Merge branch 'main' into cd.new-regions

README.md

@@ -77,7 +77,7 @@ Guidelines for contributing can be found [here](https://github.com/target/strelk
 
 ## Known Issues
 There is currently a known issue with compilation on ARM based hosts (e.g., Apple M1). Attempting to compile the current version of Strelka will lead to the following issue:
-https://github.com/target/strelka/issues/188. You can bypass this compilation issue by removing `pymupdf` from the backend Python `requirements.txt` file and commenting out ScanPDF in the `backend.yml` file. Doing this will allow you to compile the current version of Strelka at the expense of being unable to scan PDF files.
+https://github.com/target/strelka/issues/188. You can bypass this compilation issue by removing `pymupdf` from the backend Python `requriements.txt` file and commenting out ScanPDF in the `backend.yml` file. Doing this will allow you to compile the current version of Strelka at the expense of being unable to scan PDF files.
 
 ## Related Projects
 * [Laika BOSS](https://github.com/lmco/laikaboss)

build/python/backend/Dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:22.10
+FROM ubuntu:22.04
 ARG DEBIAN_FRONTEND=noninteractive
 LABEL maintainer="Target Brands, Inc. [email protected]"
 

build/python/backend/requirements.txt

@@ -29,7 +29,7 @@ olefile==0.46
 oletools==0.60.1
 opencv-python==4.6.0.66
 opencv-contrib-python==4.6.0.66
-PyMuPDF==1.22.5  # https://github.com/pymupdf/PyMuPDF/issues/2617
+PyMuPDF==1.19.6
 pefile==2019.4.18
 pgpdump3==1.5.2
 pyelftools==0.27

src/python/strelka/scanners/scan_ocr.py

@@ -22,9 +22,8 @@ def scan(self, data, file, options, expire_at):
         pdf_to_png = options.get('pdf_to_png', False)
 
         if pdf_to_png and 'application/pdf' in file.flavors.get('mime', []):
-            # TODO: Use fitz builtin OCR support which also wraps tesseract
             doc = fitz.open(stream=data, filetype='pdf')
-            data = doc.get_page_pixmap(0, dpi=120).tobytes('png')
+            data = doc.get_page_pixmap(0).tobytes('png')
 
         with tempfile.NamedTemporaryFile(dir=tmp_directory) as tmp_data:
             tmp_data.write(data)