4102a564a3
Introduces a preprocessing that scans each page for page sized images. If one is encountered, all images that are below a configured ratio in respect to the page size are dropped. This step has to occur before the image stiching logic, but MIGHT introduce the problem of dropping image parts that might constitue an image. This hoever is not solveable since we want to drop the small images before further processing since the faulty character images are also stiched to a valid image, that in reality isn't an image.
101 lines
2.4 KiB
Python
101 lines
2.4 KiB
Python
"""Defines utilities for PDF processing."""
|
|
|
|
import json
|
|
from operator import itemgetter
|
|
|
|
from PDFNetPython3.PDFNetPython import (
|
|
PDFDoc,
|
|
PDFNet,
|
|
Square,
|
|
Rect,
|
|
ColorPt,
|
|
BorderStyle,
|
|
SDFDoc,
|
|
Point,
|
|
Text,
|
|
)
|
|
|
|
from image_prediction.utils import get_logger
|
|
|
|
logger = get_logger()
|
|
|
|
|
|
def annotate_image(doc, image_info):
|
|
def draw_box():
|
|
sq = Square.Create(doc.GetSDFDoc(), Rect(*coords))
|
|
sq.SetColor(ColorPt(*color), 3)
|
|
sq.SetBorderStyle(BorderStyle(BorderStyle.e_dashed, 2, 0, 0, [4, 2]))
|
|
sq.SetPadding(4)
|
|
sq.RefreshAppearance()
|
|
page.AnnotPushBack(sq)
|
|
|
|
def add_note():
|
|
txt = Text.Create(doc.GetSDFDoc(), Point(*coords[:2]))
|
|
txt.SetContents(json.dumps(image_info, indent=2, ensure_ascii=False))
|
|
txt.SetColor(ColorPt(*color))
|
|
page.AnnotPushBack(txt)
|
|
txt.RefreshAppearance()
|
|
|
|
red = (1, 0, 0)
|
|
green = (0, 1, 0)
|
|
blue = (0, 0, 1)
|
|
|
|
if image_info["filters"]["allPassed"]:
|
|
color = green
|
|
elif image_info["filters"]["probability"]["unconfident"]:
|
|
color = red
|
|
else:
|
|
color = blue
|
|
|
|
page = doc.GetPage(image_info["position"]["pageNumber"])
|
|
coords = itemgetter("x1", "y1", "x2", "y2")(image_info["position"])
|
|
|
|
draw_box()
|
|
add_note()
|
|
|
|
|
|
def init():
|
|
PDFNet.Initialize(
|
|
# "Knecon AG(en.knecon.swiss):OEM:DDA-R::WL+:AMS(20211029):BECC974307DAB4F34B513BC9B2531B24496F6FCB83CD8AC574358A959730B622FABEF5C7"
|
|
"Knecon AG:OEM:DDA-R::WL+:AMS(20270129):EA5FDFB23C7F36B9C2AE606F4F0D9197DE1FB649119F9730B622FABEF5C7"
|
|
)
|
|
|
|
|
|
def draw_metadata_box(pdf_path, metadata, store_path):
|
|
|
|
init()
|
|
|
|
doc = PDFDoc(pdf_path)
|
|
|
|
color = (1, 0, 0)
|
|
|
|
print(metadata)
|
|
|
|
coords = itemgetter("x1", "y1", "x2", "y2")(metadata)
|
|
page = doc.GetPage(1)
|
|
|
|
sq = Square.Create(doc.GetSDFDoc(), Rect(*coords))
|
|
sq.SetColor(ColorPt(*color), 3)
|
|
sq.SetBorderStyle(BorderStyle(BorderStyle.e_dashed, 2, 0, 0, [4, 2]))
|
|
sq.SetPadding(4)
|
|
sq.RefreshAppearance()
|
|
page.AnnotPushBack(sq)
|
|
|
|
doc.Save(store_path, SDFDoc.e_linearized)
|
|
|
|
logger.info(f"Saved annotated PDF to {store_path}")
|
|
|
|
|
|
def annotate_pdf(pdf_path, responses, store_path):
|
|
|
|
init()
|
|
|
|
doc = PDFDoc(pdf_path)
|
|
|
|
for image_info in responses:
|
|
annotate_image(doc, image_info)
|
|
|
|
doc.Save(store_path, SDFDoc.e_linearized)
|
|
|
|
logger.info(f"Saved annotated PDF to {store_path}")
|