v4.0: release notes

Since the corrected font is provided in the Docker image, there's no
reason to show the warning.

.dockerignore

@@ -0,0 +1,31 @@
+*.ipynb
+*.pdf
+*.pyc
+*.rst
+*.sublime*
+*/*.pyc
+*/*/*.pyc
+*/*/*/*.pyc
+*/*/*/*/*.pyc
+*/*/*/*/*/*.pyc
+*/*/*/*/*/*/*.pyc
+*/*/*/*/*/*/*/*.pyc
+.cache/
+.git/
+.ipynb_checkpoints/
+.ruffus_history.sqlite
+bin/
+build/
+dist/
+htmlcov/
+include/
+lib/
+MANIFEST.in
+ocrmypdf.egg-info/
+staging/
+tests/cache/
+tests/output/
+tests/resources/private/
+tmp/
+venv-3.4/
+venv-3.5/

.gitignore

@@ -1,3 +1,29 @@
-tmp/
+# Development environment
+*.pyc
+*.sublime-*
+venv-*/
+pyvenv.cfg
+
+# Package building
+*.egg-info/
+.cache/
+.eggs/
+build/
+dist/
+
+# Automatically generated files
+ocrmypdf/lib/_*.py
+ocrmypdf/version.py
+
+# Code coverage
+.coverage
+htmlcov/
+
+# Testing
 log/
-*.pyc
+/*.pdf
+.ipynb_checkpoints/
+tests/cache/
+tests/output/
+tests/resources/private
+tmp/

.travis.yml

@@ -0,0 +1,46 @@
+language: python
+
+cache: pip
+
+cache:
+    directories:
+        - $HOME/.ccache
+        - tarballs
+        - tests/cache
+
+python:
+    - 3.4
+
+before_cache:
+    - rm -f $HOME/.cache/pip/log/debug.log
+
+before_install:
+    # Ubuntu packages
+    - sudo add-apt-repository ppa:evl.ms/precise -y  # for Ghostscript 9.15
+    - sudo add-apt-repository ppa:lyrasis/precise-backports -y  # for Tesseract 3.03
+    - sudo add-apt-repository ppa:b-eltzner/qpdfview-exp -y  # for QPDF 5
+    - sudo add-apt-repository ppa:itachi-san/ffmpeg -y  # for libav 11.2 (for unpaper)
+    - sudo apt-get update -qq  # must go after all add-apt-repo
+    - sudo apt-get install -y ghostscript tesseract-ocr tesseract-ocr-deu tesseract-ocr-eng tesseract-ocr-fra qpdf poppler-utils gcc libavformat-dev libavcodec-dev libavutil-dev automake make pkg-config xsltproc libffi-dev
+
+    # pip
+    - pip install --upgrade pip
+
+    # Download, make and install unpaper (using ccache)
+    - mkdir -p tarballs
+    - "[ -f tarballs/unpaper-6.1.tar.xz ] || wget -q https://www.flameeyes.eu/files/unpaper-6.1.tar.xz -O tarballs/unpaper-6.1.tar.xz"
+    - tar -xvf tarballs/unpaper-6.1.tar.xz
+    - export PATH="/usr/lib/ccache:$PATH"
+    - pushd unpaper-6.1 && ./configure --prefix=/usr && make -j && sudo make install && popd
+
+install:
+    - pip install -r requirements.txt
+    - pip install -r test_requirements.txt
+
+script:
+    - python setup.py clean
+    - python setup.py install
+    - python setup.py test
+
+os:
+    - linux

Dockerfile

@@ -0,0 +1,85 @@
+# OCRmyPDF
+#
+# VERSION               3.2
+FROM      debian:stretch
+MAINTAINER James R. Barlow <jim@purplerock.ca>
+
+# Add unprivileged user
+RUN useradd docker \
+  && mkdir /home/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 \
+  python3 \
+  python3-pip \
+  python3-venv \
+  python3-reportlab \
+  python3-pil \
+  python3-wheel
+
+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
+
+RUN apt-get install -qy --no-install-recommends \
+  libffi-dev \
+  libpython3-dev \
+  gcc
+
+# Enforce UTF-8
+# Borrowed from https://index.docker.io/u/crosbymichael/python/ 
+RUN dpkg-reconfigure locales && \
+  locale-gen C.UTF-8 && \
+  /usr/sbin/update-locale LANG=C.UTF-8
+ENV LC_ALL C.UTF-8
+
+
+# Set up a Python virtualenv and take all of the system packages, so we can
+# rely on the platform packages rather than importing GCC and compiling them
+RUN pyvenv /appenv \
+  && pyvenv --system-site-packages /appenv
+
+COPY . /application/
+
+# Replace stock Tesseract 3.04.00 font with improved sharp2.ttf that resolves
+# issues in many PDF viewers.
+# Discussion is in https://github.com/tesseract-ocr/tesseract/issues/182
+COPY ./share/sharp2.ttf /usr/share/tesseract-ocr/tessdata/pdf.ttf
+RUN chmod 644 /usr/share/tesseract-ocr/tessdata/pdf.ttf
+
+# Set this here to force a docker version, allowing non-tagged versions to
+# be built
+# ENV SETUPTOOLS_SCM_PRETEND_VERSION=v3.3.0
+
+# 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 /application \
+  && pip install --no-cache-dir -r /application/test_requirements.txt
+
+# Remove the junk
+RUN apt-get remove -qy gcc
+RUN apt-get autoremove -y && apt-get clean -y
+RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/*
+
+USER docker
+WORKDIR /home/docker
+
+ENV OCRMYPDF_TEST_OUTPUT=/tmp/test-output
+ENV OCRMYPDF_IN_DOCKER=1
+ENV OCRMYPDF_SHARP_TTF=1
+
+# Must use array form of ENTRYPOINT
+# Non-array form does not append other arguments, because that is "intuitive"
+ENTRYPOINT ["/application/docker-wrapper.sh"]

Dockerfile.polyglot

@@ -0,0 +1,16 @@
+# OCRmyPDF polyglot
+#
+# VERSION               3.2
+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"]

LICENSE.md

@@ -1,19 +0,0 @@
-Copyright (c) 2013 fritz-hh from Github
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.

LICENSE.rst

@@ -0,0 +1,20 @@
+Copyright (c) 2013-2015, The OCRmyPDF Authors
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

MANIFEST.in

@@ -0,0 +1,4 @@
+recursive-exclude tests/output *
+include requirements.txt
+include test_requirements.txt
+include share/*

OCRmyPDF.sh

@@ -3,299 +3,4 @@
 # Copyright (c) 2013-14: fritz-hh from Github (https://github.com/fritz-hh)
 ##############################################################################
 
-# Determine real path of this script, following symlinks if present
-! command -v python2 > /dev/null && echo "Please install python v2.x. Exiting..." && exit 1
-BASEPATH="$(dirname $(python2 -c "import os; print os.path.realpath(\"$0\")"))"
-
-# Import required scripts
-. "$BASEPATH/src/config.sh"
-
-# Set variables corresponding to the input parameters
-ARGUMENTS="$@"
-
-START=`date +%s`
-
-usage() {
-	cat << EOF
---------------------------------------------------------------------------------------
-Script aimed at generating a searchable PDF file from a PDF file containing only images.
-(The script performs optical character recognition of each respective page using the
-tesseract engine)
-
-Copyright: fritz-hh  from Github (https://github.com/fritz-hh)
-Version: $VERSION
-
-Usage: OCRmyPDF.sh  [-h] [-v] [-g] [-k] [-d] [-c] [-i] [-o dpi] [-f] [-l language] [-C filename] inputfile outputfile
-
--h : Display this help message
--v : Increase the verbosity (this option can be used more than once) (e.g. -vvv)
--k : Do not delete the temporary files
--g : Activate debug mode:
-     - Generates a PDF file containing each page twice (once with the image, once without the image
-       but with the OCRed text as well as the detected bounding boxes)
-     - Set the verbosity to the highest possible
-     - Do not delete the temporary files
--d : Deskew each page before performing OCR
--c : Clean each page before performing OCR
--i : Incorporate the cleaned image in the final PDF file (by default the original image	
-     image, or the deskewed image if the -d option is set)
--o : If the resolution of an image is lower than dpi value provided as argument, provide the OCR engine with 
-     an oversampled image having the latter dpi value. This can improve the OCR results but can lead to a larger output PDF file.
-     (default: no oversampling performed)
--f : Force to OCR the whole document, even if some page already contain font data 
-     (which should not be the case for PDF files built from scanned images) 
--l : Set the language of the PDF file in order to improve OCR results (default "eng")
-     Any language supported by tesseract is supported (Tesseract uses 3-character ISO 639-2 language codes)
-     Multiple languages may be specified, separated by '+' characters.
--C : Pass an additional configuration file to the tesseract OCR engine.
-     (this option can be used more than once)
-     Note 1: The configuration file must be available in the "tessdata/configs" folder of your tesseract installation
-inputfile  : PDF file to be OCRed
-outputfile : The PDF/A file that will be generated 
---------------------------------------------------------------------------------------
-EOF
-}
-
-
-#################################################
-# Get an absolute path from a relative path to a file
-#
-# Param1 : Relative path
-# Returns: 1 if the folder in which the file is located does not exist
-#          0 otherwise
-################################################# 
-absolutePath() {
-	local wdsave absolutepath 
-	wdsave="$(pwd)"
-	! cd "$(dirname "$1")" 1> /dev/null 2> /dev/null && return 1
-	absolutepath="$(pwd)/$(basename "$1")"
-	cd "$wdsave"
-	echo "$absolutepath"
-	return 0
-}
-
-
-# Initialization the configuration parameters with default values
-VERBOSITY="$LOG_ERR"		# default verbosity level
-LAN="eng"			# default language of the PDF file (required to get good OCR results)
-KEEP_TMP="0"			# 0=no, 1=yes (keep the temporary files)
-PREPROCESS_DESKEW="0"		# 0=no, 1=yes (deskew image)
-PREPROCESS_CLEAN="0"		# 0=no, 1=yes (clean image to improve OCR)
-PREPROCESS_CLEANTOPDF="0"	# 0=no, 1=yes (put cleaned image in final PDF)
-OVERSAMPLING_DPI="0"		# 0=do not perform oversampling (dpi value under which oversampling should be performed)
-PDF_NOIMG="0"			# 0=no, 1=yes (generates each PDF page twice, with and without image)
-FORCE_OCR="0"			# 0=do not force, 1=force (force to OCR the whole document, even if some page already contain font data)
-TESS_CFG_FILES=""		# list of additional configuration files to be used by tesseract
-
-# Parse optional command line arguments
-while getopts ":hvgkdcio:fl:C:" opt; do
-	case $opt in
-		h) usage ; exit 0 ;;
-		v) VERBOSITY=$(($VERBOSITY+1)) ;;
-		k) KEEP_TMP="1" ;;
-		g) PDF_NOIMG="1"; VERBOSITY="$LOG_DEBUG"; KEEP_TMP="1" ;;
-		d) PREPROCESS_DESKEW="1" ;;
-		c) PREPROCESS_CLEAN="1" ;;
-		i) PREPROCESS_CLEANTOPDF="1" ;;
-		o) OVERSAMPLING_DPI="$OPTARG" ;;
-		f) FORCE_OCR="1" ;;
-		l) LAN="$OPTARG" ;;
-		C) TESS_CFG_FILES="$OPTARG $TESS_CFG_FILES" ;;
-		\?)
-			echo "Invalid option: -$OPTARG"
-			usage
-			exit $EXIT_BAD_ARGS ;;
-		:)
-			echo "Option -$OPTARG requires an argument"
-			usage
-			exit $EXIT_BAD_ARGS ;;
-	esac
-done
-
-# Remove the optional arguments parsed above.
-shift $((OPTIND-1))
-
-# Check if the number of mandatory parameters provided is as expected
-if [ "$#" -ne "2" ]; then
-	echo "Exactly two mandatory argument shall be provided ($# arguments provided)"
-	usage
-	exit $EXIT_BAD_ARGS
-fi
-
-[ ! -f "$1" ] \
-	&& echo "The input file does not exist. Exiting..." && exit $EXIT_BAD_ARGS
-FILE_INPUT_PDF="`absolutePath "$1"`"
-
-! absolutePath "$2" > /dev/null \
-	&& echo "The folder in which the output file should be generated does not exist. Exiting..." && exit $EXIT_BAD_ARGS
-FILE_OUTPUT_PDFA="`absolutePath "$2"`"
-
-
-
-# set script path as working directory
-cd "$BASEPATH"
-
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "$TOOLNAME version: $VERSION"
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Arguments: $ARGUMENTS"
-
-# check if the required utilities are installed
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Checking if all dependencies are installed"
-! command -v identify > /dev/null && echo "Please install ImageMagick. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! command -v parallel > /dev/null && echo "Please install GNU Parallel. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! command -v pdfimages > /dev/null && echo "Please install poppler-utils. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! command -v pdftoppm > /dev/null && echo "Please install poppler-utils. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! command -v pdffonts > /dev/null && echo "Please install poppler-utils. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-[ $PREPROCESS_CLEAN -eq 1 ] && ! command -v unpaper > /dev/null && echo "Please install unpaper. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! command -v tesseract > /dev/null && echo "Please install tesseract and tesseract-data. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! python2 -c 'import lxml' 2>/dev/null && echo "Please install the python library lxml. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! python2 -c 'import sys, reportlab; (getattr(reportlab, "Version", "0.0") >= "3.0") or sys.exit(1)' 2>/dev/null \
-	&& echo "Please install the python library reportlab. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-
-! command -v gs > /dev/null && echo "Please install ghostscript. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! command -v java > /dev/null && echo "Please install java. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-
-
-# ensure the right tesseract version is installed
-# older versions are known to produce malformed hocr output and should not be used
-# Even 3.02.01 fails in few cases (see issue #28). I decided to allow this version anyway because
-# 3.02.02 is not yet available for some widespread linux distributions
-reqtessversion="3.02.01"
-tessversion=`tesseract -v 2>&1 | grep "tesseract" | sed s/[^0-9.]//g`
-tesstooold=$(echo "`echo $tessversion | sed s/[.]//2`-`echo $reqtessversion | sed s/[.]//2` < 0" | bc)
-[ "$tesstooold" -eq "1" ] \
-	&& echo "Please install tesseract ${reqtessversion} or newer (currently installed version is ${tessversion})" && exit $EXIT_MISSING_DEPENDENCY
-
-# ensure the right GNU parallel version is installed
-# older version do not support -q flag (required to escape special characters)
-reqparallelversion="20121122"
-parallelversion=`parallel --minversion 0`
-! parallel --minversion "$reqparallelversion" > /dev/null \
-	&& echo "Please install GNU parallel ${reqparallelversion} or newer (currently installed version is ${parallelversion})" && exit $EXIT_MISSING_DEPENDENCY
-
-# ensure pdftoppm is provided by poppler-utils, not the older xpdf version
-! pdftoppm -v 2>&1 | grep -q 'Poppler' && echo "Please remove xpdf and install poppler-utils. Exiting..." && $EXIT_MISSING_DEPENDENCY
-
-
-
-# Display the version of the tools if log level is LOG_DEBUG
-if [ $VERBOSITY -ge $LOG_DEBUG ]; then
-	echo "--------------------------------"
-	echo "ImageMagick version:"
-	identify --version
-	echo "--------------------------------"
-	echo "GNU Parallel version:"
-	parallel --version
-	echo "--------------------------------"
-	echo "Poppler-utils version:"
-	pdfimages -v
-	pdftoppm -v
-	pdffonts -v
-	echo "--------------------------------"
-	echo "unpaper version:"
-	unpaper --version
-	echo "--------------------------------"
-	echo "tesseract version:"
-	tesseract --version
-	echo "--------------------------------"
-	echo "python2 version:"
-	python2 --version
-	echo "--------------------------------"
-	echo "Ghostscript version:"
-	gs --version
-	echo "--------------------------------"
-	echo "Java version:"
-	java -version
-	echo "--------------------------------"
-fi
-
-
-
-# check if the languages passed to tesseract are all supported
-for currentlan in `echo "$LAN" | sed 's/+/ /g'`; do
-	if ! tesseract --list-langs 2>&1 | grep "^$currentlan\$" > /dev/null; then
-		echo "The language \"$currentlan\" is not supported by tesseract."
-		tesseract --list-langs 2>&1 | tr '\n' ' '; echo
-		echo "Exiting..."
-		exit $EXIT_BAD_ARGS
-	fi
-done
-
-
-
-# Initialize path to temporary files using mktemp
-# Goal: save tmp file in a sub-folder of the $TMPDIR environment variable (or in "/tmp" if unset)
-# Unfortunately, Linux mktemp is not compatible with FreeBSD/OSX mktemp
-# Linux version requires no arg
-# FreeBSD requires '-t prefix' to be used so that $TMPDIR is taken into account
-# But in Linux '-t template' is handled differently than in FreeBSD
-# Therefore different calls must be used for Linux and for FreeBSD
-prefix="$(date +"%Y%m%d_%H%M").filename.$(basename "$FILE_INPUT_PDF" | sed 's/[.][^.]*$//')"	# prefix made of date, time and pdf file name without extension
-TMP_FLD=`mktemp -d 2>/dev/null || mktemp -d -t "${prefix}" 2>/dev/null`				# try Linux syntax first, if it fails try FreeBSD/OSX			
-if [ $? -ne 0 ]; then
-	if [ -z "$TMPDIR" ]; then
-		echo "Could not create folder for temporary files. Please ensure you have sufficient right and \"/tmp\" exists"
-	else
-		echo "Could not create folder for temporary files. Please ensure you have sufficient right and \"$TMPDIR\" exists"
-	fi
-	exit $EXIT_FILE_ACCESS_ERROR
-fi
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Created temporary folder: \"$TMP_FLD\""
-
-FILE_TMP="${TMP_FLD}/tmp.txt"						# temporary file with a very short lifetime (may be used for several things)
-FILE_PAGES_INFO="${TMP_FLD}/pages-info.txt"				# for each page: page #; width in pt; height in pt
-FILE_VALIDATION_LOG="${TMP_FLD}/pdf_validation.log"			# log file containing the results of the validation of the PDF/A file
-
-
-
-# get the size of each pdf page (width / height) in pt (i.e. inch/72)
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Input file: Extracting size of each page (in pt)"
-! identify -format "%w %h\n" "$FILE_INPUT_PDF" > "$FILE_TMP" \
-	&& echo "Could not get size of PDF pages. Exiting..." && exit $EXIT_BAD_INPUT_FILE
-# removing empty lines (last one should be) and add page # before each line
-sed '/^$/d' "$FILE_TMP" | awk '{printf "%04d %s\n", NR, $0}' > "$FILE_PAGES_INFO"
-numpages=`tail -n 1 "$FILE_PAGES_INFO" | cut -f1 -d" "`
-
-# process each page of the input pdf file
-parallel --gnu -q -k --halt-on-error 1 "$OCR_PAGE" "$FILE_INPUT_PDF" "{}" "$numpages" "$TMP_FLD" \
-	"$VERBOSITY" "$LAN" "$KEEP_TMP" "$PREPROCESS_DESKEW" "$PREPROCESS_CLEAN" "$PREPROCESS_CLEANTOPDF" "$OVERSAMPLING_DPI" \
-	"$PDF_NOIMG" "$TESS_CFG_FILES" "$FORCE_OCR" < "$FILE_PAGES_INFO"
-ret_code="$?"
-[ $ret_code -ne 0 ] && exit $ret_code 
-
-# concatenate all pages and convert the pdf file to match PDF/A format
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Concatenating all pages to the final PDF/A file" 
-! gs -dQUIET -dPDFA -dBATCH -dNOPAUSE -dUseCIEColor \
-	-sProcessColorModel=DeviceCMYK -sDEVICE=pdfwrite -sPDFACompatibilityPolicy=2 \
-	-sOutputFile="$FILE_OUTPUT_PDFA" "${TMP_FLD}/"*ocred*.pdf 1> /dev/null 2> /dev/null \
-	&& echo "Could not concatenate all pages to the final PDF/A file. Exiting..." && exit $EXIT_OTHER_ERROR
-
-# validate generated pdf file (compliance to PDF/A)
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Checking compliance to PDF/A standard" 
-! java -jar "$JHOVE" -c "$JHOVE_CFG" -m PDF-hul "$FILE_OUTPUT_PDFA" 2> /dev/null 1> "$FILE_VALIDATION_LOG" \
-	&& echo "Unexpected error while checking compliance to PDF/A file. Exiting..." && exit $EXIT_OTHER_ERROR
-grep -i "Status|Message" "$FILE_VALIDATION_LOG" # summary of the validation
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "The full validation log is available here: \"$FILE_VALIDATION_LOG\""
-# check the validation results
-pdf_valid=1
-grep -i 'ErrorMessage' "$FILE_VALIDATION_LOG" && pdf_valid=0
-grep -i 'Status.*not valid' "$FILE_VALIDATION_LOG" && pdf_valid=0
-grep -i 'Status.*Not well-formed' "$FILE_VALIDATION_LOG" && pdf_valid=0
-! grep -i 'Profile:.*PDF/A-1' "$FILE_VALIDATION_LOG" > /dev/null && echo "PDF file profile is not PDF/A-1" && pdf_valid=0
-[ $pdf_valid -ne 1 ] && echo "Output file: The generated PDF/A file is INVALID"
-[ $pdf_valid -eq 1 ] && [ $VERBOSITY -ge $LOG_INFO ] && echo "Output file: The generated PDF/A file is VALID"
-
-
-
-
-# delete temporary files
-if [ $KEEP_TMP -eq 0 ]; then
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Deleting temporary files"
-	rm -r -f "${TMP_FLD}"
-fi
-
-
-END=`date +%s`
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Script took $(($END-$START)) seconds"
-
-
-[ $pdf_valid -ne 1 ] && exit $EXIT_INVALID_OUTPUT_PDFA || exit 0
+python3 -m ocrmypdf.main "$@"

