terrakit 0.2.0__tar.gz → 0.2.2__tar.gz

{terrakit-0.2.0 → terrakit-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: terrakit
-Version: 0.2.0
+Version: 0.2.2
 Summary: A Python package for finding and getting geospatial data.
 Author: Blair Edwards, Rosie Lickorish, Leonardo Pondian Tizzei, Fred Ochieng Otieno, Beldine Moturi, Catherine Wanjiru, Benedikt Blumenstiel, Brian Ogolla, Romeo Kienzler
 Author-email: Blair Edwards <bedwards@uk.ibm.com>

{terrakit-0.2.0 → terrakit-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "TerraKit"
-version = "0.2.0"
+version = "0.2.2"
 description = "A Python package for finding and getting geospatial data."
 readme = "README.md"
 requires-python = ">=3.11"

{terrakit-0.2.0 → terrakit-0.2.2}/terrakit/download/collections.json

@@ -86,7 +86,7 @@
       "B02"
     ],
     "resolution_m": 10,
-    "query_template": "Template(\"\"\" //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } \"\"\")",
+    "query_template": " //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } ",
     "collection_name": "s2_l1c",
     "modality_tag": "S2L1C",
     "data_collection": "DataCollection.SENTINEL2_L1C",
@@ -111,7 +111,7 @@
     },
     "connector": "sentinelhub",
     "resolution_m": null,
-    "query_template": "Template(\"\"\" //VERSION=3 \\n\nfunction setup() { return { input: [\"DEM\"], output:{ id: \"default\", bands: 1, sampleType: SampleType.FLOAT32 } } }\nfunction evaluatePixel(sample) { return [sample.DEM] } \"\"\")",
+    "query_template": " //VERSION=3 \\n\nfunction setup() { return { input: [\"DEM\"], output:{ id: \"default\", bands: 1, sampleType: SampleType.FLOAT32 } } }\nfunction evaluatePixel(sample) { return [sample.DEM] } ",
     "collection_name": "dem",
     "modality_tag": "DEM",
     "data_collection": "DataCollection.DEM_COPERNICUS_30",
@@ -151,7 +151,7 @@
     "connector": "sentinelhub",
     "modality_tag": "S1GRD",
     "resolution_m": 10,
-    "query_template": "Template(\"\"\" //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"LINEAR_POWER\" }], output: { bands: ${num_bands}, sampleType: \"FLOAT32\" } }; }\nfunction evaluatePixel(sample) { return ${band_samples}; } \"\"\")",
+    "query_template": " //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"LINEAR_POWER\" }], output: { bands: ${num_bands}, sampleType: \"FLOAT32\" } }; }\nfunction evaluatePixel(sample) { return ${band_samples}; } ",
     "collection_name": "s1_grd",
     "data_collection": "DataCollection.SENTINEL1_IW",
     "request_input_data": {
@@ -241,7 +241,7 @@
       "band": "SCL",
       "encoding": "sentinel2_lulc"
     },
-    "query_template": "Template(\"\"\" //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } \"\"\")",
+    "query_template": " //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } ",
     "collection_name": "hls_l30",
     "data_collection": "DataCollection.HARMONIZED_LANDSAT_SENTINEL",
     "request_input_data": {
@@ -352,7 +352,7 @@
       "band": "SCL",
       "encoding": "sentinel2_lulc"
     },
-    "query_template": "Template(\"\"\" //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } \"\"\")",
+    "query_template": " //VERSION=3 \\n function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } ",
     "collection_name": "s2_l2a",
     "data_collection": "DataCollection.SENTINEL2_L2A",
     "request_input_data": {
@@ -458,7 +458,7 @@
       "band": "SCL",
       "encoding": "sentinel2_lulc"
     },
-    "query_template": "Template(\"\"\" //VERSION=3 function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } \"\"\")",
+    "query_template": " //VERSION=3 function setup() { return { input: [{ bands: ${bands}, units: \"DN\" }], output: { bands: ${num_bands}, sampleType: \"INT16\" } }; } function evaluatePixel(sample) { return ${band_samples}; } ",
     "collection_name": "hls_s30",
     "data_collection": "DataCollection.HARMONIZED_LANDSAT_SENTINEL",
     "request_input_data": {

