QPR-12014 comapre xml files using xmldiff, make deliberate change to expected result to test the xml diff tool

Author: pcaspers

Docker/Dockerfile-Test

@@ -5,7 +5,7 @@ RUN apt-get update \
   && DEBIAN_FRONTEND=noninteractive apt-get install -y dos2unix python3 python3-pip libxml2-utils xsltproc \
   && apt-get clean \
   && rm -rf /var/lib/apt/lists/* \
-  && pip3 install matplotlib pandas nose nose_xunitmp datacompy jsondiff lxml
+  && pip3 install matplotlib pandas nose nose_xunitmp datacompy jsondiff lxml xmldiff
 
 CMD bash
 

Tools/PythonTools/compare_files.py

@@ -11,6 +11,8 @@
 from datacompy.core import Compare
 import re
 import jsondiff
+from lxml import etree
+from xmldiff import main, formatting
 
 
 def is_float(num: str):
@@ -253,10 +255,11 @@ def compare_files(file_1, file_2, name, config: dict = None) -> bool:
             raise ValueError('File, ' + file_1 + ', requires a comparison configuration but none given.')
         if ext_2 == '.csv':
             raise ValueError('File, ' + file_2 + ', requires a comparison configuration but none given.')
-
-    if comp_config is None:
-        # If there was no configuration then fall back to a straight file comparison.
-        result = compare_files_direct(name, file_1, file_2)
+        if ext_1 == '.xml' and ext_2 == '.xml':
+            result = compare_files_xml(name, file_1, file_2)
+        else:
+            # If there was no configuration then fall back to a straight file comparison.
+            result = compare_files_direct(name, file_1, file_2)
     else:
         config_type = comp_config.get('type')
         if config_type == 'csv':
@@ -549,6 +552,15 @@ def compare_files_direct(name, file_1, file_2):
 
     return match
 
+def compare_files_xml(name, file_1, file_2):
+    logger = logging.getLogger(__name__)
+    logger.debug('%s: Comparing file %s against %s using xml diff', name, file_1, file_2)
+    diff = main.diff_files('file1.xml', 'file2.xml', formatter=formatting.XMLFormatter())
+    match = True
+    for line in diff:
+        match = False
+        logger.warning(line.rstrip('\n'))
+    return match
 
 def compare_files_json(name, file_1, file_2, config) -> bool:
     # Compare JSON files using configuration.