Fix a bug with state change that can make index out of range

utils.py

@@ -175,7 +175,7 @@ def build_df3(noVoice, oneVoice, multiVoice):
     """Voice category totals DataFrame."""
     return pd.DataFrame({
         "values": [su.sumTimes(noVoice), su.sumTimes(oneVoice), su.sumTimes(multiVoice)],
-        "names":  ["No Voice", "One Voice", "Multi Voice"],
+        "names":  ["No Voice", "Single Voice", "Multi Voice"],
     })
 
 
@@ -234,9 +234,9 @@ def build_df5(oneVoice, multiVoice, sumNoVoice, sumOneVoice, sumMultiVoice, curr
 
     return pd.DataFrame({
         "ids":    ["NV", "OV", "MV"] + [f"OV_{i}" for i in range(n_ov)] + [f"MV_{i}" for i in range(n_mv)],
-        "labels": ["No Voice", "One Voice", "Multi Voice"] + speakerList + multiSpeakerList,
+        "labels": ["No Voice", "Single Voice", "Multi Voice"] + speakerList + multiSpeakerList,
         "parents":      ["", "", ""] + ["OV"] * n_ov + ["MV"] * n_mv,
-        "parentNames":  ["Total", "Total", "Total"] + ["One Voice"] * n_ov + ["Multi Voice"] * n_mv,
+        "parentNames":  ["Total", "Total", "Total"] + ["Single Voice"] * n_ov + ["Multi Voice"] * n_mv,
         "values":       [sumNoVoice, sumOneVoice, sumMultiVoice] + timeList + multiTimeList,
         "valueStrings": [
             su.timeToString(sumNoVoice),
@@ -295,7 +295,7 @@ def build_fig_pie2(df4, speakerNames, speakerColors, catColors, get_display_name
     df4["names"] = df4["names"].apply(lambda s: get_display_name_fn(s, currFile))
     fig = go.Figure()
     fig.update_layout(
-        title_text="Percentage of Speakers and Custom Categories",
+        title_text="Percentage of Speakers per Role",
         colorway=catColors + figColors,
         **TRANSPARENT_BG,
     )
@@ -451,20 +451,35 @@ def build_fig_bar(df2, speakerNames, catColors, speakerColors, get_display_name_
 # Multi-file summary DataFrames
 # ---------------------------------------------------------------------------
 
-def build_multifile_category_df(validNames, results, summaries, categories, categorySelect):
-    """Build df6 (category breakdown per file) for the multi-file expander."""
+def build_multifile_category_df(validNames, results, summaries, categories, categorySelect,
+                                speakerRenames=None):
+    """Build df6 (category breakdown per file) for the multi-file expander.
+
+    speakerRenames: {filename: {raw_sp: display_name}} — used to apply display
+    names to unassigned speaker columns (extraCats).
+    """
+    speakerRenames = speakerRenames or {}
     df6_dict    = {"files": validNames}
     allCategories = copy.deepcopy(categories)
 
     for fn in validNames:
         currAnnotation, _ = results[fn]
-        # categorySelect is now a global token list [[token,...], ...]; extract raw IDs for fn
         prefix = fn + ": "
         per_file_selections = [
             [t[len(prefix):] for t in tokens if t.startswith(prefix)]
             for tokens in categorySelect
         ]
-        catSummary, extraCats = su.calcCategories(currAnnotation, per_file_selections)
+        try:
+            catSummary, extraCats = su.calcCategories(currAnnotation, per_file_selections)
+        except (UnboundLocalError, Exception):
+            # calcCategories can fail when a role contains a speaker with no
+            # segments in this annotation (e.g. assigned in quick succession
+            # before the UI has settled).  Skip this file for the summary.
+            summaries[fn]["categories"] = ([], [])
+            continue
+        # Apply display names to raw speaker IDs in extraCats
+        renames = speakerRenames.get(fn, {})
+        extraCats = [renames.get(sp, sp) for sp in extraCats]
         summaries[fn]["categories"] = (catSummary, extraCats)
         for extra in extraCats:
             df6_dict.setdefault(extra, [])
@@ -490,7 +505,7 @@ def build_multifile_category_df(validNames, results, summaries, categories, cate
 
 def build_multifile_voice_df(validNames, summaries):
     """Build df7 (no/one/multi voice percentages per file) for the multi-file expander."""
-    voiceNames = ["No Voice", "One Voice", "Multi Voice"]
+    voiceNames = ["No Voice", "Single Voice", "Multi Voice"]
     df7_dict   = {"files": validNames}
     for name in voiceNames:
         df7_dict[name] = []