{terrakit-0.2.0 → terrakit-0.2.2}/terrakit/download/data_connectors/nasa_earthdata.py

@@ -168,25 +168,46 @@ def get_band(date_items, band, bbox, temp_creds_req, working_dir):
     # Transform the bounding box to the CRS of the first link
     hls_bbox = list(rio.warp.transform_bounds("EPSG:4326", hls_proj, *bbox))
 
-    # Prepare the gdalbuildvrt command based on whether a NASA_EARTH_BEARER_TOKEN is available
-    if NASA_EARTH_BEARER_TOKEN:
-        build_vrt = f"gdalbuildvrt {working_dir}/links_{band}_{date}.vrt -separate --config GDAL_HTTP_AUTH BEARER --config GDAL_HTTP_BEARER {NASA_EARTH_BEARER_TOKEN} --config AWS_ACCESS_KEY_ID {temp_creds_req['accessKeyId']} --config AWS_SECRET_ACCESS_KEY {temp_creds_req['secretAccessKey']} --config AWS_SESSION_TOKEN {temp_creds_req['sessionToken']} --config GDAL_DISABLE_READDIR_ON_OPEN TRUE"
-    else:
-        build_vrt = f"gdalbuildvrt {working_dir}/links_{band}_{date}.vrt -separate --config AWS_ACCESS_KEY_ID {temp_creds_req['accessKeyId']} --config AWS_SECRET_ACCESS_KEY {temp_creds_req['secretAccessKey']} --config AWS_SESSION_TOKEN {temp_creds_req['sessionToken']} --config GDAL_DISABLE_READDIR_ON_OPEN TRUE"
+    # Prepare the gdalbuildvrt argument list
+    vrt_path = os.path.join(working_dir, f"links_{band}_{date}.vrt")
+    build_vrt = ["gdalbuildvrt", vrt_path, "-separate"]
 
-    # Combine the gdalbuildvrt command with the list of links
-    build_vrt = " ".join([build_vrt] + links)
+    if NASA_EARTH_BEARER_TOKEN:
+        build_vrt += [
+            "--config",
+            "GDAL_HTTP_AUTH",
+            "BEARER",
+            "--config",
+            "GDAL_HTTP_BEARER",
+            NASA_EARTH_BEARER_TOKEN,
+        ]
 
-    # Execute the gdalbuildvrt command using subprocess
-    subprocess.call(build_vrt, shell=True)
+    build_vrt += [
+        "--config",
+        "AWS_ACCESS_KEY_ID",
+        temp_creds_req["accessKeyId"],
+        "--config",
+        "AWS_SECRET_ACCESS_KEY",
+        temp_creds_req["secretAccessKey"],
+        "--config",
+        "AWS_SESSION_TOKEN",
+        temp_creds_req["sessionToken"],
+        "--config",
+        "GDAL_DISABLE_READDIR_ON_OPEN",
+        "TRUE",
+    ]
+
+    # Each link is a separate list element
+    build_vrt += links
+
+    # Execute gdalbuildvrt directly
+    result = subprocess.run(build_vrt, check=True)
 
     # Define chunking parameters for efficient reading of the VRT
     chunks = dict(band=1, x=512, y=512)
 
     # Open the VRT file using rioxarray
-    data = rioxarray.open_rasterio(
-        f"{working_dir}/links_{band}_{date}.vrt", chunks=chunks
-    )
+    data = rioxarray.open_rasterio(vrt_path, chunks=chunks)
 
     # Rename the 'band' dimension to 'time' and add a new 'band' dimension
     data = data.rename({"band": "time"})

{terrakit-0.2.0 → terrakit-0.2.2}/terrakit/download/data_connectors/sentinelhub.py

