Merge pull request #238 from golnazads/master

added xe specifier for custom format to output eprint comment

exportsrv/formatter/customFormat.py

@@ -39,14 +39,14 @@ class CustomFormat(Format):
         re.compile(r'(%Z(?:EOL):\".*\"\s?)'),
     ]
     REGEX_CUSTOME_FORMAT = re.compile(
-        r'''(                                                   # start of capture group 1
-            %                                                   # literal "%"
-            (?:[\\></=])?                                       # field encoding
-            (?:                                                 # first option
-            (?:\d+|\*)?                                         # width
-            (?:\.(?:\d+|\*))?                                   # precision
+        r'''(                                                       # start of capture group 1
+            %                                                       # literal "%"
+            (?:[\\></=])?                                           # field encoding
+            (?:                                                     # first option
+            (?:\d+|\*)?                                             # width
+            (?:\.(?:\d+|\*))?                                       # precision
             (?:\^)?
-            p{0,2}[AaBcCdDeEfFGgHhiIJjKkLlMmNnOopPQqRSTUuVWXxY] # type
+            [px]{0,2}[AaBcCdDeEfFGgHhiIJjKkLlMmNnOopPQqRSTUuVWXxY]  # type
             )
         )''', flags=re.X
     )
@@ -202,6 +202,7 @@ def __get_solr_field(self, specifier):
             'W': 'doctype',
             'X': 'eid,identifier',
             'x': 'comment',
+            'xe': 'pubnote',
             'Y': 'year'
         }
         specifier = ''.join(re.findall(r'([AaBcCdDeEfFGgHhiIJjKkLlMmNnOopPQqRSTUuVWXxY]{1,2})', specifier))
@@ -310,8 +311,9 @@ def __parse(self):
         for m in self.REGEX_CUSTOME_FORMAT.finditer(self.custom_format):
             self.parsed_spec.append(tuple((m.start(1), m.group(1), self.__get_solr_field(m.group(1)))))
         # we have %p, %pp, and %pc, when doing replace, %p causes other two to be replaced
-        # re did not work, so pushing %p to the end to be the last item to get replaced
-        self.parsed_spec = sorted(self.parsed_spec, key=lambda tup: tup[1] == '%p')
+        # similarly %x and %xe
+        # so pushing %p and %x to the end to be the last item to get replaced
+        self.parsed_spec = sorted(self.parsed_spec, key=lambda tup: tup[1] in ['%p', '%x'])
         self.__escape()
         self.__for_csv()
 
@@ -829,7 +831,7 @@ def __get_doc(self, index):
         result = self.custom_format
         a_doc = self.from_solr['response'].get('docs')[index]
         for field in self.parsed_spec:
-            if (field[2] == 'title') or (field[2] == 'doi') or (field[2] == 'comment'):
+            if (field[2] == 'title') or (field[2] == 'doi') or (field[2] == 'comment') or (field[2] == 'pubnote'):
                 result = self.__add_in(result, field, ''.join(a_doc.get(field[2], '')))
             elif (field[2] == 'author'):
                 result = self.__add_in(result, field, self.__get_author_list(field[1], index))

exportsrv/tests/unittests/stubdata/solrdata.py

@@ -1381,4 +1381,34 @@
             }
         ]
     }
+}
+
+data_15 = \
+{
+    u'responseHeader': {
+         u'status': 0,
+         u'QTime': 8,
+         u'params': {
+             u'q': u'bibcode:(2023JSMTE2023b3301M OR 2023yCat..19220186H OR 2019Sci...365..565B)',
+             u'fl': u'bibcode,comment,pubnote',
+             u'_': u'1686158703270'
+         }
+    },
+    u'response': {
+        'numFound': 3,
+        'start': 0,
+        'docs': [
+            {
+                u'bibcode': u'2019Sci...365..565B',
+                u'comment': [u'Galaxies B and C from figures 2 are not in SIMBAD.'],
+                u'pubnote': [u'Published online in Science 27 June 2019; doi:10.1126/science.aaw5903']},
+            {
+                u'bibcode': u'2023JSMTE2023b3301M',
+                u'pubnote': [u'doi:10.1088/1742-5468/acaf82']},
+            {
+                u'bibcode': u'2023yCat..19220186H',
+                u'comment': [u'fig1.dat 6946x39 Keck/NIRES near-IR spectrum of peculiar type Ia; SN2020qxp/ASASSN-20jq taken at +191d past the epoch ; of rest-frame B-band maximum (MJD=59277.50)']
+            }
+        ]
+    }
 }

exportsrv/tests/unittests/test_custom_format_functionality.py

@@ -400,5 +400,15 @@ def test_author_without_firstname(self):
         assert (custom_format.get().get('export', '') == r''.join(formatted))
 
 
+    def test_comment_and_pubnote(self):
+        # verify the new specifier xe which should output putnote
+        formatted = [u'2019Sci...365..565B\n comment:Galaxies B and C from figures 2 are not in SIMBAD.\n eprint_comment: Published online in Science 27 June 2019; doi:10.1126/science.aaw5903\n',
+                     u'2023JSMTE2023b3301M\n comment:\n eprint_comment: doi:10.1088/1742-5468/acaf82\n',
+                     u'2023yCat..19220186H\n comment:fig1.dat 6946x39 Keck/NIRES near-IR spectrum of peculiar type Ia; SN2020qxp/ASASSN-20jq taken at +191d past the epoch ; of rest-frame B-band maximum (MJD=59277.50)\n eprint_comment:\n']
+        custom_format = CustomFormat(custom_format=r'%R\n comment:%x\n eprint_comment: %xe')
+        custom_format.set_json_from_solr(solrdata.data_15)
+        assert (custom_format.get().get('export', '') == r''.join(formatted))
+
+
 if __name__ == '__main__':
     unittest.main()

exportsrv/tests/unittests/test_export_service.py

@@ -185,7 +185,7 @@ def test_ads_formatter(self):
 
     def test_default_solr_fields(self):
         default_fields = 'author,title,year,pubdate,pub,pub_raw,issue,volume,page,page_range,aff,aff_canonical,doi,abstract,' \
-                         'read_count,bibcode,identifier,copyright,keyword,doctype,[citations],comment,version,' \
+                         'read_count,bibcode,identifier,copyright,keyword,doctype,[citations],comment,pubnote,version,' \
                          'property,esources,data,isbn,eid,issn,arxiv_class,editor,series,publisher,bibstem,page_count,orcid_pub'
         assert (views.default_solr_fields() == default_fields)
 

exportsrv/views.py

@@ -27,7 +27,7 @@ def default_solr_fields():
     :return: list of fields needed from solr
     """
     return 'author,title,year,pubdate,pub,pub_raw,issue,volume,page,page_range,aff,aff_canonical,doi,abstract,' \
-           'read_count,bibcode,identifier,copyright,keyword,doctype,[citations],comment,version,' \
+           'read_count,bibcode,identifier,copyright,keyword,doctype,[citations],comment,pubnote,version,' \
            'property,esources,data,isbn,eid,issn,arxiv_class,editor,series,publisher,bibstem,page_count,orcid_pub'