README.md

@@ -1,69 +0,0 @@
-OCRmyPDF
-========
-
-OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
-
-To get the script usage, call: sh ./OCRmyPDF.sh -h
-
-Main features
---------
-
-- Generates a searchable PDF/A file from a PDF file containing only images
-- Places OCRed text accurately below the image to ease copy / paste
-- Keeps the exact resolution of the original embedded images
-    - or if requested oversamples the images before OCRing so as to get better results 
-- If requested deskews and / or clean the image before performing OCR
-- Validates the generated file against the PDF/A specification using jhove
-- Provides debug mode to enable easy verification of the OCR results
-- Processes several pages in parallel if more than one CPU core is available
-
-For details: please consult the release notes
-
-Motivation
-----------
-
-I searched the web for a free command line tool to OCR PDF files on linux/unix:
-I found many, but none of them were really satisfying.
-- Either they produced PDF files with misplaced text under the image (making copy/paste impossible)
-- Or they did not display correctly some escaped html characters located in the hocr file produced by the OCR engine
-- Or they changed the resolution of the embedded images
-- Or they generated PDF file having a ridiculous big size
-- Or they crashed when trying to OCR some of my PDF files
-- Or they did not produce valid PDF files (even though they were readable with my current PDF reader) 
-- On top of that none of them produced PDF/A files (format dedicated for long time storage / archiving)
-
-... so I decided to develop my own tool (using various existing scripts as an inspiration)
-
-Install
--------
-
-Download OCRmyPDF here: https://github.com/fritz-hh/OCRmyPDF/releases
-
-Copy the file in onto your linux/unix machine and extract it.
-
-Run: "sh ./OCRmyPDF.sh -h" to get the script usage
-
-If not yet installed, the script will notify you about dependencies that need to be installed.
-The script requires specific versions of the dependencies. Older version than the ones mentioned in the release notes are likely not to be compatible to OCRmyPDF.
-
-Support
--------
-
-In case you detect an issue, please:
-
-- Check if your issue is already known
-- If no problem report exists on github, please create one here: https://github.com/fritz-hh/OCRmyPDF/issues
-- Describe your problem thoroughly
-- Append the console output of the script when running the debug mode (-g option)
-- If possible provide your input PDF file as well as the content of the temporary folder (using a file sharing service like www.file-upload.net)
-
-Press & Media
--------------
-
-- c't 1-2014, page 59: Detailed presentation of OCRmyPDF v1.0 in the leading german IT magazine c't (http://www.heise.de/ct/inhalt/2014/1/58/) 
-- heise Open Source, 09/2014: Texterkennung mit OCRmyPDF (http://www.heise.de/-2356670)
-
-Disclaimer
-----------
-
-The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

README.rst

@@ -0,0 +1,265 @@
+OCRmyPDF
+========
+
+OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
+be searched.
+
+Main features
+-------------
+
+-  Generates a searchable
+   `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
+-  Keeps file size about the same
+-  If requested deskews and/or cleans the image before performing OCR
+-  Validates input and output files
+-  Provides debug mode to enable easy verification of the OCR results
+-  Processes pages in parallel when more than one CPU core is
+   available
+-  Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`__ engine
+-  Supports the `39 languages <https://code.google.com/p/tesseract-ocr/downloads/list>`__ recognized by Tesseract
+-  Battle-tested on thousands of PDFs, a test suite and continuous integration
+
+For details: please consult the `release notes <RELEASE_NOTES.rst>`__.
+
+Motivation
+----------
+
+I searched the web for a free command line tool to OCR PDF files on
+Linux/UNIX: I found many, but none of them were really satisfying.
+
+-  Either they produced PDF files with misplaced text under the image (making copy/paste impossible) 
+-  Or they did not display correctly some escaped HTML characters located in the hOCR file produced by the OCR engine 
+-  Or they changed the resolution of the embedded images
+-  Or they generated PDF files having a ridiculous big size
+-  Or they crashed when trying to OCR some of my PDF files
+-  Or they did not produce valid PDF files (even though they were readable with my current PDF reader)
+-  On top of that none of them produced PDF/A files (format dedicated for long time storage)
+
+... so I decided to develop my own tool (using various existing scripts
+as an inspiration)
+
+Installation
+------------
+
+Download OCRmyPDF here: https://github.com/jbarlow83/OCRmyPDF/releases
+
+You can install it to a Python virtual environment or system-wide. 
+
+Installing the Docker image
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For many users, installing the Docker image will be easier than installing all of OCRmyPDF's dependencies. For Windows, it is the only option.
+
+If you have `Docker <https://docs.docker.com/>`__ installed on your system, you can install
+a Docker image of the latest release.
+
+Follow the Docker installation instructions for your platform.  If you can run this command
+successfully, your system is ready to download and execute the image::
+
+   docker run hello-world
+   
+OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine instance on Windows and OS X has only a single CPU core enabled. Use the VirtualBox Manager to determine the name of your Docker engine host, and then follow these optional steps to enable multiple CPUs::
+
+   # Optional step for Mac OS X users
+   docker-machine stop "yourVM"
+   VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
+   docker-machine start "yourVM"
+   eval $(docker-machine env "yourVM")
+
+Assuming you have a Docker engine running somewhere, you can run these commands to download
+the image::
+
+   docker pull jbarlow83/ocrmypdf
+
+Then tag it to give a more convenient name, just ocrmypdf::
+
+   docker tag jbarlow83/ocrmypdf ocrmypdf
+
+This image contains language packs for English, French, Spanish and German. The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__::
+
+   # Alternative step: If you need all language packs
+   docker pull jbarlow83/ocrmypdf-polyglot
+   docker tag jbarlow83/ocrmypdf-polyglot ocrmypdf
+
+You can then run ocrmypdf using the command::
+
+   docker run ocrmypdf --help
+  
+To execute the OCRmyPDF on a local file, you must `provide a writable volume to the Docker image <https://docs.docker.com/userguide/dockervolumes/>`__, such as this in this template::
+
+   docker run -v "$(pwd):/home/docker" <other docker arguments>   ocrmypdf <your arguments to ocrmypdf>
+
+In this worked example, the current working directory contains an input file called ``test.pdf`` and the output will go to ``output.pdf``:: 
+
+   docker run -v "$(pwd):/home/docker"   ocrmypdf --skip-text test.pdf output.pdf
+
+Note that ``ocrmypdf`` has its own separate ``-v VERBOSITYLEVEL`` argument to control debug verbosity. All Docker arguments should before the ``ocrmypdf`` image name and all arguments to ``ocrmypdf`` should be listed after.
+
+
+Installing on Mac OS X
+~~~~~~~~~~~~~~~~~~~~~~
+
+These instructions probably work on all Mac OS X versions later than 10.7 (Lion). OCRmyPDF is known to work on Yosemite and El Capitan, and regularly tested on El Capitan.
+
+If it's not already present, `install Homebrew <http://brew.sh/>`__.
+
+Update Homebrew::
+
+   brew update
+   
+Install or upgrade the required Homebrew packages, if any are missing::
+
+   brew install libpng openjpeg jbig2dec     # image libraries
+   brew install qpdf
+   brew install ghostscript
+   brew install python3
+   brew install libxml2
+   brew install leptonica
+   brew install tesseract
+   
+Update the homebrew pip and install Pillow::
+
+   pip3 install --upgrade pip
+   pip3 install --upgrade pillow
+
+You can then install OCRmyPDF from PyPI::
+
+   pip3 install ocrmypdf
+
+The command line program should now be available::
+
+   ocrmypdf --help
+
+Installing on Ubuntu 14.04 LTS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Installing on Ubuntu 14.04 LTS (trusty) is more difficult than other options, because of certain bugs in Python package installation.
+
+Update apt-get::
+
+   sudo apt-get update
+   sudo apt-get upgrade
+   
+Install system dependencies::
+
+   sudo apt-get install \
+      zlib1g-dev \
+      libjpeg-dev \
+      ghostscript \
+      tesseract-ocr \
+      qpdf \
+      unpaper \
+      python3-pip \
+      python3-pil \
+      python3-pytest \
+      python3-reportlab
+
+If you wish install OCRmyPDF to the system Python, then install as follows (note this installs new packages
+into your system Python, which could interfere with other programs)::
+
+   sudo pip3 install ocrmypdf
+   
+If you wish to install OCRmyPDF to a virtual environment to isolate system Python from modified, you can
+follow these steps.  This includes a workaround `for a known, unresolved issue in Ubuntu 14.04's ensurepip
+package <http://www.thefourtheye.in/2014/12/Python-venv-problem-with-ensurepip-in-Ubuntu.html>`__::
+
+   sudo apt-get install python3-venv
+   python3 -m venv venv-ocrmypdf --without-pip
+   source venv-ocrmypdf/bin/activate
+   wget -O - -o /dev/null https://bootstrap.pypa.io/get-pip.py | python
+   deactivate
+   pyvenv --system-site-packages venv-ocrmypdf
+   source venv-ocrmypdf/bin/activate
+   pip install ocrmypdf
+
+Ubuntu 14.04 only installs ``unpaper`` version 0.4.2, which is not supported by OCRmyPDF because it is produces invalid output. This program is an optional dependency, and provides page deskewing and cleaning. See `Dockerfile <Dockerfile>`__ for an example of how to building unpaper 6.1 from source. If you choose to install unpaper later, OCRmyPDF will use the foremost version on the system PATH.
+
+Installing on Windows
+~~~~~~~~~~~~~~~~~~~~~
+
+Direct installation on Windows is not possible.  Install the Docker container as described above.
+
+      
+Installing HEAD revision from sources
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If you have ``git`` and ``python3.4`` or ``python3.5`` installed, you can install from source. When the ``pip`` installer runs,
+it will alert you if dependencies are missing.
+
+To install the HEAD revision from sources in the current Python 3 environment::
+
+   pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
+
+Or, to install in `development mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,  allowing customization of OCRmyPDF, use the ``-e`` flag::
+
+   pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
+   
+On certain Linux distributions such as Ubuntu, you may need to use 
+run the install command as superuser::
+
+   sudo pip3 install [-e] git+https://github.com/jbarlow83/OCRmyPDF.git
+   
+Note that this will alter your system's Python distribution. If you prefer 
+to not install as superuser, you can install the package in a Python virtual environment::
+
+   git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+   pyvenv venv
+   source venv/bin/activate
+   cd OCRmyPDF
+   pip3 install .
+
+However, ``ocrmypdf`` will only be accessible on the system PATH after
+you activate the virtual environment.
+
+To run the program::
+   
+   ocrmypdf --help
+
+If not yet installed, the script will notify you about dependencies that
+need to be installed. The script requires specific versions of the
+dependencies. Older version than the ones mentioned in the release notes
+are likely not to be compatible to OCRmyPDF.
+
+Languages
+---------
+
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users,
+you can often find packages that provide language packs::
+
+   # Debian/Ubuntu users
+   sudo apt-get install tesseract-ocr-chi-sim
+   
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
+languages can be requested.
+
+Support
+-------
+
+In case you detect an issue, please:
+
+-  Check if your issue is already known
+-  If no problem report exists on github, please create one here:
+   https://github.com/jbarlow83/OCRmyPDF/issues
+-  Describe your problem thoroughly
+-  Append the console output of the script when running the debug mode
+   (``-v 1`` option)
+-  If possible provide your input PDF file as well as the content of the
+   temporary folder (using a file sharing service like Dropbox)
+
+Press & Media
+-------------
+
+-  `c't 1-2014, page 59 <http://www.heise.de/ct/inhalt/2014/1/58/>`__:
+   Detailed presentation of OCRmyPDF v1.0 in the leading German IT
+   magazine c't
+-  `heise Open Source, 09/2014: Texterkennung mit
+   OCRmyPDF <http://www.heise.de/-2356670>`__
+
+Disclaimer
+----------
+
+The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied.

