Merge pull request #241 from golnazads/master

added author format %E for custom format to output author list as spe…

exportsrv/cslstyles/ads-author-E.csl

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="utf-8"?>
+<style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" version="1.0" initialize="false">
+  <info>
+    <title>ADS Author Custom Format E</title>
+    <title-short>ADS Author Custom Format E</title-short>
+    <id>https://ui.adsabs.harvard.edu</id>
+    <category citation-format="author"/>
+    <category field="generic-base"/>
+    <summary>Format E: last name followed by initials, no 'and' before the last author</summary>
+    <updated>2017-06-23T15:43:04+00:00</updated>
+    <rights license="http://creativecommons.org/licenses/by-sa/3.0/">This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License</rights>
+  </info>
+  <locale xml:lang="en"/>
+  <macro name="author"/>
+  <citation>
+    <layout/>
+  </citation>
+  <bibliography initialize="false" entry-spacing="0" hanging-indent="true">
+    <layout>
+      <text macro="author"/>
+      <names variable="author">
+        <name delimiter-precedes-last="contextual" initialize="false" initialize-with="" name-as-sort-order="all" delimiter="; "/>
+        <label prefix=", "/>
+      </names>
+    </layout>
+  </bibliography>
+</style>

exportsrv/cslstyles/ads-author-ee.csl

@@ -1,12 +1,12 @@
 <?xml version="1.0" encoding="utf-8"?>
 <style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" version="1.0" and="text" initialize="false">
   <info>
-    <title>ADS Author Custom Format L</title>
-    <title-short>ADS Author Custom Format L</title-short>
+    <title>ADS Author Custom Format e</title>
+    <title-short>ADS Author Custom Format e</title-short>
     <id>https://ui.adsabs.harvard.edu</id>
     <category citation-format="author"/>
     <category field="generic-base"/>
-    <summary>Format L: Author as appears in db, with 'and' before the last author</summary>
+    <summary>Format e: last name followed by initials with dots, with 'and' before the last author</summary>
     <updated>2017-06-23T15:43:04+00:00</updated>
     <rights license="http://creativecommons.org/licenses/by-sa/3.0/">This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License</rights>
   </info>

exportsrv/cslstyles/ads-author-ff.csl

@@ -1,12 +1,12 @@
 <?xml version="1.0" encoding="utf-8"?>
 <style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" version="1.0" and="text" initialize="false">
   <info>
-    <title>ADS Author Custom Format M</title>
-    <title-short>ADS Author Custom Format M</title-short>
+    <title>ADS Author Custom Format f</title>
+    <title-short>ADS Author Custom Format f</title-short>
     <id>https://ui.adsabs.harvard.edu</id>
     <category citation-format="author"/>
     <category field="generic-base"/>
-    <summary>Format M: First Author has the format: lastname, Second Author on has the format: lastname, Before Last Author there is and text, and when shorten has the format: n author(s), et al.</summary>
+    <summary>Format f: lastname only</summary>
     <updated>2017-07-12T17:59:57+00:00</updated>
     <rights license="http://creativecommons.org/licenses/by-sa/3.0/">This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License</rights>
   </info>

exportsrv/formatter/customFormat.py

@@ -167,6 +167,7 @@ def __get_solr_field(self, specifier):
             'd': 'doi',
             'D': 'pubdate',
             'e': 'author',
+            'E': 'author',
             'F': 'aff',
             'f': 'author',
             'G': 'author',
@@ -403,17 +404,18 @@ def __get_affiliation_list(self, a_doc):
         return ''
 
 
-    def __get_n_authors(self, author_list, n_parts_author, before_last, format):
+    def __get_n_authors(self, author_list, n_parts_author, before_last, format, separator=', '):
         """
 
         :param author_list:
         :param n_parts_author:
         :param before_last:
         :param format:
+        :param separator:
         :return:
         """
         split_parts = author_list.replace(before_last, '').split('; ')
-        return self.__replace_author_separator(', '.join(split_parts[:n_parts_author]), format)
+        return self.__replace_author_separator(separator.join(split_parts[:n_parts_author]), format)
 
     def __get_first_author(self, author_list, format):
         """
@@ -427,6 +429,9 @@ def __get_first_author(self, author_list, format):
         # this special case, only last name is returned
         if format == 'n':
             return split_parts[0].split(', ')[0]
+        # another special case, there is no comma between last name and first/middle initials
+        if format == 'E':
+            return split_parts[0].replace(',', '')
         return split_parts[0]
 
