Tools/tool_lib/read_table.py

import pandas as pd

def add_zeros_zipcodes(list):
    for each_zipcode in range(0, len(list)):
        if len(list[each_zipcode]) < 5:
            counter = 5-len(list[each_zipcode])
            for each_missing_digit in range(0,counter):
                list[each_zipcode]='0'+list[each_zipcode]
        elif len(list[each_zipcode]) > 5:
            try:
                list[each_zipcode] = list[each_zipcode][0:list[each_zipcode].index('.0')]
                if len(list[each_zipcode]) < 5:
                    counter = 5 - len(list[each_zipcode])
                    for each_missing_digit in range(0, counter):
                        list[each_zipcode] = '0' + list[each_zipcode]
            except:
                assert False, "zipcode {} contains more than 5 digits".format(list[each_zipcode])
    return list



class Read_Table(object):

    def __init__(self,path, axes=[], encoding = 'utf-8', seperation = ';', type='xlsx', name=''):
        '''
        :param type:  Currently Available csv, xlsx and ods
        '''
        self.axes = axes
        self.path = path
        self.encoding = encoding
        self.seperation = seperation
        self.type = type
        if type == 'xlsx':
            self.engine = 'openpyxl'
            self.name = name
        if type == 'ods':
            self.engine = 'odf'

    # low Level
    def read_table_excel_or_ods(self):
        return pd.read_excel(self.path, engine= self.engine)

    def read_table_SQL(self):
        raise NotImplementedError

    def read_table_csv_(self):
        return pd.read_csv(self.path, sep = self.seperation, encoding = self.encoding)

    # mid Level
    def get_column_titles(self):
        if self.type== 'xlsx':
            return self.read_table_excel_or_ods().columns.values
        if self.type== 'ods':
            raise NotImplementedError
        if self.type == 'csv':
            raise NotImplementedError

    def get_values_from_columns(self, column_titles: list):
        values=[]
        for each_element in column_titles:
            if self.type== 'xlsx':
                table= pd.read_excel(self.path, engine=self.engine)
                values+=[[val for val in table[each_element].dropna()]]
            if self.type== 'ods':
                raise NotImplementedError
            if self.type == 'csv':
                raise NotImplementedError
        return values

    # high Level
    def table_to_dict(self):
        if self.type == 'xlsx':
            column_titles = self.get_column_titles()
            values = self.get_values_from_columns(column_titles)
            return dict(zip(column_titles,values))
        if self.type == 'ods':
            raise NotImplementedError
        if self.type == 'csv':
            raise NotImplementedError

class Read_unordered_Table(Read_Table):
    '''
    This Class is for Tables which do not have a column to value Struct
    '''
    def __init__(self,path, axes=[], encoding = 'utf-8', seperation = ';', type='xlsx', name=''):
        Read_Table.__init__(self,path, axes=axes, encoding = encoding, seperation = seperation, type=type, name=name)

    #High Level
    def get_values_after_key_as_dict(self, list_of_keys):
        dict_ = self.table_to_dict()
        ordered_dict= {}
        for each_key in list_of_keys:
            for each_list in dict_.values():
                for c,each_value in enumerate(each_list):
                    if each_value == each_key:
                        ordered_dict[each_value] = each_list[c+1:]
        return ordered_dict