[lit, python3] Update lit error logging to work correctly in python3 and other test fixes

[stella.stamenova]

Summary

In Python2 'unicode' is a distinct type from 'str', but in Python3 'unicode' does not exist and instead all 'str' objects are Unicode string. This change updates the logic in the test logging for lit to correctly process each of the types, and more importantly, to not just fail in Python3.

This change also reverses the use of quotes in several of the cfg files. By using '""' we are guaranteeing that the resulting path will work correctly on Windows while "''" only works correctly sometimes. This also fixes one of the failing tests.

[zturner]

We have a function somewhere in lit utils that does this, but I’m OOO so I
can’t look for it. Can you try to find it?

[stella.stamenova]

In D50397#1191201, @zturner wrote:

We have a function somewhere in lit utils that does this, but I’m OOO so I
can’t look for it. Can you try to find it?

You are thinking of to_string in util.py. I could use it here, but the code in Test.py explicitly ignores any errors from the encode/decode calls while to_string raises an exception when it fails to encode. I could modify to_string to take an optional parameter to determine whether to raise an exception instead of having some of the same functionality in Test.py.

[zturner]

No that’s fine, only makes sense to use it if it fits naturally. As long as
you tried. Lgtm as is

utils/lit/lit/Test.py

def writeJUnitXML(self, fil):
             class_name = safe_name + "." + safe_name
         class_name = quoteattr(class_name)
         testcase_template = '<testcase classname={class_name} name={test_name} time="{time:.2f}"'
         elapsed_time = self.result.elapsed if self.result.elapsed is not None else 0.0
         testcase_xml = testcase_template.format(class_name=class_name, test_name=test_name, time=elapsed_time)
         fil.write(testcase_xml)
         if self.result.code.isFailure:
             fil.write(">\n\t<failure ><![CDATA[")
-            if type(self.result.output) == unicode:
-                encoded_output = self.result.output.encode("utf-8", 'ignore')
-            else:
+            # In Python2, 'str' and 'unicode' are distinct types, but in Python3, the type 'unicode' does not exist
+            # and instead 'bytes' is distinct
+            # in Python3, there's no unicode
+            if isinstance(self.result.output, str):
                 encoded_output = self.result.output
+            elif isinstance(self.result.output, bytes):
+                encoded_output = self.result.output.decode("utf-8", 'ignore')
+            else:
+                encoded_output = self.result.output.encode("utf-8", 'ignore')
             # In the unlikely case that the output contains the CDATA terminator
             # we wrap it by creating a new CDATA block
             fil.write(encoded_output.replace("]]>", "]]]]><![CDATA[>"))
             fil.write("]]></failure>\n</testcase>")
         elif self.result.code == UNSUPPORTED:
             unsupported_features = self.getMissingRequiredFeatures()
             if unsupported_features:
                 skip_message = "Skipping because of: " + ", ".join(unsupported_features)
             else:
                 skip_message = "Skipping because of configuration."
 
             fil.write(">\n\t<skipped message={} />\n</testcase>\n".format(quoteattr(skip_message)))
         else:
             fil.write("/>")

utils/lit/lit/llvm/config.py

class LLVMConfig(object):
     def use_default_substitutions(self):
         tool_patterns = [
             ToolSubst('FileCheck', unresolved='fatal'),
             # Handle these specially as they are strings searched for during testing.
             ToolSubst(r'\| \bcount\b', command=FindTool(
                 'count'), verbatim=True, unresolved='fatal'),
             ToolSubst(r'\| \bnot\b', command=FindTool('not'), verbatim=True, unresolved='fatal')]
 
-        self.config.substitutions.append(('%python', "'%s'" % (sys.executable)))
+        self.config.substitutions.append(('%python', '"%s"' % (sys.executable)))
 
         self.add_tool_substitutions(
             tool_patterns, [self.config.llvm_tools_dir])
 
     def use_llvm_tool(self, name, search_env=None, required=False, quiet=False):
         """Find the executable program 'name', optionally using the specified
         environment variable as an override before searching the
         configuration's PATH."""

utils/lit/tests/Inputs/shtest-env/lit.cfg

 import lit.formats
 config.name = 'shtest-env'
 config.suffixes = ['.txt']
 config.test_format = lit.formats.ShTest()
 config.test_source_root = None
 config.test_exec_root = None
 config.environment['FOO'] = '1'
 config.environment['BAR'] = '2'
-config.substitutions.append(('%{python}', "'%s'" % (sys.executable)))
+config.substitutions.append(('%{python}', '"%s"' % (sys.executable)))

utils/lit/tests/Inputs/shtest-shell/lit.cfg

 import lit.formats
 config.name = 'shtest-shell'
 config.suffixes = ['.txt']
 config.test_format = lit.formats.ShTest()
 config.test_source_root = None
 config.test_exec_root = None
-config.substitutions.append(('%{python}', "'%s'" % (sys.executable)))
+config.substitutions.append(('%{python}', '"%s"' % (sys.executable)))

utils/lit/tests/Inputs/shtest-timeout/lit.cfg

 config.test_format = lit.formats.ShTest(execute_external=externalShell)
 config.suffixes = ['.py']
 
 config.test_source_root = os.path.dirname(__file__)
 config.test_exec_root = config.test_source_root
 config.target_triple = '(unused)'
 src_root = os.path.join(config.test_source_root, '..')
 config.environment['PYTHONPATH'] = src_root
-config.substitutions.append(('%{python}', "'%s'" % (sys.executable)))
+config.substitutions.append(('%{python}', '"%s"' % (sys.executable)))

utils/lit/tests/lit.cfg

else:
   lit_path = src_root
 
 config.environment['PYTHONPATH'] = lit_path # Required because some tests import the lit module
 config.substitutions.append(('%{src_root}', src_root))
 config.substitutions.append(('%{inputs}', os.path.join(
             src_root, 'tests', 'Inputs')))
 config.substitutions.append(('%{lit}', "%%{python} %s" % (
             os.path.join(lit_path, 'lit.py'),)))
-config.substitutions.append(('%{python}', "'%s'" % (sys.executable)))
+config.substitutions.append(('%{python}', '"%s"' % (sys.executable)))
 
 
 # Enable coverage.py reporting, assuming the coverage module has been installed
 # and sitecustomize.py in the virtualenv has been modified appropriately.
 if lit_config.params.get('check-coverage', None):
     config.environment['COVERAGE_PROCESS_START'] = os.path.join(
         os.path.dirname(__file__), ".coveragerc")
 

utils/lit/tests/shtest-timeout.py

 # REQUIRES: python-psutil
 
-# PR33944
-# XFAIL: windows
-
 # FIXME: This test is fragile because it relies on time which can
 # be affected by system performance. In particular we are currently
 # assuming that `short.py` can be successfully executed within 2
 # seconds of wallclock time.
 
 # Test per test timeout using external shell
 # RUN: not %{lit} \
 # RUN: %{inputs}/shtest-timeout/infinite_loop.py \