Skip to content

REF: Deduplicate to_xml code #45132

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
Jan 1, 2022
Merged

REF: Deduplicate to_xml code #45132

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
f991d2c
REF: Deduplicate to_xml code
phofl Dec 30, 2021
0d6ee97
Merge branch 'master' of https://github.com/pandas-dev/pandas into re…
phofl Dec 30, 2021
97a6168
Refactor to fix mypy
phofl Dec 30, 2021
97b90f1
Return value
phofl Dec 30, 2021
8e2d899
Return value
phofl Dec 30, 2021
2991eec
Adjust type hints
phofl Dec 31, 2021
1632c83
Adjust code
phofl Dec 31, 2021
aac9d31
Add hint
phofl Dec 31, 2021
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
4 changes: 2 additions & 2 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2948,8 +2948,8 @@ def to_xml(
root_name: str | None = "data",
row_name: str | None = "row",
na_rep: str | None = None,
attr_cols: str | list[str] | None = None,
elem_cols: str | list[str] | None = None,
attr_cols: list[str] | None = None,
elem_cols: list[str] | None = None,
namespaces: dict[str | None, str] | None = None,
prefix: str | None = None,
encoding: str = "utf-8",
Expand Down
188 changes: 60 additions & 128 deletions pandas/io/formats/xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,6 @@
from pandas._typing import (
CompressionOptions,
FilePath,
ReadBuffer,
StorageOptions,
WriteBuffer,
)
Expand Down Expand Up @@ -96,8 +95,8 @@ class BaseXMLFormatter:
def __init__(
self,
frame: DataFrame,
path_or_buffer: FilePath | WriteBuffer[bytes] | None = None,
index: bool | None = True,
path_or_buffer: FilePath | WriteBuffer[bytes] | WriteBuffer[str] | None = None,
index: bool = True,
root_name: str | None = "data",
row_name: str | None = "row",
na_rep: str | None = None,
Expand All @@ -108,7 +107,7 @@ def __init__(
encoding: str = "utf-8",
xml_declaration: bool | None = True,
pretty_print: bool | None = True,
stylesheet: FilePath | ReadBuffer[str] | None = None,
stylesheet: FilePath | WriteBuffer[bytes] | WriteBuffer[str] | None = None,
compression: CompressionOptions = "infer",
storage_options: StorageOptions = None,
) -> None:
Expand All @@ -132,6 +131,11 @@ def __init__(
self.orig_cols = self.frame.columns.tolist()
self.frame_dicts = self.process_dataframe()

self.validate_columns()
self.validate_encoding()
self.prefix_uri = self.get_prefix_uri()
self.handle_indexes()

def build_tree(self) -> bytes:
"""
Build tree from data.
Expand Down Expand Up @@ -189,8 +193,8 @@ def process_dataframe(self) -> dict[int | str, dict[str, Any]]:
if self.index:
df = df.reset_index()

if self.na_rep:
df = df.replace({None: self.na_rep, float("nan"): self.na_rep})
if self.na_rep is not None:
df = df.fillna(self.na_rep)

return df.to_dict(orient="index")

Expand Down Expand Up @@ -247,17 +251,37 @@ def other_namespaces(self) -> dict:

return nmsp_dict

def build_attribs(self) -> None:
def build_attribs(self, d: dict[str, Any], elem_row: Any) -> None:
"""
Create attributes of row.

This method adds attributes using attr_cols to row element and
works with tuples for multindex or hierarchical columns.
"""

raise AbstractMethodError(self)
if not self.attr_cols:
return

def build_elems(self) -> None:
for col in self.attr_cols:
attr_name = self._get_flat_col_name(col)
try:
val = None if isna(d[col]) else str(d[col])
if val is not None:
elem_row.attrib[attr_name] = val
Copy link
Contributor

Choose a reason for hiding this comment

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

should this be copied?

Copy link
Contributor

Choose a reason for hiding this comment

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

Maybe avoid val? (This change came on last recent to_xml PR).

if not isna(d[col]):
    elem_row.attrib[attr_name] = str(d[col])

Copy link
Member Author

Choose a reason for hiding this comment

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

Yep thx, this sounds good

except KeyError:
raise KeyError(f"no valid column, {col}")

def _get_flat_col_name(self, col: str | tuple) -> str:
flat_col = col
if isinstance(col, tuple):
flat_col = (
"".join([str(c) for c in col]).strip()
if "" in col
else "_".join([str(c) for c in col]).strip()
)
return f"{self.prefix_uri}{flat_col}"

def build_elems(self, d: dict[str, Any], elem_row: Any) -> None:
"""
Create child elements of row.

