unescape organization names from erddap

Fixes #398
HakaiInstitute · Mar 24, 2023 · edde7cc · edde7cc
1 parent 275c065
commit edde7cc
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 2 deletions.
diff --git a/harvester/cde_harvester/__main__.py b/harvester/cde_harvester/__main__.py
@@ -8,7 +8,11 @@
 import queue
 import numpy as np
 import pandas as pd
-from cde_harvester.ckan.create_ckan_erddap_link import get_ckan_records, unescape_ascii
+from cde_harvester.ckan.create_ckan_erddap_link import (
+    get_ckan_records,
+    unescape_ascii,
+    unescape_ascii_list,
+)
 from cde_harvester.harvest_erddap import harvest_erddap
 from cde_harvester.utils import (
     cf_standard_names,
@@ -134,7 +138,8 @@ def worker():
 
     # prioritize with organizations from CKAN and then pull ERDDAP if needed
     datasets["organizations"] = datasets.apply(
-        lambda x: x["ckan_organizations"] or x["organizations"], axis=1
+        lambda x: x["ckan_organizations"] or unescape_ascii_list(x["organizations"]),
+        axis=1,
     )
     del datasets["title"]
     # del datasets["summary"]

diff --git a/harvester/cde_harvester/ckan/create_ckan_erddap_link.py b/harvester/cde_harvester/ckan/create_ckan_erddap_link.py
@@ -21,6 +21,8 @@ def split_erddap_url(url):
     dataset_id = f.split(".html")[0]
     return (erddap_host, dataset_id)
 
+def unescape_ascii_list(l):
+    return  [unescape_ascii(x) for x in l]
 
 def unescape_ascii(x):
     try: