v9.1.1 release notes

Smaller download, needed for manylinux2010.

.docker/Dockerfile

@@ -10,16 +10,21 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   build-essential autoconf automake libtool \
   libleptonica-dev \
   zlib1g-dev \
-  python3-setuptools \
+  python3 \
-  python3-pip \
+  python3-distutils \
-  wget \
+  ca-certificates \
+  curl \
   git
 
+# Get the latest pip (Ubuntu version doesn't support manylinux2010)
+RUN \
+  curl https://bootstrap.pypa.io/get-pip.py | python3
+
 # Compile and install jbig2
 # Needs libleptonica-dev, zlib1g-dev
 RUN \
   mkdir jbig2 \
-  && wget -q https://github.com/agl/jbig2enc/archive/0.29.tar.gz -O - | \
+  && curl -L https://github.com/agl/jbig2enc/archive/0.29.tar.gz | \
   tar xz -C jbig2 --strip-components=1 \
   && cd jbig2 \
   && ./autogen.sh && ./configure && make && make install \

docs/docker.rst

@@ -108,9 +108,9 @@ on the public one:
    FROM jbarlow83/ocrmypdf
 
    # Add French
-   RUN apk add tesseract-ocr-data-fra
+   RUN apt install tesseract-ocr-fra
 
-You can also copy training data to ``/usr/share/tessdata``.
+You can also copy training data to ``/usr/share/tesseract-ocr/<tesseract version>/tessdata``.
 
 Executing the test suite
 ========================

docs/installation.rst

@@ -134,8 +134,7 @@ first install the system version to get most of the dependencies:
 
     sudo apt-get update
     sudo apt-get install \
-        ocrmypdf \
+        ocrmypdf
-        python3-pip
 
 There are a few system dependency changes since ocrmypdf 6.1.2. Let's
 get these, too.
@@ -146,13 +145,18 @@ get these, too.
         libxml2 \
         pngquant
 
+We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
+
+.. code-block:: bash
+
+    wget https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py
+
 Then install the most recent ocrmypdf for the local user and set the
 user's ``PATH`` to check for the user's Python packages.
 
 .. code-block:: bash
 
     export PATH=$HOME/.local/bin:$PATH
-    python3 -m pip install --user --upgrade pip
     python3 -m pip install --user ocrmypdf
 
 To add JBIG2 encoding, see :ref:`jbig2`.

docs/release_notes.rst

@@ -13,6 +13,13 @@ Note that it is licensed under GPLv3, so scripts that
 ``import ocrmypdf`` and are released publicly should probably also be
 licensed under GPLv3.
 
+v9.1.1
+======
+
+-  Expand the range of pdfminer.six versions that are supported.
+-  Fixed Docker build when using pikepdf 1.7.0.
+-  Fixed documentation to recommend using pip from get-pip.py.
+
 v9.1.0
 ======
 

requirements/dev.txt

@@ -1,4 +1,2 @@
-check-manifest >= 0.35
 twine >= 1.8.1
 coverage >= 4.5
-GitPython == 2.1.3

requirements/main.txt

@@ -3,7 +3,7 @@
 # installation
 cffi == 1.13.2
 img2pdf == 0.3.3
-pdfminer.six == 20191020
+pdfminer.six == 20191110
 pikepdf == 1.7.0
 Pillow >= 6.2.0
 reportlab == 3.5.32

setup.py

@@ -96,7 +96,7 @@ setup(
         'chardet >= 3.0.4, < 4',  # unlisted requirement of pdfminer.six 20181108
         'cffi >= 1.9.1',  # must be a setup and install requirement
         'img2pdf >= 0.3.0, < 0.4',  # pure Python, so track HEAD closely
-        'pdfminer.six >= 20181108, <= 20191020',
+        'pdfminer.six >= 20181108, <= 20191110',
         'pikepdf >= 1.7.0, < 2',
         'Pillow >= 6.2.0',
         'reportlab >= 3.3.0',  # oldest released version with sane image handling