def parseGumby(gumbyFile, exonFile, baseSeq):
# parses gumbyFile, removes things that overlap exons and gumbies that consist only of gaps on baseSeq
# returns a list of gumbyBlocks
infile = open(gumbyFile, "r")
exons = []
if exonFile!=None:
fh = open(exonFile, "r")
for l in fh:
fs = l.split()
if fs[0].lower()!=baseSeq:
continue
exons.append([ int(fs[3]), int(fs[4]) ] )
# print exons
re1 = compile("[a-z]+[ ]+[0-9]+[ ]+[0-9]+")
seqs = {}
pos = {}
i = -1
resultLst = alignment.Alignment()
for l in infile:
l = l.strip()
l = l.replace("*","-")
l = l.replace("<", "-")
l = l.replace(">", "-")
if l.startswith("start"):
if i!=-1:
resultLst.extend(procData(baseSeq, exons, i, seqs, pos, pval, length, score))
f = l.split()
pval = float(f[-1])
length = int(f[6].strip(","))
score = int(f[8].strip(","))
i+=1
seqs={}
if re1.match(l):
f = l.split()
name = f[0]
start = int(f[1])-1
end = int(f[2])-1
seq = f[3]
if name not in seqs:
faseq = Fasta.FastaSeq(name, seq)
faseq.chrom = name
faseq.start = start
faseq.end = end
seqs[name] = faseq
else:
faseq = seqs[f[0]]
faseq.nucl += f[3]
pos[name] = (name, start,end)
resultLst.extend(procData(baseSeq, exons, i, seqs, pos, pval, length, score))
return resultLst
