Source Code for Module Bio.SwissProt.KeyWList

 1  # Copyright 1999 by Jeffrey Chang.  All rights reserved. 
 2  # This code is part of the Biopython distribution and governed by its 
 3  # license.  Please see the LICENSE file that should have been included 
 4  # as part of this package. 
 5   
 6  """Code to parse the keywlist.txt file from SwissProt/UniProt 
 7   
 8  See: 
 9  http://www.expasy.ch/sprot/sprot-top.html 
10  ftp://ftp.expasy.org/databases/uniprot/current_release/knowledgebase/complete/docs/keywlist.txt 
11   
12  Classes: 
13  Record            Stores the information about one keyword or one category 
14                    in the keywlist.txt file. 
15   
16  Functions: 
17  parse             Parses the keywlist.txt file and returns an iterator to 
18                    the records it contains. 
19  """ 
20   
21   
22 -class Record(dict): 
23      """ 
24      This record stores the information of one keyword or category in the 
25      keywlist.txt as a Python dictionary. The keys in this dictionary are 
26      the line codes that can appear in the keywlist.txt file: 
27   
28      ---------  ---------------------------     ---------------------- 
29      Line code  Content                         Occurrence in an entry 
30      ---------  ---------------------------     ---------------------- 
31      ID         Identifier (keyword)            Once; starts a keyword entry 
32      IC         Identifier (category)           Once; starts a category entry 
33      AC         Accession (KW-xxxx)             Once 
34      DE         Definition                      Once or more 
35      SY         Synonyms                        Optional; once or more 
36      GO         Gene ontology (GO) mapping      Optional; once or more 
37      HI         Hierarchy                       Optional; once or more 
38      WW         Relevant WWW site               Optional; once or more 
39      CA         Category                        Once per keyword entry; absent 
40                                                 in category entries 
41      """ 
42 -    def __init__(self): 
43          dict.__init__(self) 
44          for keyword in ("DE", "SY", "GO", "HI", "WW"): 
45              self[keyword] = [] 
46   
47   
48 -def parse(handle): 
49      record = Record() 
50      # First, skip the header - look for start of a record 
51      for line in handle: 
52          if line.startswith("ID   "): 
53              # Looks like there was no header 
54              record["ID"] = line[5:].strip() 
55              break 
56          if line.startswith("IC   "): 
57              # Looks like there was no header 
58              record["IC"] = line[5:].strip() 
59              break 
60      # Now parse the records 
61      for line in handle: 
62          if line.startswith("-------------------------------------"): 
63              # We have reached the footer 
64              break 
65          key = line[:2] 
66          if key == "//": 
67              record["DE"] = " ".join(record["DE"]) 
68              record["SY"] = " ".join(record["SY"]) 
69              yield record 
70              record = Record() 
71          elif line[2:5] == "   ": 
72              value = line[5:].strip() 
73              if key in ("ID", "IC", "AC", "CA"): 
74                  record[key] = value 
75              elif key in ("DE", "SY", "GO", "HI", "WW"): 
76                  record[key].append(value) 
77              else: 
78                  print "Ignoring: %s" % line.strip() 
79      # Read the footer and throw it away 
80      for line in handle: 
81          pass 
82