from Bio import SeqIO
from TAMO import MotifTools

# from string import * # non necessario

handle = open("unr.fasta", 'r')

EcoRI = MotifTools.Motif_from_text('GAATTC')
BamHI = MotifTools.Motif_from_text('GGATCC')
HindIII = MotifTools.Motif_from_text('AAGCTT')

enzimes = [ EcoRI, BamHI, HindIII ]

for sequnr in SeqIO.parse(handle, "fasta"):
  for enz in enzimes:
    digest(sequnr, enz)


def digest(sequnr, enz) :
  """
  trova tutte le occorrenze di un motivo in una sequenza. (corretto?)

  esempio:
  >>> from StringIO import StringIO
  >>> from TAMO import MotifTools
  >>> from Bio import SeqIO
  >>> fastafile = StringIO('>seq1\nGGATcCCGGATGCATGCTA')
  >>> fastafile.seek(0)
  >>> enz = MotifTools.Motif_from_text('GGATCC')

  >>> print digest(SeqIO.parse(fastafile, 'fasta'), enz)
  (['GGATcC'], [(0, 5)], [11.685195480635185])
  """    

  occurrencies = enz.scan(sequnr.seq.tostring())
  return occurencies

>>> import re
>>> seq1 = 'ACGATGGCTACGTACGTACGTACGA'
>>> seq2 = 'AAAAAAAACCAAAAAAAAAAAAAAA'

>>> re.findall('AC', seq1)
['AC']

>>> for match in re.finditer('AA', seq2):
        print match.start(), match.end(), match.group()

# nota come anche con le regex il comportamento é incorretto, perché non si tiene conto che una N rappresenta qualsiasi nucleotide:
>>> seq3 = 'ANAA'
>>> re.findall('AA', seq3)