Expand All @@ -267,6 +291,19 @@ def build_elems(self) -> None:

raise AbstractMethodError(self)

def _build_elems(self, sub_element_cls, d: dict[str, Any], elem_row: Any) -> None:

if not self.elem_cols:
return

for col in self.elem_cols:
elem_name = self._get_flat_col_name(col)
try:
val = None if isna(d[col]) or d[col] == "" else str(d[col])
sub_element_cls(elem_row, elem_name).text = val
except KeyError:
raise KeyError(f"no valid column, {col}")

def write_output(self) -> str | None:
xml_doc = self.build_tree()

Expand All @@ -291,14 +328,6 @@ class EtreeXMLFormatter(BaseXMLFormatter):
modules: `xml.etree.ElementTree` and `xml.dom.minidom`.
"""

def __init__(self, *args, **kwargs) -> None:
super().__init__(*args, **kwargs)

self.validate_columns()
self.validate_encoding()
self.handle_indexes()
self.prefix_uri = self.get_prefix_uri()

def build_tree(self) -> bytes:
from xml.etree.ElementTree import (
Element,
Expand All @@ -311,16 +340,15 @@ def build_tree(self) -> bytes:
)

for d in self.frame_dicts.values():
self.d = d
self.elem_row = SubElement(self.root, f"{self.prefix_uri}{self.row_name}")
elem_row = SubElement(self.root, f"{self.prefix_uri}{self.row_name}")

if not self.attr_cols and not self.elem_cols:
self.elem_cols = list(self.d.keys())
self.build_elems()
self.elem_cols = list(d.keys())
self.build_elems(d, elem_row)

else:
self.build_attribs()
self.build_elems()
self.build_attribs(d, elem_row)
self.build_elems(d, elem_row)

self.out_xml = tostring(self.root, method="xml", encoding=self.encoding)

Expand Down Expand Up @@ -357,56 +385,10 @@ def get_prefix_uri(self) -> str:

return uri

def build_attribs(self) -> None:
if not self.attr_cols:
return

for col in self.attr_cols:
flat_col = col
if isinstance(col, tuple):
flat_col = (
"".join([str(c) for c in col]).strip()
if "" in col
else "_".join([str(c) for c in col]).strip()
)

attr_name = f"{self.prefix_uri}{flat_col}"
try:
val = (
None
if self.d[col] is None or self.d[col] != self.d[col]
else str(self.d[col])
)
if val is not None:
self.elem_row.attrib[attr_name] = val
except KeyError:
raise KeyError(f"no valid column, {col}")

def build_elems(self) -> None:
def build_elems(self, d: dict[str, Any], elem_row: Any) -> None:
from xml.etree.ElementTree import SubElement

if not self.elem_cols:
return

for col in self.elem_cols:
flat_col = col
if isinstance(col, tuple):
flat_col = (
"".join([str(c) for c in col]).strip()
if "" in col
else "_".join([str(c) for c in col]).strip()
)

elem_name = f"{self.prefix_uri}{flat_col}"
try:
val = (
None
if self.d[col] in [None, ""] or self.d[col] != self.d[col]
else str(self.d[col])
)
SubElement(self.elem_row, elem_name).text = val
except KeyError:
raise KeyError(f"no valid column, {col}")
self._build_elems(SubElement, d, elem_row)

def prettify_tree(self) -> bytes:
"""
Expand Down Expand Up @@ -458,12 +440,7 @@ class LxmlXMLFormatter(BaseXMLFormatter):
def __init__(self, *args, **kwargs) -> None:
super().__init__(*args, **kwargs)

self.validate_columns()
self.validate_encoding()
self.prefix_uri = self.get_prefix_uri()

self.convert_empty_str_key()
self.handle_indexes()

def build_tree(self) -> bytes:
"""
Expand All @@ -481,16 +458,15 @@ def build_tree(self) -> bytes:
self.root = Element(f"{self.prefix_uri}{self.root_name}", nsmap=self.namespaces)

for d in self.frame_dicts.values():
self.d = d
self.elem_row = SubElement(self.root, f"{self.prefix_uri}{self.row_name}")
elem_row = SubElement(self.root, f"{self.prefix_uri}{self.row_name}")

