Feat: add splitter (#10161)

### What problem does this PR solve?


### Type of change
- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
This commit is contained in:
Kevin Hu
2025-09-19 10:15:19 +08:00
committed by GitHub
parent f9c7404bee
commit a1b947ffd6
81 changed files with 3083 additions and 799 deletions

View File

@ -16,24 +16,28 @@
import io
import sys
import threading
import pdfplumber
from .ocr import OCR
from .recognizer import Recognizer
from .layout_recognizer import AscendLayoutRecognizer
from .layout_recognizer import LayoutRecognizer4YOLOv10 as LayoutRecognizer
from .table_structure_recognizer import TableStructureRecognizer
LOCK_KEY_pdfplumber = "global_shared_lock_pdfplumber"
if LOCK_KEY_pdfplumber not in sys.modules:
sys.modules[LOCK_KEY_pdfplumber] = threading.Lock()
def init_in_out(args):
from PIL import Image
import os
import traceback
from PIL import Image
from api.utils.file_utils import traversal_files
images = []
outputs = []
@ -44,8 +48,7 @@ def init_in_out(args):
nonlocal outputs, images
with sys.modules[LOCK_KEY_pdfplumber]:
pdf = pdfplumber.open(fnm)
images = [p.to_image(resolution=72 * zoomin).annotated for i, p in
enumerate(pdf.pages)]
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")
@ -57,10 +60,10 @@ def init_in_out(args):
pdf_pages(fnm)
return
try:
fp = open(fnm, 'rb')
fp = open(fnm, "rb")
binary = fp.read()
fp.close()
images.append(Image.open(io.BytesIO(binary)).convert('RGB'))
images.append(Image.open(io.BytesIO(binary)).convert("RGB"))
outputs.append(os.path.split(fnm)[-1])
except Exception:
traceback.print_exc()
@ -81,6 +84,7 @@ __all__ = [
"OCR",
"Recognizer",
"LayoutRecognizer",
"AscendLayoutRecognizer",
"TableStructureRecognizer",
"init_in_out",
]