osm_poi_matchmaker.dataproviders.hu_generic

Complexity

Total Complexity

11

Size/Duplication

Total Lines	91
Duplicated Lines	0 %

Importance

Changes

0

6 Methods

Rating	Name	Duplication	Size	Complexity
A	hu_city_postcode_from_xml.__init__()	0	5	1
A	hu_city_postcode.process()	0	19	2
A	hu_city_postcode.__init__()	0	3	1
A	hu_city_postcode_from_xml.process()	0	13	3
A	hu_street_types_from_xml.__init__()	0	5	1
A	hu_street_types_from_xml.process()	0	12	3

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

Missing module docstring

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

This line is too long as per the coding-style (104/100).

    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():

Class name "hu_city_postcode" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern)

Missing class docstring

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

    def process(self):

Missing function or method docstring

        xl = pd.ExcelFile(self.link)

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)

        df = xl.parse("Települések")

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)

        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)

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)

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

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)

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


class hu_city_postcode_from_xml():

Class name "hu_city_postcode_from_xml" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern)

Missing class docstring

    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):

Missing function or method docstring

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

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.

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

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)

            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)

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)

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


class hu_street_types_from_xml():

Class name "hu_street_types_from_xml" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern)

Missing class docstring

    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):

Missing function or method docstring

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

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.

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

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)

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

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)

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