v3.2.1

All tests pass when forced to rely on img2pdf, so seems okay

.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

@@ -1,6 +1,6 @@
 # OCRmyPDF
 #
-# VERSION               3.0.2
+# VERSION               3.2
 FROM      debian:stretch
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 

Dockerfile.polyglot

@@ -1,6 +1,6 @@
 # OCRmyPDF polyglot
 #
-# VERSION               3.0.2
+# VERSION               3.2
 FROM      jbarlow83/ocrmypdf:latest
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 

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 +6,36 @@ Please always read this file before installing the package
 Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
 
 
-v3.2-rc1:
+v3.2.1:
-=========
+=======
+
+Changes
+-------
+
+-  Fixed issue #47 "convert() got and unexpected keyword argument 'dpi'" by upgrading to img2pdf 0.2
+-  Tweaked the Dockerfiles
+
+
+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 +60,7 @@ 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/main.py

@@ -165,9 +165,6 @@ parser.add_argument(
     '--skip-big', type=float, metavar='MPixels',
     help="skip OCR on pages larger than the specified amount of megapixels, "
          "but include skipped pages in final output")
-# parser.add_argument(
-#     '--exact-image', action='store_true',
-#     help="Use original page from PDF without re-rendering")
 
 advanced = parser.add_argument_group(
     "Advanced",
@@ -592,9 +589,18 @@ def select_image_layer(
         re_symlink(page_pdf, output_file)
     else:
         pageinfo = get_pageinfo(image, pdfinfo, pdfinfo_lock)
-        dpi = round(max(pageinfo['xres'], pageinfo['yres'], options.oversample))
+        dpi = round(max(pageinfo['xres'], pageinfo['yres'],
-        with open(output_file, 'wb') as pdf:
+                        options.oversample))
-            img2pdf.convert([image], dpi=dpi, outputstream=pdf)
+        imgsize = ((img2pdf.ImgSize.dpi, dpi), (img2pdf.ImgSize.dpi, dpi))
+
+        layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
+
+        with open(image, 'rb') as imfile, \
+                open(output_file, 'wb') as pdf:
+            rawdata = imfile.read()
+            pdf.write(img2pdf.convert(
+                rawdata, producer="img2pdf", with_pdfrw=False,
+                layout_fun=layout_fun))
 
 
 @active_if(options.pdf_renderer == 'hocr')

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:

requirements.txt

@@ -1,5 +1,5 @@
-ruffus>=2.6.3
+ruffus==2.6.3
-Pillow>=2.4.0
+Pillow==3.1.1
-reportlab>=3.1.44
+reportlab==3.2.0
-PyPDF2>=1.25.1
+PyPDF2==1.25.1
-git+https://github.com/jbarlow83/img2pdf.git@e9bcce0afc3720752ca53a991db93f911a1df709#egg=img2pdf-0.1.5.dev
+img2pdf==0.2

setup.py

@@ -210,11 +210,11 @@ setup(
     ],
     use_scm_version={'version_scheme': 'post-release'},
     install_requires=[
-        'ruffus',
+        'ruffus>=2.6.3',
-        'Pillow',
+        'Pillow>=2.4.0',
-        'reportlab',
+        'reportlab>=3.1.44',
-        'PyPDF2',
+        'PyPDF2>=1.25.1',
-        'img2pdf'
+        'img2pdf>=0.2.0'
     ],
     tests_require=tests_require,
     entry_points={

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]