def test_write(self, DummyPivotTable):
out = BytesIO()
archive = ZipFile(out, "w")
manifest = Manifest()
defn = DummyPivotTable
defn._write(archive, manifest)
assert archive.namelist() == [defn.path[1:]]
assert manifest.find(defn.mime_type)
def test_write(self, DummyCache):
out = BytesIO()
archive = ZipFile(out, mode="w")
manifest = Manifest()
xml = tostring(DummyCache.to_tree())
DummyCache._write(archive, manifest)
assert archive.namelist() == [DummyCache.path[1:]]
assert manifest.find(DummyCache.mime_type)
def __init__(self, workbook, archive):
self._archive = archive
self.workbook = workbook
self.manifest = Manifest()
self.vba_modified = set()
self._tables = []
self._charts = []
self._images = []
self._drawings = []
self._comments = []
def test_write(self, RecordList):
out = BytesIO()
archive = ZipFile(out, mode="w")
manifest = Manifest()
records = RecordList()
xml = tostring(records.to_tree())
records._write(archive, manifest)
manifest.append(records)
assert archive.namelist() == [records.path[1:]]
assert manifest.find(records.mime_type)
def load_workbook_img(
filename,
read_only=False,
keep_vba=False,
guess_types=False,
data_only=False,
):
archive = _validate_archive(filename)
src = archive.read(ARC_CONTENT_TYPES)
root = fromstring(src)
package = Manifest.from_tree(root)
wb = load_workbook(filename, read_only, keep_vba, guess_types, data_only)
valid_files = archive.namelist()
wb_sheet_names = wb.sheetnames
wb_part = _find_workbook_part(package)
parser = WorkbookParser(archive, wb_part.PartName[1:])
parser.parse()
for sheet, rel in parser.find_sheets():
sheet_name = sheet.name
ws = wb[sheet_name]
worksheet_path = rel.target
if not worksheet_path in valid_files:
continue
if not sheet_name in wb_sheet_names:
continue
drawings_file = get_drawings_file(worksheet_path, archive, valid_files)
if drawings_file is not None:
ws = wb[sheet_name]
read_drawings(ws, drawings_file, archive, valid_files)
return wb
def __init__(self, workbook, archive):
self.archive = archive
self.workbook = workbook
self.manifest = Manifest()
self.vba_modified = set()
self._tables = []
self._charts = []
self._images = []
self._drawings = []
self._comments = []
def test_overwritten_default():
from ..excel import _find_workbook_part
src = """
<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
<Default Extension="xml" ContentType="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet.main+xml"/>
</Types>
"""
node = fromstring(src)
package = Manifest.from_tree(node)
assert _find_workbook_part(package) == Override("/xl/workbook.xml", XLSX)
def test_find_standard_workbook_part(datadir, wb_type, wb_name):
from ..excel import _find_workbook_part
src = """
<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
<Override ContentType="{0}"
PartName="{1}"/>
</Types>
""".format(wb_type, wb_name)
node = fromstring(src)
package = Manifest.from_tree(node)
assert _find_workbook_part(package) == Override(wb_name, wb_type)
def load_workbook(filename, read_only=False, keep_vba=KEEP_VBA,
data_only=False, guess_types=False, keep_links=True):
"""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 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
:param keep_links: whether links to external workbooks should be preserved. The default is True
:type keep_links: 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
src = archive.read(ARC_CONTENT_TYPES)
root = fromstring(src)
package = Manifest.from_tree(root)
wb_part = _find_workbook_part(package)
parser = WorkbookParser(archive, wb_part.PartName[1:])
wb = parser.wb
wb._data_only = data_only
wb._read_only = read_only
wb._keep_links = keep_links
wb.guess_types = guess_types
wb.template = wb_part.ContentType in (XLTX, XLTM)
parser.parse()
wb._sheets = []
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:
wb.vba_archive = ZipFile(BytesIO(), 'a', ZIP_DEFLATED)
for name in archive.namelist():
wb.vba_archive.writestr(name, archive.read(name))
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
if ARC_CORE in valid_files:
src = fromstring(archive.read(ARC_CORE))
wb.properties = DocumentProperties.from_tree(src)
shared_strings = []
ct = package.find(SHARED_STRINGS)
if ct is not None:
strings_path = ct.PartName[1:]
shared_strings = read_string_table(archive.read(strings_path))
if ARC_THEME in valid_files:
wb.loaded_theme = archive.read(ARC_THEME)
apply_stylesheet(archive, wb) # bind styles to workbook
