Merge pull request pandas-dev#6 from dimastbk/issue-50395

bump python-calamine to 0.1.0

Author: kostyafarber

ci/deps/actions-310.yaml

@@ -55,5 +55,5 @@ dependencies:
   - zstandard>=0.15.2
 
   - pip:
-    - tzdata>=2022.1
     - python-calamine
+    - tzdata>=2022.1

ci/deps/actions-311.yaml

@@ -55,4 +55,5 @@ dependencies:
   - zstandard>=0.15.2
 
   - pip:
+    - python-calamine>=0.1.0
     - tzdata>=2022.1

ci/deps/actions-38-minimum_versions.yaml

@@ -59,5 +59,5 @@ dependencies:
 
   - pip:
     - pyqt5==5.15.1
-    - python-calamine==0.0.8
+    - python-calamine==0.1.0
     - tzdata==2022.1

ci/deps/actions-38.yaml

@@ -55,5 +55,5 @@ dependencies:
   - zstandard>=0.15.2
 
   - pip:
+    - python-calamine
     - tzdata>=2022.1
-    - python-calamine

ci/deps/actions-39.yaml

@@ -55,5 +55,5 @@ dependencies:
   - zstandard>=0.15.2
 
   - pip:
+    - python-calamine
     - tzdata>=2022.1
-    - python-calamine

ci/deps/circle-38-arm64.yaml

@@ -54,6 +54,6 @@ dependencies:
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
-  
- - pip:
-  - python-calamine
+
+  - pip:
+    - python-calamine

doc/source/getting_started/install.rst

@@ -345,6 +345,7 @@ xlrd                      2.0.1              excel           Reading Excel
 xlsxwriter                1.4.3              excel           Writing Excel
 openpyxl                  3.0.7              excel           Reading / writing for xlsx files
 pyxlsb                    1.0.8              excel           Reading for xlsb files
+python-calamine           0.1.0              excel           Reading for xls/xlsx/xlsb/ods files
 ========================= ================== =============== =============================================================
 
 HTML

doc/source/user_guide/io.rst

@@ -3420,7 +3420,8 @@ Excel files
 The :func:`~pandas.read_excel` method can read Excel 2007+ (``.xlsx``) files
 using the ``openpyxl`` Python module. Excel 2003 (``.xls``) files
 can be read using ``xlrd``. Binary Excel (``.xlsb``)
-files can be read using ``pyxlsb``.
+files can be read using ``pyxlsb``. Also, all this formats can be read using ``python-calamine``,
+but this library has sime limitation, for example, can't detect date in most formats.
 The :meth:`~DataFrame.to_excel` instance method is used for
 saving a ``DataFrame`` to Excel.  Generally the semantics are
 similar to working with :ref:`csv<io.read_csv_table>` data.

doc/source/whatsnew/v2.0.0.rst

@@ -275,7 +275,6 @@ Other enhancements
 - Improved error message in :func:`to_datetime` for non-ISO8601 formats, informing users about the position of the first error (:issue:`50361`)
 - Improved error message when trying to align :class:`DataFrame` objects (for example, in :func:`DataFrame.compare`) to clarify that "identically labelled" refers to both index and columns (:issue:`50083`)
 - Performance improvement in :func:`to_datetime` when format is given or can be inferred (:issue:`50465`)
-- Added ``calamine`` as an engine to ``read_excel`` (:issue: ``50395``)
 - Added support for :meth:`Index.min` and :meth:`Index.max` for pyarrow string dtypes (:issue:`51397`)
 - Added :meth:`DatetimeIndex.as_unit` and :meth:`TimedeltaIndex.as_unit` to convert to different resolutions; supported resolutions are "s", "ms", "us", and "ns" (:issue:`50616`)
 - Added :meth:`Series.dt.unit` and :meth:`Series.dt.as_unit` to convert to different resolutions; supported resolutions are "s", "ms", "us", and "ns" (:issue:`51223`)