RELEASE_NOTES.md

@@ -1,335 +0,0 @@
-RELEASE NOTES
-=============
-
-Please always read this file before installing the package
-
-Download software here: https://github.com/fritz-hh/OCRmyPDF/tags
-
-v2.2-stable (2014-09-29):
-=======
-
-New features
-------------
-
-- None
-
-Changes
--------
-
-- Update to jhove v1.11
-- Request the python library reportlab v3.0 or newer (So that we could remove a patch to the previous version of reportlab leading to issues for some users)
-
-Fixes
------
-
-- Fix bug on Mac OS X (resolution of simlink to OCRmyPDF.sh script) (thanks to jbarlow83)
-- Check if the input pdf file exists before to continue
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.2
-- Dependencies:
-   - parallel 20140822
-   - poppler-utils 0.24.5
-   - ImageMagick 6.8.9-4 2014-09-17
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.8
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_65"
-
-v2.1-stable (2014-09-20):
-=======
-
-New features
-------------
-
-- None
-
-Changes
--------
-
-- None
-
-Fixes
------
-
-- Allow execution via simlink
-- Add support for tesseract 3.03
-- Add support for newer version of reportlab
-- Lowered minimum version of gnu parallel
-- Various typo
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - parallel 20130222
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"
-
-v2.0-stable (2014-01-25):
-=======
-
-New features
-------------
-
-- Check if the language(s) passed using the -l option is supported by tesseract (fixes #60)
-
-Changes
--------
-
-- Allow OCRmyPDF to be used with tesseract 3.02.01, even though OCR might fail for few PDF file (see issue #28). Rationale: For some linux distribution, no newer version than tesseract 3.02.01 is available
-
-Fixes
------
-
-- More robust algorithm for checking the version of the installed tesseract package
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - parallel 20130222
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"
-
-v2.0-rc2 (2014-01-16):
-=======
-   
-New features
-------------
-
-- None
-
-Changes
--------
-
-- Size reduction of final PDF file: (fixes #50)
-   - Support for monochrome (Black&White) images (massive size reduction in final PDF: >80%)
-   - Reduced size of grayscale images (by 13% on test PDF file)
-- Preventing fi, fl ligatures does not require anymore to pass an additional config file to tesseract using the -C option (fixes #58)
-- Location of temporary folder according to content of environment variable TMPDIR.
-- Dependency to pdftk removed
-- Check for compatible versions of dependencies: (fixes #51)
-   - parallel and tesseract
-   - python libraries reportlab and lxml
-
-Fixes
------
-
-- Improved portability with various shells (dash, bash, tcsh) and OS (FreeBSD, MAC OSX, Linux) (fixes #59)
-- Corrected bug in case the input PDF file contains a space character (fixes #48)
-- Prevent spurious error message in case there is no image in a PDF page
-- Prevent collision of temporary folder names (fixes #57)
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - parallel 20130222
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"
-
-v2.0-rc1 (2014-01-07):
-====
-
-New features
-------------
-
-- Huge performance improvement on machines having multiple CPU/cores (processing of several pages concurrently) (fixes #18)
-- By default prevent from processing a PDF file already containing fonts (i.e. text)(it can be overridden with the -f flag) (fixes #16)
-- Warn if the resolution is too low to get reasonable OCR results (fixes #37)
-- New option (-o) to perform automatic oversampling if the image resolution is too low. This can improve OCR results.
-- Warn if using a tesseract version older than v3.02.02 (as older versions are known to produce invalid output) (fixes #41)
-- Echo version of the installed dependencies (e.g. tesseract) in debug mode in order to ease support (fixes #35)
-- Echo the arguments passed to the script in debug mode to ease support
-
-Changes
--------
-
-- In debug mode: The debug page is now placed after the respective "normal" page
-- Reduced disk space usage in temporary folder if -d (deskew) or -c (cleanup) options are not selected
-- New file src/config.sh containing various configuration parameters
-- Documentation of the tesseract config file "tess-cfg/no_ligature" improved 
-- Improved consistency of the temporary file names
-
-Fixes
------
-
-- Improved robustness:
-   - in case vertical resolution differs from horizontal resolution (fixes #38)
-   - in case a PDF page contains more than one image (fixes #36)
-- Fix a problem occurring if python 3 is the standard interpreter (fixes #33)
-- Fix a problem occurring if the input PDF file contains special characters like "#" (fixes #34)
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - parallel 20130222
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - pdftk 1.45
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"
-
-v1.1-stable (2014-01-06):
-====
-
-New features
-------------
-
-- N/A
-
-Changes
--------
-
-- N/A
-
-Fixes
------
-
-- Fixed syntax error (bashism) leading to an error message on certain systems (fixes #42)
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - pdftk 1.45
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"
-
-v1.0-stable (2013-05-06):
-====
-
-New features
-------------
-
-- In debug mode: compute and echo time required for processing (fixes #26)
-
-Changes
--------
-
-- Removed feature to add metadata in final pdf file (because it lead to to final PDF file that does not comply to the PDF/A-1 format)
-- Removed feature to set same owner & permissions in final PDF file than in input file
-- Removed many unused jhove files (e.g. documentation, *.java and *.class files)
-
-Fixes
------
-
-- Correction to handle correctly path and input PDF files having spaces (fixes #31)
-- Resolutions (x/y) that are nearly equal are now supported (fixes #25)
-- Fix compatibility issue with Ubuntu server 12.04 / Ubuntu server 10.04 / Linux Mint 13 Maya and probably other Linux distributions (fixes #27)
-- Commit missing jhove files (*.jar mainly) due to wrong .gitignore
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - pdftk 1.45
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"
-
-v1.0-rc2 (2013-04-29):
-====
-
-New features
-------------
-
-- Keep temporary files if debug mode is set (fixes #22)
-- Set same owner & permissions in final PDF file than in input file (fixes #9)
-- Added metadata in final pdf file (fixes #4)
-
-Changes
--------
-
-- N/A
-
-Fixes
------
-
-- Fixed wrong image cropping when deskew option is activated
-- Exit with error message if page size is not found in hocr file (fixes #21)
-- Various minor fixes in log messages
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - pdftk 1.45
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"
-
-v1.0-rc1 (2013-04-26):
-====
-
-New features
-------------
-
-- First release candidate
-
-Changes
--------
-
-- N/A
-
-Fixes
------
-
-- N/A
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - pdftk 1.45
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_17"

RELEASE_NOTES.rst

@@ -0,0 +1,614 @@
+RELEASE NOTES
+=============
+
+Please always read this file before installing the package
+
+Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
+
+
+v4.0:
+=====
+
+New features
+------------
+
+-  Automatic page rotation (``-r``) is now available. It uses ignores any prior rotation information
+   on PDFs and sets rotation based on the dominant orientation of detectable text. This feature is
+   fairly reliable but some false positives occur especially if there is not much text to work with. (#4) 
+-  Deskewing is now performed using Leptonica instead of unpaper. Leptonica deskews images faster and
+   more reliably than unpaper.
+
+
+Fixes
+-----
+
+-  Fixed an issue where lossless reconstruction could cause some pages to be appear incorrectly
+   rotated in the page had a /Rotate tag applied (#50)
+-  Fixed an issue where lossless reconstruction could misalign the graphics layer with respect to
+   text layer if the page had been cropped such that its origin is not (0, 0) (#49)
+
+
+Changes
+-------
+
+-  Logging output much is now better
+-  ``--deskew`` is now performed by Leptonica instead of unpaper (#25)
+-  libffi is now required
+-  Some changes were made to the Docker and Travis build environments to support libffi
+-  ``--pdf-renderer=tesseract`` now displays a warning if the Tesseract version is less than 3.04.01,
+   the planned release that will include fixes to an important OCR text rendering bug in Tesseract 3.04.00.
+   You can also manually install ./share/sharp2.ttf on top of pdf.ttf in your Tesseract tessdata folder
+   to correct the problem.
+
+
+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 
+   otherwise manipulating the content and layout of a PDF page. For example, a PDF containing a mix
+   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:
+=======
+
+Changes
+-------
+
+-  Fixed bug that caused incorrect page size and DPI calculations on documents with mixed page sizes
+
+v3.1:
+=====
+
+Changes
+-------
+
+-  Default output format is now PDF/A-2b instead of PDF/A-1b
+-  Python 3.5 and OS X El Capitan are now supported platforms - no changes were
+   needed to implement support
+-  Improved some error messages related to missing input files
+-  Fixed issue #20 - uppercase .PDF extension not accepted
+-  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. 
+   Currently it always chooses the 'hocrtransform' renderer but that behavior may change.
+-  Set up Travis CI automatic integration testing
+
+v3.0:
+=====
+
+New features
+------------
+
+-  Easier installation with a Docker container or Python's ``pip`` package manager 
+-  Eliminated many external dependencies, so it's easier to setup
+-  Now installs ``ocrmypdf`` to ``/usr/local/bin`` or equivalent for system-wide
+   access and easier typing
+-  Improved command line syntax and usage help (``--help``)
+-  Tesseract 3.03+ PDF page rendering can be used instead for better positioning
+   of recognized text (``--pdf-renderer tesseract``)
+-  PDF metadata (title, author, keywords) are now transferred to the 
+   output PDF
+-  PDF metadata can also be set from the command line (``--title``, etc.)
+-  Automatic repairs malformed input PDFs if possible
+-  Added test cases to confirm everything is working
+-  Added option to skip extremely large pages that take too long to OCR and are 
+   often not OCRable (e.g. large scanned maps or diagrams); other pages are still
+   processed (``--skip-big``)
+-  Added option to kill Tesseract OCR process if it seems to be taking too long on
+   a page, while still processing other pages (``--tesseract-timeout``)
+-  Less common colorspaces (CMYK, palette) are now supported by conversion to RGB
+-  Multiple images on the same PDF page are now supported
+
+Changes
+-------
+
+-  New, robust rewrite in Python 3.4+ with ruffus_ pipelines
+-  Now uses Ghostscript 9.14's improved color conversion model to preserve PDF colors
+-  OCR text is now rendered in the PDF as invisible text. Previous versions of OCRmyPDF
+   incorrectly rendered visible text with an image on top.
+-  All "tasks" in the pipeline can be executed in parallel on any
+   available CPUs, increasing performance
+-  The ``-o DPI`` argument has been phased out, in favor of ``--oversample DPI``, in
+   case we need ``-o OUTPUTFILE`` in the future
+-  Removed several dependencies, so it's easier to install.  We no 
+   longer use:
+   
+   - GNU parallel_
+   - ImageMagick_
+   - Python 2.7
+   - Poppler
+   - MuPDF_ tools
+   - shell scripts
+   - Java and JHOVE_
+   - libxml2
+
+-  Some new external dependencies are required or optional, compared to v2.x:
+
+   - Ghostscript 9.14+
+   - qpdf_ 5.0.0+
+   - Unpaper_ 6.1 (optional)
+   - some automatically managed Python packages
+  
+.. _ruffus: http://www.ruffus.org.uk/index.html
+.. _parallel: https://www.gnu.org/software/parallel/
+.. _ImageMagick: http://www.imagemagick.org/script/index.php
+.. _MuPDF: http://mupdf.com/docs/
+.. _qpdf: http://qpdf.sourceforge.net/
+.. _Unpaper: https://github.com/Flameeyes/unpaper
+.. _JHOVE: http://jhove.sourceforge.net/
+
+Release candidates
+------------------
+
+-  rc9:
+
+   - fix issue #118: report error if ghostscript iccprofiles are missing
+   - fixed another issue related to #111: PDF rasterized to palette file
+   - add support image files with a palette
+   - don't try to validate PDF file after an exception occurs
+
+-  rc8:
+
+   - fix issue #111: exception thrown if PDF is missing DocumentInfo dictionary
+
+-  rc7:
+
+   - fix error when installing direct from pip, "no such file 'requirements.txt'"
+
+-  rc6:
+
+   - dropped libxml2 (Python lxml) since Python 3's internal XML parser is sufficient
+   - set up Docker container
+   - fix Unicode errors if recognized text contains Unicode characters and system locale is not UTF-8
+
+-  rc5:
+
+   - dropped Java and JHOVE in favour of qpdf
+   - improved command line error output
+   - additional tests and bug fixes
+   - tested on Ubuntu 14.04 LTS
+
+-  rc4:
+
+   - dropped MuPDF in favour of qpdf
+   - fixed some installer issues and errors in installation instructions
+   - improve performance: run Ghostscript with multithreaded rendering
+   - improve performance: use multiple cores by default
+   - bug fix: checking for wrong exception on process timeout 
+
+-  rc3: skipping version number intentionally to avoid confusion with Tesseract
+-  rc2: first release for public testing to test-PyPI, Github
+-  rc1: testing release process
+
+Compatibility notes
+-------------------
+
+-  ``./OCRmyPDF.sh`` script is still available for now
+-  Stacking the verbosity option like ``-vvv`` is no longer supported
+
+-  The configuration file ``config.sh`` has been removed.  Instead, you can
+   feed a file to the arguments for common settings:
+
+::
+
+   ocrmypdf input.pdf output.pdf @settings.txt
+
+where ``settings.txt`` contains *one argument per line*, for example:
+
+::
+
+   -l 
+   deu 
+   --author 
+   A. Merkel 
+   --pdf-renderer 
+   tesseract
+
+
+Fixes
+-----
+
+-  Handling of filenames containing spaces: fixed
+
+Notes and known issues
+----------------------
+
+-  Some dependencies may work with lower versions than tested, so try
+   overriding dependencies if they are "in the way" to see if they work.
+
+-  ``--pdf-renderer tesseract`` will output files with an incorrect page size in Tesseract 3.03,
+   due to a bug in Tesseract.
+
+-  PDF files containing "inline images" are not supported and won't be for the 3.0 release. Scanned
+   images almost never contain inline images.
+
+
+v2.2-stable (2014-09-29):
+=========================
+
+New features
+------------
+
+- None
+
+Changes
+-------
+
+- Update to jhove v1.11
+- Request the python library reportlab v3.0 or newer (So that we could remove a patch to the previous version of reportlab leading to issues for some users)
+
+Fixes
+-----
+
+- Fix bug on Mac OS X (resolution of simlink to OCRmyPDF.sh script) (thanks to jbarlow83)
+- Check if the input pdf file exists before to continue
+
+Tested with
+-----------
+
+- Operating system: FreeBSD 9.2
+- Dependencies:
+
+   - parallel 20140822
+   - poppler-utils 0.24.5
+   - ImageMagick 6.8.9-4 2014-09-17
+   - Unpaper 0.3
+   - tesseract 3.02.02
+   - Python 2.7.8
+   - ghostcript (gs): 9.06
+   - java: openjdk version "1.7.0_65"
+
+
+v2.1-stable (2014-09-20):
+=========================
+
+New features
+------------
+
+-  None
+
+Changes
+-------
+
+-  None
+
+Fixes
+-----
+
+-  Allow execution via simlink
+-  Add support for tesseract 3.03
+-  Add support for newer version of reportlab
+-  Lowered minimum version of gnu parallel
+-  Various typo
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  parallel 20130222
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"
+
+v2.0-stable (2014-01-25):
+=========================
+
+New features
+------------
+
+-  Check if the language(s) passed using the -l option is supported by
+   tesseract (fixes #60)
+
+Changes
+-------
+
+-  Allow OCRmyPDF to be used with tesseract 3.02.01, even though OCR
+   might fail for few PDF file (see issue #28). Rationale: For some
+   linux distribution, no newer version than tesseract 3.02.01 is
+   available
+
+Fixes
+-----
+
+-  More robust algorithm for checking the version of the installed
+   tesseract package
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  parallel 20130222
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"
+
+v2.0-rc2 (2014-01-16):
+======================
+
+New features
+------------
+
+-  None
+
+Changes
+-------
+
+-  Size reduction of final PDF file: (fixes #50)
+-  Support for monochrome (Black&White) images (massive size reduction
+   in final PDF: >80%)
+-  Reduced size of grayscale images (by 13% on test PDF file)
+-  Preventing fi, fl ligatures does not require anymore to pass an
+   additional config file to tesseract using the -C option (fixes #58)
+-  Location of temporary folder according to content of environment
+   variable TMPDIR.
+-  Dependency to pdftk removed
+-  Check for compatible versions of dependencies: (fixes #51)
+-  parallel and tesseract
+-  python libraries reportlab and lxml
+
+Fixes
+-----
+
+-  Improved portability with various shells (dash, bash, tcsh) and OS
+   (FreeBSD, MAC OSX, Linux) (fixes #59)
+-  Corrected bug in case the input PDF file contains a space character
+   (fixes #48)
+-  Prevent spurious error message in case there is no image in a PDF
+   page
+-  Prevent collision of temporary folder names (fixes #57)
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  parallel 20130222
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"
+
+v2.0-rc1 (2014-01-07):
+======================
+
+New features
+------------
+
+-  Huge performance improvement on machines having multiple CPU/cores
+   (processing of several pages concurrently) (fixes #18)
+-  By default prevent from processing a PDF file already containing
+   fonts (i.e. text)(it can be overridden with the -f flag) (fixes #16)
+-  Warn if the resolution is too low to get reasonable OCR results
+   (fixes #37)
+-  New option (-o) to perform automatic oversampling if the image
+   resolution is too low. This can improve OCR results.
+-  Warn if using a tesseract version older than v3.02.02 (as older
+   versions are known to produce invalid output) (fixes #41)
+-  Echo version of the installed dependencies (e.g. tesseract) in debug
+   mode in order to ease support (fixes #35)
+-  Echo the arguments passed to the script in debug mode to ease support
+
+Changes
+-------
+
+-  In debug mode: The debug page is now placed after the respective
+   "normal" page
+-  Reduced disk space usage in temporary folder if -d (deskew) or -c
+   (cleanup) options are not selected
+-  New file src/config.sh containing various configuration parameters
+-  Documentation of the tesseract config file "tess-cfg/no\_ligature"
+   improved
+-  Improved consistency of the temporary file names
+
+Fixes
+-----
+
+-  Improved robustness:
+-  in case vertical resolution differs from horizontal resolution (fixes
+   #38)
+-  in case a PDF page contains more than one image (fixes #36)
+-  Fix a problem occurring if python 3 is the standard interpreter
+   (fixes #33)
+-  Fix a problem occurring if the input PDF file contains special
+   characters like "#" (fixes #34)
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  parallel 20130222
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  pdftk 1.45
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"
+
+v1.1-stable (2014-01-06):
+=========================
+
+New features
+------------
+
+-  N/A
+
+Changes
+-------
+
+-  N/A
+
+Fixes
+-----
+
+-  Fixed syntax error (bashism) leading to an error message on certain
+   systems (fixes #42)
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  pdftk 1.45
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"
+
+v1.0-stable (2013-05-06):
+=========================
+
+New features
+------------
+
+-  In debug mode: compute and echo time required for processing (fixes
+   #26)
+
+Changes
+-------
+
+-  Removed feature to add metadata in final pdf file (because it lead to
+   to final PDF file that does not comply to the PDF/A-1 format)
+-  Removed feature to set same owner & permissions in final PDF file
+   than in input file
+-  Removed many unused jhove files (e.g. documentation, \*.java and
+   \*.class files)
+
+Fixes
+-----
+
+-  Correction to handle correctly path and input PDF files having spaces
+   (fixes #31)
+-  Resolutions (x/y) that are nearly equal are now supported (fixes #25)
+-  Fix compatibility issue with Ubuntu server 12.04 / Ubuntu server
+   10.04 / Linux Mint 13 Maya and probably other Linux distributions
+   (fixes #27)
+-  Commit missing jhove files (\*.jar mainly) due to wrong .gitignore
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  pdftk 1.45
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"
+
+v1.0-rc2 (2013-04-29):
+======================
+
+New features
+------------
+
+-  Keep temporary files if debug mode is set (fixes #22)
+-  Set same owner & permissions in final PDF file than in input file
+   (fixes #9)
+-  Added metadata in final pdf file (fixes #4)
+
+Changes
+-------
+
+-  N/A
+
+Fixes
+-----
+
+-  Fixed wrong image cropping when deskew option is activated
+-  Exit with error message if page size is not found in hocr file (fixes
+   #21)
+-  Various minor fixes in log messages
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  pdftk 1.45
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"
+
+v1.0-rc1 (2013-04-26):
+======================
+
+New features
+------------
+
+-  First release candidate
+
+Changes
+-------
+
+-  N/A
+
+Fixes
+-----
+
+-  N/A
+
+Tested with
+-----------
+
+-  Operating system: FreeBSD 9.1
+-  Dependencies:
+-  poppler-utils 0.22.2
+-  ImageMagick 6.8.0-7 2013-03-30
+-  Unpaper 0.3
+-  tesseract 3.02.02
+-  Python 2.7.3
+-  pdftk 1.45
+-  ghoscript (gs): 9.06
+-  java: openjdk version "1.7.0\_17"