pivot_caches = parser.pivot_caches
# get worksheets
for sheet, rel in parser.find_sheets():
sheet_name = sheet.name
worksheet_path = rel.target
rels_path = get_rels_path(worksheet_path)
rels = []
if rels_path in valid_files:
rels = get_dependents(archive, rels_path)
if not worksheet_path in valid_files:
continue
if read_only:
ws = ReadOnlyWorksheet(wb, sheet_name, worksheet_path, None,
shared_strings)
wb._sheets.append(ws)
else:
fh = archive.open(worksheet_path)
ws = wb.create_sheet(sheet_name)
ws._rels = rels
ws_parser = WorkSheetParser(ws, fh, shared_strings)
ws_parser.parse()
if rels:
# assign any comments to cells
for r in rels.find(COMMENTS_NS):
src = archive.read(r.target)
comment_sheet = CommentSheet.from_tree(fromstring(src))
for ref, comment in comment_sheet.comments:
ws[ref].comment = comment
# preserve link to VML file if VBA
if (
wb.vba_archive is not None
and ws.legacy_drawing is not None
):
ws.legacy_drawing = rels[ws.legacy_drawing].target
for t in ws_parser.tables:
src = archive.read(t)
xml = fromstring(src)
table = Table.from_tree(xml)
ws.add_table(table)
pivot_rel = rels.find(TableDefinition.rel_type)
for r in pivot_rel:
pivot_path = r.Target
src = archive.read(pivot_path)
tree = fromstring(src)
pivot = TableDefinition.from_tree(tree)
pivot.cache = pivot_caches[pivot.cacheId]
ws.add_pivot(pivot)
ws.sheet_state = sheet.state
ws._rels = [] # reset
parser.assign_names()
#wb._differential_styles.styles = [] # tables may depened upon dxf
archive.close()
return wb
def load_workbook(filename, read_only=False, keep_vba=KEEP_VBA,
data_only=False, guess_types=False, keep_links=True):
"""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 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
:param keep_links: whether links to external workbooks should be preserved. The default is True
:type keep_links: 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
parser = WorkbookParser(archive)
wb = parser.wb
wb._data_only = data_only
wb._read_only = read_only
wb._keep_links = keep_links
wb.guess_types = guess_types
parser.parse()
wb._sheets = []
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:
wb.vba_archive = ZipFile(BytesIO(), 'a', ZIP_DEFLATED)
for name in archive.namelist():
wb.vba_archive.writestr(name, archive.read(name))
if read_only:
wb._archive = ZipFile(filename)
# get workbook-level information
if ARC_CORE in valid_files:
src = fromstring(archive.read(ARC_CORE))
wb.properties = DocumentProperties.from_tree(src)
# is workbook a template or note
src = archive.read(ARC_CONTENT_TYPES)
root = fromstring(src)
package = Manifest.from_tree(root)
wb.template = XLTX in package or XLTM in package
shared_strings = []
ct = package.find(SHARED_STRINGS)
if ct is not None:
strings_path = ct.PartName[1:]
shared_strings = read_string_table(archive.read(strings_path))
if ARC_THEME in valid_files:
wb.loaded_theme = archive.read(ARC_THEME)
apply_stylesheet(archive, wb) # bind styles to workbook
# get worksheets
for sheet, rel in parser.find_sheets():
sheet_name = sheet.name
worksheet_path = rel.target
rels_path = get_rels_path(worksheet_path)
rels = []
if rels_path in valid_files:
rels = get_dependents(archive, rels_path)
if not worksheet_path in valid_files:
continue
if read_only:
ws = ReadOnlyWorksheet(wb, sheet_name, worksheet_path, None,
shared_strings)
wb._sheets.append(ws)
else:
fh = archive.open(worksheet_path)
ws = wb.create_sheet(sheet_name)
ws._rels = rels
ws_parser = WorkSheetParser(ws, fh, shared_strings)
ws_parser.parse()
if rels:
# assign any comments to cells
for r in rels.find(COMMENTS_NS):
src = archive.read(r.target)
comment_sheet = CommentSheet.from_tree(fromstring(src))
for ref, comment in comment_sheet.comments:
ws[ref].comment = comment
# preserve link to VML file if VBA
if (
wb.vba_archive is not None
and ws.legacy_drawing is not None
):
ws.legacy_drawing = rels[ws.legacy_drawing].target
ws.sheet_state = sheet.state
ws._rels = [] # reset
parser.assign_names()
wb._differential_styles.styles = []
archive.close()
return wb
def check_content_type(workbook_type, archive):
src = archive.read(ARC_CONTENT_TYPES)
node = fromstring(src)
package = Manifest.from_tree(node)
assert workbook_type in package
def test_no_workbook():
from ..excel import _find_workbook_part
with pytest.raises(IOError):
part = _find_workbook_part(Manifest())
class ExcelWriter(object):
"""Write a workbook object to an Excel file."""
