Mirrors/Stirling-PDF
1
0
Fork 0
mirror of https://github.com/Frooodle/Stirling-PDF.git synced 2026-02-17 13:52:14 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix: correct paths for python scripts and implement classpath extraction (#3984)

Browse Source 
# Description of Changes

- **What was changed**  
- Relocated `png_to_webp.py` and `split_photos.py` from `scripts/` to
`app/core/src/main/resources/static/python/`.
- Updated `.github/labeler-config-srvaroa.yml` and
`.pre-commit-config.yaml` to include the new script directory in their
file-matching patterns.
- Added `GeneralUtils.extractScript(String scriptName)` to load Python
scripts from the classpath (`static/python/`), extract them into a
temporary directory at runtime, and return the filesystem path.

- **Why the change was made**  
- To fix the Internal Server Error caused by missing script files at
their old locations.
- Ensure the Python helper scripts are packaged inside the JAR/WAR and
reliably accessible when the application runs.
  - Only local installations were affected

---

## Checklist

### General

- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [x] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md)
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md)
(if applicable)
- [x] I have performed a self-review of my own code
- [x] My changes generate no new warnings

### Documentation

- [ ] I have updated relevant docs on [Stirling-PDF's doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
(if functionality has heavily changed)
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)

### UI Changes (if applicable)

- [ ] Screenshots or videos demonstrating the UI changes are attached
(e.g., as comments or direct attachments in the PR)

### Testing (if applicable)

- [ ] I have tested my changes locally. Refer to the [Testing
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing)
for more details.

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Ludy
2025-07-20 23:21:12 +02:00
committed by GitHub
parent 7b61bbaced
commit 04ba3cebab
10 changed files with 70 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
app/core/.gitignore vendored
View File

@@ -194,3 +194,5 @@ id_ed25519.pub
# node_modules
node_modules/
scripts/**/*

13
app/core/src/main/java/stirling/software/SPDF/controller/api/converters/ConvertImgPDFController.java
View File

@@ -56,8 +56,8 @@ public class ConvertImgPDFController {
summary = "Convert PDF to image(s)",
description =
"This endpoint converts a PDF file to image(s) with the specified image format,"
+ " color type, and DPI. Users can choose to get a single image or multiple"
+ " images. Input:PDF Output:Image Type:SI-Conditional")
+ " color type, and DPI. Users can choose to get a single image or multiple"
+ " images. Input:PDF Output:Image Type:SI-Conditional")
public ResponseEntity<byte[]> convertToImage(@ModelAttribute ConvertToImageRequest request)
throws Exception {
MultipartFile file = request.getFileInput();
@@ -117,10 +117,14 @@ public class ConvertImgPDFController {
}
String pythonVersion = CheckProgramInstall.getAvailablePythonCommand();
Path pngToWebpScript = GeneralUtils.extractScript("png_to_webp.py");
List<String> command = new ArrayList<>();
command.add(pythonVersion);
command.add("./scripts/png_to_webp.py"); // Python script to handle the conversion
command.add(
pngToWebpScript
.toAbsolutePath()
.toString()); // Python script to handle the conversion
// Create a temporary directory for the output WebP files
tempOutputDir = Files.createTempDirectory("webp_output");
@@ -232,7 +236,8 @@ public class ConvertImgPDFController {
PdfUtils.imageToPdf(file, fitOption, autoRotate, colorType, pdfDocumentFactory);
return WebResponseUtils.bytesToWebResponse(
bytes,
new File(file[0].getOriginalFilename()).getName().replaceFirst("[.][^.]+$", "") + "_converted.pdf");
new File(file[0].getOriginalFilename()).getName().replaceFirst("[.][^.]+$", "")
+ "_converted.pdf");
}
private String getMediaType(String imageFormat) {

10
app/core/src/main/java/stirling/software/SPDF/controller/api/misc/ExtractImageScansController.java
View File

@@ -34,6 +34,7 @@ import stirling.software.SPDF.model.api.misc.ExtractImageScansRequest;
import stirling.software.common.service.CustomPDFDocumentFactory;
import stirling.software.common.util.CheckProgramInstall;
import stirling.software.common.util.ExceptionUtils;
import stirling.software.common.util.GeneralUtils;
import stirling.software.common.util.ProcessExecutor;
import stirling.software.common.util.ProcessExecutor.ProcessExecutorResult;
import stirling.software.common.util.WebResponseUtils;
@@ -54,9 +55,9 @@ public class ExtractImageScansController {
summary = "Extract image scans from an input file",
description =
"This endpoint extracts image scans from a given file based on certain"
+ " parameters. Users can specify angle threshold, tolerance, minimum area,"
+ " minimum contour area, and border size. Input:PDF Output:IMAGE/ZIP"
+ " Type:SIMO")
+ " parameters. Users can specify angle threshold, tolerance, minimum area,"
+ " minimum contour area, and border size. Input:PDF Output:IMAGE/ZIP"
+ " Type:SIMO")
public ResponseEntity<byte[]> extractImageScans(
@ModelAttribute ExtractImageScansRequest request)
throws IOException, InterruptedException {
@@ -78,6 +79,7 @@ public class ExtractImageScansController {
}
String pythonVersion = CheckProgramInstall.getAvailablePythonCommand();
Path splitPhotosScript = GeneralUtils.extractScript("split_photos.py");
try {
// Check if input file is a PDF
if ("pdf".equalsIgnoreCase(extension)) {
@@ -120,7 +122,7 @@ public class ExtractImageScansController {
new ArrayList<>(
Arrays.asList(
pythonVersion,
"./scripts/split_photos.py",
splitPhotosScript.toAbsolutePath().toString(),
images.get(i),
tempDir.toString(),
"--angle_threshold",

