edifact-extractor/parse_edifact.py at master · amnay-mo/edifact-extractor · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
from collections import namedtuple
import json


def parse_prd(prd_line):
    elements = prd_line.split('+')
    company_id = elements[-1]
    fes = elements[1].split(':')
    fes_length = len(fes)
    if fes_length < 4:
        fes += [None] * (4 - fes_length)
    return {
        'company_id': company_id,
        'train_service_id': fes[0],
        'service_character': fes[1],
        'pricing_category': fes[2],
        'item_description_code': fes[3]
    }


def parse_pop(pop_line):
    elements = pop_line.split('+')
    components = elements[1].split(':')
    dates = components[1].split('/')
    start_date = dates[0]
    end_date = dates[1]
    return {
        'start_date': start_date,
        'end_date': end_date,
        'period_days': components[3]
    }

def parse_als(als_line):
    elements = als_line.split('+')
    location_type = elements[1]
    components = elements[2].split(':')
    location_id = components[0]
    name = components[1]
    longitude = elements[3]
    latitude = elements[4]
    return {
        'location_id': location_id,
        'location_type': location_type,
        'name': name,
        'longitude': longitude,
        'latitude': latitude
    }


def parse_por(por_line):

    elements = por_line.split('+')
    location_id = elements[1]
    time = elements[2].split('*')

    if len(time) == 2:
        arrival_time = time[0]
        departure_time = time[1]
    else:
        arrival_time = elements[2]
        departure_time = ''

    return {
        'location_id': location_id,
        'arrival_time': arrival_time,
        'departure_time': departure_time
    }

def parse_pdt(pdt_line):
    elements = pdt_line.split('+')
    components = elements[2].split(':')
    train_type = components[3]
    return {
        'train_type': train_type
        }


def parse_segment(lines):
    global output
    list_por = []
    if lines == []:
        return None
    if lines[0][:3] != 'PRD':
        raise Exception('First line of segment is not PRD')
    pop, prd, start_date, end_date = {}, {}, None, None
    pdt = {'train_type': None}
    train_service_id = None
    for line in lines:
        if line[:3] == 'PRD':
            prd = parse_prd(line)
            train_service_id = prd['train_service_id']
        if line[:3] == 'POP':
            pop = parse_pop(line)
            start_date = pop['start_date']
            end_date = pop['end_date']
        if line[:3] == 'PDT':
            pdt = parse_pdt(line)
        if line[:3] == 'POR':
            por = parse_por(line)
            list_por.append(por)

    if pdt == {}:
        print('PDT IS NONE!', train_service_id)


    output[train_service_id + '_' + start_date + ' ' + end_date] = {
        'train_service': {**prd, **pop, **pdt},
        'train_timetable': list_por

    }


if __name__ == '__main__':
    output = {}
    segment = []

    with open('SKDUPD.20160624082533_3.r') as f:
        for line in f:
            if line[:3] == 'HDR':
                break
        for line in f:
            if line[:3] == 'PRD':
                parse_segment(segment)
                segment = [line.rstrip()]
            if line[:3] != 'PRD':
                segment.append(line.rstrip())


#    print(json.dumps(output))