mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-04-23 06:30:00 +08:00
daa65199e8
### What problem does this PR solve? ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
from deepdoc.parser.utils import get_text
|
|
from rag.nlp import num_tokens_from_string
|
|
|
|
|
|
class RAGFlowTxtParser:
|
|
def __call__(self, fnm, binary=None, chunk_token_num=128, delimiter="\n!?;。；！？"):
|
|
txt = get_text(fnm, binary)
|
|
return self.parser_txt(txt, chunk_token_num, delimiter)
|
|
|
|
@classmethod
|
|
def parser_txt(cls, txt, chunk_token_num=128, delimiter="\n!?;。；！？"):
|
|
if not isinstance(txt, str):
|
|
raise TypeError("txt type should be str!")
|
|
cks = [""]
|
|
tk_nums = [0]
|
|
|
|
def add_chunk(t):
|
|
nonlocal cks, tk_nums, delimiter
|
|
tnum = num_tokens_from_string(t)
|
|
if tnum < 8:
|
|
pos = ""
|
|
if tk_nums[-1] > chunk_token_num:
|
|
cks.append(t)
|
|
tk_nums.append(tnum)
|
|
else:
|
|
cks[-1] += t
|
|
tk_nums[-1] += tnum
|
|
|
|
s, e = 0, 1
|
|
while e < len(txt):
|
|
if txt[e] in delimiter:
|
|
add_chunk(txt[s: e + 1])
|
|
s = e + 1
|
|
e = s + 1
|
|
else:
|
|
e += 1
|
|
if s < e:
|
|
add_chunk(txt[s: e + 1])
|
|
|
|
return [[c,""] for c in cks] |