Commit 54c68bab by Celine Mercier

Fixed a bug when parsing embl files: accession ids end with ';' in recent embl…

Fixed a bug when parsing embl files: accession ids end with ';' in recent embl formats. The ';' was kept by the old embl parser, resulting in many possible bugs.
parent 5dc1f4d3
......@@ -25,9 +25,11 @@ def __emblparser(text):
seq = _cleanSeq.sub('',seq).upper()
acs = _acMatcher.search(text).group()
acs = acs.replace(';', ' ')
acs = acs.split()
ac = acs[0]
acs = acs[1:]
de = _deMatcher.search(header).group()
de = _cleanDe.sub(' ',de).strip().strip('.')
......@@ -47,4 +49,4 @@ def emblIterator(file):
for e in nucEntryIterator(file):
yield emblParser(e)
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment