#4147: merge with 3.2.

Lib/test/test_minidom.py

@@ -467,12 +467,39 @@ class MinidomTest(unittest.TestCase):
         dom.unlink()
         self.confirm(domstr == str.replace("\n", "\r\n"))
 
+    def test_toprettyxml_with_text_nodes(self):
+        # see issue #4147, text nodes are not indented
+        decl = '<?xml version="1.0" ?>\n'
+        self.assertEqual(parseString('<B>A</B>').toprettyxml(),
+                         decl + '<B>A</B>\n')
+        self.assertEqual(parseString('<C>A<B>A</B></C>').toprettyxml(),
+                         decl + '<C>\n\tA\n\t<B>A</B>\n</C>\n')
+        self.assertEqual(parseString('<C><B>A</B>A</C>').toprettyxml(),
+                         decl + '<C>\n\t<B>A</B>\n\tA\n</C>\n')
+        self.assertEqual(parseString('<C><B>A</B><B>A</B></C>').toprettyxml(),
+                         decl + '<C>\n\t<B>A</B>\n\t<B>A</B>\n</C>\n')
+        self.assertEqual(parseString('<C><B>A</B>A<B>A</B></C>').toprettyxml(),
+                         decl + '<C>\n\t<B>A</B>\n\tA\n\t<B>A</B>\n</C>\n')
+
+    def test_toprettyxml_with_adjacent_text_nodes(self):
+        # see issue #4147, adjacent text nodes are indented normally
+        dom = Document()
+        elem = dom.createElement('elem')
+        elem.appendChild(dom.createTextNode('TEXT'))
+        elem.appendChild(dom.createTextNode('TEXT'))
+        dom.appendChild(elem)
+        decl = '<?xml version="1.0" ?>\n'
+        self.assertEqual(dom.toprettyxml(),
+                         decl + '<elem>\n\tTEXT\n\tTEXT\n</elem>\n')
+
     def test_toprettyxml_preserves_content_of_text_node(self):
-        str = '<A>B</A>'
-        dom = parseString(str)
-        dom2 = parseString(dom.toprettyxml())
-        self.assertEqual(dom.childNodes[0].childNodes[0].toxml(),
-                         dom2.childNodes[0].childNodes[0].toxml())
+        # see issue #4147
+        for str in ('<B>A</B>', '<A><B>C</B></A>'):
+            dom = parseString(str)
+            dom2 = parseString(dom.toprettyxml())
+            self.assertEqual(
+                dom.getElementsByTagName('B')[0].childNodes[0].toxml(),
+                dom2.getElementsByTagName('B')[0].childNodes[0].toxml())
 
     def testProcessingInstruction(self):
         dom = parseString('<e><?mypi \t\n data \t\n ?></e>')

Lib/xml/dom/minidom.py

@@ -837,11 +837,15 @@ class Element(Node):
             writer.write("\"")
         if self.childNodes:
             writer.write(">")
-            if self.childNodes[0].nodeType != Node.TEXT_NODE:
+            if (len(self.childNodes) == 1 and
+                self.childNodes[0].nodeType == Node.TEXT_NODE):
+                self.childNodes[0].writexml(writer, '', '', '')
+            else:
                 writer.write(newl)
-            for node in self.childNodes:
-                node.writexml(writer,indent+addindent,addindent,newl)
-            writer.write("%s</%s>%s" % (indent,self.tagName,newl))
+                for node in self.childNodes:
+                    node.writexml(writer, indent+addindent, addindent, newl)
+                writer.write(indent)
+            writer.write("</%s>%s" % (self.tagName, newl))
         else:
             writer.write("/>%s"%(newl))
 
@@ -1063,7 +1067,7 @@ class Text(CharacterData):
         return newText
 
     def writexml(self, writer, indent="", addindent="", newl=""):
-        _write_data(writer, self.data)
+        _write_data(writer, "%s%s%s" % (indent, self.data, newl))
 
     # DOM Level 3 (WD 9 April 2002)
 

Misc/NEWS

@@ -377,6 +377,10 @@ Core and Builtins
 Library
 -------
 
+- Issue #4147: minidom's toprettyxml no longer adds whitespace around a text
+  node when it is the only child of an element.  Initial patch by Dan
+  Kenigsberg.
+
 - Issue #13374: The Windows bytes API has been deprecated in the os module. Use
   Unicode filenames instead of bytes filenames to not depend on the ANSI code
   page anymore and to support any filename.