.fods parser correction for hyperlinks

Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6.
- [Release notes](https://github.com/actions/checkout/releases)
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/checkout/compare/v5...v6)

---
updated-dependencies:
- dependency-name: actions/checkout
  dependency-version: '6'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/dependabot.yml

@@ -0,0 +1,22 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    commit-message:
+      prefix: 💚 ci
+      include: "scope"
+
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    commit-message:
+      prefix: ⬆️  dep-bump
+      include: "scope"

.github/workflows/lint_and_test.yml

@@ -0,0 +1,47 @@
+name: Lint and test
+
+on:
+  push:
+    branches: ["**"]
+  pull_request:
+    branches: [master]
+
+jobs:
+  test:
+    name: Test on ${{ matrix.python_version }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python_version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+      fail-fast: false
+
+    steps:
+      - uses: actions/checkout@v6
+      - name: Set up Python ${{ matrix.python_version }}
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python_version }}
+      - name: Install poetry
+        uses: abatilo/actions-poetry@v4
+        with:
+          poetry-version: "2.1.2"
+      - name: Configure poetry
+        run: |
+          poetry config virtualenvs.create true --local
+          poetry config virtualenvs.in-project true --local
+      - uses: actions/cache@v4
+        name: Define a cache for the virtual environment based on the dependencies lock file
+        with:
+          path: ./.venv
+          key: ${{ runner.os }}-python-${{ env.pythonLocation }}-${{ hashFiles('poetry.lock') }}-venv
+      - name: Install build dependencies
+        run: sudo apt install -y libxml2-dev libxslt-dev
+      - name: Install Dependencies
+        run: poetry install
+      - name: Lint with black
+        run: |
+          # stop the build if there are Python syntax errors or undefined names
+          poetry run black --check --diff pandas_ods_reader/ tests/
+      - name: Test with pytest
+        run: |
+          poetry run pytest tests/

.gitignore

@@ -27,3 +27,15 @@ venv/
 
 # vim config
 .vim/
+
+# Coverage
+.coverage
+
+# mypy
+.mypy_cache/
+
+# pyenv
+.python-version
+
+# mise
+mise.local.toml

.pre-commit-config.yaml

@@ -0,0 +1,5 @@
+repos:
+  - repo: https://github.com/commitizen-tools/commitizen
+    rev: v2.38.0
+    hooks:
+    - id: commitizen

MANIFEST.in

@@ -1,3 +0,0 @@
-include LICENSE.txt
-include README.md
-include pandas_ods_reader/VERSION

README.md

@@ -1,15 +1,13 @@
-pandas_ods_reader
+pandas-ods-reader
 ===
 
-Provides a function to read in an ODS file and returns a pandas DataFrame.
+Provides a function to read in a **.ods** or **.fods** file and returns a pandas DataFrame.
 
-It uses `ezodf` to read in the ods file. If a range is specified in the sheet
-to be imported, it seems that `ezodf` imports empty cells as well. Therefore,
-completely empty rows and columns are dropped from the DataFrame, before it is
-returned. Only trailing empty rows and columns are dropped.
+It uses `ezodf` to read in **.ods** files. Since **.fods** files are essentially xml, `lxml` is used to read them. The correct parser is automatically chosen based on the file's extension.
 
-If the ODS file contains duplicated column names, they will be numbered and the
-number is appended to the column name in the resulting DataFrame.
+If a range is specified in the sheet to be imported, it seems that `ezodf` imports empty cells as well. Therefore, completely empty rows and columns are dropped from the DataFrame, before it is returned. Only trailing empty rows and columns are dropped.
+
+If the ODS file contains duplicated column names, they will be numbered and the number is appended to the column name in the resulting DataFrame.
 
 Dependencies
 ---
@@ -21,7 +19,7 @@ Dependencies
 Installation
 ---
 
-`pip install pandas_ods_reader`
+`pip install pandas-ods-reader`
 
 Usage
 ---
@@ -35,7 +33,7 @@ path = "path/to/file.ods"
 df = read_ods(path)
 
 # load a sheet based on its index (1 based)
-sheet_idx = 1
+sheet_idx = 2
 df = read_ods(path, sheet_idx)
 
 # load a sheet based on its name

pandas_ods_reader/VERSION

@@ -1 +0,0 @@
-0.0.9

pandas_ods_reader/__init__.py

@@ -1,6 +1,11 @@
-import pkg_resources
+import sys
 
-from .parser import read_ods
+from .main import read_ods
+
+if sys.version_info >= (3, 8):
+    from importlib.metadata import version
+else:
+    from importlib_metadata import version
 
 
-__version__ = pkg_resources.get_distribution("pandas_ods_reader").version
+__version__ = version("pandas-ods-reader")

pandas_ods_reader/algo.py

@@ -0,0 +1,99 @@
+from collections import OrderedDict
+from pathlib import Path
+from types import ModuleType
+from typing import Any, Dict, Iterator, List, Union
+
+import pandas as pd
+
+from .utils import sanitize_df
+
+
+def get_columns_from_headers(backend: ModuleType, row: Any) -> List[str]:
+    repeat_until = -1
+    repeat_value = None
+    # columns as lists in a dictionary
+    columns = []
+    # parse the first row as column names
+    for k, cell in enumerate(row):
+        value, n_repeated = backend.get_value(cell)
+        if n_repeated > 0:
+            repeat_value = value
+            repeat_until = n_repeated + k
+        if not value and k <= repeat_until:
+            value = repeat_value
+        if k == repeat_until:
+            # reset to allow for more than one repeated column
+            repeat_until = -1
+        if value and value not in columns:
+            columns.append(value)
+        else:
+            column_name = value if value else "unnamed"
+            # add count to column name
+            idx = 1
+            while f"{column_name}.{idx}" in columns:
+                idx += 1
+            columns.append(f"{column_name}.{idx}")
+    return columns
+
+
+def get_generic_columns(row: Any) -> List[str]:
+    return [f"column.{j}" for j in range(len(row))]
+
+
+def get_columns(backend: ModuleType, row: Any, headers: bool) -> List[str]:
+    if headers:
+        return get_columns_from_headers(backend, row)
+    return get_generic_columns(row)
+
+
+def parse_data(
+    backend: ModuleType,
+    rows: Iterator[List[Any]],
+    headers: bool,
+    columns: List[str],
+    skiprows: int,
+) -> pd.DataFrame:
+    df_dict: OrderedDict[str, Any] = OrderedDict()
+    col_index: Dict[int, str] = {}
+
+    for _ in range(skiprows):
+        next(rows)
+
+    for i, row in enumerate(rows):
+        # row is a list of cells
+        if i == 0:
+            columns = columns or get_columns(backend, row, headers)
+            df_dict = OrderedDict((column, []) for column in columns)
+            # create index for the column headers
+            col_index = {j: column for j, column in enumerate(columns)}
+            if headers:
+                continue
+
+        for j, cell in enumerate(row):
+            if j < len(col_index):
+                value, _ = backend.get_value(cell, parsed=True)
+                # use header instead of column index
+                df_dict[col_index[j]].append(value)
+
+    # make sure all columns are of the same length
+    max_col_length = max(len(df_dict[col]) for col in df_dict)
+    for col in df_dict:
+        col_length = len(df_dict[col])
+        if col_length < max_col_length:
+            df_dict[col] += [None] * (max_col_length - col_length)
+
+    return pd.DataFrame(df_dict)
+
+
+def read_data(
+    backend: ModuleType,
+    file_or_path: Path,
+    sheet_id: Union[str, int],
+    headers: bool,
+    columns: List[str],
+    skiprows: int,
+) -> pd.DataFrame:
+    doc = backend.get_doc(file_or_path)
+    rows = backend.get_rows(doc, sheet_id)
+    df = parse_data(backend, rows, headers=headers, columns=columns, skiprows=skiprows)
+    return sanitize_df(df)