def __init__(self, workbook, archive):
self._archive = archive
self.workbook = workbook
self.manifest = Manifest()
self.vba_modified = set()
self._tables = []
self._charts = []
self._images = []
self._drawings = []
self._comments = []
self._pivots = []
def write_data(self):
"""Write the various xml files into the zip archive."""
# cleanup all worksheets
archive = self._archive
archive.writestr(ARC_ROOT_RELS, write_root_rels(self.workbook))
props = ExtendedProperties()
archive.writestr(ARC_APP, tostring(props.to_tree()))
archive.writestr(ARC_CORE,
tostring(self.workbook.properties.to_tree()))
if self.workbook.loaded_theme:
archive.writestr(ARC_THEME, self.workbook.loaded_theme)
else:
archive.writestr(ARC_THEME, write_theme())
self._write_worksheets()
self._write_chartsheets()
self._write_images()
self._write_charts()
self._archive.writestr(
ARC_SHARED_STRINGS,
write_string_table(self.workbook.shared_strings))
self._write_external_links()
stylesheet = write_stylesheet(self.workbook)
archive.writestr(ARC_STYLE, tostring(stylesheet))
archive.writestr(ARC_WORKBOOK, write_workbook(self.workbook))
archive.writestr(ARC_WORKBOOK_RELS, write_workbook_rels(self.workbook))
self._merge_vba()
self.manifest._write(archive, self.workbook)
def _merge_vba(self):
"""
If workbook contains macros then extract associated files from cache
of old file and add to archive
"""
ARC_VBA = re.compile("|".join(
('xl/vba', r'xl/drawings/.*vmlDrawing\d\.vml', 'xl/ctrlProps',
'customUI', 'xl/activeX', r'xl/media/.*\.emf')))
if self.workbook.vba_archive:
for name in set(
self.workbook.vba_archive.namelist()) - self.vba_modified:
if ARC_VBA.match(name):
self._archive.writestr(
name, self.workbook.vba_archive.read(name))
def _write_images(self):
# delegate to object
for img in self._images:
self._archive.writestr(img.path[1:], img._data())
def _write_charts(self):
# delegate to object
if len(self._charts) != len(set(self._charts)):
raise InvalidFileException(
"The same chart cannot be used in more than one worksheet")
for chart in self._charts:
self._archive.writestr(chart.path[1:], tostring(chart._write()))
self.manifest.append(chart)
def _write_drawing(self, drawing):
"""
Write a drawing
"""
self._drawings.append(drawing)
drawing._id = len(self._drawings)
for chart in drawing.charts:
self._charts.append(chart)
chart._id = len(self._charts)
for img in drawing.images:
self._images.append(img)
img._id = len(self._images)
rels_path = get_rels_path(drawing.path)[1:]
self._archive.writestr(drawing.path[1:], tostring(drawing._write()))
self._archive.writestr(rels_path, tostring(drawing._write_rels()))
self.manifest.append(drawing)
def _write_chartsheets(self):
for idx, sheet in enumerate(self.workbook.chartsheets, 1):
sheet._id = idx
xml = tostring(sheet.to_tree())
self._archive.writestr(sheet.path[1:], xml)
self.manifest.append(sheet)
if sheet._drawing:
self._write_drawing(sheet._drawing)
rel = Relationship(type="drawing", Target=sheet._drawing.path)
rels = RelationshipList()
rels.append(rel)
tree = rels.to_tree()
rels_path = get_rels_path(sheet.path[1:])
self._archive.writestr(rels_path, tostring(tree))
def _write_comment(self, ws):
cs = CommentSheet.from_comments(ws._comments)
self._comments.append(cs)
cs._id = len(self._comments)
self._archive.writestr(cs.path[1:], tostring(cs.to_tree()))
self.manifest.append(cs)
if ws.legacy_drawing is None:
ws.legacy_drawing = 'xl/drawings/commentsDrawing{0}.vml'.format(
cs._id)
vml = None
else:
vml = fromstring(self.workbook.vba_archive.read(ws.legacy_drawing))
vml = cs.write_shapes(vml)
self._archive.writestr(ws.legacy_drawing, vml)
self.vba_modified.add(ws.legacy_drawing)
