Skip to main content
  • Home
  • Development
  • Documentation
  • Donate
  • Operational login
  • Browse the archive

swh logo
SoftwareHeritage
Software
Heritage
Archive
Features
  • Search

  • Downloads

  • Save code now

  • Add forge now

  • Help

  • 910ecf4
  • /
  • utils
  • /
  • lastz_parser.py
Raw File Download

To reference or cite the objects present in the Software Heritage archive, permalinks based on SoftWare Hash IDentifiers (SWHIDs) must be used.
Select below a type of object currently browsed in order to display its associated SWHID and permalink.

  • content
  • directory
content badge Iframe embedding
swh:1:cnt:58cb5018d3f259b79662b515184bab588f3f0e63
directory badge Iframe embedding
swh:1:dir:fdfbc8ce7f5ad712860694246e7cf5b3c069e96e

This interface enables to generate software citations, provided that the root directory of browsed objects contains a citation.cff or codemeta.json file.
Select below a type of object currently browsed in order to generate citations for them.

  • content
  • directory
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
lastz_parser.py

#(c) 2013-2014 by Authors
#This file is a part of Ragout program.
#Released under the BSD license (see LICENSE file)

"""
Functions for lastz input handling
"""

import subprocess
import os
from itertools import combinations

from .common import AlignmentColumn, AlignmentRow

def parse_lastz_maf(filename):
    alignments = []
    with open(filename, "r") as f:
        while True:
            line = f.readline()
            if not line:
                break

            if not line.startswith("a"):
                state = 1
                continue

            #read two next lines
            ref_line = f.readline().strip()
            qry_line = f.readline().strip()
            assert ref_line.startswith("s") and qry_line.startswith("s")

            def parse_column(string):
                seq_id, start, aln_len, strand, seq_len = string.split()[1:6]
                aln_len, seq_len = int(aln_len), int(seq_len)
                strand = 1 if strand == "+" else -1
                if strand > 0:
                    start, end = int(start), int(start) + aln_len
                else:
                    end = seq_len - 1 - int(start)
                    start = end - aln_len

                assert end >= start
                return AlignmentRow(start, end, strand, seq_len, seq_id)

            alignments.append(AlignmentColumn(parse_column(ref_line),
                                              parse_column(qry_line)))

    return alignments


def filter_intersecting(alignments):
    to_filter = set()

    def filter_by_rows(rows):
        for row_1, row_2 in combinations(rows, 2):
            if row_1.seq_id != row_2.seq_id:
                continue

            if row_1.start <= row_2.start <= row_1.end:
                to_filter.add(row_2)
                if not (row_1.start <= row_2.end <= row_1.end):
                    to_filter.add(row_1)
            continue

            if row_2.start <= row_1.start <= row_2.end:
                to_filter.add(row_1)
                if not (row_2.start <= row_1.end <= row_2.end):
                    to_filter.add(row_2)

    filter_by_rows(list(map(lambda ap: ap.ref, alignments)))
    filter_by_rows(list(map(lambda ap: ap.qry, alignments)))

    return [a for a in alignments if a.ref not in to_filter and
                                     a.qry not in to_filter]


def filter_by_length(alignments, min_len):
    func = (lambda a: abs(a.ref.start - a.ref.end) > min_len and
                      abs(a.qry.start - a.qry.end) > min_len)
    return list(filter(func, alignments))


LASTZ_BIN = "lastz"
def run_lastz(reference, target, out_file):
    print("Running lastz")
    reference = os.path.abspath(reference)
    target = os.path.abspath(target)
    out_file = os.path.abspath(out_file)
    cmdline = [LASTZ_BIN, reference + "[multiple,nameparse=darkspace]",
               target + "[nameparse=darkspace]","--notransition",
               "--step=20", "--chain", "--gapped", "--gfextend",
               "--ambiguous=n", "--format=maf", "--output=" + out_file,
               "--rdotplot=dotplot.txt"]
    devnull = os.devnull
    subprocess.check_call(cmdline, stderr=open(devnull, "w"))

back to top

Software Heritage — Copyright (C) 2015–2025, The Software Heritage developers. License: GNU AGPLv3+.
The source code of Software Heritage itself is available on our development forge.
The source code files archived by Software Heritage are available under their own copyright and licenses.
Terms of use: Archive access, API— Content policy— Contact— JavaScript license information— Web API