def test_read_external_link(datadir):
from openpyexcel.packaging.relationship import get_dependents
from .. external import read_external_link
datadir.chdir()
archive = ZipFile("book1.xlsx")
rels = get_dependents(archive, ARC_WORKBOOK_RELS)
rel = rels["rId4"]
book = read_external_link(archive, rel.Target)
assert book.file_link.Target == "book2.xlsx"
def read_external_link(archive, book_path):
src = archive.read(book_path)
node = fromstring(src)
book = ExternalLink.from_tree(node)
link_path = get_rels_path(book_path)
deps = get_dependents(archive, link_path)
book.file_link = deps.Relationship[0]
return book
def find_images(archive, path):
"""
Given the path to a drawing file extract charts and images
Ingore errors due to unsupported parts of DrawingML
"""
src = archive.read(path)
tree = fromstring(src)
try:
drawing = SpreadsheetDrawing.from_tree(tree)
except TypeError:
warn(
"DrawingML support is incomplete and limited to charts and images only. Shapes and drawings will be lost."
)
return [], []
rels_path = get_rels_path(path)
deps = []
if rels_path in archive.namelist():
deps = get_dependents(archive, rels_path)
charts = []
for rel in drawing._chart_rels:
cs = get_rel(archive, deps, rel.id, ChartSpace)
chart = read_chart(cs)
chart.anchor = rel.anchor
charts.append(chart)
images = []
if not PILImage: # Pillow not installed, drop images
return charts, images
for rel in drawing._blip_rels:
dep = deps[rel.embed]
if dep.Type == IMAGE_NS:
try:
image = Image(BytesIO(archive.read(dep.target)))
except (OSError, IOError): # Python 2.7
msg = "The image {0} will be removed because it cannot be read".format(
dep.target)
warn(msg)
continue
if image.format.upper() == "WMF": # cannot save
msg = "{0} image format is not supported so the image is being dropped".format(
image.format)
warn(msg)
continue
image.anchor = rel.anchor
images.append(image)
return charts, images
def rels(self):
if self._rels is None:
self._rels = get_dependents(self.archive, get_rels_path(self.workbook_part_name))
return self._rels
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:`openpyexcel.workbook.Workbook`
.. note::
When using lazy load, all worksheets will be :class:`openpyexcel.worksheet.iter_worksheet.IterableWorksheet`
and the returned workbook will be read-only.
"""
archive = _validate_archive(filename)
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():
if "chartsheet" in rel.Type:
continue
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)
drawings = rels.find(SpreadsheetDrawing._rel_type)
for rel in drawings:
charts, images = find_images(archive, rel.target)
for c in charts:
ws.add_chart(c, c.anchor)
for im in images:
ws.add_image(im, im.anchor)
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