Normalize DOI and support ORCID

README.md

@@ -9,7 +9,7 @@ There are 3 supported [Digital Commons structure types](https://bepress.com/refe
 
 ## Installation Instructions
 1. Clone this repository into the Janeway plugins folder (`path/to/janeway/src/plugins/`)
-2. Run the plugin installation command: `python3 src/manage.py install_plugins typesetting`.
+2. Run the plugin installation command: `python3 src/manage.py install_plugins bepress`.
 3. Run the migration command `python3 src/manage.py migrate bepress`
 4. Restart your webserver
 
@@ -31,7 +31,7 @@ The spreadsheet needs to be exported as a CSV before you can import it into Jane
 ### Importing from OAI
 Another alternative for those who don't have access to the archive files is to generate one using Bepress OAI endpoint. This feature is only supported via command line however and can take a long time, since it will generate an archive of the metadata for the entire institution.
 
-To run this command all you need is the OAI url for your institution and then run the command `import_bepress_from_oai`.
+To run this command all you need is the OAI url for your institution (do not include parameters) and then run the command `import_bepress_from_oai`.
 
 The resulting metadata archives will be saved under `src/files/plugins/bepress` and will be displayed in the bepress plugin management page, ready to be loaded into any Janeway site.
 

templates/bepress/index.html

@@ -25,7 +25,7 @@
                 {% endif %}
             <br />
                 <label for="bepress_structure">
-                    Select the <a target="_blank" href="https://www.bepress.com/reference_guide_dc/digital-commons-structures/">strucuture</a> of the content being imported
+                    Select the <a target="_blank" href="https://www.bepress.com/reference_guide_dc/digital-commons-structures/">structure</a> of the content being imported
                 </label>
                 <select name="bepress_structure">
                     <option value="series">Series</option>

utils.py

@@ -20,9 +20,10 @@
 from core import files
 from core.models import Account, Galley, SupplementaryFile
 from production.logic import save_galley
-from identifiers.models import Identifier
+from identifiers.models import Identifier, DOI_RE
 from submission import models as submission_models
 from journal import models as journal_models
+from utils.orcid import COMPILED_ORCID_REGEX
 from utils.logger import get_logger
 
 from plugins.bepress import const
@@ -47,7 +48,7 @@ class FakeRequest():
 
 def get_bepress_import_folders():
     if os.path.exists(BEPRESS_PATH):
-        return os.listdir(BEPRESS_PATH)
+        return sorted(os.listdir(BEPRESS_PATH))
     else:
         return []
 
@@ -101,6 +102,7 @@ def create_article_record(dump_name, soup, journal, default_section, section_key
     metadata_doi(soup, article)
     metadata_keywords(soup, article)
     metadata_authors(soup, article)
+    metadata_orcid(soup, article)
     metadata_license(soup, article)
     metadata_citation(soup, article)
     metadata_pages(soup, article)
@@ -120,11 +122,13 @@ def create_article_record(dump_name, soup, journal, default_section, section_key
 def metadata_doi(soup, article):
     field = soup.fields.find(attrs={"name": "doi"})
     if field and field.value:
-        Identifier.objects.get_or_create(
-            id_type="doi",
-            article=article,
-            identifier=field.value.string
-        )
+        result = DOI_RE.search(field.value.string)
+        if result:
+            Identifier.objects.get_or_create(
+                id_type="doi",
+                article=article,
+                identifier=result.group(0)
+            )
 
 
 def metadata_keywords(soup, article):
@@ -404,6 +408,22 @@ def make_dummy_email(author):
     return "{0}@{1}".format(hashed, settings.DUMMY_EMAIL_DOMAIN)
 
 
+def metadata_orcid(soup, article):
+    """
+    For single-author articles, we can find and use the ORCID field.
+    To do: work out how to support ORCID for multi-author articles.
+    """
+    field = soup.fields.find(attrs={"name": "orcid"})
+    if not field:
+        field = soup.fields.find(attrs={"name": "orcid_id"})
+    if field and field.value and article.frozenauthor_set.count() == 1:
+        result = COMPILED_ORCID_REGEX.search(field.value.string)
+        if result:
+            author = article.frozenauthor_set.first()
+            author.frozen_orcid = result.group(0)
+            author.save()
+
+
 def fetch_remote_galley(soup, stamped=False):
     url = getattr(soup, "fulltext-url").string
     if url:
@@ -827,7 +847,7 @@ def add_to_issue(article, root_path, export_path, struct, soup):
     :param article: The submission.Article being imported
     :param root_path: The absolute path in which the metadata.xml was found
     :param export_path: The absolute path to the provided exported data
-    :param struct: (str) One of const.BEPRESS_STRUCTURESujj
+    :param struct: (str) One of const.BEPRESS_STRUCTURES
     :param soup: (bs4.Soup) Soupified metadata.xml
     """
     relative_path = root_path.replace(export_path, "")