forked from jonathansick/ads_bibdesk
-
Notifications
You must be signed in to change notification settings - Fork 2
/
adsbibdesk.py
1408 lines (1216 loc) · 54.3 KB
/
adsbibdesk.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
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
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python
"""
ADS to BibDesk -- frictionless import of ADS publications into BibDesk
Copyright (C) 2013 Rui Pereira <[email protected]> and
Jonathan Sick <[email protected]>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Based on ADS to Bibdesk automator action by
Jonathan Sick, [email protected], August 2007
Input may be one of the following:
- ADS abstract page URL
- ADS bibcode
- arXiv abstract page
- arXiv identifier
"""
import datetime
import difflib
import fnmatch
import glob
import logging
import math
import optparse
import os
import pprint
import re
import socket
import sys
import tempfile
import time
# cgi.parse_qs is deprecated since 2.6
# but OS X 10.5 only has 2.5
import cgi
import urllib2
import urlparse
import subprocess as sp
try:
import AppKit
except ImportError:
# is this not the system python?
syspath = eval(sp.Popen('/usr/bin/env python -c "import sys; print(sys.path)"',
shell=True, stdout=sp.PIPE).stdout.read())
for p in syspath:
if os.path.isdir(p) and glob.glob(os.path.join(p, '*AppKit*')):
sys.path.insert(0, p)
break
# retry
try:
import AppKit
except ImportError:
import webbrowser
url = 'http://packages.python.org/pyobjc/install.html'
msg = 'Please install PyObjC...'
print msg
sp.call('osascript -e "tell application \\"System Events\\" to display dialog \\"%s\\" buttons {\\"OK\\"} default button \\"OK\\""' % msg,
shell=True, stdout=open('/dev/null', 'w'))
# open browser in PyObjC install page
webbrowser.open(url)
sys.exit()
from HTMLParser import HTMLParser, HTMLParseError
from htmlentitydefs import name2codepoint
# default timeout for url calls
socket.setdefaulttimeout(240)
def main():
"""Parse options and launch main loop"""
usage = """Usage: %prog [options] [article_token or pdf_directory]
adsbibdesk helps you add astrophysics articles listed on NASA/ADS
and arXiv.org to your BibDesk database. There are three modes
in this command line interface:
1. Article mode, for adding single papers to BibDesk given tokens.
2. PDF Ingest mode, where PDFs in a directory are analyzed and added to
BibDesk with ADS meta data.
3. Pre-print Update mode, for updating arXiv pre-prints automatically
with newer bibcodes.
In article mode, adsbibdesk accepts many kinds of article tokens:
- the URL of an ADS or arXiv article page,
- the ADS bibcode of an article (e.g. 1998ApJ...500..525S), or
- the arXiv identifier of an article (e.g. 0911.4956).
(Example: `adsbibdesk 1998ApJ...500..525S`)
In PDF Ingest mode, you specify a directory containing PDFs instead of
an article token (Example: `adsbibdesk -p pdfs` will ingest PDFs from
the pdfs/ directory).
In Pre-print Update mode, every article with an arXiv bibcode will be
updated if it has a new bibcode."""
version = "3.1"
epilog = "For more information, visit www.jonathansick.ca/adsbibdesk" \
+ " email jonathansick at mac.com or tweet @jonathansick"
parser = optparse.OptionParser(usage=usage, version=version,
epilog=epilog)
parser.add_option('-d', '--debug',
dest="debug", default=False, action="store_true",
help="Debug mode; prints extra statements")
parser.add_option('-o', '--only_pdf',
default=False, action='store_true',
help="Download and open PDF for the selected [article_token].")
pdfIngestGroup = optparse.OptionGroup(parser, "PDF Ingest Mode",
description=None)
pdfIngestGroup.add_option('-p', '--ingest_pdfs',
dest="ingestPdfs", default=False, action="store_true",
help="Ingest a folder of PDFs."
" Positional argument should be directory"
" containing PDFs."
