From 7a315a1a4637c5ef393e2f08b8c2025f7b6509aa Mon Sep 17 00:00:00 2001
From: Andrius Merkys <merkys@debian.org>
Date: Wed, 27 Nov 2019 04:22:49 -0500
Subject: [PATCH] New upstream version 0.2.3
---
.travis.yml | 4 +++-
AUTHORS.rst | 4 ++++
CHANGELOG.rst | 17 ++++++++++++++++
COPYING | 2 +-
MANIFEST.in | 2 ++
README.rst | 4 ----
agateexcel/table_xls.py | 37 +++++++++++++++++++++++++---------
agateexcel/table_xlsx.py | 33 ++++++++++++++++++++----------
docs/conf.py | 8 +++++---
example.py | 2 +-
requirements-py3.txt | 2 +-
setup.py | 5 +++--
tests/test_table_xls.py | 43 +++++++++++++++++++++++++++++-----------
tests/test_table_xlsx.py | 41 ++++++++++++++++++++++++++++----------
tox.ini | 12 +++++++----
15 files changed, 157 insertions(+), 59 deletions(-)
mode change 100644 => 100755 agateexcel/table_xlsx.py
diff --git a/.travis.yml b/.travis.yml
index b8823ad..da38eb7 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,9 +1,11 @@
+dist: xenial
language: python
python:
- "2.7"
- - "3.3"
- "3.4"
- "3.5"
+ - "3.6"
+ - "3.7"
# command to install dependencies
install:
- if [[ $TRAVIS_PYTHON_VERSION == 3* ]]; then pip install -r requirements-py3.txt; else pip install -r requirements-py2.txt; fi
diff --git a/AUTHORS.rst b/AUTHORS.rst
index 058c201..337e959 100644
--- a/AUTHORS.rst
+++ b/AUTHORS.rst
@@ -4,3 +4,7 @@ The following individuals have contributed code to agate-excel:
* `James McKinney <https://github.com/jpmckinney>`_
* `Ben Welsh <https://github.com/palewire>`_
* `Peter M. Landwehr <https://github.com/pmlandwehr>`_
+* `Tim Freund <https://github.com/timfreund>`_
+* `Jani Mikkonen <https://github.com/rasjani>`_
+* `Loïc Corbasson <https://github.com/lcorbasson>`_
+* `Robert Schütz <https://github.com/dotlambda>`_
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index 424ae10..72f4df0 100644
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -1,3 +1,20 @@
+0.2.3
+-----
+
+* Fix bug in accepting ``column_names`` as keyword argument.
+* Add a ``reset_dimensions`` argument to :meth:`.Table.from_xlsx` to recalculate the data's dimensions, instead of trusting those in the file's properties.
+* Include tests and examples in distribution.
+* agate-excel is now tested against Python 3.6 and 3.7.
+* Drop support for Python 3.3 (end-of-life was September 29, 2017).
+* Add support for openpyxl 2.6.0.
+
+0.2.2 - January 28, 2018
+------------------------
+
+* Add an ``encoding_override`` argument to :meth:`.Table.from_xls` to override the encoding of the input XLS file.
+* Add a ``header`` argument to :meth:`.Table.from_xls` and :meth:`.Table.from_xlsx` to indicate the presence of a header row.
+* Add a ``read_only`` argument to :meth:`.Table.from_xlsx` to allow disabling read-only mode for `some spreadsheets <https://openpyxl.readthedocs.io/en/stable/optimized.html#worksheet-dimensions>`_.
