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
|
# -*- coding: iso-8859-1 -*-
# This file is part of pybliographer
#
# Copyright (C) 1998-2004 Frederic GOBRY
# Email : gobry@pybliographer.org
#
# 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 2
# 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, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
#
#
# Extension module for Medline files
from Pyblio import Base, Fields, Types, Autoload, Open, Iterator, Utils, Config
import re, string,sys
header = re.compile ('^(\w\w[\w ][\w ])- (.*)$')
contin = re.compile ('^ (.*)$')
one_to_one = Config.get ('medline/mapping').data
medurl = 'http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?cmd=prlinks&dbfrom=pubmed&retmode=ref&id='
class MedlineIterator (Iterator.Iterator):
def __init__ (self, file):
self.file = file
return
def first (self):
# rewind the file
self.file.seek (0)
return self.next ()
def next (self):
current = None
data = ''
table = {}
# Skip whitespace
while 1:
line = self.file.readline ()
if line == '': return table
line = string.rstrip (line)
if line != '': break
while 1:
head = header.match (line)
if head:
if current:
if table.has_key (current):
table [current].append (data)
else:
table [current] = [data]
current = string.strip (head.group (1))
data = head.group (2)
else:
cont = contin.match (line)
if cont:
data = data + ' ' + cont.group (1)
line = self.file.readline ()
if line == '': break
line = string.rstrip (line)
if line == '': break
# don't forget the last item
if current:
if table.has_key (current):
table [current].append (data)
else:
table [current] = [data]
# create the entry with the actual fields
norm = {}
type = Types.get_entry ('article')
if table.has_key ('PMID'):
norm ['url'] = Fields.URL (medurl + table ['PMID'] [0])
norm ['medline-pmid'] = Fields.Text (table ['PMID'] [0])
del table ['PMID']
if table.has_key ('UI'):
norm [one_to_one ['UI']] = Fields.Text (table ['UI'] [0])
del table ['UI']
if table.has_key ('AU'):
group = Fields.AuthorGroup ()
for au in table ['AU']:
# analyze the author by ourself.
first, last, lineage = [], [], []
for part in string.split (au, ' '):
if part.isupper ():
# in upper-case, this is a first name
if len (last) > 0:
first.append (part)
else:
# if there is no last name, there can't be a first name
last.append (part)
else:
if len (first) > 0:
# there was a first name, this must be a lineage
lineage.append (part)
else:
last.append (part)
if len (first) > 1:
print "medline: long first name found. skipping."
first = first [0:1]
if len (first) > 0:
first = string.join (first [0], '. ') + '.'
else:
first = None
if len (last) > 0:
last = string.join (last, ' ')
else:
last = None
if len (lineage) > 0:
lineage = string.join (lineage, ' ')
else:
lineage = None
group.append (Fields.Author ((None, first, last, lineage)))
norm [one_to_one ['AU']] = group
del table ['AU']
if table.has_key ('DP'):
fields = string.split (table ['DP'][0], ' ')
norm [one_to_one ['DP']] = Fields.Date (fields [0])
del table ['DP']
# The simple fields...
for f in table.keys ():
f_mapped = one_to_one.get(f, 'medline-%s' %(f.lower()))
text_type = Types.get_field(f_mapped).type
norm [f_mapped] = text_type (string.join (table [f], " ; "))
return Base.Entry (None, type, norm)
# UI identifiant unique
# AU auteurs *
# TI titre
# LA langue *
# MH mots cls *
# PT * type : JOURNAL ARTICLE, REVIEW, REVIEW, TUTORIAL,CLINICAL TRIAL,
# RANDOMIZED CONTROLLED TRIAL, LETTER, EDITORIAL, MULTICENTER STUDY,
# NEWS, HISTORICAL ARTICLE
# DA date de ?? en yyyymmdd
# DP date de ?? en yyyy mois +/-j
# IS
# TA titre de la revue
# PG
# SB
# CY pays d'dition ?
# IP
# VI
# JC
# AA semble tre toujours Author ou AUTHOR
# EM date de?? en yyyymm
# AB
# AD
# PMID
# SO rfrence complte
# RN semble indexer des substances chimiques
# TT titre dans la langue d'origine
# 4099 URL vers l'article
# 4100 URL vers abstract de l'article ??
class Medline (Base.DataBase):
id = 'Medline'
properties = {
'change_id' : 0,
'change_type' : 0
}
def __init__ (self, url):
Base.DataBase.__init__ (self, url)
iter = iterator (url, 0)
entry = iter.first ()
while entry:
self.add (entry)
entry = iter.next ()
return
def writer (iter, output, **argh):
entry = iter.first ()
while entry:
ekeys = {}
for k in entry.keys (): ekeys [k] = 1
med = one_to_one ['UI']
if entry.has_key (med):
del ekeys [med]
ui = str (entry [med])
else:
print "warning: entry has no medline reference"
ui = 0
output.write ('%-4.4s- %s\n' % ('UI', ui))
med = one_to_one ['AU']
if entry.has_key (med):
del ekeys [med]
for auth in entry [med]:
first = auth.first or ''
compact = []
for seq in string.split (first, ' '):
if len (seq) > 0: compact.append (seq [0])
first = string.join (compact, '')
text = string.join ((auth.last or '', first, auth.lineage or ''), ' ')
output.write ('%-4.4s- %s\n' % ('AU', text))
med = one_to_one ['DP']
if entry.has_key (med):
del ekeys [med]
output.write ('%-4.4s- %s\n' % ('DP', str (entry [med])))
# write the remaining know fields
for key in one_to_one.keys ():
field = one_to_one [key]
if not ekeys.has_key (field): continue
del ekeys [field]
output.write ('%-4.4s- %s\n' % (key, Utils.format (str (entry [field]),
75, 0, 6)))
# write the unknown fields
remaining = ekeys.keys ()
remaining.sort ()
for field in remaining:
if field [0:8] == 'medline-':
key = string.upper (field [8:])
output.write ('%-4.4s- %s\n' % (key, Utils.format (str (entry [field]),
75, 0, 6)))
entry = iter.next ()
if entry: output.write ('\n')
def opener (url, check):
base = None
if (not check) or (url.url [2] [-4:] == '.med'):
base = Medline (url)
return base
def iterator (url, check):
''' This methods returns an iterator that will parse the
database on the fly (useful for merging or to parse broken
databases '''
if check and url.url [2] [-4:] != '.med': return
return MedlineIterator (open (Open.url_to_local (url), 'r'))
Autoload.register ('format', 'Medline', {'open' : opener,
'write' : writer,
'iter' : iterator})
### Local Variables:
### Mode: python
### py-master-file : "ut_medline.py"
### End:
|
