Merge pull request #82 from jreiberkyle/geotiff-download-80

use rasterio to determine if path is a valid tif

Author: drewbo

label_maker/utils.py

@@ -119,8 +119,21 @@ def get_tile_wms(tile, imagery, folder, imagery_offset):
 
 
 def is_tif(imagery):
-    """Determine if an imagery path has a valid tif extension"""
-    return op.splitext(imagery)[1].lower() in ['.tif', '.tiff', '.vrt']
+    """Determine if an imagery path leads to a valid tif"""
+    valid_drivers = ['GTiff', 'VRT']
+    try:
+        with rasterio.open(imagery) as test_ds:
+            if test_ds.meta['driver'] not in valid_drivers:
+                # rasterio can open path, but it is not a tif
+                valid_tif = False
+            else:
+                valid_tif = True
+    except rasterio._err.CPLE_HttpResponseError: #pylint: disable=protected-access
+        # rasterio cannot open the path. this is the case for a
+        # tile service
+        valid_tif = False
+
+    return valid_tif
 
 def is_wms(imagery):
     """Determine if an imagery path is a WMS endpoint"""

test/unit/test_utils.py

@@ -1,11 +1,13 @@
 """Tests for utils.py"""
 import os
 from os import path as op, makedirs
+import shutil
+import tempfile
 import unittest
 import numpy as np
 from PIL import Image
 
-from label_maker.utils import url, class_match, get_tile_tif, get_tile_wms
+from label_maker.utils import url, class_match, get_tile_tif, get_tile_wms, is_tif
 
 class TestUtils(unittest.TestCase):
     """Tests for utility functions"""
@@ -43,6 +45,33 @@ def test_class_match_segmentation(self):
         self.assertTrue(class_match(ml_type, passing, class_index))
         self.assertFalse(class_match(ml_type, failing, class_index))
 
+    def test_is_tif(self):
+        """Test identifying tif or vrt files as tif"""
+        img_dir = op.join('test', 'fixtures')
+
+        # tif with .tif extension identified as tif
+        test_tif = op.join(img_dir, 'drone.tif')
+        self.assertTrue(is_tif(test_tif))
+
+        # vrt with .vrt extension identified as tif
+        test_vrt = op.join(img_dir, 'drone.vrt')
+        self.assertTrue(is_tif(test_vrt))
+
+
+        # tif with no extension identified as tif
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            test_tif_no_ext = op.join(tmpdirname, 'drone')
+            shutil.copy(test_tif, test_tif_no_ext)
+            self.assertTrue(is_tif(test_tif_no_ext))
+
+        # vrt with no extension identified as tif
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            test_vrt_no_ext = op.join(tmpdirname, 'drone')
+            shutil.copy(test_vrt, test_vrt_no_ext)
+            self.assertTrue(is_tif(test_vrt_no_ext))
+
+
+
     def test_get_tile_tif(self):
         """Test reading of tile from geotiff"""
         tile = '1087767-1046604-21'