upstream-dependencies/galaxy-sequence-utils/galaxy_utils/sequence/scripts/fastq_to_tabular.py
1# Dan Blankenberg
2
3
4import sys
5
6from galaxy_utils.sequence.fastq import fastqReader
7
8
9def main():
10 if len(sys.argv) != 5:
11 _stop_err("Wrong number of arguments. Expect: fasta tabular desrc_split [type]")
12 input_filename = sys.argv[1]
13 output_filename = sys.argv[2]
14 descr_split = int(sys.argv[3]) - 1
15 if descr_split < 0:
16 _stop_err("Bad description split value (should be 1 or more)")
17 input_type = sys.argv[4] or 'sanger' # input type should ordinarily be unnecessary
18
19 num_reads = None
20 fastq_read = None
21 out = open(output_filename, "w")
22
23 with fastqReader(path=input_filename, format=input_type) as reader:
24 if descr_split == 0:
25 # Don't divide the description into multiple columns
26 for num_reads, fastq_read in enumerate(reader):
27 out.write("{}\t{}\t{}\n".format(fastq_read.identifier[1:].replace('\t', ' '), fastq_read.sequence.replace('\t', ' '), fastq_read.quality.replace('\t', ' '))) # noqa: SFS201
28 else:
29 for num_reads, fastq_read in enumerate(reader):
30 words = fastq_read.identifier[1:].replace('\t', ' ').split(None, descr_split)
31 # pad with empty columns if required
32 words += [""] * (descr_split - len(words))
33 out.write("{}\t{}\t{}\n".format("\t".join(words), fastq_read.sequence.replace('\t', ' '), fastq_read.quality.replace('\t', ' '))) # noqa: SFS201
34
35 if num_reads is None:
36 print("No valid FASTQ reads could be processed.")
37 else:
38 print(f"{num_reads + 1:d} FASTQ reads were converted to Tabular.")
39
40
41def _stop_err(msg):
42 sys.stderr.write(msg)
43 sys.exit()
44
45
46if __name__ == "__main__":
47 main()