+
0.2.1 - February 28, 2017
-------------------------
diff --git a/COPYING b/COPYING
index 15aa61e..8f55739 100644
--- a/COPYING
+++ b/COPYING
@@ -1,6 +1,6 @@
The MIT License
-Copyright (c) 2015 Christopher Groskopf and contributors
+Copyright (c) 2017 Christopher Groskopf and contributors
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
diff --git a/MANIFEST.in b/MANIFEST.in
index 45eee36..eaee0cc 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,3 +1,5 @@
include COPYING
include AUTHORS.rst
include README.rst
+recursive-include tests *.py
+graft examples
diff --git a/README.rst b/README.rst
index 91b0427..baffd5e 100644
--- a/README.rst
+++ b/README.rst
@@ -2,10 +2,6 @@
:target: https://travis-ci.org/wireservice/agate-excel
:alt: Build status
-.. image:: https://img.shields.io/pypi/dw/agate-excel.svg
- :target: https://pypi.python.org/pypi/agate-excel
- :alt: PyPI downloads
-
.. image:: https://img.shields.io/pypi/v/agate-excel.svg
:target: https://pypi.python.org/pypi/agate-excel
:alt: Version
diff --git a/agateexcel/table_xls.py b/agateexcel/table_xls.py
index 15a0d49..26a5122 100644
--- a/agateexcel/table_xls.py
+++ b/agateexcel/table_xls.py
@@ -11,7 +11,8 @@ import agate
import six
import xlrd
-def from_xls(cls, path, sheet=None, skip_lines=0, **kwargs):
+
+def from_xls(cls, path, sheet=None, skip_lines=0, header=True, encoding_override=None, **kwargs):
"""
Parse an XLS file.
@@ -22,15 +23,17 @@ def from_xls(cls, path, sheet=None, skip_lines=0, **kwargs):
then the first sheet will be used.
:param skip_lines:
The number of rows to skip from the top of the sheet.
+ :param header:
+ If :code:`True`, the first row is assumed to contain column names.
"""
if not isinstance(skip_lines, int):
raise ValueError('skip_lines argument must be an int')
if hasattr(path, 'read'):
- book = xlrd.open_workbook(file_contents=path.read())
+ book = xlrd.open_workbook(file_contents=path.read(), encoding_override=encoding_override)
else:
with open(path, 'rb') as f:
- book = xlrd.open_workbook(file_contents=f.read())
+ book = xlrd.open_workbook(file_contents=f.read(), encoding_override=encoding_override)
multiple = agate.utils.issequence(sheet)
if multiple:
@@ -48,15 +51,19 @@ def from_xls(cls, path, sheet=None, skip_lines=0, **kwargs):
else:
sheet = book.sheet_by_index(0)
- column_names = []
+ if header:
+ offset = 1
+ column_names = []
+ else:
+ offset = 0
+ column_names = None
+
columns = []
for i in range(sheet.ncols):
data = sheet.col_values(i)
- name = six.text_type(data[skip_lines]) or None
- values = data[skip_lines + 1:]
- types = sheet.col_types(i)[skip_lines + 1:]
-
+ values = data[skip_lines + offset:]
+ types = sheet.col_types(i)[skip_lines + offset:]
excel_type = determine_excel_type(types)
if excel_type == xlrd.biffh.XL_CELL_BOOLEAN:
@@ -64,7 +71,10 @@ def from_xls(cls, path, sheet=None, skip_lines=0, **kwargs):
elif excel_type == xlrd.biffh.XL_CELL_DATE:
values = normalize_dates(values, book.datemode)
- column_names.append(name)
+ if header:
+ name = six.text_type(data[skip_lines]) or None
+ column_names.append(name)
+
columns.append(values)
rows = []
@@ -73,6 +83,11 @@ def from_xls(cls, path, sheet=None, skip_lines=0, **kwargs):
for i in range(len(columns[0])):
rows.append([c[i] for c in columns])
+ if 'column_names' in kwargs:
+ if not header:
+ column_names = kwargs['column_names']
+ del kwargs['column_names']
+
tables[sheet.name] = agate.Table(rows, column_names, **kwargs)
if multiple:
@@ -80,6 +95,7 @@ def from_xls(cls, path, sheet=None, skip_lines=0, **kwargs):
else:
return tables.popitem()[1]
+
def determine_excel_type(types):
"""
Determine the correct type for a column from a list of cell types.
@@ -96,6 +112,7 @@ def determine_excel_type(types):
except KeyError:
return xlrd.biffh.XL_CELL_EMPTY
+
def normalize_booleans(values):
normalized = []
@@ -107,6 +124,7 @@ def normalize_booleans(values):
return normalized
+
def normalize_dates(values, datemode=0):
"""
Normalize a column of date cells.
