v12.3.0 release notes

Pillow decided against round-tripping DPI values.
https://github.com/python-pillow/Pillow/pull/5476

Fixes #802

docs/api.rst

@@ -44,7 +44,7 @@ execution. To do this, it will:
 The Python process that calls ``ocrmypdf.ocr()`` must be sufficiently
 privileged to perform these actions.
 
-There is no currently no option to manage how jobs are scheduled other
+There currently is no option to manage how jobs are scheduled other
 than the argument ``jobs=`` which will limit the number of worker
 processes.
 

docs/pdfsecurity.rst

@@ -19,7 +19,7 @@ PDF is a rich, complex file format. The official PDF 1.7 specification,
 ISO 32000:2008, is hundreds of pages long and references several annexes
 each of which are similar in length. PDFs can contain video, audio, XML,
 JavaScript and other programming, and forms. In some cases, they can
-open internet connections to pre-selected URLs. All of these possible
+open internet connections to pre-selected URLs. All of these are possible
 attack vectors.
 
 In short, PDFs `may contain
@@ -31,7 +31,7 @@ describes a high-paranoia method which allows potentially hostile PDFs
 to be viewed and rasterized safely in a disposable virtual machine. A
 trusted PDF created in this manner is converted to images and loses all
 information making it searchable and losing all compression. OCRmyPDF
-could be used restore searchability.
+could be used to restore searchability.
 
 How OCRmyPDF processes PDFs
 ===========================
@@ -66,8 +66,8 @@ service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
 online one should be prepared to comply with Ghostscript's Affero GPL
 license, and any other licenses.
 
-Setting aside these concerns, a side effect of OCRmyPDF is it may
+Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs that contain certain types of malware. It
+incidentally sanitize PDFs containing certain types of malware. It
 repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
 structures that are part of an attack. When PDF/A output is selected
 (the default), the input PDF is partially reconstructed by Ghostscript.
@@ -83,7 +83,7 @@ Limiting CPU usage
 OCRmyPDF will attempt to use all available CPUs and storage, so
 executing ``nice ocrmypdf`` or limiting the number of jobs with the
 ``-j`` argument may ensure the server remains available. Another option
-would be run OCRmyPDF jobs inside a Docker container, a virtual machine,
+would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
 or a cloud instance, which can impose its own limits on CPU usage and be
 terminated "from orbit" if it fails to complete.
 

docs/release_notes.rst

@@ -13,6 +13,19 @@ The public API may be useful in scripts that launch OCRmyPDF processes or that
 wish to use some of its features for working with PDFs.
 
 
+v12.3.0
+=======
+
+-  Fixed a regression introduced in Pillow 8.3.0. Pillow no longer rounds DPI
+   for image resolutions. We now account for this. (:issue:`802`)
+-  We no longer use some API calls that are deprecated in the latest versions of
+   pikepdf.
+-  Improved error message when a language is requested that doesn't look like a
+   typical ISO 639-2 code.
+-  Fixed some tests that attempted to symlink on Windows, breaking tests on a
+   Windows desktop but not usually on CI.
+-  Documentation fixes (thanks to @mara004)
+
 v12.2.0
 =======
 

setup.cfg

@@ -79,7 +79,7 @@ test =
                                  # or brew install exempi
 docs =
     sphinx
-    sphinx_rtd_theme
+    sphinx-rtd-theme
     sphinx-issues
 extended_test =
     PyMuPDF == 1.13.4

src/ocrmypdf/_graft.py

@@ -47,7 +47,8 @@ def strip_invisible_text(pdf, page):
     render_mode = 0
     text_objects = []
 
-    page.page_contents_coalesce()
+    rich_page = pikepdf.Page(page)
+    rich_page.contents_coalesce()
     for operands, operator in pikepdf.parse_content_stream(page, ''):
         if not in_text_obj:
             if operator == pikepdf.Operator('BT'):
@@ -307,7 +308,14 @@ class OcrGrafter:
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
 
-            base_page.page_contents_add(new_text_layer, prepend=True)
+            if hasattr(pikepdf.Page, 'contents_add'):
+                # pikepdf >= 2.14 adds this method and deprecates the one below
+                pikepdf.Page(base_page).contents_add(new_text_layer, prepend=True)
+            else:
+                # pikepdf < 2.14
+                base_page.page_contents_add(
+                    new_text_layer, prepend=True
+                )  # pragma: no cover
 