" e.g., `adsbibdesk -p .` for the current directory")
pdfIngestGroup.add_option('-r', '--recursive',
dest='recursive', default=True, action="store_false",
help="Search for PDFs recursively in the directory tree.")
parser.add_option_group(pdfIngestGroup)
arXivUpdateGroup = optparse.OptionGroup(parser, "Pre-print Update Mode",
description=None)
arXivUpdateGroup.add_option('-u', '--update_arxiv',
default=False, action="store_true",
help='Check arXiv pre-prints for updated bibcodes')
arXivUpdateGroup.add_option('-f', '--from_date',
help='MM/YY date of publication from which to start updating arXiv')
arXivUpdateGroup.add_option('-t', '--to_date',
help='MM/YY date of publication up to which update arXiv')
parser.add_option_group(arXivUpdateGroup)
options, args = parser.parse_args()
# Get preferences from (optional) config file
prefs = Preferences()
# inject options into preferences for later reference
prefs['options'] = options.__dict__
if options.debug:
prefs['debug'] = True
# Logging saves to log file on when in DEBUG mode
# Always prints to STDOUT as well
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(name)s %(levelname)s %(message)s',
filename=prefs['log_path'])
if not prefs['debug']:
logging.getLogger('').setLevel(logging.INFO)
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
logging.getLogger('').addHandler(ch)
logging.info("Starting ADS to BibDesk")
logging.debug("ADS to BibDesk version %s", version)
logging.debug("Python: %s", sys.version)
if options.ingestPdfs:
ingest_pdfs(options, args, prefs)
elif options.only_pdf:
# short-circuit process_articles
# since BibDesk is not needed
process_token(args[0], prefs, None)
elif options.update_arxiv:
update_arxiv(options, prefs)
else:
process_articles(args, prefs)
def mkMNRAS(author, year):
# Make MNRAS bibtex entry.
# Adapted from Natalia's original version
N_authors = len(author)
author1 = re.sub('},.*|\W', '', author[0])
if (N_authors >= 2): author2 = re.sub('},.*|\W', '', author[1])
if (N_authors >= 3): author3 = re.sub('},.*|\W', '', author[2])
if (N_authors == 1): MNRAScitekey = author1 + '.' + year
if (N_authors == 2): MNRAScitekey = author1 + '.' + author2 + '.' + year
if (N_authors == 3): MNRAScitekey = author1 + '.' + author2 + '.' + author3 + '.' + year
if (N_authors >= 4): MNRAScitekey = author1 + '.etal.' + year
return {'MNRAScitekey': MNRAScitekey}
def process_articles(args, prefs, delay=15):
"""Workflow for processing article tokens"""
if args:
articleTokens = list(args)
else:
# Try to use standard input
articleTokens = [s.strip()
for s in sys.stdin.readlines()
if s.strip()]
# AppKit hook for BibDesk
bibdesk = BibDesk()
for articleToken in articleTokens:
process_token(articleToken, prefs, bibdesk)
if len(articleTokens) > 1 and articleToken != articleTokens[-1]:
time.sleep(delay)
bibdesk.app.dealloc()
def process_token(articleToken, prefs, bibdesk):
"""Process a single article token from the user.
:param articleToken: Any user-supplied `str` token.
:param prefs: A `Preferences` instance.
:param bibdesk: A `BibDesk` AppKit hook instance.
"""
# Determine what we're dealing with
# The goal is to get a URL into ADS
logging.debug("process_token found article token %s", articleToken)
connector = ADSConnector(articleToken, prefs)
# parse the ADS HTML file
ads = ADSHTMLParser(prefs=prefs)
if isinstance(connector.adsRead, basestring):
ads.parse(connector.adsRead)
# parsed from arXiv - dummy ads info
elif connector.adsRead and getattr(connector, 'bibtex') is not None:
ads.bibtex = connector.bibtex
ads.arxivid = ads.bibtex.Eprint
ads.author = ads.bibtex.Author.split(' and ')
ads.year = ads.bibtex.Year
ads.title = ads.bibtex.Title
ads.abstract = ads.bibtex.Abstract
ads.comment = ads.bibtex.AdsComment
# original URL where we *should* have gotten the info
ads.bibtex.AdsURL = connector.adsURL
# inject arXiv mirror into ArXivURL
if 'arxiv_mirror' in prefs and prefs['arxiv_mirror']:
tmpurl = urlparse.urlsplit(ads.bibtex.ArXivURL)
ads.bibtex.ArXivURL = urlparse.urlunsplit((tmpurl.scheme,
prefs['arxiv_mirror'],
tmpurl.path, tmpurl.query,
tmpurl.fragment))
# link for PDF download
try:
ads.links = {'preprint': [l.get('href', '')
for l in ads.bibtex.info['link']
if l.get('title') == 'pdf'][0]}
except IndexError:
pass
elif connector.adsRead is None:
logging.debug("process_token skipping %s", articleToken)
return False
# Get MnrasCitekey
if connector.adsRead is not None:
ads.bibtex.info.update(mkMNRAS(ads.author, ads.year))
if not isinstance(connector.adsRead, basestring):
if getattr(connector, 'bibtex') is not None:
ads.bibtex.MNRAScitekey = ads.bibtex.info['MNRAScitekey']