pandas_ods_reader/main.py

@@ -0,0 +1,49 @@
+"""Imports an ods or fods file into a DataFrame object"""
+
+from pathlib import Path
+from typing import Optional, List, Union
+
+import pandas as pd
+
+from .parsers import fods, ods
+from . import algo
+
+
+EXT_MAP = {".ods": ods, ".fods": fods}
+
+
+def read_ods(
+    file_or_path: Union[str, Path],
+    sheet: Union[str, int] = 1,
+    headers: bool = True,
+    columns: Optional[List[str]] = None,
+    skiprows: int = 0,
+) -> pd.DataFrame:
+    """
+    Read in the provided ods or .ods file and convert it to `pandas.DataFrame`.
+    Will detect the filetype based on the file's extension or fall back to
+    ods.
+
+    Args:
+        file_or_path: The path to the .ods or .fods file.
+        sheet: If `int`, the 1 based index of the sheet to be read. If `str`, the
+            name of the sheet to be read.
+        headers: If `True`, then the first row is treated as the list of column names.
+        columns: A list of column names to be used as headers.
+        skiprows: The number of rows to skip before starting to read data.
+
+    Returns:
+        The content of the specified sheet as a DataFrame.
+    """
+    path = file_or_path if isinstance(file_or_path, Path) else Path(file_or_path)
+    if not path.is_file():
+        raise FileNotFoundError(f"file {path} does not exist")
+    backend = EXT_MAP.get(path.suffix, ods)
+    return algo.read_data(
+        backend,
+        path,
+        sheet,
+        headers=headers,
+        columns=columns or [],
+        skiprows=skiprows,
+    )

pandas_ods_reader/parser.py

@@ -1,14 +0,0 @@
-"""Imports an ods or fods file into a DataFrame object"""
-from pathlib import Path
-
-from .parsers import fods, ods
-
-
-EXT_MAP = {".ods": ods, ".fods": fods}
-
-
-def read_ods(file_or_path, sheet=1, headers=True, columns=None):
-    loader = EXT_MAP.get(Path(file_or_path).suffix)
-    if not loader:
-        raise ValueError("Unknown filetype.")
-    return loader.read(file_or_path, sheet, headers=headers, columns=columns)

pandas_ods_reader/parsers/fods.py

@@ -1,9 +1,7 @@
-from collections import defaultdict
+from pathlib import Path
+from typing import Iterator, Optional, Tuple, Union
 
 from lxml import etree
-import pandas as pd
-
-from ..tools import sanitize_df
 
 
 BODY_TAG = "office:body"
@@ -18,11 +16,16 @@ TABLE_CELL_REPEATED_ATTRIB = "number-columns-repeated"
 VALUE_TYPE_ATTRIB = "value-type"
 
 
-def get_sheet(spreadsheet, sheet_id):
+def get_doc(file_or_path: Path) -> etree._ElementTree:
+    return etree.parse(str(file_or_path))
+
+
+def get_sheet(spreadsheet: etree._Element, sheet_id: Union[str, int]) -> etree._Element:
     namespaces = spreadsheet.nsmap
     if isinstance(sheet_id, str):
         sheet = spreadsheet.find(
-            f"{TABLE_TAG}[@table:name='{sheet_id}']", namespaces=namespaces
+            f"{TABLE_TAG}[@table:name='{sheet_id}']",
+            namespaces=namespaces,
         )
         if sheet is None:
             raise KeyError(f"There is no sheet named {sheet_id}.")
@@ -33,83 +36,39 @@ def get_sheet(spreadsheet, sheet_id):
     return tables[sheet_id - 1]
 
 
-def parse_columns(cells, headers=True, columns=None):
-    orig_columns = cells.pop(0) if headers else None
-    if columns is None:
-        if orig_columns:
-            repeated_val = None
-            columns = []
-            repeated_dict = defaultdict(lambda: 0)
-            for i, col in enumerate(orig_columns):
-                text = col.find(TABLE_CELL_TEXT_TAG, namespaces=col.nsmap)
-                if text is not None:
-                    value = text.text
-                elif text is None and repeated_val:
-                    value = repeated_val
-                else:
-                    value = "unnamed"
-                    idx = 1
-                    while "{}.{}".format(value, idx) in columns:
-                        idx += 1
-                    value = f"{value}.{idx}"
-                repeated = col.attrib.get(
-                    f"{{{col.nsmap[TABLE_KEY]}}}{TABLE_CELL_REPEATED_ATTRIB}"
-                )
-                if repeated:
-                    repeated_dict[value] += 1
-                    repeated_val = f"{value}.{repeated_dict[value]}"
-                column = value if value not in columns else f"{value}.{i}"
-                columns.append(column)
-        else:
-            columns = [f"column.{i}" for i in range(len(cells[0]))]
-    return columns, cells
-
-
-def parse_value(cell):
-    text = cell.find(TABLE_CELL_TEXT_TAG, namespaces=cell.nsmap)
-    is_float = (
-        cell.attrib.get(f"{{{cell.nsmap[OFFICE_KEY]}}}{VALUE_TYPE_ATTRIB}") == "float"
-    )
-    if text is None:
-        return None
-    value = text.text
-    if is_float:
-        return float(value)
-    return value
-
-
-def load_fods(doc, sheet_id, headers=True, columns=None):
+def get_rows(
+    doc: etree._ElementTree,
+    sheet_id: Union[str, int],
+) -> Iterator[etree._Element]:
     if not isinstance(sheet_id, (str, int)):
         raise ValueError("Sheet id has to be either `str` or `int`")
     root = doc.getroot()
     namespaces = root.nsmap
-    spreadsheet = doc.find(BODY_TAG, namespaces=namespaces).find(
+    spreadsheet = doc.find(BODY_TAG, namespaces=namespaces).find(  # type: ignore
         SPREADSHEET_TAG, namespaces=namespaces
     )
     sheet = get_sheet(spreadsheet, sheet_id)
-    rows = sheet.findall(TABLE_ROW_TAG, namespaces=namespaces)
-    allcells = []
-    for row in rows:
-        cells = row.findall(TABLE_CELL_TAG, namespaces=namespaces)
-        allcells.append(cells)
-    columns, values = parse_columns(allcells, headers, columns)
-    data = []
-    for row in values:
-        rowvalues = [parse_value(cell) for cell in row]
-        data.append(rowvalues)
-    final_rows = []
-    for row in data:
-        final_row = []
-        for i in range(len(columns)):
-            if i < len(row):
-                final_row.append(row[i])
-            else:
-                final_row.append(None)
-        final_rows.append(final_row)
-    return pd.DataFrame(final_rows, columns=columns)
+    return sheet.iterfind(TABLE_ROW_TAG, namespaces=namespaces)
 
