[PR #12148/5004c9f7 backport][stable-13] xml: preserve DOCTYPE declaration when writing XML files (#12249)

xml: preserve DOCTYPE declaration when writing XML files (#12148)

* fix(xml): preserve DOCTYPE declaration when writing XML files

Pass `doctype=tree.docinfo.doctype` to all `ElementTree.write()` calls
so lxml does not silently drop the DOCTYPE on serialization. Also replace
`etree.tostring()` with BytesIO+write() in the diff and xmlstring paths
for consistency.

Fixes #2762



* test(xml): add integration test for DOCTYPE preservation



* feat(changelog): add fragment for xml DOCTYPE fix (#12148)



---------


(cherry picked from commit 5004c9f70f)

Co-authored-by: Alexei Znamensky <103110+russoz@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

changelogs/fragments/12148-xml-preserve-doctype.yml

@@ -0,0 +1,2 @@
+bugfixes:
+  - "xml - preserve DOCTYPE declaration when writing modified XML files (https://github.com/ansible-collections/community.general/issues/2762, https://github.com/ansible-collections/community.general/pull/12148)."

plugins/modules/xml.py

@@ -813,9 +813,15 @@ def children_to_nodes(module=None, children=None, type="yaml"):
 
 
 def make_pretty(module, tree):
-    xml_string = etree.tostring(
-        tree, xml_declaration=True, encoding="UTF-8", pretty_print=module.params["pretty_print"]
+    buf = BytesIO()
+    tree.write(
+        buf,
+        xml_declaration=True,
+        encoding="UTF-8",
+        pretty_print=module.params["pretty_print"],
+        doctype=tree.docinfo.doctype or None,
     )
+    xml_string = buf.getvalue()
 
     result = dict(
         changed=False,
@@ -830,7 +836,11 @@ def make_pretty(module, tree):
                     if module.params["backup"]:
                         result["backup_file"] = module.backup_local(module.params["path"])
                     tree.write(
-                        xml_file, xml_declaration=True, encoding="UTF-8", pretty_print=module.params["pretty_print"]
+                        xml_file,
+                        xml_declaration=True,
+                        encoding="UTF-8",
+                        pretty_print=module.params["pretty_print"],
+                        doctype=tree.docinfo.doctype or None,
                     )
 
     elif module.params["xmlstring"]:
@@ -859,10 +869,23 @@ def finish(module, tree, xpath, namespaces, changed=False, msg="", hitcount=0, m
 
     if result["changed"]:
         if module._diff:
-            result["diff"] = dict(
-                before=etree.tostring(orig_doc, xml_declaration=True, encoding="UTF-8", pretty_print=True),
-                after=etree.tostring(tree, xml_declaration=True, encoding="UTF-8", pretty_print=True),
+            before_buf = BytesIO()
+            orig_doc.write(
+                before_buf,
+                xml_declaration=True,
+                encoding="UTF-8",
+                pretty_print=True,
+                doctype=orig_doc.docinfo.doctype or None,
             )
+            after_buf = BytesIO()
+            tree.write(
+                after_buf,
+                xml_declaration=True,
+                encoding="UTF-8",
+                pretty_print=True,
+                doctype=tree.docinfo.doctype or None,
+            )
+            result["diff"] = dict(before=before_buf.getvalue(), after=after_buf.getvalue())
 
         if module.params["path"] and not module.check_mode:
             if module.params["backup"]:
@@ -872,12 +895,19 @@ def finish(module, tree, xpath, namespaces, changed=False, msg="", hitcount=0, m
                 xml_declaration=True,
                 encoding="UTF-8",
                 pretty_print=module.params["pretty_print"],
+                doctype=tree.docinfo.doctype or None,
             )
 
     if module.params["xmlstring"]:
-        result["xmlstring"] = etree.tostring(
-            tree, xml_declaration=True, encoding="UTF-8", pretty_print=module.params["pretty_print"]
+        xmlstring_buf = BytesIO()
+        tree.write(
+            xmlstring_buf,
+            xml_declaration=True,
+            encoding="UTF-8",
+            pretty_print=module.params["pretty_print"],
+            doctype=tree.docinfo.doctype or None,
         )
+        result["xmlstring"] = xmlstring_buf.getvalue()
 
     module.exit_json(**result)
 

tests/integration/targets/xml/fixtures/ansible-xml-doctype.xml

@@ -0,0 +1,3 @@
+<?xml version='1.0' encoding='UTF-8'?>
+<!DOCTYPE foo SYSTEM "foo.dtd">
+<foo value="0"/>

tests/integration/targets/xml/fixtures/ansible-xml-doctype.xml.license

@@ -0,0 +1,3 @@
+GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
+SPDX-License-Identifier: GPL-3.0-or-later
+SPDX-FileCopyrightText: Ansible Project

tests/integration/targets/xml/results/test-preserve-doctype.xml

@@ -0,0 +1,3 @@
+<?xml version='1.0' encoding='UTF-8'?>
+<!DOCTYPE foo SYSTEM "foo.dtd">
+<foo value="1"/>

tests/integration/targets/xml/results/test-preserve-doctype.xml.license

@@ -0,0 +1,3 @@
+GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
+SPDX-License-Identifier: GPL-3.0-or-later
+SPDX-FileCopyrightText: Ansible Project

tests/integration/targets/xml/tasks/main.yml

@@ -79,6 +79,7 @@
     - include_tasks: test-print-match.yml
     - include_tasks: test-xmlstring.yml
     - include_tasks: test-children-elements-xml.yml
+    - include_tasks: test-preserve-doctype.yml
 
     # Unicode tests
     - include_tasks: test-add-children-elements-unicode.yml

tests/integration/targets/xml/tasks/test-preserve-doctype.yml

@@ -0,0 +1,46 @@
+# Copyright (c) Ansible Project
+# GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+- name: Setup test fixture
+  copy:
+    src: fixtures/ansible-xml-doctype.xml
+    dest: /tmp/ansible-xml-doctype.xml
+
+- name: Set '/foo/@value' to '1' (file has DOCTYPE)
+  xml:
+    path: /tmp/ansible-xml-doctype.xml
+    xpath: /foo
+    attribute: value
+    value: "1"
+  register: set_attribute_doctype
+
+- name: Add trailing newline
+  shell: echo "" >> /tmp/ansible-xml-doctype.xml
+
+- name: Compare to expected result
+  copy:
+    src: results/test-preserve-doctype.xml
+    dest: /tmp/ansible-xml-doctype.xml
+  check_mode: true
+  diff: true
+  register: comparison
+
+- name: Test expected result (DOCTYPE is preserved)
+  assert:
+    that:
+      - set_attribute_doctype is changed
+      - comparison is not changed
+
+- name: Set '/foo/@value' to '1' again (idempotency)
+  xml:
+    path: /tmp/ansible-xml-doctype.xml
+    xpath: /foo
+    attribute: value
+    value: "1"
+  register: set_attribute_doctype_idempotent
+
+- name: Test idempotency
+  assert:
+    that:
+      - set_attribute_doctype_idempotent is not changed