add cli tool to look at differences between two output definition files

nomenclature/cli.py

@@ -1,13 +1,14 @@
-from pathlib import Path
-from typing import List, Optional
 import importlib.util
 import sys
+from pathlib import Path
+from typing import List, Optional
 
 import click
-
+import pandas as pd
 from pyam import IamDataFrame
-from nomenclature.definition import DataStructureDefinition
+
 from nomenclature.codelist import VariableCodeList
+from nomenclature.definition import DataStructureDefinition
 from nomenclature.processor import RegionProcessor
 from nomenclature.testing import assert_valid_structure, assert_valid_yaml
 
@@ -189,6 +190,50 @@ def cli_export_definitions_to_excel(
     DataStructureDefinition(path / "definitions").to_excel(target)
 
 
+@cli.command("diff-definitions")
+@click.argument("source", type=click.Path(exists=True, path_type=Path))
+@click.argument("target", type=click.Path(exists=True, path_type=Path))
+@click.option("--sheet_name", default="variable")
+@click.option("--output", type=click.Path(path_type=Path), default="diff.xlsx")
+def cli_diff_definitions_to_excel(
+    source: Path,
+    target: Path,
+    sheet_name: Optional[str],
+    output: Optional[Path],
+):
+    """Report the difference between two excel sheets generated by `export-definitions`.
+
+    Values in `source` but not in `target` are placed in the column named "source".
+    Values in `target` but not `source` are placed in a column named "target".
+
+    Parameters
+    ----------
+    source : Path
+        Path and file name for the source file
+    target : Path
+        Path and file name for the target file
+    sheet_name : Optional[str]
+        If given, exports the results from region processing to a file called
+        `processed_data`, by default "variable"
+    output : Optional[Path]
+        If given, exports the results from the diff to a file called
+        `processed_data`, by default "diff.xlsx"
+    """
+    s_col = set(pd.read_excel(source, sheet_name=sheet_name)[sheet_name])
+    t_col = set(pd.read_excel(target, sheet_name=sheet_name)[sheet_name])
+    diff = pd.concat(
+        [
+            pd.Series(list(s_col.difference(t_col)), name=source),
+            pd.Series(list(t_col.difference(s_col)), name=target),
+        ],
+        axis="columns",
+    )
+    if output:
+        diff.to_excel(output, sheet_name=sheet_name, index=False)
+    else:
+        print(output)
+
+
 @cli.command("list-missing-variables")
 @click.argument("data", type=click.Path(exists=True, path_type=Path))
 @click.option(