doc/source/whatsnew/v2.1.0.rst

@@ -37,6 +37,7 @@ Other enhancements
 - Improve error message when having incompatible columns using :meth:`DataFrame.merge` (:issue:`51861`)
 - Improved error message when creating a DataFrame with empty data (0 rows), no index and an incorrect number of columns. (:issue:`52084`)
 - :meth:`arrays.SparseArray.map` now supports ``na_action`` (:issue:`52096`).
+- Added ``calamine`` as an engine to ``read_excel`` (:issue:`50395`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_210.notable_bug_fixes:

pandas/compat/_optional.py

@@ -37,7 +37,7 @@
     "pyarrow": "7.0.0",
     "pyreadstat": "1.1.2",
     "pytest": "7.0.0",
-    "python-calamine": "0.0.8",
+    "python-calamine": "0.1.0",
     "pyxlsb": "1.0.8",
     "s3fs": "2021.08.0",
     "scipy": "1.7.1",

pandas/core/config_init.py

@@ -503,11 +503,11 @@ def use_inf_as_na_cb(key) -> None:
     auto, {others}.
 """
 
-_xls_options = ["xlrd"]
-_xlsm_options = ["xlrd", "openpyxl"]
-_xlsx_options = ["xlrd", "openpyxl"]
-_ods_options = ["odf"]
-_xlsb_options = ["pyxlsb"]
+_xls_options = ["xlrd", "calamine"]
+_xlsm_options = ["xlrd", "openpyxl", "calamine"]
+_xlsx_options = ["xlrd", "openpyxl", "calamine"]
+_ods_options = ["odf", "calamine"]
+_xlsb_options = ["pyxlsb", "calamine"]
 
 
 with cf.config_prefix("io.excel.xls"):

pandas/io/excel/_base.py

@@ -149,13 +149,15 @@
     of dtype conversion.
 engine : str, default None
     If io is not a buffer or path, this must be set to identify io.
-    Supported engines: "xlrd", "openpyxl", "odf", "pyxlsb".
+    Supported engines: "xlrd", "openpyxl", "odf", "pyxlsb", "calamine".
     Engine compatibility :
 
     - "xlrd" supports old-style Excel files (.xls).
     - "openpyxl" supports newer Excel file formats.
     - "odf" supports OpenDocument file formats (.odf, .ods, .odt).
     - "pyxlsb" supports Binary Excel files.
+    - "calamine" supports Excel (.xls, .xlsx, .xlsm, .xlsb)
+      and OpenDocument (.ods) file formats.
 
     .. versionchanged:: 1.2.0
         The engine `xlrd <https://xlrd.readthedocs.io/en/latest/>`_
@@ -375,7 +377,7 @@ def read_excel(
     | Callable[[str], bool]
     | None = ...,
     dtype: DtypeArg | None = ...,
-    engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb"] | None = ...,
+    engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb", "calamine"] | None = ...,
     converters: dict[str, Callable] | dict[int, Callable] | None = ...,
     true_values: Iterable[Hashable] | None = ...,
     false_values: Iterable[Hashable] | None = ...,
@@ -414,7 +416,7 @@ def read_excel(
     | Callable[[str], bool]
     | None = ...,
     dtype: DtypeArg | None = ...,
-    engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb"] | None = ...,
+    engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb", "calamine"] | None = ...,
     converters: dict[str, Callable] | dict[int, Callable] | None = ...,
     true_values: Iterable[Hashable] | None = ...,
     false_values: Iterable[Hashable] | None = ...,
@@ -453,7 +455,7 @@ def read_excel(
     | Callable[[str], bool]
     | None = None,
     dtype: DtypeArg | None = None,
-    engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb"] | None = None,
+    engine: Literal["xlrd", "openpyxl", "odf", "pyxlsb", "calamine"] | None = None,
     converters: dict[str, Callable] | dict[int, Callable] | None = None,
     true_values: Iterable[Hashable] | None = None,
     false_values: Iterable[Hashable] | None = None,
@@ -1418,13 +1420,15 @@ class ExcelFile:
         .xls, .xlsx, .xlsb, .xlsm, .odf, .ods, or .odt file.
     engine : str, default None
         If io is not a buffer or path, this must be set to identify io.
-        Supported engines: ``xlrd``, ``openpyxl``, ``odf``, ``pyxlsb``
+        Supported engines: ``xlrd``, ``openpyxl``, ``odf``, ``pyxlsb``, ``calamine``
         Engine compatibility :
 
