fix documentation; doctests now pass. This PR includes significant

refactor of some broken code and renames some variables for clarity.

The assertions are added because one test case resulted in a
supposedly-json file being read in as a string, which resulted in
breakage downstream

Author: keflavich

astroquery/splatalogue/build_species_table.py

@@ -67,6 +67,7 @@ def get_json_species_ids(*, outfile='splat-species.json', base_url=conf.base_url
             species[kid['class'][0]][kid['value']] = kid.text
 
     with open(data_path(outfile), 'w') as f:
+        assert isinstance(species, dict)
         json.dump(species, f)
 
     return json.dumps(species)

astroquery/splatalogue/core.py

@@ -76,14 +76,14 @@ def set_default_options(self, **kwargs):
         """
         self.data.update(self._parse_kwargs(**kwargs))
 
-    def get_species_ids(self, *, restr=None, reflags=0, recache=False):
+    def get_species_ids(self, regex_str=None, *, reflags=0, recache=False):
         """
         Get a dictionary of "species" IDs, where species refers to the molecule
         name, mass, and chemical composition.
 
         Parameters
         ----------
-        restr : str
+        regex_str : str
             String to compile into an re, if specified.   Searches table for
             species whose names match
         reflags : int
@@ -95,7 +95,7 @@ def get_species_ids(self, *, restr=None, reflags=0, recache=False):
         --------
         >>> import re
         >>> import pprint # unfortunate hack required for documentation testing
-        >>> rslt = Splatalogue.get_species_ids(restr='Formaldehyde')
+        >>> rslt = Splatalogue.get_species_ids(regex_str='Formaldehyde')
         >>> pprint.pprint(rslt)
         {'03023 H2CO - Formaldehyde': '194',
          '03106 H213CO - Formaldehyde': '324',
@@ -107,7 +107,7 @@ def get_species_ids(self, *, restr=None, reflags=0, recache=False):
          '03301 D213CO - Formaldehyde': '1220',
          '03315 HDC18O - Formaldehyde': '21141',
          '0348 D2C18O - Formaldehyde': '21140'}
-        >>> rslt = Splatalogue.get_species_ids(restr='H2CO')
+        >>> rslt = Splatalogue.get_species_ids(regex_str='H2CO')
         >>> pprint.pprint(rslt)
         {'03023 H2CO - Formaldehyde': '194',
          '03109 H2COH+ - Hydroxymethylium ion': '224',
@@ -125,9 +125,9 @@ def get_species_ids(self, *, restr=None, reflags=0, recache=False):
          '08903 CH3CHNH2COOH - II - α-Alanine': '1322'}
         >>> # note the whitespace, preventing H2CO within other
         >>> # more complex molecules
-        >>> Splatalogue.get_species_ids(restr=' H2CO ')
+        >>> Splatalogue.get_species_ids(regex_str=' H2CO ')
         {'03023 H2CO - Formaldehyde': '194'}
-        >>> Splatalogue.get_species_ids(restr=' h2co ', reflags=re.IGNORECASE)
+        >>> Splatalogue.get_species_ids(regex_str=' h2co ', reflags=re.IGNORECASE)
         {'03023 H2CO - Formaldehyde': '194'}
 
         """
@@ -136,8 +136,8 @@ def get_species_ids(self, *, restr=None, reflags=0, recache=False):
         if not hasattr(self, '_species_ids'):
             self._species_ids = load_species_table.species_lookuptable(recache=recache)
 
-        if restr is not None:
-            return self._species_ids.find(restr, flags=reflags)
+        if regex_str is not None:
+            return self._species_ids.find(regex_str, flags=reflags)
         else:
             return self._species_ids
 
@@ -319,7 +319,7 @@ def _parse_kwargs(self, *, min_frequency=None, max_frequency=None,
             payload['sid[]'] = []
         elif chemical_name is not None:
             if parse_chemistry_locally:
-                species_ids = self.get_species_ids(restr=chemical_name, reflags=chem_re_flags)
+                species_ids = self.get_species_ids(regex_str=chemical_name, reflags=chem_re_flags)
                 if len(species_ids) == 0:
                     raise ValueError("No matching chemical species found.")
                 payload['sid[]'] = list(species_ids.values())

astroquery/splatalogue/data/splat-species.json

@@ -66,10 +66,12 @@ def species_lookuptable(*, filename='splat-species.json', recache=False):
     # check to see if the file exists; if not, we run the
     # scraping routine
     if recache or not os.path.isfile(file_cache):
-        species = get_json_species_ids(filename)
+        species = get_json_species_ids(outfile=filename)
+        assert isinstance(species, dict)
     else:
         with open(data_path(filename), 'r') as f:
             species = json.load(f)
+            assert isinstance(species, dict)
     lookuptable = SpeciesLookuptable(dict((v, k) for d in species.values()
                                           for k, v in d.items()))