if not self.attr_cols and not self.elem_cols:
self.elem_cols = list(self.d.keys())
self.build_elems()
self.elem_cols = list(d.keys())
self.build_elems(d, elem_row)

else:
self.build_attribs()
self.build_elems()
self.build_attribs(d, elem_row)
self.build_elems(d, elem_row)

self.out_xml = tostring(
self.root,
Expand Down Expand Up @@ -529,54 +505,10 @@ def get_prefix_uri(self) -> str:

return uri

def build_attribs(self) -> None:
if not self.attr_cols:
return

for col in self.attr_cols:
flat_col = col
if isinstance(col, tuple):
flat_col = (
"".join([str(c) for c in col]).strip()
if "" in col
else "_".join([str(c) for c in col]).strip()
)

attr_name = f"{self.prefix_uri}{flat_col}"
try:
val = (
None
if self.d[col] is None or self.d[col] != self.d[col]
else str(self.d[col])
)
if val is not None:
self.elem_row.attrib[attr_name] = val
except KeyError:
raise KeyError(f"no valid column, {col}")

def build_elems(self) -> None:
def build_elems(self, d: dict[str, Any], elem_row: Any) -> None:
from lxml.etree import SubElement

if not self.elem_cols:
return

for col in self.elem_cols:
flat_col = col
if isinstance(col, tuple):
flat_col = (
"".join([str(c) for c in col]).strip()
if "" in col
else "_".join([str(c) for c in col]).strip()
)

elem_name = f"{self.prefix_uri}{flat_col}"
try:
val = (
None if isna(self.d[col]) or self.d[col] == "" else str(self.d[col])
)
SubElement(self.elem_row, elem_name).text = val
except KeyError:
raise KeyError(f"no valid column, {col}")
self._build_elems(SubElement, d, elem_row)

def transform_doc(self) -> bytes:
"""
Expand Down
17 changes: 11 additions & 6 deletions pandas/io/xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
FilePath,
ReadBuffer,
StorageOptions,
WriteBuffer,
)
from pandas.compat._optional import import_optional_dependency
from pandas.errors import (
Expand Down Expand Up @@ -569,11 +570,18 @@ def _transform_doc(self) -> bytes:


def get_data_from_filepath(
filepath_or_buffer: FilePath | bytes | ReadBuffer[bytes] | ReadBuffer[str],
filepath_or_buffer: FilePath
| bytes
| ReadBuffer[bytes]
| ReadBuffer[str]
| WriteBuffer[bytes]
| WriteBuffer[str],
encoding,
compression: CompressionOptions,
storage_options: StorageOptions,
) -> str | bytes | ReadBuffer[bytes] | ReadBuffer[str]:
) -> str | bytes | ReadBuffer[bytes] | ReadBuffer[str] | WriteBuffer[
bytes
] | WriteBuffer[str]:
"""
Extract raw XML data.

Expand Down Expand Up @@ -605,10 +613,7 @@ def get_data_from_filepath(
storage_options=storage_options,
) as handle_obj:
filepath_or_buffer = (
# error: Incompatible types in assignment (expression has type
# "Union[str, IO[str]]", variable has type "Union[Union[str,
# PathLike[str]], bytes, ReadBuffer[bytes], ReadBuffer[str]]")
handle_obj.handle.read() # type: ignore[assignment]
handle_obj.handle.read()
if hasattr(handle_obj.handle, "read")
else handle_obj.handle
)
Expand Down
6 changes: 3 additions & 3 deletions pandas/tests/io/xml/test_to_xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1309,7 +1309,7 @@ def test_filename_and_suffix_comp(parser, compression_only):


@td.skip_if_no("lxml")
def test_ea_dtypes(any_numeric_ea_dtype):
def test_ea_dtypes(any_numeric_ea_dtype, parser):
# GH#43903
expected = """<?xml version='1.0' encoding='utf-8'?>
<data>
Expand All @@ -1319,8 +1319,8 @@ def test_ea_dtypes(any_numeric_ea_dtype):
</row>
</data>"""
df = DataFrame({"a": [NA]}).astype(any_numeric_ea_dtype)
result = df.to_xml()
assert result.strip() == expected
result = df.to_xml(parser=parser)
assert equalize_decl(result).strip() == expected


def test_unsuported_compression(datapath, parser):
Expand Down