comparison jbrowse2.py @ 93:4c517a0041a8 draft

planemo upload for repository https://github.com/usegalaxy-eu/temporary-tools/tree/master/jbrowse2 commit aeef2fbc0f90a9366851941ff51baeba410c56e4

92:3c4db8203fad

from collections import defaultdict

logging.basicConfig(level=logging.DEBUG)
log = logging.getLogger("jbrowse")

JB2VER = "v2.10.3"
# version pinned if cloning - but not cloning now
logCommands = True
# useful for seeing what's being written but not for production setups
TODAY = datetime.datetime.now().strftime("%Y-%m-%d")
SELF_LOCATION = os.path.dirname(os.path.realpath(__file__))

                if genome_name == primaryGenome:  # first one
                    this_genome["genome_name"] = genome_name  # first one for all tracks
                    this_genome["genome_sequence_adapter"] = assem["sequence"][
                        "adapter"
                    ]
                    this_genome["genome_firstcontig"] = None
                    if not useuri:
                        fl = open(fapath, "r").readline()
                        fls = fl.strip().split(">")
                        if len(fls) > 1:
                            fl = fls[1]
                            if len(fl.split()) > 1:
                                this_genome["genome_firstcontig"] = fl.split()[
                                    0
                                ].strip()
                            else:
                                this_genome["genome_firstcontig"] = fl
                    else:
                        try:
                            scontext = ssl.SSLContext(ssl.PROTOCOL_TLS)
                            scontext.verify_mode = ssl.VerifyMode.CERT_NONE
                            with urllib.request.urlopen(
                                url=fapath + ".fai", context=scontext
                            ) as f:
                                fl = f.readline()
                        except Exception:
                            fl = None
                        if fl:  # is first row of the text fai so the first contig name
                            this_genome["genome_firstcontig"] = (
                                fl.decode("utf8").strip().split()[0]
                            )
                assmeta.append(this_genome)
        self.assemblies += assembly
        self.assmeta[primaryGenome] = assmeta
        self.tracksToAdd[primaryGenome] = []
        return primaryGenome

        """added code to grab the first contig name and length for broken default session from Anthony and Helena's code
        that poor Bjoern is trying to figure out.
        """
        if useuri:
            faname = fapath
            adapter = {
                "type": "BgzipFastaAdapter",
                "fastaLocation": {"uri": faname, "locationType": "UriLocation"},
                "faiLocation": {"uri": faname + ".fai", "locationType": "UriLocation"},
                "gziLocation": {"uri": faname + ".gzi", "locationType": "UriLocation"},
            }
            scontext = ssl.SSLContext(ssl.PROTOCOL_TLS)
            scontext.verify_mode = ssl.VerifyMode.CERT_NONE
            with urllib.request.urlopen(url=faname + ".fai", context=scontext) as f:
                fl = f.readline()
            contig = fl.decode("utf8").strip()

                fadest,
                fadest,
                fadest,
            )
            self.subprocess_popen(cmd)

            adapter = {
                "type": "BgzipFastaAdapter",
                "fastaLocation": {
                    "uri": faname,
                },
                "faiLocation": {
                    "uri": faname + ".fai",
                },
                "gziLocation": {
                    "uri": faname + ".gzi",
                },
            }
            contig = open(fadest + ".fai", "r").readline().strip()
        first_contig = contig.split()[:2]
        first_contig.insert(0, gname)
        trackDict = {
            "name": gname,
            "sequence": {

            self.subprocess_check_call(["cp", data, dest])
            url = fname
            bindex = fname + ".bai"
            bi = bam_indexes.split(",")
            bam_index = [
                x.split(":")[1].strip()
                for x in bi
                if ":" in x and x.split(":")[0].strip() == realFName
            ]
            logging.debug(
                "===realFName=%s got %s as bam_indexes %s as bi, %s for bam_index"
                % (realFName, bam_indexes, bi, bam_index)
            )

            dest = os.path.join(self.outdir, fname)
            url = fname
            self.subprocess_check_call(["cp", data, dest])
            ci = cram_indexes.split(",")
            cram_index = [
                x.split(":")[1].strip()
                for x in ci
                if ":" in x and x.split(":")[0].strip() == realFName
            ]
            logging.debug(
                "===realFName=%s got %s as cram_indexes %s as ci, %s for cram_index"
                % (realFName, cram_indexes, ci, cram_index)
            )

            url = data
            nrow = self.getNrow(url)
        categ = trackData["category"]
        pg = pafOpts["genome"].split(",")
        pgc = [x.strip() for x in pg if x.strip() > ""]
        gnomes = [x.split(":") for x in pgc]
        passnames = [trackData["assemblyNames"]]  # always first
        for i, (gpath, gname) in enumerate(gnomes):
            # may have been forgotten by user for uri
            if len(gname) == 0:
                gn = os.path.basename(gpath)

