Merge branch 'develop'

Dockerfile

@@ -1,6 +1,6 @@
 # OCRmyPDF
 #
-# VERSION               3.0.2
+# VERSION               3.2
 FROM      debian:stretch
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 
@@ -47,13 +47,11 @@ RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/*
 RUN pyvenv /appenv \
   && pyvenv --system-site-packages /appenv
 
-COPY . /application/
-
 # Install application and dependencies
 # In this arrangement Pillow and reportlab will be provided by the system
 RUN . /appenv/bin/activate; \
   pip install --upgrade pip \
-  && pip install --no-cache-dir /application \
+  && pip install ocrmypdf \
   && pip install --no-cache-dir -r /application/test_requirements.txt
 
 USER docker

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>
 

RELEASE_NOTES.rst

@@ -6,8 +6,18 @@ Please always read this file before installing the package
 Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
 
 
+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
 ------------

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))
-        with open(output_file, 'wb') as pdf:
-            img2pdf.convert([image], dpi=dpi, outputstream=pdf)
+        dpi = round(max(pageinfo['xres'], pageinfo['yres'],
+                        options.oversample))
+        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')

requirements.txt

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

setup.py

@@ -212,11 +212,11 @@ setup(
     ],
     use_scm_version={'version_scheme': 'post-release'},
     install_requires=[
-        'ruffus',
-        'Pillow',
-        'reportlab',
-        'PyPDF2',
-        'img2pdf'
+        'ruffus>=2.6.3',
+        'Pillow>=2.4.0',
+        'reportlab>=3.1.44',
+        'PyPDF2>=1.25.1',
+        'img2pdf>=0.2.0'
     ],
     tests_require=tests_require,
     entry_points={