docker-wrapper.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+. /appenv/bin/activate
+cd /home/docker
+exec ocrmypdf "$@"

jhove/COPYING

@@ -1,502 +0,0 @@
-		  GNU LESSER GENERAL PUBLIC LICENSE
-		       Version 2.1, February 1999
-
- Copyright (C) 1991, 1999 Free Software Foundation, Inc.
-     59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-[This is the first released version of the Lesser GPL.  It also counts
- as the successor of the GNU Library Public License, version 2, hence
- the version number 2.1.]
-
-			    Preamble
-
-  The licenses for most software are designed to take away your
-freedom to share and change it.  By contrast, the GNU General Public
-Licenses are intended to guarantee your freedom to share and change
-free software--to make sure the software is free for all its users.
-
-  This license, the Lesser General Public License, applies to some
-specially designated software packages--typically libraries--of the
-Free Software Foundation and other authors who decide to use it.  You
-can use it too, but we suggest you first think carefully about whether
-this license or the ordinary General Public License is the better
-strategy to use in any particular case, based on the explanations below.
-
-  When we speak of free software, we are referring to freedom of use,
-not price.  Our General Public Licenses are designed to make sure that
-you have the freedom to distribute copies of free software (and charge
-for this service if you wish); that you receive source code or can get
-it if you want it; that you can change the software and use pieces of
-it in new free programs; and that you are informed that you can do
-these things.
-
-  To protect your rights, we need to make restrictions that forbid
-distributors to deny you these rights or to ask you to surrender these
-rights.  These restrictions translate to certain responsibilities for
-you if you distribute copies of the library or if you modify it.
-
-  For example, if you distribute copies of the library, whether gratis
-or for a fee, you must give the recipients all the rights that we gave
-you.  You must make sure that they, too, receive or can get the source
-code.  If you link other code with the library, you must provide
-complete object files to the recipients, so that they can relink them
-with the library after making changes to the library and recompiling
-it.  And you must show them these terms so they know their rights.
-
-  We protect your rights with a two-step method: (1) we copyright the
-library, and (2) we offer you this license, which gives you legal
-permission to copy, distribute and/or modify the library.
-
-  To protect each distributor, we want to make it very clear that
-there is no warranty for the free library.  Also, if the library is
-modified by someone else and passed on, the recipients should know
-that what they have is not the original version, so that the original
-author's reputation will not be affected by problems that might be
-introduced by others.
-
-  Finally, software patents pose a constant threat to the existence of
-any free program.  We wish to make sure that a company cannot
-effectively restrict the users of a free program by obtaining a
-restrictive license from a patent holder.  Therefore, we insist that
-any patent license obtained for a version of the library must be
-consistent with the full freedom of use specified in this license.
-
-  Most GNU software, including some libraries, is covered by the
-ordinary GNU General Public License.  This license, the GNU Lesser
-General Public License, applies to certain designated libraries, and
-is quite different from the ordinary General Public License.  We use
-this license for certain libraries in order to permit linking those
-libraries into non-free programs.
-
-  When a program is linked with a library, whether statically or using
-a shared library, the combination of the two is legally speaking a
-combined work, a derivative of the original library.  The ordinary
-General Public License therefore permits such linking only if the
-entire combination fits its criteria of freedom.  The Lesser General
-Public License permits more lax criteria for linking other code with
-the library.
-
-  We call this license the "Lesser" General Public License because it
-does Less to protect the user's freedom than the ordinary General
-Public License.  It also provides other free software developers Less
-of an advantage over competing non-free programs.  These disadvantages
-are the reason we use the ordinary General Public License for many
-libraries.  However, the Lesser license provides advantages in certain
-special circumstances.
-
-  For example, on rare occasions, there may be a special need to
-encourage the widest possible use of a certain library, so that it becomes
-a de-facto standard.  To achieve this, non-free programs must be
-allowed to use the library.  A more frequent case is that a free
-library does the same job as widely used non-free libraries.  In this
-case, there is little to gain by limiting the free library to free
-software only, so we use the Lesser General Public License.
-
-  In other cases, permission to use a particular library in non-free
-programs enables a greater number of people to use a large body of
-free software.  For example, permission to use the GNU C Library in
-non-free programs enables many more people to use the whole GNU
-operating system, as well as its variant, the GNU/Linux operating
-system.
-
-  Although the Lesser General Public License is Less protective of the
-users' freedom, it does ensure that the user of a program that is
-linked with the Library has the freedom and the wherewithal to run
-that program using a modified version of the Library.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.  Pay close attention to the difference between a
-"work based on the library" and a "work that uses the library".  The
-former contains code derived from the library, whereas the latter must
-be combined with the library in order to run.
-
-		  GNU LESSER GENERAL PUBLIC LICENSE
-   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
-
-  0. This License Agreement applies to any software library or other
-program which contains a notice placed by the copyright holder or
-other authorized party saying it may be distributed under the terms of
-this Lesser General Public License (also called "this License").
-Each licensee is addressed as "you".
-
-  A "library" means a collection of software functions and/or data
-prepared so as to be conveniently linked with application programs
-(which use some of those functions and data) to form executables.
-
-  The "Library", below, refers to any such software library or work
-which has been distributed under these terms.  A "work based on the
-Library" means either the Library or any derivative work under
-copyright law: that is to say, a work containing the Library or a
-portion of it, either verbatim or with modifications and/or translated
-straightforwardly into another language.  (Hereinafter, translation is
-included without limitation in the term "modification".)
-
-  "Source code" for a work means the preferred form of the work for
-making modifications to it.  For a library, complete source code means
-all the source code for all modules it contains, plus any associated
-interface definition files, plus the scripts used to control compilation
-and installation of the library.
-
-  Activities other than copying, distribution and modification are not
-covered by this License; they are outside its scope.  The act of
-running a program using the Library is not restricted, and output from
-such a program is covered only if its contents constitute a work based
-on the Library (independent of the use of the Library in a tool for
-writing it).  Whether that is true depends on what the Library does
-and what the program that uses the Library does.
-  
-  1. You may copy and distribute verbatim copies of the Library's
-complete source code as you receive it, in any medium, provided that
-you conspicuously and appropriately publish on each copy an
-appropriate copyright notice and disclaimer of warranty; keep intact
-all the notices that refer to this License and to the absence of any
-warranty; and distribute a copy of this License along with the
-Library.
-
-  You may charge a fee for the physical act of transferring a copy,
-and you may at your option offer warranty protection in exchange for a
-fee.
-
-  2. You may modify your copy or copies of the Library or any portion
-of it, thus forming a work based on the Library, and copy and
-distribute such modifications or work under the terms of Section 1
-above, provided that you also meet all of these conditions:
-
-    a) The modified work must itself be a software library.
-
-    b) You must cause the files modified to carry prominent notices
-    stating that you changed the files and the date of any change.
-
-    c) You must cause the whole of the work to be licensed at no
-    charge to all third parties under the terms of this License.
-
-    d) If a facility in the modified Library refers to a function or a
-    table of data to be supplied by an application program that uses
-    the facility, other than as an argument passed when the facility
-    is invoked, then you must make a good faith effort to ensure that,
-    in the event an application does not supply such function or
-    table, the facility still operates, and performs whatever part of
-    its purpose remains meaningful.
-
-    (For example, a function in a library to compute square roots has
-    a purpose that is entirely well-defined independent of the
-    application.  Therefore, Subsection 2d requires that any
-    application-supplied function or table used by this function must
-    be optional: if the application does not supply it, the square
-    root function must still compute square roots.)
-
-These requirements apply to the modified work as a whole.  If
-identifiable sections of that work are not derived from the Library,
-and can be reasonably considered independent and separate works in
-themselves, then this License, and its terms, do not apply to those
-sections when you distribute them as separate works.  But when you
-distribute the same sections as part of a whole which is a work based
-on the Library, the distribution of the whole must be on the terms of
-this License, whose permissions for other licensees extend to the
-entire whole, and thus to each and every part regardless of who wrote
-it.
-
-Thus, it is not the intent of this section to claim rights or contest
-your rights to work written entirely by you; rather, the intent is to
-exercise the right to control the distribution of derivative or
-collective works based on the Library.
-
-In addition, mere aggregation of another work not based on the Library
-with the Library (or with a work based on the Library) on a volume of
-a storage or distribution medium does not bring the other work under
-the scope of this License.
-
-  3. You may opt to apply the terms of the ordinary GNU General Public
-License instead of this License to a given copy of the Library.  To do
-this, you must alter all the notices that refer to this License, so
-that they refer to the ordinary GNU General Public License, version 2,
-instead of to this License.  (If a newer version than version 2 of the
-ordinary GNU General Public License has appeared, then you can specify
-that version instead if you wish.)  Do not make any other change in
-these notices.
-
-  Once this change is made in a given copy, it is irreversible for
-that copy, so the ordinary GNU General Public License applies to all
-subsequent copies and derivative works made from that copy.
-
-  This option is useful when you wish to copy part of the code of
-the Library into a program that is not a library.
-
-  4. You may copy and distribute the Library (or a portion or
-derivative of it, under Section 2) in object code or executable form
-under the terms of Sections 1 and 2 above provided that you accompany
-it with the complete corresponding machine-readable source code, which
-must be distributed under the terms of Sections 1 and 2 above on a
-medium customarily used for software interchange.
-
-  If distribution of object code is made by offering access to copy
-from a designated place, then offering equivalent access to copy the
-source code from the same place satisfies the requirement to
-distribute the source code, even though third parties are not
-compelled to copy the source along with the object code.
-
-  5. A program that contains no derivative of any portion of the
-Library, but is designed to work with the Library by being compiled or
-linked with it, is called a "work that uses the Library".  Such a
-work, in isolation, is not a derivative work of the Library, and
-therefore falls outside the scope of this License.
-
-  However, linking a "work that uses the Library" with the Library
-creates an executable that is a derivative of the Library (because it
-contains portions of the Library), rather than a "work that uses the
-library".  The executable is therefore covered by this License.
-Section 6 states terms for distribution of such executables.
-
-  When a "work that uses the Library" uses material from a header file
-that is part of the Library, the object code for the work may be a
-derivative work of the Library even though the source code is not.
-Whether this is true is especially significant if the work can be
-linked without the Library, or if the work is itself a library.  The
-threshold for this to be true is not precisely defined by law.
-
-  If such an object file uses only numerical parameters, data
-structure layouts and accessors, and small macros and small inline
-functions (ten lines or less in length), then the use of the object
-file is unrestricted, regardless of whether it is legally a derivative
-work.  (Executables containing this object code plus portions of the
-Library will still fall under Section 6.)
-
-  Otherwise, if the work is a derivative of the Library, you may
-distribute the object code for the work under the terms of Section 6.
-Any executables containing that work also fall under Section 6,
-whether or not they are linked directly with the Library itself.
-
-  6. As an exception to the Sections above, you may also combine or
-link a "work that uses the Library" with the Library to produce a
-work containing portions of the Library, and distribute that work
-under terms of your choice, provided that the terms permit
-modification of the work for the customer's own use and reverse
-engineering for debugging such modifications.
-
-  You must give prominent notice with each copy of the work that the
-Library is used in it and that the Library and its use are covered by
-this License.  You must supply a copy of this License.  If the work
-during execution displays copyright notices, you must include the
-copyright notice for the Library among them, as well as a reference
-directing the user to the copy of this License.  Also, you must do one
-of these things:
-
-    a) Accompany the work with the complete corresponding
-    machine-readable source code for the Library including whatever
-    changes were used in the work (which must be distributed under
-    Sections 1 and 2 above); and, if the work is an executable linked
-    with the Library, with the complete machine-readable "work that
-    uses the Library", as object code and/or source code, so that the
-    user can modify the Library and then relink to produce a modified
-    executable containing the modified Library.  (It is understood
-    that the user who changes the contents of definitions files in the
-    Library will not necessarily be able to recompile the application
-    to use the modified definitions.)
-
-    b) Use a suitable shared library mechanism for linking with the
-    Library.  A suitable mechanism is one that (1) uses at run time a
-    copy of the library already present on the user's computer system,
-    rather than copying library functions into the executable, and (2)
-    will operate properly with a modified version of the library, if
-    the user installs one, as long as the modified version is
-    interface-compatible with the version that the work was made with.
-
-    c) Accompany the work with a written offer, valid for at
-    least three years, to give the same user the materials
-    specified in Subsection 6a, above, for a charge no more
-    than the cost of performing this distribution.
-
-    d) If distribution of the work is made by offering access to copy
-    from a designated place, offer equivalent access to copy the above
-    specified materials from the same place.
-
-    e) Verify that the user has already received a copy of these
-    materials or that you have already sent this user a copy.
-
-  For an executable, the required form of the "work that uses the
-Library" must include any data and utility programs needed for
-reproducing the executable from it.  However, as a special exception,
-the materials to be distributed need not include anything that is
-normally distributed (in either source or binary form) with the major
-components (compiler, kernel, and so on) of the operating system on
-which the executable runs, unless that component itself accompanies
-the executable.
-
-  It may happen that this requirement contradicts the license
-restrictions of other proprietary libraries that do not normally
-accompany the operating system.  Such a contradiction means you cannot
-use both them and the Library together in an executable that you
-distribute.
-
-  7. You may place library facilities that are a work based on the
-Library side-by-side in a single library together with other library
-facilities not covered by this License, and distribute such a combined
-library, provided that the separate distribution of the work based on
-the Library and of the other library facilities is otherwise
-permitted, and provided that you do these two things:
-
-    a) Accompany the combined library with a copy of the same work
-    based on the Library, uncombined with any other library
-    facilities.  This must be distributed under the terms of the
-    Sections above.
-
-    b) Give prominent notice with the combined library of the fact
-    that part of it is a work based on the Library, and explaining
-    where to find the accompanying uncombined form of the same work.
-
-  8. You may not copy, modify, sublicense, link with, or distribute
-the Library except as expressly provided under this License.  Any
