File size: 3,905 Bytes
cdba7f7 51482f3 41c7a59 cdba7f7 51482f3 a8294f2 cdba7f7 51482f3 cdba7f7 51482f3 a8294f2 51482f3 41c7a59 a8294f2 51482f3 a8294f2 51482f3 a8294f2 51482f3 a8294f2 51482f3 407b252 a8294f2 51482f3 a8294f2 51482f3 a8294f2 41c7a59 51482f3 a8294f2 51482f3 a8294f2 51482f3 |
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 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
# 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.
#
import copy
import re
from rag.app import laws
from rag.nlp import huqie, is_english, tokenize, naive_merge
from deepdoc.parser import PdfParser
from rag.settings import cron_logger
class Pdf(PdfParser):
def __call__(self, filename, binary=None, from_page=0,
to_page=100000, zoomin=3, callback=None):
self.__images__(
filename if not binary else binary,
zoomin,
from_page,
to_page)
callback(0.1, "OCR finished")
from timeit import default_timer as timer
start = timer()
self._layouts_rec(zoomin)
callback(0.77, "Layout analysis finished")
cron_logger.info("paddle layouts:".format((timer() - start) / (self.total_page + 0.1)))
self._naive_vertical_merge()
return [(b["text"], self._line_tag(b, zoomin)) for b in self.boxes]
def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", callback=None, **kwargs):
"""
Supported file formats are docx, pdf, txt.
This method apply the naive ways to chunk files.
Successive text will be sliced into pieces using 'delimiter'.
Next, these successive pieces are merge into chunks whose token number is no more than 'Max token number'.
"""
doc = {
"docnm_kwd": filename,
"title_tks": huqie.qie(re.sub(r"\.[a-zA-Z]+$", "", filename))
}
doc["title_sm_tks"] = huqie.qieqie(doc["title_tks"])
pdf_parser = None
sections = []
if re.search(r"\.docx?$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
for txt in laws.Docx()(filename, binary):
sections.append((txt, ""))
callback(0.8, "Finish parsing.")
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf()
sections = pdf_parser(filename if not binary else binary,
from_page=from_page, to_page=to_page, callback=callback)
elif re.search(r"\.txt$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
txt = ""
if binary:
txt = binary.decode("utf-8")
else:
with open(filename, "r") as f:
while True:
l = f.readline()
if not l: break
txt += l
sections = txt.split("\n")
sections = [(l, "") for l in sections if l]
callback(0.8, "Finish parsing.")
else:
raise NotImplementedError("file type not supported yet(docx, pdf, txt supported)")
parser_config = kwargs.get("parser_config", {"chunk_token_num": 128, "delimiter": "\n!?。；！？"})
cks = naive_merge(sections, parser_config["chunk_token_num"], parser_config["delimiter"])
eng = lang.lower() == "english"#is_english(cks)
res = []
# wrap up to es documents
for ck in cks:
print("--", ck)
d = copy.deepcopy(doc)
if pdf_parser:
d["image"] = pdf_parser.crop(ck)
ck = pdf_parser.remove_tag(ck)
tokenize(d, ck, eng)
res.append(d)
return res
if __name__ == "__main__":
import sys
def dummy(a, b):
pass
chunk(sys.argv[1], from_page=0, to_page=10, callback=dummy)
|