         - ``xlrd`` supports old-style Excel files (.xls).
         - ``openpyxl`` supports newer Excel file formats.
         - ``odf`` supports OpenDocument file formats (.odf, .ods, .odt).
         - ``pyxlsb`` supports Binary Excel files.
+        - ``calamine`` supports Excel (.xls, .xlsx, .xlsm, .xlsb)
+          and OpenDocument (.ods) file formats.
 
         .. versionchanged:: 1.2.0
 

pandas/io/excel/_calaminereader.py

@@ -5,36 +5,31 @@
     datetime,
     time,
 )
-from tempfile import NamedTemporaryFile
 from typing import (
+    TYPE_CHECKING,
     Union,
-    cast,
 )
 
-from pandas._typing import (
-    FilePath,
-    ReadBuffer,
-    Scalar,
-    StorageOptions,
-)
 from pandas.compat._optional import import_optional_dependency
 from pandas.util._decorators import doc
 
 import pandas as pd
 from pandas.core.shared_docs import _shared_docs
 
-from pandas.io.common import stringify_path
-from pandas.io.excel._base import (
-    BaseExcelReader,
-    inspect_excel_format,
-)
+from pandas.io.excel._base import BaseExcelReader
 
-ValueT = Union[int, float, str, bool, time, date, datetime]
+if TYPE_CHECKING:
+    from pandas._typing import (
+        FilePath,
+        ReadBuffer,
+        Scalar,
+        StorageOptions,
+    )
 
+_CellValueT = Union[int, float, str, bool, time, date, datetime]
 
-class CalamineExcelReader(BaseExcelReader):
-    _sheet_names: list[str] | None = None
 
+class CalamineExcelReader(BaseExcelReader):
     @doc(storage_options=_shared_docs["storage_options"])
     def __init__(
         self,
@@ -55,26 +50,14 @@ def __init__(
 
     @property
     def _workbook_class(self):
-        from python_calamine import CalamineReader
+        from python_calamine import CalamineWorkbook
 
-        return CalamineReader
+        return CalamineWorkbook
 
     def load_workbook(self, filepath_or_buffer: FilePath | ReadBuffer[bytes]):
-        if hasattr(filepath_or_buffer, "read") and hasattr(filepath_or_buffer, "seek"):
-            filepath_or_buffer = cast(ReadBuffer, filepath_or_buffer)
-            ext = inspect_excel_format(filepath_or_buffer)
-            with NamedTemporaryFile(suffix=f".{ext}", delete=False) as tmp_file:
-                filepath_or_buffer.seek(0)
-                tmp_file.write(filepath_or_buffer.read())
-                filepath_or_buffer = tmp_file.name
-        else:
-            filepath_or_buffer = stringify_path(filepath_or_buffer)
-
-        assert isinstance(filepath_or_buffer, str)
-
-        from python_calamine import CalamineReader
+        from python_calamine import load_workbook
 
-        return CalamineReader.from_path(filepath_or_buffer)
+        return load_workbook(filepath_or_buffer)  # type: ignore[arg-type]
 