# Remove ADS keywords?
if not ads.prefs['ads_keywords']:
if 'keywords' in ads.bibtex.info.keys():
del ads.bibtex.info['keywords']
# get PDF first
pdf = ads.getPDF()
if prefs['options'].get('only_pdf'):
if not pdf.endswith('.pdf'):
return False
# just open PDF
reader = ('pdf_reader' in prefs and
prefs['pdf_reader'] is not None) and\
prefs['pdf_reader'] or 'Finder'
app = AppKit.NSAppleScript.alloc()
app.initWithSource_('tell application "%s" '
'to open ("%s" as POSIX file)' % (reader, pdf)
).executeAndReturnError_(None)
# get name of the used viewer
# (Finder may be defaulted to something else than Preview)
if reader == 'Finder':
reader = app.initWithSource_(
'return name of (info for (path to frontmost application))'
).executeAndReturnError_(None)[0].stringValue()
logging.debug('opening %s with %s' % (pdf, reader))
if 'skim' in reader.lower():
time.sleep(1) # give it time to open
app.initWithSource_('tell application "%s" to set view settings '
'of first document to {auto scales:true}'
% reader).executeAndReturnError_(None)
app.dealloc()
return True
# search for already existing publication
# with exactly the same title and first author
# match title and first author using fuzzy string comparison
found = difflib.get_close_matches(ads.title, bibdesk.titles,
n=1, cutoff=.7)
keptPDFs = []
# first author is the same
if found and difflib.SequenceMatcher(None,
bibdesk.authors(bibdesk.pid(found[0]))[0],
ads.author[0]).ratio() > .6:
delete_pubs = True
if prefs['debug']:
pubs = bibdesk.citekeys(bibdesk.pid(found[0]))
print "@@> Found repeated publications: %s" % pubs
answer = raw_input(" Delete them [y/N]? ")
if ((answer == '') | (answer == 'n') | (answer == 'N')):
delete_pubs = False
print "@@> Not deleting %s" % pubs
else:
print "@@> Deleting %s" % pubs
if delete_pubs:
# Copy old keywords
if not ads.prefs['ads_keywords']:
ads.bibtex.info['keywords'] = bibdesk.keywords(bibdesk.pid(found[0]))
# Deal with pdf
keptPDFs += bibdesk.safe_delete(bibdesk.pid(found[0]))
notify('Duplicate publication removed',
articleToken, ads.title)
bibdesk.refresh()
# add new entry
pub = bibdesk('import from "%s"' % ads.bibtex.__str__().replace('\\', r'\\').replace('"', r'\"'))
pub = pub.descriptorAtIndex_(1).descriptorAtIndex_(3).stringValue() # pub id
# automatic cite key
bibdesk('set cite key to generated cite key', pub)
# abstract
if ads.abstract.startswith('http://'):
# old scanned articles
bibdesk('make new linked URL at end of linked URLs '
'with data "%s"' % ads.abstract, pub)
else:
bibdesk('set abstract to "%s"'
% balance_brackets(ads.abstract.replace('\\', r'\\').replace('"', r'\"')), pub)
if pdf.endswith('.pdf'):
# register PDF into BibDesk
bibdesk('add POSIX file "%s" to beginning of linked files' % pdf, pub)
# URL for electronic version - only add it if no DOI link present
# (they are very probably the same)
elif 'http' in pdf and not bibdesk('value of field "doi"', pub).stringValue():
bibdesk('make new linked URL at end of linked URLs with data "%s"' % pdf, pub)
# add URLs as linked URL if not there yet
urls = bibdesk('value of fields whose name ends with "url"', pub, strlist=True)
urlspub = bibdesk('linked URLs', pub, strlist=True)
for u in [u for u in urls if u not in urlspub]:
bibdesk('make new linked URL at end of linked URLs with data "%s"' % u, pub)
# add old annotated files
for keptPDF in keptPDFs:
bibdesk('add POSIX file "%s" to end of linked files' % keptPDF, pub)
# automatic file name
if 'auto_file' in prefs:
if prefs['auto_file']:
bibdesk('auto file', pub)
# save bibdesk file
bibdesk('save')
notify('New publication added',
bibdesk('cite key', pub).stringValue(),
ads.title)
def balance_brackets(instr):
'''
Balance unpaired brackets in abstracts, which cause errors in Bibdesk.
