metadata.py
6.26 KB
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
176
'Retrieve metadata'
import datetime
import os
import re
from committees import committee
def metadata(headers, filename):
'Create a dictionary with metadata based on paragraph content'
basename = os.path.basename(filename)
data = {}
data['original_file'] = filename
data['title'] = _title(headers)
data['house'] = _house(headers)
(data['abbreviation'], data['type']) = _type(data['house'], headers)
data['termNo'] = basename.split('_')[0]
data['dayNo'] = '1'
data['sessionNo'] = _session(headers)
data['date'] = _date(headers)
data['system'] = _system(data['date'])
data['file_id'] = _file_id(data)
_validate(data)
return data
def _validate(data):
'Check if the values are correct'
for key, value in data.items():
if key not in ['abbreviation', 'file_id'] and '??' in value:
print(
f'{data["original_file"]}: warning: invalid value for {key}: {value}')
def _title(headers):
'Determine title of the document'
for header in headers:
if header.who == 'komentarz':
return header.u.strip('()')
return '???'
def _house(headers):
'Determine house of Parliament'
for header in headers:
if header.who != 'komentarz':
continue
if 'Senat' in header.u:
return 'Senat'
if 'Sejm' in header.u:
return 'Sejm'
return 'Sejm'
def _type(house, headers):
'Determine type of session'
for header in headers:
match = re.search(
r'((KOMISJA|ZESPÓŁ|RADA) .*?)(?:, obradując|\s\[|\s\()', header.u, re.I)
if match:
return committee(house, match.group(1))
if re.search(f'z posiedzenia {house}u', header.u):
return 'Posiedzenie plenarne'
return ('pp', 'Posiedzenie plenarne')
def _date(headers):
'Determine date of the session'
for header in headers:
match = re.search(r'(\d{1,2})\.(\d{1,2})[\.\s](\d{4})', header.u)
if match: # 12.02.1980
return str(datetime.date(int(match.group(3)), int(match.group(2)), int(match.group(1))))
match = re.search(r'dni[ua] (\d{1,2}) (\w+) (\d{4})', header.u) or re.search(
r'dniach (\d{1,2}) i \d{1,2} (\w+) (\d{4})', header.u) or re.search(
r'(\d{1,2}) (\w+) (\d{4})', header.u)
if match: # 12 maja 1980
return str(datetime.date(int(match.group(3)), _MONTHS[match.group(2)],
int(match.group(1))))
match = re.search(r'(\d{1,2})[\.\s]([IXV]+)[\.\s](\d{4})', header.u)
if match: # 12.IV.1980
return str(datetime.date(int(match.group(3)), _ROMANS[match.group(2)],
int(match.group(1))))
return '????-??-??'
def _session(headers):
'Determine session'
for header in headers:
if header.who != 'komentarz':
continue
for regex in [r'(\d+) posiedzeni[ae]', r'(?:KOMISJA|ZESPÓŁ|RADA) .*? \((\d+)\)']:
match = re.search(regex, header.u, re.I)
if match:
return match.group(1)
match = re.search(r'(?:^|z )(.*) posiedzeni[ea]', header.u, re.I)
if match:
session = _numeral(match.group(1))
if session:
return session
# Initial session often has no number
if re.search(r'(KOMISJA|ZESPÓŁ|RADA)\s', header.u, re.I):
return '1'
return '???'
def _system(date):
'Return system based on date'
if date < '1940':
return 'II RP'
if date < '1989.07':
return 'PRL'
return 'III RP'
def _file_id(data):
(start, end) = _years(data['house'], data['date'])
house = _house_codes(data['house'])
try:
session = int(data['sessionNo'])
except ValueError:
print(f'Warning: wrong session in {data["original_file"]}')
session = 1
day = int(data['dayNo'])
abbreviation = data['abbreviation'] + 'x' * (5 - len(data['abbreviation']))
return f'{start}{end[2:]}-{house}-{abbreviation}-{session:05d}-{day:02d}'
def _years(house, date):
'Return years of given term'
sejm = ['1919-02-10', '1922-11-28', '1928-03-27', '1930-12-09', '1935-10-04', '1938-11-28',
'1947-02-04', '1952-11-20', '1957-02-20', '1961-04-16', '1965-05-30', '1969-06-01',
'1972-03-19', '1976-03-21', '1980-03-23', '1985-10-13', '1989-06-18', '1991-11-25',
'1993-09-19', '1997-10-20', '2001-10-19', '2005-10-19', '2007-11-05', '2011-11-08',
'2015-11-12', '2019-11-12', '2023-11-12']
senat = ['1922-11-12', '1928-03-11', '1930-11-23', '1935-10-04', '1938-11-13', '1991-11-25',
'1991-11-26', '1993-10-15', '2005-10-20', '2007-11-05', '2011-11-08', '2015-11-12',
'2019-11-12', '2023-11-12']
dates = senat if house == 'Senat' else sejm
for (index, start) in enumerate(dates):
if date <= start:
return (dates[index - 1][:4], start[:4])
return ('????', '????')
def _house_codes(house):
'Return the file ID section for given house'
house_codes = {'Sejm': 'sjm', 'Senat': 'snt',
'Krajowa Rada Narodowa': 'krn'}
return house_codes[house]
def _numeral(text):
'Convert text numerals to numbers'
total = 0
for word in text.lower().split():
for pattern, value in _NUMERALS.items():
if word.startswith(pattern):
total += value
return str(total)
_NUMERALS = {'pierwsz': 1, 'drugi': 2, 'trzeci': 3, 'czwart': 4, 'piąt': 5,
'szóst': 6, 'siódm': 7, 'ósm': 8, 'dziewiąt': 9, 'dziesiąt': 10,
'jedenast': 11, 'dwunast': 12, 'trzynast': 13, 'czternast': 14,
'piętnast': 15, 'szesnast': 16, 'siedemnast': 17, 'osiemnast': 18,
'dziewiętnast': 19, 'dwudziest': 20, 'trzydziest': 30, 'czterdziest': 40,
'pięćdziesiąt': 50, 'sześćdziesiąt': 60, 'siedemdziesiąt': 70,
'osiemdziesiąt': 80, 'dziewięćdziesiąt': 90}
_MONTHS = {'stycznia': 1, 'lutego': 2, 'marca': 3, 'kwietnia': 4, 'maja': 5, 'czerwca': 6,
'lipca': 7, 'sierpnia': 8, 'września': 9, 'października': 10, 'listopada': 11,
'grudnia': 12}
_ROMANS = {'I': 1, 'II': 2, 'III': 3, 'IV': 4, 'V': 5, 'VI': 6, 'VII': 7, 'VIII': 8, 'IX': 9,
'X': 10, 'XI': 11, 'XII': 12}