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 \

.travis.yml

@@ -86,30 +86,30 @@ matrix:
             - tesseract-ocr-eng
             - tesseract-ocr-fra
             - unpaper
-    # - os: linux
+    - os: linux
-    #   dist: bionic
+      dist: bionic
-    #   sudo: required
+      sudo: required
-    #   language: python
+      language: python
-    #   python: "3.8"
+      python: "3.8"
-    #   env:
+      env:
-    #     - DIST=bionic
+        - DIST=bionic
-    #   addons:
+      addons:
-    #     apt:
+        apt:
-    #       update: true
+          update: true
-    #       sources:
+          sources:
-    #         - sourceline: "ppa:alex-p/tesseract-ocr"
+            - sourceline: "ppa:alex-p/tesseract-ocr"
-    #       packages:
+          packages:
-    #         - ghostscript
+            - ghostscript
-    #         - libexempi3
+            - libexempi3
-    #         - libffi-dev
+            - libffi-dev
-    #         - pngquant
+            - pngquant
-    #         - poppler-utils
+            - poppler-utils
-    #         - qpdf
+            - qpdf
-    #         - tesseract-ocr
+            - tesseract-ocr
-    #         - tesseract-ocr-deu
+            - tesseract-ocr-deu
-    #         - tesseract-ocr-eng
+            - tesseract-ocr-eng
-    #         - tesseract-ocr-fra
+            - tesseract-ocr-fra
-    #         - unpaper
+            - unpaper
     - os: osx
       language: generic
       addons:

docs/api.rst

@@ -71,7 +71,8 @@ Progress monitoring
 OCRmyPDF uses the ``tqdm`` package to implement its progress bars.
 :func:`ocrmypdf.configure_logging` will set up logging output to
 ``sys.stderr`` in a way that is compatible with the display of the
-progress bar.
+progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable
+the progress bar.
 
 Exceptions
 ----------

docs/batch.rst

@@ -244,6 +244,9 @@ Caveats
 Alternatives
 ------------
 
+-  `systemd user services <https://wiki.archlinux.org/index.php/Systemd/User>`__
+   can be configured to automatically perform OCR on a collection of files.
+
 -  `Watchman <https://facebook.github.io/watchman/>`__ is a more
    powerful alternative to ``watchmedo``.
 

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/index.rst

@@ -12,6 +12,7 @@ PDF is the best format for storing and exchanging scanned documents.  Unfortunat
    introduction
    release_notes
    installation
+   optimizer
    languages
    jbig2
 

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 +145,19 @@ 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
-    pip3 install --user ocrmypdf
+    python3 -m pip install --user ocrmypdf
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 

docs/optimizer.rst

@@ -0,0 +1,71 @@
+================
+PDF optimization
+================
+
+OCRmyPDF includes an image-oriented PDF optimizer. By default, the optimizer
+runs with safe settings with the goal of improving compression at no loss of
+quality. At higher optimization levels, lossy optimizations may be applied and
+tuned. Optimization occurs after OCR, and only if OCR succeeded.  It does not
+perform other possible optimizations such as deduplicating resources,
+consolidating fonts, simplifying vector drawings, or anything of that nature.
+
+Optimization ranges from ``-O0`` through ``-O3``, where ``0`` disables
+optimization and ``3`` implements all options. ``1``, the default, performs only
+safe and lossless optimizations. (This is similar to GCC's optimization
+parameter.) The exact type of optimizations performed will vary over time.
+
+Optimizations that always occurs
+================================
+
+OCRmyPDF will automatically replace obsolete or inferior compression schemes
+such as RLE or LZW with superior schemes such as Deflate and converting
+monochrome images to CCITT G4. Since this is harmless it always occurs and there
+is no way to disable it. Other non-image compressed objects are compressed as
+well.
+
+Fast web view
+=============
+
+OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's
+parlance, or equivalently, linearizes PDFs so that the resources they reference
+are presented in the order a viewer needs them for sequential display. This
+reduces the latency of viewing a PDF both online and from local storage. This
+actually slightly increases the file size.
+
+To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
+or the shorthand ``-O0``.
+
+Lossless optimizations
+======================
+
+At optimization level ``-O1`` (the default), OCRmyPDF will also attempt lossless
+image optimization.
+
+If a JBIG2 encoder is available, then monochrome images will be converted to
+JBIG2, with the potential for huge savings on large black and white images,
+since JBIG2 is far more efficient than any other monochrome (bi-level)
+compression. (All known US patents related to JBIG2 have probably expired, but
+it remains the responsibility of the user to supply a JBIG2 encoder such as
+`jbig2enc <https://github.com/agl/jbig2enc>`__. OCRmyPDF does not implement
+JBIG2 encoding on its own.)
+
+OCRmyPDF currently does not attempt to recompress losslessly compressed objects
+more aggressively.
+
+Lossy optimizations
+===================
+
+At optimization level ``-O2`` and ``-O3``, OCRmyPDF will some attempt lossy
+image optimization.
+
+If ``pngquant`` is installed, OCRmyPDF will use it to perform quantize paletted
+images to reduce their size.
+
+The quality of JPEGs may be lowered, on the assumption that a lower quality
+image may be suitable for storage after OCR.
+
+It is not possible to optimize all image types. Uncommon image types may be
+skipped by the optimizer.
+
+OCRmyPDF provides :ref:`lossy mode JBIG2 <jbig2-lossy>` as an advanced feature
+that additional requires the argument ``--jbig2-lossy``.

