BUG: using read_xml with iterparse and names will ignore duplicate values (#47630)

Author: ParfaitG

pandas/io/xml.py

@@ -342,7 +342,7 @@ def _iterparse_nodes(self, iterparse: Callable) -> list[dict[str, str | None]]:
  for col, nm in zip(self.iterparse[row_node], self.names):
  if curr_elem == col:
  elem_val = elem.text.strip() if elem.text else None
- if elem_val not in row.values() and nm not in row:
+ if row.get(nm) != elem_val and nm not in row:
  row[nm] = elem_val
  if col in elem.attrib:
  if elem.attrib[col] not in row.values() and nm not in row:

pandas/tests/io/xml/test_xml.py

@@ -824,6 +824,46 @@ def test_repeat_names(parser):
  tm.assert_frame_equal(df_iter, df_expected)
 
 
+def test_repeat_values_new_names(parser):
+ xml = """\
+<shapes>
+ <shape>
+ <name>rectangle</name>
+ <family>rectangle</family>
+ </shape>
+ <shape>
+ <name>square</name>
+ <family>rectangle</family>
+ </shape>
+ <shape>
+ <name>ellipse</name>
+ <family>ellipse</family>
+ </shape>
+ <shape>
+ <name>circle</name>
+ <family>ellipse</family>
+ </shape>
+</shapes>"""
+ df_xpath = read_xml(xml, xpath=".//shape", parser=parser, names=["name", "group"])
+
+ df_iter = read_xml_iterparse(
+ xml,
+ parser=parser,
+ iterparse={"shape": ["name", "family"]},
+ names=["name", "group"],
+ )
+
+ df_expected = DataFrame(
+ {
+ "name": ["rectangle", "square", "ellipse", "circle"],
+ "group": ["rectangle", "rectangle", "ellipse", "ellipse"],
+ }
+ )
+
+ tm.assert_frame_equal(df_xpath, df_expected)
+ tm.assert_frame_equal(df_iter, df_expected)
+
+
 def test_names_option_wrong_length(datapath, parser):
  filename = datapath("io", "data", "xml", "books.xml")