def copy(wb): w = XLWTWriter() process( XLRDReader(wb, 'unknown.xls'), w ) return w.output[0][1], w.style_list
def copy2(wb):
w = XLWTWriter()
process(
XLRDReader(wb,'unknown.xls'),
w
)
return w.style_list
def copy_hack(self):
"""
хак для копирования стилей из шаблона в отчет
"""
w = XLWTWriter()
process(XLRDReader(self.work_book, 'unknown.xls'), w)
return w.output[0][1], w.style_list
def copy2(wb):
"""
Patch: add this function to the end of xlutils/copy.py
:param wb: excel workbook using xlrd
:return: workbook with format preserved
"""
w = XLWTWriter()
process(XLRDReader(wb, "unknown.xls"), w)
return w.output[0][1], w.style_list
def copy(wb):
"""
Copy an :class:`xlrd.Book` into an :class:`xlwt.Workbook` preserving as much
information from the source object as possible.
See the :doc:`copy` documentation for an example.
"""
w = XLWTWriter()
process(XLRDReader(wb, 'unknown.xls'), w)
return w.output[0][1]
def create_bfx_reimport_xlbook(book, feature_sheetidxs):
assert all([f == feature_sheetidxs[0] for f in feature_sheetidxs]), \
"All raw features must be on the same sheet for BFX format"
normalization_sheet_name = 'Normalization 1'
provenance_sheet_name = 'BFX Provenance Tracking'
from xlutils.filter import process, XLRDReader, XLWTWriter, BaseFilter
import xlwt
class OnlyRelevantSheet(BaseFilter):
def __init__(self):
self.__on = False
def sheet(self, rdsheet, wtsheet_name):
if rdsheet == book.sheet_by_index(feature_sheetidxs[0]):
self.__on = True
# only write this sheet
self.next.sheet(rdsheet, wtsheet_name)
else:
self.__on = False
# no call
def set_rdsheet(self,rdsheet):
self.next.sheet(rdsheet,wtsheet_name)
def row(self,rdrowx,wtrowx):
if self.__on:
self.next.row(rdrowx,wtrowx)
def cell(self,rdrowx,rdcolx,wtrowx,wtcolx):
if self.__on:
self.next.cell(rdrowx,rdcolx,wtrowx,wtcolx)
class WrapWT(XLWTWriter):
def sheet(self, rdsheet, wtsheet_name):
XLWTWriter.sheet(self, rdsheet, wtsheet_name)
def finish(self):
# add two new sheets at the end
self.normalization_sheet = self.wtbook.add_sheet(normalization_sheet_name)
self.provenance_sheet = self.wtbook.add_sheet(provenance_sheet_name)
XLWTWriter.finish(self)
# hackity hack - need to force non-ascii encoding
orig_Workbook_init = xlwt.Workbook.__init__
def replacement(self, encoding='utf-8', style_compression=0):
orig_Workbook_init(self, encoding, style_compression)
xlwt.Workbook.__init__ = replacement
w = WrapWT()
process(XLRDReader(book, 'unknown.xls'), OnlyRelevantSheet(), w)
outbook = w.output[0][1]
xlwt.Workbook.__init__ = orig_Workbook_init
return outbook, w.normalization_sheet, w.provenance_sheet
def test_setup(self):
class DummyReader:
def __call__(self,filter):
filter.finished()
F1 = Mock()
F2 = Mock()
process(DummyReader(),F1,F2)
self.failUnless(F1.next is F2)
self.failUnless(isinstance(F2.next,Mock))
compare(F1.method_calls,[('finished',(),{})])
compare(F2.method_calls,[])
def copy(wb):
"""
Copy an :class:`xlrd.Book` into an :class:`xlwt.Workbook` preserving as much
information from the source object as possible.
See the :doc:`copy` documentation for an example.
"""
w = XLWTWriter()
process(
XLRDReader(wb,'unknown.xls'),
w
)
return w.output[0][1]
def save(wb, filename_or_stream):
"Save the supplied :class:`xlrd.Book` to the supplied stream or filename."