174
app/core/src/main/resources/static/python/png_to_webp.py Normal file
View File

@@ -0,0 +1,174 @@
"""
Author: Ludy87
Description: This script converts a PDF file to WebP images. It includes functionality to resize images if they exceed specified dimensions and handle conversion of PDF pages to WebP format.
Example
-------
To convert a PDF file to WebP images with each page as a separate WebP file:
python script.py input.pdf output_directory
To convert a PDF file to a single WebP image:
python script.py input.pdf output_directory --single
To adjust the DPI resolution for rendering PDF pages:
python script.py input.pdf output_directory --dpi 150
"""
import argparse
import os
from pdf2image import convert_from_path
from PIL import Image
def resize_image(input_image_path, output_image_path, max_size=(16383, 16383)):
"""
Resize the image if its dimensions exceed the maximum allowed size and save it as WebP.
Parameters
----------
input_image_path : str
Path to the input image file.
output_image_path : str
Path where the output WebP image will be saved.
max_size : tuple of int, optional
Maximum allowed dimensions for the image (width, height). Default is (16383, 16383).
Returns
-------
None
"""
try:
# Open the image
image = Image.open(input_image_path)
width, height = image.size
max_width, max_height = max_size
# Check if the image dimensions exceed the maximum allowed dimensions
if width > max_width or height > max_height:
# Calculate the scaling ratio
ratio = min(max_width / width, max_height / height)
new_width = int(width * ratio)
new_height = int(height * ratio)
# Resize the image
resized_image = image.resize((new_width, new_height), Image.LANCZOS)
resized_image.save(output_image_path, format="WEBP", quality=100)
print(
f"The image was successfully resized to ({new_width}, {new_height}) and saved as WebP: {output_image_path}"
)
else:
# If dimensions are within the allowed limits, save the image directly
image.save(output_image_path, format="WEBP", quality=100)
print(f"The image was successfully saved as WebP: {output_image_path}")
except Exception as e:
print(f"An error occurred: {e}")
def convert_image_to_webp(input_image, output_file):
"""
Convert an image to WebP format, resizing it if it exceeds the maximum dimensions.
Parameters
----------
input_image : str
Path to the input image file.
output_file : str
Path where the output WebP image will be saved.
Returns
-------
None
"""
# Resize the image if it exceeds the maximum dimensions
resize_image(input_image, output_file, max_size=(16383, 16383))
def pdf_to_webp(pdf_path, output_dir, dpi=300):
"""
Convert each page of a PDF file to WebP images.
Parameters
----------
pdf_path : str
Path to the input PDF file.
output_dir : str
Directory where the WebP images will be saved.
dpi : int, optional
DPI resolution for rendering PDF pages. Default is 300.
Returns
-------
None
"""
# Convert the PDF to a list of images
images = convert_from_path(pdf_path, dpi=dpi)
for page_number, image in enumerate(images):
# Define temporary PNG path
temp_png_path = os.path.join(output_dir, f"temp_page_{page_number + 1}.png")
image.save(temp_png_path, format="PNG")
# Define the output path for WebP
output_path = os.path.join(output_dir, f"page_{page_number + 1}.webp")
# Convert PNG to WebP
convert_image_to_webp(temp_png_path, output_path)
# Delete the temporary PNG file
os.remove(temp_png_path)
def main(pdf_image_path, output_dir, dpi=300, single_images_flag=False):
"""
Main function to handle conversion from PDF to WebP images.
Parameters
----------
pdf_image_path : str
Path to the input PDF file or image.
output_dir : str
Directory where the WebP images will be saved.
dpi : int, optional
DPI resolution for rendering PDF pages. Default is 300.
single_images_flag : bool, optional
If True, combine all pages into a single WebP image. Default is False.
Returns
-------
None
"""
if single_images_flag:
# Combine all pages into a single WebP image
output_path = os.path.join(output_dir, "combined_image.webp")
convert_image_to_webp(pdf_image_path, output_path)
else:
# Convert each PDF page to a separate WebP image
pdf_to_webp(pdf_image_path, output_dir, dpi)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Convert a PDF file to WebP images.")
parser.add_argument("pdf_path", help="The path to the input PDF file.")
parser.add_argument(
"output_dir", help="The directory where the WebP images should be saved."
)
parser.add_argument(
"--dpi",
type=int,
default=300,
help="The DPI resolution for rendering the PDF pages (default: 300).",
)
parser.add_argument(
"--single",
action="store_true",
help="Combine all pages into a single WebP image.",
)
args = parser.parse_args()
os.makedirs(args.output_dir, exist_ok=True)
main(
args.pdf_path,
args.output_dir,
dpi=args.dpi,
single_images_flag=args.single,
)

