Try tweaking Dockerfile for automated build again

Now checks input image to ensure the implied page size of its .hocr file
matches the rest of the PDF.

.gitignore

@@ -1,26 +1,31 @@
-tmp/
+# Development environment
-log/
 *.pyc
-tests/output/
-.ruffus_history.sqlite
 *.sublime-*
-/*.pdf
-build/
-dist/
-*.egg-info/
-venv/
 venv-3.4/
 venv-3.5/
-*/test/output
+venv/
-bin/
-include/
-lib/
-pip-selfcheck.json
 pyvenv.cfg
-htmlcov/
+
-.coverage
+# Package building
+*.egg-info/
 .cache/
+.eggs/
+build/
+dist/
+
+# Automatically generated files
+ocrmypdf/lib/_*.py
+ocrmypdf/version.py
+
+# Code coverage
+.coverage
+htmlcov/
+
+# Testing
+log/
+/*.pdf
 .ipynb_checkpoints/
 tests/cache/
+tests/output/
 tests/resources/private
-ocrmypdf/version.py
+tmp/

Dockerfile

@@ -10,20 +10,26 @@ RUN useradd docker \
   && chown docker:docker /home/docker
 
 # Update system and install our dependencies
+# If this command takes too Docker hub's automated build will timeout,
+# so try it in portions
 RUN apt-get update && apt-get install -y --no-install-recommends \
   locales \
-  ghostscript \
-  tesseract-ocr \
-  tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra \
-  qpdf \
-  poppler-utils \
   python3 \
   python3-pip \
   python3-venv \
   python3-reportlab \
   python3-pil \
-  python3-wheel \
+  python3-wheel
-  unpaper
+
+RUN apt-get install -y --no-install-recommends \
+  unpaper \
+  ghostscript \
+  qpdf \
+  poppler-utils
+
+RUN apt-get install -y --no-install-recommends \
+  tesseract-ocr \
+  tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra
 
 # Enforce UTF-8
 # Borrowed from https://index.docker.io/u/crosbymichael/python/ 

Dockerfile.polyglot

@@ -5,9 +5,12 @@ FROM      jbarlow83/ocrmypdf:latest
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 
 # Update system and install our dependencies
+USER root
 RUN apt-get update && apt-get install -y --no-install-recommends \
   tesseract-ocr-all 
 
+USER docker
+
 # Must use array form of ENTRYPOINT
 # Non-array form does not append other arguments, because that is "intuitive"
 ENTRYPOINT ["/application/docker-wrapper.sh"]

README.rst

@@ -11,12 +11,7 @@ Main features
    `PDF/A <https://en.wikipedia.org/?title=PDF/A>`__ file from a regular PDF
 -  Places OCR text accurately below the image to ease copy / paste
 -  Keeps the exact resolution of the original embedded images
-
+-  When possible, inserts OCR information as a "lossless" operation without rendering vector information
-   -  or if requested oversamples the images before OCRing so as to get
-      better results
-
--  When possible, inserts OCR information as a "lossless" operation without transcoding
-   images or rendering vector information
 -  Keeps file size about the same
 -  If requested deskews and/or cleans the image before performing OCR
 -  Validates input and output files

RELEASE_NOTES.rst

@@ -6,16 +6,26 @@ Please always read this file before installing the package
 Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
 
 
-v3.2-rc1:
+v3.2:
 =========
 
 New features
 ------------
 
--  Lossless reconstruction: when possible, OCRmyPDF will inject text layers without transcoding
+-  Lossless reconstruction: when possible, OCRmyPDF will inject text layers without 
-   images or otherwise manipulating the PDF.
+   otherwise manipulating the content and layout of a PDF page. For example, a PDF containing a mix
--  New argument --tesseract-pagesegmode allows you to pass page segmentation arguments to Tesseract OCR.
+   of vector and raster content would see the vector content preserved. Images may still be transcoded
+   during PDF/A conversion.  (``--deskew`` and ``--clean-final`` disable this mode, necessarily.)
+-  New argument ``--tesseract-pagesegmode`` allows you to pass page segmentation arguments to Tesseract OCR.
    This helps for two column text and other situations that confuse Tesseract.
+-  Added a new "polyglot" version of the Docker image, that generates Tesseract with all languages packs installed,
+   for the polyglots among us. It is much larger.
+
+Changes
+-------
+
+-  JPEG transcoding quality is now 95 instead of the default 75. Bigger file sizes for less degradation.
+
 
 
 v3.1.1:
@@ -40,7 +50,7 @@ Changes
 -  Fixed an issue where OCRmyPDF failed to text that certain pages contained previously OCR'ed text, 
    such as OCR text produced by Tesseract 3.04
 -  Inserts /Creator tag into PDFs so that errors can be traced back to this project
--  Added new option --pdf-renderer=auto, to let OCRmyPDF pick the best PDF renderer. 
+-  Added new option ``--pdf-renderer=auto``, to let OCRmyPDF pick the best PDF renderer. 
    Currently it always chooses the 'hocrtransform' renderer but that behavior may change.
 -  Set up Travis CI automatic integration testing
 

ocrmypdf/ghostscript.py

@@ -45,6 +45,7 @@ def generate_pdfa(pdf_pages, output_file, threads=1):
             "-sDEVICE=pdfwrite",
             "-sColorConversionStrategy=/RGB",
             "-sProcessColorModel=DeviceRGB",
+            "-dJPEGQ=95",
             "-dPDFA=2",
             "-sPDFACompatibilityPolicy=2",
             "-sOutputICCProfile=srgb.icc",

ocrmypdf/hocrtransform.py

@@ -1,4 +1,4 @@
-#!/usr/local/bin/python3
+#!/usr/bin/env python3
 ##############################################################################
 # Copyright (c) 2013-14: fritz-hh from Github
 #   (https://github.com/fritz-hh)

ocrmypdf/tesseract.py

@@ -94,7 +94,6 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
         badxml,
         'hocr'
     ] + tessconfig)
-    print(args_tesseract)
     p = Popen(args_tesseract, close_fds=True, stdout=PIPE, stderr=PIPE,
               universal_newlines=True)
     try:

tests/spoof/tesseract_noop.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 import sys
 import img2pdf
+from PIL import Image
 
 
 VERSION_STRING = '''tesseract 3.04.00
@@ -40,9 +41,12 @@ def main():
         print('List of available languages (1):\neng', file=sys.stderr)
         sys.exit(0)
     elif sys.argv[-1] == 'hocr':
+        inputf = sys.argv[-3]
         output = sys.argv[-2]
-        with open(output + '.hocr', 'w', encoding='utf-8') as f:
+        with Image.open(inputf) as im, \
-            f.write(HOCR_TEMPLATE.format('1000', '1000'))
+                open(output + '.hocr', 'w', encoding='utf-8') as f:
+            w, h = im.size
+            f.write(HOCR_TEMPLATE.format(str(w), str(h)))
     elif sys.argv[-1] == 'pdf':
         inputf = sys.argv[-3]
         output = sys.argv[-2]