mirror of
https://github.com/opendatalab/MinerU.git
synced 2026-03-29 03:58:37 +07:00
b0529b6fbd
- Decrease the maximum width and height from 9000 to 4500 pixels - This change aims to prevent excessive resource usage when rendering PDFs
33 lines
917 B
Python
33 lines
917 B
Python
|
|
import fitz
|
|
import numpy as np
|
|
|
|
from magic_pdf.utils.annotations import ImportPIL
|
|
|
|
|
|
@ImportPIL
|
|
def fitz_doc_to_image(doc, dpi=200) -> dict:
|
|
"""Convert fitz.Document to image, Then convert the image to numpy array.
|
|
|
|
Args:
|
|
doc (_type_): pymudoc page
|
|
dpi (int, optional): reset the dpi of dpi. Defaults to 200.
|
|
|
|
Returns:
|
|
dict: {'img': numpy array, 'width': width, 'height': height }
|
|
"""
|
|
from PIL import Image
|
|
mat = fitz.Matrix(dpi / 72, dpi / 72)
|
|
pm = doc.get_pixmap(matrix=mat, alpha=False)
|
|
|
|
# If the width or height exceeds 4500 after scaling, do not scale further.
|
|
if pm.width > 4500 or pm.height > 4500:
|
|
pm = doc.get_pixmap(matrix=fitz.Matrix(1, 1), alpha=False)
|
|
|
|
img = Image.frombytes('RGB', (pm.width, pm.height), pm.samples)
|
|
img = np.array(img)
|
|
|
|
img_dict = {'img': img, 'width': pm.width, 'height': pm.height}
|
|
|
|
return img_dict
|