almet/dangerzone
1
0
Fork 0
mirror of https://github.com/freedomofpress/dangerzone.git synced 2025-04-28 18:02:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

Fix DPI mismatch between doc2pixels and pixels2pdf

Browse source 
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
This commit is contained in:
deeplow 2023-12-04 16:38:53 +00:00
parent e5dbe25abb
commit 576cbd3382
No known key found for this signature in database
GPG key ID: 577982871529A52A
4 changed files with 8 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
CHANGELOG.md
View file

@ -7,6 +7,9 @@ since 0.4.1, and this project adheres to [Semantic Versioning](https://semver.or
## Unreleased ## 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 ### 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)) - 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))

1
dangerzone/conversion/common.py
View file

@ -15,6 +15,7 @@ from typing import Callable, Dict, List, Optional, Tuple, Union
TIMEOUT_PER_PAGE: float = 30 # (seconds) TIMEOUT_PER_PAGE: float = 30 # (seconds)
TIMEOUT_PER_MB: float = 30 # (seconds) TIMEOUT_PER_MB: float = 30 # (seconds)
TIMEOUT_MIN: float = 60 # (seconds) TIMEOUT_MIN: float = 60 # (seconds)
DEFAULT_DPI = 150 # Pixels per inch
def running_on_qubes() -> bool: def running_on_qubes() -> bool:

4
dangerzone/conversion/doc_to_pixels.py
View file

@ -19,7 +19,7 @@ import fitz
import magic import magic
from . import errors from . import errors
from .common import DangerzoneConverter, running_on_qubes from .common import DEFAULT_DPI, DangerzoneConverter, running_on_qubes
class DocumentToPixels(DangerzoneConverter): class DocumentToPixels(DangerzoneConverter):
@ -245,7 +245,7 @@ class DocumentToPixels(DangerzoneConverter):
self.update_progress( self.update_progress(
f"Converting page {page_num}/{doc.page_count} to pixels" 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 rgb_buf = pix.samples_mv
await self.write_page_width(pix.width, width_filename) await self.write_page_width(pix.width, width_filename)
await self.write_page_height(pix.height, height_filename) await self.write_page_height(pix.height, height_filename)

3
dangerzone/conversion/pixels_to_pdf.py
View file

@ -15,7 +15,7 @@ from typing import Optional
import fitz 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): class PixelsToPDF(DangerzoneConverter):
@ -52,6 +52,7 @@ class PixelsToPDF(DangerzoneConverter):
pixmap = fitz.Pixmap( pixmap = fitz.Pixmap(
fitz.Colorspace(fitz.CS_RGB), width, height, untrusted_rgb_data, False fitz.Colorspace(fitz.CS_RGB), width, height, untrusted_rgb_data, False
) )
pixmap.set_dpi(DEFAULT_DPI, DEFAULT_DPI)
if ocr_lang: # OCR the document if ocr_lang: # OCR the document
self.update_progress( self.update_progress(
f"Converting page {page_num}/{num_pages} from pixels to searchable PDF" f"Converting page {page_num}/{num_pages} from pixels to searchable PDF"