Code based on
https://stackoverflow.com/questions/6701853/parentheses-pairing-issue
The difference is that it balances out the string.
Commented by Natalia@UFSC - 14/Sep/2017.
'''
# Creating a dictionary where key = opening bracket and value = closing bracket.
iparens = iter('(){}[]<>')
parens = dict(zip(iparens, iparens))
inv_parens = {v: k for k, v in parens.iteritems()}
closing = parens.values()
# Starting a stack of closing brackets to be searched for
stack = []
# Starting the paired output string
outstr = ''
for c in instr:
# See if this character matches an opening bracket in the dictionary.
# If so, save the closing bracket in the variable d -- to be matched later on!
d = parens.get(c, None)
outstr += c
# Save this to-be-matched opening bracket to the stack
if d is not None:
stack.append(d)
# For each closing bracket, check if there is a previous opening bracket by
# consulting the stack.
# Note that (not list) = False if the list is empty, and it is the pythonic way
# to test whether a list is empty.
elif c in closing:
if (stack):
c_popped = stack.pop()
# This opening bracket is unpaired: pair it!
if (c != c_popped):
outstr = outstr[:-1] + c_popped
# This closing bracket is unpaired: pair it!
else:
outstr = outstr[:-1] + inv_parens[c] + c
# If thre is anything left on the stack, add the end of the string to pair
# the opening brackets without matchs
if (stack):
outstr += ''.join(stack)
return outstr
def ingest_pdfs(options, args, prefs):
"""Workflow for attempting to ingest a directory of PDFs into BibDesk.
This workflow attempts to scape DOIs from the PDF text, which are then
added to BibDesk using the usual `process_token` function.
"""
assert len(args) == 1, "Please pass a path to a directory"
pdfDir = args[0]
assert os.path.exists(pdfDir) is True, "%s does not exist" % pdfDir
print "Searching", pdfDir
if options.recursive:
# Recursive glob solution from
# http://stackoverflow.com/questions/2186525/use-a-glob-to-find-files-recursively-in-python
pdfPaths = []
for root, dirnames, filenames in os.walk(pdfDir):
for filename in fnmatch.filter(filenames, '*.pdf'):
pdfPaths.append(os.path.join(root, filename))
else:
pdfPaths = glob.glob(os.path.join(pdfDir, "*.pdf"))
# Process each PDF, looking for a DOI
grabber = PDFDOIGrabber()
found = []
for i, pdfPath in enumerate(pdfPaths):
dois = grabber.search(pdfPath)
if len(dois) == 0:
logging.info("%i of %i: no DOIs for %s" % (i + 1, len(pdfPaths), pdfPath))
else:
found.extend(list(dois))
for doi in dois:
logging.info("%i of %i: %s = %s" % (i + 1, len(pdfPaths),
os.path.basename(pdfPath), doi))
# let process_articles inject everything
if found:
logging.info('Adding %i articles to BibDesk...' % len(found))
process_articles(found, prefs)
def update_arxiv(options, prefs):
"""
Workflow for updating arXiv pre-prints automatically with newer bibcodes
(replaces update_bibdesk_arxiv.sh)
"""
assert options.from_date is None or \
re.match('^\d{2}/\d{2}$', options.from_date) is not None, \
'--from_date needs to be in MM/YY format'
assert options.to_date is None or \
re.match('^\d{2}/\d{2}$', options.to_date) is not None, \
'--to_date needs to be in MM/YY format'
def b2d(bibtex):
"""BibTex -> publication date"""
m = re.search('Month = \{?(\w*)\}?', bibtex).group(1)
y = re.search('Year = \{?(\d{4})\}?', bibtex).group(1)
return datetime.datetime.strptime(m+y, '%b%Y')
