Merge branch 'master' of github.com:jbarlow83/OCRmyPDF

Fixes #642

docs/installation.rst

@@ -190,7 +190,8 @@ of ocrmypdf, and install the following dependencies:
         python3-reportlab \
         qpdf \
         tesseract-ocr \
-        zlib1g
+        zlib1g \
+        unpaper
 
 We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
 

docs/release_notes.rst

@@ -12,12 +12,28 @@ may be unreliable. Use the API to depend on precise behavior.
 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.
 
+v11.1.2
+=======
+
+-  Fix hOCR renderer writing the text in roughly reverse order. This should not
+   affect reasonably smart PDF readers that properly locate the position of all
+   text, but may confuse those that rely on the order of objects in the content
+   stream. (#642)
+
+v11.1.1
+=======
+
+-  We now avoid using named temporary files when using pngquant allowing containerized
+   pngquant installs to be used.
+-  Clarified an error message.
+-  Highest number of 1's in a release ever!
+
 v11.1.0
 =======
 
 -  Fixed page rotation issues: #634, #589.
 -  Fixed some cases where optimization created an invalid image such as a
-   1-bit "RGB" iamge: #629, #620.
+   1-bit "RGB" image: #629, #620.
 -  Page numbers are now displayed in debug logs when pages are being grafted.
 -  ocrmypdf.optimize.rewrite_png and ocrmypdf.optimize.rewrite_png_as_g4 were
    marked deprecated. Strictly speaking these should have been internal APIs,

src/ocrmypdf/_exec/pngquant.py

@@ -7,7 +7,11 @@
 
 """Interface to pngquant executable"""
 
+from contextlib import contextmanager
+from io import BytesIO
 from os import fspath
+from pathlib import Path
+from subprocess import PIPE
 from tempfile import NamedTemporaryFile
 
 from PIL import Image
@@ -28,34 +32,32 @@ def available():
     return True
 
 
-def quantize(input_file, output_file, quality_min, quality_max):
-    input_file = fspath(input_file)
-    output_file = fspath(output_file)
-    if input_file.endswith('.jpg'):
-        with Image.open(input_file) as im, NamedTemporaryFile(suffix='.png') as tmp:
-            im.save(tmp)
-            args = [
-                'pngquant',
-                '--force',
-                '--skip-if-larger',
-                '--output',
-                output_file,
-                '--quality',
-                f'{quality_min}-{quality_max}',
-                '--',
-                tmp.name,
-            ]
-            run(args)
+@contextmanager
+def input_as_png(input_file: Path):
+    if not input_file.name.endswith('.png'):
+        with Image.open(input_file) as im:
+            bio = BytesIO()
+            im.save(bio, format='png')
+            bio.seek(0)
+            yield bio
     else:
+        with open(input_file, 'rb') as f:
+            yield f
+
+
+def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
+    with input_as_png(input_file) as input_stream:
         args = [
             'pngquant',
             '--force',
             '--skip-if-larger',
-            '--output',
-            output_file,
             '--quality',
             f'{quality_min}-{quality_max}',
-            '--',
-            input_file,
+            '--',  # pngquant: stop processing arguments
+            '-',  # pngquant: stream input and output
         ]
-        run(args)
+        result = run(args, stdin=input_stream, stdout=PIPE, stderr=PIPE, check=False)
+
+    if result.returncode == 0:
+        # input_file could be the same as output_file, so we defer the write
+        output_file.write_bytes(result.stdout)

src/ocrmypdf/_exec/unpaper.py

@@ -107,7 +107,7 @@ def run(input_file, output_file, dpi, mode_args):
 
 def validate_custom_args(args: str):
     unpaper_args = shlex.split(args)
-    if any('/' in arg for arg in unpaper_args):
+    if any(('/' in arg or arg == '.' or arg == '..') for arg in unpaper_args):
         raise ValueError('No filenames allowed in --unpaper-args')
     return unpaper_args
 

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -39,13 +39,11 @@ def check_options(options):
     if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
         # https://bugs.ghostscript.com/show_bug.cgi?id=696874
         # Ghostscript < 9.20 fails to encode multibyte characters properly
-        msg = (
-            "The installed version of Ghostscript does not work correctly "
-            "with the OCR languages you specified. Use --output-type pdf or "
+        log.warning(
+            f"The installed version of Ghostscript ({gs_version}) does not work "
+            "correctly with the OCR languages you specified. Use --output-type pdf or "
             "upgrade to Ghostscript 9.20 or later to avoid this issue."
         )
-        msg += f"Found Ghostscript {gs_version}"
-        log.warning(msg)
 
     if options.output_type == 'pdfa':
         options.output_type = 'pdfa-2'

src/ocrmypdf/hocrtransform.py

@@ -167,7 +167,10 @@ class HocrTransform:
     def topdown_position(self, element):
         pxl_line_coords = self.element_coordinates(element)
         line_box = self.pt_from_pixel(pxl_line_coords)
-        return -line_box.y2
+        # Coordinates here are still in the hocr coordinate system, so 0 on the y axis
+        # is the top of the page and increasing values of y will move towards the
+        # bottom of the page.
+        return line_box.y2
 
     def to_pdf(
         self,

src/ocrmypdf/optimize.py

@@ -417,6 +417,7 @@ def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
                 im_obj[key] = local_image[key]
         for key in del_keys:
             del im_obj[key]
+    return True
 
 
 def transcode_pngs(

tests/test_validation.py

@@ -55,7 +55,7 @@ def test_old_ghostscript(caplog):
         vd._check_options(
             *make_opts_pm(language='chi_sim', output_type='pdfa'), {'chi_sim'}
         )
-        assert 'Ghostscript does not work correctly' in caplog.text
+        assert 'does not work correctly' in caplog.text
 
     with patch('ocrmypdf._exec.ghostscript.version', return_value='9.18'), patch(
         'ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=True