From 576cbd33820f45df3909d6ad1119502e370598ea Mon Sep 17 00:00:00 2001
From: deeplow <deeplower@protonmail.com>
Date: Mon, 4 Dec 2023 16:38:53 +0000
Subject: [PATCH] Fix DPI mismatch between doc2pixels and pixels2pdf

The original document was larger in dimensions than the original one due
to a mismatch in DPI settings. When converting documents to pixels we
were setting the DPI to 150 pixels per inch. Then when converting back
into a PDF we were using 70 DPI. This difference would result in an
overall larger document in dimensions (though not necessarily in file
size).

Fixes #626
---
 CHANGELOG.md                           | 3 +++
 dangerzone/conversion/common.py        | 1 +
 dangerzone/conversion/doc_to_pixels.py | 4 ++--
 dangerzone/conversion/pixels_to_pdf.py | 3 ++-
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index d9ca256..f808968 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,9 @@ since 0.4.1, and this project adheres to [Semantic Versioning](https://semver.or
 
 ## Unreleased
 
+## Fixed
+- Fix mismatched between between original document and converted one ([issue #626](https://github.com/freedomofpress/dangerzone/issues/)). This does not affect the quality of the final document.
+
 ### Changed
 
 - Feature: Add support for HWP/HWPX files (Hancom Office) for macOS Apple Silicon devices ([issue #498](https://github.com/freedomofpress/dangerzone/issues/498), thanks to [@OctopusET](https://github.com/OctopusET))
diff --git a/dangerzone/conversion/common.py b/dangerzone/conversion/common.py
index 94f9580..5b75186 100644
--- a/dangerzone/conversion/common.py
+++ b/dangerzone/conversion/common.py
@@ -15,6 +15,7 @@ from typing import Callable, Dict, List, Optional, Tuple, Union
 TIMEOUT_PER_PAGE: float = 30  # (seconds)
 TIMEOUT_PER_MB: float = 30  # (seconds)
 TIMEOUT_MIN: float = 60  # (seconds)
+DEFAULT_DPI = 150  # Pixels per inch
 
 
 def running_on_qubes() -> bool:
diff --git a/dangerzone/conversion/doc_to_pixels.py b/dangerzone/conversion/doc_to_pixels.py
index d3d351a..60157d7 100644
--- a/dangerzone/conversion/doc_to_pixels.py
+++ b/dangerzone/conversion/doc_to_pixels.py
@@ -19,7 +19,7 @@ import fitz
 import magic
 
 from . import errors
-from .common import DangerzoneConverter, running_on_qubes
+from .common import DEFAULT_DPI, DangerzoneConverter, running_on_qubes
 
 
 class DocumentToPixels(DangerzoneConverter):
@@ -245,7 +245,7 @@ class DocumentToPixels(DangerzoneConverter):
             self.update_progress(
                 f"Converting page {page_num}/{doc.page_count} to pixels"
             )
-            pix = page.get_pixmap(dpi=150)
+            pix = page.get_pixmap(dpi=DEFAULT_DPI)
             rgb_buf = pix.samples_mv
             await self.write_page_width(pix.width, width_filename)
             await self.write_page_height(pix.height, height_filename)
diff --git a/dangerzone/conversion/pixels_to_pdf.py b/dangerzone/conversion/pixels_to_pdf.py
index 13516e0..d5732dc 100644
--- a/dangerzone/conversion/pixels_to_pdf.py
+++ b/dangerzone/conversion/pixels_to_pdf.py
@@ -15,7 +15,7 @@ from typing import Optional
 
 import fitz
 
-from .common import DangerzoneConverter, get_tessdata_dir, running_on_qubes
+from .common import DEFAULT_DPI, DangerzoneConverter, get_tessdata_dir, running_on_qubes
 
 
 class PixelsToPDF(DangerzoneConverter):
@@ -52,6 +52,7 @@ class PixelsToPDF(DangerzoneConverter):
             pixmap = fitz.Pixmap(
                 fitz.Colorspace(fitz.CS_RGB), width, height, untrusted_rgb_data, False
             )
+            pixmap.set_dpi(DEFAULT_DPI, DEFAULT_DPI)
             if ocr_lang:  # OCR the document
                 self.update_progress(
                     f"Converting page {page_num}/{num_pages} from pixels to searchable PDF"