def recent(added, fdate, tdate):
fromdate = fdate is not None and\
datetime.datetime.strptime(fdate, '%m/%y')\
or datetime.datetime(1900, 1, 1)
todate = tdate is not None and\
datetime.datetime.strptime(tdate, '%m/%y')\
or datetime.datetime(3000, 1, 1)
return fromdate <= added <= todate
# frontmost opened BibDesk document
bibdesk = BibDesk()
ids = []
# check for adsurl containing arxiv or astro.ph bibcodes
arxiv = bibdesk('return publications whose '
'(value of field "Adsurl" contains "arXiv") or '
'(value of field "Adsurl" contains "astro.ph")')
if arxiv.numberOfItems():
# extract arxiv id from the ADS url
ids = [u.split('bib_query?')[-1].split('abs/')[-1] for u in
bibdesk('tell publications whose '
'(value of field "Adsurl" contains "arXiv") or '
'(value of field "Adsurl" contains "astro.ph") '
'to return value of field "Adsurl"', strlist=True)]
dates = [b2d(b) for b in
bibdesk('tell publications whose '
'(value of field "Adsurl" contains "arXiv") or '
'(value of field "Adsurl" contains "astro.ph") '
'to return bibtex string', strlist=True)]
# arxiv ids to search
ids = [b for d, b in zip(dates, ids)
if recent(d, options.from_date, options.to_date)]
bibdesk.app.dealloc()
if not ids:
print 'Nothing to update!'
sys.exit()
else:
n = len(ids)
t = math.ceil(n * 15. / 60.)
logging.info('Checking %i arXiv entries for changes...' % n)
logging.info('(to prevent ADS flooding this will take a while, check back '
'in around %i %s)' % (t, t > 1 and 'minutes' or 'minute'))
changed = []
for n, i in enumerate(ids):
# sleep for 15 seconds, to prevent ADS flooding
time.sleep(15)
logging.debug("arxiv id %s" % i)
# these are ADS bibcodes by default
adsURL = urlparse.urlunsplit(('http', prefs['ads_mirror'],
'cgi-bin/bib_query', i, ''))
logging.debug("adsURL %s" % adsURL)
# parse the ADS HTML file
ads = ADSHTMLParser(prefs=prefs)
try:
ads.parse_at_url(adsURL)
except ADSException, err:
logging.debug('%s update failed: %s' % (i, err))
continue
logging.debug("ads.bibtex %s" % ads.bibtex)
if ads.bibtex is None: # ADSHTMLParser failed
logging.debug("FAILURE: ads.bibtex is None!")
continue
if ads.bibtex.bibcode != i:
logging.info('%i. %s has become %s' % (n + 1, i, ads.bibtex.bibcode))
changed.append(i)
else:
logging.info('%i. %s has not changed' % (n + 1, i))
continue
# run changed entries through the main loop
if changed and raw_input('Updating %i entries, continue? (y/[n]) '
% len(changed)) in ('Y', 'y'):
logging.info('(to prevent ADS flooding, we will wait for a while between '
'each update, so go grab a coffee)')
process_articles(changed, prefs)
elif not changed:
logging.info('Nothing to update!')
# adapted of original by Moises Aranas
# https://github.com/maranas/pyNotificationCenter
def notify(title, subtitle, desc, sticky=False):
try:
import objc
notification = objc.lookUpClass('NSUserNotification').alloc().init()
notification.setTitle_(title)
notification.setInformativeText_(desc)
notification.setSubtitle_(subtitle)
objc.lookUpClass('NSUserNotificationCenter').defaultUserNotificationCenter().scheduleNotification_(notification)
notification.dealloc()
# this will be either ImportError or objc.nosuchclass_error
except Exception:
# revert to growl
if subtitle:
desc = subtitle + ': ' + desc
growlNotify(title, desc, sticky)
def growlNotify(title, desc, sticky=False):
title = title.replace('"', r'\"')
desc = desc.replace('"', r'\"')
