From 71ffcabe92e3ff8224d0e4407fac73406d523983 Mon Sep 17 00:00:00 2001
From: Philip Hackstock <20710924+phackstock@users.noreply.github.com>
Date: Fri, 13 Sep 2024 10:05:23 +0200
Subject: [PATCH] Improve missing data output (#384)

* Remove index, justify left and remove shortening for required data output

* Rename required data output column to year(s)

* Adjust tests
---
 nomenclature/processor/required_data.py       |  9 +++++-
 .../requiredData_apply_error.yaml             |  2 +-
 tests/test_required_data.py                   | 32 ++++++++-----------
 3 files changed, 23 insertions(+), 20 deletions(-)

diff --git a/nomenclature/processor/required_data.py b/nomenclature/processor/required_data.py
index 3d229e81..65643bd9 100644
--- a/nomenclature/processor/required_data.py
+++ b/nomenclature/processor/required_data.py
@@ -178,7 +178,13 @@ def apply(self, df: IamDataFrame) -> IamDataFrame:
             for model, data_list in missing_data.items():
                 missing_data_log_info += f"Missing for '{model}':\n"
                 for data in data_list:
-                    missing_data_log_info += f"{data}\n\n"
+                    missing_data_log_info += (
+                        data.to_string(
+                            index=False,
+                            justify="left",
+                        )
+                        + "\n\n"
+                    )
             logger.error(
                 "Missing required data.\nFile: %s\n\n%s",
                 get_relative_path(self.file),
@@ -212,6 +218,7 @@ def check_required_data_per_model(
                         .to_frame()
                         .reset_index()
                         .drop(columns=["model"])
+                        .rename(columns={"year": "year(s)"})
                     )
         return missing_data
 
diff --git a/tests/data/required_data/required_data/requiredData_apply_error.yaml b/tests/data/required_data/required_data/requiredData_apply_error.yaml
index d309ddfb..b52dd085 100644
--- a/tests/data/required_data/required_data/requiredData_apply_error.yaml
+++ b/tests/data/required_data/required_data/requiredData_apply_error.yaml
@@ -1,7 +1,7 @@
 model: model_a
 required_data:
   - measurand:
-    - Primary Energy:
+    - Primary Energy|Making sure that a really long variable is displayed completely:
         unit: [GWh/yr, Mtoe]
     year: [2005, 2010, 2015] # 2015 is missing from simple_df for all models
   - variable: Final Energy
diff --git a/tests/test_required_data.py b/tests/test_required_data.py
index e616e250..cbb90741 100644
--- a/tests/test_required_data.py
+++ b/tests/test_required_data.py
@@ -100,24 +100,20 @@ def test_RequiredData_apply_raises(simple_df, caplog):
         required_data_validator.apply(simple_df)
 
     missing_data = [
-        """
-  scenario        variable    unit            year
-0   scen_a  Primary Energy  GWh/yr  2005,2010,2015
-1   scen_a  Primary Energy    Mtoe  2005,2010,2015
-2   scen_b  Primary Energy  GWh/yr  2005,2010,2015
-3   scen_b  Primary Energy    Mtoe  2005,2010,2015""",
-        """
-  scenario      variable
-0   scen_a  Final Energy
-1   scen_b  Final Energy""",
-        """
-  scenario       variable       unit
-0   scen_a  Emissions|CO2  Mt CO2/yr
-1   scen_b  Emissions|CO2  Mt CO2/yr""",
-        """
-  scenario region      variable
-0   scen_a  World  Final Energy
-1   scen_b  World  Final Energy""",
+        """scenario variable                                                                       unit   year(s)""",
+        """scen_a   Primary Energy|Making sure that a really long variable is displayed completely GWh/yr 2005,2010,2015
+scen_a   Primary Energy|Making sure that a really long variable is displayed completely   Mtoe 2005,2010,2015
+scen_b   Primary Energy|Making sure that a really long variable is displayed completely GWh/yr 2005,2010,2015
+scen_b   Primary Energy|Making sure that a really long variable is displayed completely   Mtoe 2005,2010,2015""",
+        """scenario variable""",
+        """scen_a   Final Energy
+scen_b   Final Energy""",
+        """scenario variable      unit""",
+        """scen_a   Emissions|CO2 Mt CO2/yr
+scen_b   Emissions|CO2 Mt CO2/yr""",
+        """scenario region variable""",
+        """scen_a   World  Final Energy
+scen_b   World  Final Energy""",
     ]
     # check if the log message contains the correct information
     assert all(