# HG changeset patch # User devteam # Date 1727957515 0 # Node ID 5cbde03c110344653d68a790018f2f697d9997c5 # Parent 7d37cfda8e0080c7db796fc35001a30d7191bdfd planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fasta_compute_length commit 9f0b8eb9fd7cf9e2513e7c822767153dbd4bc3b2 diff -r 7d37cfda8e00 -r 5cbde03c1103 fasta_compute_length.py --- a/fasta_compute_length.py Mon Mar 02 06:46:51 2020 -0500 +++ b/fasta_compute_length.py Thu Oct 03 12:11:55 2024 +0000 @@ -1,10 +1,47 @@ #!/usr/bin/env python """ -Uses fasta_to_len converter code. +Input: fasta, int +Output: tabular +Return titles with lengths of corresponding seq """ import sys -from utils.fasta_to_len import compute_fasta_length -compute_fasta_length(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4] == 'id_only') +def compute_fasta_length(fasta_file, out_file, keep_first_char, keep_first_word=False): + keep_first_char = int(keep_first_char) + fasta_title = '' + seq_len = 0 + + # number of char to keep in the title + if keep_first_char == 0: + keep_first_char = None + else: + keep_first_char += 1 + + first_entry = True + with open(fasta_file) as in_fh, open(out_file, 'w') as out_fh: + for line in in_fh: + line = line.strip() + if not line or line.startswith('#'): + continue + if line[0] == '>': + if first_entry is False: + if keep_first_word: + fasta_title = fasta_title.split()[0] + out_fh.write("%s\t%d\n" % (fasta_title[1:keep_first_char], seq_len)) + else: + first_entry = False + fasta_title = line + seq_len = 0 + else: + seq_len += len(line) + + # last fasta-entry + if keep_first_word: + fasta_title = fasta_title.split()[0] + out_fh.write("%s\t%d\n" % (fasta_title[1:keep_first_char], seq_len)) + + +if __name__ == "__main__": + compute_fasta_length(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4] == 'id_only') diff -r 7d37cfda8e00 -r 5cbde03c1103 fasta_compute_length.xml --- a/fasta_compute_length.xml Mon Mar 02 06:46:51 2020 -0500 +++ b/fasta_compute_length.xml Thu Oct 03 12:11:55 2024 +0000 @@ -1,8 +1,11 @@ - + - python + python + + + #if $ref.ref_source == 'dbkey': cp '${ref.index.fields.len_path}' '$output' diff -r 7d37cfda8e00 -r 5cbde03c1103 utils/__init__.py diff -r 7d37cfda8e00 -r 5cbde03c1103 utils/fasta_to_len.py --- a/utils/fasta_to_len.py Mon Mar 02 06:46:51 2020 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,47 +0,0 @@ -#!/usr/bin/env python -""" -Input: fasta, int -Output: tabular -Return titles with lengths of corresponding seq -""" - -import sys - - -def compute_fasta_length(fasta_file, out_file, keep_first_char, keep_first_word=False): - keep_first_char = int(keep_first_char) - fasta_title = '' - seq_len = 0 - - # number of char to keep in the title - if keep_first_char == 0: - keep_first_char = None - else: - keep_first_char += 1 - - first_entry = True - with open(fasta_file) as in_fh, open(out_file, 'w') as out_fh: - for line in in_fh: - line = line.strip() - if not line or line.startswith('#'): - continue - if line[0] == '>': - if first_entry is False: - if keep_first_word: - fasta_title = fasta_title.split()[0] - out_fh.write("%s\t%d\n" % (fasta_title[1:keep_first_char], seq_len)) - else: - first_entry = False - fasta_title = line - seq_len = 0 - else: - seq_len += len(line) - - # last fasta-entry - if keep_first_word: - fasta_title = fasta_title.split()[0] - out_fh.write("%s\t%d\n" % (fasta_title[1:keep_first_char], seq_len)) - - -if __name__ == "__main__": - compute_fasta_length(sys.argv[1], sys.argv[2], sys.argv[3], True)