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
|
# Author: Srinath Avadhanula
# This file is distributed as part of the vim-latex project
# http://vim-latex.sf.net
import re
import os
try:
from urllib.request import urlopen, pathname2url
except ImportError:
from urllib import urlopen, pathname2url
# Compatibility functions
# Check for existence of builtin function next()
try:
next
except NameError:
def next(it):
return it.next()
# Define items(dict) as an iterator over the items
if not("iteritems" in dir(dict())):
# In python3, the job of iteritems() is done by items()
def items(dictionary):
return dictionary.items()
else:
# In python2, we use iteritems()
def items(dictionary):
return dictionary.iteritems()
class Bibliography(dict):
def __init__(self, txt, macros={}):
"""
txt:
a string which represents the entire bibtex entry. A typical
entry is of the form:
@ARTICLE{ellington:84:part3,
author = {Ellington, C P},
title = {The Aerodynamics of Hovering Insect Flight. III. Kinematics},
journal = {Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences},
year = {1984},
volume = {305},
pages = {41-78},
number = {1122},
owner = {Srinath},
pdf = {C:\srinath\research\papers\Ellington-3-Kinematics.pdf},
timestamp = {2006.01.02},
}
"""
for k, v in items(macros):
txt = txt.replace(k, '{' + v + '}')
m = re.match(r'\s*@(\w+)\s*{\s*((\S+),)?(.*)}\s*', txt,
re.MULTILINE | re.DOTALL)
if not m:
return None
self['bibtype'] = m.group(1).capitalize()
self['key'] = m.group(3)
self['body'] = m.group(4)
body = self['body']
self['bodytext'] = ''
while 1:
m = re.search(r'(\S+?)\s*=\s*(.)', body)
if not m:
break
field = m.group(1)
body = body[(m.start(2) + 1):]
if m.group(2) == '{':
# search for the next closing brace. This is not simply a
# matter of searching for the next closing brace since
# braces can be nested. The following code basically goes
# to the next } which has not already been closed by a
# following {.
mniter = re.finditer(r'{|}', body)
count = 1
while 1:
try:
mn = next(mniter)
except StopIteration:
return None
if mn.group(0) == '{':
count += 1
else:
count -= 1
if count == 0:
value = body[:(mn.start(0))]
break
elif m.group(2) == '"':
# search for the next unquoted double-quote. To be more
# precise, a double quote which is preceded by an even
# number of double quotes.
mn = re.search(r'(?!\\)(\\\\)*"', body)
if not mn:
return None
value = body[:(mn.start(0))]
else:
# $ always matches. So we do not need to do any
# error-checking.
mn = re.search(r',|$', body)
value = m.group(2) + body[:(mn.start(0))].rstrip()
self[field.lower()] = re.sub(r'\s+', ' ', value)
body = body[(mn.start(0) + 1):]
self['bodytext'] += (' %s: %s\n' % (field, value))
if self['bibtype'].lower() == 'string':
self['macro'] = {field: value}
self['bodytext'] = self['bodytext'].rstrip()
def __getitem__(self, key):
try:
return dict.__getitem__(self, key)
except KeyError:
return ''
def __str__(self):
if self['bibtype'].lower() == 'string':
return 'String: %(macro)s' % self
elif self['bibtype'].lower() == 'article':
return ('Article [%(key)s]\n' +
'TI "%(title)s"\n' +
'AU %(author)s\n' +
'IN In %(journal)s, %(year)s') % self
elif self['bibtype'].lower() == 'conference':
return ('Conference [%(key)s]\n' +
'TI "%(title)s"\n' +
'AU %(author)s\n' +
'IN In %(booktitle)s, %(year)s') % self
elif self['bibtype'].lower() == 'mastersthesis':
return ('Masters [%(key)s]\n' +
'TI "%(title)s"\n' +
'AU %(author)s\n' +
'IN In %(school)s, %(year)s') % self
elif self['bibtype'].lower() == 'phdthesis':
return ('PhD [%(key)s]\n' +
'TI "%(title)s"\n' +
'AU %(author)s\n' +
'IN In %(school)s, %(year)s') % self
elif self['bibtype'].lower() == 'book':
return ('Book [%(key)s]\n' +
'TI "%(title)s"\n' +
'AU %(author)s\n' +
'IN %(publisher)s, %(year)s') % self
else:
s = '%(bibtype)s [%(key)s]\n' % self
if self['title']:
s += 'TI "%(title)s"\n' % self
if self['author']:
s += 'AU %(author)s\n' % self
for k, v in items(self):
if k not in ['title', 'author', 'bibtype', 'key', 'id', 'file',
'body', 'bodytext']:
s += 'MI %s: %s\n' % (k, v)
return s.rstrip()
def satisfies(self, filters):
for field, regexp in filters:
if not re.search(regexp, self[field], re.I):
return False
return True
class BibFile:
def __init__(self, filelist=''):
self.bibentries = []
self.filters = []
self.macros = {}
self.sortfields = []
if filelist:
for f in filelist.splitlines():
self.addfile(f)
def addfile(self, file):
fields = urlopen('file://' + pathname2url(os.path.abspath(file))).read().decode('utf-8').split('@')
for f in fields:
if not (f and re.match('string', f, re.I)):
continue
b = Bibliography('@' + f)
self.macros.update(b['macro'])
for f in fields:
if not f or re.match('string', f, re.I):
continue
b = Bibliography('@' + f, self.macros)
if b:
b['file'] = file
b['id'] = len(self.bibentries)
self.bibentries += [b]
def addfilter(self, filterspec):
self.filters += [filterspec.split()]
def rmfilters(self):
self.filters = []
def __str__(self):
s = ''
for b in self.bibentries:
if b['key'] and b.satisfies(self.filters):
s += '%s\n\n' % b
return s
def addsortfield(self, field):
self.sortfields += [field]
def rmsortfields(self):
self.sortfields = []
def sort(self):
self.bibentries.sort(key=lambda x:[x[field] for field in self.sortfields])
if __name__ == "__main__":
import sys
bf = BibFile(sys.argv[1])
print(bf)
|
