Move to lxml

python/publish/junit.py

@@ -1,13 +1,19 @@
 import os
 from collections import defaultdict
-from typing import Optional, Iterable, Union, Any, List, Dict
+from typing import Optional, Iterable, Union, Tuple, List, Dict
 
 import junitparser
 from junitparser import Element, JUnitXml, TestCase, TestSuite, Skipped
 from junitparser.junitparser import etree
 
 from publish.unittestresults import ParsedUnitTestResults, UnitTestCase, ParseError
 
+try:
+    import lxml
+    lxml_available = True
+except ImportError:
+    lxml_available = False
+
 
 def get_results(results: Union[Element, List[Element]], status: Optional[str] = None) -> List[Element]:
     """
@@ -97,10 +103,24 @@ def end(self, tag: Union[str, bytes]) -> Element:
             if self._stack:
                 self._stack.pop()
 
+    def close(self) -> Element:
+        # when lxml is around, we have to return an ElementTree here, otherwise
+        #   XMLParser(target=...).parse(..., parser=...)
+        # returns an Element, not a ElementTree, but junitparser expects an ElementTree
+        #
+        # https://lxml.de/parsing.html:
+        #   Note that the parser does not build a tree when using a parser target. The result of the parser run is
+        #   whatever the target object returns from its .close() method. If you want to return an XML tree here, you
+        #   have to create it programmatically in the target object.
+        if lxml_available:
+            return lxml.etree.ElementTree(super().close())
+        else:
+            return super().close()
+
 
 def parse_junit_xml_files(files: Iterable[str], time_factor: float = 1.0, drop_testcases: bool = False) -> ParsedUnitTestResults:
     """Parses junit xml files and returns aggregated statistics as a ParsedUnitTestResults."""
-    def parse(path: str) -> Union[str, Any]:
+    def parse(path: str) -> Union[JUnitXml, BaseException]:
         if not os.path.exists(path):
             return FileNotFoundError(f'File does not exist.')
         if os.stat(path).st_size == 0:
@@ -114,8 +134,7 @@ def parse(path: str) -> Union[str, Any]:
         except BaseException as e:
             return e
 
-    parsed_files = [(result_file, parse(result_file))
-                    for result_file in files]
+    parsed_files = [(result_file, parse(result_file)) for result_file in files]
     junits = [(result_file, junit)
               for result_file, junit in parsed_files
               if not isinstance(junit, BaseException)]

python/requirements.txt

@@ -3,4 +3,5 @@ dataclasses;python_version<"3.7"
 junitparser==2.5.0
 PyGithub==1.55
 urllib3==1.26.9
-requests==2.27.1
+requests==2.27.1
+lxml==4.8.0

python/test/test_junit.py

@@ -399,7 +399,7 @@ def test_parse_junit_xml_files_with_non_xml_file(self):
             parse_junit_xml_files([result_file]),
             ParsedUnitTestResults(
                 files=1,
-                errors=[ParseError(file=result_file, message='File is not a valid XML file:\nsyntax error: line 1, column 0', line=1, column=0)],
+                errors=[ParseError(file=result_file, message="Start tag expected, '<' not found, line 1, column 1 (non-xml.xml, line 1)", line=None, column=None)],
                 suites=0,
                 suite_tests=0,
                 suite_skipped=0,
@@ -415,7 +415,7 @@ def test_parse_junit_xml_files_with_corrupt_xml_file(self):
             parse_junit_xml_files([result_file]),
             ParsedUnitTestResults(
                 files=1,
-                errors=[ParseError(file=result_file, message='File is not a valid XML file:\nno element found: line 11, column 21', line=11, column=21)],
+                errors=[ParseError(file=result_file, message='Premature end of data in tag skipped line 9, line 11, column 22 (corrupt-xml.xml, line 11)', line=None, column=None)],
                 suites=0,
                 suite_tests=0,
                 suite_skipped=0,