Merge pull request #49 from forrestfwilliams/develop

Release v0.5.2

Author: forrestfwilliams

CHANGELOG.md

@@ -6,6 +6,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [PEP 440](https://www.python.org/dev/peps/pep-0440/)
 and uses [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.5.2]
+
+### Fixed
+* Removed hyp3lib to fix environment build issue related to pinning of GDAL version.
+
 ## [0.5.1]
 
 ### Added

environment.yml

@@ -18,7 +18,8 @@ dependencies:
   - sarpy
   - burst2safe
   - tqdm
-  - hyp3lib
+  - requests
+  - urllib3
   # For multimetric
   - matplotlib
   - pandas

pyproject.toml

@@ -31,7 +31,8 @@ dependencies = [
     "sarpy",
     "burst2safe",
     "tqdm",
-    "hyp3lib",
+    "requests",
+    "urllib3",
     "matplotlib",
     "pandas",
     "lmfit",

src/multirtc/dem.py

@@ -8,10 +8,11 @@
 
 import numpy as np
 import shapely
-from hyp3lib.fetch import download_file
 from osgeo import gdal, osr
 from shapely.geometry import LinearRing, Polygon, box
 
+from multirtc.fetch import download_file
+
 
 gdal.UseExceptions()
 URL = 'https://nisar.asf.earthdatacloud.nasa.gov/STATIC/DEM/v1.1/EPSG4326'

src/multirtc/fetch.py

@@ -0,0 +1,75 @@
+"""Utilities for fetching things from external endpoints. Vendored from hyp3lib"""
+
+import logging
+from email.message import Message
+from os.path import basename
+from pathlib import Path
+from urllib.parse import urlparse
+
+import requests
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
+
+
+def _get_download_path(url: str, content_disposition: str | None = None, directory: Path | str = '.'):
+    filename = None
+    if content_disposition is not None:
+        message = Message()
+        message['content-type'] = content_disposition
+        filename = message.get_param('filename')
+    if not filename:
+        filename = basename(urlparse(url).path)
+    if not filename:
+        raise ValueError(f'could not determine download path for: {url}')
+    assert isinstance(filename, str)
+    return Path(directory) / filename
+
+
+def download_file(
+    url: str,
+    directory: Path | str = '.',
+    chunk_size=None,
+    retries=2,
+    backoff_factor=1,
+    auth: tuple[str, str] | None = None,
+    token: str | None = None,
+) -> str:
+    """Download a file
+
+    Args:
+        url: URL of the file to download
+        directory: Directory location to place files into
+        chunk_size: Size to chunk the download into
+        retries: Number of retries to attempt
+        backoff_factor: Factor for calculating time between retries
+        auth: Username and password for HTTP Basic Auth
+        token: Token for HTTP Bearer authentication
+
+    Returns:
+        download_path: The path to the downloaded file
+    """
+    logging.info(f'Downloading {url}')
+
+    session = requests.Session()
+    session.auth = auth
+    if token:
+        session.headers.update({'Authorization': f'Bearer {token}'})
+
+    retry_strategy = Retry(
+        total=retries,
+        backoff_factor=backoff_factor,
+        status_forcelist=[429, 500, 502, 503, 504],
+    )
+    session.mount('https://', HTTPAdapter(max_retries=retry_strategy))
+    session.mount('http://', HTTPAdapter(max_retries=retry_strategy))
+
+    with session.get(url, stream=True) as s:
+        download_path = _get_download_path(s.url, s.headers.get('content-disposition'), directory)
+        s.raise_for_status()
+        with open(download_path, 'wb') as f:
+            for chunk in s.iter_content(chunk_size=chunk_size):
+                if chunk:
+                    f.write(chunk)
+    session.close()
+
+    return str(download_path)