Failing test output sometimes contains control characters like \x1b (e.g.
if there was some -fcolor-diagnostics output) which are not allowed inside
XML files. This causes problems with CI systems: for example, the Jenkins
JUnit XML will throw an exception when ecountering those characters and
similar problems also occur with GitLab CI.
Reviewed By: yln, jdenny
Differential Revision: https://reviews.llvm.org/D84233
file.write('\n')
+_invalid_xml_chars_dict = {c: None for c in range(32) if chr(c) not in ('\t', '\n', '\r')}
+
+
+def remove_invalid_xml_chars(s):
+ # According to the XML 1.0 spec, control characters other than
+ # \t,\r, and \n are not permitted anywhere in the document
+ # (https://www.w3.org/TR/xml/#charsets) and therefore this function
+ # removes them to produce a valid XML document.
+ #
+ # Note: In XML 1.1 only \0 is illegal (https://www.w3.org/TR/xml11/#charsets)
+ # but lit currently produces XML 1.0 output.
+ return s.translate(_invalid_xml_chars_dict)
+
+
class XunitReport(object):
def __init__(self, output_file):
self.output_file = output_file
# terminator we wrap it by creating a new CDATA block.
output = test.result.output.replace(']]>', ']]]]><![CDATA[>')
if isinstance(output, bytes):
- output.decode("utf-8", 'ignore')
+ output = output.decode("utf-8", 'ignore')
+
+ # Failing test output sometimes contains control characters like
+ # \x1b (e.g. if there was some -fcolor-diagnostics output) which are
+ # not allowed inside XML files.
+ # This causes problems with CI systems: for example, the Jenkins
+ # JUnit XML will throw an exception when ecountering those
+ # characters and similar problems also occur with GitLab CI.
+ output = remove_invalid_xml_chars(output)
file.write(output)
file.write(']]></failure>\n</testcase>\n')
elif test.result.code in self.skipped_codes:
--- /dev/null
+# Run a command that fails and prints control characters on stdout.
+# This tests checks that the xunit output correctly escapes them in the XML.
+#
+# RUN: %{python} %S/write-control-chars.py
+
--- /dev/null
+#!/usr/bin/env python
+
+from __future__ import print_function
+import sys
+
+print("a line with \x1b[2;30;41mcontrol characters\x1b[0m.")
+sys.exit(1)
# CHECK-NEXT: a line with bad encoding:
# CHECK: --
+# CHECK: FAIL: shtest-format :: external_shell/fail_with_control_chars.txt
+# CHECK-NEXT: *** TEST 'shtest-format :: external_shell/fail_with_control_chars.txt' FAILED ***
+# CHECK: Command Output (stdout):
+# CHECK-NEXT: --
+# CHECK-NEXT: a line with {{.*}}control characters{{.*}}.
+# CHECK: --
+
# CHECK: PASS: shtest-format :: external_shell/pass.txt
# CHECK: FAIL: shtest-format :: fail.txt
# CHECK-NEXT: true
# CHECK-NEXT: --
-# CHECK: Failed Tests (3)
+# CHECK: Failed Tests (4)
# CHECK: shtest-format :: external_shell/fail.txt
# CHECK: shtest-format :: external_shell/fail_with_bad_encoding.txt
+# CHECK: shtest-format :: external_shell/fail_with_control_chars.txt
# CHECK: shtest-format :: fail.txt
# CHECK: Unexpectedly Passed Tests (1)
# CHECK: Passed : 6
# CHECK: Expectedly Failed : 4
# CHECK: Unresolved : 3
-# CHECK: Failed : 3
+# CHECK: Failed : 4
# CHECK: Unexpectedly Passed: 1
# XUNIT: <?xml version="1.0" encoding="UTF-8"?>
# XUNIT-NEXT: <testsuites time="{{[0-9.]+}}">
-# XUNIT-NEXT: <testsuite name="shtest-format" tests="21" failures="7" skipped="4">
+# XUNIT-NEXT: <testsuite name="shtest-format" tests="22" failures="8" skipped="4">
# XUNIT: <testcase classname="shtest-format.external_shell" name="fail.txt" time="{{[0-9]+\.[0-9]+}}">
# XUNIT-NEXT: <failure{{[ ]*}}>
# XUNIT: </failure>
# XUNIT-NEXT: </testcase>
+# XUNIT: <testcase classname="shtest-format.external_shell" name="fail_with_control_chars.txt" time="{{[0-9]+\.[0-9]+}}">
+# XUNIT-NEXT: <failure><![CDATA[Script:
+# XUNIT: Command Output (stdout):
+# XUNIT-NEXT: --
+# XUNIT-NEXT: a line with [2;30;41mcontrol characters[0m.
+# XUNIT: </failure>
+# XUNIT-NEXT: </testcase>
+
# XUNIT: <testcase classname="shtest-format.external_shell" name="pass.txt" time="{{[0-9]+\.[0-9]+}}"/>
# XUNIT: <testcase classname="shtest-format.shtest-format" name="fail.txt" time="{{[0-9]+\.[0-9]+}}">