# http://bylr.net/3/2011/09/applescript-and-growl/
# is growl running?
app = AppKit.NSAppleScript.alloc()
growl = app.initWithSource_('tell application "System Events" to return '
'processes whose creator type contains "GRRR"'
).executeAndReturnError_(None)[0]
if growl.numberOfItems():
growlapp = growl.descriptorAtIndex_(1).descriptorAtIndex_(3).stringValue()
# register
app.initWithSource_('tell application "%s" to register as '
'application "BibDesk" '
'all notifications {"BibDesk notification"} '
'default notifications {"BibDesk notification"}'
% growlapp).executeAndReturnError_(None)
# and notify
app.initWithSource_('tell application "%s" to notify with name '
'"BibDesk notification" application name "BibDesk" '
'priority 0 title "%s" description "%s" %s'
% (growlapp, title, desc, "with sticky" if sticky else '')
).executeAndReturnError_(None)
app.dealloc()
def hasAnnotations(f):
return sp.Popen("strings %s | grep -E 'Contents[ ]{0,1}\('" % f,
shell=True, stdout=sp.PIPE,
stderr=open('/dev/null', 'w')).stdout.read() != ''
def getRedirect(url):
"""Utility function to intercept final URL of HTTP redirection"""
import httplib
url = urlparse.urlsplit(url)
conn = httplib.HTTPConnection(url.netloc)
conn.request('GET', url.path + '?' + url.query)
return conn.getresponse().getheader('Location')
class PDFDOIGrabber(object):
"""Converts PDFs to text and attempts to match all DOIs"""
def __init__(self):
super(PDFDOIGrabber, self).__init__()
regstr = r'(10[.][0-9]{4,}(?:[.][0-9]+)*/(?:(?!["&\'<>\)])\S)+)'
self.pattern = re.compile(regstr)
def search(self, pdfPath):
"""Return a list of DOIs in the text of the PDF at `pdfPath`"""
jsonPath = os.path.splitext(pdfPath)[0] + ".json"
if os.path.exists(jsonPath):
os.remove(jsonPath)
sp.call('pdf2json -q "%s" "%s"' % (pdfPath, jsonPath), shell=True)
data = open(jsonPath, 'r').read()
doiMatches = self.pattern.findall(data)
if os.path.exists(jsonPath):
os.remove(jsonPath)
# strings can find some stuff that pdf2json does not
if not doiMatches:
data = sp.Popen("strings %s" % pdfPath,
shell=True, stdout=sp.PIPE,
stderr=open('/dev/null', 'w')).stdout.read()
doiMatches = self.pattern.findall(data)
return set(doiMatches)
class ADSConnector(object):
"""Receives input (token), derives an ADS url, and attempts to connect
to the corresponding ADS abstract page with urllib2.urlopen().
Tokens are tested in order of:
- arxiv identifiers
- bibcodes / digital object identifier (DOI)
- ADS urls
- arxiv urls
"""
def __init__(self, token, prefs):
super(ADSConnector, self).__init__()
self.token = str(token)
self.prefs = prefs
self.adsURL = None # string URL to ADS
self.adsRead = None # a urllib2.urlopen connection to ADS
self.urlParts = urlparse.urlsplit(token) # supposing it is a URL
# An arXiv identifier or URL?
if self._is_arxiv():
logging.debug("ADSConnector found arXiv ID %s", self.token)
# Try to open the ADS page
if not self._read(self.adsURL):
# parse arxiv instead:
logging.debug('ADS page (%s) not found for %s' %
(self.adsURL, self.token))
notify('ADS page not found', self.token,
'Parsing the arXiv page...')
arxivBib = ArXivParser()
try:
arxivBib.parse_at_id(self.arxivID)
logging.debug("arXiv page (%s) parsed for %s" % (arxivBib.url, self.token))
except ArXivException, err:
logging.debug("ADS and arXiv failed, you're in trouble...")
raise ADSException(err)
# dummy adsRead and bibtex
self.adsRead = True
self.bibtex = arxivBib
# A bibcode from ADS?
elif not self.urlParts.scheme and self._is_bibcode():
logging.debug("ADSConnector found bibcode/DOI %s", self.token)
else:
# If the path lacks http://, tack it on because the token *must* be a URL now
if not self.token.startswith("http://"):
self.token = 'http://' + self.token
# supposing it is a URL
self.urlParts = urlparse.urlsplit(self.token)
