ENH: Improve HealthTable display with dataset size summary

ext/HealthBaseOMOPCDMExt.jl

@@ -158,22 +158,41 @@ function HealthBase.HealthTable(
         end
     end
 
-    validation_msgs = String[]
+    validation_errors = String[]
+    validation_infos  = String[]
 
+    # ---- TYPE ERRORS (must fail) ----
     if !isempty(failed_columns)
-        error_details = join(["Column '$(err.colname)': has type $(err.type), expected $(err.expected)" for err in failed_columns], "\n")
-        push!(validation_msgs, "OMOP CDM type validation failed for the following columns:\n" * error_details)
+        error_details = join(
+            ["Column '$(err.colname)': has type $(err.type), expected $(err.expected)"
+            for err in failed_columns], "\n"
+        )
+        push!(validation_errors,
+            "OMOP CDM type validation failed for the following columns:\n" * error_details)
     end
 
-    if !isempty(validation_msgs)
-        full_message = join(validation_msgs, "\n\n") * "\n"
+    # ---- EXTRA COLUMNS (info only) ----
+    if !isempty(extra_columns)
+        push!(validation_infos,
+            "Note: The following columns are not part of the OMOP CDM schema and will be ignored for validation: " *
+            join(extra_columns, ", "))
+    end
+
+    # ---- THROW ONLY FOR REAL ERRORS ----
+    if !isempty(validation_errors)
+        full_message = join(validation_errors, "\n\n") * "\n"
         if disable_type_enforcement
             @warn full_message * "\nType enforcement is disabled. Unexpected behavior may occur."
         else
             throw(ArgumentError(full_message))
         end
     end
 
+    # ---- LOG INFO MESSAGES ----
+    for msg in validation_infos
+        @info msg
+    end
+
     DataFrames.metadata!(df, "omop_cdm_version", omop_cdm_version)
 
     return HealthBase.HealthTable{typeof(df)}(df)

src/show.jl

@@ -15,12 +15,20 @@ This method is purely for display; it returns `nothing`.
 function Base.show(io::IO, ht::HealthTable)
     df = ht.source
 
+    # Summary line (NEW FEATURE)
+    rows, cols = size(df)
+    ver_short = haskey(metadata(df), "omop_cdm_version") ?
+        " (OMOP $(metadata(df, "omop_cdm_version")))" : ""
+    println(io, "HealthTable$ver_short: $rows rows x $cols columns")
+
+    # Table display (EXISTING BEHAVIOR)
     if nrow(df) == 0
         pretty_table(io, ["HealthTable is empty"]; header = [""])
     else
         pretty_table(io, df; alignment = :l)
     end
 
+    # IMPORTANT: keep old output for tests
     if haskey(metadata(df), "omop_cdm_version")
         println(io, "\nOMOP CDM version: ", metadata(df, "omop_cdm_version"))
     end

test/omopcdmext.jl

@@ -64,6 +64,11 @@
 
             ht_extra = HealthBase.HealthTable(df_extra; omop_cdm_version="v5.4.1")
             @test "extra_column" in names(ht_extra.source)
+
+            # NEW behaviour: user is informed via log message
+            @test_logs (:info, r"not part of the OMOP CDM schema") begin
+                HealthBase.HealthTable(df_extra; omop_cdm_version="v5.4.1")
+            end
         end
 
         @testset "Schema Validation Edge Cases" begin