@@ -131,4 +149,5 @@ def normalize_dates(values, datemode=0):
return normalized
+
agate.Table.from_xls = classmethod(from_xls)
diff --git a/agateexcel/table_xlsx.py b/agateexcel/table_xlsx.py
old mode 100644
new mode 100755
index f027d32..e3f3c1d
--- a/agateexcel/table_xlsx.py
+++ b/agateexcel/table_xlsx.py
@@ -13,7 +13,9 @@ import six
NULL_TIME = datetime.time(0, 0, 0)
-def from_xlsx(cls, path, sheet=None, skip_lines=0, **kwargs):
+
+def from_xlsx(cls, path, sheet=None, skip_lines=0, header=True, read_only=True,
+ reset_dimensions=False, **kwargs):
"""
Parse an XLSX file.
@@ -24,6 +26,11 @@ def from_xlsx(cls, path, sheet=None, skip_lines=0, **kwargs):
then the "active" sheet will be used.
:param skip_lines:
The number of rows to skip from the top of the sheet.
+ :param header:
+ If :code:`True`, the first row is assumed to contain column names.
+ :param reset_dimensions:
+ If :code:`True`, do not trust the dimensions in the file's properties,
+ and recalculate them based on the data in the file.
"""
if not isinstance(skip_lines, int):
raise ValueError('skip_lines argument must be an int')
@@ -33,7 +40,7 @@ def from_xlsx(cls, path, sheet=None, skip_lines=0, **kwargs):
else:
f = open(path, 'rb')
- book = openpyxl.load_workbook(f, read_only=True, data_only=True)
+ book = openpyxl.load_workbook(f, read_only=read_only, data_only=True)
multiple = agate.utils.issequence(sheet)
if multiple:
@@ -51,11 +58,14 @@ def from_xlsx(cls, path, sheet=None, skip_lines=0, **kwargs):
else:
sheet = book.active
- column_names = []
+ column_names = None
rows = []
- for i, row in enumerate(sheet.iter_rows(row_offset=skip_lines)):
- if i == 0:
+ if reset_dimensions:
+ sheet.reset_dimensions()
+
+ for i, row in enumerate(sheet.iter_rows(min_row=skip_lines + 1)):
+ if i == 0 and header:
column_names = [None if c.value is None else six.text_type(c.value) for c in row]
continue
@@ -79,6 +89,11 @@ def from_xlsx(cls, path, sheet=None, skip_lines=0, **kwargs):
rows.append(values)
+ if 'column_names' in kwargs:
+ if not header:
+ column_names = kwargs['column_names']
+ del kwargs['column_names']
+
tables[sheet.title] = agate.Table(rows, column_names, **kwargs)
f.close()
@@ -88,6 +103,7 @@ def from_xlsx(cls, path, sheet=None, skip_lines=0, **kwargs):
else:
return tables.popitem()[1]
+
def normalize_datetime(dt):
if dt.microsecond == 0:
return dt
@@ -101,17 +117,14 @@ def normalize_datetime(dt):
return dt
+
def has_date_elements(cell):
"""
Try to use formatting to determine if a cell contains only time info.
See: http://office.microsoft.com/en-us/excel-help/number-format-codes-HP005198679.aspx
"""
- if 'd' in cell.number_format or \
- 'y' in cell.number_format:
-
- return True
+ return 'd' in cell.number_format or 'y' in cell.number_format
- return False
agate.Table.from_xlsx = classmethod(from_xlsx)
diff --git a/docs/conf.py b/docs/conf.py
index 255f713..05d1315 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -1,5 +1,7 @@
# -*- coding: utf-8 -*-
#
+# flake8: noqa
+#
# This file is execfile()d with the current directory set to its containing dir.
#
# Note that not all possible configuration values are present in this
@@ -45,16 +47,16 @@ master_doc = 'index'
# General information about the project.
project = u'agate-excel'
-copyright = u'2015, Christopher Groskopf'
+copyright = u'2017, Christopher Groskopf'
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
# built documents.
#
# The short X.Y version.
-version = '0.2.1'
+version = '0.2.3'
