def _load_workbook(wb, archive, filename, use_iterators, keep_vba):
valid_files = archive.namelist()
# If are going to preserve the vba then attach the archive to the
# workbook so that is available for the save.
if keep_vba:
wb.vba_archive = archive
# get workbook-level information
try:
wb.properties = read_properties_core(archive.read(ARC_CORE))
wb.read_workbook_settings(archive.read(ARC_WORKBOOK))
except KeyError:
wb.properties = DocumentProperties()
try:
string_table = read_string_table(archive.read(ARC_SHARED_STRINGS))
except KeyError:
string_table = {}
try:
wb.loaded_theme = archive.read(ARC_THEME) # some writers don't output a theme, live with it (fixes #160)
except KeyError:
assert wb.loaded_theme == None, "even though the theme information is missing there is a theme object ?"
style_properties = read_style_table(archive.read(ARC_STYLE))
style_table = style_properties.pop('table')
wb.style_properties = style_properties
wb.properties.excel_base_date = read_excel_base_date(xml_source=archive.read(ARC_WORKBOOK))
# get worksheets
wb.worksheets = [] # remove preset worksheet
content_types = read_content_types(archive.read(ARC_CONTENT_TYPES))
sheet_types = [(sheet, contyp) for sheet, contyp in content_types if contyp in WORK_OR_CHART_TYPE]
sheet_names = read_sheets_titles(archive.read(ARC_WORKBOOK))
worksheet_names = [worksheet for worksheet, sheet_type in zip(sheet_names, sheet_types) if sheet_type[1] == VALID_WORKSHEET]
for i, sheet_name in enumerate(worksheet_names):
sheet_codename = 'sheet%d.xml' % (i + 1)
worksheet_path = '%s/%s' % (PACKAGE_WORKSHEETS, sheet_codename)
if not worksheet_path in valid_files:
continue
if not use_iterators:
new_ws = read_worksheet(archive.read(worksheet_path), wb, sheet_name, string_table, style_table, style_properties['color_index'], keep_vba=keep_vba)
else:
xml_source = unpack_worksheet(archive, worksheet_path)
new_ws = read_worksheet(xml_source, wb, sheet_name, string_table, style_table, style_properties['color_index'], filename, sheet_codename)
wb.add_sheet(new_ws, index=i)
wb._named_ranges = read_named_ranges(archive.read(ARC_WORKBOOK), wb)
def test_read_content_types(datadir, DummyArchive):
from openpyxl.reader.workbook import read_content_types
archive = DummyArchive
datadir.chdir()
with open("content_types.xml") as src:
archive.writestr(ARC_CONTENT_TYPES, src.read())
assert list(read_content_types(archive)) == [
('/xl/workbook.xml',
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml'
),
('/xl/worksheets/sheet1.xml',
'application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml'
),
('/xl/chartsheets/sheet1.xml',
'application/vnd.openxmlformats-officedocument.spreadsheetml.chartsheet+xml'
),
('/xl/worksheets/sheet2.xml',
'application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml'
),
('/xl/theme/theme1.xml',
'application/vnd.openxmlformats-officedocument.theme+xml'),
('/xl/styles.xml',
'application/vnd.openxmlformats-officedocument.spreadsheetml.styles+xml'
),
('/xl/sharedStrings.xml',
'application/vnd.openxmlformats-officedocument.spreadsheetml.sharedStrings+xml'
),
('/xl/drawings/drawing1.xml',
'application/vnd.openxmlformats-officedocument.drawing+xml'),
('/xl/charts/chart1.xml',
'application/vnd.openxmlformats-officedocument.drawingml.chart+xml'),
('/xl/drawings/drawing2.xml',
'application/vnd.openxmlformats-officedocument.drawing+xml'),
('/xl/charts/chart2.xml',
'application/vnd.openxmlformats-officedocument.drawingml.chart+xml'),
('/xl/calcChain.xml',
'application/vnd.openxmlformats-officedocument.spreadsheetml.calcChain+xml'
),
('/docProps/core.xml',
'application/vnd.openxmlformats-package.core-properties+xml'),
('/docProps/app.xml',
'application/vnd.openxmlformats-officedocument.extended-properties+xml'
)
]
def test_read_content_types():
from openpyxl.reader.workbook import read_content_types
fname = os.path.join(DATADIR, "reader", "contains_chartsheets.xlsx")
archive = zipfile.ZipFile(fname)
assert list(read_content_types(archive)) == [
('/xl/workbook.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml'),
('/xl/worksheets/sheet1.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml'),
('/xl/chartsheets/sheet1.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.chartsheet+xml'),
('/xl/worksheets/sheet2.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml'),
('/xl/theme/theme1.xml', 'application/vnd.openxmlformats-officedocument.theme+xml'),
('/xl/styles.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.styles+xml'),
('/xl/sharedStrings.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sharedStrings+xml'),
('/xl/drawings/drawing1.xml', 'application/vnd.openxmlformats-officedocument.drawing+xml'),