122
app/core/src/main/resources/static/python/split_photos.py Normal file
View File

@@ -0,0 +1,122 @@
import argparse
import sys
import cv2
import numpy as np
import os
def find_photo_boundaries(image, background_color, tolerance=30, min_area=10000, min_contour_area=500):
mask = cv2.inRange(image, background_color - tolerance, background_color + tolerance)
mask = cv2.bitwise_not(mask)
kernel = np.ones((5,5),np.uint8)
mask = cv2.dilate(mask, kernel, iterations=2)
contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
photo_boundaries = []
for contour in contours:
x, y, w, h = cv2.boundingRect(contour)
area = w * h
contour_area = cv2.contourArea(contour)
if area >= min_area and contour_area >= min_contour_area:
photo_boundaries.append((x, y, w, h))
return photo_boundaries
def estimate_background_color(image, sample_points=5):
h, w, _ = image.shape
points = [
(0, 0),
(w - 1, 0),
(w - 1, h - 1),
(0, h - 1),
(w // 2, h // 2),
]
colors = []
for x, y in points:
colors.append(image[y, x])
return np.median(colors, axis=0)
def auto_rotate(image, angle_threshold=1):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 50, 150, apertureSize=3)
lines = cv2.HoughLines(edges, 1, np.pi / 180, 200)
if lines is None:
return image
# compute the median angle of the lines
angles = []
for rho, theta in lines[:, 0]:
angles.append((theta * 180) / np.pi - 90)
angle = np.median(angles)
if abs(angle) < angle_threshold:
return image
(h, w) = image.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, angle, 1.0)
return cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
def crop_borders(image, border_color, tolerance=30):
mask = cv2.inRange(image, border_color - tolerance, border_color + tolerance)
contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
if len(contours) == 0:
return image
largest_contour = max(contours, key=cv2.contourArea)
x, y, w, h = cv2.boundingRect(largest_contour)
return image[y:y+h, x:x+w]
def split_photos(input_file, output_directory, tolerance=30, min_area=10000, min_contour_area=500, angle_threshold=10, border_size=0):
image = cv2.imread(input_file)
background_color = estimate_background_color(image)
# Add a constant border around the image
image = cv2.copyMakeBorder(image, border_size, border_size, border_size, border_size, cv2.BORDER_CONSTANT, value=background_color)
photo_boundaries = find_photo_boundaries(image, background_color, tolerance)
if not os.path.exists(output_directory):
os.makedirs(output_directory)
# Get the input file's base name without the extension
input_file_basename = os.path.splitext(os.path.basename(input_file))[0]
for idx, (x, y, w, h) in enumerate(photo_boundaries):
cropped_image = image[y:y+h, x:x+w]
cropped_image = auto_rotate(cropped_image, angle_threshold)
# Remove the added border, but ensure we don't create an empty image
if border_size > 0 and cropped_image.shape[0] > 2 * border_size and cropped_image.shape[1] > 2 * border_size:
cropped_image = cropped_image[border_size:-border_size, border_size:-border_size]
# Check if the cropped image is valid before saving
if cropped_image.size == 0 or cropped_image.shape[0] == 0 or cropped_image.shape[1] == 0:
print(f"Warning: Skipping empty image for region {idx+1}")
continue
output_path = os.path.join(output_directory, f"{input_file_basename}_{idx+1}.png")
cv2.imwrite(output_path, cropped_image)
print(f"Saved {output_path}")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Split photos in an image")
parser.add_argument("input_file", help="The input scanned image containing multiple photos.")
parser.add_argument("output_directory", help="The directory where the result images should be placed.")
parser.add_argument("--tolerance", type=int, default=30, help="Determines the range of color variation around the estimated background color (default: 30).")
parser.add_argument("--min_area", type=int, default=10000, help="Sets the minimum area threshold for a photo (default: 10000).")
parser.add_argument("--min_contour_area", type=int, default=500, help="Sets the minimum contour area threshold for a photo (default: 500).")
parser.add_argument("--angle_threshold", type=int, default=10, help="Sets the minimum absolute angle required for the image to be rotated (default: 10).")
parser.add_argument("--border_size", type=int, default=0, help="Sets the size of the border added and removed to prevent white borders in the output (default: 0).")
args = parser.parse_args()
split_photos(args.input_file, args.output_directory, tolerance=args.tolerance, min_area=args.min_area, min_contour_area=args.min_contour_area, angle_threshold=args.angle_threshold, border_size=args.border_size)