docs/release_notes.rst

@@ -13,6 +13,21 @@ 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
+======
+
+-  Improved diagnostics when file size increases at output. Now warns if JBIG2
+   or pngquant were not available.
+-  pikepdf 1.7.0 is now required, to pick up changes that remove the need for
+   a source install on Linux systems running Python 3.8.
+
 v9.0.5
 ======
 

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

@@ -3,8 +3,8 @@
 # installation
 cffi == 1.13.2
 img2pdf == 0.3.3
-pdfminer.six == 20191020
+pdfminer.six == 20191110
-pikepdf == 1.6.5
+pikepdf == 1.7.0
 Pillow >= 6.2.0
 reportlab == 3.5.32
 tqdm == 4.37.0

setup.py

@@ -96,8 +96,8 @@ 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 >= 1.6.5, < 2',
+        'pikepdf >= 1.7.0, < 2',
         'Pillow >= 6.2.0',
         'reportlab >= 3.3.0',  # oldest released version with sane image handling
         'tqdm >= 4',

src/ocrmypdf/_validation.py

@@ -418,6 +418,20 @@ def report_output_file_size(options, input_file, output_file):
                 f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
             )
 
+    if options.optimize == 0:
+        reasons.append("Optimization was disabled.")
+    else:
+        image_optimizers = {
+            'jbig2': jbig2enc.available(),
+            'pngquant': pngquant.available(),
+        }
+        for name, available in image_optimizers.items():
+            if not available:
+                reasons.append(
+                    f"The optional dependency '{name}' was not found, so some image "
+                    f"optimizations could not be attempted."
+                )
+
     if reasons:
         explanation = "Possible reasons for this include:\n" + '\n'.join(reasons) + "\n"
     else:

src/ocrmypdf/exec/ghostscript.py

@@ -15,8 +15,11 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+"""Interface to Ghostscript executable"""
+
 import logging
 import re
+import warnings
 from functools import lru_cache
 from os import fspath
 from shutil import copy
@@ -193,7 +196,7 @@ def generate_pdfa(
     output_file,
     compression,
     log,
-    threads=1,
+    threads=None,  # deprecated parameter
     pdf_version='1.5',
     pdfa_part='2',
 ):
@@ -216,6 +219,10 @@ def generate_pdfa(
     """
     if not log:
         log = gslog
+    if threads is not None:
+        warnings.warn(
+            "use of deprecated parameter 'threads'", category=DeprecationWarning
+        )
 
     compression_args = []
     if compression == 'jpeg':

src/ocrmypdf/exec/jbig2enc.py

@@ -15,6 +15,8 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+"""Interface to jbig2 executable"""
+
 from functools import lru_cache
 from subprocess import PIPE, run
 

src/ocrmypdf/exec/pngquant.py

@@ -15,6 +15,8 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+"""Interface to pngquant executable"""
+
 from functools import lru_cache
 from subprocess import run
 from tempfile import NamedTemporaryFile

src/ocrmypdf/exec/qpdf.py

@@ -15,6 +15,8 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+"""Interface to qpdf executable"""
+
 from functools import lru_cache
 from os import fspath
 from subprocess import PIPE, STDOUT, CalledProcessError, run

src/ocrmypdf/exec/tesseract.py

@@ -15,10 +15,13 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+"""Interface to Tesseract executable"""
+
 import os
 import shutil
 from collections import namedtuple
 from contextlib import suppress
+import logging
 from os import fspath
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired, run
 
@@ -50,6 +53,11 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
 """
 
