#324 update schema validator and text_downloader

Author: bhawana11

pyQuARC/code/schema_validator.py

@@ -3,7 +3,7 @@
 import re
 
 from io import BytesIO
-from jsonschema import Draft7Validator, draft7_format_checker, RefResolver
+from jsonschema import Draft7Validator, RefResolver 
 from lxml import etree
 from urllib.request import pathname2url
 
@@ -90,9 +90,7 @@ def run_json_validator(self, content_to_validate):
 
         resolver = RefResolver.from_schema(schema, store=schema_store)
 
-        validator = Draft7Validator(
-            schema, format_checker=draft7_format_checker, resolver=resolver
-        )
+        validator = Draft7Validator(schema, format_checker=Draft7Validator.FORMAT_CHECKER)
 
         for error in sorted(
             validator.iter_errors(json.loads(content_to_validate)), key=str
@@ -136,13 +134,13 @@ def _build_errors(error_log, paths):
             # For DIF, because the namespace is specified in the metadata file, lxml library
             # provides field name concatenated with the namespace,
             # the following 3 lines of code removes the namespace
-            namespaces = re.findall("(\{http[^}]*\})", line)
+            namespaces = re.findall(r"(\{http[^}]*\})", line)
             for namespace in namespaces:
                 line = line.replace(namespace, "")
-            field_name = re.search("Element\s'(.*)':", line)[1]
+            field_name = re.search(r"Element\s'(.*)':", line)[1]
             field_paths = [abs_path for abs_path in paths if field_name in abs_path]
             field_name = field_paths[0] if len(field_paths) == 1 else field_name
-            message = re.search("Element\s'.+':\s(\[.*\])?(.*)", line)[2].strip()
+            message = re.search(r"Element\s'.+':\s(\[.*\])?(.*)", line)[2].strip()
             errors.setdefault(field_name, {})["schema"] = {
                 "message": [f"Error: {message}"],
                 "valid": False,

tests/test_downloader.py

@@ -9,11 +9,11 @@ class TestDownloader:
     def setup_method(self):
         self.concept_ids = {
             "collection": {
-                "real": "C1339230297-GES_DISC",
+                "real": "C1000000010-CDDIS",
                 "dummy": "C123456-LPDAAC_ECS",
             },
             "granule": {
-                "real": "G1370895082-GES_DISC",
+                "real": "G1001434969-CDDIS",
                 "dummy": "G1000000002-CMR_PROV",
             },
             "invalid": "asdfasdf",