     @property
     def sheet_names(self) -> list[str]:
@@ -91,7 +74,7 @@ def get_sheet_by_index(self, index: int):
     def get_sheet_data(
         self, sheet, file_rows_needed: int | None = None
     ) -> list[list[Scalar]]:
-        def _convert_cell(value: ValueT) -> Scalar:
+        def _convert_cell(value: _CellValueT) -> Scalar:
             if isinstance(value, float):
                 val = int(value)
                 if val == value:
@@ -105,7 +88,7 @@ def _convert_cell(value: ValueT) -> Scalar:
 
             return value
 
-        rows: list[list[ValueT]] = sheet.to_python(skip_empty_area=False)
+        rows: list[list[_CellValueT]] = sheet.to_python(skip_empty_area=False)
         data: list[list[Scalar]] = []
 
         for row in rows:

pyproject.toml

@@ -62,7 +62,7 @@ computation = ['scipy>=1.7.1', 'xarray>=0.21.0']
 fss = ['fsspec>=2021.07.0']
 aws = ['s3fs>=2021.08.0']
 gcp = ['gcsfs>=2021.07.0', 'pandas-gbq>=0.15.0']
-excel = ['odfpy>=1.4.1', 'openpyxl>=3.0.7', 'pyxlsb>=1.0.8', 'xlrd>=2.0.1', 'xlsxwriter>=1.4.3']
+excel = ['odfpy>=1.4.1', 'openpyxl>=3.0.7', 'python-calamine>=0.1.0', 'pyxlsb>=1.0.8', 'xlrd>=2.0.1', 'xlsxwriter>=1.4.3']
 parquet = ['pyarrow>=7.0.0']
 feather = ['pyarrow>=7.0.0']
 hdf5 = [# blosc only available on conda (https://github.com/Blosc/python-blosc/issues/297)
@@ -104,7 +104,7 @@ all = ['beautifulsoup4>=4.9.3',
        'pytest>=7.0.0',
        'pytest-xdist>=2.2.0',
        'pytest-asyncio>=0.17.0',
-       'python-calamine>=0.0.8',
+       'python-calamine>=0.1.0',
        'python-snappy>=0.6.0',
        'pyxlsb>=1.0.8',
        'qtpy>=2.2.0',

scripts/tests/data/deps_expected_random.yaml

@@ -55,3 +55,6 @@ dependencies:
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - python-calamine>=0.1.0

scripts/tests/data/deps_minimum.toml

@@ -62,7 +62,7 @@ computation = ['scipy>=1.7.1', 'xarray>=0.21.0']
 fss = ['fsspec>=2021.07.0']
 aws = ['s3fs>=2021.08.0']
 gcp = ['gcsfs>=2021.07.0', 'pandas-gbq>=0.15.0']
-excel = ['odfpy>=1.4.1', 'openpyxl>=3.0.7', 'pyxlsb>=1.0.8', 'xlrd>=2.0.1', 'xlsxwriter>=1.4.3']
+excel = ['odfpy>=1.4.1', 'openpyxl>=3.0.7', 'python-calamine>=0.1.0', 'pyxlsb>=1.0.8', 'xlrd>=2.0.1', 'xlsxwriter>=1.4.3']
 parquet = ['pyarrow>=7.0.0']
 feather = ['pyarrow>=7.0.0']
 hdf5 = [# blosc only available on conda (https://github.com/Blosc/python-blosc/issues/297)
@@ -104,6 +104,7 @@ all = ['beautifulsoup4>=5.9.3',
        'pytest>=7.0.0',
        'pytest-xdist>=2.2.0',
        'pytest-asyncio>=0.17.0',
+       'python-calamine>=0.1.0',
        'python-snappy>=0.6.0',
        'pyxlsb>=1.0.8',
        'qtpy>=2.2.0',

scripts/tests/data/deps_unmodified_random.yaml

@@ -55,3 +55,6 @@ dependencies:
   - xlrd>=2.0.1
   - xlsxwriter>=1.4.3
   - zstandard>=0.15.2
+
+  - pip:
+    - python-calamine>=0.1.0