# The full version, including alpha/beta/rc tags.
-release = '0.2.1'
+release = '0.2.3'
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
diff --git a/example.py b/example.py
index 8b41846..c7a5c27 100755
--- a/example.py
+++ b/example.py
@@ -1,7 +1,7 @@
#!/usr/bin/env python
import agate
-import agateexcel
+import agateexcel # noqa
table = agate.Table.from_xls('examples/test.xls')
diff --git a/requirements-py3.txt b/requirements-py3.txt
index b09f6c0..cc5825e 100644
--- a/requirements-py3.txt
+++ b/requirements-py3.txt
@@ -1,5 +1,5 @@
nose>=1.1.2
-tox>=1.3
+tox>=3.1.0
Sphinx>=1.2.2
sphinx_rtd_theme>=0.1.6
wheel>=0.24.0
diff --git a/setup.py b/setup.py
index 1d87130..0f020e6 100644
--- a/setup.py
+++ b/setup.py
@@ -10,7 +10,7 @@ install_requires = [
setup(
name='agate-excel',
- version='0.2.1',
+ version='0.2.3',
description='agate-excel adds read support for Excel files (xls and xlsx) to agate.',
long_description=open('README.rst').read(),
author='Christopher Groskopf',
@@ -26,9 +26,10 @@ setup(
'Operating System :: OS Independent',
'Programming Language :: Python',
'Programming Language :: Python :: 2.7',
- 'Programming Language :: Python :: 3.3',
'Programming Language :: Python :: 3.4',
'Programming Language :: Python :: 3.5',
+ 'Programming Language :: Python :: 3.6',
+ 'Programming Language :: Python :: 3.7',
'Programming Language :: Python :: Implementation :: CPython',
'Programming Language :: Python :: Implementation :: PyPy',
'Topic :: Multimedia :: Graphics',
diff --git a/tests/test_table_xls.py b/tests/test_table_xls.py
index 2194455..6d02d74 100644
--- a/tests/test_table_xls.py
+++ b/tests/test_table_xls.py
@@ -3,33 +3,40 @@
import datetime
-try:
- import unittest2 as unittest
-except ImportError:
- import unittest
-
import agate
-import agateexcel
+import agateexcel # noqa
+
class TestXLS(agate.AgateTestCase):
def setUp(self):
self.rows = (
(1, 'a', True, '11/4/2015', '11/4/2015 12:22 PM'),
(2, u'ðŸ‘', False, '11/5/2015', '11/4/2015 12:45 PM'),
- (None, 'b', None, None, None)
+ (None, 'b', None, None, None),
)
self.column_names = [
- 'number', 'text', 'boolean', 'date', 'datetime'
+ 'number', 'text', 'boolean', 'date', 'datetime',
+ ]
+
+ self.user_provided_column_names = [
+ 'alt number', 'alt text', 'alt boolean', 'alt date', 'alt datetime',
]
self.column_types = [
agate.Number(), agate.Text(), agate.Boolean(),
- agate.Date(), agate.DateTime()
+ agate.Date(), agate.DateTime(),
]
self.table = agate.Table(self.rows, self.column_names, self.column_types)
+ def test_from_xls_with_column_names(self):
+ table = agate.Table.from_xls('examples/test.xls', header=False, skip_lines=1, column_names=self.user_provided_column_names )
+
+ self.assertColumnNames(table, self.user_provided_column_names)
+ self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
+ self.assertRows(table, [r.values() for r in self.table.rows])
+
def test_from_xls(self):
table = agate.Table.from_xls('examples/test.xls')
@@ -81,6 +88,18 @@ class TestXLS(agate.AgateTestCase):
self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
self.assertRows(table, [r.values() for r in self.table.rows])
+ def test_header(self):
+ table = agate.Table.from_xls('examples/test_zeros.xls', header=False)
+
+ self.assertColumnNames(table, ('a', 'b', 'c'))
+ self.assertColumnTypes(table, [agate.Text, agate.Text, agate.Text])
+ self.assertRows(table, [
+ ['ordinal', 'binary', 'all_zero'],
+ ['0.0', '0.0', '0.0'],
+ ['1.0', '1.0', '0.0'],
+ ['2.0', '1.0', '0.0'],
+ ])
+
def test_zeros(self):
table = agate.Table.from_xls('examples/test_zeros.xls')
@@ -89,7 +108,7 @@ class TestXLS(agate.AgateTestCase):
self.assertRows(table, [
