16072458076

Committed 04 Jul 2025 11:11AM UTC coverage: 90.83% (+0.005%) from 90.825%

Build # 16072458076

Build Type

push

github

Committed by

web-flow

Commit Message

Merge pull request #2390 from GavinHuttley/develop

Finalise the migration to new types 🎉

Coverage Stats

4044 of 4283 new or added lines in 43 files covered. (94.42%)

44 existing lines in 11 files now uncovered.

30101 of 33140 relevant lines covered (90.83%)

5.45 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

88.0

/src/cogent3/parse/tinyseq.py

"""Parser for NCBI Tiny Seq XML format.
DOCTYPE TSeqSet PUBLIC "-//NCBI//NCBI TSeq/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_TSeq.dtd"
"""

import io
import xml.dom.minidom

from cogent3.core import moltype as c3_moltype

"""
CAUTION:
This XML PARSER uses minidom. This means a bad performance for
big files (>5MB), and huge XML files will for sure crash the program!
"""


def TinyseqParser(doc):
    """Parser for NCBI Tiny Seq XML format.
    DOCTYPE TSeqSet PUBLIC "-//NCBI//NCBI TSeq/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_TSeq.dtd"

    Parameters
    ----------
    doc
        An xml.dom.minidom.Document, file object of string

    Returns
    -------
    name, cogent sequence

    CAUTION:
    This XML PARSER uses minidom. This means a bad performance for
    big files (>5MB), and huge XML files will for sure crash the program!
    """
    if isinstance(doc, xml.dom.minidom.Document):
        dom_obj = doc
    elif isinstance(doc, io.IOBase):
        dom_obj = xml.dom.minidom.parse(doc)
    elif isinstance(doc, str):
        dom_obj = xml.dom.minidom.parseString(doc)
    else:
        raise TypeError
    for record in dom_obj.getElementsByTagName("TSeq"):
        raw_seq = (
            record.getElementsByTagName("TSeq_sequence")[0].childNodes[0].nodeValue
        )
        name = record.getElementsByTagName("TSeq_accver")[0].childNodes[0].nodeValue

        # cast as string to de-unicode
        raw_string = str(raw_seq).upper()
        name = str(name)

        if (
            record.getElementsByTagName("TSeq_seqtype")[0].getAttribute("value")
            == "protein"
        ):
            alphabet = c3_moltype.PROTEIN
        else:
            alphabet = c3_moltype.DNA

        seq = alphabet.make_seq(seq=raw_string, name=name)

        seq.add_feature(biotype="genbank_id", name=name, spans=[(0, len(seq))])

        organism = str(
            record.getElementsByTagName("TSeq_orgname")[0].childNodes[0].nodeValue,
        )

        seq.add_feature(biotype="organism", name=organism, spans=[(0, len(seq))])

        yield (name, seq)

1	"""Parser for NCBI Tiny Seq XML format.
2	DOCTYPE TSeqSet PUBLIC "-//NCBI//NCBI TSeq/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_TSeq.dtd"
3	"""
4
5	import io	6✔
6	import xml.dom.minidom	6✔
7
8	from cogent3.core import moltype as c3_moltype	6✔
9
10	"""	6✔
11	CAUTION:
12	This XML PARSER uses minidom. This means a bad performance for
13	big files (>5MB), and huge XML files will for sure crash the program!
14	"""
15
16
17	def TinyseqParser(doc):	6✔
18	"""Parser for NCBI Tiny Seq XML format.
19	DOCTYPE TSeqSet PUBLIC "-//NCBI//NCBI TSeq/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_TSeq.dtd"
20
21	Parameters
22	----------
23	doc
24	An xml.dom.minidom.Document, file object of string
25
26	Returns
27	-------
28	name, cogent sequence
29
30	CAUTION:
31	This XML PARSER uses minidom. This means a bad performance for
32	big files (>5MB), and huge XML files will for sure crash the program!
33	"""
34	if isinstance(doc, xml.dom.minidom.Document):	6✔
35	dom_obj = doc	6✔
36	elif isinstance(doc, io.IOBase):	6✔
37	dom_obj = xml.dom.minidom.parse(doc)	×
38	elif isinstance(doc, str):	6✔
39	dom_obj = xml.dom.minidom.parseString(doc)	6✔
40	else:
41	raise TypeError	×
42	for record in dom_obj.getElementsByTagName("TSeq"):	6✔
43	raw_seq = (	6✔
44	record.getElementsByTagName("TSeq_sequence")[0].childNodes[0].nodeValue
45	)
46	name = record.getElementsByTagName("TSeq_accver")[0].childNodes[0].nodeValue	6✔
47
48	# cast as string to de-unicode
49	raw_string = str(raw_seq).upper()	6✔
50	name = str(name)	6✔
51
52	if (	6✔
53	record.getElementsByTagName("TSeq_seqtype")[0].getAttribute("value")
54	== "protein"
55	):
NEW 56	alphabet = c3_moltype.PROTEIN	×
57	else:
58	alphabet = c3_moltype.DNA	6✔
59
60	seq = alphabet.make_seq(seq=raw_string, name=name)	6✔
61
62	seq.add_feature(biotype="genbank_id", name=name, spans=[(0, len(seq))])	6✔
63
64	organism = str(	6✔
65	record.getElementsByTagName("TSeq_orgname")[0].childNodes[0].nodeValue,
66	)
67
68	seq.add_feature(biotype="organism", name=organism, spans=[(0, len(seq))])	6✔
69
70	yield (name, seq)	6✔

cogent3 / cogent3 / 16072458076

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous