28 lines
1.2 KiB
Python
28 lines
1.2 KiB
Python
|
|
"""按完整表格行分段;表头重复,重叠行不跨表/工作表。"""
|
||
|
|
def split_table_rows(header, rows, limit, overlap=0):
|
||
|
|
limit, overlap = int(limit), int(overlap)
|
||
|
|
if limit <= 0 or not 0 <= overlap < limit:
|
||
|
|
raise ValueError("Invalid table splitting limits")
|
||
|
|
chunks, current = [], []
|
||
|
|
length = len(header)
|
||
|
|
for row in rows:
|
||
|
|
if current and length + len(row) > limit:
|
||
|
|
chunks.append({"content": header + "".join(current), "title": ""})
|
||
|
|
carry, carried = [], 0
|
||
|
|
if overlap:
|
||
|
|
for previous in reversed(current):
|
||
|
|
carry.insert(0, previous)
|
||
|
|
carried += len(previous)
|
||
|
|
if carried >= overlap:
|
||
|
|
break
|
||
|
|
# 必须留出至少一条新行的空间,不能只重复旧行。
|
||
|
|
while carry and len(header) + sum(map(len, carry)) + len(row) > limit:
|
||
|
|
carry.pop(0)
|
||
|
|
current = carry
|
||
|
|
length = len(header) + sum(map(len, current))
|
||
|
|
current.append(row)
|
||
|
|
length += len(row)
|
||
|
|
if current:
|
||
|
|
chunks.append({"content": header + "".join(current), "title": ""})
|
||
|
|
return chunks
|