def get_head_line(sheet_data: xlrd.sheet.Sheet):
"""
获取第一行cell数据列表
:param sheet_data:
:return:
"""
return sheet_data.row_values(0, 0, sheet_data.ncols)
def diff_sheet(self, s1: xlrd.sheet.Sheet, s2: xlrd.sheet.Sheet):
"""
get sheet diff
:param s1: sheet 1
:param s2: sheet 2
:return: sheet diff of s1 and s2
"""
sheet_diff = {
'added_cols': [],
'removed_cols': [],
'modified_data': {},
}
modified = False
# diff header
headers1 = [
str(v) for v in s1.row_values(self._header_row,
start_colx=self._start_col)
]
headers2 = [
str(v) for v in s2.row_values(self._header_row,
start_colx=self._start_col)
]
# may contain header with same name
header_cols1, header_cols2 = dict(), dict()
l1, l2 = len(headers1), len(headers2)
for i in range(l1):
h1 = headers1[i]
if h1 not in header_cols1.keys():
header_cols1[h1] = list()
header_cols1[h1].append(i)
for i in range(l2):
h2 = headers2[i]
if h2 not in header_cols2.keys():
header_cols2[h2] = list()
header_cols2[h2].append(i)
removed_cols, kept_cols, added_cols = get_iter_diff(
header_cols1.keys(), header_cols2.keys())
# please do not change col name or switch data frequently!
if len(removed_cols) > 0:
sheet_diff['removed_cols'] = [{
'name': h,
'indices': header_cols1[h]
} for h in removed_cols]
modified = True
if len(added_cols) > 0:
sheet_diff['added_cols'] = [{
'name': h,
'indices': header_cols2[h]
} for h in added_cols]
modified = True
for h in kept_cols:
cols1, cols2 = header_cols1[h], header_cols2[h]
l1, l2 = len(cols1), len(cols2)
if l1 > l2:
sheet_diff['removed_cols'].append({
'name': h,
'indices': cols1[l2 - l1:]
})
header_cols1[h] = cols1[:l2]
modified = True
elif l1 < l2:
sheet_diff['added_cols'].append({
'name': h,
'indices': cols2[l1 - l2:]
})
header_cols2[h] = cols2[:l1]
modified = True
# map cols
cols1_header = dict()
cols1_cols2 = dict()
for header in header_cols1:
if header in kept_cols:
col1_indices = header_cols1[header]
col2_indices = header_cols2[header]
while len(col1_indices) > 0 and len(col2_indices) > 0:
col_idx1 = col1_indices.pop()
col_idx2 = col2_indices.pop()
cols1_header[col_idx1] = header
cols1_cols2[col_idx1] = col_idx2
indices1 = list(cols1_header.keys())
indices1.sort()
d1, d2 = [], []
if self._start_row > s1.nrows:
LOGGER.warn('Sheet %s: start row %d is larger than num rows %d!' %
(s1.name, self._start_row, s1.nrows))
else:
for i in range(self._start_row, s1.nrows):
d1.append([str(s1.cell_value(i, c)) for c in indices1])
if self._start_row > s2.nrows:
LOGGER.warn('Sheet %s: start row %d is larger then num rows %d!' %
(s2.name, self._start_row, s2.nrows))
else:
for i in range(self._start_row, s2.nrows):
d2.append(
[str(s2.cell_value(i, cols1_cols2[c])) for c in indices1])
# diff data
data_diff = self.diff_data(d1, d2)
if data_diff:
modified = True
data_diff['modified_cells'] = [
dict(
d, **{
'src_col':
indices1[d['src_col']] + self._start_col,
'dest_col':
cols1_cols2[indices1[d['dest_col']]] + self._start_col,
}) for d in data_diff['modified_cells']
]
sheet_diff['modified_data'] = data_diff
# +1 to all indices if using excel
if modified and self._use_excel_indices:
sheet_diff = ExcelDiffer._convert_idx_of_sheet_diff(sheet_diff)
return sheet_diff if modified else None
