Fix source naming and escaping

.github/workflows/tests.yml

@@ -13,22 +13,23 @@ jobs:
         key: ${{ runner.os }}-pip-${{ hashFiles('**/setup.py') }}
         restore-keys: |
           ${{ runner.os }}-pip-
-    - name: Set up Python 3.6
+    - name: Set up Python 3.8
       uses: actions/setup-python@v1
       with:
-        python-version: 3.6
+        python-version: 3.8
     - name: Install dependencies
       run: |
         # Install Graphviz
         sudo apt-get update
         sudo apt-get install libstdc++6 python3-dev graphviz libgraphviz-dev pkg-config
         sudo apt-get install graphviz
         # Tests use the web ontology but this is here as backup
-        mkdir -p $HOME/.indra/bio_ontology/1.11
-        wget -nv https://bigmech.s3.amazonaws.com/travis/bio_ontology/1.11/mock_ontology.pkl -O $HOME/.indra/bio_ontology/1.11/bio_ontology.pkl
+        bio_ontology_version=1.30
+        mkdir -p $HOME/.indra/bio_ontology/$bio_ontology_version
+        wget -nv https://bigmech.s3.amazonaws.com/travis/bio_ontology/$bio_ontology_version/mock_ontology.pkl -O $HOME/.indra/bio_ontology/$bio_ontology_version/bio_ontology.pkl
         # Now do some regular pip installs
         python -m pip install --upgrade pip
-        pip install numpy scipy sympy cython==0.23.5 nose lxml matplotlib pandas kappy==4.0.0 boto3 nose-timer coverage
+        pip install numpy scipy sympy cython==0.23.5 nose lxml matplotlib pandas<2.0.0 kappy==4.0.0 boto3 nose-timer coverage
         # Install Bionetgen
         wget --no-check-certificate "http://www.csb.pitt.edu/Faculty/Faeder/wp-content/uploads/2017/04/BioNetGen-2.2.6-stable_Linux.tar.gz" -O bionetgen.tar.gz -nv
         tar xzf bionetgen.tar.gz

bioagents/msa/local_query.py

@@ -9,7 +9,7 @@
 from indra.sources.indra_db_rest.query import And, HasType, HasAgent
 from indra.assemblers.html.assembler import get_available_source_counts
 from indra.util.statement_presentation import _get_available_ev_source_counts, \
-    _get_initial_source_counts
+    _get_initial_source_counts, internal_source_mappings
 
 from bioagents.msa.exceptions import EntityError
 
@@ -93,7 +93,8 @@ def get_statements_from_query(self, query, **ignored_kwargs):
         else:
             raise EntityError("Could not form a usable query from given "
                               "constraints.")
-        logger.info('Found %d statements from query' % len(all_stmts))
+        logger.info('Found %d statements from query'
+                    % 0 if all_stmts is None else len(all_stmts))
         self.statements = all_stmts
         return self
 
@@ -110,7 +111,7 @@ def _filter_stmts_by_query(self, query, all_stmts):
         elif isinstance(query, HasType):
             return self._filter_for_type(all_stmts, query.stmt_types[0])
         else:
-            logger.warning("Query {query} not handled.")
+            logger.warning(f"Query {query} not handled.")
             return all_stmts
 
     def sort_statements(self, stmts):
@@ -271,14 +272,18 @@ def _process_relations(self, relations):
         stmt_jsons = []
         for rel in relations:
             mkh = rel.data.get('stmt_hash')
-            stmt_json = json.loads(
-                rel.data.get('stmt_json').replace('\\\\', '\\').replace('\\\\', '\\'))
+            stmt_json = json.loads(_str_escaping(rel.data.get('stmt_json')))
             source_counts = json.loads(rel.data.get('source_counts'))
             stmt_jsons.append(stmt_json)
             if mkh not in self.source_counts:
                 self.source_counts[mkh] = _get_initial_source_counts()
             for source, num in source_counts.items():
-                self.source_counts[mkh][source] += num
+                # The dict from _get_initial_source_counts() contains the
+                # source names as they appear in indra_db while the
+                # source names in CoGEx are as they appear in INDRA,
+                # e.g. 'bel' (in CoGEx) instead of 'bel_lc' (indra_db).
+                mapped_source = internal_source_mappings.get(source, source)
+                self.source_counts[mkh][mapped_source] += num
         return stmts_from_json(stmt_jsons)
 
 
@@ -307,3 +312,9 @@ def get_resoure(self, key):
 
 resource_manager = ResourceManager(preloads=preloads)
 
+
+def _str_escaping(s: str) -> str:
+    """Remove double escaped characters and other escaping artifacts."""
+    return s.replace(
+        '\\\\', '\\').replace('\\\\', '\\').replace('\\{', '{').replace(
+        '\\}', '}')