~ubuntu-branches/debian/jessie/bibus/jessie

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
# Copyright 2004,2005 Pierre Martineau <pmartino@users.sourceforge.net>
# This file is part of Bibus, a bibliographic database that can
# work together with OpenOffice.org to generate bibliographic indexes.
#
# Bibus 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.
#
# Bibus 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 Bibus; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA.
#
# RIS format
# from ReferenceManger Web site
#
from __future__ import generators		# to be removed in python 2.3
import BIB

DEFAULT_ENCODING = 'latin_1'

class importRef(object):
	"""Class is iterable. Return records one by one with None for the id (first field)."""
	# conversion RIS <-> Openoffice.org Publication Type: dictionary Type[RIS name]=OpenofficeName. Only REQUIRED for NON ARTICLE
 	Type={
	'ABST':'MISC',
	'ADVS':'MISC' ,
	'ART':'MISC' ,
	'BILL':'MISC' ,
	'BOOK':'BOOK' ,
	'CASE':'MISC' ,
	'CHAP':'INBOOK' ,
	'COMP':'MISC' ,
	'CONF':'PROCEEDINGS' ,
	'CTLG':'MISC' ,
	'DATA':'MISC' ,
	'ELEC':'MISC' ,
	'GEN':'MISC' ,
	'HEAR':'UNPUBLISHED' ,
	'ICOMM':'UNPUBLISHED' ,
	'INPR':'ARTICLE' ,
	'JFULL':'ARTICLE' ,
	'JOUR':'ARTICLE' ,
	'MAP':'MISC' ,
	'MGZN':'JOURNAL' ,
	'MPCT': 'MISC' ,
	'MUSIC': 'MISC' ,
	'NEWS':'JOURNAL' ,
	'PAMP': 'MISC' ,
	'PAT': 'MISC' ,
	'PCOMM':'UNPUBLISHED' ,
	'RPRT': 'TECHREPORT' ,
	'SER': 'INCOLLECTION',
	'SLIDE': 'MISC' ,
	'SOUND': 'MISC' ,
	'STAT': 'MISC' ,
	'THES': 'PHDTHESIS',
	'UNBILL': 'MISC' ,
	'UNPB':'UNPUBLISHED' ,
	'VIDEO': 'MISC'
	}
	# types in clear to put in the field howpublished
 	TypeFull={
	'ABST':'Abstract',
	'ADVS':'Audiovisual material' ,
	'ART':'Art Work' ,
	'BILL':'Bill/Resolution' ,
	'BOOK':'Book' ,
	'CASE':'Case' ,
	'CHAP':'Book chapter' ,
	'COMP':'Computer program' ,
	'CONF':'Conference proceeding' ,
	'CTLG':'Catalog' ,
	'DATA':'Data file' ,
	'ELEC':'Electronic citation' ,
	'GEN':'Generic' ,
	'HEAR':'Hearing' ,
	'ICOMM':'Internet Communication' ,
	'INPR':'In Press' ,
	'JFULL':'Journal' ,
	'JOUR':'Journal' ,
	'MAP':'Map' ,
	'MGZN':'Magazine article' ,
	'MPCT': 'Motion picture' ,
	'MUSIC': 'Music score' ,
	'NEWS':'Newspaper' ,
	'PAMP': 'Pamphlet' ,
	'PAT': 'Patent' ,
	'PCOMM':'Personal communication' ,
	'RPRT': 'Report' ,
	'SER': 'Serial',
	'SLIDE': 'Slide' ,
	'SOUND': 'Sound recording' ,
	'STAT': 'Statute' ,
	'THES': 'Thesis/Dissertation',
	'UNBILL': 'Unenacted bill/resolution' ,
	'UNPB':'Unpublished work' ,
	'VIDEO': 'Video recording'
	}

	def __init__(self,infile):
		self.infile = infile	# must be a file type. Need a readline() function.
		while self.infile.read(1) != 'T': pass	# this is needed because EndNote8 refer files start with strange chars
		else: self.infile.seek(-1,1)

	def __iter__(self):
		"""Generator of records. for record in <instance>: ...
		RIS record starts with "TY  - " and end with "ER  - "
		"""
		record  = []
		line = self.infile.readline()
		while line != '':					# we should make it more robust by testing for TY as the first field
			if line.strip() != '':
				#print 'line = %r' %line
				if line[:6] != "ER  - ":	# still not finished
					if line[2:6] != "  - ": # it is a continuation of the previous line
						#print record,line
						record[-1] = ' '.join([record[-1],line[:-1].strip()])
					else:
						record.append(line[:-1].strip())
				elif record != []:
					#print record
					yield self.__convertRecord(record)
					record  = []
				else:
					pass
			line = self.infile.readline()

