Entrytitle - Revised #325

Author: lavanya3k

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
 
@@ -91,7 +91,8 @@ 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
+            schema, 
+            format_checker=Draft7Validator.FORMAT_CHECKER, resolver=resolver
         )
 
         for error in sorted(
@@ -136,13 +137,13 @@ 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,

pyQuARC/code/string_validator.py

@@ -1,7 +1,7 @@
 from .base_validator import BaseValidator
 from .gcmd_validator import GcmdValidator
 from .utils import cmr_request, collection_in_cmr, if_arg, set_cmr_prms
-
+import re
 
 class StringValidator(BaseValidator):
     """
@@ -38,15 +38,21 @@ def length_check(string, extent, relation):
     def compare(first, second, relation):
         """
         Compares two strings based on the relationship
-
         Returns:
-            (dict) An object with the validity of the check and the instance
+           (dict) An object with the validity of the check and the instance
         """
+  
+        # Check if 'first' and 'second' contain any special characters
+        first_clean = re.sub(r'[^a-zA-Z0-9]', '', first).upper()
+        second_clean = re.sub(r'[^a-zA-Z0-9]', '', second).upper()
+  
+        # If either string contains special characters, return a warning or handle as needed
         return {
-            "valid": BaseValidator.compare(first.upper(), second.upper(), relation),
+            "valid": BaseValidator.compare(first_clean, second_clean, relation),
             "value": (first, second),
         }
 
+
     @staticmethod
     @if_arg
     def controlled_keywords_check(value, keywords_list):

pyQuARC/schemas/check_messages_override.json

@@ -1 +1,11 @@
-{}
+{
+    "shortname_uniqueness": {
+        "failure": "The EntryTitle/DataSetId `{}` is identical to the ShortName `{}`.",
+        "help": {
+            "message": "",
+            "url": "https://wiki.earthdata.nasa.gov/display/CMR/Entry+Title"
+        },
+        "remediation": "Recommend providing a more descriptive title for the dataset. "
+    }
+}
+

tests/test_downloader.py

@@ -9,11 +9,11 @@ class TestDownloader:
     def setup_method(self):
         self.concept_ids = {
             "collection": {
-                "real": "C1339230297-GES_DISC",
+                "real": "C1000000042-CDDIS",
                 "dummy": "C123456-LPDAAC_ECS",
             },
             "granule": {
-                "real": "G1370895082-GES_DISC",
+                "real": "G1018577631-CDDIS",
                 "dummy": "G1000000002-CMR_PROV",
             },
             "invalid": "asdfasdf",