obitools/obitools3
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 66 Wiki Activity

Genbank parser: now reading ORIGIN lines with comments without

Browse Source 
triggering error
This commit is contained in:
Celine Mercier
2020-05-28 20:41:34 +02:00
parent 6094ce2bbc
commit ffe2485e94
1 changed files with 17 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
python/obitools3/parsers/genbank.pyx
View File

@ -25,8 +25,9 @@ from libc.string cimport strcpy, strlen
_featureMatcher = re.compile(b'^FEATURES.+\n(?=ORIGIN)',re.DOTALL + re.M) _featureMatcher = re.compile(b'^FEATURES.+\n(?=ORIGIN)',re.DOTALL + re.M)
_headerMatcher = re.compile(b'^LOCUS.+(?=\nFEATURES)', re.DOTALL + re.M) _headerMatcher = re.compile(b'^LOCUS.+(?=\nFEATURES)', re.DOTALL + re.M)
_seqMatcher = re.compile(b'(?<=ORIGIN).+(?=//\n)', re.DOTALL + re.M) _seqMatcher = re.compile(b'ORIGIN.+(?=//\n)', re.DOTALL + re.M)
_cleanSeq = re.compile(b'[ \n0-9]+') _cleanSeq1 = re.compile(b'ORIGIN.+\n')
_cleanSeq2 = re.compile(b'[ \n0-9]+')
_acMatcher = re.compile(b'(?<=^ACCESSION ).+',re.M) _acMatcher = re.compile(b'(?<=^ACCESSION ).+',re.M)
_deMatcher = re.compile(b'(?<=^DEFINITION ).+\n( .+\n)*',re.M) _deMatcher = re.compile(b'(?<=^DEFINITION ).+\n( .+\n)*',re.M)
_cleanDe = re.compile(b'\n *') _cleanDe = re.compile(b'\n *')
@ -42,7 +43,8 @@ def genbankParser(bytes text):
ft = _featureMatcher.search(text).group() ft = _featureMatcher.search(text).group()
s = _seqMatcher.search(text).group() s = _seqMatcher.search(text).group()
s = _cleanSeq.sub(b'', s).upper() s = _cleanSeq1.sub(b'', s)
s = _cleanSeq2.sub(b'', s)
acs = _acMatcher.search(text).group() acs = _acMatcher.search(text).group()
acs = acs.split() acs = acs.split()
@ -51,23 +53,23 @@ def genbankParser(bytes text):
de = _deMatcher.search(header).group() de = _deMatcher.search(header).group()
de = _cleanDe.sub(b' ',de).strip().strip(b'.') de = _cleanDe.sub(b' ',de).strip().strip(b'.')
tags = {}
extractTaxon(ft, tags)
seq = Nuc_Seq(ac,
s,
definition=de,
quality=None,
offset=-1,
tags=tags)
except Exception as e: except Exception as e:
print("\nCould not import sequence id:", text.split()[1], "(error raised:", e, ")") print("\nCould not import sequence id:", text.split()[1], "(error raised:", e, ")")
# Do not raise any Exception if you need the possibility to resume the generator # Do not raise any Exception if you need the possibility to resume the generator
# (Python generators can't resume after any exception is raised) # (Python generators can't resume after any exception is raised)
return None return None
tags = {}
extractTaxon(ft, tags)
seq = Nuc_Seq(ac,
s,
definition=de,
quality=None,
offset=-1,
tags=tags)
return seq return seq