Merge pull request #262 from hiaselhans/py310

cleanup setup.py & tests

pyexcel/__version__.py

@@ -1,2 +1,2 @@
-__version__ = '0.7.0'
-__author__ = 'C.W.'
+__version__ = "0.7.0"
+__author__ = "C.W."

pyexcel/docstrings/core.py

@@ -9,7 +9,6 @@
 """
 from . import keywords
 
-
 __GET_ARRAY__ = (
     keywords.SOURCE_PARAMS_TABLE
     + """
@@ -18,10 +17,7 @@
     + keywords.SOURCE_PARAMS
 )
 
-__GET_SHEET__ = (
-    keywords.EXAMPLE_NOTE_PAGINATION
-    + __GET_ARRAY__
-)
+__GET_SHEET__ = keywords.EXAMPLE_NOTE_PAGINATION + __GET_ARRAY__
 
 __GET_BOOK__ = (
     keywords.SOURCE_BOOK_PARAMS_TABLE

pyexcel/internal/sheets/_shared.py

@@ -9,6 +9,7 @@
 """
 import re
 import types
+from typing import Tuple
 from functools import partial
 
 from pyexcel._compact import PY2
@@ -71,47 +72,36 @@ def analyse_slice(aslice, upper_bound):
     return my_range
 
 
-def excel_column_index(index_chars):
-    """translate MS excel column position to index"""
-    if len(index_chars) < 1:
-        return -1
-    else:
-        return _get_index(index_chars.upper())
-
+def excel_cell_position(pos_chars: str) -> Tuple[int, int]:
+    """
+    translate MS excel position to index
+    Return: (row: int, column: int)
+    """
+    match = re.match("([A-Za-z]+)([0-9]+)", pos_chars)
 
-def excel_cell_position(pos_chars):
-    """translate MS excel position to index"""
-    if len(pos_chars) < 2:
-        return -1, -1
-    group = re.match("([A-Za-z]+)([0-9]+)", pos_chars)
-    if group:
-        return int(group.group(2)) - 1, excel_column_index(group.group(1))
+    if match:
+        return int(match.group(2)) - 1, excel_column_index(match.group(1))
     else:
-        raise IndexError
+        raise KeyError(f"invalid index: {pos_chars}")
 
 
 """
 In order to easily compute the actual index of 'X' or 'AX', these utility
 functions were written
 """
-_INDICES = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
-
-
-def _get_index(index_chars):
-    length = len(index_chars)
-    index_chars_length = len(_INDICES)
-    if length > 1:
-        index = 0
-        for i in range(0, length):
-            if i < (length - 1):
-                index += (_INDICES.index(index_chars[i]) + 1) * (
-                    index_chars_length ** (length - 1 - i)
-                )
-            else:
-                index += _INDICES.index(index_chars[i])
-        return index
-    else:
-        return _INDICES.index(index_chars[0])
+INDEX_CHARS = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+INDEX_BASE = len(INDEX_CHARS)
+
+
+def excel_column_index(index_chars: str) -> int:
+    index = -1
+    for i, char in enumerate(index_chars.upper()[::-1]):
+        # going from right to left, the multiplicator is:
+        # 26^0 = 1
+        # 26^1 = 26
+        index += (1 + INDEX_CHARS.index(char)) * INDEX_BASE**i
+
+    return index
 
 
 def names_to_indices(names, series):

pyexcel/internal/sheets/matrix.py

@@ -10,6 +10,7 @@
 """
 import copy
 import types
+from typing import Tuple, Union
 from functools import partial
 from itertools import chain
 
@@ -23,6 +24,8 @@
 
 from . import _shared as utils
 
+MatrixIndex = Union[Tuple[int, int], str]
+
 
 class Matrix(SheetMeta):
     """The internal representation of a sheet data. Each element
@@ -460,29 +463,29 @@ def delete_columns(self, column_indices):
                         del self.__array[i][j]
             self.__width = longest_row_number(self.__array)
 
-    def __setitem__(self, aset, cell_value):
+    def __setitem__(self, index: MatrixIndex, cell_value):
         """Override the operator to set items"""
-        if isinstance(aset, tuple):
-            return self.cell_value(aset[0], aset[1], cell_value)
-        elif isinstance(aset, str):
-            row, column = utils.excel_cell_position(aset)
+        if isinstance(index, tuple):
+            return self.cell_value(index[0], index[1], cell_value)
+        elif isinstance(index, str):
+            row, column = utils.excel_cell_position(index)
             return self.cell_value(row, column, cell_value)
-        else:
-            raise IndexError
 