 
@@ -440,22 +445,25 @@ def __replace_author_separator(self, author_list, format):
             if format in ['H', 'h']:
                 # remove the last separator before and for these formats, then split and rejoin
                 split_parts = author_list.replace('; and', ' and').split('; ')
+            elif format == 'E':
+                # remove commas between lastname and firstname
+                split_parts = author_list.replace(',', '').split('; ')
             else:
                 split_parts = author_list.split('; ')
             return ', '.join(split_parts)
         # formats that have no comma between last name and first/middle names
         # or only display last name, hence once split each is an one element
-        if format in ['f','g', 'H', 'h', 'M', 'm', 'n', 'O', 'o','k']:
+        if format in ['f','g', 'H', 'h', 'M', 'm', 'n', 'O', 'o']:
             split_parts = author_list.split('; ')
             return self.author_sep.join(split_parts)
         # only last names are displayed here
         if format in ['H', 'h']:
             split_parts = author_list.split('; ')
             return self.author_sep.join(split_parts)
         # formats that have a comma between last name and first/middle names
-        # so that each are author is two elements
+        # so that each author is two elements
         # 12/19 changed the author separator in cls to semicolon, and now can split and join
-        if format in ['A','a','e','G','I','i','L','l','N']:
+        if format in ['A','a','G','I','i','L','l','N']:
             split_parts = author_list.split('; ')
             return self.author_sep.join(split_parts)
         return author_list
@@ -466,21 +474,24 @@ def __get_author_list_abbreviated(self, author_list, num_authors, format, m):
         """
         Formats	    First Author	        Second Author..	Before Last	    abbreviated
         A	        As in db	            As in db	    and	            first author,..., m authors and xx colleagues
+        a	        As in db	            As in db	    &	            first author,..., m authors et al.
+        E           lastname fi             lastname fi                     first author,..., m authors et al
+        e           lastname f.m.           lastname f.m.   and             first author, and xx colleagues
+        f           lastname                lastname        and             first author \\emph{et al.}
         G	        lastname f. i.	        lastname f. i.	                first author, et al.
+        g	        lastname, f.i.	        lastname, f.i.	and	            first author, and xx colleagues
         H	        lastname	            lastname	    and	            display requested number of authors
+        h	        lastname	            lastname	    &
         I	        lastname, f. i.	        f. i. lastname	and	            first author, and xx colleagues
-        L	        lastname, f. i.	        lastname, f. i.	and	            first author, and xx colleagues
-        N	        lastname, f. i.	        lastname, f. i.		            first author, and xx colleagues
-        O           f. i lastname           f. i lastname   and             first author, and xx colleagures
-        l	        lastname, f. i.	        lastname, f. i.	&	            first author, et al.
+        i	        lastname, f. i.	        f. i. lastname	&	            first author, et al.
+        k           firstname i lastname    firstname i lastname   &        first author, et al.
+        L	        lastname, f. i.	        lastname, f. i.	and	            first author, and xx colleagures
+        l	        lastname, f. i.	        lastname, f. i.	&	            first author, et al. colleagues
         M	        lastname	            lastname	and	                first author, et al.
         m	        lastname	            lastname	&	                first author, et al.
+        N	        lastname, f. i.	        lastname, f. i.		            first author, and xx colleagues
         n	        lastname	            +
-        a	        As in db	            As in db	    &	            first author,..., m authors et al.
-        g	        lastname, f.i.	        lastname, f.i.	and	            first author, and xx colleagues
-        h	        lastname	            lastname	    and	            first author \\emph{et al.}
-        i	        lastname, f. i.	        f. i. lastname	&	            first author, et al.
-        k           firstname i lastname    firstname i lastname   &        first author, et al.
+        O           f. i lastname           f. i lastname   and             first author, and xx
         o           f. i lastname           f. i lastname   &               first author, et al.
 
         n.m: Maximum number of entries in field (optional).
@@ -495,6 +506,7 @@ def __get_author_list_abbreviated(self, author_list, num_authors, format, m):
         """
         format_etal = u'{}, et al.'
         format_etal_no_comma = u'{} et al.'
+        format_etal_no_dot = u'{} et al'
         format_n_authors = u'{}'
         format_with_n_colleagues = u'{}, and {} colleagues'
         format_escape_emph = u'{} \\emph{{et al.}}'
@@ -515,8 +527,13 @@ def __get_author_list_abbreviated(self, author_list, num_authors, format, m):
                 return format_with_n_colleagues.format(', '.join(authors[:m]), num_authors-m)
             elif (format == 'O'):
                 return format_with_n_colleagues.format(', '.join(authors[:m]), num_authors-m)
+        if (format == 'E'):
+            # there are no commas between last and first/middle intitials, so to remove those
+            # send a separator different than comma, so that it can be used to separate authors after
+            # commas are removed
+            return format_etal_no_dot.format(self.__get_n_authors(author_list, m, u'', format, '; '))
         if (format == 'G'):
-            # return n authors (LastName, first and middle initials) et. al. - list is seprated by comma
+            # return n authors (LastName, first and middle initials) et. al. - list is separated by comma
             return format_etal.format(self.__get_n_authors(author_list, m, u'', format))
         if (format == 'i'):
             # here the first author is lastname comma first and middle initials

