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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
|
import re
import os
import csv
import string
import codecs
import gspread
import simplejson as json
from oauth2client.service_account import ServiceAccountCredentials
def read_citation_list(index=0):
filename = './datasets/citations.csv'
if index > 0:
fn, ext = os.path.splitext(filename)
filename = fn + '-' + str(index) + ext
with open(filename, 'r') as f:
reader = csv.reader(f)
lines = list(reader)
keys = lines[0]
lines = lines[1:]
return keys, lines
def unfussy_reader(reader):
while True:
try:
yield next(reader)
except StopIteration:
return
except csv.Error:
print(csv.Error)
# log the problem or whatever
continue
def read_csv(fn, keys=True, create=False):
try:
with open(fn, 'r', newline='', encoding='utf-8') as f:
# reader = csv.reader( (line.replace('\0','') for line in f) )
reader = csv.reader(f)
lines = list(unfussy_reader(reader))
if keys:
keys = lines[0]
lines = lines[1:]
return keys, lines
return lines
except:
if create:
return []
raise
def csv_writer(fn):
with open(fn, 'w', newline='', encoding='utf-8') as f:
return csv.writer(f)
def write_csv(fn, keys, rows):
with open(fn, 'w', newline='', encoding='utf-8') as f:
writer = csv.writer(f)
if keys is not None:
writer.writerow(keys)
for row in rows:
writer.writerow(row)
def read_text(fn):
with open(fn, 'r') as f:
return f.read()
def read_json(fn):
with open(fn, 'r') as json_file:
return json.load(json_file)
def write_json(fn, data):
with open(fn, 'w') as outfile:
json.dump(data, outfile)
def write_report(fn, title=None, keys=None, rows=[]):
with open(fn, 'w') as f:
f.write("<!doctype html>")
f.write("<html>")
f.write("<head>")
f.write("<meta charset='utf-8'>")
if title is not None:
f.write("<title>{}</title>".format(title))
f.write("<link rel='stylesheet' href='reports.css'>")
f.write("</head>")
f.write("<body>")
if title is not None:
f.write("<h2>{}</h2>".format(title))
count = write_table(f, keys=keys, rows=rows)
f.write("</body>")
f.write("</html>")
print("{} {}".format(fn, count))
def percent(m, n):
if n == 0:
return 100
return round(m / n * 100)
class NameLine(object):
def __init__(self, s):
self.s = s.strip()
def __str__(self):
return '<span class="name">' + self.s + '</span>'
class BoldLine(object):
def __init__(self, s):
self.s = s.strip()
def __str__(self):
return '<b>' + self.s + '</b>'
class LinkLine(object):
def __init__(self, href, txt):
self.href = href
self.txt = txt.strip()
def __str__(self):
if self.href:
return '<a href="{}">{}</a>'.format(self.href, self.txt)
else:
return '<span class="gray">{}</a>'.format(self.txt)
def write_table(f, keys, rows):
count = 0
f.write("<table border='1' cellpadding='3' cellspacing='3'>")
if keys is not None:
for key in keys:
f.write("<th>{}</th>".format(key))
for row in rows:
if row is None:
return
count += 1
f.write("<tr>")
for cell in row:
if isinstance(cell, list) or isinstance(cell, tuple):
f.write("<td>{}</td>".format('<br/>'.join(str(x) for x in cell)))
else:
f.write("<td>{}</td>".format(cell))
f.write("</tr>")
f.write("</table>")
return count
def paper_path(key='papers', paper_id=''):
return '{}/{}/{}/{}/paper.json'.format('./datasets/s2', key, paper_id[0:2], paper_id)
class DbPaper(object):
def __init__(self, paper_id):
self.paper_id = paper_id
self.data = read_json(paper_path('db_papers', paper_id))
@property
def title(self):
return self.data['title']
@property
def journal(self):
return self.data['journalName']
@property
def year(self):
return self.data['year'] if 'year' in self.data else ''
@property
def authors(self):
return [ (author['ids'][0] if len(author['ids']) else '', author['name']) for author in self.data['authors'] ]
@property
def pdf_link(self):
if self.data['s2PdfUrl']:
return self.data['s2PdfUrl']
if len(self.data['pdfUrls']):
