Spaces:
Paused
Paused
File size: 2,697 Bytes
dcaa7a1 85d85d8 dcaa7a1 85d85d8 dcaa7a1 85d85d8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
def breakdown_txt_to_satisfy_token_limit(txt, get_token_fn, limit):
def cut(txt_tocut, must_break_at_empty_line): # 递归
if get_token_fn(txt_tocut) <= limit:
return [txt_tocut]
else:
lines = txt_tocut.split('\n')
estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
estimated_line_cut = int(estimated_line_cut)
for cnt in reversed(range(estimated_line_cut)):
if must_break_at_empty_line:
if lines[cnt] != "": continue
print(cnt)
prev = "\n".join(lines[:cnt])
post = "\n".join(lines[cnt:])
if get_token_fn(prev) < limit: break
if cnt == 0:
print('what the fuck ?')
raise RuntimeError("存在一行极长的文本！")
# print(len(post))
# 列表递归接龙
result = [prev]
result.extend(cut(post, must_break_at_empty_line))
return result
try:
return cut(txt, must_break_at_empty_line=True)
except RuntimeError:
return cut(txt, must_break_at_empty_line=False)
def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
def cut(txt_tocut, must_break_at_empty_line): # 递归
if get_token_fn(txt_tocut) <= limit:
return [txt_tocut]
else:
lines = txt_tocut.split('\n')
estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
estimated_line_cut = int(estimated_line_cut)
cnt = 0
for cnt in reversed(range(estimated_line_cut)):
if must_break_at_empty_line:
if lines[cnt] != "": continue
print(cnt)
prev = "\n".join(lines[:cnt])
post = "\n".join(lines[cnt:])
if get_token_fn(prev) < limit: break
if cnt == 0:
# print('what the fuck ? 存在一行极长的文本！')
raise RuntimeError("存在一行极长的文本！")
# print(len(post))
# 列表递归接龙
result = [prev]
result.extend(cut(post, must_break_at_empty_line))
return result
try:
return cut(txt, must_break_at_empty_line=True)
except RuntimeError:
try:
return cut(txt, must_break_at_empty_line=False)
except RuntimeError:
# 这个中文的句号是故意的，作为一个标识而存在
res = cut(txt.replace('.', '。\n'), must_break_at_empty_line=False)
return [r.replace('。\n', '.') for r in res]
|