Improved description handling

Author: tmorrell

caltechdata_api/caltechdata_edit.py

@@ -124,14 +124,22 @@ def caltechdata_edit(
     # Check if file links were provided in the metadata
     descriptions = []
     ex_file_links = []
+    ex_file_descriptions = []
     if "descriptions" in metadata:
         for d in metadata["descriptions"]:
             if d["description"].startswith("Files available via S3"):
                 file_text = d["description"]
                 file_list = file_text.split('href="')
+                # Check if we have file_descriptions
+                split_comma = file_list[0].split(", ")
+                if len(split_comma) == 3:
+                    ex_file_descriptions.append(split_comma[1])
                 # Loop over links in description, skip header text
                 for file in file_list[1:]:
                     ex_file_links.append(file.split('"\n')[0])
+                    split_comma = file.split(", ")
+                    if len(split_comma) == 3:
+                        ex_file_descriptions.append(split_comma[1])
             else:
                 descriptions.append(d)
         # We remove file link descriptions, and re-add below
@@ -145,7 +153,7 @@ def caltechdata_edit(
     # Otherwise we add file links found in the mtadata file
     elif ex_file_links:
         metadata = add_file_links(
-            metadata, ex_file_links, file_descriptions, s3_link=s3_link
+            metadata, ex_file_links, ex_file_descriptions, s3_link=s3_link
         )
 
     if authors == False:

caltechdata_api/caltechdata_write.py

@@ -81,7 +81,11 @@ def add_file_links(
         size = s3.info(path)["size"]
         size = humanbytes(size)
         try:
-            desc = file_descriptions[index] + ","
+            description = file_descriptions[index]
+            if description != " ":
+                desc = description + ","
+            else:
+                desc = ""
         except IndexError:
             desc = ""
         if link_string == "":

caltechdata_api/get_metadata.py

@@ -31,10 +31,12 @@ def get_metadata(
             url = "https://data.caltechlibrary.dev/api/records/"
         verify = True
 
+    base_headers = {
+        "accept": "application/json",
+    }
+
     if authors:
-        headers = {
-            "accept": "application/json",
-        }
+        headers = base_headers
         validate = False
     else:
         headers = {
@@ -49,7 +51,25 @@ def get_metadata(
         raise Exception(response.text)
     else:
         metadata = response.json()
-
+        if not authors:
+            response = requests.get(url + idv, headers=base_headers, verify=verify)
+            if response.status_code != 200:
+                raise Exception(response.text)
+            else:
+                instance = response.json()
+                base_metadata = instance["metadata"]
+                metadata["descriptions"][0]["description"] = base_metadata.get(
+                    "description"
+                )
+                additional_descriptions = base_metadata.get(
+                    "additional_descriptions", []
+                )
+                count = 1
+                for desc in additional_descriptions:
+                    metadata["descriptions"][count]["description"] = desc["description"]
+                    count += 1
+            if "formats" in metadata:
+                metadata["formats"] = list(set(metadata["formats"]))
         if validate:
             if schema == "43":
                 try: