capturing identifier from header for dublincore parser

adsingestp/parsers/dubcore.py

@@ -53,6 +53,12 @@ def _parse_ids(self):
         self.base_metadata["ids"] = {}
         self.base_metadata["ids"]["pub-id"] = []
 
+        if self.input_header.find("identifier"):
+            for dc_id in self.input_header.find_all("identifier"):
+                self.base_metadata["ids"]["pub-id"].append(
+                    {"attribute": "publisher-id", "Identifier": dc_id.get_text()}
+                )
+
         if self.input_metadata.find("dc:identifier"):
             for dc_id in self.input_metadata.find_all("dc:identifier"):
                 self.base_metadata["ids"]["pub-id"].append(

tests/stubdata/output/arxiv_0901_2443.json

@@ -85,6 +85,10 @@
     "pubYear": "2009"
   },
   "publisherIDs": [
+    {
+      "Identifier": "oai:arXiv.org:0901.2443",
+      "attribute": "publisher-id"
+    },
     {
       "Identifier": "http://arxiv.org/abs/0901.2443",
       "attribute": "publisher-id"

tests/stubdata/output/arxiv_1711_04702.json

@@ -57,6 +57,10 @@
     "pubYear": "2017"
   },
   "publisherIDs": [
+    {
+      "Identifier": "oai:arXiv.org:1711.04702",
+      "attribute": "publisher-id"
+    },
     {
       "Identifier": "http://arxiv.org/abs/1711.04702",
       "attribute": "publisher-id"

tests/stubdata/output/arxiv_1711_05739.json

@@ -42,6 +42,10 @@
     "pubYear": "2017"
   },
   "publisherIDs": [
+    {
+      "Identifier": "oai:arXiv.org:1711.05739",
+      "attribute": "publisher-id"
+    },
     {
       "Identifier": "http://arxiv.org/abs/1711.05739",
       "attribute": "publisher-id"

tests/stubdata/output/arxiv_math_0306266.json

@@ -26,6 +26,10 @@
     "pubYear": "2003"
   },
   "publisherIDs": [
+    {
+      "Identifier": "oai:arXiv.org:math/0306266",
+      "attribute": "publisher-id"
+    },
     {
       "Identifier": "http://arxiv.org/abs/math/0306266",
       "attribute": "publisher-id"

tests/stubdata/output/dubcore_pos_ecrs_002.json

@@ -24,6 +24,10 @@
     "publisher": "Sissa Medialab"
   },
   "publisherIDs": [
+    {
+      "Identifier": "oai:pos.sissa.it:ECRS/002",
+      "attribute": "publisher-id"
+    },
     {
       "Identifier": "PoS(ECRS)002",
       "attribute": "publisher-id"

tests/test_dublincore.py

@@ -32,12 +32,12 @@ def test_dubcore(self):
             with open(test_infile, "rb") as fp:
                 input_data = fp.read()
 
+            parsed = parser.parse(input_data)
+
             with open(test_outfile, "rb") as fp:
                 output_text = fp.read()
                 output_data = json.loads(output_text)
 
-            parsed = parser.parse(input_data)
-
             # make sure this is valid schema
             try:
                 ads_schema_validator().validate(parsed)
@@ -53,6 +53,7 @@ def test_dubcore(self):
             self.assertTrue(abs(time_difference) < datetime.timedelta(seconds=10))
             parsed["recordData"]["parsedTime"] = ""
 
+            self.maxDiff = None
             self.assertEqual(parsed, output_data)
 
 
@@ -77,11 +78,12 @@ def test_dubcore_multi(self):
             with open(test_infile, "r") as fp:
                 input_data = fp.read()
 
+            parsed = parser.parse(input_data, header=True)
+
             with open(test_outfile_header, "r") as fp:
                 output_text = fp.read()
                 output_data_header = output_text.strip().split("\n\n")
 
-            parsed = parser.parse(input_data, header=True)
             self.assertEqual(parsed, output_data_header)
 
             with open(test_outfile_noheader, "r") as fp: