Run wf

gga_load_data.py

@@ -2,7 +2,6 @@
 # -*- coding: utf-8 -*-
 import re
 
-import bioblend
 import argparse
 import os
 import logging
@@ -39,54 +38,6 @@ class LoadData(speciesData.SpeciesData):
         self.bam_metadata_cache = {}
         super().__init__(parameters_dictionary)
 
-    def get_history(self):
-        """
-        Create or set the working history to the current species one
-
-        :return:
-        """
-        try:
-            histories = self.instance.histories.get_histories(name=str(self.genus_species))
-            if len(histories) == 1:
-                self.history_id = histories[0]["id"]
-                logging.debug("History ID set for {0} {1}: {2}".format(self.genus, self.species, self.history_id))
-            else:
-                logging.critical("Multiple histories exists for {0}: {1}".format(self.genus, self.species))
-        except IndexError:
-            logging.info("Creating history for {0} {1}".format(self.genus, self.species))
-            hist_dict = self.instance.histories.create_history(name=str(self.genus_species))
-            self.history_id = hist_dict["id"]
-            logging.debug("History ID set for {0} {1}: {2}".format(self.genus, self.species, self.history_id))
-
-        return self.history_id
-
-    def remove_homo_sapiens_from_db(self):
-        """
-        Run the GMOD tool to remove the "Homo sapiens" default organism from the original database
-        Will do nothing if H. sapiens isn't in the database
-
-        """
-
-        logging.debug("Getting 'Homo sapiens' ID in chado database")
-        get_sapiens_id_json_output = utilities_bioblend.run_tool_and_download_single_output_dataset(
-            self.instance,
-            tool_id=constants.GET_ORGANISMS_TOOL, # If this version if not found, Galaxy will use the one that is found
-            history_id=self.history_id,
-            tool_inputs={"genus": "Homo", "species": "sapiens"})
-
-        logging.info("Deleting Homo 'sapiens' in the instance's chado database")
-        try:
-            get_sapiens_id_final_output = json.loads(get_sapiens_id_json_output)[0]
-            sapiens_id = str(get_sapiens_id_final_output["organism_id"])  # needs to be str to be recognized by the chado tool
-            utilities_bioblend.run_tool(
-                self.instance,
-                tool_id=constants.DELETE_ORGANISMS_TOOL,
-                history_id=self.history_id,
-                tool_inputs={"organism": sapiens_id})
-        except IndexError:
-            logging.error("Homo sapiens isn't in the instance's chado database (IndexError)")
-            pass
-
     def purge_histories(self):
         """
         Delete all histories in the instance
@@ -130,13 +81,13 @@ class LoadData(speciesData.SpeciesData):
             existing = gio.libraries.get_previews(name=constants.GALAXY_LIBRARY_NAME)
             for lib in existing:
                 if not lib.deleted:
-                    logging.info('Pre-existing {0} library {1}} found, removing it'.format(constants.GALAXY_LIBRARY_NAME, lib.id))
+                    logging.info('Pre-existing {0} library {1} found, removing it'.format(constants.GALAXY_LIBRARY_NAME, lib.id))
                     gio.libraries.delete(lib.id)
 
             logging.info("Creating new %s library" % constants.GALAXY_LIBRARY_NAME)
             prj_lib = gio.libraries.create(constants.GALAXY_LIBRARY_NAME, constants.GALAXY_LIBRARY_DESC)
-            self.library_id = prj_lib.id  # project data folder/library
-            logging.info("Library for {0}: {1}".format(self.full_name, self.library_id))
+            library_id = prj_lib.id  # project data folder/library
+            logging.info("Library for {0}: {1}".format(self.full_name, library_id))
 
             for fname, files in folders.items():
                 if fname and files:
@@ -278,7 +229,33 @@ class LoadData(speciesData.SpeciesData):
                 logging.info("Did not find metadata in %s " % meta_file)
             return self.get_bam_label(dirname, bam_file)
 
-    
+def remove_homo_sapiens_from_db(instance, history_id):
+    """
+    Run the GMOD tool to remove the "Homo sapiens" default organism from the original database
+    Will do nothing if H. sapiens isn't in the database
+
+    """
+
+    logging.debug("Getting 'Homo sapiens' ID in chado database")
+    get_sapiens_id_json_output = utilities_bioblend.run_tool_and_download_single_output_dataset(
+        instance,
+        tool_id=constants.GET_ORGANISMS_TOOL, # If this version if not found, Galaxy will use the one that is found
+        history_id=history_id,
+        tool_inputs={"genus": "Homo", "species": "sapiens"})
+
+    logging.info("Deleting Homo 'sapiens' in the instance's chado database")
+    try:
+        get_sapiens_id_final_output = json.loads(get_sapiens_id_json_output)[0]
+        sapiens_id = str(get_sapiens_id_final_output["organism_id"])  # needs to be str to be recognized by the chado tool
+        utilities_bioblend.run_tool(
+            instance,
+            tool_id=constants.DELETE_ORGANISMS_TOOL,
+            history_id=history_id,
+            tool_inputs={"organism": sapiens_id})
+    except IndexError:
+        logging.error("Homo sapiens isn't in the instance's chado database (IndexError)")
+        pass
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Load data into Galaxy library")
 
@@ -290,6 +267,10 @@ if __name__ == "__main__":
                         help="Increase output verbosity",
                         action="store_true")
 
+    parser.add_argument("-vv", "--very_verbose",
+                        help="Increase output verbosity",
+                        action="store_true")
+
     parser.add_argument("--config",
                         type=str,
                         help="Config path, default to 'examples/config.yml'")
@@ -300,11 +281,15 @@ if __name__ == "__main__":
 
     args = parser.parse_args()
 
-    if args.verbose:
+    if args.verbose or args.very_verbose:
         logging.basicConfig(level=logging.DEBUG)
     else:
         logging.basicConfig(level=logging.INFO)
 
+    if not args.very_verbose:
+        logging.getLogger("urllib3").setLevel(logging.INFO)
+        logging.getLogger("bioblend").setLevel(logging.INFO)
+
     # Parsing the config file if provided, using the default config otherwise
     if args.config:
         config_file = os.path.abspath(args.config)
@@ -359,12 +344,17 @@ if __name__ == "__main__":
             load_data_for_current_species.setup_library()
             logging.debug("Successfully set up library in galaxy for {0} {1}".format(load_data_for_current_species.genus, load_data_for_current_species.species))
 
-            # Set or get the history for the current organism
-            load_data_for_current_species.get_history()
-            
+            # Get default history
+            history_id = utilities_bioblend.get_history(
+                instance=load_data_for_current_species.instance,
+                history_name="Unnamed history")
+
             # Remove H. sapiens from database if here
             # TODO: set a dedicated history for removing H. sapiens (instead of doing it into a species history)
-            load_data_for_current_species.remove_homo_sapiens_from_db()
+            remove_homo_sapiens_from_db(
+                instance=load_data_for_current_species.instance,
+                history_id=history_id
+            )
 
             # logging.info("Importing datasets into history for %s" % load_data_for_current_species.full_name)
             # load_data_for_current_species.import_datasets_into_history()  # Option "--load-history"