 
-def read(file_or_path, sheet=1, headers=True, columns=None):
-    doc = etree.parse(str(file_or_path))
-    df = load_fods(doc, sheet, headers=headers, columns=columns)
-    return sanitize_df(df)
+def is_float(cell: etree._Element) -> bool:
+    return (
+        cell.attrib.get(f"{{{cell.nsmap[OFFICE_KEY]}}}{VALUE_TYPE_ATTRIB}") == "float"
+    )
+
+
+def get_value(
+    cell: etree._Element,
+    parsed: bool = False,
+) -> Tuple[Optional[Union[str, float]], int]:
+    text = cell.find(TABLE_CELL_TEXT_TAG, namespaces=cell.nsmap)
+    if text is None:
+        return None, 0
+    value: Union[str, float] = "".join(text.itertext())
+    if parsed and is_float(cell):
+        value = float(value)
+    _n_repeated = cell.attrib.get(
+        f"{{{cell.nsmap[TABLE_KEY]}}}{TABLE_CELL_REPEATED_ATTRIB}"
+    )
+    n_repeated = int(_n_repeated) if _n_repeated is not None else 0
+    return value, n_repeated

pandas_ods_reader/parsers/ods.py

@@ -1,79 +1,28 @@
-from collections import OrderedDict
+from pathlib import Path
+from typing import Any, Iterator, List, Tuple, Union
 
-import ezodf
-import pandas as pd
-
-from ..tools import sanitize_df
+import ezodf  # type: ignore[import]
+from ezodf.document import FlatXMLDocument, PackagedDocument  # type: ignore[import]
 
 
-def load_ods(doc, sheet_id, headers=True, columns=None):
-    # convert the sheet to a pandas.DataFrame
+def get_doc(file_or_path: Path) -> Union[FlatXMLDocument, PackagedDocument]:
+    return ezodf.opendoc(file_or_path)
+
+
+def get_rows(
+    doc: Union[FlatXMLDocument, PackagedDocument],
+    sheet_id: Union[str, int],
+) -> Iterator[List[ezodf.Cell]]:
     if not isinstance(sheet_id, (int, str)):
         raise ValueError("Sheet id has to be either `str` or `int`")
     if isinstance(sheet_id, str):
-        sheets = [sheet.name for sheet in doc.sheets]
+        sheets: List[str] = [sheet.name for sheet in doc.sheets]
         if sheet_id not in sheets:
             raise KeyError("There is no sheet named {}".format(sheet_id))
         sheet_id = sheets.index(sheet_id) + 1
-    sheet = doc.sheets[sheet_id - 1]
-    df_dict = OrderedDict()
-    col_index = {}
-    for i, row in enumerate(sheet.rows()):
-        # row is a list of cells
-        if headers and i == 0 and not columns:
-            # columns as lists in a dictionary
-            columns = []
-            for cell in row:
-                if cell.value and cell.value not in columns:
-                    columns.append(cell.value)
-                else:
-                    column_name = cell.value if cell.value else "unnamed"
-                    # add count to column name
-                    idx = 1
-                    while "{}.{}".format(column_name, idx) in columns:
-                        idx += 1
-                    columns.append("{}.{}".format(column_name, idx))
-
-            df_dict = OrderedDict((column, []) for column in columns)
-            # create index for the column headers
-            col_index = {j: column for j, column in enumerate(columns)}
-            continue
-        elif i == 0:
-            columns = columns if columns else ([f"column.{j}" for j in range(len(row))])
-            # columns as lists in a dictionary
-            df_dict = OrderedDict((column, []) for column in columns)
-            # create index for the column headers
-            col_index = {j: column for j, column in enumerate(columns)}
-            if headers:
-                continue
-        for j, cell in enumerate(row):
-            if j < len(col_index):
-                # use header instead of column index
-                df_dict[col_index[j]].append(cell.value)
-            else:
-                continue
-    df = pd.DataFrame(df_dict)
-    return df
+    sheet: ezodf.Sheet = doc.sheets[sheet_id - 1]
+    return sheet.rows()
 
 
-def read(file_or_path, sheet=1, headers=True, columns=None):
-    """
-    This function reads in the provided ods file and converts it to a
-    dictionary. The dictionary is converted to a DataFrame. Trailing empty rows
-    and columns are dropped from the DataFrame, before it is returned.
-
-    :param file_or_path: str
-    the path to the ODS file
-    :param sheet: int or str, default 1
-    if int, the 1 based index of the sheet to be read in. If str, the name of
-    the sheet to be read in
-    :param header: bool, default True
-    if True, the first row is read in as headers
-    :param columns: list, default None
-    a list of column names to be used as headers
-    :returns: pandas.DataFrame
-    the ODS file as a pandas DataFrame
-    """
-    doc = ezodf.opendoc(file_or_path)
-    df = load_ods(doc, sheet, headers, columns)
-    return sanitize_df(df)
+def get_value(cell: ezodf.Cell, parsed: bool = False) -> Tuple[Any, int]:
+    return cell.value, 0

pandas_ods_reader/utils.py

@@ -1,5 +1,7 @@
 """Provides utility functions for the parser"""
 