	def __convertRecord(self,record):
		"""return a list of the record fields using
		('Identifier', 'Bibliographic_Type', 'Address', 'Annote', 'Author', 'Booktitle', 'Chapter', 'Edition', 'Editor','HowPublished', 'Institution', 'Journal', 'Month', 'Note', 'Number', 'Organizations', 'Pages', 'Publisher', 'School', 'Series', 'Title', 'Report_Type', 'Volume', 'Year', 'URL', 'Custom1', 'Custom2', 'Custom3', 'Custom4', 'Custom5', 'ISBN','Abstract')"""
		Record={}
		for line in record:
				refKey,tmpline = line[:2].strip(),line[6:].strip()
				if tmpline.endswith('.'):
					tmpline = tmpline[:-1].rstrip()   	# remove final dot if present
				if Record.has_key(refKey):	   # create a new key or add to a previous one
					Record[refKey] = BIB.SEP.join([Record[refKey],tmpline])
				else:
					Record[refKey] = tmpline
		#print Record
		#
		try: Identifier = Record['ID']
		except KeyError : Identifier = ''
		#
		try: Bibliographic_Type = BIB.BIBLIOGRAPHIC_TYPE[importRef.Type[Record['TY'].split(BIB.SEP)[0]]]
		except: Bibliographic_Type = BIB.BIBLIOGRAPHIC_TYPE['ARTICLE'] # default type = ARTICLE
		#
		try: Address = Record['AD']
		except KeyError: Address = ''
		#
		Annote = ''
		#
		try: Author = Record['A1'].replace('.','')		# remove all the dots
		except KeyError:
			try: Author = Record['AU'].replace('.','')	# remove all the dots
			except KeyError: Author = ''
		#
		try:
			if Bibliographic_Type != 'BOOK':
				Booktitle = Record['BT']
			else:
				raise KeyError
		except KeyError: Booktitle = ''
		#
		Chapter = ''
		#
		Edition = ''
		#
		try: Editor = Record['A3'].replace('.','')	# remove all the dots
		except KeyError: Editor = ''
		#
		HowPublished = importRef.TypeFull[Record['TY']]					# we put the record type, so we now it is a patent, etc...
		#
		Institution = ''
		#
		try: Journal =  Record['JA'].replace('.','')
		except KeyError:
			try: Journal =  Record['JO']
			except KeyError:
				try: Journal =  Record['JF']
				except KeyError: Journal = ''
		#
		try: Month = Record['Y1'].split('/')[1]
		except KeyError:
			try: Month = Record['PY'].split('/')[1]
			except (KeyError,IndexError): Month = ''
		except IndexError:
			Month = ''
		#
		try: Note = Record['N1']
		except: Note = ''
		#
		try: Number = Record['IS']
		except KeyError: Number = ''
		#
		Organizations = ''
		#
		try:
			endPage = Record['EP']
			try: Pages = '-'.join( (Record['SP'] , endPage) )
			except KeyError: Pages = endPage
		except KeyError:
			try: Pages = Record['SP']
			except KeyError: Pages = ''
		#
		try: publiAddress = Record['CY']
		except KeyError: publiAddress = ''
		if publiAddress:
			try: Publisher = ', '.join( (Record['PB'], publiAddress) )	# Publisher, Address
			except KeyError: Publisher = publiAddress
		else:
			try: Publisher = Record['PB']
			except KeyError: Publisher = ''
		#
		School = ''
		#
		try: Series = Record['T3']
		except KeyError: Series = ''
		#
		try:
			Title = Record['T1']
		except KeyError:
			try: Title = Record['TI']
			except KeyError:
				if Bibliographic_Type != 'BOOK':
					try:
						Title = Record['BT']
					except KeyError:
						Title = ''
				else:
					Title = ''
		#
		Report_Type = ''
		#
		try: Volume = Record['VL']
		except KeyError: Volume = ''
		#
		try: Year = Record['Y1'].split('/')[0]
		except:
			try: Year = Record['PY'].split('/')[0]
			except: Year = ''
		#
		try: URL = Record['UR']
		except KeyError: URL = ''
		#
		try: Custom1 = Record['U1']
		except KeyError: Custom1 = ''
		#
		try: Custom2 = Record['U2']
		except KeyError: Custom2 = ''
		#
		try: Custom3 = Record['U3']
		except KeyError: Custom3 = ''
		#
		try: Custom4 = Record['U4']
		except KeyError: Custom4 = ''
		#
		try: Custom5 = Record['U5']
		except KeyError: Custom5 = ''
		#
		try: ISBN = Record['SN']
		except KeyError: ISBN = ''
		#
		try: Abstract = Record['N2']
		except KeyError:
			try: Abstract = Record['AB']		# ScienceDirect uses 'AB' for Abstracts instead of 'N2'
			except KeyError: Abstract = ''
		#
		#print [Identifier, Bibliographic_Type,Address, Annote, Author, Booktitle, Chapter, Edition, Editor,HowPublished, Institution, Journal, Month, Note, Number,Organizations, Pages,Publisher,School, Series, Title, Report_Type, Volume,Year,URL,Custom1,Custom2,Custom3,Custom4,Custom5,ISBN,Abstract]
		return [None,Identifier, Bibliographic_Type, Address, Annote, Author, Booktitle, Chapter, Edition, Editor,HowPublished, Institution, Journal, Month, Note, Number,Organizations, Pages, Publisher, School, Series, Title, Report_Type, Volume,Year,URL,Custom1,Custom2,Custom3,Custom4,Custom5,ISBN,Abstract]