Merge pull request #9 from gregory-halverson-jpl/main

fixing download

Author: gregory-halverson-jpl

README.md

@@ -45,7 +45,7 @@ pip install gedi-canopy-height
 Import this package as `gedi_canopy_height` with under-scores.
 
 ```python
-import gedi_canopy_height
+from gedi_canopy_height import load_canopy_height
 ```
 
 ## References

Using wget package.ipynb

@@ -0,0 +1,41 @@
+import os
+import requests
+import posixpath
+from tqdm.notebook import tqdm
+
+def download(URL, filename):
+    # Get the current file size if it exists
+    existing_file_size = os.path.getsize(filename) if os.path.exists(filename) else 0
+    # Request the file details using Range header if a partial file exists
+    headers = {'Range': f'bytes={existing_file_size}-'} if existing_file_size else {}
+    response = requests.get(URL, headers=headers, stream=True)
+
+    # Check for resumable support (206 Partial Content response)
+    if response.status_code not in (200, 206):
+        raise Exception(f"Server does not support resuming or returned an error: {response.status_code}")
+
+    # Determine total size based on Content-Range or Content-Length
+    content_range = response.headers.get('Content-Range')
+    if content_range:
+        total_size = int(content_range.split('/')[-1])
+    else:
+        total_size = int(response.headers.get('content-length', 0)) + existing_file_size
+
+    # Set mode to append if resuming, otherwise write
+    mode = 'ab' if existing_file_size else 'wb'
+    
+    # Start download
+    with open(filename, mode) as f, tqdm(
+        initial=existing_file_size,
+        total=total_size,
+        unit='B',
+        unit_scale=True,
+        unit_divisor=1024,
+        desc=f"Downloading {posixpath.basename(URL)}"
+    ) as bar:
+        for chunk in response.iter_content(chunk_size=8192):
+            if chunk:
+                f.write(chunk)
+                bar.update(len(chunk))
+
+    print(f"Download completed: {filename}")

gedi_canopy_height/download.py

@@ -12,6 +12,8 @@
 import rasters as rt
 from rasters import RasterGeometry, Raster
 
+from .download import download
+
 GEDI_DOWNLOAD_DIRECTORY = join("~", "data", "gedi-canopy-height")
 
 CANOPY_COLORMAP = LinearSegmentedColormap.from_list(
@@ -56,9 +58,10 @@ def download_file(self, URL: str, filename: str) -> str:
         directory = dirname(filename_absolute)
         makedirs(directory, exist_ok=True)
         partial_filename = f"{filename_absolute}.download"
-        command = f'wget -c -O "{partial_filename}" "{URL}"'
+        # command = f'wget -c -O "{partial_filename}" "{URL}"'
         download_start = perf_counter()
         # system(command)
+        download(URL, partial_filename)
         download_end = perf_counter()
         download_duration = download_end - download_start
         self.logger.info(f"completed download in {download_duration:0.2f} seconds: {filename}")

gedi_canopy_height/gedi_canopy_height.py

@@ -1 +1 @@
-1.1.1
+1.2.0

gedi_canopy_height/version.txt

@@ -3,7 +3,7 @@ requires = ["setuptools>=60", "setuptools-scm>=8.0", "wheel"]
 
 [project]
 name = "gedi-canopy-height"
-version = "1.1.1"
+version = "1.2.0"
 description = "generates rasters of canopy height from the Global Ecosystem Dynamics Investigation (GEDI) mission"
 readme = "README.md"
 authors = [