+import pandas as pd
+
 
 def ods_info(doc):
     """Print the number of sheets, their names, and number of rows and columns"""
@@ -14,8 +16,8 @@ def ods_info(doc):
         )
 
 
-def sanitize_df(df):
-    """Drop empty rows and columns from the DataFrame and returns it"""
+def sanitize_df(df: pd.DataFrame) -> pd.DataFrame:
+    """Drop empty rows and columns from the DataFrame and return it."""
     # Delete empty rows
     for i in df.index.tolist()[-1::-1]:
         if df.iloc[i].isna().all():

pyproject.toml

@@ -0,0 +1,42 @@
+[tool.poetry]
+name = "pandas-ods-reader"
+version = "1.0.2"
+description = "Read in .ods and .fods files and return a pandas.DataFrame."
+authors = ["iuvbio <iuvbio@users.noreply.github.com>"]
+license = "MIT"
+readme = "README.md"
+repository = "https://github.com/iuvbio/pandas_ods_reader"
+keywords = ["data", "io", "pandas", "ods"]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3",
+  "Topic :: Utilities",
+]
+
+[tool.poetry.dependencies]
+python = ">=3.9,<4"
+ezodf = ">=0.3.2"
+lxml = ">=4.9.2"
+pandas = ">=2.2.3"
+
+[tool.poetry.group.dev.dependencies]
+black = ">=22.10.0"
+pytest = ">=7.1.3"
+pytest-cov = ">=4.0.0"
+mypy = ">=0.991"
+flake8 = ">=6.0.0"
+pandas-stubs = ">=1.5.2.221213"
+types-lxml = ">=2022.11.8"
+commitizen = ">=2.38.0"
+pre-commit = ">=3.7.1"
+
+[tool.commitizen]
+name = "cz_conventional_commits"
+tag_format = "v$version"
+version_provider = "poetry"
+version_files = ["pyproject.toml:version"]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

setup.cfg

@@ -1,31 +0,0 @@
-[metadata]
-name = pandas_ods_reader
-version = file: pandas_ods_reader/VERSION
-description = Read in an ODS file and return it as a pandas.DataFrame
-long_description = file: README.md, LICENSE.txt
-long_description_content_type = text/markdown
-classifiers = 
-    Development Status :: 2 - Beta
-    License :: OSI Approved :: MIT License
-    Programming Language :: Python :: 3
-    Topic :: Utilities
-keywords = data, io, pandas, ods
-url = "http://github.com/iuvbio/pandas_ods_reader"
-author = iuvbio
-author_email = cryptodemigod@protonmail.com
-license = MIT
-
-[options]
-zip_safe = False
-packages = find:
-include_package_data = True
-install_requires =
-    ezodf
-    pandas
-    lxml
-
-[options.extras_require]
-test = pytest
-
-[aliases]
-test = pytest

setup.py

@@ -1,4 +0,0 @@
-from setuptools import setup
-
-
-setup()