-attempt otherwise to copy, modify, sublicense, link with, or
-distribute the Library is void, and will automatically terminate your
-rights under this License.  However, parties who have received copies,
-or rights, from you under this License will not have their licenses
-terminated so long as such parties remain in full compliance.
-
-  9. You are not required to accept this License, since you have not
-signed it.  However, nothing else grants you permission to modify or
-distribute the Library or its derivative works.  These actions are
-prohibited by law if you do not accept this License.  Therefore, by
-modifying or distributing the Library (or any work based on the
-Library), you indicate your acceptance of this License to do so, and
-all its terms and conditions for copying, distributing or modifying
-the Library or works based on it.
-
-  10. Each time you redistribute the Library (or any work based on the
-Library), the recipient automatically receives a license from the
-original licensor to copy, distribute, link with or modify the Library
-subject to these terms and conditions.  You may not impose any further
-restrictions on the recipients' exercise of the rights granted herein.
-You are not responsible for enforcing compliance by third parties with
-this License.
-
-  11. If, as a consequence of a court judgment or allegation of patent
-infringement or for any other reason (not limited to patent issues),
-conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot
-distribute so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you
-may not distribute the Library at all.  For example, if a patent
-license would not permit royalty-free redistribution of the Library by
-all those who receive copies directly or indirectly through you, then
-the only way you could satisfy both it and this License would be to
-refrain entirely from distribution of the Library.
-
-If any portion of this section is held invalid or unenforceable under any
-particular circumstance, the balance of the section is intended to apply,
-and the section as a whole is intended to apply in other circumstances.
-
-It is not the purpose of this section to induce you to infringe any
-patents or other property right claims or to contest validity of any
-such claims; this section has the sole purpose of protecting the
-integrity of the free software distribution system which is
-implemented by public license practices.  Many people have made
-generous contributions to the wide range of software distributed
-through that system in reliance on consistent application of that
-system; it is up to the author/donor to decide if he or she is willing
-to distribute software through any other system and a licensee cannot
-impose that choice.
-
-This section is intended to make thoroughly clear what is believed to
-be a consequence of the rest of this License.
-
-  12. If the distribution and/or use of the Library is restricted in
-certain countries either by patents or by copyrighted interfaces, the
-original copyright holder who places the Library under this License may add
-an explicit geographical distribution limitation excluding those countries,
-so that distribution is permitted only in or among countries not thus
-excluded.  In such case, this License incorporates the limitation as if
-written in the body of this License.
-
-  13. The Free Software Foundation may publish revised and/or new
-versions of the Lesser General Public License from time to time.
-Such new versions will be similar in spirit to the present version,
-but may differ in detail to address new problems or concerns.
-
-Each version is given a distinguishing version number.  If the Library
-specifies a version number of this License which applies to it and
-"any later version", you have the option of following the terms and
-conditions either of that version or of any later version published by
-the Free Software Foundation.  If the Library does not specify a
-license version number, you may choose any version ever published by
-the Free Software Foundation.
-
-  14. If you wish to incorporate parts of the Library into other free
-programs whose distribution conditions are incompatible with these,
-write to the author to ask for permission.  For software which is
-copyrighted by the Free Software Foundation, write to the Free
-Software Foundation; we sometimes make exceptions for this.  Our
-decision will be guided by the two goals of preserving the free status
-of all derivatives of our free software and of promoting the sharing
-and reuse of software generally.
-
-			    NO WARRANTY
-
-  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
-WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
-EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
-OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
-KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
-LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
-THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
-WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
-AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
-FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
-CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
-LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
-RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
-FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
-SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
-DAMAGES.
-
-		     END OF TERMS AND CONDITIONS
-
-           How to Apply These Terms to Your New Libraries
-
-  If you develop a new library, and you want it to be of the greatest
-possible use to the public, we recommend making it free software that
-everyone can redistribute and change.  You can do so by permitting
-redistribution under these terms (or, alternatively, under the terms of the
-ordinary General Public License).
-
-  To apply these terms, attach the following notices to the library.  It is
-safest to attach them to the start of each source file to most effectively
-convey the exclusion of warranty; and each file should have at least the
-"copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the library's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This library is free software; you can redistribute it and/or
-    modify it under the terms of the GNU Lesser General Public
-    License as published by the Free Software Foundation; either
-    version 2.1 of the License, or (at your option) any later version.
-
-    This library is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-    Lesser General Public License for more details.
-
-    You should have received a copy of the GNU Lesser General Public
-    License along with this library; if not, write to the Free Software
-    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-
-Also add information on how to contact you by electronic and paper mail.
-
-You should also get your employer (if you work as a programmer) or your
-school, if any, to sign a "copyright disclaimer" for the library, if
-necessary.  Here is a sample; alter the names:
-
-  Yoyodyne, Inc., hereby disclaims all copyright interest in the
-  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
-
-  <signature of Ty Coon>, 1 April 1990
-  Ty Coon, President of Vice
-
-That's all there is to it!

jhove/LICENSE

@@ -1,17 +0,0 @@
-JHOVE - JSTOR/Harvard Object Validation Environment
-Copyright 2003-2008 by JSTOR and the President and Fellows of Harvard College
-
-This program is free software; you can redistribute it and/or modify
-it under the terms of the GNU Lessor General Public License as
-published by the Free Software Foundation; either version 2.1 of the
-License, or (at your option) any later version.
-
-This program is distributed in the hope that it will be useful, but
-WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-Lesser General Public License for more details.
-
-You should have received a copy of the GNU Lesser General Public
-License along with this program; if not, write to the Free Software
-Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
-USA

jhove/README

@@ -1,227 +0,0 @@
-JHOVE - JSTOR/Harvard Object Validation Environment
-Copyright 2003-2012 by JSTOR and the President and Fellows of Harvard College
-JHOVE is made available under the GNU Lesser General Public License (LGPL;
-see the file LICENSE for details)
-
-Rev. 1.11, 2013-09-29
-
-JHOVE (the JSTOR/Harvard Object Validation Environment, pronounced "jhove")
-is an extensible software framework for performing format identification,
-validation, and characterization of digital objects.
-
-o Format identification is the process of determining the format to which a
-  digital object conforms: "I have a digital object; what format is it?"
-o Format validation is the process of determining the level of compliance of a
-  digital object to the specification for its purported format: "I have an
-  object purportedly of format F; is it?"
-o Format characterization is the process of determing the format-specific
-  significant properties of an object of a given format: "I have an object of
-  format F; what are its salient properties?"
-
-These actions are frequently necessary during routine operation of digital
-repositories and for digital preservation activities.
-
-The output from JHOVE is controlled by output handlers. JHOVE uses an
-extensible plug-in architecture; it can be configured at the time of its
-invocation to include whatever specific format modules and output handlers
-that are desired. The initial release of JHOVE includes modules for
-arbitrary byte streams, ASCII and UTF-8 encoded text, AIFF and WAVE audio,
-GIF, JPEG, JPEG 2000, TIFF, and PDF; and text and XML output handlers.
-
-The JHOVE project is a collaboration of JSTOR and the Harvard University
-Library.  Development of JHOVE was funded in part by the Andrew W. Mellon
-Foundation.  JHOVE is made available under the GNU Lesser General Public
-License (LGPL; see the file LICENSE for details).
-
-JHOVE is currently being maintained by indpendent developers.
-
-REQUIREMENTS
-
-1. Java J2SE 1.5
-(JHOVE was originally implemented using the Sun J2SE SDK 1.4.1 and has
-been tested to work with 1.5)
-
-2. If you would like to compile the JHOVE source code, then
-Apache Ant, a Java-based build tool <http://ant.apache.org/> is necessary.
-Note that the JAVA_HOME environment variable must be set appropriately for
-Ant to work properly.
-(JHOVE was implemented and tested using Ant 1.5.1.)
-
-DISTRIBUTION
-
-The JHOVE distribution package includes:
-
-    jhove/                                 # JHOVE home directory
-          COPYING                          # GNU Lesser General Public License
-          LICENSE                          # JHOVE license information
-          README
-          RELEASENOTES                     # JHOVE release notes
-          bin/
-                    jhove.jar              # JHOVE API package
-                    jhove-handler.jar      # Standard output handler package
-                    jhove-module.jar       # Standard module package
-                    JhoveApp.jar           # JHOVE command line application
-                    JhoveView.jar          # JHOVE with Swing GUI front-end
-          build.xml                        # Ant configuration file
-          classes/
-                    build.xml              # Ant configuration file
-                    edu/ ...               # JHOVE API packages
-                    ADump.*                # AIFF dump utility class
-                    GDump.*                # GIF dump utility class
-                    Jhove.*                # JHOVE main class
-                    JDump.*                # JPEG dump utility class
-                    J2Dump.*               # JPEG 2000 dump utility class
-                    PDump.*                # PDF dump utility class
-                    TDump.*                # TIFF dump utility class
-                    UserHome.*             # user.home property utility class
-                    WDump.*                # WAVE dump utility class
-          conf/
-                   jhove.conf              # JHOVE configuration file
-                   jhove.xsd               # JHOVE output schema
-                   jhoveConfig.xsd         # JHOVE configuration file schema
-          doc/
-                   *.html                  # API documentation
-                   ...
-          examples/                        # Sample files
-                   ascii/ ...
-                   gif/   ...
-                   jpeg/  ...
-                   jpeg2000/ ...
-                   pdf/   ...
-                   tiff/  ...
-                   utf-8/ ...
-          adump*                           # AIFF dump Bourne shell driver
-          adump.bat*                       # AIFF dump DOS shell driver script
-          gdump*                           # GIF dump Bourne shell driver
-          gdump.bat*                       # GIF dump DOS shell driver script
-          jdump*                           # JPEG dump Bourne shell driver
-          jdump.bat*                       # JPEG dump DOS shell driver script
-          j2dump*                          # JPEG 2000 dump Bourne shell driver
-          j2dump.bat*                      # JPEG 2000 dump DOS shell driver
-          jhove.tmpl*                      # Template for JHOVE Bourne shell driver script
-          jhove_bat.tmpl*                  # Template for JHOVE DOS shell driver script
-          pdump*                           # PDF dump Bourne shell driver
-          pdump.bat*                       # PDF dump DOS shell driver script
-          tdump*                           # TIFF dump Bourne shell driver
-          tdump.bat*                       # TIFF dump DOS shell driver script
-          userhome*                        # user.home Bourne shell driver
-          userhome.bat*                    # user.home DOS shell driver script
-          wdump*                           # WAVE dump Bourne shell driver
-          wdump.bat*                       # WAVE dump DOS shell driver script
-
-INSTALLATION
-
-Edit the configuration file, jhove/conf/jhove.conf, and set the absolute
-pathname of the JHOVE home directory and the temporary directory (in which
-temporary files are created):
-
-    <jhoveHome>jhove-home-directory</jhoveHome>
-    <tempDirectory>temporary-directory</tempDirectory>
-
-The JHOVE home directory is the top-most directory in the distribution TAR
-or ZIP file.  On Unix systems, "/var/tmp" is an appropriate temporary
-directory; on Windows, "C:\Temp".  For example, if the distribution TAR
-file is disaggregated on a Unix system in the directory "/users/stephen/
-projects", then the configuration file should read:
-
-    <jhoveHome>/users/stephen/projects/jhove</jhoveHome>
-    <tempDirectory>/var/tmp</jhoveHome>
-
-In the JHOVE home directory, copy the JHOVE Bourne shell driver script
-template, "jhove.tmpl", to "jhove" (or the equivalent Windows shell 
-script, "jhove_bat.tmpl" to "jhove.bat"), and set the
-JHOVE home directory, Java home directory, and Java interpreter:
-
-    JHOVE_HOME=jhove-home-directory
-    JAVA_HOME=java-home-directory
-    JAVA=java-interpreter
-
-The JAVA_HOME property should provide the absolute pathname of the Java
-runtime or SDK installation; JAVA should provide the absolute pathname of the
-Java interpreter.  For example:
-
-    JHOVE_HOME=/users/stephen/projects/jhove
-    JAVA_HOME=/usr/local/j2re1.4.1_02
-    JAVA=$JAVA_HOME/bin/java
-
-In the DOS shell driver script, jhove.bat, the equivalent three
-variables are:
-
-    SET JHOVE_HOME=jhove-home-directory
-    SET JAVA_HOME=java-home-directory
-    SET JAVA=%JAVA_HOME%\bin\java
-
-For example:
-
-    SET JHOVE_HOME="C:\Program Files\jhove"
-    SET JAVA_HOME="C:\Program Files\java\j2re1.4.1_02"
-    SET JAVA=%JAVA_HOME%\bin\java
-
-The quotation marks are necessary because of the embedded space characters.
-On Windows platforms it may also be necessary to add the Java bin subdirectory
-to the System PATH environment variable:
-
-    PATH=C:\Program Files\java\j2re1.4.1_02\bin;...
-
-(For information on setting a Windows environment variable, consult your local
-documentation or system administrator.)
-
-USAGE
-
-    java Jhove [-c config] [-m module] [-h handler] [-e encoding] [-H handler]
-               [-o output] [-x saxclass] [-t tempdir] [-b bufsize]
-               [-l loglevel] [[-krs] dir-file-or-uri [...]]
-
-where -c config   Configuration file pathname
-      -m module   Module name
-      -h handler  Output handler name (defaults to TEXT)
-      -e encoding Character encoding used by output handler (defaults to UTF-8)
-      -H handler  About handler name
-      -o output   Output file pathname (defaults to standard output)
-      -x saxclass SAX parser class (defaults to J2SE default)
-      -t tempdir  Temporary directory in which to create temporary files
-      -b bufsize  Buffer size for buffered I/O (defaults to J2SE 1.4 default)
-      -l loglevel Logging level
-      -k          Calculate CRC32, MD5, and SHA-1 checksums
-      -r          Display raw data flags, not textual equivalents
-      -s          Format identification based on internal signatures only
-      dir-file-or-uri Directory or file pathname or URI of formated content
-                      stream
-
-All named modules and output handlers must be found on the Java CLASSPATH at
-the time of invocation.  The JHOVE driver script, jhove/jhove, automatically
-sets the CLASSPATH and invokes the Jhove main class:
-
-    jhove [-c config] [-m module] [-h handler] [-e encoding] [-H handler]
-          [-o output] [-x saxclass] [-t tempdir] [-b bufsize] [-l loglevel]
-          [[-krs] dir-file-or-uri [...]]
-
-The following additional programs are available, primarily for testing
-and debugging purposes.  They display a minimally processed, human-readable
-version of the contents of AIFF, GIF, JPEG, JPEG 2000, PDF, TIFF, and WAVE
-files:
-
-    java ADump  aiff-file
-    java GDump  gif-file
-    java JDump  jpeg-file
-    java J2Dump jpeg2000-file
-    java PDump  pdf-file
-    java TDump  tiff-file
-    java WDump  wave-file
-
-For convenience, the following driver scripts are also available:
-
-    adump  aiff-file
-    gdump  gif-file
-    jdump  jpeg-file
-    j2dump jpeg2000-file
-    pdump  pdf-file
-    tdump  tiff-file
-    wdump  wave-file
-
-The JHOVE Swing-based GUI interface can be invoked from a command shell from
-the jhove/bin sub-directory:
-
-    java -jar JhoveView.jar -c <configFile>
-
-where <configFile> is the pathname of the JHOVE configuration file.

