more exceptions for invalid formats

also include string that isn't validating

Author: eseiver

allofplos/article_class.py

@@ -107,7 +107,7 @@ def doi(self, d):
         instantiating the article object.
         """
         if validate_doi(d) is False:
-            raise Exception("Invalid format for PLOS DOI")
+            raise Exception("Invalid format for PLOS DOI: {}".format(d))
         self.reset_memoized_attrs()
         self._doi = d
 

allofplos/transformations.py

@@ -95,13 +95,13 @@ def filename_to_doi(filename):
     :return: full unique identifier for a PLOS article
     """
     filename = os.path.basename(filename)
-    if correction in filename and validate_filename(filename):
+    if not validate_filename(filename):
+        raise Exception("Invalid format for PLOS filename: {}".format(filename))
+    elif correction in filename:
         article = 'annotation/' + filename.split('.', 4)[2]
         doi = PREFIX + article
-    elif validate_filename(filename):
-        doi = PREFIX + os.path.splitext(filename)[0]
     else:
-        doi = ''
+        doi = PREFIX + os.path.splitext(filename)[0]
     return doi
 
 
@@ -154,6 +154,8 @@ def doi_to_url(doi):
     :param doi: full unique identifier for a PLOS article
     :return: online location of a PLOS article's XML
     """
+    if validate_doi(doi) is False:
+        raise Exception("Invalid format for PLOS DOI: {}".format(doi))
     journal = Journal.doi_to_journal(doi)
     base_page = _get_base_page(journal)
     return ''.join([base_page, 'article/file?id=', doi, URL_SUFFIX])
@@ -177,9 +179,8 @@ def doi_to_path(doi, directory=None):
         article_file = os.path.join(directory, "plos.correction." + doi.split('/')[-1] + SUFFIX_LOWER)
     elif validate_doi(doi):
         article_file = os.path.join(directory, doi.lstrip(PREFIX) + SUFFIX_LOWER)
-    # NOTE: The following check is weird, a DOI should never validate as a file name.
-    elif validate_filename(doi):
-        article_file = doi
+    else:
+        raise Exception("Invalid format for PLOS DOI: {}".format(doi))
     return article_file