# An abstract page at any ADS mirror site?
if self.urlParts.netloc in self.prefs.adsmirrors and self._is_ads_page():
logging.debug("ADSConnector found ADS page %s", self.token)
def _is_arxiv(self):
"""Try to classify the token as an arxiv article, either:
- new style (YYMM.NNNN), or
- old style (astro-ph/YYMMNNN)
:return: True if ADS page is recovered
"""
arxivPattern = re.compile('(\d{4,6}.\d{4,6}|astro\-ph/\d{7})')
arxivMatches = arxivPattern.findall(self.token)
if len(arxivMatches) == 1:
self.arxivID = arxivMatches[0]
self.adsURL = urlparse.urlunsplit(('http',
self.prefs['ads_mirror'],
'cgi-bin/bib_query',
'arXiv:%s' % self.arxivID, ''))
return True
else:
self.arxivID = None
return False
def _is_bibcode(self):
"""Test if the token corresponds to an ADS bibcode or DOI"""
self.adsURL = urlparse.urlunsplit(('http', self.prefs['ads_mirror'],
'doi/%s' % self.token, '', ''))
read = self._read(self.adsURL)
if read:
return read
else:
self.adsURL = urlparse.urlunsplit(('http',
self.prefs['ads_mirror'],
'abs/%s' % self.token, '', ''))
read = self._read(self.adsURL)
return read
def _is_ads_page(self):
"""Test if the token is a url to an ADS abstract page"""
# use our ADS mirror
url = self.urlParts
self.adsURL = urlparse.urlunsplit((url.scheme,
self.prefs['ads_mirror'],
url.path, url.query, url.fragment))
return self._read(self.adsURL)
def _read(self, adsURL):
"""Attempt a connection to adsURL, saving the read to
self.adsread.
:return: True if successful, False otherwise
"""
try:
# remove <head>...</head> - often broken HTML
self.adsRead = re.sub(r'<head>[\s\S]*</head>', '',
urllib2.urlopen(adsURL).read())
return True
except urllib2.HTTPError:
return False
class Preferences(object):
"""Manages the preferences on disk and in memory. Preferences are accessed
with by a dictionary-like interface.
"""
def __init__(self):
self.prefsPath = os.path.join(os.getenv('HOME'), '.adsbibdesk')
self._adsmirrors = ['adsabs.harvard.edu',
'cdsads.u-strasbg.fr',
'ukads.nottingham.ac.uk',
'esoads.eso.org',
'ads.ari.uni-heidelberg.de',
'ads.inasan.ru',
'ads.mao.kiev.ua',
'ads.astro.puc.cl',
'ads.on.br',
'ads.nao.ac.jp',
'ads.bao.ac.cn',
'ads.iucaa.ernet.in',
'www.ads.lipi.go.id']
self.prefs = self._getDefaultPrefs() # Hard coded defaults dictionary
newPrefs = self._getPrefs() # load user prefs from disk
self.prefs.update(newPrefs) # override defaults with user prefs
self._keys = self.prefs.keys()
self._iterIndex = -1
def __getitem__(self, key):
return self.prefs[key]
def __setitem__(self, key, value):
self.prefs[key] = value
self._keys = self.prefs.keys()
def __iter__(self):
return self
def next(self):
if self._iterIndex == len(self._keys) - 1:
self._iterIndex = -1
raise StopIteration
self._iterIndex += 1
return self._keys[self._iterIndex]
def _getDefaultPrefs(self):
""":return: a dictionary of the full set of default preferences. This
is done in case the user's preference file is missing a key-value pair.
"""
return {"ads_mirror": "adsabs.harvard.edu",
"arxiv_mirror": None,
"download_pdf": True,
"pdf_reader": None,
"auto_file": True,
"ssh_user": None,
"ssh_server": None,
"ads_keywords": True,
"debug": False,
"log_path": os.path.expanduser("~/.adsbibdesk.log")}
def _getPrefs(self):
"""Read preferences files from `self.prefsPath`, creates one otherwise."""
