v4.3.5: Python 3.6 compatibility

Revert to exactly what the previous passing build specified.

.travis.yml

@@ -11,8 +11,9 @@ cache:
         - tests/cache
 
 python:
-    - 3.4
-    - 3.5
+    - "3.4"
+    - "3.5"
+    - "3.6-dev"  # 3.6 not available yet
 
 before_cache:
     - rm -f $HOME/.cache/pip/log/debug.log

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 +3,18 @@ RELEASE NOTES
 
 OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
 
+v4.3.5:
+=======
+
+-  Update documentation to confirm Python 3.6.0 compatibility. No code changes were needed, so many earlier versions are likely supported.
+
+
+v4.3.4:
+=======
+
+-  Fixed "decimal.InvalidOperation: quantize result has too many digits" for high DPI images
+
+
 v4.3.3:
 =======
 

dev_requirements.txt

@@ -1,4 +1,9 @@
-check-manifest>=0.33
-setuptools-scm>=1.11.1
-twine>=1.8.1
-coverage>=4.2
+check-manifest >= 0.34
+twine >= 1.8.1
+coverage >= 4.3.1
+pytest-xdist >= 1.15.0
+
+# Known good versions: 1.11.1
+# Known broken versions: 1.15.0
+setuptools-scm == 1.11.1
+setuptools-scm-git-archive == 1.0

docs/installation.rst

@@ -78,6 +78,8 @@ In this worked example, the current working directory contains an input file cal
 
    docker run --rm -v "$(pwd):/home/docker"   ocrmypdf --skip-text test.pdf output.pdf
 
+.. note:: The working directory should be a writable local volume or Docker may not have permission to access it.
+
 Note that ``ocrmypdf`` has its own separate ``-v VERBOSITYLEVEL`` argument to control debug verbosity. All Docker arguments should before the ``ocrmypdf`` image name and all arguments to ``ocrmypdf`` should be listed after.
 
 
@@ -105,6 +107,8 @@ Install or upgrade the required Homebrew packages, if any are missing:
    brew install libxml2 libffi leptonica
    brew install unpaper   # optional
    
+Python 3.4, 3.5 and 3.6 are supported.
+
 Install the required Tesseract OCR engine with the language packs you plan to use:
    
 .. code-block:: bash

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()
-        if stdout:
-            if 'error' in stdout:
-                log.error(stdout)  # Ghostscript puts errors in stdout
-            else:
-                log.debug(stdout)
-        if stderr:
-            log.error(stderr)
+        stdout, _ = p.communicate()
+        if 'error' in stdout:
+            log.error(stdout)  # Ghostscript puts errors in stdout
+        else:
+            log.debug(stdout)
 
         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()
-        if stdout:
-            if 'error' in stdout:
-                log.error(stdout)
-            elif 'overprint mode not set' in stdout:
-                # Unless someone is going to print PDF/A documents on a
-                # magical sRGB printer I can't see the removal of overprinting
-                # being a problem....
-                log.debug(
-                    "Ghostscript had to remove PDF 'overprinting' from the "
-                    "input file to complete PDF/A conversion. "
-                    )
-            else:
-                log.debug(stdout)
-        if stderr:
-            log.error(stderr)
+        stdout, _ = p.communicate()
+
+        if 'error' in stdout:
+            log.error(stdout)
+        elif 'overprint mode not set' in stdout:
+            # Unless someone is going to print PDF/A documents on a
+            # magical sRGB printer I can't see the removal of overprinting
+            # being a problem....
+            log.debug(
+                "Ghostscript had to remove PDF 'overprinting' from the "
+                "input file to complete PDF/A conversion. "
+                )
+        else:
+            log.debug(stdout)
 
         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)]
 
 

requirements.txt

@@ -2,8 +2,8 @@
 # setup.py lists a separate set of requirements that are looser to simplify
 # installation
 ruffus==2.6.3
-Pillow==3.3.0
-reportlab==3.2.0
+Pillow==4.0.0
+reportlab==3.3.0
 PyPDF2==1.26
 img2pdf==0.2.1
-cffi==1.5.2
+cffi==1.9.1

setup.py

@@ -191,11 +191,14 @@ 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=[
         "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.4",
+        "Programming Language :: Python :: 3.5",
+        "Programming Language :: Python :: 3.6",
         "Development Status :: 5 - Production/Stable",
         "Environment :: Console",
         "Intended Audience :: End Users/Desktop",

test_requirements.txt

@@ -1 +1 @@
-pytest>=2.7.2
+pytest >= 2.7.2

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
@@ -104,4 +107,6 @@ 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 
+.. _`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)