more elegant solution for deduplicating instruments

also edits help for deduplicate_instruments... to better explain what it
does; also fixes small typo ('default=' instead of 'default ='), row 448

src/main.py

@@ -100,7 +100,9 @@ def chain_layer_to_target(layer_object):
 
 def deduplicate_instruments_from_layers(layers):
     '''
-    Takes a list of Layer-class objects and for each layer gets the instruments used (laser, depo chamber and RHEED), returns deduplicated list. Ideally, the lists should only contain one element.
+    Takes a list of Layer-class objects and for each layer gets the instruments used (laser, depo chamber and RHEED), returns dictionary with one item per category. This means that if more layers share the same instruments it returns a dictionary with just their names as strings (no lists or sub-dictionaries).
+    
+    If different layers have different instruments (e.g. laser systems) the user is prompted to only select one.
     '''
     lasers = []
     chambers = []
@@ -110,11 +112,57 @@ def deduplicate_instruments_from_layers(layers):
         lasers.append(instruments["laser_system"])
         chambers.append(instruments["deposition_chamber"])
         rheeds.append(instruments["rheed_system"])
+    ded_lasers = list( set( lasers ) )
+    ded_chambers = list( set( chambers ) )
+    ded_rheeds = list( set( rheeds ) )
+    elegant_dict = {
+        # Keep key names human readable since they're used in the messages of the following errors
+        "Laser Systems": ded_lasers,
+        "Deposition Chamber": ded_chambers,
+        "RHEED Systems": ded_rheeds
+    } # dictionary's name's a joke
+    updated_dict = {} # use this for containing the final dataset
+    for ded in elegant_dict:
+        if len(elegant_dict[ded]) == 0:
+            # if len of list is 0 - empty list - raise error
+            raise IndexError(f"Missing data: no Laser System, Chamber and/or RHEED System is specified in any of the Deposition-type experiments related to this sample. Fix this on eLabFTW before retrying. Affected list: {ded}.")
+        elif len(elegant_dict[ded]) > 1:
+            # if len of list is > 1 - too many values - allow the user to pick one
+            print("Warning: different instruments have been used for different layers - which is currently not allowed.")
+            # there's a better way to do this but I can't remember now for the life of me...
+            i = 0
+            while i < len(elegant_dict[ded]):
+                print(f"{i} - {elegant_dict[ded][i]}")
+                i += 1
+            ans = None
+            while not type(ans) == int or not ans in range(0, len(elegant_dict[ded])):
+                ans = input("Please pick one of the previous (0, 1, ...) [default = 0]: ") or "0"
+                if ans.isdigit():
+                    ans = int(ans)
+                continue # unnecessary?
+            updated_dict[ded] = elegant_dict[ded][ans]
+        elif elegant_dict[ded][0] in ["", 0, None]:
+            # if len is 1 BUT value is "", 0 or None raise error
+            raise ValueError(f"Missing data: a Laser System, Chamber and/or RHEED System which is specified across all the Deposition-type experiments related to this sample is either empty or invalid. Fix this on eLabFTW before retrying. Affected list: {ded}.")
+        else:
+            # if none of the previous (only 1 value), that single value is used
+            updated_dict[ded] = elegant_dict[ded][0]
     instruments_used_dict = {
-        "laser_system": list( set( lasers ) ),
-        "deposition_chamber": list( set( chambers ) ),
-        "rheed_system" : list( set( rheeds ) ),
+        "laser_system": updated_dict["Laser Systems"],
+        "deposition_chamber": updated_dict["Deposition Chamber"],
+        "rheed_system": updated_dict["RHEED Systems"],
     }
+    return instruments_used_dict
+    
+    ### OLD CODE
+    # if 0 in [ len(i) for i in elegant_list ]:
+    #     # i.e. if length of one of the lists in elegant_list is zero (missing data):
+    #     raise IndexError("Missing data: no Laser System, Chamber and/or RHEED System is specified in any of the Deposition-type experiments related to this sample.")
+    # if not all([ len(i) == 1 for i in elegant_list ]):
+    #     print("Warning: different instruments have been used for different layers - which is currently not allowed.")
+    #     # for every element in elegant list check if len > 1 and if it is 
+    #     print("Selecting the first occurence for every category...")
+    ###
     # lasers = { f"layer_{lyr.layer_number}": lyr.laser_system for lyr in layers }
     # chambers = { f"layer_{lyr.layer_number}": lyr.deposition_chamber for lyr in layers }
     # rheeds = { f"layer_{lyr.layer_number}": lyr.rheed_system for lyr in layers }
@@ -123,7 +171,6 @@ def deduplicate_instruments_from_layers(layers):
     #     "deposition_chamber": chambers,
     #     "rheed_system": rheeds,
     # }
-    return instruments_used_dict
 
