This repository has been archived by the owner on Nov 12, 2023. It is now read-only.
/
mag_papers_to_db.py
197 lines (174 loc) · 5.06 KB
/
mag_papers_to_db.py
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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
import ipdb
import csv
import argparse
import pathlib
import functools
import dateutil.parser
import pymysql
import collections
import datetime
import ipdb
import frogress
import utils
PapersRecord = collections.namedtuple(
'PapersRecord',
(
'paper_id',
'original_paper_title',
'normalized_paper_title',
'paper_publish_year',
'paper_publish_date',
'paper_doi',
'original_venue_name',
'normalized_venue_name',
'journal_id_mapped_to_venue_name',
'converence_series_id_mapped_to_venue_name',
'paper_rank',
),
)
@functools.lru_cache(1000)
def parse_date(date):
values = date.split('/')
if len(values) < 3:
return None
try:
return datetime.date(*map(int, values))
except ValueError as e:
print('Warning: parse_date ', date, 'error', e)
return None
def parse_papers_record(raw_record):
(
paper_id,
original_paper_title,
normalized_paper_title,
paper_publish_year,
paper_publish_date,
paper_doi,
original_venue_name,
normalized_venue_name,
journal_id_mapped_to_venue_name,
converence_series_id_mapped_to_venue_name,
paper_rank,
) = raw_record
if not paper_publish_year:
paper_publish_year = None
else:
paper_publish_year = int(paper_publish_year)
if not paper_publish_date:
paper_publish_date = None
else:
paper_publish_date = parse_date(paper_publish_date)
return PapersRecord(
paper_id,
original_paper_title,
normalized_paper_title,
paper_publish_year,
paper_publish_date,
paper_doi,
original_venue_name,
normalized_venue_name,
journal_id_mapped_to_venue_name,
converence_series_id_mapped_to_venue_name,
paper_rank,
)
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
'input_csv',
type=pathlib.Path,
)
parser.add_argument(
'mysql_url',
type=utils.parse_mysql_url,
help='MYSQL Database URL',
)
parser.add_argument(
'--create-tables', '-c',
action='store_true',
default=False,
required=False,
)
parser.add_argument(
'--expected-records',
type=int,
required=False,
default=None,
help='Expected number of record for visualization purposes',
)
return parser.parse_args()
def create_tables_and_indexes(cursor):
with cursor:
cursor.execute('''
CREATE TABLE IF NOT EXISTS `mag_papers` (
`paper_id` varchar(50) NOT NULL,
`original_paper_title` varchar(255) DEFAULT NULL,
`normalized_paper_title` TEXT DEFAULT NULL,
`paper_publish_year` int(4) DEFAULT NULL,
`paper_publish_date` datetime DEFAULT NULL,
`paper_doi` varchar(255) DEFAULT NULL,
`original_venue_name` TEXT DEFAULT NULL,
`normalized_venue_name` TEXT DEFAULT NULL,
`journal_id_mapped_to_venue_name` varchar(255) DEFAULT NULL,
`conference_series_id_mapped_to_venue_name` varchar(255) DEFAULT NULL,
`paper_rank` int(11) DEFAULT NULL,
PRIMARY KEY (`paper_id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
''')
def main():
args = parse_args()
db_conn = pymysql.connect(**args.mysql_url)
insert_tpl = '''
INSERT INTO `mag_papers` (
`paper_id`,
`original_paper_title`,
`normalized_paper_title`,
`paper_publish_year`,
`paper_publish_date`,
`paper_doi`,
`original_venue_name`,
`normalized_venue_name`,
`journal_id_mapped_to_venue_name`,
`conference_series_id_mapped_to_venue_name`,
`paper_rank`
) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
'''
if args.create_tables:
print('Creating tables and indexes')
create_tables_and_indexes(db_conn.cursor())
db_conn.commit()
print('Reading', args.input_csv, '...')
input_file = utils.open_compressed_file(args.input_csv)
cursor = db_conn.cursor()
with input_file, cursor:
csvreader = csv.reader(
input_file,
delimiter='\t',
quoting=csv.QUOTE_NONE,
)
records = (
parse_papers_record(r)
for r in csvreader
)
records_truncated = (
(
r.paper_id[:50],
r.original_paper_title[:255],
r.normalized_paper_title[:255],
r.paper_publish_year,
r.paper_publish_date,
r.paper_doi[:255],
r.original_venue_name[:255],
r.normalized_venue_name[:255],
r.journal_id_mapped_to_venue_name[:255],
r.converence_series_id_mapped_to_venue_name[:255],
r.paper_rank,
) for r in records
)
records_with_progress = frogress.bar(
records_truncated,
steps=args.expected_records,
)
cursor.executemany(insert_tpl, records_with_progress)
db_conn.commit()
if __name__ == '__main__':
main()