File size: 3,397 Bytes
9cba22c 3079197 d54aa01 3079197 2d09c38 b837154 08bab63 366c531 08bab63 0404a52 366c531 79ada0b 366c531 0404a52 366c531 08bab63 3079197 0404a52 3079197 0404a52 79ada0b 3079197 1550520 0404a52 79ada0b 0404a52 3079197 1550520 9fe9fc4 75faa66 1550520 d54aa01 b5b25b4 1550520 3079197 2d09c38 3079197 |
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 |
# 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 openpyxl import load_workbook
import sys
from io import BytesIO
from rag.nlp import find_codec
class RAGFlowExcelParser:
def html(self, fnm, chunk_rows=256):
if isinstance(fnm, str):
wb = load_workbook(fnm)
else:
wb = load_workbook(BytesIO(fnm))
tb_chunks = []
for sheetname in wb.sheetnames:
ws = wb[sheetname]
rows = list(ws.rows)
if not rows:
continue
tb_rows_0 = "<tr>"
for t in list(rows[0]):
tb_rows_0 += f"<th>{t.value}</th>"
tb_rows_0 += "</tr>"
for chunk_i in range((len(rows) - 1) // chunk_rows + 1):
tb = ""
tb += f"<table><caption>{sheetname}</caption>"
tb += tb_rows_0
for r in list(
rows[1 + chunk_i * chunk_rows : 1 + (chunk_i + 1) * chunk_rows]
):
tb += "<tr>"
for i, c in enumerate(r):
if c.value is None:
tb += "<td></td>"
else:
tb += f"<td>{c.value}</td>"
tb += "</tr>"
tb += "</table>\n"
tb_chunks.append(tb)
return tb_chunks
def __call__(self, fnm):
if isinstance(fnm, str):
wb = load_workbook(fnm)
else:
wb = load_workbook(BytesIO(fnm))
res = []
for sheetname in wb.sheetnames:
ws = wb[sheetname]
rows = list(ws.rows)
if not rows:
continue
ti = list(rows[0])
for r in list(rows[1:]):
fields = []
for i, c in enumerate(r):
if not c.value:
continue
t = str(ti[i].value) if i < len(ti) else ""
t += ("：" if t else "") + str(c.value)
fields.append(t)
line = "; ".join(fields)
if sheetname.lower().find("sheet") < 0:
line += " ——" + sheetname
res.append(line)
return res
@staticmethod
def row_number(fnm, binary):
if fnm.split(".")[-1].lower().find("xls") >= 0:
wb = load_workbook(BytesIO(binary))
total = 0
for sheetname in wb.sheetnames:
ws = wb[sheetname]
total += len(list(ws.rows))
return total
if fnm.split(".")[-1].lower() in ["csv", "txt"]:
encoding = find_codec(binary)
txt = binary.decode(encoding, errors="ignore")
return len(txt.split("\n"))
if __name__ == "__main__":
psr = RAGFlowExcelParser()
psr(sys.argv[1])
|