Merge pull request #47 from seasidesparrow/orcid_issue.2023May16

Orcid issue.2023 may16

adsingestp/parsers/jats.py

@@ -161,13 +161,13 @@ def _match_xref_clean(self):
                 # note that the ingest schema allows a single email address,
                 # but we've extracted all here in case that changes to allow
                 #  more than one
-                if auth["email"]:
+                if auth.get("email", []):
                     auth["email"] = auth["email"][0]
                 else:
                     auth["email"] = ""
 
                 # same for orcid
-                if auth["orcid"]:
+                if auth.get("orcid", []):
                     auth["orcid"] = auth["orcid"][0]
                 else:
                     auth["orcid"] = ""
@@ -180,7 +180,7 @@ def parse(self, article_metadata):
         """
         article_metadata = self._decompose(soup=article_metadata, tag="label")
 
-        art_contrib_groups = None
+        art_contrib_groups = []
         if article_metadata.find("contrib-group"):
             art_contrib_groups = article_metadata.find_all("contrib-group")
 
@@ -773,7 +773,7 @@ def _parse_ids(self):
             x_name = self._detag(ax.find("meta-name"), [])
             x_value = self._detag(ax.find("meta-value"), [])
             if x_name and x_name == "arxivppt":
-                self.base_metadata["ids"]["preprint"].append({"source": "arxiv", "id": x_value})
+                self.base_metadata["ids"]["preprint"] = {"source": "arxiv", "id": x_value}
 
     def _parse_pubdate(self):
         pub_dates = self.article_meta.find_all("pub-date")

