示例#1
0
    def to_api_dict(self, full=True, api_version: ComparableVersion = None) -> dict:
        """
        API-version-aware conversion of batch job metadata to jsonable openEO API compatible dict.
        see https://openeo.org/documentation/1.0/developers/api/reference.html#operation/describe-job
        """
        # Basic/full fields to export
        fields = ["id", "title", "description", "status", "progress", "created", "updated", "plan", "costs", "budget"]
        if full:
            fields.extend(["process"])
        result = {f: getattr(self, f) for f in fields}

        # Additional cleaning and massaging.
        result["created"] = rfc3339.datetime(self.created) if self.created else None
        result["updated"] = rfc3339.datetime(self.updated) if self.updated else None

        if full:
            usage = self.usage or {}
            if self.cpu_time:
                usage["cpu"] = {"value": int(round(self.cpu_time.total_seconds())), "unit": "cpu-seconds"}
            if self.duration:
                usage["duration"] = {"value": int(round(self.duration.total_seconds())), "unit": "seconds"}
            if self.memory_time_megabyte:
                usage["memory"] = {"value": int(round(self.memory_time_megabyte.total_seconds())), "unit": "mb-seconds"}
            if usage:
                result["usage"] = usage

        if api_version and api_version.below("1.0.0"):
            result["process_graph"] = result.pop("process", {}).get("process_graph")
            result["submitted"] = result.pop("created", None)
            # TODO wider status checking coverage?
            if result["status"] == "created":
                result["status"] = "submitted"

        return dict_no_none(result)
示例#2
0
    def set_status(self, job_id: str, user_id: str, status: str) -> None:
        """Updates a registered batch job with its status. Additionally, updates its "updated" property."""

        self.patch(job_id,
                   user_id,
                   status=status,
                   updated=rfc3339.datetime(datetime.utcnow()))
        _log.debug("batch job {j} -> {s}".format(j=job_id, s=status))
示例#3
0
 def register(self,
              job_id: str,
              user_id: str,
              api_version: str,
              specification: dict,
              title: str = None,
              description: str = None) -> dict:
     """Registers a to-be-run batch job."""
     # TODO: use `BatchJobMetadata` instead of free form dict here?
     job_info = {
         'job_id': job_id,
         'user_id': user_id,
         'status': 'created',
         # TODO: move api_Version into specification?
         'api_version': api_version,
         # TODO: why json-encoding `specification` when the whole job_info dict will be json-encoded anyway?
         'specification': json.dumps(specification),
         'application_id': None,
         'created': rfc3339.datetime(datetime.utcnow()),
         'title': title,
         'description': description,
     }
     self._create(job_info)
     return job_info
示例#4
0
def test_rfc3339_datetime():
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime("2020-03-17")
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime("2020/03/17")
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime("2020:03:17")
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime("2020_03_17")
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime("2020-03-17-12-34-56")
    assert "2020-03-17T12:34:00Z" == rfc3339.datetime("2020-03-17-12-34")
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime("2020:03:17:12:34:56")
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime("2020/03/17/12/34/56")
    assert "2020-03-17T12:34:00Z" == rfc3339.datetime("2020/03/17/12/34")
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime("2020_03_17_12_34_56")
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime("2020-03-17T12:34:56Z")
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime(date(2020, 3, 17))
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime(datetime(2020, 3, 17, 12, 34, 56))
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime((2020, 3, 17))
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime([2020, 3, 17])
    assert "2020-03-17T00:00:00Z" == rfc3339.datetime(2020, 3, 17)
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime((2020, 3, 17, 12, 34, 56))
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime([2020, 3, 17, 12, 34, 56])
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime(2020, 3, 17, 12, 34, 56)
    assert "2020-03-17T12:34:00Z" == rfc3339.datetime(2020, 3, 17, 12, 34)
    assert "2020-03-17T12:34:56Z" == rfc3339.datetime((2020, "3", 17, "12", "34", 56))
    assert "2020-09-17T12:34:56Z" == rfc3339.datetime([2020, "09", 17, "12", "34", 56])
    assert "2020-09-17T12:34:56Z" == rfc3339.datetime(2020, "09", "17", "12", "34", 56)
示例#5
0
def load_test_collection(
    collection_id: str,
    collection_metadata: GeopysparkCubeMetadata,
    extent,
    srs: str,
    from_date: str,
    to_date: str,
    bands=None,
    correlation_id: str = "NA",
) -> Dict[int, geopyspark.TiledRasterLayer]:
    """
    Load synthetic data as test collection
    :param collection_id:
    :param collection_metadata:
    :param extent:
    :param srs:
    :param from_date:
    :param to_date:
    :param bands:
    :param correlation_id:
    :return:
    """
    # TODO: support more test collections
    assert collection_id == "TestCollection-LonLat4x4"
    grid_size: float = 1.0
    tile_size = 4

    # TODO: support other srs'es?
    assert srs == "EPSG:4326"

    # Get bounds of tiling layout
    extent = geopyspark.Extent(extent.xmin(), extent.ymin(), extent.xmax(),
                               extent.ymax())
    col_min = int(math.floor(extent.xmin / grid_size))
    row_min = int(math.floor(extent.ymin / grid_size))
    col_max = int(math.ceil(extent.xmax / grid_size) - 1)
    row_max = int(math.ceil(extent.ymax / grid_size) - 1)

    # Simulate sparse range of observation dates
    from_date = rfc3339.parse_datetime(rfc3339.datetime(from_date))
    to_date = rfc3339.parse_datetime(rfc3339.datetime(to_date))
    dates = dates_between(from_date, to_date)

    # Build RDD of tiles with requested bands.
    tile_builder = TestCollectionLonLat(tile_size=tile_size,
                                        grid_size=grid_size)
    bands = bands or [b.name for b in collection_metadata.bands]
    rdd_data = [(SpaceTimeKey(col, row, date),
                 tile_builder.get_tile(bands=bands,
                                       col=col,
                                       row=row,
                                       date=date))
                for col in range(col_min, col_max + 1)
                for row in range(row_min, row_max + 1) for date in dates]
    rdd = SparkContext.getOrCreate().parallelize(rdd_data)

    metadata = Metadata(
        bounds=Bounds(SpaceTimeKey(col_min, row_min, min(dates)),
                      SpaceTimeKey(col_max, row_max, max(dates))),
        crs="+proj=longlat +datum=WGS84 +no_defs ",
        cell_type=CellType.FLOAT64,
        extent=extent,
        layout_definition=LayoutDefinition(
            extent=geopyspark.Extent(col_min * grid_size, row_min * grid_size,
                                     (col_max + 1) * grid_size,
                                     (row_max + 1) * grid_size),
            tileLayout=TileLayout(layoutCols=col_max - col_min + 1,
                                  layoutRows=row_max - row_min + 1,
                                  tileCols=tile_size,
                                  tileRows=tile_size)))
    layer = TiledRasterLayer.from_numpy_rdd(LayerType.SPACETIME, rdd, metadata)
    return {0: layer}
示例#6
0
 def prepare_for_json(self) -> dict:
     """Prepare metadata for JSON serialization"""
     d = self._asdict()  # pylint: disable=no-member
     d["created"] = rfc3339.datetime(self.created) if self.created else None
     return d
示例#7
0
def utcnow_rfc3339() -> str:
    """Current datetime formatted as RFC-3339 string."""
    return rfc3339.datetime(datetime.utcnow())