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
|
###############################################################################
#
# This file is part of the Utopia Documents application.
# Copyright (c) 2008-2014 Lost Island Labs
# <info@utopiadocs.com>
#
# Utopia Documents is free software: you can redistribute it and/or modify
# it under the terms of the GNU GENERAL PUBLIC LICENSE VERSION 3 as
# published by the Free Software Foundation.
#
# Utopia Documents 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.
#
# In addition, as a special exception, the copyright holders give
# permission to link the code of portions of this program with the OpenSSL
# library under certain conditions as described in each individual source
# file, and distribute linked combinations including the two.
#
# You must obey the GNU General Public License in all respects for all of
# the code used other than OpenSSL. If you modify file(s) with this
# exception, you may extend this exception to your version of the file(s),
# but you are not obligated to do so. If you do not wish to do so, delete
# this exception statement from your version.
#
# You should have received a copy of the GNU General Public License
# along with Utopia Documents. If not, see <http://www.gnu.org/licenses/>
#
###############################################################################
import base64
import common.eutils
import common.nlm
import common.utils
import re
import spineapi
import urllib
import utopia.document
from lxml import etree
# Turn a string into a matching regex with a bit of fuzz
def fuzz(input, strict = False):
if strict:
ANY = r'.?'
else:
ANY = r'.{0,4}'
return r'\.'.join((re.sub(r'[^\w\d.]', ANY,
re.sub(r'(^[a-zA-Z0-9#]*;|&[^;]+;|&[a-zA-Z0-9#]*$)', r'.', token))
for token in input.split('.')))
class PubMedCentral(utopia.document.Annotator):
"""PubMedCentral NLM parsing"""
keys = ('publication-title', 'publisher', 'issn', 'doi', 'pmid', 'pmcid', 'pii', 'authors', 'title',
'volume', 'issue', 'pages', 'pagefrom', 'pageto', 'abstract', 'keywords', 'year', 'month',
'abbreviations', 'label', 'url', 'type', 'html', 'displayText')
@utopia.document.buffer
def on_ready_event(self, document):
info = common.nlm.parse(common.utils.metadata(document, 'raw_pmc_nlm'))
if info is not None and len(info) > 0:
# Enrich citation information with identifiers from PMC
parser = etree.XMLParser(ns_clean=True, recover=True, remove_blank_text=True, encoding='utf8')
pmids = dict(((citation['pmid'], citation['id']) for citation in info['citations'] if 'pmid' in citation and 'id' in citation))
if len(pmids) > 0:
pubmed_abstracts = etree.fromstring(common.eutils.efetch(id=','.join(pmids.keys()), retmode='xml', rettype='abstract'), parser)
for idList in pubmed_abstracts.xpath('PubmedArticle/PubmedData/ArticleIdList'):
#print etree.tostring(idList)
pmid = idList.findtext('ArticleId[@IdType="pubmed"]')
if pmid in pmids:
citation = info['citations_by_id'][pmids[pmid]]
for key_name, id_name in (('doi', 'doi'), ('pmcid', 'pmc'), ('pii', 'pii')):
id = idList.findtext('ArticleId[@IdType="{0}"]'.format(id_name))
if key_name not in citation and id is not None:
citation[key_name] = id
# Create Metadata link annotation
link = document.newAccList('metadata', 50)
link['property:sourceDatabase'] = 'pmc'
link['property:sourceTitle'] = 'PubMed Central'
link['property:sourceDescription'] = '<p><a href="http://www.ncbi.nlm.nih.gov/pmc/">PubMed Central</a> is the U.S. National Institutes of Health (NIH) digital archive of biomedical and life sciences journal literature.</p>'
# Create Metadata annotation
annotation = spineapi.Annotation()
annotation['concept'] = 'DocumentMetadata'
for k in self.keys:
v = info.get(k)
if v is not None:
annotation['property:{0}'.format(k)] = v
document.addAnnotation(annotation, link['scratch'])
# Create Bibliography annotations
for citation in info.get('citations', []):
annotation = spineapi.Annotation()
annotation['concept'] = 'DocumentReference'
for k in self.keys:
v = citation.get(k)
if v is not None:
annotation['property:{0}'.format(k)] = v
document.addAnnotation(annotation, link['scratch'])
# Citations
for citation in info['citations']:
# Find cross refs
for pre, label, post in citation.get('contexts', []):
matches = document.findInContext(pre, label, post)
#print matches
if len(matches) > 0:
try:
annotation = spineapi.Annotation()
annotation['concept'] = 'ForwardCitation'
annotation['property:state'] = 'found'
if 'title' in citation:
annotation['property:title'] = citation['title']
if 'id' in citation:
annotation['property:bibid'] = citation['id']
if 'doi' in citation and citation['doi'].startswith('10.1371/'):
citation['pdf'] = 'http://www.ploscompbiol.org/article/fetchObjectAttachment.action?uri={0}&representation=PDF'.format('info:doi/{0}'.format(citation['doi']))
if 'pmcid' in citation:
citation['pdf'] = 'http://www.ncbi.nlm.nih.gov/pmc/articles/{0}/pdf/'.format(citation['pmcid'])
#print citation
for k in self.keys + ('authors', 'pdf', 'first_author_surname'):
if k in citation:
annotation['property:{0}'.format(k)] = citation[k]
#print annotation.get('property:label'), annotation.get('property:pdf')
for match in matches:
annotation.addExtent(match)
document.addAnnotation(annotation, link['scratch'])
#print citation
except:
raise
pass # FIXME
# Tables
for id, table in info.get('tables', {}).iteritems():
if 'caption' in table and 'xml' in table:
regex = fuzz(table['caption'], strict = True)
matches = document.search(regex, spineapi.RegExp + spineapi.IgnoreCase)
if len(matches) == 1:
annotation = spineapi.Annotation()
annotation['concept'] = 'Table'
annotation['session:upload_files'] = 'data:application/xml;name=data.xml;base64,%s' % base64.standard_b64encode(table['xml'])
annotation.addExtent(matches[0])
document.addAnnotation(annotation, link['scratch'])
else:
print '*********** failed to match table:', id
|
