v4.3.4: release notes

Redirect stderr->stdout to hopefully make GS output easier to work with
overall, since the previous code didn’t seem to account for mixed used
properly.

MANIFEST.in

@@ -14,6 +14,7 @@ include .dockerignore
 # tests
 include pytest.ini
 recursive-include tests *.jpg
+recursive-include tests *.png
 recursive-include tests *.pdf
 recursive-include tests *.py
 recursive-include tests *.rst

RELEASE_NOTES.rst

@@ -3,6 +3,12 @@ RELEASE NOTES
 
 OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
 
+v4.3.4:
+=======
+
+-  Fixed "decimal.InvalidOperation: quantize result has too many digits" for high DPI images
+
+
 v4.3.3:
 =======
 

ocrmypdf/ghostscript.py

@@ -2,7 +2,7 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from tempfile import NamedTemporaryFile
-from subprocess import Popen, PIPE, check_call
+from subprocess import Popen, PIPE, STDOUT, check_call
 from shutil import copy
 from . import get_program
 from .pdfa import SRGB_ICC_PROFILE
@@ -25,16 +25,13 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
             input_file
         ]
 
-        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=PIPE,
+        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=STDOUT,
                   universal_newlines=True)
-        stdout, stderr = p.communicate()
+        stdout, _ = p.communicate()
-        if stdout:
+        if 'error' in stdout:
-            if 'error' in stdout:
+            log.error(stdout)  # Ghostscript puts errors in stdout
-                log.error(stdout)  # Ghostscript puts errors in stdout
+        else:
-            else:
+            log.debug(stdout)
-                log.debug(stdout)
-        if stderr:
-            log.error(stderr)
 
         if p.returncode == 0:
             copy(tmp.name, output_file)
@@ -60,24 +57,22 @@ def generate_pdfa(pdf_pages, output_file, log, threads=1):
             "-sOutputFile=" + gs_pdf.name,
         ]
         args_gs.extend(pdf_pages)
-        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=PIPE,
+        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=STDOUT,
                   universal_newlines=True)
-        stdout, stderr = p.communicate()
+        stdout, _ = p.communicate()
-        if stdout:
+
-            if 'error' in stdout:
+        if 'error' in stdout:
-                log.error(stdout)
+            log.error(stdout)
-            elif 'overprint mode not set' in stdout:
+        elif 'overprint mode not set' in stdout:
-                # Unless someone is going to print PDF/A documents on a
+            # Unless someone is going to print PDF/A documents on a
-                # magical sRGB printer I can't see the removal of overprinting
+            # magical sRGB printer I can't see the removal of overprinting
-                # being a problem....
+            # being a problem....
-                log.debug(
+            log.debug(
-                    "Ghostscript had to remove PDF 'overprinting' from the "
+                "Ghostscript had to remove PDF 'overprinting' from the "
-                    "input file to complete PDF/A conversion. "
+                "input file to complete PDF/A conversion. "
-                    )
+                )
-            else:
+        else:
-                log.debug(stdout)
+            log.debug(stdout)
-        if stderr:
-            log.error(stderr)
 
         if p.returncode == 0:
             # Ghostscript does not change return code when it fails to create

ocrmypdf/pageinfo.py

@@ -2,7 +2,7 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from subprocess import Popen, PIPE
-from decimal import Decimal, getcontext
+from decimal import Decimal
 from math import hypot
 import re
 import sys
@@ -330,9 +330,9 @@ def _find_page_regular_images(page, pageinfo, contentsinfo):
             image['dpi_h'] = max(dpi_h, image.get('dpi_h', 0))
 
         DPI_PREC = Decimal('1.000')
+        dpi = Decimal(image['dpi_w'] * image['dpi_h']).sqrt()
         image['dpi_w'] = Decimal(image['dpi_w']).quantize(DPI_PREC)
         image['dpi_h'] = Decimal(image['dpi_h']).quantize(DPI_PREC)
-        dpi = Decimal(image['dpi_w'] * image['dpi_h']).sqrt()
         image['dpi'] = dpi.quantize(DPI_PREC)
         yield image
 
@@ -407,7 +407,6 @@ def _pdf_get_pageinfo(infile, pageno: int):
 
 def pdf_get_all_pageinfo(infile):
     pdf = pypdf.PdfFileReader(infile)
-    getcontext().prec = 6
     return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]
 
 

setup.py

@@ -191,7 +191,7 @@ setup(
     url='https://github.com/jbarlow83/OCRmyPDF',
     author='James R. Barlow',
     author_email='jim@purplerock.ca',
-    license='Public Domain',
+    license='MIT',
     packages=['ocrmypdf'],
     keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
     classifiers=[

tests/resources/README.rst

@@ -31,6 +31,9 @@ In some cases they were converted from one image format to another without other
     *   - LinnSequencer.jpg, linn.pdf, linn.txt
         - `Wikimedia: LinnSequencer`_
         - Creative Commons BY-SA 3.0
+    *   - typewriter.png, 2400dpi.pdf
+        - `Wikimedia: Triumph typewrtier text Linzensoep`_
+        * Creative Commons BY-SA 2.5
 
 
 Files generated for this project
@@ -105,3 +108,5 @@ These test resources are assemblies from other previously mentioned files, relea
 .. _`Wikimedia: JPEG2000 Lichtenstein`: https://en.wikipedia.org/wiki/JPEG_2000#/media/File:Jpeg2000_2-level_wavelet_transform-lichtenstein.png
 
 .. _`Linux (Wikipedia Article)`: https://de.wikipedia.org/wiki/Linux 
+
+.. _`Wikimedia: Triumph typewrtier text Linzensoep`: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif

tests/test_main.py

@@ -60,6 +60,7 @@ def check_ocrmypdf(input_basename, output_basename, *args, env=None):
     output_file = _outfile(output_basename)
 
     p, out, err = run_ocrmypdf(input_basename, output_basename, *args, env=env)
+    print(err)  # ensure py.test collects the output, use -s to view
     if p.returncode != 0:
         print('stdout\n======')
         print(out)
@@ -748,3 +749,9 @@ def test_ghostscript_pdfa_failure(spoof_no_tess_no_pdfa):
 def test_ghostscript_feature_elision(spoof_no_tess_pdfa_warning):
     check_ocrmypdf('ccitt.pdf', 'test_feature_elision.pdf',
                    env=spoof_no_tess_pdfa_warning)
+
+
+def test_very_high_dpi(spoof_tesseract_cache):
+    "Checks for a Decimal quantize error with high DPI, etc"
+    check_ocrmypdf('2400dpi.pdf', 'test_2400dpi.pdf',
+                   env=spoof_tesseract_cache)