gh-50002: xml.dom.minidom now preserves whitespaces in attributes (GH-107947)

Also double quotes (") are now only quoted in attributes.

1 files changed, 23 insertions, 7 deletions

diff --git a/Lib/xml/dom/minidom.py b/Lib/xml/dom/minidom.py
index ef8a159..db51f35 100644
--- a/Lib/xml/dom/minidom.py
+++ b/Lib/xml/dom/minidom.py
@@ -300,12 +300,28 @@ def _in_document(node):
         node = node.parentNode
     return False
 
-def _write_data(writer, data):
+def _write_data(writer, text, attr):
     "Writes datachars to writer."
-    if data:
-        data = data.replace("&", "&amp;").replace("<", "&lt;"). \
-                    replace("\"", "&quot;").replace(">", "&gt;")
-        writer.write(data)
+    if not text:
+        return
+    # See the comments in ElementTree.py for behavior and
+    # implementation details.
+    if "&" in text:
+        text = text.replace("&", "&amp;")
+    if "<" in text:
+        text = text.replace("<", "&lt;")
+    if ">" in text:
+        text = text.replace(">", "&gt;")
+    if attr:
+        if '"' in text:
+            text = text.replace('"', "&quot;")
+        if "\r" in text:
+            text = text.replace("\r", "&#13;")
+        if "\n" in text:
+            text = text.replace("\n", "&#10;")
+        if "\t" in text:
+            text = text.replace("\t", "&#9;")
+    writer.write(text)
 
 def _get_elements_by_tagName_helper(parent, name, rc):
     for node in parent.childNodes:
@@ -883,7 +899,7 @@ class Element(Node):
 
         for a_name in attrs.keys():
             writer.write(" %s=\"" % a_name)
-            _write_data(writer, attrs[a_name].value)
+            _write_data(writer, attrs[a_name].value, True)
             writer.write("\"")
         if self.childNodes:
             writer.write(">")
@@ -1112,7 +1128,7 @@ class Text(CharacterData):
         return newText
 
     def writexml(self, writer, indent="", addindent="", newl=""):
-        _write_data(writer, "%s%s%s" % (indent, self.data, newl))
+        _write_data(writer, "%s%s%s" % (indent, self.data, newl), False)
 
     # DOM Level 3 (WD 9 April 2002)