-    def __getitem__(self, aset):
+        raise IndexError
+
+    def __getitem__(self, index: MatrixIndex):
         """By default, this class recognize from top to bottom
         from left to right"""
-        if isinstance(aset, tuple):
-            return self.cell_value(aset[0], aset[1])
-        elif isinstance(aset, str):
-            row, column = utils.excel_cell_position(aset)
+        if isinstance(index, tuple):
+            return self.cell_value(index[0], index[1])
+        elif isinstance(index, str):
+            row, column = utils.excel_cell_position(index)
             return self.cell_value(row, column)
-        elif isinstance(aset, int):
+        elif isinstance(index, int):
             print(constants.MESSAGE_DEPRECATED_ROW_COLUMN)
-            return self.row_at(aset)
-        else:
-            raise IndexError
+            return self.row_at(index)
+
+        raise IndexError
 
     def contains(self, predicate):
         """Has something in the table"""

pyexcel/internal/source_plugin.py

@@ -53,7 +53,7 @@ def load_me_now(self, key, action=None, library=None, **keywords):
         return plugin
 
     def register_a_plugin(self, plugin_cls, plugin_info):
-        """ for dynamically loaded plugin """
+        """for dynamically loaded plugin"""
         PluginManager.register_a_plugin(self, plugin_cls, plugin_info)
         self._register_a_plugin_info(plugin_info)
 

pyexcel/renderer.py

@@ -144,6 +144,7 @@ class BinaryRenderer(Renderer):
     """
     Renderer pyexcel data into a binary object
     """
+
     WRITE_FLAG = "wb"
 
     def get_io(self):

pyexcel/sheet.py

@@ -356,7 +356,7 @@ def delete_named_column_at(self, name):
             Matrix.delete_columns(self, [index])
 
     def named_row_at(self, name):
-        """Get a row by its name """
+        """Get a row by its name"""
         index = name
         index = self.rownames.index(name)
         row_array = self.row_at(index)
@@ -593,7 +593,7 @@ def __getitem__(self, aset):
                 column = aset[1]
             return self.cell_value(row, column)
         else:
-            return Matrix.__getitem__(self, aset)
+            return super().__getitem__(aset)
 
     def __setitem__(self, aset, c):
         if isinstance(aset, tuple):
@@ -608,7 +608,7 @@ def __setitem__(self, aset, c):
                 column = aset[1]
             self.cell_value(row, column, c)
         else:
-            Matrix.__setitem__(self, aset, c)
+            super().__setitem__(aset, c)
 
     def __len__(self):
         return self.number_of_rows()

setup.py

@@ -6,30 +6,10 @@
 
 import os
 import sys
-import codecs
-import locale
-import platform
 from shutil import rmtree
 
 from setuptools import Command, setup, find_packages
 
-PY2 = sys.version_info[0] == 2
-PY26 = PY2 and sys.version_info[1] < 7
-PY33 = sys.version_info < (3, 4)
-
-# Work around mbcs bug in distutils.
-# http://bugs.python.org/issue10945
-# This work around is only if a project supports Python < 3.4
-
-# Work around for locale not being set
-try:
-    lc = locale.getlocale()
-    pf = platform.system()
-    if pf != "Windows" and lc == (None, None):
-        locale.setlocale(locale.LC_ALL, "C.UTF-8")
-except (ValueError, UnicodeError, locale.Error):
-    locale.setlocale(locale.LC_ALL, "en_US.UTF-8")
-
 NAME = "pyexcel"
 AUTHOR = "C.W."
 VERSION = "0.7.0"
@@ -41,7 +21,7 @@
 )
 URL = "https://github.com/pyexcel/pyexcel"
 DOWNLOAD_URL = "%s/archive/0.7.0.tar.gz" % URL
-FILES = ["README.rst", "CONTRIBUTORS.rst", "CHANGELOG.rst"]
+README_FILES = ["README.rst", "CONTRIBUTORS.rst", "CHANGELOG.rst"]
 KEYWORDS = [
     "python",
     'tsv',
@@ -155,17 +135,14 @@ def has_gease():
 
 def read_files(*files):
     """Read files into setup"""
-    text = ""
-    for single_file in files:
-        content = read(single_file)
-        text = text + content + "\n"
-    return text
+    return "\n".join([read(filename) for filename in files])
 