('/xl/charts/chart1.xml', 'application/vnd.openxmlformats-officedocument.drawingml.chart+xml'),
('/xl/drawings/drawing2.xml', 'application/vnd.openxmlformats-officedocument.drawing+xml'),
('/xl/charts/chart2.xml', 'application/vnd.openxmlformats-officedocument.drawingml.chart+xml'),
('/xl/calcChain.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.calcChain+xml'),
('/docProps/core.xml', 'application/vnd.openxmlformats-package.core-properties+xml'),
('/docProps/app.xml', 'application/vnd.openxmlformats-officedocument.extended-properties+xml')
]
def test_read_content_types(datadir):
from openpyxl.reader.workbook import read_content_types
datadir.join("reader").chdir()
archive = zipfile.ZipFile("contains_chartsheets.xlsx")
assert list(read_content_types(archive)) == [
('/xl/workbook.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml'),
('/xl/worksheets/sheet1.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml'),
('/xl/chartsheets/sheet1.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.chartsheet+xml'),
('/xl/worksheets/sheet2.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml'),
('/xl/theme/theme1.xml', 'application/vnd.openxmlformats-officedocument.theme+xml'),
('/xl/styles.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.styles+xml'),
('/xl/sharedStrings.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sharedStrings+xml'),
('/xl/drawings/drawing1.xml', 'application/vnd.openxmlformats-officedocument.drawing+xml'),
('/xl/charts/chart1.xml', 'application/vnd.openxmlformats-officedocument.drawingml.chart+xml'),
('/xl/drawings/drawing2.xml', 'application/vnd.openxmlformats-officedocument.drawing+xml'),
('/xl/charts/chart2.xml', 'application/vnd.openxmlformats-officedocument.drawingml.chart+xml'),
('/xl/calcChain.xml', 'application/vnd.openxmlformats-officedocument.spreadsheetml.calcChain+xml'),
('/docProps/core.xml', 'application/vnd.openxmlformats-package.core-properties+xml'),
('/docProps/app.xml', 'application/vnd.openxmlformats-officedocument.extended-properties+xml')
]
def test_read_content_types(datadir, DummyArchive):
from openpyxl.reader.workbook import read_content_types
archive = DummyArchive
datadir.chdir()
with open("content_types.xml") as src:
archive.writestr(ARC_CONTENT_TYPES, src.read())
assert list(read_content_types(archive)) == [
("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml", "/xl/workbook.xml"),
("application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml", "/xl/worksheets/sheet1.xml"),
("application/vnd.openxmlformats-officedocument.spreadsheetml.chartsheet+xml", "/xl/chartsheets/sheet1.xml"),
("application/vnd.openxmlformats-officedocument.spreadsheetml.worksheet+xml", "/xl/worksheets/sheet2.xml"),
("application/vnd.openxmlformats-officedocument.theme+xml", "/xl/theme/theme1.xml"),
("application/vnd.openxmlformats-officedocument.spreadsheetml.styles+xml", "/xl/styles.xml"),
("application/vnd.openxmlformats-officedocument.spreadsheetml.sharedStrings+xml", "/xl/sharedStrings.xml"),
("application/vnd.openxmlformats-officedocument.drawing+xml", "/xl/drawings/drawing1.xml"),
("application/vnd.openxmlformats-officedocument.drawingml.chart+xml", "/xl/charts/chart1.xml"),
("application/vnd.openxmlformats-officedocument.drawing+xml", "/xl/drawings/drawing2.xml"),
("application/vnd.openxmlformats-officedocument.drawingml.chart+xml", "/xl/charts/chart2.xml"),
("application/vnd.openxmlformats-officedocument.spreadsheetml.calcChain+xml", "/xl/calcChain.xml"),
("application/vnd.openxmlformats-package.core-properties+xml", "/docProps/core.xml"),
("application/vnd.openxmlformats-officedocument.extended-properties+xml", "/docProps/app.xml"),
]
def load_workbook(filename, read_only=False, use_iterators=False, keep_vba=False, guess_types=False, data_only=False):
"""Open the given filename and return the workbook
:param filename: the path to open or a file-like object
:type filename: string or a file-like object open in binary mode c.f., :class:`zipfile.ZipFile`
:param read_only: optimised for reading, content cannot be edited
:type read_only: bool
:param use_iterators: use lazy load for cells
:type use_iterators: bool
:param keep_vba: preseve vba content (this does NOT mean you can use it)
:type keep_vba: bool
:param guess_types: guess cell content type and do not read it from the file
:type guess_types: bool
:param data_only: controls whether cells with formulae have either the formula (default) or the value stored the last time Excel read the sheet
:type data_only: bool
:rtype: :class:`openpyxl.workbook.Workbook`
.. note::
When using lazy load, all worksheets will be :class:`openpyxl.worksheet.iter_worksheet.IterableWorksheet`
and the returned workbook will be read-only.
