Multilingual ingest

multilingual_tests/create_content.csv

@@ -0,0 +1,4 @@
+file,id,title,field_subject,field_model
+,01,Ancient Architecture,Architecture,Collection
+,02,Photography Collection,Photography,Collection
+,03,Literary Manuscripts,Literature,Collection

multilingual_tests/create_content.yml

@@ -0,0 +1,11 @@
+task: create
+host: https://islandora.dev
+username: admin
+password: password
+input_csv: multilingual_tests/create_content.csv
+input_dir: ""
+content_type: islandora_object
+media_type: image
+allow_missing_files: true
+allow_adding_terms: true
+secure_ssl_only: false

multilingual_tests/create_taxonomy.csv

@@ -0,0 +1,4 @@
+term_name
+"History"
+"Photography"
+"Architecture"

multilingual_tests/create_taxonomy.yml

@@ -0,0 +1,9 @@
+task: create_terms
+host: https://islandora.dev
+username: admin
+password: password
+input_csv: multilingual_tests/create_taxonomy.csv
+input_dir: ""
+vocabulary: subject
+vocab_id: subject
+secure_ssl_only: false

multilingual_tests/translate_content.csv

@@ -0,0 +1,7 @@
+node_id,title,field_subject,langcode
+109,古代建筑,Architecture,zh-hant
+109,Architettura Antica,Architecture,it
+110,摄影收藏,Photography,zh-hant
+110,Collezione Fotografica,Photography,it
+111,文学手稿,Literature,zh-hant
+111,Manoscritti Letterari,Literature,it

multilingual_tests/translate_content.yml

@@ -0,0 +1,10 @@
+task: update
+host: https://islandora.dev
+username: admin
+password: password
+input_csv: multilingual_tests/translate_content.csv
+input_dir: ""
+content_type: islandora_object
+media_type: image
+allow_missing_files: true
+secure_ssl_only: false

multilingual_tests/translate_terms.csv

@@ -0,0 +1,7 @@
+term_id,term_name,description,langcode
+960,历史,中文历史描述,zh-hant
+960,Storia,Descrizione italiana per Storia,it
+958,摄影,中文摄影描述,zh-hant
+958,Fotografia,Descrizione italiana per Fotografia,it
+957,建筑学,中文建筑学描述,zh-hant
+957,Architettura,Descrizione italiana per Architettura,it

multilingual_tests/translate_terms.yml

@@ -0,0 +1,11 @@
+task: update_terms
+host: https://islandora.dev
+username: admin
+password: password
+input_csv: multilingual_tests/translate_terms.csv
+input_dir: ""
+vocabulary: subject
+vocab_id: subject
+secure_ssl_only: false
+log_request_url: true
+log_response_status_code: true

workbench

@@ -822,9 +822,11 @@ def update():
         if node_has_all_fields is True:
             if value_is_numeric(row["node_id"]) is False:
                 row["node_id"] = get_nid_from_url_alias(config, row["node_id"])
-            node_endpoint = (
-                config["host"] + "/node/" + str(row["node_id"]) + "?_format=json"
-            )
+
+            # Build language-specific endpoint if langcode is specified
+            langcode = row.get("langcode", "").strip() if "langcode" in row else None
+            language_prefix = f"/{langcode}" if langcode else ""
+            node_endpoint = f"{config['host']}{language_prefix}/node/{row['node_id']}?_format=json"
             node_headers = {"Content-Type": "application/json"}
             # Make a GET request to the content type
             content_type_endpoint = f"{config['host']}/entity/node_type/{config['content_type']}?_format=json"
@@ -912,6 +914,8 @@ def update():
                 create_url_alias(config, row["node_id"], row["url_alias"])
 
 
+
+
 def delete():
     """Delete nodes."""
     message = '"Delete" task started using config file ' + args.config + "."
@@ -2873,6 +2877,10 @@ def update_terms():
             if len(row["published"].strip()) != 0:
                 term["status"] = [{"value": row["published"]}]
 
+        if "langcode" in csv_column_headers:
+            if len(row["langcode"]) > 0:
+                term["langcode"] = [{"value": row["langcode"]}]
+
         # Add custom (non-required) fields.
         required_fields = ["term_id"]
         custom_fields = list(set(csv_column_headers) - set(required_fields))
@@ -2885,6 +2893,7 @@ def update_terms():
                 "description",
                 "term_name",
                 "published",
+                "langcode",
             ]
             if (
                 custom_field not in json.loads(term_response.text)
@@ -2916,6 +2925,10 @@ def update_terms():
             if custom_field == "published":
                 continue
 
+            # 'langcode' is a core Drupal field, but is not considered a base field.
+            if custom_field == "langcode":
+                continue
+
             # Assemble Drupal field structures from CSV data. If new field types are added to
             # workbench_fields.py, they need to be registered in the following if/elif/else block.
 
@@ -2932,9 +2945,10 @@ def update_terms():
             )
 
         if term_has_all_fields is True:
-            term_endpoint = (
-                config["host"] + "/taxonomy/term/" + row["term_id"] + "?_format=json"
-            )
+            # Build language-specific endpoint if langcode is specified
+            langcode = row.get("langcode", "").strip() if "langcode" in row else None
+            language_prefix = f"/{langcode}" if langcode else ""
+            term_endpoint = f"{config['host']}{language_prefix}/taxonomy/term/{row['term_id']}?_format=json"
             term_headers = {"Content-Type": "application/json"}
             term_response = issue_request(
                 config, "PATCH", term_endpoint, term_headers, term

workbench_utils.py

@@ -58,6 +58,8 @@
 commented_out_input_csv_rows_present = False
 
 
+
+
 def set_media_type(config, filepath, file_fieldname, csv_row):
     """Using either the 'media_type' or 'media_types_override' configuration
     setting, determine which media bundle type to use.
@@ -6635,7 +6637,12 @@ def get_csv_data(config, csv_file_target="node_fields", file_path=None):
                     row["node_id"] = get_nid_from_url_alias(config, row["node_id"])
 
                 try:
-                    unique_identifiers.append(row[config["id_field"]])
+                    # If langcode is present, create composite key to allow same entity ID with different langcodes
+                    if "langcode" in row and row["langcode"].strip():
+                        identifier_key = f"{row[config['id_field']]}|{row['langcode']}"
+                    else:
+                        identifier_key = row[config["id_field"]]
+                    unique_identifiers.append(identifier_key)
 
                     if (
                         "csv_value_templates" in config