if isinstance(filename_or_stream, basestring):
filename = os.path.split(filename_or_stream)[1]
stream = open(filename_or_stream, "wb")
close = True
else:
filename = "unknown.xls"
stream = filename_or_stream
close = False
process(XLRDReader(wb, filename), StreamWriter(stream))
if close:
stream.close()
def save(wb,filename_or_stream):
if isinstance(filename_or_stream,basestring):
filename = os.path.split(filename_or_stream)[1]
stream = open(filename_or_stream,'wb')
close = True
else:
filename = 'unknown.xls'
stream = filename_or_stream
close = False
process(
XLRDReader(wb,filename),
StreamWriter(stream)
)
if close:
stream.close()
def test_open_workbook_args(self):
r = TestReader(('Sheet1',[['X']]))
f = ErrorFilter()
m = Mock()
process(r,f,m)
compare(m.method_calls,[
('start',(),{}),
('workbook',(C('xlrd.Book',
pickleable=0,
formatting_info=1,
on_demand=False,
strict=False),'test.xls'),{}),
('sheet',(C('xlrd.sheet.Sheet'),u'Sheet1'),{}),
('row',(0,0),{}),
('cell',(0,0,0,0),{}),
('finish',(),{}),
])
def test_no_error_on_bools(self,h):
r = TestReader(
('Sheet',[[(XL_CELL_BOOLEAN,True)]]),
)
book = tuple(r.get_workbooks())[0][0]
# fire methods on filter
f = ErrorFilter()
c = Mock()
process(r,f,c)
compare(c.method_calls,[
('start', (), {}),
('workbook', (C('xlrd.Book'), 'test.xls'),{}),
('sheet', (C('xlrd.sheet.Sheet',name='Sheet',strict=False), u'Sheet'),{}),
('row', (0, 0),{}),
('cell', (0, 0, 0, 0),{}),
('finish', (), {})
])
self.assertEqual(len(h.records),0)
def duplicate_xlbook(book):
# add two sheets, one for normalization results, one for provenance tracking
existing_sheets = book.sheet_names()
count = 1
while 'Normalization %d'%(count) in existing_sheets:
count += 1
normalization_sheet_name = 'Normalization %d'%(count)
provenance_sheet_name = 'BFX Provenance Tracking'
add_provenance_sheet = (provenance_sheet_name not in existing_sheets)
from xlutils.filter import process, XLRDReader, XLWTWriter
import xlwt
class WrapWT(XLWTWriter):
def sheet(self, rdsheet, wtsheet_name):
# if we're just adding a normalization sheet, add it before the provenance sheet
if (not add_provenance_sheet) and (wtsheet_name == provenance_sheet_name):
self.normalization_sheet = self.wtbook.add_sheet(normalization_sheet_name)
# write the sheet as requested
XLWTWriter.sheet(self, rdsheet, wtsheet_name)
def finish(self):
# add two new sheets at the end if we're adding normalization and results
if add_provenance_sheet:
self.normalization_sheet = self.wtbook.add_sheet(normalization_sheet_name)
self.wtbook.add_sheet(provenance_sheet_name)
XLWTWriter.finish(self)
# hackity hack - need to force non-ascii encoding
orig_Workbook_init = xlwt.Workbook.__init__
def replacement(self, encoding='utf-8', style_compression=0):
orig_Workbook_init(self, encoding, style_compression)
xlwt.Workbook.__init__ = replacement
w = WrapWT()
process(XLRDReader(book, 'unknown.xls'), w)
outbook = w.output[0][1]
xlwt.Workbook.__init__ = orig_Workbook_init
for provenance_sheet_idx in range(len(existing_sheets) + 2):
if outbook.get_sheet(provenance_sheet_idx).name == provenance_sheet_name:
break
return w.output[0][1], w.normalization_sheet, outbook.get_sheet(provenance_sheet_idx)
goodlist = None
def __init__(self):
self.wtrowx = -1
self.skipped_row = -1
def workbook(self, rdbook, wtbook_name):
self.next.workbook(rdbook, 'filtered_' + wtbook_name)
def row(self, rdrowx, rwrowx):
value = self.rdsheet.cell(rdrowx, ROW).value
if value == VALUE:
self.skipped_row = rdrowx
self.wtrowx += 1
def cell(self, rdrowx, rdcolx, wtrowx, wtcolx):
if self.skipped_row == rdrowx:
self.next.cell(rdrowx, rdcolx, self.wtrowx, wtcolx)
xls_file = 's.xls'
results_folder = ''
VALUE = 'XXX'
ROW = 1
process(
GlobReader(xls_file),
ValueRowFilter(),
DirectoryWriter(results_folder)
)
def copy(wb):
w = XLWTWriter()
process(XLRDReader(wb, "unknown.xls"), w)
return w.output[0][1]
def run(infile, outfile, filter):
wb = xlrd.open_workbook(file_contents=infile.read())
reader = XLRDReader(wb, infile.name)
writer = StreamWriter(outfile)
process(reader, filter, Anonymize(), writer)
def get_stream(self,filename):
return file(filename,'wb')
class Filter(BaseFilter):
pending_row = None
wtrowxi = 0
def workbook(self,rdbook,wtbook_name):
self.next.workbook(rdbook,'filtered-'+wtbook_name)
def row(self,rdrowx,wtrowx):
self.pending_row = (rdrowx,wtrowx)
def cell(self,rdrowx,rdcolx,wtrowx,wtcolx):
if rdcolx==0:
value = self.rdsheet.cell(rdrowx,rdcolx).value
if value.strip().lower()=='x':
self.ignore_row = True
self.wtrowxi -= 1
else:
self.ignore_row = False
rdrowx, wtrowx = self.pending_row
self.next.row(rdrowx,wtrowx+self.wtrowxi)
elif not self.ignore_row:
self.next.cell(
rdrowx,rdcolx,wtrowx+self.wtrowxi,wtcolx-1
)
process(Reader(),Filter(),Writer())