"""
archive = _validate_archive(filename)
read_only = read_only or use_iterators
wb = Workbook(guess_types=guess_types, data_only=data_only, read_only=read_only)
if read_only and guess_types:
warnings.warn('Data types are not guessed when using iterator reader')
valid_files = archive.namelist()
# If are going to preserve the vba then attach a copy of the archive to the
# workbook so that is available for the save.
if keep_vba:
try:
f = open(filename, 'rb')
s = f.read()
f.close()
except:
pos = filename.tell()
filename.seek(0)
s = filename.read()
filename.seek(pos)
wb.vba_archive = ZipFile(BytesIO(s), 'r')
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
try:
wb.properties = read_properties(archive.read(ARC_CORE))
except KeyError:
wb.properties = DocumentProperties()
wb.active = read_workbook_settings(archive.read(ARC_WORKBOOK)) or 0
# what content types do we have?
cts = dict(read_content_types(archive))
strings_path = cts.get(SHARED_STRINGS)
if strings_path is not None:
if strings_path.startswith("/"):
strings_path = strings_path[1:]
shared_strings = read_string_table(archive.read(strings_path))
else:
shared_strings = []
wb.is_template = XLTX in cts or XLTM in cts
try:
wb.loaded_theme = archive.read(ARC_THEME) # some writers don't output a theme, live with it (fixes #160)
except KeyError:
assert wb.loaded_theme == None, "even though the theme information is missing there is a theme object ?"
parsed_styles = read_style_table(archive)
if parsed_styles is not None:
wb._differential_styles = parsed_styles.differential_styles
wb._cell_styles = parsed_styles.cell_styles
wb._named_styles = parsed_styles.named_styles
wb._colors = parsed_styles.color_index
wb._borders = parsed_styles.border_list
wb._fonts = parsed_styles.font_list
wb._fills = parsed_styles.fill_list
wb._number_formats = parsed_styles.number_formats
wb._protections = parsed_styles.protections
wb._alignments = parsed_styles.alignments
wb._colors = parsed_styles.color_index
wb.excel_base_date = read_excel_base_date(archive)
# get worksheets
wb._sheets = [] # remove preset worksheet
for sheet in detect_worksheets(archive):
sheet_name = sheet['title']
worksheet_path = sheet['path']
if not worksheet_path in valid_files:
continue
if read_only:
new_ws = ReadOnlyWorksheet(wb, sheet_name, worksheet_path, None,
shared_strings)
wb._add_sheet(new_ws)
else:
fh = archive.open(worksheet_path)
parser = WorkSheetParser(wb, sheet_name, fh, shared_strings)
parser.parse()
new_ws = wb[sheet_name]
new_ws.sheet_state = sheet['state']
if wb.vba_archive is not None and new_ws.legacy_drawing is not None:
# We need to get the file name of the legacy drawing
dirname, basename = worksheet_path.rsplit('/', 1)
rels_path = '/'.join((dirname, '_rels', basename + '.rels'))
rels = get_dependents(archive, rels_path)
new_ws.legacy_drawing = rels[new_ws.legacy_drawing].target
if not read_only:
# load comments into the worksheet cells
comments_file = get_comments_file(worksheet_path, archive, valid_files)
if comments_file is not None:
read_comments(new_ws, archive.read(comments_file))
drawings_file = get_drawings_file(worksheet_path, archive, valid_files)
if drawings_file is not None:
read_drawings(new_ws, drawings_file, archive, valid_files)
wb._differential_styles = [] # reset
wb._named_ranges = list(read_named_ranges(archive.read(ARC_WORKBOOK), wb))
wb.code_name = read_workbook_code_name(archive.read(ARC_WORKBOOK))
if EXTERNAL_LINK in cts:
rels = read_rels(archive)
wb._external_links = list(detect_external_links(rels, archive))
archive.close()
return wb
def check_content_type(workbook_type, archive):
assert workbook_type in dict(read_content_types(archive))
def _load_workbook(wb, archive, filename, use_iterators, keep_vba):
valid_files = archive.namelist()