@@ -5,6 +5,7 @@
 # Assisted by watsonx Code Assistant
 
 import os
+import json
 import numpy as np
 import xarray as xr
 import rioxarray
@@ -93,7 +94,12 @@ def create_request(
     data_folder="./",
     maxcc=None,
 ):
-    evalscript = eval(data_details["query_template"]).substitute(
+    qt = data_details["query_template"]
+    if not qt.strip().startswith("//VERSION=3"):
+        raise TerrakitValidationError(
+            "Invalid query_template value: does not start with //VERSION=3"
+        )
+    evalscript = Template(qt).substitute(
         {
             "bands": str(bands),
             "num_bands": len(bands),
@@ -101,17 +107,31 @@ def create_request(
         }
     )
 
+    dc_name = data_details["data_collection"]  # e.g. "DataCollection.SENTINEL2_L1C"
+    dc_prefix = "DataCollection."
+    if not dc_name.startswith(dc_prefix):
+        raise TerrakitValidationError(f"Invalid data_collection value: {dc_name!r}")
+    member_name = dc_name[len(dc_prefix) :]
+    data_collection = getattr(DataCollection, member_name)
+
     shr = SentinelHubRequest.input_data(
-        data_collection=eval(data_details["data_collection"]),
+        data_collection=data_collection,
         time_interval=(timestamp_start, timestamp_end),
     )
 
     if maxcc is not None:
         shr["maxCloudCoverage"] = maxcc / 100.0
     if "mosaicking_order" in data_details["request_input_data"]:
-        shr["mosaickingOrder"] = eval(
-            data_details["request_input_data"]["mosaicking_order"]
-        ).value
+        mosaicking_order_name = data_details["request_input_data"][
+            "mosaicking_order"
+        ]  # i.e. "MosaickingOrder.LEAST_CC"
+        mosaicking_order_prefix = "MosaickingOrder."
+        if not mosaicking_order_name.startswith(mosaicking_order_prefix):
+            raise TerrakitValidationError(
+                f"Invalid mosaicking_order value: {mosaicking_order_name!r}"
+            )
+        member_name = mosaicking_order_name[len(mosaicking_order_prefix) :]
+        shr["mosaickingOrder"] = getattr(MosaickingOrder, member_name).value
 
     logger.info(shr)
 
@@ -299,7 +319,14 @@ class SentinelHub(Connector):
                 raise ValueError(error_msg)
             data_connector_spec = data_connector_spec_list[0]
 
-        data_collection = eval(data_connector_spec["data_collection"])
+        dc_name = data_connector_spec[
+            "data_collection"
+        ]  # e.g. "DataCollection.SENTINEL2_L1C"
+        dc_prefix = "DataCollection."
+        if not dc_name.startswith(dc_prefix):
+            raise TerrakitValidationError(f"Invalid data_collection value: {dc_name!r}")
+        member_name = dc_name[len(dc_prefix) :]
+        data_collection = getattr(DataCollection, member_name)
 
         self.sh_config.sh_base_url = data_collection.service_url
         logger.info(self.sh_config.sh_base_url)
@@ -319,7 +346,12 @@ class SentinelHub(Connector):
             filter_string = ""
 
         if "fields" in data_connector_spec["search"]:
-            fields_dict = eval(data_connector_spec["search"]["fields"])
+            fields_str = data_connector_spec["search"]["fields"]
+            if len(fields_str) > 1024:
+                raise TerrakitValidationError(
+                    "search.fields value exceeds maximum allowed length"
+                )
+            fields_dict = json.loads(fields_str)
 
         else:
             fields_dict = {"include": ["id", "properties.datetime"], "exclude": []}

{terrakit-0.2.0 → terrakit-0.2.2}/terrakit/download/geodata_utils.py

@@ -23,6 +23,7 @@ from sentinelhub import (
     bbox_to_dimensions,
 )
 from pathlib import Path
+from rasterio.warp import calculate_default_transform, reproject, Resampling
 from shapely.geometry import shape
 from typing import Any, Dict, Union
 