prefs = {}
# create a default preference file if non existing
if not os.path.exists(self.prefsPath):
self._writeDefaultPrefs()
for l in open(self.prefsPath):
if l.strip() and not l.strip().startswith('#'):
if '=' not in l:
# badly formed setting
continue
k, v = l.strip().split('=')
if not v:
v = None
elif v.strip().lower() in ('true', 'yes'):
v = True
elif v.strip().lower() in ('false', 'no'):
v = False
elif v.strip().lower() == 'none':
v = None
prefs[k] = v
return prefs
def _writeDefaultPrefs(self):
"""
Set a default preferences file (~/.adsbibdesk)
"""
prefs = open(self.prefsPath, 'w')
print >> prefs, """# ADS mirror
ads_mirror=%s
# arXiv mirror
# (leave it unset to use the arXiv mirror pointed by your ADS mirror)
arxiv_mirror=%s
# download PDFs?
download_pdf=%s
# set these to use your account on a remote machine for fetching
# (refereed) PDF's you have no access locally
ssh_user=%s
ssh_server=%s""" % (self.prefs['ads_mirror'], self.prefs['arxiv_mirror'],
self.prefs['download_pdf'], self.prefs['ssh_user'],
self.prefs['ssh_server'])
prefs.close()
@property
def adsmirrors(self):
return self._adsmirrors
class BibTex(object):
def __init__(self, url):
"""
Create BibTex instance from ADS BibTex URL
"""
bibtex = urllib2.urlopen(url).readlines()
bibtex = ' '.join([l.strip() for l in bibtex]).strip()
bibtex = bibtex[re.search('@[A-Z]+\{', bibtex).start():]
self.type, self.bibcode, self.info = self.parsebib(bibtex)
def __str__(self):
return (','.join(['@' + self.type + '{' + self.bibcode] +
['%s=%s' % (i, j) for i, j in self.info.items()]) + '}'
).encode('utf-8')
def parsebib(self, bibtex):
"""
Parse bibtex code into dictionary
"""
r = re.search('(?<=^@)(?P<type>[A-Z]+){(?P<bibcode>\S+)(?P<info>,.+)}$', bibtex)
s = re.split('(,\s\w+\s=\s)', r.group('info'))
info = dict([(i[1:].replace('=', '').strip(), j.strip())
for i, j in zip(s[1::2], s[2::2])])
return r.group('type'), r.group('bibcode'), info
class BibDesk(object):
def __init__(self):
"""
Manage BibDesk publications using AppKit
"""
self.app = AppKit.NSAppleScript.alloc()
self.refresh()
def __call__(self, cmd, pid=None, strlist=False, error=False):
"""
Run AppleScript command on first document of BibDesk
:param cmd: AppleScript command string
:param pid: address call to first/last publication of document
:param strlist: return output as list of string
:param error: return full output of call, including error
"""
if pid is None:
# address all publications
cmd = 'tell first document of application "BibDesk" to %s' % cmd
else:
# address a single publicatin
cmd = 'tell first document of application "BibDesk" to '\
'tell first publication whose id is "%s" to %s' % (pid, cmd)
output = self.app.initWithSource_(cmd).executeAndReturnError_(None)
if not error:
output = output[0]
if strlist:
# objective C nuisances...
output = [output.descriptorAtIndex_(i + 1).stringValue()
for i in range(output.numberOfItems())]
return output
def refresh(self):
self.titles = self('return title of publications', strlist=True)
self.ids = self('return id of publications', strlist=True)
self.keys = self('return cite key of publications', strlist=True)
self.kwords = self('return keywords of publications', strlist=True)
def pid(self, title):
return self.ids[self.titles.index(title)]
def authors(self, pid):
"""
Get name of authors of publication
"""
return self('name of authors', pid, strlist=True)
def citekeys(self, pid):
"""
Get citekeys of publication
"""
return self.keys[self.ids == pid]
def keywords(self, pid):
"""
Get keywords of publication
"""
return '{' + self.kwords[self.ids == pid] + '}'
def safe_delete(self, pid):
"""
Safely delete publication + PDFs, taking into account
the existence of PDFs with Skim notes
"""
keptPDFs = []
files = self('POSIX path of linked files', pid, strlist=True)
notes = self('text Skim notes of linked files', pid, strlist=True)
for f, n in zip([f for f in files if f is not None],
[n for n in notes if n is not None]):
if f.lower().endswith('pdf'):
if '_notes_' in f:
keptPDFs.append(f)
else:
# check for annotations
if n or hasAnnotations(f):
suffix = 1
path, ext = os.path.splitext(f)
backup = path + '_notes_%i.pdf' % suffix
while os.path.exists(backup):
suffix += 1
backup = path + '_notes_%i.pdf' % suffix