Fix Ghostscript installation instructions and add warning

docs/installation.rst

@@ -391,15 +391,17 @@ package manager:
 
 * ``winget install -e --id Python.Python.3.11``
 * ``winget install -e --id UB-Mannheim.TesseractOCR``
-* ``winget install -e --id ArtifexSoftware.GhostScript``
 
+You will need to install Ghostscript manually, `since it does not support automated
+installs anymore <https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option>`_.
+
+* `Ghostscript download page <https://ghostscript.com/releases/gsdnld.html>`_.`
 
 (Or alternately, using the `Chocolatey <https://chocolatey.org/>`_ package manager, install
 the following when running in an Administrator command prompt):
 
 * ``choco install python3``
 * ``choco install --pre tesseract``
-* ``choco install ghostscript``
 * ``choco install pngquant`` (optional)
 
 Either set of commands will install the required software. At the mmoment there is no

docs/release_notes.rst

@@ -28,6 +28,18 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v15.4.4
+=======
+
+-  Fixed documentation for installing Ghostscript on Windows. :issue:`1198`
+-  Added warning message about security issue in older versions of Ghostscript.
+
+v15.4.3
+=======
+
+-  Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is
+   now required.
+
 v15.4.2
 =======
 

pyproject.toml

@@ -17,7 +17,7 @@ dependencies = [
   "img2pdf>=0.4.4",
   "packaging>=20",
   "pdfminer.six>=20220319",
-  "pikepdf>=8",
+  "pikepdf>=8.7.1",
   "pluggy>=0.13.0",
   "reportlab>=3.6.8",
   "rich>=13",

src/ocrmypdf/_graft.py

@@ -12,12 +12,12 @@ from pathlib import Path
 
 from pikepdf import (
     Dictionary,
+    Matrix,
     Name,
     Operator,
     Page,
     Pdf,
     PdfError,
-    PdfMatrix,
     Stream,
     parse_content_stream,
     unparse_content_stream,
@@ -268,13 +268,13 @@ class OcrGrafter:
             mediabox = base_page.mediabox
             wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            translate = PdfMatrix().translated(-wt / 2, -ht / 2)
+            translate = Matrix().translated(-wt / 2, -ht / 2)
-            untranslate = PdfMatrix().translated(wp / 2, hp / 2)
+            untranslate = Matrix().translated(wp / 2, hp / 2)
-            corner = PdfMatrix().translated(mediabox[0], mediabox[1])
+            corner = Matrix().translated(mediabox[0], mediabox[1])
             # -rotation because the input is a clockwise angle and this formula
             # uses CCW
             text_rotation = -text_rotation % 360
-            rotate = PdfMatrix().rotated(text_rotation)
+            rotate = Matrix().rotated(text_rotation)
 
             # Because of rounding of DPI, we might get a text layer that is not
             # identically sized to the target page. Scale to adjust. Normally this
@@ -285,12 +285,13 @@ class OcrGrafter:
             scale_y = hp / ht
 
             # log.debug('%r', scale_x, scale_y)
-            scale = PdfMatrix().scaled(scale_x, scale_y)
+            scale = Matrix().scaled(scale_x, scale_y)
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox
+            # finally move the lower left corner to match the mediabox. All transforms
-            ctm = translate @ rotate @ scale @ untranslate @ corner
+            # must be premultiplied so they are applied in reverse order here.
+            ctm = corner @ untranslate @ scale @ rotate @ translate
 
             base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -6,6 +6,8 @@ from __future__ import annotations
 
 import logging
 
+from packaging.version import Version
+
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import ghostscript
 from ocrmypdf.exceptions import MissingDependencyError
@@ -58,8 +60,15 @@ def check_options(options):
     if gs_version in BLACKLISTED_GS_VERSIONS:
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "
-            "supported. Please upgrade to a newer version, or downgrade to the "
+            "supported. Please upgrade to a newer version."
-            "previous version."
+        )
+    if gs_version < Version('10.02.0'):
+        log.warning(
+            f"The installed version of Ghostscript {gs_version}, contains a remote "
+            "code execution security vulnerability. Please upgrade to a newer "
+            "version. For details see CVE-2023-43115. The issue is not known to "
+            "affect OCRmyPDF or processing PDFs with Ghostscript, but upgrading "
+            "Ghostscript is recommended."
         )
 
     if options.output_type == 'pdfa':

src/ocrmypdf/pdfinfo/info.py

@@ -25,13 +25,13 @@ from warnings import warn
 
 from pdfminer.layout import LTPage, LTTextBox
 from pikepdf import (
+    Matrix,
     Name,
     Object,
     Page,
     Pdf,
     PdfImage,
     PdfInlineImage,
-    PdfMatrix,
     Stream,
     UnsupportedImageTypeError,
     parse_content_stream,
@@ -209,7 +209,7 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
     CTM unchanged.
     """
     stack = []
-    ctm = PdfMatrix(initial_shorthand)
+    ctm = Matrix(initial_shorthand)
     xobject_settings: list[XobjectSettings] = []
     inline_images: list[InlineSettings] = []
     name_index = defaultdict(lambda: [])
@@ -240,7 +240,7 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
                 # to do. Just pretend nothing happened, keep calm and carry on.
                 warn("PDF graphics stack underflowed - PDF may be malformed")
         elif operator == 'cm':
-            ctm = PdfMatrix(operands) @ ctm
+            ctm = Matrix(operands) @ ctm
         elif operator == 'Do':
             image_name = operands[0]
             settings = XobjectSettings(
@@ -614,12 +614,12 @@ def _process_content_streams(
     ):
         # Set the CTM to the state it was when the "Do" operator was
         # encountered that is drawing this instance of the Form XObject
-        ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity()
+        ctm = Matrix(shorthand) if shorthand else Matrix()
 
         # A Form XObject may provide its own matrix to map form space into
         # user space. Get this if one exists
-        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
+        form_shorthand = container.get(Name.Matrix, Matrix())
-        form_matrix = PdfMatrix(form_shorthand)
+        form_matrix = Matrix(form_shorthand)
 
         # Concatenate form matrix with CTM to ensure CTM is correct for
         # drawing this instance of the XObject