osm_poi_matchmaker.dataproviders.hu_generic.hu_city_postcode.process() - Code Metrics - KAMI911/osm_poi_matchmaker - Measure and Improve Code Quality continuously with Scrutinizer

hu_city_postcode.process() A
last analyzed 2023-01-03 16:24 UTC

↳ Parent: osm_poi_matchmaker.dataproviders.hu_generic

Complexity

Conditions

Size

Total Lines	19
Code Lines	18

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	2
eloc	18
nop	1
dl	0
loc	19
rs	9.5
c	0
b	0
f	0

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


try:
    import logging
    import sys
    import os
    import pandas as pd
    from lxml import etree
    from osm_poi_matchmaker.dao.data_handlers import insert_city_dataframe, insert_street_type_dataframe

    from osm_poi_matchmaker.libs.xml import save_downloaded_xml
except ImportError as err:
    logging.error('Error %s import module: %s', __name__, err)
    logging.exception('Exception occurred')

    sys.exit(128)

POI_COLS_CITY = ['city_post_code', 'city_name']
POI_COLS_STREET_TYPE = ['street_type']


class hu_city_postcode():


    def __init__(self, session, link):
        self.session = session
        self.link = link

    def process(self):

        xl = pd.ExcelFile(self.link)

        df = xl.parse("Települések")

        del df['Településrész']
        insert_city_dataframe(self.session, df)
        big_cities = [['Budapest', 'Bp.u.'],
                      ['Miskolc', 'Miskolc u.'],
                      ['Debrecen', 'Debrecen u.'],
                      ['Szeged', 'Szeged u.'],
                      ['Pécs', 'Pécs u.'],
                      ['Győr', 'Győr u.']
                      ]
        for city, sheet in big_cities:
            df = xl.parse(sheet)

            df.columns.values[0] = 'city_post_code'
            df['city_name'] = city
            df = df[['city_post_code', 'city_name']]

            df.drop_duplicates('city_post_code', keep='first', inplace=True)
            insert_city_dataframe(self.session, df)


class hu_city_postcode_from_xml():


    def __init__(self, session, link, download_cache, filename='hu_city_postcode.xml'):
        self.session = session
        self.link = link
        self.download_cache = download_cache
        self.filename = filename

    def process(self):

        xml = save_downloaded_xml('{}'.format(self.link), os.path.join(
            self.download_cache, self.filename))
        insert_data = []
        root = etree.fromstring(xml)

        for e in root.findall('zipCode'):

            cities = e[1].text
            postcode = e[0].text.strip()
            for i in cities.split('|'):
                insert_data.append([postcode, i.strip()])
        df = pd.DataFrame(insert_data)

        df.columns = POI_COLS_CITY
        insert_city_dataframe(self.session, df)


class hu_street_types_from_xml():


    def __init__(self, session, link, download_cache, filename='hu_street_types.xml'):
        self.session = session
        self.link = link
        self.download_cache = download_cache
        self.filename = filename

    def process(self):

        xml = save_downloaded_xml('{}'.format(self.link), os.path.join(
            self.download_cache, self.filename))
        insert_data = []
        root = etree.fromstring(xml)

        for e in root.findall('streetType'):

            if e.text is not None:
                street_type = e.text.strip()
                insert_data.append(street_type)
        df = pd.DataFrame(insert_data)

        df.columns = POI_COLS_STREET_TYPE
        insert_street_type_dataframe(self.session, df)


1			# -- coding: utf-8 --
			0 ignored issues – show introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Missing module docstring Loading history...
2
3			try:
4			import logging
5			import sys
6			import os
7			import pandas as pd
8			from lxml import etree
9			from osm_poi_matchmaker.dao.data_handlers import insert_city_dataframe, insert_street_type_dataframe
			0 ignored issues – show Coding Style introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (104/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
10			from osm_poi_matchmaker.libs.xml import save_downloaded_xml
11			except ImportError as err:
12			logging.error('Error %s import module: %s', __name__, err)
13			logging.exception('Exception occurred')
14
15			sys.exit(128)
16
17			POI_COLS_CITY = ['city_post_code', 'city_name']
18			POI_COLS_STREET_TYPE = ['street_type']
19
20
21			class hu_city_postcode():
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Class name "hu_city_postcode" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
22
23			def __init__(self, session, link):
24			self.session = session
25			self.link = link
26
27			def process(self):
			0 ignored issues – show introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
28			xl = pd.ExcelFile(self.link)
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "xl" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
29			df = xl.parse("Települések")
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
30			del df['Településrész']
31			insert_city_dataframe(self.session, df)
32			big_cities = [['Budapest', 'Bp.u.'],
33			['Miskolc', 'Miskolc u.'],
34			['Debrecen', 'Debrecen u.'],
35			['Szeged', 'Szeged u.'],
36			['Pécs', 'Pécs u.'],
37			['Győr', 'Győr u.']
38			]
39			for city, sheet in big_cities:
40			df = xl.parse(sheet)
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
41			df.columns.values[0] = 'city_post_code'
42			df['city_name'] = city
43			df = df[['city_post_code', 'city_name']]
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
44			df.drop_duplicates('city_post_code', keep='first', inplace=True)
45			insert_city_dataframe(self.session, df)
46
47
48			class hu_city_postcode_from_xml():
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Class name "hu_city_postcode_from_xml" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
49
50			def __init__(self, session, link, download_cache, filename='hu_city_postcode.xml'):
51			self.session = session
52			self.link = link
53			self.download_cache = download_cache
54			self.filename = filename
55
56			def process(self):
			0 ignored issues – show introduced 2020-10-24 18:21 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
57			xml = save_downloaded_xml('{}'.format(self.link), os.path.join(
58			self.download_cache, self.filename))
59			insert_data = []
60			root = etree.fromstring(xml)
			0 ignored issues – show introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Module 'lxml.etree' has no 'fromstring' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. Loading history...
61			for e in root.findall('zipCode'):
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "e" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
62			cities = e[1].text
63			postcode = e[0].text.strip()
64			for i in cities.split('\|'):
65			insert_data.append([postcode, i.strip()])
66			df = pd.DataFrame(insert_data)
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
67			df.columns = POI_COLS_CITY
68			insert_city_dataframe(self.session, df)
69
70
71			class hu_street_types_from_xml():
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Class name "hu_street_types_from_xml" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
72
73			def __init__(self, session, link, download_cache, filename='hu_street_types.xml'):
74			self.session = session
75			self.link = link
76			self.download_cache = download_cache
77			self.filename = filename
78
79			def process(self):
			0 ignored issues – show introduced 2020-10-24 18:21 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
80			xml = save_downloaded_xml('{}'.format(self.link), os.path.join(
81			self.download_cache, self.filename))
82			insert_data = []
83			root = etree.fromstring(xml)
			0 ignored issues – show introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Module 'lxml.etree' has no 'fromstring' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. Loading history...
84			for e in root.findall('streetType'):
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "e" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
85			if e.text is not None:
86			street_type = e.text.strip()
87			insert_data.append(street_type)
88			df = pd.DataFrame(insert_data)
			0 ignored issues – show Coding Style Naming introduced 2020-10-11 06:10 UTC by Report Bug Copy Issue Report Variable name "df" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
89			df.columns = POI_COLS_STREET_TYPE
90			insert_street_type_dataframe(self.session, df)
91

KAMI911 / osm_poi_matchmaker

hu_city_postcode.process() A last analyzed 2023-01-03 16:24 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

hu_city_postcode.process() A
last analyzed 2023-01-03 16:24 UTC