@@ -547,6 +547,8 @@ class Reader(object): for line in self.stream: if line.startswith(marker): return (''.join(lines), line) + if line.startswith("//"): + raise ValueError("Read past record separator.") lines.append(line) return (''.join(lines), None) @@ -558,20 +560,21 @@ class Record(object): self.locus = parse_locus(stream.next()) self.keywords = parse_keywords(stream.read_to("FEATURES")[0]) - if self.locus["division"] == "CON": - data = stream.read_to("//")[0] - pos = data.find("CONTIG") - self.features = parse_features(data[:pos]) - self.contig = parse_contig(data[pos:]) - self.base_count = None - self.seqiter = None + (data, mark) = stream.read_to(("BASE COUNT", "ORIGIN", "CONTIG")) + self.features = parse_features(data) + + self.base_count = None + self.contig = None + self.seqiter = None + + if mark.startswith("BASE COUNT"): + self.base_count = parse_base_count(mark) + (data, mark) = stream.read_to(("CONTIG", "ORIGIN")) + + if mark.startswith("CONTIG"): + data = ''.join([mark, stream.read_to("//")[0]]) + self.contig = parse_contig(data) else: - data, marker = stream.read_to(("ORIGIN", "BASE COUNT")) - self.features = parse_features(data) - self.contig = None - self.base_count = None - if marker.startswith("BASE COUNT"): - self.base_count = parse_base_count(marker) self.seqiter = Sequence(stream) def __repr__(self): nebgb.py @@ -40,7 +40,7 @@ setup( author = "Paul Joseph Davis", author_email = "davisp@neb.com", url = "http://github.com/davisp/nebgb", - version = "0.0.1", + version = "0.0.2", license = "MIT", keywords = "bioinformatics genbank parser", platforms = ["any"], setup.py 321f8fe8bf7e4d59613071e6e462c54247f8a2d2 Paul J. Davis paul.joseph.davis@gmail.com http://github.com/davisp/nebgb/commit/d163ba37b1095ccdc6d6de326a7c6fcbb01157da d163ba37b1095ccdc6d6de326a7c6fcbb01157da 2009-07-05T13:47:53-07:00 2009-07-05T13:47:53-07:00 A CON division does not require a CONTIG section. 70e78c9765bdc371a227aa5e7ab3361d34d90027 Paul J. Davis paul.joseph.davis@gmail.com