@@ -306,44 +307,75 @@ def verify_input_image(image, standard_dimensions=224) -> typing.Tuple[int, str]
     Return:
         tuple[int, str]: [verification_status_code, verification_msg]
     """
-    res = os.popen(f"gdalinfo {image} -json").read()
-    res_json = json.loads(res)
-    dims = res_json["size"]
+    try:
+        with rasterio.open(image) as src:
+            dims = (src.height, src.width)
 
-    # Check if image is geotiff
-    if res_json["driverShortName"] != "GTiff":
-        return 1007, f"Input {image} is not a GeoTiff."
+            # Check if image is geotiff
+            if src.driver != "GTiff":
+                return 1007, f"Input {image} is not a GeoTiff."
 
-    # Check image dimensions
-    image_input_dimensions = np.min(dims)
+            # Check image dimensions
+            image_input_dimensions = np.min(dims)
 
-    if image_input_dimensions < standard_dimensions:
-        return (
-            1002,
-            f"Input image too small for image {image} with dimensions {image_input_dimensions}. Both dimensions must be >= 224.",
-        )
-    else:
-        # Log/Show dimensions of the input image
-        logger.debug(f"Input image {image} has dimensions {image_input_dimensions}")
-        return 200, str(image_input_dimensions)
+            if image_input_dimensions < standard_dimensions:
+                return (
+                    1002,
+                    f"Input image too small for image {image} with dimensions {image_input_dimensions}. Both dimensions must be >= 224.",
+                )
+            else:
+                # Log/Show dimensions of the input image
+                logger.debug(
+                    f"Input image {image} has dimensions {image_input_dimensions}"
+                )
+                return 200, str(image_input_dimensions)
+    except rasterio.errors.RasterioIOError as e:
+        return 1001, f"Failed to open image {image}: {e}"
 
 
-def check_projection(file):
+def check_projection(file: Union[str, Path]) -> None:
     """
-    Check the projection is correct, if not reproject to EPSG:4326
+    Check the projection is correct, if not reproject to EPSG:4326.
 
     Parameters:
-        file (str): The path to the input file.
-
-    Returns:
-        None
+        file (str | Path): The path to the input file.
     """
-    res = os.popen(f"gdalinfo {file} -proj4 -json").read()
-    res_json = json.loads(res)
-    # WGS84 is the same as EPSG:4326
-    if res_json["stac"]["proj:epsg"] != 4326:
-        os.system(f"gdalwarp {file} -t_srs EPSG:4326 {file}_reprojected.tif")
-        os.system(f"mv {file}_reprojected.tif {file} ")
+    file_path = Path(file)
+    target_crs = CRS.from_epsg(4326)
+
+    with rasterio.open(file_path) as src:
+        # Check if already in EPSG:4326
+        if src.crs == target_crs or (src.crs and src.crs.to_epsg() == 4326):
+            return
+
+        transform, width, height = calculate_default_transform(
+            src.crs, target_crs, src.width, src.height, *src.bounds
+        )
+        kwargs = src.meta.copy()
+        kwargs.update(
+            {
+                "crs": target_crs,
+                "transform": transform,
+                "width": width,
+                "height": height,
+            }
+        )
+
+        temp_file = file_path.with_name(f"{file_path.stem}_reprojected.tif")
+        with rasterio.open(temp_file, "w", **kwargs) as dst:
+            for i in range(1, src.count + 1):
+                reproject(
+                    source=rasterio.band(src, i),
+                    destination=rasterio.band(dst, i),
+                    src_transform=src.transform,
+                    src_crs=src.crs,
+                    dst_transform=transform,
+                    dst_crs=target_crs,
+                    resampling=Resampling.nearest,
+                )
+
+    # Atomically replace original file with reprojected file
+    temp_file.replace(file_path)
 
 
 def pad_bbox(padding_degrees, bbox):