jhove/bin/README

@@ -1,25 +0,0 @@
-JHOVE - JSTOR/Harvard Object Validation Environment
-Copyright 2003 by JSTOR and the President and Fellows of Harvard College
-JHOVE is made available under the GNU General Public License (see the file
-LICENSE for details)
-
-Rev. 2003-11-25
-
-The following jar files are meant to be used for embedding JHOVE functionality
-into new applications or systems.
-
-  jhove.jar          Contains the JHOVE API interfaces and classes
-  jhove-module.jar   Contains the standard JHOVE modules ()
-  jhove-handler.jar  Contains the standard JHOVE output handlers (TEXT and XML)
-
-The following jar file is meant to be used with the stand-alone JHOVE
-application using a command-line interface.  It contains the main Jhove class
-and the contents of jhove.jar, jhove-module.jar, and jhove-handler.jar.
-
-  JhoveApp.jar
-
-The following jar file is meant to be used with the stand-alone JHOVE
-application using a Swing GUI interface.  It contains the main JhoveView class
-and the contents of jhove.jar, jhove-module.jar, and jhove-handler.jar.
-
-  JhoveView.jar

jhove/build.xml

@@ -1,78 +0,0 @@
-<project name="Jhove" default="dist" basedir=".">
-  <description>Project build file
-    Jhove - JSTOR/Harvard Object Validation Environment
-    Version 1.0 2004-09-10
-    Copyright 2004 by JSTOR and the President and Fellows of Harvard College
-  </description>
-
-  <!-- ant (or ant dist) Build everything
-       ant debug         Build everything with debug enabled
-       ant clean         Delete backup files
-       ant cleanclass    Delete backup and class files
-       ant cleandist     Delete backup, class, and jar files
-       ant javadoc       Build javadocs
-    -->
-
-  <!-- set global properties for this build -->
-  <property name="bin"     location="bin"/>
-  <property name="classes" location="classes"/>
-  <property name="doc"     location="doc"/>
-
-  <target name="dist" description="Create distribution">
-    <ant dir="${classes}" inheritAll="false">
-      <property name="dbg" value="off"/>
-    </ant>
-  	<chmod file="jhove" perm="ugo+x"/>
-  	<chmod file="${bin}/JhoveView.jar" perm="ugo+x"/>
-  </target>
-
-  <target name="debug" description="Create distribution with debug enabled">
-    <ant dir="${classes}" inheritAll="false">
-      <property name="dbg" value="on"/>
-    </ant>
-  </target>
-
-  <target name="view" description="Create JhoveView application">
-    <ant dir="${classes}" target="view" inheritAll="false">
-      <property name="dbs" value="on"/>
-    </ant>
-  </target>
-
-  <target name="clean" description="Delete backup files">
-    <ant dir="${classes}" target="main-clean" inheritAll="false"/>
-  </target>
-
-  <target name="cleanclass" depends="clean">
-    <ant dir="${classes}" target="main-cleanclass" inheritAll="false"/>
-  </target>
-
-  <target name="cleandist" depends="cleanclass">
-    <delete file="${bin}/jhove.jar"/>
-    <delete file="${bin}/jhove-handler.jar"/>
-    <delete file="${bin}/jhove-module.jar"/>
-    <delete file="${bin}/JhoveApp.jar"/>
-    <delete file="${bin}/JhoveView.jar"/>
-  </target>
-
-  <target name="javadoc">
-    <javadoc sourcepath="${classes}" destdir="${doc}"
-             windowtitle="JHOVE Documentation"
-             Overview="${classes}/overview.html">
-      <package name="edu.harvard.hul.ois.jhove"/>
-      <package name="edu.harvard.hul.ois.jhove.handler"/>
-      <package name="edu.harvard.hul.ois.jhove.handler.audit"/>
-      <package name="edu.harvard.hul.ois.jhove.module"/>
-      <package name="edu.harvard.hul.ois.jhove.module.aiff"/>
-      <package name="edu.harvard.hul.ois.jhove.module.gif"/>
-      <package name="edu.harvard.hul.ois.jhove.module.html"/>
-      <package name="edu.harvard.hul.ois.jhove.module.iff"/>
-      <package name="edu.harvard.hul.ois.jhove.module.jpeg"/>
-      <package name="edu.harvard.hul.ois.jhove.module.jpeg2000"/>
-      <package name="edu.harvard.hul.ois.jhove.module.pdf"/>
-      <package name="edu.harvard.hul.ois.jhove.module.tiff"/>
-      <package name="edu.harvard.hul.ois.jhove.module.wave"/>
-      <package name="edu.harvard.hul.ois.jhove.module.xml"/>
-      <package name="edu.harvard.hul.ois.jhove.viewer"/>
-    </javadoc>
-  </target>
-</project>

jhove/conf/README

@@ -1,63 +0,0 @@
-JHOVE - JSTOR/Harvard Object Validation Environment
-Copyright 2003-2007 by JSTOR and the President and Fellows of Harvard College
-JHOVE is made available under the GNU General Public License (see the file
-LICENSE for details)
-
-Rev. 2007-08-30
-
-Edit the configuration file, jhove.conf, and set the JHOVE home
-directory:
-
-    <jhoveHome>jhove-home-directory</jhoveHome>
-
-and temporary directory:
-
-    <tempDirectory>temporary-directory</tempDirectory>
-
-On most Unix systems, a reasonable temporary directory is "/var/tmp";
-on Windows, "C:\temp".
-
-The optional
-
-    <bufferSize>buffer-size</bufferSize>
-
-element defines the buffer size used for buffer I/O operations.
-
-The optional
-
-    <mixVersion>1.0</mixVersion>
-
-element specifies that the XML output handler should conform to the
-MIX 1.0 schema.  The default behavior is for handler output to conform
-to the MIX 0.2 schema.
-
-The optional
-
-    <sigBytes>n</sigBytes>
-
-element specifies that JHOVE modules will look for format signatures
-in the first <n> bytes of the file.  The default value is 1024.
-
-All class names must be fully qualified with their package name:
-
-    <module>
-      <class>fully-package-qualified-class-name</class>
-      <init>optional-initialization-argument</init>
-      <param>optional-invocation-argument</param>
-    </module>
-
-The optional <init> argument is passed to the module once at the time
-its class is instantiated.  See module-specific documentation for a
-description of any initialization options.
-
-The optional <param> argument is passed to the module every time it is
-invoked.  See module-specific documentation for a description of any
-invocation options.
-
-The order in which format modules are defined is important; when
-performing a format identification operation, JHOVE will search for a
-matching module in the order in which the modules are defined in the
-configuration file. In general, the modules for more generic formats
-should come later in the list. For example, the standard module ASCII
-should be defined before the UTF-8 module, since all ASCII objects
-are, by definition, UTF-8 objects, but not vice versa.

jhove/conf/jhove-byteoffset=true.conf

@@ -1,47 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<jhoveConfig version="1.0"
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
- xmlns="http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig"
- xsi:schemaLocation="http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig
-                     http://hul.harvard.edu/ois/xml/xsd/jhove/1.6/jhoveConfig.xsd">
- <jhoveHome>/users/stephen/projects/jhove</jhoveHome>
- <defaultEncoding>utf-8</defaultEncoding>
- <tempDirectory>/var/tmp</tempDirectory>
- <bufferSize>131072</bufferSize>
- <mixVersion>1.0</mixVersion>
- <sigBytes>1024</sigBytes>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.AiffModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.WaveModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.PdfModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.Jpeg2000Module</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.JpegModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.GifModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.TiffModule</class>
-  <param>byteoffset=true</param>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.XmlModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.HtmlModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.AsciiModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.Utf8Module</class>
- </module>
-</jhoveConfig>

jhove/conf/jhove-withTextMD.conf

@@ -1,51 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<jhoveConfig version="1.0"
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
- xmlns="http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig"
- xsi:schemaLocation="http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig
-                     http://hul.harvard.edu/ois/xml/xsd/jhove/1.6/jhoveConfig.xsd">
- <jhoveHome>/users/stephen/projects/jhove</jhoveHome>
- <defaultEncoding>utf-8</defaultEncoding>
- <tempDirectory>/var/tmp</tempDirectory>
- <bufferSize>131072</bufferSize>
- <mixVersion>1.0</mixVersion>
- <sigBytes>1024</sigBytes>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.AiffModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.WaveModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.PdfModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.Jpeg2000Module</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.JpegModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.GifModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.TiffModule</class>
-  <param>byteoffset=true</param>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.XmlModule</class>
-  <param>withTextMD=true</param>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.HtmlModule</class>
-  <param>withTextMD=true</param>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.AsciiModule</class>
-  <param>withTextMD=true</param>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.Utf8Module</class>
-  <param>withTextMD=true</param>
- </module>
-</jhoveConfig>

jhove/conf/jhove.conf

@@ -1,45 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<jhoveConfig version="1.0"
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
- xmlns="http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig"
- xsi:schemaLocation="http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig
-                     http://hul.harvard.edu/ois/xml/xsd/jhove/1.6/jhoveConfig.xsd">
- <jhoveHome>./jhove/</jhoveHome>
- <defaultEncoding>utf-8</defaultEncoding>
- <tempDirectory>/var/tmp</tempDirectory>
- <bufferSize>131072</bufferSize>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.AiffModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.WaveModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.PdfModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.Jpeg2000Module</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.JpegModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.GifModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.TiffModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.XmlModule</class>
-  <param>schema=http://www.example.com/schema;/home/schemas/exampleschema.xsd</param>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.HtmlModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.AsciiModule</class>
- </module>
- <module>
-  <class>edu.harvard.hul.ois.jhove.module.Utf8Module</class>
- </module>
-</jhoveConfig>

