v16.4.3 release notes

Fixes #1361

docs/release_notes.rst

@@ -30,6 +30,15 @@ OCRmyPDF typically supports the three most recent Python versions.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v16.4.3
+=======
+
+-  Work around pdfminer.six issue where a token on the buffer boundary is incorrectly
+   parsed as two tokens. :issue:`1361`
+-  New rules are applied to stencil masks and explicit masks when calculating the
+   optimal page DPI for rendering. :issue:`1362`
+-  Fixed attempts to use an incompatible jbig2.EXE provided by TeX Live. :issue:`1363`
+
 v16.4.2
 =======
 

src/ocrmypdf/_exec/jbig2enc.py

@@ -5,7 +5,7 @@
 
 from __future__ import annotations
 
-from subprocess import PIPE
+from subprocess import PIPE, CalledProcessError
 
 from packaging.version import Version
 
@@ -14,7 +14,13 @@ from ocrmypdf.subprocess import get_version, run
 
 
 def version() -> Version:
-    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
+    try:
+        version = get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+    except CalledProcessError as e:
+        # TeX Live for Windows provides an incompatible jbig2.EXE which may
+        # be on the PATH.
+        raise MissingDependencyError('jbig2enc') from e
+    return Version(version)
 
 
 def available():

src/ocrmypdf/pdfinfo/info.py

@@ -369,18 +369,21 @@ class ImageInfo:
             pim = PdfImage(pdfimage)
         else:
             raise ValueError("Either pdfimage or inline must be set")
-        if pim.obj.get(Name.SMask, None) is not None:
+
+        self._width = pim.width
+        self._height = pim.height
+        if (smask := pim.obj.get(Name.SMask, None)) is not None:
             # SMask is pretty much an alpha channel, but in PDF it's possible
             # for channel to have different dimensions than the image
             # itself. Some PDF writers use this to create a grayscale stencil
             # mask. For our purposes, the effective size is the size of the
             # larger component (image or smask).
-            smask = pim.obj[Name.SMask]
+            self._width = max(smask.get(Name.Width, 0), self._width)
-            self._width = max(smask.get(Name.Width, 0), pim.width)
+            self._height = max(smask.get(Name.Height, 0), self._height)
-            self._height = max(smask.get(Name.Height, 0), pim.height)
+        if (mask := pim.obj.get(Name.Mask, None)) is not None:
-        else:
+            # If the image has a /Mask entry, it has an explicit mask.
-            self._width = pim.width
+            self._width = max(mask.get(Name.Width, 0), self._width)
-            self._height = pim.height
+            self._height = max(mask.get(Name.Height, 0), self._height)
 
         # If /ImageMask is true, then this image is a stencil mask
         # (Images that draw with this stencil mask will have a reference to
@@ -484,9 +487,18 @@ class ImageInfo:
     def renderable(self) -> bool:
         """Whether the image is renderable.
 
-        Some PDFs in the wild have invalid images that are not renderable.
+        Some PDFs in the wild have invalid images that are not renderable,
+        due to unusual dimensions.
+
+        Stencil masks are not also not renderable, since they are not
+        drawn, but rather they control how rendering happens.
         """
-        return self.dpi.is_finite and self.width >= 0 and self.height >= 0
+        return (
+            self.dpi.is_finite
+            and self.width >= 0
+            and self.height >= 0
+            and self.type_ != 'stencil'
+        )
 
     @property
     def dpi(self) -> Resolution:
@@ -1065,10 +1077,14 @@ class PageInfo:
 
         Returns None if there is no meaningful DPI for the page.
         """
-        image_dpis = [
+        image_dpis = []
-            image.dpi.to_scalar() for image in self._images if image.renderable
+        image_areas = []
-        ]
+        for image in self._images:
-        image_areas = [image.printed_area for image in self._images if image.renderable]
+            if not image.renderable:
+                continue
+            image_dpis.append(image.dpi.to_scalar())
+            image_areas.append(image.printed_area)
+
         total_drawn_area = sum(image_areas)
         if total_drawn_area == 0:
             return None

src/ocrmypdf/pdfinfo/layout.py

@@ -17,6 +17,7 @@ import pdfminer
 import pdfminer.encodingdb
 import pdfminer.pdfdevice
 import pdfminer.pdfinterp
+import pdfminer.psparser
 from pdfminer.converter import PDFLayoutAnalyzer
 from pdfminer.layout import LAParams, LTChar, LTPage, LTTextBox
 from pdfminer.pdfcolor import PDFColorSpace
@@ -58,9 +59,10 @@ def pdfsimplefont__init__(
 
 setattr(PDFSimpleFont, '__init__', pdfsimplefont__init__)
 
-#
+# Patch pdfminer.six buffer size
-# pdfminer patches when creator is PScript5.dll
+# The parser doesn't properly handle keyword tokens are split across the end of the
-#
+# buffer, so increase the buffer size something far larger than will ever be seen.
+pdfminer.psparser.PSBaseParser.BUFSIZ = 256 * 1024 * 1024
 
 
 def pdftype3font__pscript5_get_height(self):