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
|
import os.path
import Bio.PDB.mmCIF.MMCIFlex
from UserDict import UserDict
__doc__="Turn an mmCIF file into a dictionary."
class MMCIF2Dict(UserDict):
# The token identifiers
NAME=1
LOOP=2
DATA=3
SEMICOLONS=4
DOUBLEQUOTED=5
QUOTED=6
SIMPLE=7
def __init__(self, filename):
# this dict will contain the name/data pairs
self.data={}
# entry for garbage
self.data[None]=[]
if not os.path.isfile(filename):
raise IOError, "File not found."
Bio.PDB.mmCIF.MMCIFlex.open_file(filename)
self._make_mmcif_dict()
Bio.PDB.mmCIF.MMCIFlex.close_file()
def _make_mmcif_dict(self):
# local copies
NAME=self.NAME
LOOP=self.LOOP
DATA=self.DATA
SEMICOLONS=self.SEMICOLONS
DOUBLEQUOTED=self.DOUBLEQUOTED
QUOTED=self.QUOTED
SIMPLE=self.SIMPLE
get_token=Bio.PDB.mmCIF.MMCIFlex.get_token
# are we looping?
loop_flag=0
# list of names in loop
temp_list=[]
# last encountered name
current_name=None
# get first token/value pair
token, value=get_token()
# print token, value
mmcif_dict=self.data
# loop until EOF (token==0)
while token:
if token==NAME:
if loop_flag:
# Make lists for all the names in the loop
while token==NAME:
# create a list for each name encountered in loop
new_list=mmcif_dict[value]=[]
temp_list.append(new_list)
token, value=get_token()
# print token, value
loop_flag=0
# nr of data items parsed
data_counter=0
# corresponding data name
pos=0
nr_fields=len(temp_list)
# Now fill all lists with the data
while token>3:
pos=data_counter%nr_fields
data_counter=data_counter+1
temp_list[pos].append(value)
token, value=get_token()
# print token, value
if pos!=nr_fields-1:
print "ERROR: broken name-data pair (data missing)!"
# The last token was not used, so
# don't set token to None! (this means the
# last parsed token goes through the loop again)
else:
# simple name-data pair (no loop)
# so next token should be the data
next_token, data=get_token()
# print token, value
mmcif_dict[value]=data
if next_token<4:
print "ERROR: broken name-data pair (name-non data pair)!"
# print token, value
else:
# get next token
token=None
elif token==LOOP:
loop_flag=1
temp_list=[]
# get next token
token=None
elif token==DATA:
mmcif_dict[value[0:5]]=value[5:]
token=None
else:
# we found some complete garbage
print "ERROR: broken name-data pair (missing name)!"
print token, value
mmcif_dict[None].append(value)
# get next token
token=None
if token==None:
token, value=get_token()
# print token, value
def __getitem__(self, key):
return self.data[key]
if __name__=="__main__":
import sys
if len(sys.argv)!=2:
print "Usage: python MMCIF2Dict filename."
filename=sys.argv[1]
mmcif_dict=MMCIF2Dict(filename)
input=""
print "Now type a key ('q' to end, 'k' for a list of all keys):"
while(input!="q"):
input=raw_input("MMCIF dictionary key ==> ")
if input=="q":
sys.exit()
if input=="k":
for key in mmcif_dict.keys():
print key
continue
try:
value=mmcif_dict[input]
if type(value)==type([]):
for item in value:
print item
else:
print value
except KeyError:
print "No such key found."
|