            # trouble from spacey names in command lines avoidance
            if len(gname.split()) > 1:
                gname = gname.split()[0]
            if gname not in passnames:
                passnames.append(gname)
            useuri = gpath.startswith("http://") or gpath.startswith("https://")
            if gname not in self.genome_names:
                # ignore if already there - eg for duplicates among pafs.
                asstrack, first_contig = self.make_assembly(gpath, gname, useuri)
                self.genome_names.append(gname)
                self.tracksToAdd[gname] = []

    trackI = 0
    for ass in root.findall("assembly"):
        genomes = [
            {
                "path": x.attrib["path"],
                "label": x.attrib["label"],
                "useuri": x.attrib["useuri"],
                "meta": metadata_from_node(x.find("metadata")),
            }
            for x in ass.findall("metadata/genomes/genome")
        ]

                pass

            trackfiles = track.findall("files/trackFile")
            if trackfiles:
                for x in trackfiles:
                    track_conf["label"] = "%s_%d" % (x.attrib["label"], trackI)
                    trackI += 1
                    track_conf["useuri"] = x.attrib["useuri"]
                    if is_multi_bigwig:
                        multi_bigwig_paths.append(
                            (

93:4c517a0041a8

from collections import defaultdict

logging.basicConfig(level=logging.DEBUG)
log = logging.getLogger("jbrowse")

JB2VER = "v2.11.0"
# version pinned if cloning - but not cloning now
logCommands = True
# useful for seeing what's being written but not for production setups
TODAY = datetime.datetime.now().strftime("%Y-%m-%d")
SELF_LOCATION = os.path.dirname(os.path.realpath(__file__))

                if genome_name == primaryGenome:  # first one
                    this_genome["genome_name"] = genome_name  # first one for all tracks
                    this_genome["genome_sequence_adapter"] = assem["sequence"][
                        "adapter"
                    ]
                    this_genome["genome_firstcontig"] = first_contig
                assmeta.append(this_genome)
        self.assemblies += assembly
        self.assmeta[primaryGenome] = assmeta
        self.tracksToAdd[primaryGenome] = []
        return primaryGenome

        """added code to grab the first contig name and length for broken default session from Anthony and Helena's code
        that poor Bjoern is trying to figure out.
        """
        if useuri:
            faname = fapath
            scontext = ssl.SSLContext(ssl.PROTOCOL_TLS)
            scontext.verify_mode = ssl.VerifyMode.CERT_NONE
            with urllib.request.urlopen(url=faname + ".fai", context=scontext) as f:
                fl = f.readline()
            contig = fl.decode("utf8").strip()

                fadest,
                fadest,
                fadest,
            )
            self.subprocess_popen(cmd)
            contig = open(fadest + ".fai", "r").readline().strip()
        adapter = {
            "type": "BgzipFastaAdapter",
            "fastaLocation": {
                "uri": faname,
            },
            "faiLocation": {
                "uri": faname + ".fai",
            },
            "gziLocation": {
                "uri": faname + ".gzi",
            },
        }
        first_contig = contig.split()[:2]
        first_contig.insert(0, gname)
        trackDict = {
            "name": gname,
            "sequence": {

            self.subprocess_check_call(["cp", data, dest])
            url = fname
            bindex = fname + ".bai"
            bi = bam_indexes.split(",")
            bam_index = [
                x.split(" ~ ")[1].strip()
                for x in bi
                if " ~ " in x and x.split(" ~ ")[0].strip() == realFName
            ]
            logging.debug(
                "===realFName=%s got %s as bam_indexes %s as bi, %s for bam_index"
                % (realFName, bam_indexes, bi, bam_index)
            )

            dest = os.path.join(self.outdir, fname)
            url = fname
            self.subprocess_check_call(["cp", data, dest])
            ci = cram_indexes.split(",")
            cram_index = [
                x.split(" ~ ")[1].strip()
                for x in ci
                if " ~ " in x and x.split(" ~ ")[0].strip() == realFName
            ]
            logging.debug(
                "===realFName=%s got %s as cram_indexes %s as ci, %s for cram_index"
                % (realFName, cram_indexes, ci, cram_index)
            )

            url = data
            nrow = self.getNrow(url)
        categ = trackData["category"]
        pg = pafOpts["genome"].split(",")
        pgc = [x.strip() for x in pg if x.strip() > ""]
        gnomes = [x.split(" ~ ") for x in pgc]
        logging.debug("pg=%s, gnomes=%s" % (pg, gnomes))
        passnames = [trackData["assemblyNames"]]  # always first
        for i, (gpath, gname) in enumerate(gnomes):
            # may have been forgotten by user for uri
            if len(gname) == 0:
                gn = os.path.basename(gpath)

            # trouble from spacey names in command lines avoidance
            if len(gname.split()) > 1:
                gname = gname.split()[0]
            if gname not in passnames:
                passnames.append(gname)
            useuri = pafOpts["useuri"] == "true"
            if gname not in self.genome_names:
                # ignore if already there - eg for duplicates among pafs.
                asstrack, first_contig = self.make_assembly(gpath, gname, useuri)
                self.genome_names.append(gname)
                self.tracksToAdd[gname] = []

    trackI = 0
    for ass in root.findall("assembly"):
        genomes = [
            {
                "path": x.attrib["path"],
                "label": x.attrib["label"].split(" ")[0].replace(",", ""),
                "useuri": x.attrib["useuri"],
                "meta": metadata_from_node(x.find("metadata")),
            }
            for x in ass.findall("metadata/genomes/genome")
        ]

                pass

            trackfiles = track.findall("files/trackFile")
            if trackfiles:
                for x in trackfiles:
                    track_conf["label"] = "%s_%d" % (
                        x.attrib["label"].replace(" ", "_").replace(",", ""),
                        trackI,
                    )
                    trackI += 1
                    track_conf["useuri"] = x.attrib["useuri"]
                    if is_multi_bigwig:
                        multi_bigwig_paths.append(
                            (