From b936539ae1d6b970a75a3b88e0dd7d11b36cb0e9 Mon Sep 17 00:00:00 2001
From: Jordan Borean <jborean93@gmail.com>
Date: Sat, 29 Aug 2020 02:54:14 +1000
Subject: [PATCH] powershell - fix nested CLIXML parser (#71412) (#71451)

(cherry picked from commit 8897d7e2ff8fa37c25cd4ba039984fd3a9e13b33)
---
 .../fragments/powershell-nested-clixml.yml    |  2 ++
 lib/ansible/plugins/shell/powershell.py       | 22 ++++++++++++++-----
 test/units/plugins/shell/test_powershell.py   | 19 ++++++++++++++++
 3 files changed, 38 insertions(+), 5 deletions(-)
 create mode 100644 changelogs/fragments/powershell-nested-clixml.yml

diff --git a/changelogs/fragments/powershell-nested-clixml.yml b/changelogs/fragments/powershell-nested-clixml.yml
new file mode 100644
index 00000000000..27ce42727e8
--- /dev/null
+++ b/changelogs/fragments/powershell-nested-clixml.yml
@@ -0,0 +1,2 @@
+bugfixes:
+- powershell - fix the CLIXML parser when it contains nested CLIXML objects - https://github.com/ansible/ansible/issues/69550
diff --git a/lib/ansible/plugins/shell/powershell.py b/lib/ansible/plugins/shell/powershell.py
index f504b16dd95..d8c2e836d3c 100644
--- a/lib/ansible/plugins/shell/powershell.py
+++ b/lib/ansible/plugins/shell/powershell.py
@@ -43,12 +43,24 @@ def _parse_clixml(data, stream="Error"):
     message encoded in the XML data. CLIXML is used by PowerShell to encode
     multiple objects in stderr.
     """
-    clixml = ET.fromstring(data.split(b"\r\n", 1)[-1])
-    namespace_match = re.match(r'{(.*)}', clixml.tag)
-    namespace = "{%s}" % namespace_match.group(1) if namespace_match else ""
+    lines = []
+
+    # There are some scenarios where the stderr contains a nested CLIXML element like
+    # '<# CLIXML\r\n<# CLIXML\r\n<Objs>...</Objs><Objs>...</Objs>'.
+    # Parse each individual <Objs> element and add the error strings to our stderr list.
+    # https://github.com/ansible/ansible/issues/69550
+    while data:
+        end_idx = data.find(b"</Objs>") + 7
+        current_element = data[data.find(b"<Objs "):end_idx]
+        data = data[end_idx:]
+
+        clixml = ET.fromstring(current_element)
+        namespace_match = re.match(r'{(.*)}', clixml.tag)
+        namespace = "{%s}" % namespace_match.group(1) if namespace_match else ""
+
+        strings = clixml.findall("./%sS" % namespace)
+        lines.extend([e.text.replace('_x000D__x000A_', '') for e in strings if e.attrib.get('S') == stream])
 
-    strings = clixml.findall("./%sS" % namespace)
-    lines = [e.text.replace('_x000D__x000A_', '') for e in strings if e.attrib.get('S') == stream]
     return to_bytes('\r\n'.join(lines))
 
 
diff --git a/test/units/plugins/shell/test_powershell.py b/test/units/plugins/shell/test_powershell.py
index 2d9997147f8..c94baabbc7c 100644
--- a/test/units/plugins/shell/test_powershell.py
+++ b/test/units/plugins/shell/test_powershell.py
@@ -56,6 +56,25 @@ def test_parse_clixml_multiple_streams():
     assert actual == expected
 
 
+def test_parse_clixml_multiple_elements():
+    multiple_elements = b'#< CLIXML\r\n#< CLIXML\r\n<Objs Version="1.1.0.1" xmlns="http://schemas.microsoft.com/powershell/2004/04">' \
+                        b'<Obj S="progress" RefId="0"><TN RefId="0"><T>System.Management.Automation.PSCustomObject</T><T>System.Object</T></TN><MS>' \
+                        b'<I64 N="SourceId">1</I64><PR N="Record"><AV>Preparing modules for first use.</AV><AI>0</AI><Nil />' \
+                        b'<PI>-1</PI><PC>-1</PC><T>Completed</T><SR>-1</SR><SD> </SD></PR></MS></Obj>' \
+                        b'<S S="Error">Error 1</S></Objs>' \
+                        b'<Objs Version="1.1.0.1" xmlns="http://schemas.microsoft.com/powershell/2004/04"><Obj S="progress" RefId="0">' \
+                        b'<TN RefId="0"><T>System.Management.Automation.PSCustomObject</T><T>System.Object</T></TN><MS>' \
+                        b'<I64 N="SourceId">1</I64><PR N="Record"><AV>Preparing modules for first use.</AV><AI>0</AI><Nil />' \
+                        b'<PI>-1</PI><PC>-1</PC><T>Completed</T><SR>-1</SR><SD> </SD></PR></MS></Obj>' \
+                        b'<Obj S="progress" RefId="1"><TNRef RefId="0" /><MS><I64 N="SourceId">2</I64>' \
+                        b'<PR N="Record"><AV>Preparing modules for first use.</AV><AI>0</AI><Nil />' \
+                        b'<PI>-1</PI><PC>-1</PC><T>Completed</T><SR>-1</SR><SD> </SD></PR></MS></Obj>' \
+                        b'<S S="Error">Error 2</S></Objs>'
+    expected = b"Error 1\r\nError 2"
+    actual = _parse_clixml(multiple_elements)
+    assert actual == expected
+
+
 def test_join_path_unc():
     pwsh = ShellModule()
     unc_path_parts = ['\\\\host\\share\\dir1\\\\dir2\\', '\\dir3/dir4', 'dir5', 'dir6\\']