tests/rsc/example_skiprows.fods

@@ -0,0 +1,423 @@
+<?xml version="1.0" encoding="UTF-8"?>
+
+<office:document xmlns:presentation="urn:oasis:names:tc:opendocument:xmlns:presentation:1.0" xmlns:css3t="http://www.w3.org/TR/css3-text/" xmlns:grddl="http://www.w3.org/2003/g/data-view#" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:rpt="http://openoffice.org/2005/report" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0" xmlns:config="urn:oasis:names:tc:opendocument:xmlns:config:1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:of="urn:oasis:names:tc:opendocument:xmlns:of:1.2" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:ooo="http://openoffice.org/2004/office" xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0" xmlns:formx="urn:openoffice:names:experimental:ooxml-odf-interop:xmlns:form:1.0" xmlns:calcext="urn:org:documentfoundation:names:experimental:calc:xmlns:calcext:1.0" xmlns:drawooo="http://openoffice.org/2010/draw" xmlns:field="urn:openoffice:names:experimental:ooo-ms-interop:xmlns:field:1.0" xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0" xmlns:number="urn:oasis:names:tc:opendocument:xmlns:datastyle:1.0" xmlns:ooow="http://openoffice.org/2004/writer" xmlns:oooc="http://openoffice.org/2004/calc" xmlns:tableooo="http://openoffice.org/2009/table" xmlns:loext="urn:org:documentfoundation:names:experimental:office:xmlns:loext:1.0" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:form="urn:oasis:names:tc:opendocument:xmlns:form:1.0" xmlns:script="urn:oasis:names:tc:opendocument:xmlns:script:1.0" xmlns:dom="http://www.w3.org/2001/xml-events" xmlns:xforms="http://www.w3.org/2002/xforms" office:version="1.2" office:mimetype="application/vnd.oasis.opendocument.spreadsheet">
+ <office:meta><meta:initial-creator>Lukas Jansen</meta:initial-creator><meta:creation-date>2019-01-27T03:31:08.931482632</meta:creation-date><dc:date>2022-10-25T08:45:33.990049580</dc:date><meta:editing-duration>PT2M33S</meta:editing-duration><meta:editing-cycles>2</meta:editing-cycles><meta:generator>LibreOffice/6.4.7.2$Linux_X86_64 LibreOffice_project/40$Build-2</meta:generator><meta:document-statistic meta:table-count="1" meta:cell-count="55" meta:object-count="0"/></office:meta>
+ <office:settings>
+  <config:config-item-set config:name="ooo:view-settings">
+   <config:config-item config:name="VisibleAreaTop" config:type="int">0</config:config-item>
+   <config:config-item config:name="VisibleAreaLeft" config:type="int">0</config:config-item>
+   <config:config-item config:name="VisibleAreaWidth" config:type="int">11288</config:config-item>
+   <config:config-item config:name="VisibleAreaHeight" config:type="int">4967</config:config-item>
+   <config:config-item-map-indexed config:name="Views">
+    <config:config-item-map-entry>
+     <config:config-item config:name="ViewId" config:type="string">view1</config:config-item>
+     <config:config-item-map-named config:name="Tables">
+      <config:config-item-map-entry config:name="Sheet1">
+       <config:config-item config:name="CursorPositionX" config:type="int">5</config:config-item>
+       <config:config-item config:name="CursorPositionY" config:type="int">2</config:config-item>
+       <config:config-item config:name="HorizontalSplitMode" config:type="short">0</config:config-item>
+       <config:config-item config:name="VerticalSplitMode" config:type="short">0</config:config-item>
+       <config:config-item config:name="HorizontalSplitPosition" config:type="int">0</config:config-item>
+       <config:config-item config:name="VerticalSplitPosition" config:type="int">0</config:config-item>
+       <config:config-item config:name="ActiveSplitRange" config:type="short">2</config:config-item>
+       <config:config-item config:name="PositionLeft" config:type="int">0</config:config-item>
+       <config:config-item config:name="PositionRight" config:type="int">0</config:config-item>
+       <config:config-item config:name="PositionTop" config:type="int">0</config:config-item>
+       <config:config-item config:name="PositionBottom" config:type="int">0</config:config-item>
+       <config:config-item config:name="ZoomType" config:type="short">0</config:config-item>
+       <config:config-item config:name="ZoomValue" config:type="int">100</config:config-item>
+       <config:config-item config:name="PageViewZoomValue" config:type="int">60</config:config-item>
+       <config:config-item config:name="ShowGrid" config:type="boolean">true</config:config-item>
+       <config:config-item config:name="AnchoredTextOverflowLegacy" config:type="boolean">false</config:config-item>
+      </config:config-item-map-entry>
+     </config:config-item-map-named>
+     <config:config-item config:name="ActiveTable" config:type="string">Sheet1</config:config-item>
+     <config:config-item config:name="HorizontalScrollbarWidth" config:type="int">1861</config:config-item>
+     <config:config-item config:name="ZoomType" config:type="short">0</config:config-item>
+     <config:config-item config:name="ZoomValue" config:type="int">100</config:config-item>
+     <config:config-item config:name="PageViewZoomValue" config:type="int">60</config:config-item>
+     <config:config-item config:name="ShowPageBreakPreview" config:type="boolean">false</config:config-item>
+     <config:config-item config:name="ShowZeroValues" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="ShowNotes" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="ShowGrid" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="GridColor" config:type="int">12632256</config:config-item>
+     <config:config-item config:name="ShowPageBreaks" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="HasColumnRowHeaders" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="HasSheetTabs" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="IsOutlineSymbolsSet" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="IsValueHighlightingEnabled" config:type="boolean">false</config:config-item>
+     <config:config-item config:name="IsSnapToRaster" config:type="boolean">false</config:config-item>
+     <config:config-item config:name="RasterIsVisible" config:type="boolean">false</config:config-item>
+     <config:config-item config:name="RasterResolutionX" config:type="int">1000</config:config-item>
+     <config:config-item config:name="RasterResolutionY" config:type="int">1000</config:config-item>
+     <config:config-item config:name="RasterSubdivisionX" config:type="int">1</config:config-item>
+     <config:config-item config:name="RasterSubdivisionY" config:type="int">1</config:config-item>
+     <config:config-item config:name="IsRasterAxisSynchronized" config:type="boolean">true</config:config-item>
+     <config:config-item config:name="AnchoredTextOverflowLegacy" config:type="boolean">false</config:config-item>
+    </config:config-item-map-entry>
+   </config:config-item-map-indexed>
+  </config:config-item-set>
+  <config:config-item-set config:name="ooo:configuration-settings">
+   <config:config-item config:name="EmbedComplexScriptFonts" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="EmbedAsianScriptFonts" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="EmbedLatinScriptFonts" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="EmbedOnlyUsedFonts" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="RasterResolutionY" config:type="int">1000</config:config-item>
+   <config:config-item config:name="IsOutlineSymbolsSet" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="RasterSubdivisionY" config:type="int">1</config:config-item>
+   <config:config-item config:name="GridColor" config:type="int">12632256</config:config-item>
+   <config:config-item config:name="HasColumnRowHeaders" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="ShowNotes" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="HasSheetTabs" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="PrinterSetup" config:type="base64Binary">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</config:config-item>
+   <config:config-item config:name="RasterResolutionX" config:type="int">1000</config:config-item>
+   <config:config-item config:name="SyntaxStringRef" config:type="short">7</config:config-item>
+   <config:config-item config:name="RasterIsVisible" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="ShowZeroValues" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="ApplyUserData" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="RasterSubdivisionX" config:type="int">1</config:config-item>
+   <config:config-item config:name="IsRasterAxisSynchronized" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="LoadReadonly" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="AutoCalculate" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="EmbedFonts" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="SaveThumbnail" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="ShowGrid" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="PrinterName" config:type="string">Generic Printer</config:config-item>
+   <config:config-item config:name="PrinterPaperFromSetup" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="CharacterCompressionType" config:type="short">0</config:config-item>
+   <config:config-item config:name="LinkUpdateMode" config:type="short">3</config:config-item>
+   <config:config-item config:name="ShowPageBreaks" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="SaveVersionOnClose" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="IsSnapToRaster" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="IsKernAsianPunctuation" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="UpdateFromTemplate" config:type="boolean">true</config:config-item>
+   <config:config-item config:name="IsDocumentShared" config:type="boolean">false</config:config-item>
+   <config:config-item config:name="AllowPrintJobCancel" config:type="boolean">true</config:config-item>
+  </config:config-item-set>
+ </office:settings>
+ <office:scripts>
+  <office:script script:language="ooo:Basic">
+   <ooo:libraries xmlns:ooo="http://openoffice.org/2004/office" xmlns:xlink="http://www.w3.org/1999/xlink"/>
+  </office:script>
+ </office:scripts>
+ <office:font-face-decls>
+  <style:font-face style:name="Liberation Sans" svg:font-family="&apos;Liberation Sans&apos;" style:font-family-generic="swiss" style:font-pitch="variable"/>
+  <style:font-face style:name="Lohit Devanagari" svg:font-family="&apos;Lohit Devanagari&apos;" style:font-family-generic="system" style:font-pitch="variable"/>
+  <style:font-face style:name="Noto Sans CJK SC" svg:font-family="&apos;Noto Sans CJK SC&apos;" style:font-family-generic="system" style:font-pitch="variable"/>
+  <style:font-face style:name="Noto Sans CJK SC Regular" svg:font-family="&apos;Noto Sans CJK SC Regular&apos;" style:font-family-generic="system" style:font-pitch="variable"/>
+ </office:font-face-decls>
+ <office:styles>
+  <style:default-style style:family="table-cell">
+   <style:paragraph-properties style:tab-stop-distance="1.25cm"/>
+   <style:text-properties style:font-name="Liberation Sans" fo:language="en" fo:country="NZ" style:font-name-asian="Noto Sans CJK SC Regular" style:language-asian="zh" style:country-asian="CN" style:font-name-complex="Lohit Devanagari" style:language-complex="hi" style:country-complex="IN"/>
+  </style:default-style>
+  <number:number-style style:name="N0">
+   <number:number number:min-integer-digits="1"/>
+  </number:number-style>
+  <style:style style:name="Default" style:family="table-cell"/>
+  <style:style style:name="Heading" style:family="table-cell" style:parent-style-name="Default">
+   <style:text-properties fo:color="#000000" fo:font-size="24pt" fo:font-style="normal" fo:font-weight="bold"/>
+  </style:style>
+  <style:style style:name="Heading_20_1" style:display-name="Heading 1" style:family="table-cell" style:parent-style-name="Heading">
+   <style:text-properties fo:color="#000000" fo:font-size="18pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Heading_20_2" style:display-name="Heading 2" style:family="table-cell" style:parent-style-name="Heading">
+   <style:text-properties fo:color="#000000" fo:font-size="12pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Text" style:family="table-cell" style:parent-style-name="Default"/>
+  <style:style style:name="Note" style:family="table-cell" style:parent-style-name="Text">
