Cmr latest version

pyQuARC/main.py

@@ -138,6 +138,39 @@ def _cmr_query(self):
             query = f"{orig_query}&page_num={page_num}"
 
         return concept_ids
+
+
+    def _get_collection_version(self, concept_id):
+        """
+        Fetches collection information from CMR for a given concept_id.
+        Args:
+            concept_id (str): The concept ID to query.
+            info_type (str): Type of information to fetch.
+                        Options: "revision" or "metadata_version".
+
+        Returns:
+            str: The requested info (revision ID or MetadataSpecification.Version), or None if not found.
+        """
+        try:
+            url = f"{self.cmr_host}/search/concepts/{concept_id}.umm_json"
+            headers = get_headers()
+            response = requests.get(url, headers=headers)
+
+            if response.status_code != 200:
+                print(f"Warning: Could not fetch data for {concept_id}. Status: {response.status_code}")
+                return {"revision_id": None, "metadata_version": None}
+
+            data = response.json() if response.content else {}
+            return {
+                "revision_id": response.headers.get("CMR-Revision-Id"),
+                "metadata_version": data.get("MetadataSpecification", {}).get("Version"),
+            }
+
+        except Exception as e:
+            # Unified error handling — return dict even on failure
+            print(f"Error fetching collection info for {concept_id}: {str(e)}")
+            return {"revision_id": None, "metadata_version": None}
+
 
     def _validate_with_cmr(self, concept_id, metadata_content):
         """
@@ -181,8 +214,19 @@ def validate(self):
 
         if self.concept_ids:
             for concept_id in tqdm(self.concept_ids):
+                # If no version specified, get the latest version
+                # Get both revision and metadata version in one call
+                info = self._get_collection_version(concept_id)
+                version_to_use = self.version or info["revision_id"]
+                metadata_version = info["metadata_version"]
+
+                if version_to_use:
+                    print(f"Using latest revision {version_to_use} for {concept_id}")
+                if metadata_version:
+                    print(f"Collection {concept_id} schema version: {metadata_version}")
+
                 downloader = Downloader(
-                    concept_id, self.metadata_format, self.version, self.cmr_host
+                    concept_id, self.metadata_format, version_to_use, self.cmr_host
                 )
                 if not (content := downloader.download()):
                     self.errors.append(
@@ -193,18 +237,13 @@ def validate(self):
                         }
                     )
                     continue
+
                 content = content.encode()
-                cmr_response = self._validate_with_cmr(concept_id, content)
                 validation_errors, pyquarc_errors = checker.run(content)
                 self.errors.append(
                     {
                         "concept_id": concept_id,
                         "errors": validation_errors,
-                        "cmr_validation": {
-                            "errors": cmr_response.json().get("errors", []),
-                            # TODO: show warnings
-                            "warnings": cmr_response.json().get("warnings", [])
-                        },
                         "pyquarc_errors": pyquarc_errors,
                     }
                 )
@@ -220,8 +259,10 @@ def validate(self):
                         "pyquarc_errors": pyquarc_errors,
                     }
                 )
+
         return self.errors
 
+
     @staticmethod
     def _error_message(messages):
         severities = ["error", "warning", "info"]
@@ -287,7 +328,10 @@ def display_results(self):
                     f"\n\t {COLOR['title']}{COLOR['bright']} pyQuARC ERRORS: {END}\n"
                 )
                 for error in pyquarc_errors:
-                    error_prompt += f"\t\t  ERROR: {error['type']}. Details: {error['details']} \n"
+                    error_prompt += (
+                        f"\t\t  ERROR: {error.get('message', 'No message available')} \n"
+                        f"\t\t  DETAILS: {error.get('details', 'No details available')} \n"
+                    )
 
             if cmr_validation := error.get("cmr_validation"):
                 cmr_error_msg = self._format_cmr_error(cmr_validation)
@@ -388,3 +432,4 @@ def display_results(self):
     )
     results = arc.validate()
     arc.display_results()
+

requirements.txt

@@ -1,7 +1,7 @@
 colorama==0.4.4
 idna==2.10
 jsonschema==4.17.3
-lxml==4.9.1
+lxml==5.3.0 #4.9.1
 pytest==5.4.3
 pytz==2020.1
 requests==2.24.0