comment_rel = Relationship(Id="comments",
type=cs._rel_type,
Target=cs.path)
ws._rels.append(comment_rel)
def _write_worksheets(self):
pivot_caches = set()
for idx, ws in enumerate(self.workbook.worksheets, 1):
ws._id = idx
xml = ws._write()
rels_path = get_rels_path(ws.path)[1:]
self._archive.writestr(ws.path[1:], xml)
self.manifest.append(ws)
if ws._drawing:
self._write_drawing(ws._drawing)
for r in ws._rels.Relationship:
if "drawing" in r.Type:
r.Target = ws._drawing.path
if ws._comments:
self._write_comment(ws)
if ws.legacy_drawing is not None:
shape_rel = Relationship(type="vmlDrawing",
Id="anysvml",
Target="/" + ws.legacy_drawing)
ws._rels.append(shape_rel)
for t in ws._tables:
self._tables.append(t)
t.id = len(self._tables)
t._write(self._archive)
self.manifest.append(t)
ws._rels[t._rel_id].Target = t.path
for p in ws._pivots:
if p.cache not in pivot_caches:
pivot_caches.add(p.cache)
p.cache._id = len(pivot_caches)
self._pivots.append(p)
p._id = len(self._pivots)
p._write(self._archive, self.manifest)
self.workbook._pivots.append(p)
r = Relationship(Type=p.rel_type, Target=p.path)
ws._rels.append(r)
if ws._rels:
tree = ws._rels.to_tree()
self._archive.writestr(rels_path, tostring(tree))
def _write_external_links(self):
# delegate to object
"""Write links to external workbooks"""
wb = self.workbook
for idx, link in enumerate(wb._external_links, 1):
link._id = idx
rels_path = get_rels_path(link.path[1:])
xml = link.to_tree()
self._archive.writestr(link.path[1:], tostring(xml))
rels = RelationshipList()
rels.append(link.file_link)
self._archive.writestr(rels_path, tostring(rels.to_tree()))
self.manifest.append(link)
def save(self, filename):
"""Write data into the archive."""
self.write_data()
self._archive.close()
def read_manifest(self):
src = self.archive.read(ARC_CONTENT_TYPES)
root = fromstring(src)
self.package = Manifest.from_tree(root)
class ExcelWriter(object):
"""Write a workbook object to an Excel file."""
def __init__(self, workbook, archive):
self._archive = archive
self.workbook = workbook
self.manifest = Manifest()
self.vba_modified = set()
self._tables = []
self._charts = []
self._images = []
self._drawings = []
self._comments = []
self._pivots = []
def write_data(self):
"""Write the various xml files into the zip archive."""
# cleanup all worksheets
archive = self._archive
archive.writestr(ARC_ROOT_RELS, write_root_rels(self.workbook))
props = ExtendedProperties()
archive.writestr(ARC_APP, tostring(props.to_tree()))
archive.writestr(ARC_CORE, tostring(self.workbook.properties.to_tree()))
if self.workbook.loaded_theme:
archive.writestr(ARC_THEME, self.workbook.loaded_theme)
else:
archive.writestr(ARC_THEME, write_theme())
self._write_worksheets()
self._write_chartsheets()
self._write_images()
self._write_charts()
self._archive.writestr(ARC_SHARED_STRINGS,
write_string_table(self.workbook.shared_strings))
self._write_external_links()
stylesheet = write_stylesheet(self.workbook)
archive.writestr(ARC_STYLE, tostring(stylesheet))
archive.writestr(ARC_WORKBOOK, write_workbook(self.workbook))
archive.writestr(ARC_WORKBOOK_RELS, write_workbook_rels(self.workbook))
self._merge_vba()
self.manifest._write(archive, self.workbook)
def _merge_vba(self):
"""
If workbook contains macros then extract associated files from cache
of old file and add to archive
"""
ARC_VBA = re.compile("|".join(
('xl/vba', r'xl/drawings/.*vmlDrawing\d\.vml',
'xl/ctrlProps', 'customUI', 'xl/activeX', r'xl/media/.*\.emf')
)
)
if self.workbook.vba_archive:
for name in set(self.workbook.vba_archive.namelist()) - self.vba_modified:
if ARC_VBA.match(name):
self._archive.writestr(name, self.workbook.vba_archive.read(name))
def _write_images(self):
