File size: 1,765 Bytes
6ed07a9 82adb1c 6ed07a9 1f75d02 82adb1c 1f75d02 6ed07a9 ef2a724 82adb1c 6ed07a9 13b285d 6ed07a9 13b285d |
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 |
# 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_txt
from rag.nlp import num_tokens_from_string
class RAGFlowTxtParser:
def __call__(self, fnm, binary=None, chunk_token_num=128, delimiter="\n!?;。；！？"):
txt = get_txt(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] |