# If are going to preserve the vba then attach the archive to the
# workbook so that is available for the save.
if keep_vba:
wb.vba_archive = archive
if use_iterators:
wb._archive = ZipFile(filename)
# get workbook-level information
try:
wb.properties = read_properties_core(archive.read(ARC_CORE))
wb.read_workbook_settings(archive.read(ARC_WORKBOOK))
except KeyError:
wb.properties = DocumentProperties()
try:
string_table = read_string_table(archive.read(ARC_SHARED_STRINGS))
except KeyError:
string_table = {}
try:
wb.loaded_theme = archive.read(
ARC_THEME
) # some writers don't output a theme, live with it (fixes #160)
except KeyError:
assert wb.loaded_theme == None, "even though the theme information is missing there is a theme object ?"
style_properties = read_style_table(archive.read(ARC_STYLE))
style_table = style_properties.pop('table')
wb.style_properties = style_properties
wb.properties.excel_base_date = read_excel_base_date(
xml_source=archive.read(ARC_WORKBOOK))
# get worksheets
wb.worksheets = [] # remove preset worksheet
content_types = read_content_types(archive.read(ARC_CONTENT_TYPES))
sheet_types = [(sheet, contyp) for sheet, contyp in content_types
if contyp in WORK_OR_CHART_TYPE]
sheet_names = read_sheets_titles(archive.read(ARC_WORKBOOK))
worksheet_names = [
worksheet for worksheet, sheet_type in zip(sheet_names, sheet_types)
if sheet_type[1] == VALID_WORKSHEET
]
for i, sheet_name in enumerate(worksheet_names):
sheet_codename = 'sheet%d.xml' % (i + 1)
worksheet_path = '%s/%s' % (PACKAGE_WORKSHEETS, sheet_codename)
if not worksheet_path in valid_files:
continue
if not use_iterators:
new_ws = read_worksheet(
archive.read(worksheet_path),
wb,
sheet_name,
string_table,
style_table,
color_index=style_properties['color_index'],
keep_vba=keep_vba)
else:
new_ws = read_worksheet(
None,
wb,
sheet_name,
string_table,
style_table,
color_index=style_properties['color_index'],
sheet_codename=sheet_codename)
wb.add_sheet(new_ws, index=i)
if not use_iterators:
# load comments into the worksheet cells
comments_file = get_comments_file(sheet_codename, archive,
valid_files)
if comments_file is not None:
read_comments(new_ws, archive.read(comments_file))
wb._named_ranges = read_named_ranges(archive.read(ARC_WORKBOOK), wb)
def _load_workbook(wb, archive, filename, read_only, keep_vba):
valid_files = archive.namelist()
# If are going to preserve the vba then attach a copy of the archive to the
# workbook so that is available for the save.
if keep_vba:
try:
f = open(filename, 'rb')
s = f.read()
f.close()
except:
pos = filename.tell()
filename.seek(0)
s = filename.read()
filename.seek(pos)
wb.vba_archive = ZipFile(BytesIO(s), 'r')
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
try:
wb.properties = read_properties_core(archive.read(ARC_CORE))
except KeyError:
wb.properties = DocumentProperties()
wb._read_workbook_settings(archive.read(ARC_WORKBOOK))
# what content types do we have?
cts = dict(read_content_types(archive))
rels = dict
strings_path = cts.get(SHARED_STRINGS)
if strings_path is not None:
if strings_path.startswith("/"):
strings_path = strings_path[1:]
shared_strings = read_string_table(archive.read(strings_path))
else:
shared_strings = []
try:
wb.loaded_theme = archive.read(
ARC_THEME
) # some writers don't output a theme, live with it (fixes #160)
except KeyError:
assert wb.loaded_theme == None, "even though the theme information is missing there is a theme object ?"
