OdekroDocumentParser/loan_parser.py at master · Hutspace/OdekroDocumentParser · 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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
# -*- coding: utf-8 -*-

import sys
import re
from datetime import datetime
from datetime import date
from parser import DocumentParser


class LoanParser(DocumentParser):
    SELECTION_MARKER = r".*(Loan Facility|Loan Agreement|Financial Agreement).*"
    ESCAPE_MARKERS = r".*(the date on which notice of the motion is given|Date:|Venue:|met on ).*"


    def __init__(self, content):
        super(LoanParser, self).__init__(content)

    @classmethod
    def filter_out_parties_to_agreement(self,line_content):
        line_content = line_content.replace(',',' ')
        all_parties1 = line_content.split('between',1)[-1]
        if len(all_parties1)>1:
            all_parties = all_parties1.split('and',1)
            party_1 = all_parties[0]
            if len(all_parties)>1:
                party_2 = all_parties[1].split('for an amount')[0].split('—',1)[0]
            else:
                party_2 = ''

            return (party_1 , party_2)
        else:
            return ( '', '' )


    @classmethod
    def filter_out_loan_purpose(self,line_content):
        line_content = line_content.replace(',',' ')
        loan_details = line_content.split('to finance',1)
        if len(loan_details)>1:
            return loan_details[1]
        else:
            #loan_details[0]
            return ''

    @classmethod
    def filter_out_loan_purpose_via_party_2(self,line_content):
        line_content = line_content.replace(',',' ')
        all_parties1 = line_content.split('between',1)[-1]
        if len(all_parties1)>1:
            all_parties = all_parties1.split('and',1)
            print all_parties
            if len(all_parties)>1:
                purpose = all_parties[1].split('for an amount')[0].split('—',1)[1]
               #party_2 = all_parties[1].split('for an amount')[0].split('—',1)[0]
            else:
                purpose  = ''

            return purpose
        else:
            return ''

    @classmethod
    def filter_out_loan_amount(self,line_content):
        line_content = line_content.replace(',',' ')
        loan_details = line_content.split('amounting to',1)
        if len(loan_details)>1:
            amount = loan_details[1].split('between',1)[0]
            return amount
        else:
            loan_details1 = line_content.split('an amount of',1)
            if len(loan_details1)>1:
                loan_details2  =loan_details1[1]
                amount = loan_details2.split('to finance',1)[0]
            else:
                amount = ''
            #loan_details[0]
            return amount


    @classmethod
    def parse_loan_summary(cls, lines):
        thekind, line, match = None, None, None
        loans = []
        valid = False

        party_1  = ''
        party_2 = ''
        purpose = ''
        amount = '';

        while len(lines):
            thekind, line, match = lines.pop(0)
            line_content = line.strip()

            if (thekind == cls.BLANK ):
                continue

            matchObjectForLoan = re.match( cls.SELECTION_MARKER , line_content)
            matchObjectForEscapeMarkers = re.match( cls.ESCAPE_MARKERS , line_content)

            if matchObjectForEscapeMarkers:
                # START PARSING SECTION
                valid = False
                continue

            if matchObjectForLoan:
                # START PARSING SECTION
                valid = True
                pass


            if valid:

                if matchObjectForLoan:

                    all_parties = cls.filter_out_parties_to_agreement(line_content)
                    party_1 = all_parties[0]
                    party_2 = all_parties[1]


                    purpose = cls.filter_out_loan_purpose(line_content)
                    amount = cls.filter_out_loan_amount(line_content)

                if (thekind == cls.LINE or thekind == cls.BLANK or thekind == cls.PAGE_HEADER):
                    continue

            else:
                # fallout
                continue


            if len(loans)==0:
                continue

        if party_1!='' and  party_2!='' and amount!='' and purpose!='':

            loans.append(dict(party_1=party_1,
                            party_2=party_2,
                            amount=amount,
                            purpose=purpose
                            ))

        return loans

    @classmethod
    def parse_body(cls, lines):
        entries = []
        loan_all = cls.parse_loan_summary( list(lines) )
        for loan in loan_all:

            if len(loan)>2:
                entries.append(loan)

        return entries


def main(argv):
    print 'Party 1 | Party 2 | Amount | Purpose '
    for filename in sys.stdin:
        handle = open(filename.strip(), 'r')
        content = handle.read()
        handle.close()

        p = LoanParser(content)
        p.parse()
        data = p.output()
        for row in data:
            print '%s|%s|%s|%s' % (row['party_1'],
                                      row['party_2'],
                                      row['amount'],
                                      row['purpose'])


if __name__ == "__main__":
    main(sys.argv)