+   <style:table-cell-properties fo:background-color="#ffffcc" style:diagonal-bl-tr="none" style:diagonal-tl-br="none" fo:border="0.74pt solid #808080"/>
+   <style:text-properties fo:color="#333333" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Footnote" style:family="table-cell" style:parent-style-name="Text">
+   <style:text-properties fo:color="#808080" fo:font-size="10pt" fo:font-style="italic" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Hyperlink" style:family="table-cell" style:parent-style-name="Text">
+   <style:text-properties fo:color="#0000ee" fo:font-size="10pt" fo:font-style="normal" style:text-underline-style="solid" style:text-underline-width="auto" style:text-underline-color="#0000ee" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Status" style:family="table-cell" style:parent-style-name="Default"/>
+  <style:style style:name="Good" style:family="table-cell" style:parent-style-name="Status">
+   <style:table-cell-properties fo:background-color="#ccffcc"/>
+   <style:text-properties fo:color="#006600" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Neutral" style:family="table-cell" style:parent-style-name="Status">
+   <style:table-cell-properties fo:background-color="#ffffcc"/>
+   <style:text-properties fo:color="#996600" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Bad" style:family="table-cell" style:parent-style-name="Status">
+   <style:table-cell-properties fo:background-color="#ffcccc"/>
+   <style:text-properties fo:color="#cc0000" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Warning" style:family="table-cell" style:parent-style-name="Status">
+   <style:text-properties fo:color="#cc0000" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Error" style:family="table-cell" style:parent-style-name="Status">
+   <style:table-cell-properties fo:background-color="#cc0000"/>
+   <style:text-properties fo:color="#ffffff" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="bold"/>
+  </style:style>
+  <style:style style:name="Accent" style:family="table-cell" style:parent-style-name="Default">
+   <style:text-properties fo:color="#000000" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="bold"/>
+  </style:style>
+  <style:style style:name="Accent_20_1" style:display-name="Accent 1" style:family="table-cell" style:parent-style-name="Accent">
+   <style:table-cell-properties fo:background-color="#000000"/>
+   <style:text-properties fo:color="#ffffff" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Accent_20_2" style:display-name="Accent 2" style:family="table-cell" style:parent-style-name="Accent">
+   <style:table-cell-properties fo:background-color="#808080"/>
+   <style:text-properties fo:color="#ffffff" fo:font-size="10pt" fo:font-style="normal" fo:font-weight="normal"/>
+  </style:style>
+  <style:style style:name="Accent_20_3" style:display-name="Accent 3" style:family="table-cell" style:parent-style-name="Accent">
+   <style:table-cell-properties fo:background-color="#dddddd"/>
+  </style:style>
+  <style:style style:name="Result" style:family="table-cell" style:parent-style-name="Default">
+   <style:text-properties fo:color="#000000" fo:font-size="10pt" fo:font-style="italic" style:text-underline-style="solid" style:text-underline-width="auto" style:text-underline-color="#000000" fo:font-weight="bold"/>
+  </style:style>
+ </office:styles>
+ <office:automatic-styles>
+  <style:style style:name="co1" style:family="table-column">
+   <style:table-column-properties fo:break-before="auto" style:column-width="2.258cm"/>
+  </style:style>
+  <style:style style:name="ro1" style:family="table-row">
+   <style:table-row-properties style:row-height="0.452cm" fo:break-before="auto" style:use-optimal-row-height="true"/>
+  </style:style>
+  <style:style style:name="ta1" style:family="table" style:master-page-name="Default">
+   <style:table-properties table:display="true" style:writing-mode="lr-tb"/>
+  </style:style>
+  <number:number-style style:name="N2">
+   <number:number number:decimal-places="2" loext:min-decimal-places="2" number:min-integer-digits="1"/>
+  </number:number-style>
+  <style:page-layout style:name="pm1">
+   <style:page-layout-properties style:writing-mode="lr-tb"/>
+   <style:header-style>
+    <style:header-footer-properties fo:min-height="0.75cm" fo:margin-left="0cm" fo:margin-right="0cm" fo:margin-bottom="0.25cm"/>
+   </style:header-style>
+   <style:footer-style>
+    <style:header-footer-properties fo:min-height="0.75cm" fo:margin-left="0cm" fo:margin-right="0cm" fo:margin-top="0.25cm"/>
+   </style:footer-style>
+  </style:page-layout>
+  <style:page-layout style:name="pm2">
+   <style:page-layout-properties style:writing-mode="lr-tb"/>
+   <style:header-style>
+    <style:header-footer-properties fo:min-height="0.75cm" fo:margin-left="0cm" fo:margin-right="0cm" fo:margin-bottom="0.25cm" fo:border="2.49pt solid #000000" fo:padding="0.018cm" fo:background-color="#c0c0c0">
+     <style:background-image/>
+    </style:header-footer-properties>
+   </style:header-style>
+   <style:footer-style>
+    <style:header-footer-properties fo:min-height="0.75cm" fo:margin-left="0cm" fo:margin-right="0cm" fo:margin-top="0.25cm" fo:border="2.49pt solid #000000" fo:padding="0.018cm" fo:background-color="#c0c0c0">
+     <style:background-image/>
+    </style:header-footer-properties>
+   </style:footer-style>
+  </style:page-layout>
+ </office:automatic-styles>
+ <office:master-styles>
+  <style:master-page style:name="Default" style:page-layout-name="pm1">
+   <style:header>
+    <text:p><text:sheet-name>???</text:sheet-name></text:p>
+   </style:header>
+   <style:header-left style:display="false"/>
+   <style:footer>
+    <text:p>Page <text:page-number>1</text:page-number></text:p>
+   </style:footer>
+   <style:footer-left style:display="false"/>
+  </style:master-page>
+  <style:master-page style:name="Report" style:page-layout-name="pm2">
+   <style:header>
+    <style:region-left>
+     <text:p><text:sheet-name>???</text:sheet-name><text:s/>(<text:title>???</text:title>)</text:p>
+    </style:region-left>
+    <style:region-right>
+     <text:p><text:date style:data-style-name="N2" text:date-value="2022-10-25">00/00/0000</text:date>, <text:time style:data-style-name="N2" text:time-value="08:45:14.557684313">00:00:00</text:time></text:p>
+    </style:region-right>
+   </style:header>
+   <style:header-left style:display="false"/>
+   <style:footer>
+    <text:p>Page <text:page-number>1</text:page-number><text:s/>/ <text:page-count>99</text:page-count></text:p>
+   </style:footer>
+   <style:footer-left style:display="false"/>
+  </style:master-page>
+ </office:master-styles>
+ <office:body>
+  <office:spreadsheet>
+   <table:calculation-settings table:automatic-find-labels="false" table:use-regular-expressions="false" table:use-wildcards="true"/>
+   <table:table table:name="Sheet1" table:style-name="ta1">
+    <table:table-column table:style-name="co1" table:number-columns-repeated="5" table:default-cell-style-name="Default"/>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>A</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>B</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>C</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>D</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>E</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:number-columns-repeated="5" office:value-type="string" calcext:value-type="string">
+      <text:p>skip this</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>a</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>b</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>c</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>d</text:p>
+     </table:table-cell>
+     <table:table-cell office:value-type="string" calcext:value-type="string">
+      <text:p>e</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="10" calcext:value-type="float">
+      <text:p>10</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="0" calcext:value-type="float">
+      <text:p>0</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="58" calcext:value-type="float">
+      <text:p>58</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="29" calcext:value-type="float">
+      <text:p>29</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="77" calcext:value-type="float">
+      <text:p>77</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="5" calcext:value-type="float">
+      <text:p>5</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="47" calcext:value-type="float">
+      <text:p>47</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="50" calcext:value-type="float">
+      <text:p>50</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="99" calcext:value-type="float">
+      <text:p>99</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="79" calcext:value-type="float">
+      <text:p>79</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="75" calcext:value-type="float">
+      <text:p>75</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="25" calcext:value-type="float">
+      <text:p>25</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="86" calcext:value-type="float">
+      <text:p>86</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="47" calcext:value-type="float">
+      <text:p>47</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="65" calcext:value-type="float">
+      <text:p>65</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="82" calcext:value-type="float">
+      <text:p>82</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="45" calcext:value-type="float">
+      <text:p>45</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="88" calcext:value-type="float">
+      <text:p>88</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="48" calcext:value-type="float">
+      <text:p>48</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="74" calcext:value-type="float">
+      <text:p>74</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="72" calcext:value-type="float">
+      <text:p>72</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="47" calcext:value-type="float">
+      <text:p>47</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="57" calcext:value-type="float">
+      <text:p>57</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="82" calcext:value-type="float">
+      <text:p>82</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="46" calcext:value-type="float">
+      <text:p>46</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="40" calcext:value-type="float">
+      <text:p>40</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="54" calcext:value-type="float">
+      <text:p>54</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="26" calcext:value-type="float">
+      <text:p>26</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="97" calcext:value-type="float">
+      <text:p>97</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="1" calcext:value-type="float">
+      <text:p>1</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="54" calcext:value-type="float">
+      <text:p>54</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="26" calcext:value-type="float">
+      <text:p>26</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="99" calcext:value-type="float">
+      <text:p>99</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="63" calcext:value-type="float">
+      <text:p>63</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="49" calcext:value-type="float">
+      <text:p>49</text:p>
+     </table:table-cell>
+    </table:table-row>
+    <table:table-row table:style-name="ro1">
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="87" calcext:value-type="float">
+      <text:p>87</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="24" calcext:value-type="float">
+      <text:p>24</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="47" calcext:value-type="float">
+      <text:p>47</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="87" calcext:value-type="float">
+      <text:p>87</text:p>
+     </table:table-cell>
+     <table:table-cell table:formula="of:=RANDBETWEEN(0; 100)" office:value-type="float" office:value="15" calcext:value-type="float">
+      <text:p>15</text:p>
+     </table:table-cell>
+    </table:table-row>
+   </table:table>
+   <table:named-expressions/>
+  </office:spreadsheet>
+ </office:body>
+</office:document>

