def print_labels(sh, labs, title):
if not labs:return
for rlo, rhi, clo, chi in labs:
print("%s label range %s:%s contains:"
% (title, xlrd.cellname(rlo, clo), xlrd.cellname(rhi-1, chi-1)))
for rx in xrange(rlo, rhi):
for cx in xrange(clo, chi):
print(" %s: %r" % (xlrd.cellname(rx, cx), sh.cell_value(rx, cx)))
def cell(self, rdrowx, rdcolx, wtrowx, wtcolx):
cell = self.rdsheet.cell(rdrowx, rdcolx)
if cell.ctype == xlrd.XL_CELL_EMPTY:
return
if cell.ctype == xlrd.XL_CELL_ERROR:
logger.error("Cell %s of sheet %r contains a bad value: %s" % (
xlrd.cellname(rdrowx, rdcolx),
quoted_sheet_name(self.rdsheet.name),
cell_display(cell, self.rdbook.datemode),
))
return
BaseWriter.cell(self, rdrowx, rdcolx, wtrowx, wtcolx)
def check_file(fname,
verbose,
do_punc=False,
fmt_info=0,
encoding='ascii',
onesheet=''):
print()
print(fname)
if do_punc:
checker = ispunc
else:
checker = None
try:
book = open_workbook(fname, formatting_info=fmt_info, on_demand=True)
except TypeError:
try:
book = open_workbook(fname, formatting_info=fmt_info)
except TypeError:
# this is becoming ridiculous
book = open_workbook(fname)
totold = totnew = totnotnull = 0
if onesheet is None or onesheet == "":
shxrange = range(book.nsheets)
else:
try:
shxrange = [int(onesheet)]
except ValueError:
shxrange = [book.sheet_names().index(onesheet)]
for shx in shxrange:
sheet = book.sheet_by_index(shx)
ngoodrows = number_of_good_rows(sheet, checker)
ngoodcols = number_of_good_cols(sheet, checker, nrows=ngoodrows)
oldncells = sheet.nrows * sheet.ncols
newncells = ngoodrows * ngoodcols
totold += oldncells
totnew += newncells
nnotnull = 0
sheet_density_pct_s = ''
if verbose >= 2:
colxrange = range(ngoodcols)
for rowx in xrange(ngoodrows):
rowtypes = sheet.row_types(rowx)
for colx in colxrange:
if rowtypes[colx] not in null_cell_types:
nnotnull += 1
totnotnull += nnotnull
sheet_density_pct = (nnotnull * 100.0) / max(1, newncells)
sheet_density_pct_s = "; den = %5.1f%%" % sheet_density_pct
if verbose >= 3:
# which rows have non_empty cells in the right-most column?
lastcolx = sheet.ncols - 1
for rowx in xrange(sheet.nrows):
cell = sheet.cell(rowx, lastcolx)
if cell.ctype != XL_CELL_EMPTY:
print "%s (%d, %d): type %d, value %r" % (cellname(
rowx,
lastcolx), rowx, lastcolx, cell.ctype, cell.value)
if (verbose or ngoodrows != sheet.nrows or ngoodcols != sheet.ncols
or (verbose >= 2 and ngoodcells and sheet_density_pct < 90.0)):
if oldncells:
pctwaste = (1.0 - float(newncells) / oldncells) * 100.0
else:
pctwaste = 0.0
shname_enc = safe_encode(sheet.name, encoding)
print "sheet #%2d: RxC %5d x %3d => %5d x %3d; %4.1f%% waste%s (%s)" \
% (shx, sheet.nrows, sheet.ncols,
ngoodrows, ngoodcols, pctwaste, sheet_density_pct_s, shname_enc)
if hasattr(book, 'unload_sheet'):
book.unload_sheet(shx)
if totold:
pctwaste = (1.0 - float(totnew) / totold) * 100.0
else:
pctwaste = 0.0
print "%d cells => %d cells; %4.1f%% waste" % (totold, totnew, pctwaste)
def check_file(fname, verbose, do_punc=False, fmt_info=0, encoding='ascii', onesheet=''):
print()
print (fname)
if do_punc:
checker = ispunc
else:
checker = None
try:
book = open_workbook(fname, formatting_info=fmt_info, on_demand=True)
except TypeError:
try:
book = open_workbook(fname, formatting_info=fmt_info)
except TypeError:
# this is becoming ridiculous
book = open_workbook(fname)
totold = totnew = totnotnull = 0
if onesheet is None or onesheet == "":
shxrange = range(book.nsheets)
else:
try:
shxrange = [int(onesheet)]
except ValueError:
shxrange = [book.sheet_names().index(onesheet)]
for shx in shxrange:
sheet = book.sheet_by_index(shx)
ngoodrows = number_of_good_rows(sheet, checker)
ngoodcols = number_of_good_cols(sheet, checker, nrows=ngoodrows)
oldncells = sheet.nrows * sheet.ncols
newncells = ngoodrows * ngoodcols
totold += oldncells
totnew += newncells
nnotnull = 0
sheet_density_pct_s = ''
if verbose >= 2:
colxrange = range(ngoodcols)
for rowx in xrange(ngoodrows):
rowtypes = sheet.row_types(rowx)
for colx in colxrange:
if rowtypes[colx] not in null_cell_types:
nnotnull += 1
totnotnull += nnotnull
sheet_density_pct = (nnotnull * 100.0) / max(1, newncells)
sheet_density_pct_s = "; den = %5.1f%%" % sheet_density_pct
if verbose >= 3:
# which rows have non_empty cells in the right-most column?
lastcolx = sheet.ncols - 1
for rowx in xrange(sheet.nrows):
cell = sheet.cell(rowx, lastcolx)
if cell.ctype != XL_CELL_EMPTY:
print "%s (%d, %d): type %d, value %r" % (
cellname(rowx, lastcolx), rowx, lastcolx, cell.ctype, cell.value)
if (verbose
or ngoodrows != sheet.nrows
or ngoodcols != sheet.ncols
or (verbose >= 2 and ngoodcells and sheet_density_pct < 90.0)
):
if oldncells:
pctwaste = (1.0 - float(newncells) / oldncells) * 100.0
else:
pctwaste = 0.0
shname_enc = safe_encode(sheet.name, encoding)
print "sheet #%2d: RxC %5d x %3d => %5d x %3d; %4.1f%% waste%s (%s)" \
% (shx, sheet.nrows, sheet.ncols,
ngoodrows, ngoodcols, pctwaste, sheet_density_pct_s, shname_enc)
if hasattr(book, 'unload_sheet'):
book.unload_sheet(shx)
if totold:
pctwaste = (1.0 - float(totnew) / totold) * 100.0
else:
pctwaste = 0.0
print "%d cells => %d cells; %4.1f%% waste" % (totold, totnew, pctwaste)