fix jimi formatter for pictures with multiple caption writers (#185)

SDCP-715
superdesk · Sep 21, 2023 · 6ecfbae · 6ecfbae
1 parent 59b4a84
commit 6ecfbae
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 7 deletions.
diff --git a/server/cp/output/formatter/jimi.py b/server/cp/output/formatter/jimi.py
@@ -7,6 +7,7 @@
 import cp.ingest.parser.globenewswire as globenewswire
 import superdesk.etree as sd_etree
 
+from typing import List, Union
 from num2words import num2words
 from collections import OrderedDict
 from celery.utils.functional import uniq
@@ -105,6 +106,12 @@ def is_french(item) -> bool:
     return "fr" in item.get("language", "en")
 
 
+def text_value(value: Union[str, List[str]]) -> str:
+    if not isinstance(value, list):
+        value = [value]
+    return ", ".join(value)
+
+
 class JimiFormatter(Formatter):
 
     ENCODING = "utf-8"
@@ -513,12 +520,12 @@ def _format_picture_metadata(self, content, item):
             content.find("Source").text = item["original_source"]
 
         if extra.get(cp.ARCHIVE_SOURCE):
-            etree.SubElement(content, "ArchiveSources").text = extra[cp.ARCHIVE_SOURCE]
+            etree.SubElement(content, "ArchiveSources").text = text_value(extra[cp.ARCHIVE_SOURCE])
 
         if extra.get(cp.PHOTOGRAPHER_CODE):
-            etree.SubElement(content, "BylineTitle").text = extra[
+            etree.SubElement(content, "BylineTitle").text = text_value(extra[
                 cp.PHOTOGRAPHER_CODE
-            ].upper()
+            ]).upper()
 
         if item.get("copyrightnotice"):
             etree.SubElement(content, "Copyright").text = item["copyrightnotice"][:50]
@@ -529,7 +536,7 @@ def _format_picture_metadata(self, content, item):
             ].replace("  ", " ")
 
         if extra.get(cp.CAPTION_WRITER):
-            etree.SubElement(content, "CaptionWriter").text = extra[cp.CAPTION_WRITER]
+            etree.SubElement(content, "CaptionWriter").text = text_value(extra[cp.CAPTION_WRITER])
 
         if item.get("ednote"):
             etree.SubElement(content, "SpecialInstructions").text = item["ednote"]
@@ -543,13 +550,13 @@ def _format_picture_metadata(self, content, item):
             ).text
 
         if extra.get(cp.INFOSOURCE):
-            etree.SubElement(content, "CustomField6").text = extra[cp.INFOSOURCE]
+            etree.SubElement(content, "CustomField6").text = text_value(extra[cp.INFOSOURCE])
 
         if extra.get(cp.XMP_KEYWORDS):
-            etree.SubElement(content, "XmpKeywords").text = extra[cp.XMP_KEYWORDS]
+            etree.SubElement(content, "XmpKeywords").text = text_value(extra[cp.XMP_KEYWORDS])
 
         if extra.get("container"):
-            etree.SubElement(content, "ContainerIDs").text = extra["container"]
+            etree.SubElement(content, "ContainerIDs").text = text_value(extra["container"])
         else:
             self._format_refs(content, item)
 

diff --git a/server/tests/output/formatter/jimi_test.py b/server/tests/output/formatter/jimi_test.py
@@ -248,6 +248,7 @@ def test_picture(self):
             "extra": {
                 cp.FILENAME: "NY538",
                 "photographer_code": "stf",
+                cp.CAPTION_WRITER: ["foo", "bar"],
             },
             "subject": [
                 {"name": "Americas", "qcode": "A", "scheme": "photo_categories"},
@@ -287,6 +288,7 @@ def test_picture(self):
         self.assertEqual(updates["copyrightnotice"][:50], item.find("Copyright").text)
         self.assertEqual(updates["description_text"], item.find("EnglishCaption").text)
         self.assertEqual("2020-06-03T17:00:56", item.find("DateTaken").text)
+        self.assertEqual("foo, bar", item.find("CaptionWriter").text)
 
         self.assertEqual("media_id", item.find("FileName").text)
         self.assertEqual("media_id.jpg", item.find("ViewFile").text)