tests/test_read_ods.py

@@ -1,4 +1,5 @@
 """Tests for core read_ods function with different files"""
+
 from pathlib import Path
 
 import pandas as pd
@@ -16,132 +17,161 @@ duplicated_column_names_file = "example_duplicated_column_names.ods"
 col_len_file = "example_col_lengths.ods"
 missing_header_file = "example_missing_header.ods"
 mixed_dtypes_file = "mixed_dtypes.ods"
+skiprows_file = "example_skiprows.ods"
 
 
-class TestOdsReader:
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_header_file_simple(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_header_file_simple(suffix: str) -> None:
+    """Test a simple file with headers."""
+    path = rsc / header_file
+    df = read_ods(path.with_suffix(suffix))
 
-        path = rsc / header_file
-        df = read_ods(path.with_suffix(suffix))
+    assert isinstance(df, pd.DataFrame)
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert isinstance(df, pd.DataFrame)
-        assert len(df) == 10
-        assert len(df.columns) == 5
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_header_file_with_int(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_header_file_with_int(suffix: str) -> None:
+    """Test referencing a sheet by index."""
+    path = rsc / header_file
+    df = read_ods(path.with_suffix(suffix), 1)
 
-        path = rsc / header_file
-        df = read_ods(path.with_suffix(suffix), 1)
+    assert isinstance(df, pd.DataFrame)
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert isinstance(df, pd.DataFrame)
-        assert len(df) == 10
-        assert len(df.columns) == 5
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_header_file_with_str(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_header_file_with_str(suffix: str) -> None:
+    """Test referencing a sheet by name."""
+    path = rsc / header_file
+    df = read_ods(path.with_suffix(suffix), "Sheet1")
 
-        path = rsc / header_file
-        df = read_ods(path.with_suffix(suffix), "Sheet1")
+    assert isinstance(df, pd.DataFrame)
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert isinstance(df, pd.DataFrame)
-        assert len(df) == 10
-        assert len(df.columns) == 5
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_header_file_with_cols(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_header_file_with_cols(suffix: str) -> None:
+    """Test overwriting haders with column names."""
+    path = rsc / header_file
+    columns = ["One", "Two", "Three", "Four", "Five"]
+    df = read_ods(path.with_suffix(suffix), "Sheet1", columns=columns)
 
