comparison jbrowse2.py @ 99:990291e918c7 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/jbrowse2 commit a1537aea75fc902d0e38c0b7c698830a939648b1-dirty

98:b1260bca5fdc

from collections import defaultdict

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

JB2VER = "v2.11.0"
# version pinned if cloning - but not used until 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__))
GALAXY_INFRASTRUCTURE_URL = None

        retcode = p.returncode
        if retcode != 0:
            log.error(command)
            log.error(output)
            log.error(err)
            raise RuntimeError(f"Command ( {command} ) failed with exit code {retcode}")

    def subprocess_check_output(self, command):
        if logCommands:
            log.debug(" ".join(command))
        return subprocess.check_output(command, cwd=self.outdir)

                    "url": "https://unpkg.com/jbrowse-plugin-mafviewer/dist/jbrowse-plugin-mafviewer.umd.production.min.js",
                }
            ]
        }
        categ = trackData["category"]
        fname = f"{tId}"
        dest = os.path.join(self.outdir, fname)
        gname = trackData["assemblyNames"]

        cmd = [
            "bash",
            os.path.join(INSTALLED_TO, "convertMAF.sh"),

        self.tracksToAdd[trackData["assemblyNames"]].append(trackDict)
        self.trackIdlist.append(tId)

    def process_annotations(self, track):
        category = track["category"].replace("__pd__date__pd__", TODAY)
        for trackIndex, (
            dataset_path,
            dataset_ext,
            useuri,
            track_human_label,

        ) in enumerate(track["trackfiles"]):
            if not dataset_path.strip().startswith("http"):
                # Unsanitize labels (element_identifiers are always sanitized by Galaxy)
                for key, value in mapped_chars.items():
                    track_human_label = track_human_label.replace(value, key)
                track_human_label = track_human_label.replace(" ", "_")
            outputTrackConfig = {
                "category": category,
                "style": {},
            }

            # hashData = [
            #    str(dataset_path),
            #    track_human_label,
            #    track["category"],
            # ]
            # hashData = "|".join(hashData).encode("utf-8")
            # hash_string = hashlib.md5(hashData).hexdigest()

            outputTrackConfig["assemblyNames"] = track["assemblyNames"]
            outputTrackConfig["key"] = track_human_label
            outputTrackConfig["useuri"] = useuri
            outputTrackConfig["path"] = dataset_path
            outputTrackConfig["ext"] = dataset_ext
            outputTrackConfig["trackset"] = track.get("trackset", {})
            outputTrackConfig["label"] = track["label"]
            # outputTrackConfig["label"] = "%s_%i_%s_%s" % (
            #    dataset_ext,
            #    trackIndex,
            #    track_human_label,
            #    hash_string,
            # )

            outputTrackConfig["metadata"] = extra_metadata
            outputTrackConfig["name"] = track_human_label
            if track["label"] in self.trackIdlist:
                logging.error(
                    "### not adding %s already in %s"

        default session settings are hard and fragile.
        .add_default_view() and other configuration code adapted from
         https://github.com/abretaud/tools-iuc/blob/jbrowse2/tools/jbrowse2/jbrowse2.py
        """
        # TODO using the default session for now, but check out session specs in the future https://github.com/GMOD/jbrowse-components/issues/2708
        track_types = {}
        with open(self.config_json_file, "r") as config_file:
            config_json = json.load(config_file)
        if self.config_json:
            config_json.update(self.config_json)

                            "type": track_types[tId],
                            "configuration": tId,
                            "displays": [style_data],
                        }
                    )
            view_json = {
                "type": "LinearGenomeView",
                "offsetPx": 0,
                "minimized": False,
                "tracks": tracks_data,
            }
            first = [x for x in self.ass_first_contigs if x[0] == gnome]
            if len(first) > 0:
                [gnome, refName, end] = first[0]
                start = 0
                end = int(end)
                drdict = {
                    "refName": refName,
                    "start": start,
                    "end": end,
                    "reversed": False,
                    "assemblyName": gnome,
                }
            else:
                ddl = default_data.get("defaultLocation", None)
                if ddl:
                    loc_match = re.search(r"^([^:]+):([\d,]*)\.*([\d,]*)$", ddl)
                    # allow commas like 100,000 but ignore as integer

                    else:
                        logging.info(
                            "@@@ regexp could not match contig:start..end in the supplied location %s - please fix"
                            % ddl
                        )
            if drdict.get("refName", None):
                # TODO displayedRegions is not just zooming to the region, it hides the rest of the chromosome
                view_json["displayedRegions"] = [
                    drdict,
                ]

