mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-05-01 08:15:18 +08:00
49 lines
1.5 KiB
Python
49 lines
1.5 KiB
Python
|
|
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 fitz
|
|
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 = fitz.open(fnm)
|
|
mat = fitz.Matrix(zoomin, zoomin)
|
|
for i, page in enumerate(pdf):
|
|
pix = page.get_pixmap(matrix=mat)
|
|
img = Image.frombytes("RGB", [pix.width, pix.height],
|
|
pix.samples)
|
|
images.append(img)
|
|
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 |