From fc26a9fda38c70c55d6511768f09765302d72b22 Mon Sep 17 00:00:00 2001
From: Eric Coissac <eric.coissac@metabarcoding.org>
Date: Fri, 15 Jun 2007 13:40:14 +0000
Subject: [PATCH] git-svn-id:
 https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/branches/refactoring@67
 60f365c0-8329-0410-b2a4-ec073aeeaa1d

---
 tools/ecoPCRFormat.py | 57 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 51 insertions(+), 6 deletions(-)

diff --git a/tools/ecoPCRFormat.py b/tools/ecoPCRFormat.py
index 2d86065..9a3205d 100755
--- a/tools/ecoPCRFormat.py
+++ b/tools/ecoPCRFormat.py
@@ -267,6 +267,30 @@ def genbankEntryParser(entry):
         Tx = None
     return {'id':Id,'taxid':Tx,'definition':De,'sequence':Sq}
 
+######################
+
+_cleanDef = re.compile('[\nDE]')
+
+def cleanDef(definition):
+    return _cleanDef.sub('',definition)
+
+_emblParseID = re.compile('(?<=^ID {3})[^ ]+(?=;)',re.MULTILINE)   
+_emblParseDE = re.compile('(?<=^DE {3}).+?\. *$(?=[^ ])',re.MULTILINE+re.DOTALL)   
+_emblParseSQ = re.compile('(?<=^  ).+?(?=^//$)',re.MULTILINE+re.DOTALL)  
+_emblParseTX = re.compile('(?<= /db_xref="taxon:)[0-9]+(?=")')
+
+def emblEntryParser(entry):
+    Id = _emblParseID.findall(entry)[0]
+    De = ' '.join(cleanDef(_emblParseDE.findall(entry)[0]).split())
+    Sq = cleanSeq(_emblParseSQ.findall(entry)[0].upper())
+    try:
+        Tx = int(_emblParseTX.findall(entry)[0])
+    except IndexError:
+        Tx = None
+    return {'id':Id,'taxid':Tx,'definition':De,'sequence':Sq}
+
+######################
+
 _fastaParseID = re.compile('(?<=^>)[^ ]+')
 _fastaParseDE = re.compile('(?<=^>).+',)   
 _fastaParseSQ = re.compile('^[^>].+',re.MULTILINE+re.DOTALL)
@@ -464,37 +488,58 @@ def ecoParseOptions(arguments):
            }
     
     o,filenames = getopt.getopt(arguments,
-                                'ht:n:gf',
+                                'ht:n:gfe',
                                 ['help',
                                  'taxonomy=',
                                  'name=',
                                  'genbank',
-                                 'fasta'])
+                                 'fasta',
+                                 'embl'])
     
     for name,value in o:
         if name in ('-h','--help'):
-            pass
+            printHelp()
+            exit()
         elif name in ('-t','--taxonomy'):
             opt['taxdir']=value
         elif name in ('-n','--name'):
             opt['prefix']=value
         elif name in ('-g','--genbank'):
             opt['parser']=sequenceIteratorFactory(genbankEntryParser,
-                                                  entryIterator
-                                                  )
+                                                  entryIterator)
+
         elif name in ('-f','--fasta'):
             opt['parser']=sequenceIteratorFactory(fastaEntryParser,
                                                   fastaEntryIterator)
+            
+        elif name in ('-e','--embl'):
+            opt['parser']=sequenceIteratorFactory(emblEntryParser,
+                                                  entryIterator)
         else:
             raise ValueError,'Unknown option %s' % name
 
     return opt,filenames
 
+def printHelp():
+    print "-----------------------------------"
+    print " ecoPCRFormat.py"
+    print "-----------------------------------"
+    print "ecoPCRFormat.py [option] <argument>"
+    print "-----------------------------------"
+    print "-e    --embl        :[E]mbl format file name"
+    print "-f    --fasta       :[F]asta format file name"
+    print "-g    --genbank     :[G]enbank format file name"
+    print "-h    --help        :[H]elp - print this help"
+    print "-n    --name        :[N]ame of the new database created"
+    print "-t    --taxonomy    :[T]axonomy - path to the taxonomy database"
+    print "                    :bcp-like dump from GenBank taxonomy database."
+    print "-----------------------------------"
+
 if __name__ == '__main__':
     
     opt,filenames = ecoParseOptions(sys.argv[1:])
     
     taxonomy = readTaxonomyDump(opt['taxdir'])
-    
+   
     ecoDBWriter(opt['prefix'], taxonomy, filenames, opt['parser'])