Closes #9 : adds a parser in obiaddtaxids for the UNITE 'general FASTA

release' format

src/obiaddtaxids.py

@@ -68,7 +68,6 @@ Otherwise,
 '''
 
 
-import sys
 import re
 
 from obitools.fasta import fastaIterator,formatFasta
@@ -111,9 +110,9 @@ def addObiaddtaxidsOptions(optionManager):
                              metavar="<FORMAT>",
                              type="string",
                              default='raw',
-                             help="type of the database with the taxa to be added. Possibilities : 'raw', 'UNITE' or 'SILVA'."
-                                  "The UNITE format must be the one used for the 'Full UNITE+INSD dataset'. Example :"
-                                  ">UDB016651|k__Fungi;p__Basidiomycota;c__Agaricomycetes;o__Thelephorales;f__Thelephoraceae;g__Tomentella;s__Tomentella sp|SH200602.06FU"
+                             help="type of the database with the taxa to be added. Possibilities : 'raw', 'UNITE_FULL', 'UNITE_GENERAL' or 'SILVA'."
+                                  "The UNITE_FULL format is the one used for the 'Full UNITE+INSD dataset', and the UNITE_GENERAL format is the "
+                                  "one used for the 'General FASTA release'."
                                   " Default : raw.")
     
     optionManager.add_option('-k','--key-name',
@@ -145,7 +144,7 @@ def numberInStr(s) :
     return containsNumber
 
 
-def UNITEIterator(f):
+def UNITEIterator_FULL(f):
     
     fastaEntryIterator = genericEntryIteratorGenerator(startEntry='>')
     for entry in fastaEntryIterator(f) :
@@ -172,6 +171,28 @@ def UNITEIterator(f):
         yield s
 
 
+def UNITEIterator_GENERAL(f):
+    
+    fastaEntryIterator = genericEntryIteratorGenerator(startEntry='>')
+    for entry in fastaEntryIterator(f) :
+        all = entry.split('\n')
+        header = all[0]
+        fields = header.split('|')  
+        
+        seq_id = fields[0][1:]
+        seq = all[1]
+        s = NucSequence(seq_id, seq)
+        
+        s['species_name'] = seq_id.replace("_", " ")
+        
+        path = fields[4]
+        path = re.sub('[a-z]__', '', path)
+        path = path.replace(';', ',')
+        s['path'] = path.replace(',,', ',')
+        
+        yield s
+
+
 def SILVAIterator(f, tax):
     
     fastaEntryIterator = genericEntryIteratorGenerator(startEntry='>')
@@ -317,8 +338,10 @@ if __name__=='__main__':
     if options.db_type == 'raw' :
         entryIterator = fastaIterator
         entries = entryIterator(entries)
-    elif options.db_type == 'UNITE' :
-        entryIterator = UNITEIterator
+    elif options.db_type == 'UNITE_FULL' :
+        entryIterator = UNITEIterator_FULL
+    elif options.db_type == 'UNITE_GENERAL' :
+        entryIterator = UNITEIterator_GENERAL
         entries = entryIterator(entries)
     elif options.db_type == 'SILVA' :
         entryIterator = SILVAIterator
@@ -353,6 +376,7 @@ if __name__=='__main__':
                     if options.genus_found is not None and len(species_name.split(' ')) >= 2 :
                         try:
                             genusTaxid = getGenusTaxid(tax, species_name, restricting_ancestor)
+                            s['genus_taxid'] = genusTaxid
                             print>>options.genus_found, formatFasta(s)
                             genusFound = True
                         except KeyError :
@@ -368,16 +392,17 @@ if __name__=='__main__':
                         print>>options.unidentified,formatFasta(s)
 
 
-    elif options.db_type == 'UNITE' :
+    elif ((options.db_type =='UNITE_FULL') or (options.db_type =='UNITE_GENERAL')) :
         
         restricting_ancestor = tax.findTaxonByName('Fungi')[0][0]
-        
+                
         for s in entries :
             
             try :
                 species_name = s['species_name']
                 taxid = getTaxid(tax, species_name, restricting_ancestor)
-                s['taxid']=taxid
+                s['taxid'] = taxid
+                s['rank'] = tax.getRank(taxid)
                 print formatFasta(s)
                 
             
@@ -386,8 +411,7 @@ if __name__=='__main__':
                 genusFound = False
                 if options.genus_found is not None :
                     try:
-                        genus_name = s['genus_name']
-                        genusTaxid = getGenusTaxid(tax, genus_name, restricting_ancestor)
+                        genusTaxid = getGenusTaxid(tax, species_name, restricting_ancestor)
                         s['genus_taxid'] = genusTaxid
                         print>>options.genus_found, formatFasta(s)
                         genusFound = True