jhove/configure.pl

@@ -1,88 +0,0 @@
-#!/usr/bin/perl
-
-########################################################################
-# Jhove - JSTOR/Harvard Object Validation Environment
-# Copyright 2004 by JSTOR and the President and Fellows of Harvard College
-#
-# A Perl script for plugging local path information into the
-# various script files of JHOVE, as well as conf/jhove.conf.
-#
-# This is configured only for Unix (including OS X).
-#
-#    Usage: configure.pl jhove_home_directory [java_home_directory [java_runtime_directory]]
-#
-#    If invoked with no arguments, it will output a usage message.
-#
-########################################################################
-use File::Copy;
-
-sub mung {
-    my $f = $_[0];
-    my $bak = $f . "~";
-    #If there is no backup file, copy the file to the
-    #backup.  Otherwise work from the backup.
-    if (!(-e $bak)) {
-        rename ($f, $bak);
-    }
-    open (INFILE, $bak);
-    open (OUTFILE, ">" . $f);
-
-    #Walks through each line of file, making substitutions.
-    #Remember that the JAVA_HOME and JAVA arguments are optional.
-    while (<INFILE>) {
-        s/^JHOVE_HOME=.*/JHOVE_HOME=$ARGV[0]/;
-        if ($narg >= 2) {
-            s/^JAVA_HOME=.*/JAVA_HOME=$ARGV[1]/;
-        }
-        if ($narg >= 3) {
-            s/^JAVA=.*/JAVA=$ARGV[2]/;
-        }
-        print OUTFILE;
-    }
-    close (INFILE);
-    close (OUTFILE);
-    if (-e $f) {
-        print ("Fixed " . $f . "\n");
-    }
-}
-
-
-$narg = $#ARGV + 1;
-if ($narg <= 0) {
-    print "Usage: configure.pl jhove_home_directory [java_home_directory [java_runtime_directory]]\n";
-    exit;
-}
-print "JHOVE_HOME will be set to " . $ARGV[0] . "\n";
-if ($narg >= 2) {
-    print "JAVA_HOME will be set to " . $ARGV[1] . "\n";
-}
-if ($narg >= 3) {
-    print "JAVA will be set to " . $ARGV[2] . "\n";
-}
-mung ("jhove");
-mung ("adump");
-mung ("gdump");
-mung ("jdump");
-mung ("j2dump");
-mung ("pdump");
-mung ("tdump");
-mung ("wdump");
-
-#Fix up the config file.  We assume that the <jhoveHome>
-#element is all on one line.
-if (!(-e "conf/jhove.conf~")) {
-    rename ("conf/jhove.conf", "conf/jhove.conf~");
-}
-open (INFILE, "conf/jhove.conf~");
-open (OUTFILE, ">conf/jhove.conf");
-while (<INFILE>) {
-    s!<jhoveHome>.*</jhoveHome>!<jhoveHome>$ARGV[0]</jhoveHome>!;
-    print OUTFILE;
-}
-close (INFILE);
-close (OUTFILE);
-if (-e "conf/jhove.conf") {
-    print "Fixed conf/jhove.conf\n";
-}
-exit;
-

jhove/gdump

@@ -1,37 +0,0 @@
-#!/bin/sh
-
-########################################################################
-# gdump - JSTOR/Harvard Object Validation Environment
-# Copyright 2004-2005 by the President and Fellows of Harvard College
-# JHOVE is made available under the GNU General Public License (see the
-# file LICENSE for details)
-#
-# Driver script for the GIF dump utility
-#
-# Usage: gdump file
-#
-# where  file  is a GIF file
-#
-# Configuration constants:
-
-JHOVE_HOME=/users/stephen/projects/jhove
-
-JAVA_HOME=/usr/java      # Java JRE directory
-JAVA=$JAVA_HOME/bin/java # Java interpreter
-
-EXTRA_JARS=              # Extra .jar files to add to CLASSPATH
-
-# NOTE: Nothing below this line should be edited
-########################################################################
-
-CP=${JHOVE_HOME}/bin/JhoveApp.jar:${EXTRA_JARS}
-
-# Retrieve a copy of all command line arguments to pass to the application.
-
-ARGS=""
-for ARG do
-    ARGS="$ARGS $ARG"
-done
-
-# Set the CLASSPATH and invoke the Java loader.
-${JAVA} -classpath $CP GDump $ARGS

jhove/j2dump

@@ -1,37 +0,0 @@
-#!/bin/sh
-
-########################################################################
-# j2dump - JSTOR/Harvard Object Validation Environment
-# Copyright 2004-2005 by the President and Fellows of Harvard College
-# JHOVE is made available under the GNU General Public License (see the
-# file LICENSE for details)
-#
-# Driver script for the JPEG 2000 dump utility
-#
-# Usage: j2dump file
-#
-# where  file  is a JPEG file
-#
-# Configuration constants:
-
-JHOVE_HOME=/users/stephen/projects/jhove
-
-JAVA_HOME=/usr/java      # Java JRE directory
-JAVA=$JAVA_HOME/bin/java # Java interpreter
-
-EXTRA_JARS=              # Extra .jar files to add to CLASSPATH
-
-# NOTE: Nothing below this line should be edited
-########################################################################
-
-CP=${JHOVE_HOME}/bin/JhoveApp.jar:${EXTRA_JARS}
-
-# Retrieve a copy of all command line arguments to pass to the application.
-
-ARGS=""
-for ARG do
-    ARGS="$ARGS $ARG"
-done
-
-# Set the CLASSPATH and invoke the Java loader.
-${JAVA} -classpath $CP J2Dump $ARGS

jhove/jdump

@@ -1,37 +0,0 @@
-#!/bin/sh
-
-########################################################################
-# jdump - JSTOR/Harvard Object Validation Environment
-# Copyright 2004-2005 by the President and Fellows of Harvard College
-# JHOVE is made available under the GNU General Public License (see the
-# file LICENSE for details)
-#
-# Driver script for the JPEG dump utility
-#
-# Usage: jdump file
-#
-# where  file  is a JPEG file
-#
-# Configuration constants:
-
-JHOVE_HOME=/users/stephen/projects/jhove
-
-JAVA_HOME=/usr/java      # Java JRE directory
-JAVA=$JAVA_HOME/bin/java # Java interpreter
-
-EXTRA_JARS=              # Extra .jar files to add to CLASSPATH
-
-# NOTE: Nothing below this line should be edited
-########################################################################
-
-CP=${JHOVE_HOME}/bin/JhoveApp.jar:${EXTRA_JARS}
-
-# Retrieve a copy of all command line arguments to pass to the application.
-
-ARGS=""
-for ARG do
-    ARGS="$ARGS $ARG"
-done
-
-# Set the CLASSPATH and invoke the Java loader.
-${JAVA} -classpath $CP JDump $ARGS

jhove/jhove

@@ -1,58 +0,0 @@
-#!/bin/sh
-
-########################################################################
-# JHOVE - JSTOR/Harvard Object Validation Environment
-# Copyright 2003-2005 by JSTOR and the President and Fellows of Harvard College
-# JHOVE is made available under the GNU General Public License (see the
-# file LICENSE for details)
-#
-# Usage: jhove [-c config] [-m module] [-h handler] [-e encoding] [-H handler]
-#              [-o output] [-x saxclass] [-t tempdir] [-b bufsize]
-#              [-l loglevel] [[-krs] dir-file-or-uri [...]]
-#
-# where -c config   Configuration file pathname
-#       -m module   Module name
-#       -h handler  Output handler name (defaults to TEXT)
-#       -e encoding Character encoding of output handler (defaults to UTF-8)
-#       -H handler  About handler name
-#       -o output   Output file pathname (defaults to standard output)
-#       -x saxclass SAX parser class (defaults to J2SE 1.4 default)
-#       -t tempdir  Temporary directory in which to create temporary files
-#       -b bufsize  Buffer size for buffered I/O (defaults to J2SE 1.4 default)
-#       -k          Calculate CRC32, MD5, and SHA-1 checksums
-#       -r          Display raw data flags, not textual equivalents
-#       -s          Format identification based on internal signatures only
-#       dir-file-or-uri Directory, file pathname or URI of formatted content
-#
-# CHANGE for JHOVE 1.8:
-# You no longer have to figure out where JAVA_HOME is; that's the
-# operating system's job. If the OS tells you it can't find Java, 
-# adjust your shell's path or revert to the old way (commented out).
-# Configuration constants:
-
-#JHOVE_HOME=/users/gary/dev/jhove
-JHOVE_HOME=[fill in path to jhove directory]
-
-JAVA_HOME=/usr/java      # Java JRE directory -- change to your local java home
-JAVA=$JAVA_HOME/bin/java # Java interpreter -- usually won't need change
-
-#XTRA_JARS=/users/stephen/xercesImpl.jar
-EXTRA_JARS=              # Extra .jar files to add to CLASSPATH
-
-# NOTE: Nothing below this line should be edited
-########################################################################
-
-CP=${JHOVE_HOME}/bin/JhoveApp.jar:${EXTRA_JARS}
-
-# Retrieve a copy of all command line arguments to pass to the application.
-
-ARGS=""
-for ARG do
-    ARGS="$ARGS $ARG"
-done
-
-# Set the CLASSPATH and invoke the Java loader.
-#{JAVA} -classpath $CP Jhove $ARGS -x org.apache.xerces.parsers.SAXParser
-#${JAVA} -classpath $CP Jhove $ARGS
-# New way, doesn't require you to use JAVA_HOME.
-java -classpath $CP Jhove $ARGS

jhove/jhove.tmpl

@@ -1,54 +0,0 @@
-#!/bin/sh
-
-########################################################################
-# JHOVE - JSTOR/Harvard Object Validation Environment
-# Copyright 2003-2004 by JSTOR and the President and Fellows of Harvard College
-# JHOVE is made available under the GNU General Public License (see the
-# file LICENSE for details)
-#
-# Copy jhove.tmpl to jhove, and replace the value of JHOVE_HOME with
-# the path to your jhove directory.
-#
-# Usage: jhove [-c config] [-m module [-p param]] [-h handler [-P param]]
-#              [-e encoding] [-H handler] [-o output] [-x saxclass]
-#              [-t tempdir] [-b bufsize] [[-krs] dir-file-or-uri [...]]
-#
-# where -c config   Configuration file pathname
-#       -m module   Module name
-#       -p param    Module-specific parameter
-#       -h handler  Output handler name (defaults to TEXT)
-#       -P param    Handler-specific parameter
-#       -o output   Output file pathname (defaults to standard output)
-#       -x saxclass SAX parser class (defaults to J2SE 1.4 default)
-#       -t tempdir  Temporary directory in which to create temporary files
-#       -b bufsize  Buffer size for buffered I/O (defaults to J2SE 1.4 default)
-#       -k          Calculate CRC32, MD5, and SHA-1 checksums
-#       -r          Display raw data flags, not textual equivalents
-#       -s          Format identification based on internal signatures only
-#       dir-file-or-uri Directory, file pathname or URI of formatted content
-#
-# Configuration constants:
-
-JHOVE_HOME=[your directory path]/jhove
-
-JAVA_HOME=/usr/java
-JAVA=/usr/bin/java
-
-#XTRA_JARS=/users/stephen/xercesImpl.jar
-EXTRA_JARS=              # Extra .jar files to add to CLASSPATH
-
-# NOTE: Nothing below this line should be edited
-########################################################################
-
-CP=${JHOVE_HOME}/bin/JhoveApp.jar:${EXTRA_JARS}
-
-# Retrieve a copy of all command line arguments to pass to the application.
-
-ARGS=""
-for ARG do
-    ARGS="$ARGS $ARG"
-done
-
-# Set the CLASSPATH and invoke the Java loader.
-#{JAVA} -classpath $CP Jhove $ARGS -x org.apache.xerces.parsers.SAXParser
-${JAVA} -classpath $CP Jhove $ARGS

jhove/jhove_bat.tmpl

@@ -1,60 +0,0 @@
-@ECHO OFF
-REM JHOVE - JSTOR/Harvard Object Validation Environment
-REM Copyright 2003-2005 by JSTOR and the President and Fellows of Harvard College
-REM JHOVE is made available under the GNU General Public License (see the
-REM file LICENSE for details)
-REM
-REM Usage: jhove [-c config] [-m module] [-h handler] [-e encoding]
-REM              [-H handler] [-o output] [-x saxclass] [-t tempdir]
-REM              [-b bufsize] [-l loglevel] [[-krs] dir-file-or-uri [...]]
-REM
-REM For Windows systems, copy jhove_bat.tmpl to jhove.bat and change
-REM the value of JHOVE_HOME to the path to your jhove directory.
-REM
-REM where -c config   Configuration file pathname
-REM       -m module   Module name
-REM       -h handler  Output handler name (defaults to TEXT)
-REM       -e encoding Character encoding of output handler (defaults to UTF-8)
-REM       -H handler  About handler name
-REM       -o output   Output file pathname (defaults to standard output)
-REM       -x saxclass SAX parser class (defaults to J2SE 1.4 default)
-REM       -t tempdir  Temporary directory in which to create temporary files
-REM       -b bufsize  Buffer size for buffered I/O (defaults to J2SE default)
-REM       -l loglevel Logging level
-REM       -k          Calculate CRC32, MD5, and SHA-1 checksums
-REM       -r          Display raw data flags, not textual equivalents
-REM       -s          Format identification based on internal signatures only
-REM       dir-file-or-uri Directory, file pathname, or URI of formatted content
-REM
-REM Configuration constants:
-REM JHOVE_HOME Jhove installation directory
-REM JAVA_HOME  Java JRE directory
-REM JAVA       Java interpreter
-REM EXTRA_JARS Extra jar files to add to CLASSPATH
-
-REM SET JHOVE_HOME="C:\Program Files\jhove"
-SET JHOVE_HOME="[your directory path]\jhove"
-
-SET EXTRA_JARS=
-
-REM NOTE: Nothing below this line should be edited
-REM #########################################################################
-
-
-SET CP=%JHOVE_HOME%\bin\JhoveApp.jar
-IF "%EXTRA_JARS%"=="" GOTO FI
-  SET CP=%CP%:%EXTRA_JARS
-:FI
-
-REM Retrieve a copy of all command line arguments to pass to the application
-
-SET ARGS=
-:WHILE
-IF "%1"=="" GOTO LOOP
-  SET ARGS=%ARGS% %1
-  SHIFT
-  GOTO WHILE
-:LOOP
-
-REM Set the CLASSPATH and invoke the Java loader
-JAVA -classpath %CP% Jhove %ARGS%

jhove/md5.pl

@@ -1,14 +0,0 @@
-#!/usr/bin/perl -w
-
-# Generate MD5 checksum
-
-use Digest::MD5;
-
-die "usage: md5.pl file\n" if $#ARGV < 0;
-
-open (FILE, "<$ARGV[0]") or die "can't open file\"$ARGV[0]\"!\n";
-$ctx = Digest::MD5->new->addfile (*FILE);
-close (FILE);
-$digest = $ctx->hexdigest;
-
-print "$digest\n";

jhove/packagejhove.sh

@@ -1,44 +0,0 @@
-#!/bin/sh
-#DO NOT RUN THIS ON A DEVELOPEMENT DIRECTORY, ONLY ON A 
-#CHECKED-OUT COPY TO BE PACKAGED!
-
-if [ "$1" = "" ]; then
- echo "Usage: packagejhove.sh [version]"
- echo "e.g., packagejhove.sh 1_8"
- exit 1
-fi
-
-echo "This script will prepare your directory for uploading."
-echo "DO NOT RUN IT unless you're a developer and know what"
-echo "you are doing. "
-
-echo "Start in the top-level directory of the JHOVE checkout."
-echo "Run ant and ant javadoc and do any necessary testing and"
-echo "committing before running this script."
-echo 
-echo
-
-echo "To continue, enter the secret phrase."
-read OATH
-if [ "$OATH" != "I solemnly swear that I am up to no good" ]; then
- exit 1
-fi
-
-cd ..
-cat >>CVSS << EOF
-CVS
-.cvsignore
-EOF
-tar cvfX jhove-$1.tar CVSS jhove
-gzip jhove-$1.tar
-cp -r jhove jhove-zip
-cd jhove-zip
-find . \( -name CVS -o -name .cvsignore \) -exec rm -r {} \;	
-cd ..
-mv jhove jhove-ok
-mv jhove-zip jhove
-zip -r jhove-$1.zip jhove
-rm -r jhove
-mv jhove-ok jhove
-jhove/md5.pl jhove-$1.tar.gz >jhove-$1.tar.gz.md5
-jhove/md5.pl jhove-$1.zip >jhove-$1.zip.md5 

jhove/pdump

@@ -1,37 +0,0 @@
-#!/bin/sh
-
-########################################################################
-# pdump - JSTOR/Harvard Object Validation Environment
-# Copyright 2003-2005 by JSTOR and the President and Fellows of Harvard College
-# JHOVE is made available under the GNU General Public License (see the
-# file LICENSE for details)
-#
-# Driver script for the PDF dump utility
-#
-# Usage: pdump file
-#
-# where  file  is a PDF file
-#
-# Configuration constants:
-
-JHOVE_HOME=/users/stephen/projects/jhove
-
-JAVA_HOME=/usr/java      # Java JRE directory
-JAVA=$JAVA_HOME/bin/java # Java interpreter
-
-EXTRA_JARS=              # Extra .jar files to add to CLASSPATH
-
-# NOTE: Nothing below this line should be edited
-########################################################################
-
-CP=${JHOVE_HOME}/bin/JhoveApp.jar:${EXTRA_JARS}
-
-# Retrieve a copy of all command line arguments to pass to the application.
-
-ARGS=""
-for ARG do
-    ARGS="$ARGS $ARG"
-done
-
-# Set the CLASSPATH and invoke the Java loader.
-${JAVA} -classpath $CP PDump $ARGS

