Skip to content

BUG: iterparse of read_xml not parsing duplicate element and attribute names #47414

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Jun 21, 2022
Merged

BUG: iterparse of read_xml not parsing duplicate element and attribute names #47414

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
4aa32cc
BUG: iterparse of read_xml not parsing duplicate element and attribut…
ParfaitG Jun 18, 2022
4a1a2a0
Merge remote-tracking branch 'upstream/main' into iterparse_names
ParfaitG Jun 18, 2022
65c09d5
Refactor duplicative code in each parser to shared base class
ParfaitG Jun 18, 2022
29211b5
Merge remote-tracking branch 'upstream/main' into iterparse_names
ParfaitG Jun 18, 2022
3c241d5
Add lxml preceding-sibling iterparse cleanup
ParfaitG Jun 19, 2022
d73b32f
Revert code refactoring back to bug fix only
ParfaitG Jun 20, 2022
35bc554
Remove whatsnew bug fix note on unreleased version feature
ParfaitG Jun 21, 2022
0379764
Merge remote-tracking branch 'upstream/main' into iterparse_names
ParfaitG Jun 21, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 32 additions & 11 deletions pandas/io/xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -413,11 +413,21 @@ def _iterparse_nodes(self) -> list[dict[str, str | None]]:
row = {}

if row is not None:
for col in self.iterparse[row_node]:
if curr_elem == col:
row[col] = elem.text.strip() if elem.text else None
if col in elem.attrib:
row[col] = elem.attrib[col]
if self.names:
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you share this?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good point. I refactored to use code once in base class of the parsers.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a bit confusing now. Could you split the refactoring and the bug fix into 2 prs? Hard to review like this

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will revert back to bug fix only and on subsequent PR refactor to remove repetitive code between parsers.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks.

I was not sure if you could share more initially, but if you can share most of the code than we can separate these

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:
row[nm] = elem_val
if col in elem.attrib:
if elem.attrib[col] not in row.values() and nm not in row:
row[nm] = elem.attrib[col]
else:
for col in self.iterparse[row_node]:
if curr_elem == col:
row[col] = elem.text.strip() if elem.text else None
if col in elem.attrib:
row[col] = elem.attrib[col]

if event == "end":
if curr_elem == row_node and row is not None:
Expand Down Expand Up @@ -661,11 +671,21 @@ def _iterparse_nodes(self) -> list[dict[str, str | None]]:
row = {}

if row is not None:
for col in self.iterparse[row_node]:
if curr_elem == col:
row[col] = elem.text.strip() if elem.text else None
if col in elem.attrib:
row[col] = elem.attrib[col]
if self.names:
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:
row[nm] = elem_val
if col in elem.attrib:
if elem.attrib[col] not in row.values() and nm not in row:
row[nm] = elem.attrib[col]
else:
for col in self.iterparse[row_node]:
if curr_elem == col:
row[col] = elem.text.strip() if elem.text else None
if col in elem.attrib:
row[col] = elem.attrib[col]

if event == "end":
if curr_elem == row_node and row is not None:
Expand Down Expand Up @@ -1020,7 +1040,8 @@ def read_xml(
names : list-like, optional
Column names for DataFrame of parsed XML data. Use this parameter to
rename original element names and distinguish same named elements.
rename original element names and distinguish same named elements and
attributes.
dtype : Type name or dict of column -> type, optional
Data type for data or columns. E.g. {{'a': np.float64, 'b': np.int32,
Expand Down
35 changes: 35 additions & 0 deletions pandas/tests/io/xml/test_xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -789,6 +789,41 @@ def test_names_option_output(datapath, parser):
tm.assert_frame_equal(df_iter, df_expected)


def test_repeat_names(parser):
xml = """\
<shapes>
<shape type="2D">
<name>circle</name>
<type>curved</type>
</shape>
<shape type="3D">
<name>sphere</name>
<type>curved</type>
</shape>
</shapes>"""
df_xpath = read_xml(
xml, xpath=".//shape", parser=parser, names=["type_dim", "shape", "type_edge"]
)

df_iter = read_xml_iterparse(
xml,
parser=parser,
iterparse={"shape": ["type", "name", "type"]},
names=["type_dim", "shape", "type_edge"],
)

df_expected = DataFrame(
{
"type_dim": ["2D", "3D"],
"shape": ["circle", "sphere"],
"type_edge": ["curved", "curved"],
}
)

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")

Expand Down