return self.data['pdfUrls'][0]
return None
def record(self):
return [ self.paper_id, self.title, self.journal, self.year ]
class RawPaper(object):
def __init__(self, paper_id):
self.paper_id = paper_id
data = read_json(paper_path('raw_papers', paper_id))
# print(data)
if 'paper' not in data:
print(data)
self.data = None
return None
self.data = data['paper']
@property
def title(self):
return self.data['title']['text']
@property
def year(self):
return self.data['year']['text']
@property
def journal(self):
if 'journal' in self.data and 'name' in self.data['journal']:
return self.data['journal']['name']
else:
return 'Unknown'
@property
def authors(self):
return [ (author[0]['ids'][0] if len(author[0]['ids']) else '', author[0]['name']) for author in self.data['authors'] ]
@property
def pdf_link(self):
if 'primaryPaperLink' in self.data:
return self.data['primaryPaperLink']
return None
def record(self):
return [ self.paper_id, self.title, self.journal, self.year ]
def load_paper(paper_id):
if os.path.exists(paper_path('db_papers', paper_id)):
# print('db paper')
return DbPaper(paper_id)
if os.path.exists(paper_path('raw_papers', paper_id)):
# print('raw paper')
return RawPaper(paper_id)
print('no paper')
return None
def dedupe(a):
p = {}
for s in a:
p[s] = None
ss = sorted(p.keys())
return ss
def read_headings(fn, paper):
headings = []
found_abstract = False
found_authors = []
journal = paper.journal.lower()
authors = [ (a[0], a[1], a[1].lower(),) for a in paper.authors ]
with open(fn, 'r') as f:
for line in f.readlines():
line = re.sub(r"\S*@\S*\s?", '', line)
l = line.lower().strip()
if len(l) < 5:
continue
if line[0] == 'a' or line[0] == 'b' or line[0] == 'c' or line[0] == '1' or line[0] == '2' or line[0] == '3' or line[0] == '4':
line = line[1:]
line = line.strip("∗†‡")
line = line.replace("fl", "fl").replace('ff', 'ff').replace('ffi', 'ffi').replace('ffl', 'ffl')
line = line.strip()
if 'abstract' in l:
found_abstract = True
break
if journal and journal in l:
continue
names = [s.strip() for s in re.split(',| and ', l)]
was_found = False
for name in names:
found = find_authors(authors, name)
if found:
was_found = True
# print("found {}".format(found[1]))
if found[0]:
found_authors.append(found)
continue
headings.append(line.strip())
return headings, found_abstract
def find_authors(authors, line):
for a in authors:
if a[2] in line:
return a
return None
class AddressBook (object):
def __init__(self):
entities = {}
lookup = {}
keys, data = fetch_google_sheet()
# keys, data = read_csv('reports/pdf_institutions_deduped.csv', keys=True)
for index, line in enumerate(data):
if line[0] == line[1] or line[0] not in entities:
entities[line[0]] = index
lookup[line[1].lower().strip()] = line[0]
self.data = data
self.lookup = lookup
self.entities = entities
def find(self, address):
address = address.lower().strip().strip(string.digits)
if address in self.lookup:
entity = self.lookup[address]
index = self.entities[entity]
return self.data[index]
for part in address.split(','):
part = part.strip().replace(' ', ' ')
if part in self.lookup:
entity = self.lookup[part]
index = self.entities[entity]
return self.data[index]
return None
def fetch_spreadsheet():
scope = ['https://spreadsheets.google.com/feeds','https://www.googleapis.com/auth/drive']
credentials = ServiceAccountCredentials.from_json_keyfile_name('./.creds/Megapixels-ef28f91112a9.json', scope)
docid = "1denb7TjYsN9igHyvYah7fQ0daABW32Z30lwV7QrDJQc"
client = gspread.authorize(credentials)
spreadsheet = client.open_by_key(docid)
return spreadsheet
def fetch_worksheet(name="institutions"):
spreadsheet = fetch_spreadsheet()
return spreadsheet.worksheet(name)
def fetch_google_sheet(name="institutions"):
rows = fetch_worksheet(name).get_all_values()
keys = rows[0]
lines = rows[1:]
return keys, lines
|
