planetary names data (gpn) added (#43)

* planetary names data (gpn) added

* debugged error

* updated test_read

* changes  to

* gpn field made multiline

* gpn format changes and gpn_id added

* rogue import removed

---------

Co-authored-by: Mugdha Polimera <mugdhapolimera@saos-MacBook-Pro.local>

adsdata/file_defs.py

@@ -69,6 +69,7 @@
 data_files['data_link'] = {'path': 'links/facet_datasources/datasources.links', 'default_value': {},
                            'extra_values': {'link_type': 'DATA', 'property': ['DATA']}, 'multiline': True,
                            'subparts': ['link_sub_type', 'item_count', ['url'], ['title']]}
+data_files['gpn'] = {'path': 'links/gpn/all.links', 'default_value': [], 'multiline': True}
 
 # file properties definitions required to generate metrics for CitationCapture records
 # use dict to hold each input files and their properties and idiosycrasies

adsdata/reader.py

@@ -99,10 +99,16 @@ def read_value_for(self, bibcode):
         # at this point, we have the first line with the bibcode in it
         # roll up possible other values on adjacent lines in file
         value = []
-        value.append(self._get_rest(current_line))
+        if self.file_info['path'] == 'links/gpn/all.links':
+            value.append("/".join(self._get_rest(current_line).split("\t")))
+        else:
+            value.append(self._get_rest(current_line))
         current_line = self._readline()
         while self.file_info.get('multiline', False) and (current_line not in [None, '']) and (bibcode == self._get_bibcode(current_line)):
-            value.append(self._get_rest(current_line))
+            if self.file_info['path'] == 'links/gpn/all.links':
+                value.append("/".join(self._get_rest(current_line).split("\t")))
+            else:
+                value.append(self._get_rest(current_line))
             current_line = self._readline()
 
         # at this point we have read beyond the desired bibcode, must back up

adsdata/tests/data1/config/links/gpn/all.links

@@ -0,0 +1,22 @@
+2000Icar..146..420D	Moon	Crater	Langrenus	3273
+2000P&SS...48..181W	Mars	Crater	Gusev   2289
+2000P&SS...48..181W	Mars	Crater	Marca   3655
+2000P&SS...48..181W	Mars	Patera	Apollinaris Patera  323
+2000P&SS...48..181W	Mars	Chasma	Capri Chasma    1012
+2004JGRE..10912009I	Mars	Patera	Apollinaris Patera	323
+2004JGRE..10912009I	Mars	Fossa	Medusae Fossae	3795
+2004JGRE..10912009I	Mars	Fossa	Sirenum Fossae	5575
+2004JGRE..10912009I	Mars	Terra	Terra Cimmeria	5930
+2004JGRE..10912009I	Mars	Terra	Terra Sirenum	5932
+2004JGRE..10912009I	Mars	Crater	Copernicus	1297
+2004JGRE..10912009I	Mars	Crater	Gusev	2289
+2004JGRE..10912009I	Mars	Crater	Kepler	2991
+2004JGRE..10912009I	Mars	Crater	New Plymouth	4231
+2004JGRE..10912009I	Mars	Crater	Newton	4236
+2024Icar..40815837G	Moon	Mare	Mare Imbrium	3678
+2024Icar..40815837G	Moon	Crater	Alder	171
+2024Icar..40815837G	Moon	Crater	Finsen	1959
+2024Icar..40815837G	Moon	Crater	Leibnitz	3335
+2024Icar..40815821L	Mars	Mons	Aeolis Mons	15000
+2024Icar..40815821L	Mars	Crater	Gale	2071
+2024Icar..40815821L	Mars	Crater	Jezero	14300

adsdata/tests/test_process.py

@@ -9,7 +9,6 @@
 from adsdata.file_defs import data_files
 from adsdata.memory_cache import Cache
 
-
 class TestMemoryCache(unittest.TestCase):
     """test higher level operations for reading in a set of data for a bibcode"""
 
@@ -44,6 +43,17 @@ def test_read(self):
             self.assertEqual(d['refereed'], {'refereed': False})
             self.assertEqual(d['relevance'], {'norm_cites': 0, 'read_count': 25, 'boost': 0.32, 'deprecated_citation_count': 0})
 
+        with Processor(compute_metrics=False) as processor, patch('adsputils.load_config', return_value={'INPUT_DATA_ROOT': './test/data1/config/'}):
+            d = processor._read_next_bibcode('2024Icar..40815837G')
+            self.assertEqual(d['canonical'], '2024Icar..40815837G')
+            self.assertFalse(d['grants'])
+            self.assertFalse(d['ned_objects'])
+            self.assertTrue(d['nonarticle'])
+            self.assertEqual(d['ocrabstract'], {'ocrabstract': False})
+            self.assertEqual(d['private'], {'private': False})
+            self.assertEqual(d['pub_openaccess'], {'pub_openaccess': False})
+            self.assertEqual(d['refereed'], {'refereed': False})
+            self.assertEqual(d['gpn'], ['Moon/Mare/Mare Imbrium/3678', 'Moon/Crater/Alder/171', 'Moon/Crater/Finsen/1959', 'Moon/Crater/Leibnitz/3335'])
     def test_protobuf(self):
         """make sure protobuf are created without an exception"""
         with Processor(compute_metrics=False) as processor, patch('adsputils.load_config', return_value={'INPUT_DATA_ROOT': './test/data1/config/'}):

adsdata/tests/test_reader.py

@@ -7,7 +7,6 @@
 from adsdata import reader
 from adsdata.file_defs import data_files
 
-
 class TestReader(unittest.TestCase):
     """ it is important to have comprehensive tests for reader
 
@@ -330,3 +329,9 @@ def test_bibgroup(self):
             self.assertEqual({"bibgroup": ["GTC", "Keck"]}, f.read_value_for('2021MNRAS.502..510J'))
             self.assertEqual({"bibgroup": []}, f.read_value_for('2021ZZZZZ.502..510J'))
 
+    def test_planetary_names(self):
+        f = reader.NonbibFileReader('gpn', data_files['gpn'])
+        self.assertEqual({'gpn': ['Moon/Crater/Langrenus/3273']}, f.read_value_for('2000Icar..146..420D'))
+        self.assertEqual({'gpn': ['Mars/Patera/Apollinaris Patera/323', 'Mars/Fossa/Medusae Fossae/3795', 'Mars/Fossa/Sirenum Fossae/5575', 'Mars/Terra/Terra Cimmeria/5930', 'Mars/Terra/Terra Sirenum/5932', 'Mars/Crater/Copernicus/1297','Mars/Crater/Gusev/2289','Mars/Crater/Kepler/2991','Mars/Crater/New Plymouth/4231','Mars/Crater/Newton/4236'] },f.read_value_for('2004JGRE..10912009I'))
+
+

requirements.txt

@@ -1 +1 @@
-adsputils==1.3.0
+adsputils==1.5.1