intrastat/tools/pyntrastat.py

'''
Created on Feb 12, 2020 @author: deeejas
'''
import xml.etree.cElementTree as ET
import pandas as pd
import datetime as dt

def indent(elem, level=0):
    i = "\n" + level * "   "
    if len(elem):
        # print(len(elem))
        if not elem.text or not elem.text.strip():
            elem.text = i + "   "
            # print(elem.text)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
            # print(elem.tail)
        for elem in elem:
            indent(elem, level + 1)
        if not elem.tail or not elem.tail.strip():
            elem.tail = i
    else:
        if level and (not elem.tail or not elem.tail.strip()):
            elem.tail = i

class ContactPerson(object):

    def __init__(self, LastName=None, FirstName=None, Email=None,
                 Phone=None, Fax=None, Position=None):
        self.LastName = LastName
        self.FirstName = FirstName
        self.Email = Email
        self.Phone = Phone
        self.Fax = Fax
        self.Position = Position

class Company(object):
    '''
    classdocs
    '''

    def __init__(self, VatNr=None, FirmName=None, RefPeriod=None,
                 CreateDt=None, ApplicationRef=None, ContactPerson=None):
        '''
        Constructor
        '''
        self.VatNr = VatNr
        self.FirmName = FirmName
        self.RefPeriod = RefPeriod
        self.CreateDt = CreateDt or dt.datetime.now().strftime('%Y-%m-%dT%H:%M:%S-08:00')
        self.ApplicationRef = ApplicationRef
        self.ContactPerson = ContactPerson

class Intrastat(object):

    def __init__(self, company: object, person: object, versions: dict,
                 header: tuple, elem_attribs: dict, supplucodes: set):
        # temporary remove filename attribute as it's only need for study
        # self.filename = filename
        self.company = company
        self.person = person
        self.versions = versions
        self.header = header
        self.elem_attribs = elem_attribs
        # self.decl = ET.parse(self.filename)
        self.supplucodes = supplucodes

    def make_arrival(self):
        # creates the type of declaration: arrival/exp
        arrival = ET.Element('InsNewArrival', self.elem_attribs)
        code_vers = ET.SubElement(arrival, self.header[0])
        decl_header = ET.SubElement(arrival, self.header[1])
        company_dict = vars(self.company)
        person_dict = vars(self.person)
        self.arrival = arrival

        for tagname, value in self.versions.items():
            e = ET.SubElement(code_vers, tagname)
            e.text = value
        for tagname, value in company_dict.items():
            e = ET.SubElement(decl_header, tagname)
            e.text = value
            if tagname == 'ContactPerson':
                for subtagname, subvalue in person_dict.items():
                    se = ET.SubElement(e, subtagname)
                    se.text = subvalue

    def make_arrival_items(self, source_xls):
        # makes each position of the decl. is subelement of newarrival
        dtypes = {'NETWEIGHT': 'int64', 'NETVALUE': 'int64'}
        self.source_xls = source_xls
        df = pd.read_excel(self.source_xls, dtype=dtypes)
        self.grouped_df = df.groupby(
            [
                'VSCODE',
                'ACode',
                'Bcode',
                'DeliveryTermsCode',
                'TransportCode',
                'CountryOfOrigin',
                'EXP',
                'SUPPL'
            ])[
                ['NETVALUE',
                 'NETWEIGHT',
                 'Q',
                 'SUPPLVALUE'
                 ]].sum()
        # helper function called here
        print(self.grouped_df)
        # print(self.grouped_df['NETVALUE'].iloc[0])
        self._arrival_items(self.grouped_df)

    def _arrival_items(self, dframe):
        # loops over grouped df and adds items
        for n in range(1, len(dframe) + 1):
            order_attrib = {'OrderNr': f'{n}'}
            # print(order_attrib)
            new_item = ET.SubElement(self.arrival, 'InsArrivalItem', order_attrib)
            new_item_code = ET.SubElement(new_item, 'Cn8Code')
            new_item_code.text = f'{self.grouped_df.index[n-1][0]}'
            new_item_val = ET.SubElement(new_item, 'InvoiceValue')
            new_item_val.text = f'{self.grouped_df["NETVALUE"].iloc[n-1]}'
            new_item_statval = ET.SubElement(new_item, 'StatisticalValue')
            if self.grouped_df.index[n - 1][7] == 1:
                new_item_statval.text = f'{int(self.grouped_df["NETVALUE"].iloc[n-1]-self.grouped_df["SUPPLVALUE"].iloc[n-1]*0.12)}'
            elif self.grouped_df.index[n - 1][7] == 2:
                new_item_statval.text = f'{int(self.grouped_df["NETVALUE"].iloc[n-1]+self.grouped_df["SUPPLVALUE"].iloc[n-1]*0.88)}'
            else:
                new_item_statval.text = f'{self.grouped_df["NETVALUE"].iloc[n-1]}'
            new_item_netmass = ET.SubElement(new_item, 'NetMass')
            new_item_netmass.text = f'{self.grouped_df["NETWEIGHT"].iloc[n-1]}'
            new_item_acode = ET.SubElement(new_item, 'NatureOfTransactionACode')
            new_item_acode.text = f'{self.grouped_df.index[n-1][1]}'
            new_item_bcode = ET.SubElement(new_item, 'NatureOfTransactionBCode')
            new_item_bcode.text = f'{self.grouped_df.index[n-1][2]}'
            new_item_delterms = ET.SubElement(new_item, 'DeliveryTermsCode')
            new_item_delterms.text = f'{self.grouped_df.index[n-1][3]}'
            new_item_transpcode = ET.SubElement(new_item, 'ModeOfTransportCode')
            new_item_transpcode.text = f'{self.grouped_df.index[n-1][4]}'
            new_item_origin = ET.SubElement(new_item, 'CountryOfOrigin')
            new_item_origin.text = f'{self.grouped_df.index[n-1][5]}'
            if f'{self.grouped_df.index[n-1][0]}' in self.supplucodes:
                new_item_supplunits = ET.SubElement(new_item, 'InsSupplUnitsInfo')
                new_item_supplunitcode = ET.SubElement(new_item_supplunits, 'SupplUnitCode')
                new_item_supplunitcode.text = 'p/st'
                new_item_supplunits = ET.SubElement(new_item_supplunits, 'QtyInSupplUnits')
                new_item_supplunits.text = f'{self.grouped_df["Q"].iloc[n-1]}'
            new_item_exp = ET.SubElement(new_item, 'CountryOfConsignment')
            new_item_exp.text = f'{self.grouped_df.index[n-1][6]}'

    def write_xml(self):
        ns = ET.register_namespace('InsNewArrival',
                                   'http://www.intrastat.ro/xml/InsSchema')
        todecl = ET.ElementTree(self.arrival)
        indent(todecl._root)
        todecl.write(
            'xml/{}_{}.xml'.format(self.company.VatNr.replace('00', '', 1),
                                   self.company.RefPeriod),
            encoding='UTF-8',
            xml_declaration=True,
            default_namespace=ns,
            method='xml')

# EOF