From 4c2ca53303a949c00707e0c552489930f059a54a Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Mon, 23 Dec 2019 14:00:59 -0800
Subject: add regression test for medlinedate -> year parsing

---
 python/tests/files/pubmed_31393839.xml | 95 ++++++++++++++++++++++++++++++++++
 python/tests/import_pubmed.py          |  7 +++
 2 files changed, 102 insertions(+)
 create mode 100644 python/tests/files/pubmed_31393839.xml

(limited to 'python')

diff --git a/python/tests/files/pubmed_31393839.xml b/python/tests/files/pubmed_31393839.xml
new file mode 100644
index 00000000..644a02ec
--- /dev/null
+++ b/python/tests/files/pubmed_31393839.xml
@@ -0,0 +1,95 @@
+<PubmedArticle>
+    <MedlineCitation Status="MEDLINE" IndexingMethod="Automated" Owner="NLM">
+        <PMID Version="1">31393839</PMID>
+        <DateCompleted>
+            <Year>2019</Year>
+            <Month>12</Month>
+            <Day>17</Day>
+        </DateCompleted>
+        <DateRevised>
+            <Year>2019</Year>
+            <Month>12</Month>
+            <Day>17</Day>
+        </DateRevised>
+        <Article PubModel="Print">
+            <Journal>
+                <ISSN IssnType="Print">0022-3875</ISSN>
+                <JournalIssue CitedMedium="Print">
+                    <Volume>53</Volume>
+                    <Issue>6</Issue>
+                    <PubDate>
+                        <MedlineDate>2019</MedlineDate>
+                    </PubDate>
+                </JournalIssue>
+                <Title>Journal of clinical orthodontics : JCO</Title>
+                <ISOAbbreviation>J Clin Orthod</ISOAbbreviation>
+            </Journal>
+            <ArticleTitle>Career-Turning Moments.</ArticleTitle>
+            <Pagination>
+                <MedlinePgn>325</MedlinePgn>
+            </Pagination>
+            <AuthorList CompleteYN="Y">
+                <Author ValidYN="Y">
+                    <LastName>Keim</LastName>
+                    <ForeName>Robert G</ForeName>
+                    <Initials>RG</Initials>
+                    <AffiliationInfo>
+                        <Affiliation>J Clin Orthod, Greenwood Village, CO.</Affiliation>
+                    </AffiliationInfo>
+                </Author>
+            </AuthorList>
+            <Language>eng</Language>
+            <PublicationTypeList>
+                <PublicationType UI="D016428">Journal Article</PublicationType>
+            </PublicationTypeList>
+        </Article>
+        <MedlineJournalInfo>
+            <Country>United States</Country>
+            <MedlineTA>J Clin Orthod</MedlineTA>
+            <NlmUniqueID>0243471</NlmUniqueID>
+            <ISSNLinking>0022-3875</ISSNLinking>
+        </MedlineJournalInfo>
+        <CitationSubset>D</CitationSubset>
+        <MeshHeadingList>
+            <MeshHeading>
+                <DescriptorName UI="D001696" MajorTopicYN="N">Biomechanical Phenomena</DescriptorName>
+            </MeshHeading>
+            <MeshHeading>
+                <DescriptorName UI="D002321" MajorTopicYN="Y">Career Choice</DescriptorName>
+            </MeshHeading>
+            <MeshHeading>
+                <DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName>
+            </MeshHeading>
+        </MeshHeadingList>
+    </MedlineCitation>
+    <PubmedData>
+        <History>
+            <PubMedPubDate PubStatus="entrez">
+                <Year>2019</Year>
+                <Month>8</Month>
+                <Day>9</Day>
+                <Hour>6</Hour>
+                <Minute>0</Minute>
+            </PubMedPubDate>
+            <PubMedPubDate PubStatus="pubmed">
+                <Year>2019</Year>
+                <Month>8</Month>
+                <Day>9</Day>
+                <Hour>6</Hour>
+                <Minute>0</Minute>
+            </PubMedPubDate>
+            <PubMedPubDate PubStatus="medline">
+                <Year>2019</Year>
+                <Month>12</Month>
+                <Day>18</Day>
+                <Hour>6</Hour>
+                <Minute>0</Minute>
+            </PubMedPubDate>
+        </History>
+        <PublicationStatus>ppublish</PublicationStatus>
+        <ArticleIdList>
+            <ArticleId IdType="pubmed">31393839</ArticleId>
+        </ArticleIdList>
+    </PubmedData>
+</PubmedArticle>
+
diff --git a/python/tests/import_pubmed.py b/python/tests/import_pubmed.py
index 0d551d02..49609f75 100644
--- a/python/tests/import_pubmed.py
+++ b/python/tests/import_pubmed.py
@@ -119,3 +119,10 @@ def test_pubmed_xml_parse(pubmed_importer):
     assert r2.refs[0].extra['unstructured'] == "Microbiology. 2009 Jun;155(Pt 6):1840-6"
     assert r2.refs[0].extra['pmid'] == "19383690"
 
+def test_pubmed_xml_dates(pubmed_importer):
+    with open('tests/files/pubmed_31393839.xml', 'r') as f:
+        soup = BeautifulSoup(f, "xml")
+        r1 = pubmed_importer.parse_record(soup.find_all("PubmedArticle")[0])
+
+    assert r1.release_year == 2019
+
-- 
cgit v1.2.3