-        path = rsc / header_file
-        columns = ["One", "Two", "Three", "Four", "Five"]
-        df = read_ods(path.with_suffix(suffix), "Sheet1", columns=columns)
+    assert list(df.columns) == columns
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert list(df.columns) == columns
-        assert len(df) == 10
-        assert len(df.columns) == 5
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_no_header_file_no_cols(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_no_header_file_no_cols(suffix: str) -> None:
+    """Test autogeneration of headers with no headers and not column names."""
+    path = rsc / no_header_file
+    df = read_ods(path.with_suffix(suffix), 1, headers=False)
 
-        path = rsc / no_header_file
-        df = read_ods(path.with_suffix(suffix), 1, headers=False)
+    assert list(df.columns) == [f"column.{i}" for i in range(len(df.columns))]
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert list(df.columns) == [f"column.{i}" for i in range(len(df.columns))]
-        assert len(df) == 10
-        assert len(df.columns) == 5
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_no_header_file_with_cols(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_no_header_file_with_cols(suffix: str) -> None:
+    """Test reading a file with no headers and passing column names."""
+    path = rsc / no_header_file
+    columns = ["A", "B", "C", "D", "E"]
+    df = read_ods(path.with_suffix(suffix), 1, headers=False, columns=columns)
 
-        path = rsc / no_header_file
-        columns = ["A", "B", "C", "D", "E"]
-        df = read_ods(path.with_suffix(suffix), 1, headers=False, columns=columns)
+    assert list(df.columns) == columns
+    assert len(df) == 10
 
-        assert list(df.columns) == columns
-        assert len(df) == 10
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_duplicated_column_names(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_duplicated_column_names(suffix: str) -> None:
+    """Test numbering duplicate column names."""
+    path = rsc / duplicated_column_names_file
+    df = read_ods(path.with_suffix(suffix), 1)
 
-        path = rsc / duplicated_column_names_file
-        df = read_ods(path.with_suffix(suffix), 1)
+    assert isinstance(df, pd.DataFrame)
+    assert len(df.columns) == 4
+    assert "website.1" in df.columns
 
-        assert isinstance(df, pd.DataFrame)
-        assert len(df.columns) == 4
-        assert "website.1" in df.columns
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_header_file_col_len(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_header_file_col_len(suffix: str) -> None:
+    """Test the correct number of columns is read."""
+    path = rsc / col_len_file
+    df = read_ods(path.with_suffix(suffix), 1)
 
-        path = rsc / col_len_file
-        df = read_ods(path.with_suffix(suffix), 1)
+    assert isinstance(df, pd.DataFrame)
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert isinstance(df, pd.DataFrame)
-        assert len(df) == 10
-        assert len(df.columns) == 5
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_wrong_id_type(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_wrong_id_type(suffix: str) -> None:
+    """Verify passing a wrong id type raises an error."""
+    path = rsc / header_file
 
-        path = rsc / header_file
+    with pytest.raises(ValueError) as e_info:
+        read_ods(path.with_suffix(suffix), 1.0)  # type: ignore[arg-type]
+        assert e_info.match("Sheet id has to be either `str` or `int`")
 
-        with pytest.raises(ValueError) as e_info:
-            read_ods(path.with_suffix(suffix), 1.0)
-            assert e_info.match("Sheet id has to be either `str` or `int`")
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_non_existent_sheet(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_non_existent_sheet(suffix: str) -> None:
+    """Verify referencing a non-existent sheet raises an error."""
+    path = rsc / header_file
+    sheet_name = "No_Sheet"
 
-        path = rsc / header_file
-        sheet_name = "No_Sheet"
+    with pytest.raises(KeyError) as e_info:
+        read_ods(path.with_suffix(suffix), sheet_name)
+        assert e_info.match(f"There is no sheet named {sheet_name}")
 
-        with pytest.raises(KeyError) as e_info:
-            read_ods(path.with_suffix(suffix), sheet_name)
-            assert e_info.match(f"There is no sheet named {sheet_name}")
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_missing_header(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_missing_header(suffix: str) -> None:
+    """Verify that a missing header is named."""
+    path = rsc / missing_header_file
+    df = read_ods(path.with_suffix(suffix), 1)
 
-        path = rsc / missing_header_file
-        df = read_ods(path.with_suffix(suffix), 1)
+    assert isinstance(df, pd.DataFrame)
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert isinstance(df, pd.DataFrame)
-        assert len(df) == 10
-        assert len(df.columns) == 5
+    assert df.columns[2] == "unnamed.1"
 
-        assert df.columns[2] == "unnamed.1"
 
-    @pytest.mark.parametrize("suffix", [".ods", ".fods"])
-    def test_mixed_dtypes(self, suffix):
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_mixed_dtypes(suffix: str) -> None:
+    """Verify loading a df with mixed types."""
+    path = rsc / mixed_dtypes_file
+    df = read_ods(path.with_suffix(suffix), 1)
 
-        path = rsc / mixed_dtypes_file
-        df = read_ods(path.with_suffix(suffix), 1)
+    assert isinstance(df, pd.DataFrame)
+    assert len(df) == 10
+    assert len(df.columns) == 5
 
-        assert isinstance(df, pd.DataFrame)
-        assert len(df) == 10
-        assert len(df.columns) == 5
+    type_list = [float, object, float, float, object]
+    assert df.dtypes.tolist() == type_list
+    col_b_types = [type(v) for v in df.B.values]
+    assert str in col_b_types and float in col_b_types
 
-        type_list = [float, object, float, float, object]
-        assert df.dtypes.tolist() == type_list
-        col_b_types = [type(v) for v in df.B.values]
-        assert str in col_b_types and float in col_b_types
+
+@pytest.mark.parametrize("suffix", [".ods", ".fods"])
+def test_skiprows(suffix: str) -> None:
+    """Verify skipping rows works correctly."""
+    path = rsc / skiprows_file
+    df = read_ods(path.with_suffix(suffix), skiprows=2)
+    assert isinstance(df, pd.DataFrame)
+    assert len(df) == 8
+    assert len(df.columns) == 5
+    assert df.columns.tolist() == ["a", "b", "c", "d", "e"]
+
+
+def test_invalid_path() -> None:
+    """Verify passing an invalid path raises an error."""
+    path = rsc / "does-not-exist.ods"
+    with pytest.raises(FileNotFoundError, match="does not exist"):
+        read_ods(path)