 
+class TesseractLoggerAdapter(logging.LoggerAdapter):
+    def process(self, msg, kwargs):
+        return '[tesseract] %s' % (msg), kwargs
+
+
 def version(tesseract_env=None):
     return get_version('tesseract', regex=r'tesseract\s(.+)', env=tesseract_env)
 
@@ -177,15 +185,16 @@ def get_orientation(input_file, engine_mode, timeout: float, log, tesseract_env=
         return oc
 
 
-def tesseract_log_output(log, stdout, input_file):
+def tesseract_log_output(mainlog, stdout, input_file):
-    prefix = "[tesseract] "
+    log = TesseractLoggerAdapter(
+        mainlog, extra=mainlog.extra if hasattr(mainlog, 'extra') else None
+    )
 
     try:
         text = stdout.decode()
     except UnicodeDecodeError:
         log.error(
-            prefix
+            "command line output was not utf-8. "
-            + "command line output was not utf-8. "
             + "This usually means Tesseract's language packs do not match "
             "the installed version of Tesseract."
         )
@@ -198,25 +207,25 @@ def tesseract_log_output(log, stdout, input_file):
         elif line.startswith("Warning in pixReadMem"):
             continue
         elif 'diacritics' in line:
-            log.warning(prefix + "lots of diacritics - possibly poor OCR")
+            log.warning("lots of diacritics - possibly poor OCR")
         elif line.startswith('OSD: Weak margin'):
-            log.warning(prefix + "unsure about page orientation")
+            log.warning("unsure about page orientation")
         elif 'Error in pixScanForForeground' in line:
             pass  # Appears to be spurious/problem with nonwhite borders
         elif 'Error in boxClipToRectangle' in line:
             pass  # Always appears with pixScanForForeground message
         elif 'parameter not found: ' in line.lower():
-            log.error(prefix + line.strip())
+            log.error(line.strip())
             problem = line.split('found: ')[1]
             raise TesseractConfigError(problem)
         elif 'error' in line.lower() or 'exception' in line.lower():
-            log.error(prefix + line.strip())
+            log.error(line.strip())
         elif 'warning' in line.lower():
-            log.warning(prefix + line.strip())
+            log.warning(line.strip())
         elif 'read_params_file' in line.lower():
-            log.error(prefix + line.strip())
+            log.error(line.strip())
         else:
-            log.info(prefix + line.strip())
+            log.info(line.strip())
 
 
 def page_timedout(log, input_file, timeout):

src/ocrmypdf/exec/unpaper.py

@@ -18,10 +18,11 @@
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
 
+"""Interface to unpaper executable"""
+
 import os
 import shlex
 import subprocess
-import sys
 from functools import lru_cache
 from subprocess import PIPE, STDOUT, CalledProcessError
 from tempfile import TemporaryDirectory

src/ocrmypdf/pdfa.py

@@ -32,8 +32,6 @@ Ghostscript's handling of pdfmark.
 """
 
 import base64
-import os
-from binascii import hexlify
 from pathlib import Path
 from string import Template
 

src/ocrmypdf/pdfinfo/layout.py

@@ -212,6 +212,7 @@ class TextPositionTracker(PDFLayoutAnalyzer):
         super().__init__(rsrcmgr, pageno, laparams)
         self.textstate = None
         self.result = None
+        self.cur_item = None  # not defined in pdfminer code as it should be
 
     def begin_page(self, page, ctm):
         super().begin_page(page, ctm)

tests/test_validation.py

@@ -15,7 +15,6 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-import locale
 import logging
 import os
 from unittest.mock import patch
@@ -117,11 +116,28 @@ def test_report_file_size(tmp_path, caplog):
     opts = make_opts()
     vd.report_output_file_size(opts, in_, out)
     assert caplog.text == ''
+    caplog.clear()
 
     os.truncate(in_, 25001)
     os.truncate(out, 50000)
+    with patch('ocrmypdf._validation.jbig2enc.available', return_value=True), patch(
+        'ocrmypdf._validation.pngquant.available', return_value=True
+    ):
+        vd.report_output_file_size(opts, in_, out)
+        assert 'No reason' in caplog.text
+    caplog.clear()
+
+    with patch('ocrmypdf._validation.jbig2enc.available', return_value=False), patch(
+        'ocrmypdf._validation.pngquant.available', return_value=True
+    ):
+        vd.report_output_file_size(opts, in_, out)
+        assert 'optional dependency' in caplog.text
+    caplog.clear()
+
+    opts = make_opts(in_, out, optimize=0)
     vd.report_output_file_size(opts, in_, out)
-    assert 'No reason' in caplog.text
+    assert 'disabled' in caplog.text
+    caplog.clear()
 
 
 def test_false_action_store_true():