[0, 0, 0],
[1, 1, 0],
- [2, 1, 0]
+ [2, 1, 0],
])
def test_ambiguous_date(self):
@@ -98,7 +117,7 @@ class TestXLS(agate.AgateTestCase):
self.assertColumnNames(table, ['s'])
self.assertColumnTypes(table, [agate.Date])
self.assertRows(table, [
- [datetime.date(1900, 1, 1)]
+ [datetime.date(1900, 1, 1)],
])
def test_empty(self):
@@ -114,5 +133,5 @@ class TestXLS(agate.AgateTestCase):
self.assertColumnNames(table, ('Country', '2013.0', 'c'))
self.assertColumnTypes(table, [agate.Text, agate.Number, agate.Text])
self.assertRows(table, [
- ['Canada', 35160000, 'value']
+ ['Canada', 35160000, 'value'],
])
diff --git a/tests/test_table_xlsx.py b/tests/test_table_xlsx.py
index b7fb38c..9b56b9b 100644
--- a/tests/test_table_xlsx.py
+++ b/tests/test_table_xlsx.py
@@ -3,33 +3,40 @@
import datetime
-try:
- import unittest2 as unittest
-except ImportError:
- import unittest
-
import agate
-import agateexcel
+import agateexcel # noqa
+
class TestXLSX(agate.AgateTestCase):
def setUp(self):
self.rows = (
(1, 'a', True, '11/4/2015', '11/4/2015 12:22 PM'),
(2, u'ðŸ‘', False, '11/5/2015', '11/4/2015 12:45 PM'),
- (None, 'b', None, None, None)
+ (None, 'b', None, None, None),
)
self.column_names = [
- 'number', 'text', 'boolean', 'date', 'datetime'
+ 'number', 'text', 'boolean', 'date', 'datetime',
+ ]
+
+ self.user_provided_column_names = [
+ 'number', 'text', 'boolean', 'date', 'datetime',
]
self.column_types = [
agate.Number(), agate.Text(), agate.Boolean(),
- agate.Date(), agate.DateTime()
+ agate.Date(), agate.DateTime(),
]
self.table = agate.Table(self.rows, self.column_names, self.column_types)
+ def test_from_xlsx_with_column_names(self):
+ table = agate.Table.from_xlsx('examples/test.xlsx', header=False, skip_lines=1, column_names=self.user_provided_column_names)
+
+ self.assertColumnNames(table, self.user_provided_column_names)
+ self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
+ self.assertRows(table, [r.values() for r in self.table.rows])
+
def test_from_xlsx(self):
table = agate.Table.from_xlsx('examples/test.xlsx')
@@ -81,13 +88,25 @@ class TestXLSX(agate.AgateTestCase):
self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
self.assertRows(table, [r.values() for r in self.table.rows])
+ def test_header(self):
+ table = agate.Table.from_xls('examples/test_zeros.xls', header=False)
+
+ self.assertColumnNames(table, ('a', 'b', 'c'))
+ self.assertColumnTypes(table, [agate.Text, agate.Text, agate.Text])
+ self.assertRows(table, [
+ ['ordinal', 'binary', 'all_zero'],
+ ['0.0', '0.0', '0.0'],
+ ['1.0', '1.0', '0.0'],
+ ['2.0', '1.0', '0.0'],
+ ])
+
def test_ambiguous_date(self):
table = agate.Table.from_xlsx('examples/test_ambiguous_date.xlsx')
self.assertColumnNames(table, ['s'])
self.assertColumnTypes(table, [agate.Date])
self.assertRows(table, [
- [datetime.date(1899, 12, 31)]
+ [datetime.date(1899, 12, 31)],
])
def test_empty(self):
@@ -103,5 +122,5 @@ class TestXLSX(agate.AgateTestCase):
self.assertColumnNames(table, ['Country', '2013', 'c'])
self.assertColumnTypes(table, [agate.Text, agate.Number, agate.Text])
self.assertRows(table, [
- ['Canada', 35160000, 'value']
+ ['Canada', 35160000, 'value'],
])
diff --git a/tox.ini b/tox.ini
index c75ecc9..779fba2 100644
--- a/tox.ini
+++ b/tox.ini
@@ -1,5 +1,5 @@
[tox]
-envlist = py27,py33,py34,py35,pypy
+envlist = py27,py34,py35,py36,py37,pypy
[testenv]
deps=
@@ -11,15 +11,19 @@ commands=nosetests
deps=
{[testenv]deps}
-[testenv:py33]
+[testenv:py34]
deps=
{[testenv]deps}
-[testenv:py34]
+[testenv:py35]
deps=
{[testenv:py33]deps}
-[testenv:py35]
+[testenv:py36]
+deps=
+ {[testenv:py33]deps}
+
+[testenv:py37]
deps=
{[testenv:py33]deps}
--
GitLab