enh: improved presentation of multiple datasets with identical sample names

Author: paulmueller

CHANGELOG

@@ -10,6 +10,7 @@
  - enh: instantaneous tool tips in block matrix
  - enh: show the created or quickviewed filter in analysis tab (#147)
  - enh: show the created plot in analysis tab
+ - enh: improved presentation of multiple datasets with identical sample names
  - ref: tentative `set_pipeline`, so widgets have direct access to the pipeline
  - ref: raise ValueError in unreachable case in DataSlot creation
  - ref: restructure pipeline management through signaling

dcscope/gui/analysis/ana_basins.py

@@ -107,8 +107,8 @@ def update_content(self, slot_index=None, **kwargs):
             self.setUpdatesEnabled(False)
             self.listWidget_dataset.clear()
             self.treeWidget_basin_name.clear()
-            for slot in self.pipeline.slots:
-                self.listWidget_dataset.addItem(slot.name)
+            for name in self.pipeline.deduce_display_names():
+                self.listWidget_dataset.addItem(name)
             self.setUpdatesEnabled(True)
             if slot_index is None or slot_index < 0:
                 slot_index = max(0, self.listWidget_dataset.currentRow())

dcscope/gui/analysis/ana_log.py

@@ -128,8 +128,8 @@ def update_content(self, slot_index=None, **kwargs):
             self.setUpdatesEnabled(False)
             self.listWidget_dataset.clear()
             self.listWidget_log_name.clear()
-            for slot in self.pipeline.slots:
-                self.listWidget_dataset.addItem(slot.name)
+            for name in self.pipeline.deduce_display_names():
+                self.listWidget_dataset.addItem(name)
             self.setUpdatesEnabled(True)
             if slot_index is None or slot_index < 0:
                 slot_index = max(0, self.listWidget_dataset.currentRow())

dcscope/gui/analysis/ana_meta.py

@@ -49,8 +49,7 @@ def update_content(self, slot_index=None, **kwargs):
             slot_index = min(slot_index, len(self.pipeline.slot_ids) - 1)
 
             self.comboBox_slots.clear()
-            self.comboBox_slots.addItems(
-                [ss.name for ss in self.pipeline.slots])
+            self.comboBox_slots.addItems(self.pipeline.deduce_display_names())
             self.comboBox_slots.setCurrentIndex(slot_index)
             self.comboBox_slots.blockSignals(False)
             # populate content

dcscope/gui/analysis/ana_slot.py

@@ -323,7 +323,7 @@ def slot_names(self):
         if self.pipeline is None:
             return []
         else:
-            return [slot.name for slot in self.pipeline.slots]
+            return self.pipeline.deduce_display_names()
 
     def get_dataset(self):
         """Return dataset associated with the current slot index

dcscope/gui/analysis/ana_tables.py

@@ -225,8 +225,8 @@ def update_content(self, slot_index=None, **kwargs):
             self.setUpdatesEnabled(False)
             self.listWidget_dataset.clear()
             self.listWidget_table_name.clear()
-            for slot in self.pipeline.slots:
-                self.listWidget_dataset.addItem(slot.name)
+            for name in self.pipeline.deduce_display_names():
+                self.listWidget_dataset.addItem(name)
             self.setUpdatesEnabled(True)
             if slot_index is None or slot_index < 0:
                 slot_index = max(0, self.listWidget_dataset.currentRow())

dcscope/gui/main.py

@@ -307,7 +307,7 @@ def add_dataslot(self, paths=None, is_dcor=False):
 
                 slot_ids.append(slot_id)
 
-        self.pipeline.compute_reduced_sample_names()
+        self.pipeline.deduce_reduced_sample_names()
 
         self.pp_mod_send.emit({"pipeline": {"slots_added": slot_ids}})
 

dcscope/pipeline/core.py

@@ -120,7 +120,7 @@ def paths(self):
     def reduced_sample_names(self):
         """Return reduced sample names for all slots"""
         if len(self.slots) != len(self._reduced_sample_names):
-            self.compute_reduced_sample_names()
+            self.deduce_reduced_sample_names()
         return self._reduced_sample_names
 
     def add_filter(self, filt=None, index=None):
@@ -306,9 +306,19 @@ def check_contour_spacing(self, plot_id):
         if old_plot_state != plot_state:
             plot.__setstate__(plot_state)
 
-    def compute_reduced_sample_names(self,
-                                     slot_indices: list[int] = None,
-                                     ) -> list[str]:
+    def deduce_display_names(self):
+        """Return slot names for displaying in lists and combo boxes in the UI
+        """
+        unique_names = self.reduced_sample_names
+        display_names = [
+            (ss.name if ss.name == un else f"{ss.name} [{un[:80]}]")
+            for ss, un in zip(self.slots, unique_names)
+        ]
+        return display_names
+
+    def deduce_reduced_sample_names(self,
+                                    slot_indices: list[int] = None,
+                                    ) -> list[str]:
         """Return a list of reduced sample names for the given indices
 
         The algorithm removes common prefixes and suffixes from sample names.
@@ -374,6 +384,9 @@ def compute_reduced_sample_names(self,
                 for jj, ii in enumerate(idx):
                     names[ii] = new_names[jj]
 
+        # avoid empty names at the end of it
+        names = [n if n else s.name for n, s in zip(names, slots)]
+
         if set_property:
             self._reduced_sample_names.clear()
             self._reduced_sample_names += names