Include 90 parenthesized DEM files in catalog

data/stac_geotiff_checks.csv

@@ -60323,3 +60323,4 @@ https://nrs.objectstore.gov.bc.ca/gdwuts/albers10k2m/_completed_dem/dem_104_045.
 https://nrs.objectstore.gov.bc.ca/gdwuts/albers10k2m/_completed_dem/dem_127_052.tif,True,False
 https://nrs.objectstore.gov.bc.ca/gdwuts/albers10k2m/_completed_dem/dem_062_089.tif,True,False
 https://nrs.objectstore.gov.bc.ca/gdwuts/albers10k2m/_completed_dem/dem_126_052.tif,True,False
+https:/nrs.objectstore.gov.bc.ca/gdwuts/082/082e/2018/dem/bc_082e003_xli1m_utm11_2018 (2).tif,True,True

scripts/item_create.py

@@ -31,6 +31,7 @@
     check_geotiff_cog,
     date_extract_from_path,
     datetime_parse_item,
+    encode_url_for_gdal,
     fix_url,
     get_output_dir,
     url_to_item_id,
@@ -80,8 +81,10 @@ def process_item(path_item: str, collection_id: str, path_local: str,
     )
 
     try:
+        # Encode for GDAL/vsicurl (spaces → %20), but keep original for asset href
+        gdal_path = encode_url_for_gdal(path_item)
         item = rio_stac.stac.create_stac_item(
-            path_item,
+            gdal_path,
             id=item_id,
             asset_media_type=media_type,
             asset_name='image',

scripts/item_reprocess.py

@@ -23,6 +23,7 @@
 from stac_utils import (
     date_extract_from_path,
     datetime_parse_item,
+    encode_url_for_gdal,
     fix_url,
     url_to_item_id,
     get_output_dir,
@@ -73,8 +74,9 @@ def process_item(path_item: str, collection, results_lookup) -> dict | None:
     )
 
     try:
+        gdal_path = encode_url_for_gdal(path_item)
         item = rio_stac.stac.create_stac_item(
-            path_item,
+            gdal_path,
             id=item_id,
             asset_media_type=media_type,
             asset_name='image',

scripts/stac_utils.py

@@ -93,8 +93,9 @@ def check_geotiff_cog(url: str) -> dict:
     Returns dict with url, is_geotiff (readable), and is_cog (cloud-optimized).
     """
     try:
+        gdal_url = encode_url_for_gdal(url)
         result = subprocess.run(
-            ["rio", "cogeo", "validate", f"/vsicurl/{url}"],
+            ["rio", "cogeo", "validate", f"/vsicurl/{gdal_url}"],
             stdout=subprocess.PIPE,
             stderr=subprocess.PIPE,
             check=False
@@ -144,6 +145,14 @@ def fix_url(url: str) -> str:
     return url
 
 
+def encode_url_for_gdal(url: str) -> str:
+    """Encode URL for use with /vsicurl/ (GDAL virtual filesystem).
+
+    Spaces in filenames cause CURL errors with /vsicurl/. URL-encode them.
+    """
+    return url.replace(" ", "%20")
+
+
 def url_to_item_id(url: str) -> str:
     """Convert a GeoTIFF URL to a STAC item ID."""
     return url[len(PATH_S3):].lstrip("/").replace("/", "-").removesuffix(".tif")

scripts/urls_fetch.R

@@ -29,10 +29,6 @@ if (test_only && file.exists("data/urls_list.txt")) {
     pattern = c("dem", "*.tif")
   )
 
-  # Remove paths with ( in them (all fail validation - see issue #8)
-  keys_clean <- keys[!stringr::str_detect(keys, "\\(")]
-
-  readr::write_lines(keys_clean, "data/urls_list.txt")
-  cat(sprintf("Fetched and saved %d URLs (excluded %d with parentheses)\n",
-              length(keys_clean), length(keys) - length(keys_clean)))
+  readr::write_lines(keys, "data/urls_list.txt")
+  cat(sprintf("Fetched and saved %d URLs\n", length(keys)))
 }