02-13 12:20 UTC

scripts.updatedata._update_municipalities_data() B

↳ Parent: scripts.updatedata

Complexity

Conditions

Size

Total Lines	62
Code Lines	47

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	47
dl	0
loc	62
rs	8.7345
c	0
b	0
f	0
cc	3
nop	0

How to fix Long Method

# -*- coding: utf-8 -*-

from benedict import benedict
from openpyxl import load_workbook
from slugify import slugify

import fsutil


def _update_countries_data():
    # https://www.anagrafenazionale.interno.it/il-progetto/strumenti-di-lavoro/tabelle-decodifica/
    data_url = "https://www.anagrafenazionale.interno.it/wp-content/uploads/2021/03/tabella_2_statiesteri.xlsx"
    data_path = fsutil.download_file(data_url, __file__, filename="countries.xlsx")

    workbook = load_workbook(filename=data_path, read_only=True)
    sheet = workbook.active

    items = []
    keys = []
    for row in sheet.iter_rows(min_row=1, max_row=1):
        keys = [cell.value for cell in row]
    for row in sheet.iter_rows(min_row=2):
        values = list([cell.value for cell in row])
        items.append(dict(zip(keys, values)))

    workbook.close()
    fsutil.remove_file(data_path)

    data = benedict({"values": items})
    data.standardize()
    # print(data.dump())

    def map_item(item):
        if not item:
            return None
        code = item.get_str("codat").upper()
        if not code:
            return None
        assert len(code) == 4, f"Invalid code: '{code}'"

        name = item.get_str("denominazione").title()
        assert name != "", f"Invalid name: '{name}'"
        name_alt = item.get_str("denominazioneistat").title()
        name_alt_en = item.get_str("denominazioneistat_en").title()
        name_slugs = sorted(
            set(
                filter(
                    bool,
                    [
                        slugify(name),
                        slugify(name_alt),
                        slugify(name_alt_en),
                    ],
                )
            )
        )
        province = "EE"

        date_created = item.get_str("datainiziovalidita")
        date_deleted = item.get_str("datafinevalidita")
        if "9999" in date_deleted:
            date_deleted = ""

        return {
            "active": False if date_deleted else True,
            "code": code,
            "date_created": date_created,
            "date_deleted": date_deleted,
            "name": name,
            "name_alt": name_alt,
            "name_alt_en": name_alt_en,
            "name_slugs": name_slugs,
            "province": province,
        }

    output_data = list(
        filter(bool, [map_item(benedict(item)) for item in data["values"]])
    )
    output_data = sorted(output_data, key=lambda item: item["name"])
    output_path = "../codicefiscale/data/countries.json"
    output_abspath = fsutil.join_path(__file__, output_path)
    fsutil.write_file_json(output_abspath, output_data, indent=4, sort_keys=True)


def _update_municipalities_data():
    # https://www.anagrafenazionale.interno.it/il-progetto/strumenti-di-lavoro/tabelle-decodifica/
    data_url = "https://www.anagrafenazionale.interno.it/wp-content/uploads/ANPR_archivio_comuni.csv"
    data = benedict.from_csv(data_url)
    data.standardize()

    def map_item(item):

        status = item.get("stato", "").upper()
        assert len(status) == 1 and status in ["A", "C"], f"Invalid status: '{status}'"
        active = status == "A"

        code = item.get_str("codcatastale").upper()
        assert code == "ND" or len(code) == 4, f"Invalid code: '{code}'"

        name = item.get_str("denominazione_it").title()
        assert name != "", f"Invalid name: {name}"

        name_trans = item.get_str("denomtraslitterata").title()
        name_alt = item.get_str("altradenominazione").title()
        name_alt_trans = item.get_str("altradenomtraslitterata").title()
        name_slugs = sorted(
            set(
                filter(
                    bool,
                    [
                        slugify(name),
                        slugify(name_trans),
                        slugify(name_alt),
                        slugify(name_alt_trans),
                    ],
                )
            )
        )
        province = item.get("siglaprovincia", "").upper()
        assert len(province) == 2, f"Invalid province: '{province}'"

        date_created = item.get_str("dataistituzione")
        date_deleted = item.get_str("datacessazione")
        if "9999" in date_deleted:
            date_deleted = ""

        return {
            "active": active,
            "code": code,
            "date_created": date_created,
            "date_deleted": date_deleted,
            "name": name,
            "name_trans": name_trans,
            "name_alt": name_alt,
            "name_alt_trans": name_alt_trans,
            "name_slugs": name_slugs,
            "province": province,
        }

    output_data = list(
        filter(bool, [map_item(benedict(item)) for item in data["values"]])
    )
    output_data = sorted(output_data, key=lambda item: item["name"])
    output_path = "../codicefiscale/data/municipalities.json"
    output_abspath = fsutil.join_path(__file__, output_path)
    fsutil.write_file_json(output_abspath, output_data, indent=4, sort_keys=True)


def main():
    _update_countries_data()
    _update_municipalities_data()


if __name__ == "__main__":
    main()


