def nadia_process_xls(filename, data_headers_location, data_values_location,
y_axis_location, global_data_vector, global_const_vector, outfile):
"""Given an XLS file and all the settings -- such as where are headers,
where is data, where is Y axis, etc. -- this function translates such
XLS file in a sequence of JSON that match very closely the format of
a CKAN package."""
sheet = open_sheet(filename)
data = data_section(sheet, data_headers_location, data_values_location)
y_axis(sheet, y_axis_location, data)
data = remove_empty_lines(data)
for name, location in global_data_vector:
global_data(data, sheet, name, location)
for name, value in global_const_vector:
global_const(data, name, value)
jsonize(data, outfile)
data[0].append("name")
data[0].append("description")
while i < len(M):
y_row = M[i][0]
i = i + 1 # XXX
if not _is_garbage(data[i]):
y_row = slugify(y_row)
data[i].append(y_row)
data[i].append("")
last = i
continue
if last == -1:
continue
data[last][-1] += y_row
def y_axis(sheet, range, data):
M = row_values(sheet, range)
for R in M:
if len(R) != 1:
raise ValueError
if _is_garbage(data[1]):
_y_axis_garbage_before_type(M, data)
else:
_y_axis_type_before_garbage(M, data)
if __name__ == "__main__":
sheet = open_sheet("test/sample1.xls")
data = data_section(sheet, "C3:R6", "C7:R24")
y_axis(sheet, "B7:B24", data)
pprint.pprint(data)