tests/stubdata/input/jats_iop_no_contribs.xml

@@ -0,0 +1,26 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.1 20151215//EN" "JATS-journalpublishing1.dtd">
+<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="rapid-communication" dtd-version="1.1" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">epl</journal-id><journal-id journal-id-type="coden">EULEEJ</journal-id><journal-title-group><journal-title xml:lang="en">Europhysics Letters</journal-title><abbrev-journal-title abbrev-type="IOP" xml:lang="en">EPL</abbrev-journal-title><abbrev-journal-title abbrev-type="publisher" xml:lang="en">EPL</abbrev-journal-title></journal-title-group><issn pub-type="ppub">0295-5075</issn><issn pub-type="epub">1286-4854</issn><publisher><publisher-name>EDP Sciences, IOP Publishing and Società Italiana di Fisica</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">epl23100304</article-id><article-id pub-id-type="doi">10.1209/0295-5075/acd024</article-id><article-id pub-id-type="manuscript">acd024</article-id><article-categories><subj-group subj-group-type="display-article-type"><subject>Editorial</subject></subj-group><subj-group subj-group-type="section"><subject>none</subject></subj-group></article-categories><title-group><article-title>Editorial —How to write a good letter for EPL</article-title></title-group><pub-date pub-type="ppub"><day>01</day><month>5</month><year>2023</year></pub-date><pub-date pub-type="epub"><day>2</day><month>5</month><year>2023</year></pub-date><volume>142</volume><issue>3</issue><elocation-id content-type="artnum">30000</elocation-id><history><date date-type="received"><day>25</day><month>4</month><year>2023</year></date><date date-type="accepted"><day>25</day><month>4</month><year>2023</year></date></history><permissions><copyright-statement>Copyright © EPLA, 2023</copyright-statement><copyright-year>2023</copyright-year><license license-type="iop-standard" xlink:href="https://publishingsupport.iopscience.iop.org/iop-standard/v1"><license-p>This article is available under the terms of the <ext-link ext-link-type="uri" xlink:href="https://publishingsupport.iopscience.iop.org/iop-standard/v1" xlink:type="simple">IOP-Standard License</ext-link>.</license-p></license></permissions><self-uri content-type="pdf" xlink:href="epl_142_3_30000.pdf" xlink:type="simple"/><counts><page-count count="2"/></counts><custom-meta-group><custom-meta xlink:type="simple"><meta-name>ccc</meta-name><meta-value/></custom-meta><custom-meta xlink:type="simple"><meta-name>printed</meta-name><meta-value>Printed in France</meta-value></custom-meta></custom-meta-group></article-meta></front><body><sec id="epl23100304s1"><title/><p>
+            <italic toggle="yes">EPL</italic> is owned by 17 Physics Societies and reinvests its profits in the Societies and the physics community at large. Our central vocation is to be useful to this community by publishing high-quality letters.</p><p>We would like to share with prospective <italic toggle="yes">EPL</italic> authors some tips on how to write impactful scientific letters. For more technical manuscript preparation guidelines, refer to <italic toggle="yes">EPL</italic>'s instructions for authors: <ext-link ext-link-type="uri" xlink:href="https://www.epletters.net/how-to-prepare-a-manuscript" xlink:type="simple">https://www.epletters.net/how-to-prepare-a-manuscript</ext-link>.</p><p>Authors may have different reasons to write a letter rather than a full-length article. Traditionally, a letter was meant to communicate urgent results, or announcing something briefly to be developed later. Modern publication processes such as e-only publication, and publishing accepted manuscripts ahead of publication, reduce this incentive. Authors may have selected <italic toggle="yes">EPL</italic> on the basis of metrics or other considerations, without paying enough attention to the letter format. This may result in cramped and unreadable manuscripts. Indeed, <italic toggle="yes">EPL</italic> strictly enforces a 7-page limit for letters.</p><p>So, why write a letter? We can make an analogy between letters/papers and short stories/novels. Both are useful schemes with different goals and features, but a short story (letter) should not necessarily lead to a novel (paper) later on. It should rather be meaningful <italic toggle="yes">per se</italic> and impact the reader with a concentrated intensity and high-quality content.</p><p>The following discussion is mostly about “formal” or “presentation” aspects.
+<list id="epl23100304l1" list-type="bullet"><list-item id="epl23100304l1.1"><label>–</label><p>
+                     <italic toggle="yes">Title</italic>. To make researchers outside of your immediate field want to read your letter, the title should be short, easy to read and catchy, sufficiently clear for a non-specialist. Several studies point to the fact that shorter titles attract more citations, the ideal length being under 12 words [<xref ref-type="bibr" rid="epl23100304bib1">1</xref>]. If possible, we recommend using “declarative” titles. These are titles that include a verb, and state the main findings or conclusions of the article. For example: “Sentiment contagion dilutes prisoner's dilemmas on social networks” [<xref ref-type="bibr" rid="epl23100304bib2">2</xref>].</p></list-item><list-item id="epl23100304l1.2"><label>–</label><p>