             _update_resources(
                 obj=base_page, font=font, font_key=font_key, procset=procset

src/ocrmypdf/_validation.py

@@ -65,13 +65,14 @@ def check_options_languages(options, ocr_engine_languages):
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
-    if not options.languages.issubset(ocr_engine_languages):
+    missing_languages = options.languages - ocr_engine_languages
+    if missing_languages:
         msg = (
             f"OCR engine does not have language data for the following "
             "requested languages: \n"
         )
-        for lang in options.languages - ocr_engine_languages:
+        msg += '\n'.join(lang for lang in missing_languages)
-            msg += lang + '\n'
+        msg += '\nNote: most languages are identified by a 3-digit ISO 639-2 Code'
         raise MissingDependencyError(msg)
 
 

src/ocrmypdf/helpers.py

@@ -25,19 +25,31 @@ log = logging.getLogger(__name__)
 
 
 class Resolution(namedtuple('Resolution', ('x', 'y'))):
-    """The number of pixels per inch in each 2D direction."""
+    """The number of pixels per inch in each 2D direction.
+
+    Resolution objects are considered "equal" for == purposes if they are
+    equal to a reasonable tolerance.
+    """
 
     __slots__ = ()
 
+    # rel_tol after converting from dpi to pixels per meter and saving
+    # as integer with rounding, as many file formats
+    CONVERSION_ERROR = 0.002
+
     def round(self, ndigits: int):
         return Resolution(round(self.x, ndigits), round(self.y, ndigits))
 
     def to_int(self):
         return Resolution(int(round(self.x)), int(round(self.y)))
 
+    @classmethod
+    def _isclose(cls, a, b):
+        return isclose(a, b, rel_tol=cls.CONVERSION_ERROR)
+
     @property
     def is_square(self) -> bool:
-        return isclose(self.x, self.y, rel_tol=1e-3)
+        return self._isclose(self.x, self.y)
 
     @property
     def is_finite(self) -> bool:
@@ -61,6 +73,13 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
     def __repr__(self):  # pragma: no cover
         return f"Resolution({self.x}x{self.y} dpi)"
 
+    def __eq__(self, other):
+        if isinstance(other, tuple) and len(other) == 2:
+            other = Resolution(*other)
+        if not isinstance(other, Resolution):
+            return NotImplemented
+        return self._isclose(self.x, other.x) and self._isclose(self.y, other.y)
+
 
 class NeverRaise(Exception):
     """An exception that is never raised"""

tests/test_ghostscript.py

@@ -72,7 +72,7 @@ def test_rasterize_rotated(francais, outdir, caplog):
 
     with Image.open(outdir / 'out.png') as im:
         assert im.size == (target_size[1], target_size[0])
-        assert im.info['dpi'] == (forced_dpi[1], forced_dpi[0])
+        assert im.info['dpi'] == forced_dpi.flip_axis()
 
 
 def test_gs_render_failure(resources, outpdf):

tests/test_helpers.py

@@ -16,6 +16,8 @@ from ocrmypdf import helpers
 
 from .conftest import running_in_docker
 
+needs_symlink = pytest.mark.skipif(os.name == 'nt', reason='needs posix symlink')
+
 
 class TestSafeSymlink:
     def test_safe_symlink_link_self(self, tmp_path, caplog):
@@ -27,6 +29,7 @@ class TestSafeSymlink:
         with pytest.raises(FileExistsError):
             helpers.safe_symlink(tmp_path / 'input', tmp_path / 'regular_file')
 
+    @needs_symlink
     def test_safe_symlink_relink(self, tmp_path):
         (tmp_path / 'regular_file_a').touch()
         (tmp_path / 'regular_file_b').write_bytes(b'ABC')
@@ -77,6 +80,7 @@ class TestFileIsWritable:
     def test_plain(self, non_existent):
         assert helpers.is_file_writable(non_existent)
 
+    @needs_symlink
     def test_symlink_loop(self, tmp_path):
         loop = tmp_path / 'loop'
         loop.symlink_to(loop)