pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Format file format from Windows/dos to Unix (#1949)

Browse Source 
### What problem does this PR solve?

Related source file is in Windows/DOS format, they are format to Unix
format.

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2024-08-15 09:17:36 +08:00
committed by GitHub
parent 1328d715db
commit 6b3a40be5c
108 changed files with 36399 additions and 36399 deletions
Download Patch File Download Diff File Expand all files Collapse all files

120
deepdoc/vision/__init__.py
View File

@ -1,61 +1,61 @@
# 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 pdfplumber
from .ocr import OCR
from .recognizer import Recognizer
from .layout_recognizer import LayoutRecognizer
from .table_structure_recognizer import TableStructureRecognizer
def init_in_out(args):
from PIL import Image
import os
import traceback
from api.utils.file_utils import traversal_files
images = []
outputs = []
if not os.path.exists(args.output_dir):
os.mkdir(args.output_dir)
def pdf_pages(fnm, zoomin=3):
nonlocal outputs, images
pdf = pdfplumber.open(fnm)
images = [p.to_image(resolution=72 * zoomin).annotated for i, p in
enumerate(pdf.pages)]
for i, page in enumerate(images):
outputs.append(os.path.split(fnm)[-1] + f"_{i}.jpg")
def images_and_outputs(fnm):
nonlocal outputs, images
if fnm.split(".")[-1].lower() == "pdf":
pdf_pages(fnm)
return
try:
images.append(Image.open(fnm))
outputs.append(os.path.split(fnm)[-1])
except Exception as e:
traceback.print_exc()
if os.path.isdir(args.inputs):
for fnm in traversal_files(args.inputs):
images_and_outputs(fnm)
else:
images_and_outputs(args.inputs)
for i in range(len(outputs)): outputs[i] = os.path.join(args.output_dir, outputs[i])
# 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 pdfplumber
from .ocr import OCR
from .recognizer import Recognizer
from .layout_recognizer import LayoutRecognizer
from .table_structure_recognizer import TableStructureRecognizer
def init_in_out(args):
from PIL import Image
import os
import traceback
from api.utils.file_utils import traversal_files
images = []
outputs = []
if not os.path.exists(args.output_dir):
os.mkdir(args.output_dir)
def pdf_pages(fnm, zoomin=3):
nonlocal outputs, images
pdf = pdfplumber.open(fnm)
images = [p.to_image(resolution=72 * zoomin).annotated for i, p in
enumerate(pdf.pages)]
for i, page in enumerate(images):
outputs.append(os.path.split(fnm)[-1] + f"_{i}.jpg")
def images_and_outputs(fnm):
nonlocal outputs, images
if fnm.split(".")[-1].lower() == "pdf":
pdf_pages(fnm)
return
try:
images.append(Image.open(fnm))
outputs.append(os.path.split(fnm)[-1])
except Exception as e:
traceback.print_exc()
if os.path.isdir(args.inputs):
for fnm in traversal_files(args.inputs):
images_and_outputs(fnm)
else:
images_and_outputs(args.inputs)
for i in range(len(outputs)): outputs[i] = os.path.join(args.output_dir, outputs[i])
return images, outputs