+                     <italic toggle="yes">Abstract</italic>. Although there is a size limit for letters in <italic toggle="yes">EPL</italic>, this should not be at the detriment of the abstract. A good size abstract for a letter in <italic toggle="yes">EPL</italic> is around 150 words. Many letters have much shorter abstracts, lacking background which would make the reader understand why the research was conducted. The abstract should cover all four main parts of the article: background, materials and methods, results, and discussion/conclusion. A good example is the abstract of “The role of syntax in the formation of scale-free language networks” [<xref ref-type="bibr" rid="epl23100304bib3">3</xref>]. It covers all parts of the article, including one sentence of background. It includes transition words and phrases such as “however”, “to answer this question”. It makes good use of the active (“we show”, “we propose)” <italic toggle="yes">vs</italic>. passive voice (“is determined”) to clearly indicate the original contribution of the article. The passive voice is used to discuss results that have been previously published. The active voice is used for the methods and results of the present study.</p></list-item><list-item id="epl23100304l1.3"><label>–</label><p>
+                     <italic toggle="yes">Writing style</italic>. Motivate the work, put it in context, compare, make connections, spend time reading some more related papers than the ones you already know, in particular for the introduction and the discussion. A letter should be clear and readable, not cramped just because it is short. Use plain language, as if you were talking to colleagues so that they understand. Avoid or minimize jargon. Tell a comprehensible story interesting for a broader audience than strict specialists. Some cautious speculation on possible applications or impact is fine, but do not overdo it. Avoid hype and grand statements. Be honest and tell limitations.</p></list-item><list-item id="epl23100304l1.4"><label>–</label><p>
+                     <italic toggle="yes">English language</italic>. <italic toggle="yes">EPL</italic> provides free language editing after acceptance, however this is often too late, as editors and reviewers may be unfavorably biased against poorly written papers. If you are not a native English speaker, we recommend that you get help to edit the English of your manuscript before submission.</p></list-item><list-item id="epl23100304l1.5"><label>–</label><p>
+                     <italic toggle="yes">Graphical elements</italic>. If data or figures are included, provide an interpretation. Figures should be self-contained: the figure and its caption should provide sufficient information for the reader to quickly understand what it depicts, without having to search for this information in the text. Be very careful with details. Are all symbols defined? Are the figures reproducible with the data provided? Do they have proper units?</p></list-item><list-item id="epl23100304l1.6"><label>–</label><p>
+                     <italic toggle="yes">Supplementary material</italic>. Supplementary material (SM) should not be used as a backdoor way to squeeze a full-length article into the letter format. SM has a number of drawbacks: while in principle accessible, in practice it is often not read, or not printed, and the references there are not counted as citations for the authors. Referees tend not to look at it and the quality of presentation is often poorer. In <italic toggle="yes">EPL</italic>, all SM should enhance a reader's understanding of the associated article without being essential to that understanding.</p></list-item></list>
+         </p><p>The substance of a letter is of course its content, and no polishing can fix results that are erroneous, not new, or not very exciting because they only provide minor extensions to existing knowledge. Yet, if you have found something new, important, and relevant to colleagues, a good presentation will greatly enhance its impact and dissemination. Take your time and improve the manuscript in several rounds. Ask colleagues for a critical reading. Set ambitious goals for the quality of the paper, beyond “just publishing”. Make it memorable and inspiring to others. We look forward to your next letter!</p><p>
+            <italic toggle="yes">J. Gonzalo Muga</italic>
+         </p><p>Editor-in-Chief</p><p>
+            <italic toggle="yes">Anne Ruimy</italic>
+         </p><p>Executive Editor</p></sec></body><back><ref-list content-type="numerical"><title>References</title><ref id="epl23100304bib1"><label>1</label><element-citation publication-type="journal" xlink:type="simple"><person-group person-group-type="author">
+                  <name name-style="western"><surname>Letchford</surname><given-names>Adrian</given-names></name>
+                  <name name-style="western"><surname>Moat Helen</surname><given-names>Susannah</given-names></name>
+                  <name name-style="western"><surname>Preis</surname><given-names>Tobias</given-names></name>
+               </person-group><year>2015</year><source>R. Soc. Open Sci.</source><volume>2</volume><elocation-id content-type="artnum">150266</elocation-id></element-citation></ref><ref id="epl23100304bib2"><label>2</label><element-citation publication-type="journal" xlink:type="simple"><person-group person-group-type="author">
+                  <name name-style="western"><surname>Li</surname><given-names>Kun</given-names></name>
+                  <etal/>
+               </person-group><year>2019</year><source>EPL</source><volume>128</volume><elocation-id content-type="artnum">38002</elocation-id></element-citation></ref><ref id="epl23100304bib3"><label>3</label><element-citation publication-type="journal" xlink:type="simple"><person-group person-group-type="author">
+                  <name name-style="western"><surname>Yang</surname><given-names>Mu</given-names></name>
+                  <name name-style="western"><surname>Liu</surname><given-names>Haitao</given-names></name>
+               </person-group><year>2022</year><source>EPL</source><volume>139</volume><elocation-id content-type="artnum">61002</elocation-id></element-citation></ref></ref-list></back></article>