            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:

99:990291e918c7

from collections import defaultdict

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

JB2VER = "v2.11.1"
# 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__))
GALAXY_INFRASTRUCTURE_URL = None

        retcode = p.returncode
        if retcode != 0:
            log.error(command)
            log.error(output)
            log.error(err)
            raise RuntimeError("Command failed with exit code %s" % (retcode))

    def subprocess_check_output(self, command):
        if logCommands:
            log.debug(" ".join(command))
        return subprocess.check_output(command, cwd=self.outdir)

                    "url": "https://unpkg.com/jbrowse-plugin-mafviewer/dist/jbrowse-plugin-mafviewer.umd.production.min.js",
                }
            ]
        }
        categ = trackData["category"]
        fname = tId
        dest = "%s/%s" % (self.outdir, fname)
        gname = trackData["assemblyNames"]

        cmd = [
            "bash",
            os.path.join(INSTALLED_TO, "convertMAF.sh"),

        self.tracksToAdd[trackData["assemblyNames"]].append(trackDict)
        self.trackIdlist.append(tId)

    def process_annotations(self, track):
        category = track["category"].replace("__pd__date__pd__", TODAY)
        tt1 = ",/ :;\\"
        tt2 = "______"
        labttab = str.maketrans(tt1,tt2)
        for trackIndex, (
            dataset_path,
            dataset_ext,
            useuri,
            track_human_label,

        ) in enumerate(track["trackfiles"]):
            if not dataset_path.strip().startswith("http"):
                # Unsanitize labels (element_identifiers are always sanitized by Galaxy)
                for key, value in mapped_chars.items():
                    track_human_label = track_human_label.replace(value, key)
                track_human_label = track_human_label.translate(labttab)
            outputTrackConfig = {
                "category": category,
                "style": {},
            }

            outputTrackConfig["assemblyNames"] = track["assemblyNames"]
            outputTrackConfig["key"] = track_human_label
            outputTrackConfig["useuri"] = useuri
            outputTrackConfig["path"] = dataset_path
            outputTrackConfig["ext"] = dataset_ext
            outputTrackConfig["trackset"] = track.get("trackset", {})
            outputTrackConfig["label"] = track["label"]
            outputTrackConfig["metadata"] = extra_metadata
            outputTrackConfig["name"] = track_human_label
            if track["label"] in self.trackIdlist:
                logging.error(
                    "### not adding %s already in %s"

        default session settings are hard and fragile.
        .add_default_view() and other configuration code adapted from
         https://github.com/abretaud/tools-iuc/blob/jbrowse2/tools/jbrowse2/jbrowse2.py
        """
        # TODO using the default session for now, but check out session specs in the future https://github.com/GMOD/jbrowse-components/issues/2708
        bpPerPx = 50 # this is tricky since browser window width is unknown - this seems a compromise that sort of works....
        track_types = {}
        with open(self.config_json_file, "r") as config_file:
            config_json = json.load(config_file)
        if self.config_json:
            config_json.update(self.config_json)

                            "type": track_types[tId],
                            "configuration": tId,
                            "displays": [style_data],
                        }
                    )
            first = [x for x in self.ass_first_contigs if x[0] == gnome]
            drdict = {
                    "reversed": False,
                    "assemblyName": gnome,
                }
            if len(first) > 0:
                [gnome, refName, end] = first[0]
                drdict["refName"] = refName
                drdict["start"] = 0
                end = int(end)
                drdict["end"] = end        
            else:
                ddl = default_data.get("defaultLocation", None)
                if ddl:
                    loc_match = re.search(r"^([^:]+):([\d,]*)\.*([\d,]*)$", ddl)
                    # allow commas like 100,000 but ignore as integer

                    else:
                        logging.info(
                            "@@@ regexp could not match contig:start..end in the supplied location %s - please fix"
                            % ddl
                        )
            view_json = {
                "type": "LinearGenomeView",
                "offsetPx": 0,
                "bpPerPx" : bpPerPx,
                "minimized": False,
                "tracks": tracks_data
            }
            if drdict.get("refName", None):
                # TODO displayedRegions is not just zooming to the region, it hides the rest of the chromosome
                view_json["displayedRegions"] = [
                    drdict,
                ]

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