style_table, color_index, cond_styles = read_style_table(
archive.read(ARC_STYLE))
wb.shared_styles = style_table
wb.style_properties = {'dxf_list': cond_styles}
wb.cond_styles = cond_styles
wb.properties.excel_base_date = read_excel_base_date(
xml_source=archive.read(ARC_WORKBOOK))
# get worksheets
wb.worksheets = [] # remove preset worksheet
for sheet in detect_worksheets(archive):
sheet_name = sheet['title']
worksheet_path = sheet['path']
if not worksheet_path in valid_files:
continue
if not read_only:
new_ws = read_worksheet(archive.read(worksheet_path),
wb,
sheet_name,
shared_strings,
style_table,
color_index=color_index,
keep_vba=keep_vba)
else:
new_ws = read_worksheet(None,
wb,
sheet_name,
shared_strings,
style_table,
color_index=color_index,
worksheet_path=worksheet_path)
new_ws.sheet_state = sheet.get('state') or 'visible'
wb._add_sheet(new_ws)
if not read_only:
# load comments into the worksheet cells
comments_file = get_comments_file(worksheet_path, archive,
valid_files)
if comments_file is not None:
read_comments(new_ws, archive.read(comments_file))
drawings_file = get_drawings_file(worksheet_path, archive,
valid_files)
if drawings_file is not None:
read_drawings(new_ws, drawings_file, archive, valid_files)
wb._named_ranges = list(read_named_ranges(archive.read(ARC_WORKBOOK), wb))
wb.code_name = read_workbook_code_name(archive.read(ARC_WORKBOOK))
if EXTERNAL_LINK in cts:
rels = read_rels(archive)
wb._external_links = list(detect_external_links(rels, archive))
def _load_workbook(wb, archive, filename, read_only, keep_vba):
valid_files = archive.namelist()
# If are going to preserve the vba then attach a copy of the archive to the
# workbook so that is available for the save.
if keep_vba:
try:
f = open(filename, 'rb')
s = f.read()
f.close()
except:
pos = filename.tell()
filename.seek(0)
s = filename.read()
filename.seek(pos)
wb.vba_archive = ZipFile(BytesIO(s), 'r')
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
try:
wb.properties = read_properties_core(archive.read(ARC_CORE))
except KeyError:
wb.properties = DocumentProperties()
wb._read_workbook_settings(archive.read(ARC_WORKBOOK))
# what content types do we have?
cts = dict(read_content_types(archive))
rels = dict
strings_path = cts.get(SHARED_STRINGS)
if strings_path is not None:
if strings_path.startswith("/"):
strings_path = strings_path[1:]
shared_strings = read_string_table(archive.read(strings_path))
else:
shared_strings = []
try:
wb.loaded_theme = archive.read(ARC_THEME) # some writers don't output a theme, live with it (fixes #160)
except KeyError:
assert wb.loaded_theme == None, "even though the theme information is missing there is a theme object ?"
style_table, color_index, cond_styles = read_style_table(archive.read(ARC_STYLE))
wb.shared_styles = style_table
wb.style_properties = {'dxf_list':cond_styles}
wb.cond_styles = cond_styles
wb.properties.excel_base_date = read_excel_base_date(xml_source=archive.read(ARC_WORKBOOK))
# get worksheets
wb.worksheets = [] # remove preset worksheet
for sheet in detect_worksheets(archive):
sheet_name = sheet['title']
worksheet_path = sheet['path']
if not worksheet_path in valid_files:
continue
if not read_only:
new_ws = read_worksheet(archive.read(worksheet_path), wb,
sheet_name, shared_strings, style_table,
color_index=color_index,
keep_vba=keep_vba)
else:
new_ws = read_worksheet(None, wb, sheet_name, shared_strings,
style_table,
color_index=color_index,
worksheet_path=worksheet_path)
new_ws.sheet_state = sheet.get('state') or 'visible'
wb._add_sheet(new_ws)
if not read_only:
# load comments into the worksheet cells
comments_file = get_comments_file(worksheet_path, archive, valid_files)
if comments_file is not None:
read_comments(new_ws, archive.read(comments_file))
wb._named_ranges = list(read_named_ranges(archive.read(ARC_WORKBOOK), wb))
if EXTERNAL_LINK in cts:
rels = read_rels(archive)
wb._external_links = list(detect_external_links(rels, archive))
def check_content_type(workbook_type, archive):
assert workbook_type in dict(read_content_types(archive))
