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
|
import os
import re
import glob
import json
import math
import operator
import click
from util import *
@click.command()
def s2_citation_report():
addresses = AddressBook()
for fn in glob.iglob('datasets/s2/papers/**/*.json', recursive=True):
process_paper(fn, addresses)
def process_paper(fn, addresses):
res = {}
address_count = 0
geocode_count = 0
geocoded_citations = []
unknown_citations = []
display_geocoded_citations = []
with open(fn, 'r') as f:
data = json.load(f)
print('>> {}'.format(data['paperId']))
paper = load_paper(data['paperId'])
if paper.data is None:
print("Paper missing! {}".format(data['paperId']))
return
res['paperId'] = paper.paper_id
res['title'] = paper.title
res['journal'] = paper.journal
res['authors'] = paper.authors
res['citations'] = []
for cite in data['citations']:
citationId = cite['paperId']
citation = load_paper(citationId)
if citation.data is None:
print("Citation missing! {}".format(cite['paperId']))
continue
institutions = load_institutions(citationId)
geocoded_institutions = []
unknown_institutions = []
institution = ''
address = None
for inst in sorted(institutions, key=operator.itemgetter(1)):
# print(inst[1])
address_count += 1
institution = inst[1]
next_address = addresses.find(institution)
if next_address:
address = next_address
geocode_count += 1
geocoded_institutions.append(institution)
else:
unknown_institutions.append(institution)
if not address:
if os.path.exists(file_path('pdf', citationId, 'paper.txt')):
headings, found_abstract = read_headings(file_path('pdf', citationId, 'paper.txt'), citation)
heading_string = '\n'.join(headings[0:20])
found_addresses = []
if len(headings):
for heading in headings:
l = heading.lower().strip()
if l:
next_address = addresses.find(l)
if next_address:
address = next_address
geocode_count += 1
geocoded_institutions.append(heading)
else:
unknown_institutions.append(heading)
res['citations'].append({
'title': citation.title,
'journal': citation.journal,
'authors': citation.authors,
'institutions': [inst[1] for inst in institutions],
'geocoded': geocoded_institutions,
})
if address:
geocoded_citations.append([
citation.title,
institution,
] + address)
display_geocoded_citations.append([
citation.title,
] + address)
else:
unknown_citations.append([
citation.title,
'<br>'.join(unknown_institutions),
])
paper_institutions = load_institutions(paper.paper_id)
paper_address = None
for inst in sorted(paper_institutions, key=operator.itemgetter(1)):
# print(inst[1])
address_count += 1
institution = inst[1]
paper_address = addresses.find(institution)
if paper_address:
print(paper_address)
total_citations = len(geocoded_citations) + len(unknown_citations)
os.makedirs('reports/papers/', exist_ok=True)
with open('reports/papers/{}.html'.format(paper.paper_id), 'w') as f:
f.write("<!doctype html>")
f.write("<html>")
f.write("<head>")
f.write('<meta charset="utf-8">')
f.write("<title>{}</title>".format(paper.title))
f.write("<link rel='stylesheet' href='../reports.css'>")
f.write('<link rel="stylesheet" href="https://unpkg.com/leaflet@1.3.4/dist/leaflet.css" integrity="sha512-puBpdR0798OZvTTbP4A8Ix/l+A4dHDD0DGqYW6RQ+9jxkRFclaxxQb/SJAWZfWAkuyeQUytO7+7N4QKrDh+drA==" crossorigin=""/>')
f.write("</head>")
f.write("<body>")
f.write("<div id='mapid'></div>")
f.write("<h2>{}</h2>".format(paper.title))
f.write('<ul>')
if paper.journal:
f.write('<li>Journal: {}</li>'.format(paper.journal))
if paper_address:
f.write('<li>Research institution: {}</li>'.format(paper_address[0]))
f.write('<li>Address: {}</li>'.format(paper_address[3]))
f.write('<li>{}</li>'.format(paper.year))
f.write('<li>{} / {} citations were located ({} %).</li>'.format(len(geocoded_citations), total_citations, math.floor(len(geocoded_citations) / total_citations * 100)))
f.write('</ul>')
f.write('<h3>{}</h3>'.format('Geocoded Citations'))
write_table(f, keys=None, rows=sorted(display_geocoded_citations, key=operator.itemgetter(0)))
f.write('<h3>{}</h3>'.format('Other Citations'))
write_table(f, keys=None, rows=sorted(unknown_citations, key=operator.itemgetter(0)))
f.write("</body>")
f.write('<script src="../snap.svg-min.js"></script>')
f.write('<script src="https://unpkg.com/leaflet@1.3.4/dist/leaflet.js" integrity="sha512-nMMmRyTVoLYqjP9hrbed9S+FzjZHW5gY1TWCHA5ckwXZBadntCNs8kEqAWdrb9O7rxbCaA4lKTIWjDXZxflOcA==" crossorigin=""></script>')
f.write('<script src="../leaflet.arc.js"></script>')
f.write('<script src="../leaflet.bezier.js"></script>')
f.write('<script type="text/json" id="address">')
json.dump(paper_address, f)
f.write('</script>')
f.write('<script type="text/json" id="citations">')
json.dump(geocoded_citations, f)
f.write('</script>')
f.write('<script src="../map.js"></script>')
f.write("</html>")
return res
def load_institutions(paperId):
if os.path.exists(file_path('pdf', paperId, 'institutions.json')):
return read_json(file_path('pdf', paperId, 'institutions.json'))['institutions']
elif os.path.exists(file_path('doi', paperId, 'institutions.json')):
return read_json(file_path('doi', paperId, 'institutions.json'))['institutions']
else:
return []
def data_path(key, paper_id):
return 'datasets/s2/{}/{}/{}'.format(key, paper_id[0:2], paper_id)
def file_path(key, paper_id, fn):
return os.path.join(data_path(key, paper_id), fn)
if __name__ == '__main__':
s2_citation_report()
|