# delegate to object
for img in self._images:
self._archive.writestr(img.path[1:], img._data())
def _write_charts(self):
# delegate to object
if len(self._charts) != len(set(self._charts)):
raise InvalidFileException("The same chart cannot be used in more than one worksheet")
for chart in self._charts:
self._archive.writestr(chart.path[1:], tostring(chart._write()))
self.manifest.append(chart)
def _write_drawing(self, drawing):
"""
Write a drawing
"""
self._drawings.append(drawing)
drawing._id = len(self._drawings)
for chart in drawing.charts:
self._charts.append(chart)
chart._id = len(self._charts)
for img in drawing.images:
self._images.append(img)
img._id = len(self._images)
rels_path = get_rels_path(drawing.path)[1:]
self._archive.writestr(drawing.path[1:], tostring(drawing._write()))
self._archive.writestr(rels_path, tostring(drawing._write_rels()))
self.manifest.append(drawing)
def _write_chartsheets(self):
for idx, sheet in enumerate(self.workbook.chartsheets, 1):
sheet._id = idx
xml = tostring(sheet.to_tree())
self._archive.writestr(sheet.path[1:], xml)
self.manifest.append(sheet)
if sheet._drawing:
self._write_drawing(sheet._drawing)
rel = Relationship(type="drawing", Target=sheet._drawing.path)
rels = RelationshipList()
rels.append(rel)
tree = rels.to_tree()
rels_path = get_rels_path(sheet.path[1:])
self._archive.writestr(rels_path, tostring(tree))
def _write_comment(self, ws):
cs = CommentSheet.from_comments(ws._comments)
self._comments.append(cs)
cs._id = len(self._comments)
self._archive.writestr(cs.path[1:], tostring(cs.to_tree()))
self.manifest.append(cs)
if ws.legacy_drawing is None:
ws.legacy_drawing = 'xl/drawings/commentsDrawing{0}.vml'.format(cs._id)
vml = None
else:
vml = fromstring(self.workbook.vba_archive.read(ws.legacy_drawing))
vml = cs.write_shapes(vml)
self._archive.writestr(ws.legacy_drawing, vml)
self.vba_modified.add(ws.legacy_drawing)
comment_rel = Relationship(Id="comments", type=cs._rel_type, Target=cs.path)
ws._rels.append(comment_rel)
def _write_worksheets(self):
pivot_caches = set()
for idx, ws in enumerate(self.workbook.worksheets, 1):
ws._id = idx
xml = ws._write()
rels_path = get_rels_path(ws.path)[1:]
self._archive.writestr(ws.path[1:], xml)
self.manifest.append(ws)
if ws._drawing:
self._write_drawing(ws._drawing)
for r in ws._rels.Relationship:
if "drawing" in r.Type:
r.Target = ws._drawing.path
if ws._comments:
self._write_comment(ws)
if ws.legacy_drawing is not None:
shape_rel = Relationship(type="vmlDrawing", Id="anysvml",
Target="/" + ws.legacy_drawing)
ws._rels.append(shape_rel)
for t in ws._tables:
self._tables.append(t)
t.id = len(self._tables)
t._write(self._archive)
self.manifest.append(t)
ws._rels[t._rel_id].Target = t.path
for p in ws._pivots:
if p.cache not in pivot_caches:
pivot_caches.add(p.cache)
p.cache._id = len(pivot_caches)
self._pivots.append(p)
p._id = len(self._pivots)
p._write(self._archive, self.manifest)
self.workbook._pivots.append(p)
r = Relationship(Type=p.rel_type, Target=p.path)
ws._rels.append(r)
if ws._rels:
tree = ws._rels.to_tree()
self._archive.writestr(rels_path, tostring(tree))
def _write_external_links(self):
# delegate to object
"""Write links to external workbooks"""
wb = self.workbook
for idx, link in enumerate(wb._external_links, 1):
link._id = idx
rels_path = get_rels_path(link.path[1:])
xml = link.to_tree()
self._archive.writestr(link.path[1:], tostring(xml))
rels = RelationshipList()
rels.append(link.file_link)
self._archive.writestr(rels_path, tostring(rels.to_tree()))
self.manifest.append(link)
def save(self, filename):
"""Write data into the archive."""
self.write_data()
self._archive.close()