 def make_nexus_schema_dictionary(substrate_object, layers):
     '''
@@ -297,16 +344,22 @@ def build_nexus_file(pld_fabrication, output_path):
             nx_layer.attrs["NX_class"] = "NXsubentry"
             layer_dict = multilayer_dict[layer]
             # Sub-groups of a layer
+            ## Target
             nx_target = nx_layer.create_group("target")
             nx_target.attrs["NX_class"] = "NXsample"
             target_dict = layer_dict["target"]
+            ## Rastering and Annealing
             nx_laser_rastering = nx_layer.create_group("laser_rastering")
-            nx_pre_annealing = nx_layer.create_group("pre_annealing")
-            nx_post_annealing = nx_layer.create_group("post_annealing")
             nx_laser_rastering.attrs["NX_class"] = "NXprocess"
+            rastering_dict = layer_dict["laser_rastering"]
+            nx_pre_annealing = nx_layer.create_group("pre_annealing")
             nx_pre_annealing.attrs["NX_class"] = "NXprocess"
+            pre_ann_dict = layer_dict["pre_annealing"]
+            nx_post_annealing = nx_layer.create_group("post_annealing")
             nx_post_annealing.attrs["NX_class"] = "NXprocess"
+            post_ann_dict = layer_dict["post_annealing"]
 
+            ## Target metadata
             try:
                 nx_target.create_dataset("name", data = target_dict["name"])
                 nx_target.create_dataset("chemical_formula", data = target_dict["chemical_formula"])
@@ -320,6 +373,7 @@ def build_nexus_file(pld_fabrication, output_path):
                 nx_target.create_dataset("batch_id", data = target_dict["batch_id"])
             except TypeError as te:
                 raise TypeError(te)
+            ## Other layer-specific metadata
             try:
                 nx_layer.create_dataset("start_time", data = layer_dict["start_time"])
                 nx_layer.create_dataset("operator", data = layer_dict["operator"])
@@ -346,6 +400,45 @@ def build_nexus_file(pld_fabrication, output_path):
                 nx_layer["laser_energy"].attrs["units"] = layer_dict["laser_energy"]["units"]
             except TypeError as te:
                 raise TypeError(te)
+            ## Rastering metadata
+            try:
+                nx_laser_rastering.create_dataset("geometry", data = rastering_dict["geometry"])
+                nx_laser_rastering.create_dataset("positions", data = rastering_dict["positions"])
+                nx_laser_rastering.create_dataset("velocities", data = rastering_dict["velocities"])
+            except TypeError as te:
+                raise TypeError(te)
+            ## Annealing metadata
+            try:
+                nx_pre_annealing.create_dataset("ambient_gas", data = pre_ann_dict["ambient_gas"])
+                nx_pre_annealing.create_dataset("pressure", data = pre_ann_dict["pressure"]["value"])
+                nx_pre_annealing["pressure"].attrs["units"] = pre_ann_dict["pressure"]["units"]
+                nx_pre_annealing.create_dataset("temperature", data = pre_ann_dict["temperature"]["value"])
+                nx_pre_annealing["temperature"].attrs["units"] = pre_ann_dict["temperature"]["units"]
+                nx_pre_annealing.create_dataset("duration", data = pre_ann_dict["duration"]["value"])
+                nx_pre_annealing["duration"].attrs["units"] = pre_ann_dict["duration"]["units"]
+            except TypeError as te:
+                raise TypeError(te)
+            try:
+                nx_post_annealing.create_dataset("ambient_gas", data = post_ann_dict["ambient_gas"])
+                nx_post_annealing.create_dataset("pressure", data = post_ann_dict["pressure"]["value"])
+                nx_post_annealing["pressure"].attrs["units"] = post_ann_dict["pressure"]["units"]
+                nx_post_annealing.create_dataset("temperature", data = post_ann_dict["temperature"]["value"])
+                nx_post_annealing["temperature"].attrs["units"] = post_ann_dict["temperature"]["units"]
+                nx_post_annealing.create_dataset("duration", data = post_ann_dict["duration"]["value"])
+                nx_post_annealing["duration"].attrs["units"] = post_ann_dict["duration"]["units"]
+            except TypeError as te:
+                raise TypeError(te)
+        
+        # Instruments used section
+        nx_instruments = nx_pld_entry.create_group("instruments_used")
+        nx_instruments.attrs["NX_class"] = "NXinstrument"
+        instruments_dict = pld_fabrication["instruments_used"]
+        try:
+            nx_instruments.create_dataset("laser_system", data = instruments_dict["laser_system"])
+            nx_instruments.create_dataset("deposition_chamber", data = instruments_dict["deposition_chamber"])
+            nx_instruments.create_dataset("rheed_system", data = instruments_dict["rheed_system"])
+        except TypeError as te:
+            raise TypeError(te)
     return
 
 if __name__=="__main__":