 
-def read(afile):
+def read(filename):
     """Read a file into setup"""
-    the_relative_file = os.path.join(HERE, afile)
-    with codecs.open(the_relative_file, "r", "utf-8") as opened_file:
+    filename_absolute = os.path.join(HERE, filename)
+
+    with open(filename_absolute) as opened_file:
         content = filter_out_test_code(opened_file)
         content = "".join(list(content))
         return content
@@ -205,7 +182,7 @@ def filter_out_test_code(file_handle):
         description=DESCRIPTION,
         url=URL,
         download_url=DOWNLOAD_URL,
-        long_description=read_files(*FILES),
+        long_description=read_files(*README_FILES),
         license=LICENSE,
         keywords=KEYWORDS,
         python_requires=PYTHON_REQUIRES,

tests/test_bug_fixes.py

@@ -7,9 +7,9 @@
 
 import psutil
 import pyexcel as p
-from _compact import StringIO, OrderedDict
 
 from nose.tools import eq_
+from ._compact import StringIO, OrderedDict
 
 
 def test_bug_01():
@@ -166,7 +166,7 @@ def test_issue_51_normal_dict_in_records():
 
 
 def test_issue_55_unicode_in_headers():
-    headers = [u"Äkkilähdöt", u"Matkakirjoituksia", u"Matkatoimistot"]
+    headers = ["Äkkilähdöt", "Matkakirjoituksia", "Matkatoimistot"]
     content = [headers, [1, 2, 3]]
     sheet = p.Sheet(content)
     sheet.name_columns_by_row(0)
@@ -566,7 +566,7 @@ def test_issue_241():
     +---------+---------+---+---------+"""
     ).lstrip()
     eq_(str(book), expected)
-    os.unlink('issue_241.xlsx')
+    os.unlink("issue_241.xlsx")
 
 
 def test_issue_250():

tests/test_cookbook.py

@@ -1,9 +1,9 @@
 import os
 
 import pyexcel as pe
-from base import clean_up_files
 
 from nose.tools import eq_, raises
+from .base import clean_up_files
 
 
 class TestSpliting:
@@ -12,7 +12,7 @@ def setUp(self):
         self.content4 = {
             "Sheet1": [[1, 1, 1, 1], [2, 2, 2, 2], [3, 3, 3, 3]],
             "Sheet2": [[4, 4, 4, 4], [5, 5, 5, 5], [6, 6, 6, 6]],
-            "Sheet3": [[u"X", u"Y", u"Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]],
+            "Sheet3": [["X", "Y", "Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]],
         }
         pe.save_book_as(dest_file_name=self.testfile4, bookdict=self.content4)
 
@@ -87,7 +87,7 @@ def setUp(self):
         self.content4 = {
             "Sheet1": [[1, 1, 1, 1], [2, 2, 2, 2], [3, 3, 3, 3]],
             "Sheet2": [[4, 4, 4, 4], [5, 5, 5, 5], [6, 6, 6, 6]],
-            "Sheet3": [[u"X", u"Y", u"Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]],
+            "Sheet3": [["X", "Y", "Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]],
         }
         pe.save_book_as(dest_file_name=self.testfile4, bookdict=self.content4)
 

tests/test_django_related_functions.py

@@ -1,7 +1,7 @@
 import pyexcel as pe
-from _compact import OrderedDict
 
 from nose.tools import eq_, raises
+from ._compact import OrderedDict
 
 
 class Attributable:
@@ -187,10 +187,10 @@ class TestBook:
     def setUp(self):
         self.content = OrderedDict()
         self.content.update(
-            {"Sheet1": [[u"X", u"Y", u"Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
+            {"Sheet1": [["X", "Y", "Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
         )
         self.content.update(
-            {"Sheet2": [[u"A", u"B", u"C"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
+            {"Sheet2": [["A", "B", "C"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
         )
         self.result1 = [
             {"Y": 4, "X": 1, "Z": 7},
@@ -223,9 +223,7 @@ def test_book_save_to_models_with_bulk_save_false(self):
 
     def test_model_save_to_models(self):
         model = FakeDjangoModel("Sheet1")
-        data = {
-            "Sheet1": [[u"X", u"Y", u"Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]
-        }
+        data = {"Sheet1": [["X", "Y", "Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
         pe.save_book_as(dest_models=[model, None, None], bookdict=data)
         assert model.objects.objs == self.result1
 
@@ -235,7 +233,7 @@ def test_load_book_from_django_model(self):
         # with an exception.
         model = FakeDjangoModel("Sheet1")
         book = pe.Book(
-            {"Sheet1": [[u"X", u"Y", u"Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
+            {"Sheet1": [["X", "Y", "Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
         )
         book.save_to_django_models([model])
         assert model.objects.objs == self.result1

tests/test_examples.py

@@ -42,7 +42,7 @@ def test_them(self):
                     fn(path)
 
 
-class TestPyexcelServer(TestCase):
+class x(TestCase):
     """
     This test tells how difficult to test unicode vs bytes when
     dealing with csv files in relation to pyexcel. and this