Fix ZeroDivisionError on files containing images drawn at scale 0

Fixes #761

src/ocrmypdf/helpers.py

@@ -15,7 +15,7 @@ from collections.abc import Iterable
 from contextlib import suppress
 from functools import wraps
 from io import StringIO
-from math import isclose
+from math import isclose, isfinite
 from pathlib import Path
 from typing import Any, Sequence
 
@@ -39,6 +39,10 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
     def is_square(self) -> bool:
         return isclose(self.x, self.y, rel_tol=1e-3)
 
+    @property
+    def is_finite(self) -> bool:
+        return isfinite(self.x) and isfinite(self.y)
+
     def take_max(self, vals, yvals=None):
         if yvals is not None:
             return Resolution(max(self.x, *vals), max(self.y, *yvals))

src/ocrmypdf/pdfinfo/info.py

@@ -14,7 +14,7 @@ from contextlib import ExitStack
 from decimal import Decimal
 from enum import Enum
 from functools import partial
-from math import hypot, isclose
+from math import hypot, isclose, ulp
 from os import PathLike
 from pathlib import Path
 from typing import Container, Iterator, Optional, Tuple, Union
@@ -260,8 +260,9 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
     image_drawn_height = hypot(c, d)
 
     # The scale of the image is pixels per unit of default user space (1/72")
-    scale_w = image_size[0] / image_drawn_width
-    scale_h = image_size[1] / image_drawn_height
+    # use ulp to turn divide by zero into infinity
+    scale_w = image_size[0] / (image_drawn_width + ulp(0))
+    scale_h = image_size[1] / (image_drawn_height + ulp(0))
 
     # DPI = scale * 72
     dpi_w = scale_w * 72.0
@@ -365,6 +366,10 @@ class ImageInfo:
     def enc(self):
         return self._enc
 
+    @property
+    def renderable(self):
+        return self.dpi.is_finite and self.width >= 0 and self.height >= 0
+
     @property
     def dpi(self):
         return _get_dpi(self._shorthand, (self._width, self._height))
@@ -734,7 +739,9 @@ class PageInfo:
 
         self._dpi = None
         if self._images:
-            dpi = Resolution(0.0, 0.0).take_max(image.dpi for image in self._images)
+            dpi = Resolution(0.0, 0.0).take_max(
+                image.dpi for image in self._images if image.renderable
+            )
             self._dpi = dpi
             self._width_pixels = int(round(dpi.x * float(self._width_inches)))
             self._height_pixels = int(round(dpi.y * float(self._height_inches)))

tests/test_pdfinfo.py

@@ -17,6 +17,7 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf import pdfinfo
 from ocrmypdf.exceptions import InputFileError
+from ocrmypdf.helpers import Resolution
 from ocrmypdf.pdfinfo import Colorspace, Encoding
 from ocrmypdf.pdfinfo.layout import PDFPage
 
@@ -194,3 +195,23 @@ def test_pages_issue700(monkeypatch, resources):
             progbar=False,
             max_workers=1,
         )
+
+
+def test_image_scale0(resources, outpdf):
+    with pikepdf.open(resources / 'cmyk.pdf') as cmyk:
+        xobj = pikepdf.Page(cmyk.pages[0]).as_form_xobject()
+
+        p = pikepdf.Pdf.new()
+        p.add_blank_page(page_size=(72, 72))
+        objname = pikepdf.Page(p.pages[0]).add_resource(
+            p.copy_foreign(xobj), pikepdf.Name.XObject, pikepdf.Name.Im0
+        )
+        print(objname)
+        p.pages[0].Contents = pikepdf.Stream(
+            p, b"q 0 0 0 0 0 0 cm %s Do Q" % bytes(objname)
+        )
+        p.save(outpdf)
+
+    pi = pdfinfo.PdfInfo(outpdf, detailed_analysis=True, progbar=False, max_workers=1)
+    assert not pi.pages[0]._images[0].dpi.is_finite
+    assert pi.pages[0].dpi == Resolution(0, 0)