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
|
# Copyright 2001 by Katharine Lindner. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""
This module provides code to work with html files from InterPro.
http://www.ebi.ac.uk/interpro/
Classes:
Record Holds interpro sequence data.
InterProParser Parses interpro sequence data into a Record object.
"""
from types import *
import string
from Bio import File
from Bio import Index
import urllib
import sgmllib
from Bio.ParserSupport import *
from Bio.SeqFeature import Reference
class Record( dict ):
def __str__( self ):
keys = self.keys()
keys.sort()
out = ''
for key in keys:
val = self[ key ]
if( key == 'References' ):
out = out + '\n%s\n' % key
for reference in val:
out = out + '%s\n' % str( reference )
out = out + '\n'
elif( key == 'Examples' ):
out = out + '\n%s\n' % key
for example in val:
out = out + '%s\n' % example
elif( key == 'Abstract' ):
out = out + '\n%s\n' % key
out = out + '%s...\n' % val[ : 80 ]
elif( type( self[ key ] ) == type( [] ) ):
out = out + '\n%s\n' % key
for item in val:
out = out + '%s\n' % item
else:
out = out + '%s: %s\n' % ( key, self[ key ] )
return out
class InterProParser( sgmllib.SGMLParser ):
"""Parses InterPro sequence data into a Record object.
"""
def reset(self):
sgmllib.SGMLParser.reset( self )
self.text = ''
self.inter_pro_dict = Record()
self.inter_pro_dict[ 'Database' ] = ''
self.inter_pro_dict[ 'Accession' ] = ''
self.inter_pro_dict[ 'Name' ] = ''
self.inter_pro_dict[ 'Dates' ] = ''
self.inter_pro_dict[ 'Type' ] = ''
self.inter_pro_dict[ 'Parent' ] = ''
self.inter_pro_dict[ 'Process' ] = ''
self.inter_pro_dict[ 'Function' ] = ''
self.inter_pro_dict[ 'Component' ] = ''
self.inter_pro_dict[ 'Signatures' ] = []
self.inter_pro_dict[ 'Abstract' ] = ''
self.inter_pro_dict[ 'Examples' ] = []
self.inter_pro_dict[ 'References' ] = []
self.inter_pro_dict[ 'Database links' ] = []
self._state = 'title'
self._reference_state = ''
self._key_waiting = ''
self._current_reference = ''
def parse(self, handle):
self.reset()
self.feed(handle)
return self.inter_pro_dict
def feed(self, handle):
"""feed(self, handle )
Feed in interpro data for scanning. handle is a file-like object
containing interpro data. consumer is a Consumer object that will
receive events as the ndb data is scanned.
"""
if isinstance(handle, File.UndoHandle):
uhandle = handle
else:
uhandle = File.UndoHandle(handle)
text = ''
while 1:
line = uhandle.readline()
if( not line ):
break
line = string.strip( line )
if( line[ -7: ] == '</HTML>' ):
break
text = text + ' ' + line
sgmllib.SGMLParser.feed( self, text )
def handle_data(self, newtext ):
newtext = string.strip( newtext )
self.text = self.text + newtext
def start_table( self, attrs ):
dict = pairlist_to_dict( attrs )
for key in dict.keys():
val = dict[ key ]
def start_h2( self, attrs ):
pass
def end_h2( self ):
self._state = 'chugging_along'
def start_td( self, attrs ):
dict = pairlist_to_dict( attrs )
if( self._state == 'chugging_along' ):
if( dict.has_key( 'class' ) ):
if( dict[ 'class' ] == 'tag' ):
self._state = 'waiting_tag'
self._flush_text()
elif( dict[ 'class' ] == 'inf' ):
self._state = 'waiting_inf'
self._flush_text()
def end_td( self ):
if( self._state == 'waiting_tag' ):
self._key_waiting = self._flush_text()
self._state = 'chugging_along'
elif( self._state == 'waiting_inf' ):
key = self._key_waiting
if( self.inter_pro_dict.has_key( key ) ):
val = self._flush_text()
if( key == 'Signatures' ):
pass
elif( key == 'Database links' ):
pass
else:
self.inter_pro_dict[ key ] = val
self._key_waiting = ''
self._state = 'chugging_along'
def start_ul( self, attrs ):
if( self._key_waiting == 'Examples' ):
self._state = 'examples'
self._flush_text()
def end_ul( self ):
self._key_waiting = ''
self._state = 'chugging_along'
def start_ol( self, attrs ):
if( self._key_waiting == 'References' ):
self._state = 'references'
self._reference_state = 'pubmed_id'
self._flush_text()
self._references = []
def end_ol( self ):
if( self._state == 'references' ):
self._references.append( self._current_reference )
self.inter_pro_dict[ 'References' ] = self._references
self._state = 'chugging_along'
def start_li( self, attrs ):
if( self._state == 'references' ):
self._reference_state = 'pubmed_id'
self._flush_text()
if( self._current_reference != '' ):
self._references.append( self._current_reference )
self._current_reference = Reference()
def end_li( self ):
if( self._state == 'examples' ):
text = self._flush_text()
( self.inter_pro_dict[ 'Examples' ] ).append( text )
def start_a( self, attrs ):
dict = pairlist_to_dict( attrs )
if( self._state == 'references' ):
if( self._reference_state == 'pubmed_id' ):
if( dict.has_key( 'name' ) ):
self._current_reference.pubmed_id = dict[ 'name' ]
self._reference_state = 'authors'
elif( self._reference_state == 'journal' ):
self._current_reference.journal = self._flush_text()
self._reference_state = 'medline_id'
def end_a( self ):
if( self._state == 'references' ):
if( self._reference_state == 'medline_id' ):
text = self._flush_text()
cols = text.split( ':' )
try:
medline_id = cols[ 1 ]
except IndexError:
medline_id = None
else:
medline_id = medline_id[ : -1 ]
self._current_reference.medline_id = medline_id
def do_br( self, attrs ):
if( self._state == 'references' ):
if( self._reference_state == 'authors' ):
self._current_reference.authors = self._flush_text()
self._reference_state = 'title'
elif( self._key_waiting == 'Signatures' ):
self.inter_pro_dict[ 'Signatures' ].append( self._flush_text() )
elif( self._key_waiting == 'Database links' ):
self.inter_pro_dict[ 'Database links' ].append( self._flush_text() )
def start_i( self, attrs ):
pass
def end_i( self ):
if( self._state == 'references' ):
if( self._reference_state == 'title' ):
text = self._flush_text()
self._current_reference.title = text
self._reference_state = 'journal'
def handle_starttag(self, tag, method, attrs):
if( self._state == 'references' ):
if( tag == 'li' ):
self.stack.pop()
elif( tag == 'a' ):
if( self._reference_state == 'pubmed_id' ):
self.stack.pop()
method(attrs)
def _flush_text( self ):
text = string.strip( self.text )
self.text = ''
return text[:]
def pairlist_to_dict( pairs ):
dict = {}
for pair in pairs:
key = pair[ 0 ]
val = pair[ 1 ]
dict[key ] = val
return dict
if( __name__ == '__main__' ):
handle = open( 'IPR001064.htm')
undo_handle = Bio.File.UndoHandle( handle )
interpro_parser = InterProParser()
record = interpro_parser.parse( handle )
print str( record )
|