exportsrv/tests/unittests/test_custom_format_functionality.py

@@ -124,13 +124,13 @@ def test_get_affiliation_list_limit(self):
     def test_get_author_list(self):
         # Optional parameters for author field: n.m
         # If the number of authors in the list is larger than n, the list will be truncated and m authors are returned
-        custom_format = CustomFormat(custom_format=r'%A,%3.2A,%a,%3.2a,%G,%3.2G,%g,%3.2g,'
-                                                   r'%H,%3.2H,%2.1H,%h,%3.2h,%I,%3.2I,%i,%3.2i,'
-                                                   r'%L,%3.2L,%l,%3.2l,%M,%3.2M,%m,%3.2m,'
-                                                   r'%N,%3.2N,%n,%3.2n,%e,%3.2e,%f,%3.2f,'
-                                                   r'%O,%3.2O,%o,%3.2o,%k,%3.2k,'
-                                                   r'%^A,%^a,%^G,%^g,%^H,%^h,%^I,%^i,%^L,%^l,%^M,%^m,%^N,%^n,%^e,%^f,'
-                                                   r'%^O,%^o,%^k'
+        custom_format = CustomFormat(custom_format=r'%A,%3.2A,%a,%3.2a,%E,%3.2E,%e,%3.2e,'
+                                                   r'%G,%3.2G,%g,%3.2g,%H,%3.2H,%2.1H,%h,%3.2h,'
+                                                   r'%I,%3.2I,%i,%3.2i,%L,%3.2L,%l,%3.2l,'
+                                                   r'%M,%3.2M,%m,%3.2m,%N,%3.2N,%n,%3.2n,'
+                                                   r'%f,%3.2f,%O,%3.2O,%o,%3.2o,%k,%3.2k,'
+                                                   r'%^A,%^a,%^E,%^e,%^G,%^g,%^H,%^h,%^I,%^i,%^L,%^l,%^M,%^m,%^N,%^n,'
+                                                   r'%^f,%^O,%^o,%^k'
         )
         custom_format.set_json_from_solr(solrdata.data_3)
 
@@ -141,6 +141,10 @@ def test_get_author_list(self):
                             ('%a', 'English, Jayanne, Taylor, A. R., Mashchenko, S. Y., Irwin, Judith A., Basu, Shantanu, & Johnstone, Doug'),
                             ('%3.2a', 'English, Jayanne, Taylor, A. R., et al.'),
                             ('%G', 'English, J., Taylor, A. R., Mashchenko, S. Y., Irwin, J. A., Basu, S., Johnstone, D.'),
+                            ('%E', 'English J, Taylor AR, Mashchenko SY, Irwin JA, Basu S, Johnstone D'),
+                            ('%3.2E', 'English J, Taylor AR et al'),
+                            ('%e', 'English, J., Taylor, A.R., Mashchenko, S.Y., Irwin, J.A., Basu, S., and Johnstone, D.'),
+                            ('%3.2e', 'English, J., Taylor, A.R., and 4 colleagues'),
                             ('%3.2G', 'English, J., Taylor, A. R., et al.'),
                             ('%g', 'English J., Taylor A. R., Mashchenko S. Y., Irwin J. A., Basu S., Johnstone D.'),
                             ('%3.2g', 'English J., Taylor A. R., et al.'),
@@ -165,8 +169,6 @@ def test_get_author_list(self):
                             ('%3.2N',  'English, J., Taylor, A. R., and 4 colleagues'),
                             ('%n',  'English,+'),
                             ('%3.2n',  'English,+'),
-                            ('%e', 'English, J., Taylor, A.R., Mashchenko, S.Y., Irwin, J.A., Basu, S., and Johnstone, D.'),
-                            ('%3.2e', 'English, J., Taylor, A.R., and 4 colleagues'),
                             ('%f', 'English, Taylor, Mashchenko, Irwin, Basu, and Johnstone'),
                             ('%3.2f', 'English, Taylor \\emph{et al.}'),
                             ('%O', 'J. English, A. R. Taylor, S. Y. Mashchenko, J. A. Irwin, S. Basu, and D. Johnstone'),
@@ -177,6 +179,8 @@ def test_get_author_list(self):
                             ('%3.2k', 'Jayanne English, A. R. Taylor, et al.'),
                             ('%^A', 'English, Jayanne'),
                             ('%^a', 'English, Jayanne'),
+                            ('%^E', 'English J'),
+                            ('%^e', 'English, J.'),
                             ('%^G', 'English, J.'),
                             ('%^g', 'English J.'),
                             ('%^H', 'English'),
@@ -189,7 +193,6 @@ def test_get_author_list(self):
                             ('%^m', 'English'),
                             ('%^N', 'English, J.'),
                             ('%^n', 'English'),
-                            ('%^e', 'English, J.'),
                             ('%^f', 'English'),
                             ('%^O', 'J. English'),
                             ('%^o', 'J. English'),