fix: handle percent-encoded urls TDE-1054 (#881)

* fix: handle percent-encoded urls TDE-1054

* fix: typo

scripts/files/file_tiff.py

@@ -1,6 +1,7 @@
 import json
 from enum import Enum
 from typing import Any, Dict, List, Optional
+from urllib.parse import unquote
 
 from scripts.gdal.gdal_helper import GDALExecutionException, gdal_info, run_gdal
 from scripts.gdal.gdalinfo import GdalInfo
@@ -24,10 +25,17 @@ class FileTiff:
 
     def __init__(
         self,
-        path: List[str],
+        paths: List[str],
         preset: Optional[str] = None,
     ) -> None:
-        self._path_original = path
+        paths_original = []
+        for p in paths:
+            # paths can be URL containing percent-encoded (like `%20` for space) sequences
+            # which would make the process fail later TDE-1054
+            # FIXME: we should use URLs in the code base
+            paths_original.append(unquote(p))
+
+        self._paths_original = paths_original
         self._path_standardised = ""
         self._errors: List[Dict[str, Any]] = []
         self._gdalinfo: Optional[GdalInfo] = None
@@ -138,14 +146,14 @@ def get_errors(self) -> List[Dict[str, Any]]:
         """
         return self._errors
 
-    def get_path_original(self) -> List[str]:
+    def get_paths_original(self) -> List[str]:
         """Get the path(es) of the original (non standardised) file.
         It can be a list of path if the standardised file is a retiled image.
 
         Returns:
             a list of file path
         """
-        return self._path_original
+        return self._paths_original
 
     def get_path_standardised(self) -> str:
         """Get the path of the standardised file.

scripts/standardise_validate.py

@@ -77,7 +77,7 @@ def main() -> None:
                 # If the file is not valid (Non Visual QA errors)
                 # Logs the `vsis3` path to use `gdal` on the file directly from `s3`
                 # This is to help data analysts to verify the file.
-                original_path: List[str] = file.get_path_original()
+                original_path: List[str] = file.get_paths_original()
                 standardised_path = file.get_path_standardised()
                 env_argo_template = os.environ.get("ARGO_TEMPLATE")
                 if env_argo_template:

scripts/standardising.py

@@ -139,9 +139,9 @@ def standardising(
         footprint_tmp_path = os.path.join(tmp_path, footprint_file_name)
         sidecars: List[str] = []
         for extension in [".prj", ".tfw"]:
-            for file_input in files.inputs:
+            for file_input in tiff.get_paths_original():
                 sidecars.append(f"{os.path.splitext(file_input)[0]}{extension}")
-        source_files = write_all(files.inputs, f"{tmp_path}/source/")
+        source_files = write_all(tiff.get_paths_original(), f"{tmp_path}/source/")
         write_sidecars(sidecars, f"{tmp_path}/source/")
 
         source_tiffs = [file for file in source_files if is_tiff(file)]