1			# -- coding: utf-8 --
2
3			from benedict import benedict
4			from openpyxl import load_workbook
5			from slugify import slugify
6
7			import fsutil
8
9
10			def _update_countries_data():
11			# https://www.anagrafenazionale.interno.it/il-progetto/strumenti-di-lavoro/tabelle-decodifica/
12			data_url = "https://www.anagrafenazionale.interno.it/wp-content/uploads/2021/03/tabella_2_statiesteri.xlsx"
13			data_path = fsutil.download_file(data_url, __file__, filename="countries.xlsx")
14
15			workbook = load_workbook(filename=data_path, read_only=True)
16			sheet = workbook.active
17
18			items = []
19			keys = []
20			for row in sheet.iter_rows(min_row=1, max_row=1):
21			keys = [cell.value for cell in row]
22			for row in sheet.iter_rows(min_row=2):
23			values = list([cell.value for cell in row])
24			items.append(dict(zip(keys, values)))
25
26			workbook.close()
27			fsutil.remove_file(data_path)
28
29			data = benedict({"values": items})
30			data.standardize()
31			# print(data.dump())
32
33			def map_item(item):
34			if not item:
35			return None
36			code = item.get_str("codat").upper()
37			if not code:
38			return None
39			assert len(code) == 4, f"Invalid code: '{code}'"
40
41			name = item.get_str("denominazione").title()
42			assert name != "", f"Invalid name: '{name}'"
43			name_alt = item.get_str("denominazioneistat").title()
44			name_alt_en = item.get_str("denominazioneistat_en").title()
45			name_slugs = sorted(
46			set(
47			filter(
48			bool,
49			[
50			slugify(name),
51			slugify(name_alt),
52			slugify(name_alt_en),
53			],
54			)
55			)
56			)
57			province = "EE"
58
59			date_created = item.get_str("datainiziovalidita")
60			date_deleted = item.get_str("datafinevalidita")
61			if "9999" in date_deleted:
62			date_deleted = ""
63
64			return {
65			"active": False if date_deleted else True,
66			"code": code,
67			"date_created": date_created,
68			"date_deleted": date_deleted,
69			"name": name,
70			"name_alt": name_alt,
71			"name_alt_en": name_alt_en,
72			"name_slugs": name_slugs,
73			"province": province,
74			}
75
76			output_data = list(
77			filter(bool, [map_item(benedict(item)) for item in data["values"]])
78			)
79			output_data = sorted(output_data, key=lambda item: item["name"])
80			output_path = "../codicefiscale/data/countries.json"
81			output_abspath = fsutil.join_path(__file__, output_path)
82			fsutil.write_file_json(output_abspath, output_data, indent=4, sort_keys=True)
83
84
85			def _update_municipalities_data():
86			# https://www.anagrafenazionale.interno.it/il-progetto/strumenti-di-lavoro/tabelle-decodifica/
87			data_url = "https://www.anagrafenazionale.interno.it/wp-content/uploads/ANPR_archivio_comuni.csv"
88			data = benedict.from_csv(data_url)
89			data.standardize()
90
91			def map_item(item):
92
93			status = item.get("stato", "").upper()
94			assert len(status) == 1 and status in ["A", "C"], f"Invalid status: '{status}'"
95			active = status == "A"
96
97			code = item.get_str("codcatastale").upper()
98			assert code == "ND" or len(code) == 4, f"Invalid code: '{code}'"
99
100			name = item.get_str("denominazione_it").title()
101			assert name != "", f"Invalid name: {name}"
102
103			name_trans = item.get_str("denomtraslitterata").title()
104			name_alt = item.get_str("altradenominazione").title()
105			name_alt_trans = item.get_str("altradenomtraslitterata").title()
106			name_slugs = sorted(
107			set(
108			filter(
109			bool,
110			[
111			slugify(name),
112			slugify(name_trans),
113			slugify(name_alt),
114			slugify(name_alt_trans),
115			],
116			)
117			)
118			)
119			province = item.get("siglaprovincia", "").upper()
120			assert len(province) == 2, f"Invalid province: '{province}'"
121
122			date_created = item.get_str("dataistituzione")
123			date_deleted = item.get_str("datacessazione")
124			if "9999" in date_deleted:
125			date_deleted = ""
126
127			return {
128			"active": active,
129			"code": code,
130			"date_created": date_created,
131			"date_deleted": date_deleted,
132			"name": name,
133			"name_trans": name_trans,
134			"name_alt": name_alt,
135			"name_alt_trans": name_alt_trans,
136			"name_slugs": name_slugs,
137			"province": province,
138			}
139
140			output_data = list(
141			filter(bool, [map_item(benedict(item)) for item in data["values"]])
142			)
143			output_data = sorted(output_data, key=lambda item: item["name"])
144			output_path = "../codicefiscale/data/municipalities.json"
145			output_abspath = fsutil.join_path(__file__, output_path)
146			fsutil.write_file_json(output_abspath, output_data, indent=4, sort_keys=True)
147
148
149			def main():
150			_update_countries_data()
151			_update_municipalities_data()
152
153
154			if __name__ == "__main__":
155			main()
156

fabiocaccamo / python-codicefiscale

Push — master ( d7a7a9...fa1f03 )

scripts.updatedata._update_municipalities_data() B

Complexity

Size

Duplication

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like