jhove/userhome

@@ -1,24 +0,0 @@
-#!/bin/sh
-
-########################################################################
-# userhome - JSTOR/Harvard Object Validation Environment
-# Copyright 2004-2006 by the President and Fellows of Harvard College
-# JHOVE is made available under the GNU General Public License (see the
-# file LICENSE for details)
-#
-# Driver script to display the default Java user.home property
-#
-# Usage: userhome
-#
-# Configuration constants:
-
-JHOVE_HOME=/users/stephen/projects/jhove
-
-JAVA_HOME=/usr/java      # Java JRE directory
-JAVA=$JAVA_HOME/bin/java # Java interpreter
-
-# NOTE: Nothing below this line should be edited
-########################################################################
-
-# Set the CLASSPATH and invoke the Java loader.
-${JAVA} -classpath ${JHOVE_HOME}/classes UserHome

ocrmypdf/__init__.py

@@ -0,0 +1,22 @@
+from enum import IntEnum
+import os
+
+
+class ExitCode(IntEnum):
+    ok = 0
+    bad_args = 1
+    input_file = 2
+    missing_dependency = 3
+    invalid_output_pdfa = 4
+    file_access_error = 5
+    already_done_ocr = 6
+    other_error = 15
+
+
+def get_program(name):
+    envvar = 'OCRMYPDF_' + name.upper()
+    return os.environ.get(envvar, name)
+
+
+def page_number(input_file):
+    return int(os.path.basename(input_file)[0:6])

ocrmypdf/ghostscript.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from tempfile import NamedTemporaryFile
+from subprocess import Popen, PIPE, check_call
+from shutil import copy
+from . import get_program
+
+
+def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
+                  pageno=1):
+    with NamedTemporaryFile(delete=True) as tmp:
+        args_gs = [
+            get_program('gs'),
+            '-dQUIET',
+            '-dBATCH',
+            '-dNOPAUSE',
+            '-sDEVICE=%s' % raster_device,
+            '-dFirstPage=%i' % pageno,
+            '-dLastPage=%i' % pageno,
+            '-o', tmp.name,
+            '-r{0}x{1}'.format(str(xres), str(yres)),
+            input_file
+        ]
+
+        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=PIPE,
+                  universal_newlines=True)
+        stdout, stderr = p.communicate()
+        if stdout:
+            log.debug(stdout)
+        if stderr:
+            log.error(stderr)
+
+        if p.returncode == 0:
+            copy(tmp.name, output_file)
+        else:
+            log.error('Ghostscript rendering failed')
+
+
+def generate_pdfa(pdf_pages, output_file, threads=1):
+    with NamedTemporaryFile(delete=True) as gs_pdf:
+        args_gs = [
+            get_program("gs"),
+            "-dQUIET",
+            "-dBATCH",
+            "-dNOPAUSE",
+            '-dNumRenderingThreads=' + str(threads),
+            "-sDEVICE=pdfwrite",
+            "-dAutoRotatePages=/None",
+            "-sColorConversionStrategy=/RGB",
+            "-sProcessColorModel=DeviceRGB",
+            "-dJPEGQ=95",
+            "-dPDFA=2",
+            "-sPDFACompatibilityPolicy=2",
+            "-sOutputICCProfile=srgb.icc",
+            "-sOutputFile=" + gs_pdf.name,
+        ]
+        args_gs.extend(pdf_pages)
+        check_call(args_gs)
+        copy(gs_pdf.name, output_file)

ocrmypdf/hocrtransform.py

@@ -0,0 +1,230 @@
+#!/usr/bin/env python3
+##############################################################################
+# Copyright (c) 2013-14: fritz-hh from Github
+#   (https://github.com/fritz-hh)
+#
+# Copyright (c) 2010: Jonathan Brinley from Github
+#   (https://github.com/jbrinley/HocrConverter)
+#   Initial version by Jonathan Brinley, jonathanbrinley@gmail.com
+##############################################################################
+from reportlab.pdfgen.canvas import Canvas
+from reportlab.lib.units import inch
+from xml.etree import ElementTree
+from PIL import Image
+from collections import namedtuple
+import re
+import argparse
+
+
+Rect = namedtuple('Rect', ['x1', 'y1', 'x2', 'y2'])
+
+
+class HocrTransformError(Exception):
+    pass
+
+
+class HocrTransform():
+
+    """
+    A class for converting documents from the hOCR format.
+    For details of the hOCR format, see:
+    http://docs.google.com/View?docid=dfxcv4vc_67g844kf
+    """
+
+    def __init__(self, hocrFileName, dpi):
+        self.dpi = dpi
+        self.boxPattern = re.compile(r'bbox((\s+\d+){4})')
+
+        self.hocr = ElementTree.parse(hocrFileName)
+
+        # if the hOCR file has a namespace, ElementTree requires its use to
+        # find elements
+        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
+        self.xmlns = ''
+        if matches:
+            self.xmlns = matches.group(1)
+
+        # get dimension in pt (not pixel!!!!) of the OCRed image
+        self.width, self.height = None, None
+        for div in self.hocr.findall(
+                ".//%sdiv[@class='ocr_page']" % (self.xmlns)):
+            coords = self.element_coordinates(div)
+            pt_coords = self.pt_from_pixel(coords)
+            self.width = pt_coords.x2 - pt_coords.x1
+            self.height = pt_coords.y2 - pt_coords.y1
+            # there shouldn't be more than one, and if there is, we don't want
+            # it
+            break
+        if self.width is None or self.height is None:
+            raise HocrTransformError("hocr file is missing page dimensions")
+
+    def __str__(self):
+        """
+        Return the textual content of the HTML body
+        """
+        if self.hocr is None:
+            return ''
+        body = self.hocr.find(".//%sbody" % (self.xmlns))
+        if body:
+            return self._get_element_text(body)
+        else:
+            return ''
+
+    def _get_element_text(self, element):
+        """
+        Return the textual content of the element and its children
+        """
+        text = ''
+        if element.text is not None:
+            text += element.text
+        for child in element.getchildren():
+            text += self._get_element_text(child)
+        if element.tail is not None:
+            text += element.tail
+        return text
+
+    def element_coordinates(self, element):
+        """
+        Returns a tuple containing the coordinates of the bounding box around
+        an element
+        """
+        out = (0, 0, 0, 0)
+        if 'title' in element.attrib:
+            matches = self.boxPattern.search(element.attrib['title'])
+            if matches:
+                coords = matches.group(1).split()
+                out = Rect._make(int(coords[n]) for n in range(4))
+        return out
+
+    def pt_from_pixel(self, pxl):
+        """
+        Returns the quantity in PDF units (pt) given quantity in pixels
+        """
+        return Rect._make(
+            (c / self.dpi * inch) for c in pxl)
+
+    def replace_unsupported_chars(self, s):
+        """
+        Given an input string, returns the corresponding string that:
+        - is available in the helvetica facetype
+        - does not contain any ligature (to allow easy search in the PDF file)
+        """
+        # The 'u' before the character to replace indicates that it is a
+        # unicode character
+        s = s.replace(u"fl", "fl")
+        s = s.replace(u"fi", "fi")
+        return s
+
+    def to_pdf(self, outFileName, imageFileName=None, showBoundingboxes=False,
+               fontname="Helvetica", invisibleText=False):
+        """
+        Creates a PDF file with an image superimposed on top of the text.
+        Text is positioned according to the bounding box of the lines in
+        the hOCR file.
+        The image need not be identical to the image used to create the hOCR
+        file.
+        It can have a lower resolution, different color mode, etc.
+        """
+        # create the PDF file
+        # page size in points (1/72 in.)
+        pdf = Canvas(
+            outFileName, pagesize=(self.width, self.height), pageCompression=1)
+
+        # draw bounding box for each paragraph
+        # light blue for bounding box of paragraph
+        pdf.setStrokeColorRGB(0, 1, 1)
+        # light blue for bounding box of paragraph
+        pdf.setFillColorRGB(0, 1, 1)
+        pdf.setLineWidth(0)		# no line for bounding box
+        for elem in self.hocr.findall(
+                ".//%sp[@class='%s']" % (self.xmlns, "ocr_par")):
+
+            elemtxt = self._get_element_text(elem).rstrip()
+            if len(elemtxt) == 0:
+                continue
+
+            pxl_coords = self.element_coordinates(elem)
+            pt = self.pt_from_pixel(pxl_coords)
+
+            # draw the bbox border
+            if showBoundingboxes:
+                pdf.rect(
+                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
+                    fill=1)
+
+        # check if element with class 'ocrx_word' are available
+        # otherwise use 'ocr_line' as fallback
+        elemclass = "ocr_line"
+        if self.hocr.find(
+                ".//%sspan[@class='ocrx_word']" % (self.xmlns)) is not None:
+            elemclass = "ocrx_word"
+
+        # itterate all text elements
+        # light green for bounding box of word/line
+        pdf.setStrokeColorRGB(1, 0, 0)
+        pdf.setLineWidth(0.5)		# bounding box line width
+        pdf.setDash(6, 3)		# bounding box is dashed
+        pdf.setFillColorRGB(0, 0, 0)  # text in black
+        for elem in self.hocr.findall(
+                ".//%sspan[@class='%s']" % (self.xmlns, elemclass)):
+
+            elemtxt = self._get_element_text(elem).rstrip()
+
+            elemtxt = self.replace_unsupported_chars(elemtxt)
+
+            if len(elemtxt) == 0:
+                continue
+
+            pxl_coords = self.element_coordinates(elem)
+            pt = self.pt_from_pixel(pxl_coords)
+
+            # draw the bbox border
+            if showBoundingboxes:
+                pdf.rect(
+                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
+                    fill=0)
+
+            text = pdf.beginText()
+            fontsize = pt.y2 - pt.y1
+            text.setFont(fontname, fontsize)
+            if invisibleText:
+                text.setTextRenderMode(3)  # Invisible (indicates OCR text)
+
+            # set cursor to bottom left corner of bbox (adjust for dpi)
+            text.setTextOrigin(pt.x1, self.height - pt.y2)
+
+            # scale the width of the text to fill the width of the bbox
+            text.setHorizScale(
+                100 * (pt.x2 - pt.x1) / pdf.stringWidth(
+                    elemtxt, fontname, fontsize))
+
+            # write the text to the page
+            text.textLine(elemtxt)
+            pdf.drawText(text)
+
+        # put the image on the page, scaled to fill the page
+        if imageFileName is not None:
+            pdf.drawImage(imageFileName, 0, 0,
+                          width=self.width, height=self.height)
+
+        # finish up the page and save it
+        pdf.showPage()
+        pdf.save()
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
+    parser.add_argument('-b', '--boundingboxes', action="store_true",
+                        default=False, help='Show bounding boxes borders')
+    parser.add_argument('-r', '--resolution', type=int,
+                        default=300,
+                        help='Resolution of the image that was OCRed')
+    parser.add_argument('-i', '--image', default=None,
+                        help='Path to the image to be placed above the text')
+    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
+    parser.add_argument(
+        'outputfile', help='Path to the PDF file to be generated')
+    args = parser.parse_args()
+
+    hocr = HocrTransform(args.hocrfile, args.resolution)
+    hocr.to_pdf(args.outputfile, args.image, args.boundingboxes)

ocrmypdf/leptonica.py

@@ -0,0 +1,308 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+#
+# © 2013-15: jbarlow83 from Github (https://github.com/jbarlow83)
+#
+#
+# Use Leptonica to detect find and remove page skew.  Leptonica uses the method
+# of differential square sums, which its author claim is faster and more robust
+# than the Hough transform used by ImageMagick.
+
+from __future__ import print_function, absolute_import, division
+import argparse
+import sys
+import os
+import logging
+from tempfile import TemporaryFile
+from ctypes.util import find_library
+from .lib._leptonica import ffi
+from functools import lru_cache
+
+lept = ffi.dlopen(find_library('lept'))
+
+logger = logging.getLogger(__name__)
+
+
+def stderr(*objs):
+    """Python 2/3 compatible print to stderr.
+    """
+    print("leptonica.py:", *objs, file=sys.stderr)
+
+
+class LeptonicaErrorTrap(object):
+    """Context manager to trap errors reported by Leptonica.
+
+    Leptonica's error return codes are unreliable to the point of being
+    almost useless.  It does, however, write errors to stderr provided that is
+    not disabled at its compile time.  Fortunately this is done using error
+    macros so it is very self-consistent.
+
+    This context manager redirects stderr to a temporary file which is then
+    read and parsed for error messages.  As a side benefit, debug messages
+    from Leptonica are also suppressed.
+
+    """
+    def __enter__(self):
+        self.tmpfile = TemporaryFile()
+
+        # Save the old stderr, and redirect stderr to temporary file
+        self.old_stderr_fileno = os.dup(sys.stderr.fileno())
+        os.dup2(self.tmpfile.fileno(), sys.stderr.fileno())
+        return
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        # Restore old stderr
+        os.dup2(self.old_stderr_fileno, sys.stderr.fileno())
+
+        # Get data from tmpfile (in with block to ensure it is closed)
+        with self.tmpfile as tmpfile:
+            tmpfile.seek(0)  # Cursor will be at end, so move back to beginning
+            leptonica_output = tmpfile.read().decode(errors='replace')
+
+        # If there are Python errors, let them bubble up
+        if exc_type:
+            logger.warning(leptonica_output)
+            return False
+
+        # If there are Leptonica errors, wrap them in Python excpetions
+        if 'Error' in leptonica_output:
+            if 'image file not found' in leptonica_output:
+                raise FileNotFoundError()
+            if 'pixWrite: stream not opened' in leptonica_output:
+                raise LeptonicaIOError()
+            raise LeptonicaError(leptonica_output)
+
+        return False
+
+
+class LeptonicaError(Exception):
+    pass
+
+
+class LeptonicaIOError(LeptonicaError):
+    pass
+
+
+class Pix:
+    def __init__(self, cpix):
+        self.cpix = ffi.gc(cpix, Pix._pix_destroy)
+
+    def __repr__(self):
+        if self.cpix:
+            s = "<leptonica.Pix image size={0}x{1} depth={2} at 0x{3:x}>"
+            return s.format(self.cpix.w, self.cpix.h, self.cpix.d,
+                            int(ffi.cast("intptr_t", self.cpix)))
+        else:
+            return "<leptonica.Pix image NULL>"
+
+    @classmethod
+    def read(cls, filename):
+        """Load an image file into a PIX object.
+
+        Leptonica can load TIFF, PNM (PBM, PGM, PPM), PNG, and JPEG.  If
+        loading fails then the object will wrap a C null pointer.
+        """
+        with LeptonicaErrorTrap():
+            return cls(lept.pixRead(
+                filename.encode(sys.getfilesystemencoding())))
+
+    def write_implied_format(
+            self, filename, jpeg_quality=0, jpeg_progressive=0):
+        """Write pix to the filename, with the extension indicating format.
+
+        jpeg_quality -- quality (iff JPEG; 1 - 100, 0 for default)
+        jpeg_progressive -- (iff JPEG; 0 for baseline seq., 1 for progressive)
+        """
+        fileroot, extension = os.path.splitext(filename)
+        fix_pnm = False
+        if extension.lower() in ('.pbm', '.pgm', '.ppm'):
+            # Leptonica does not process handle these extensions correctly, but
+            # does handle .pnm correctly.  Add another .pnm suffix.
+            filename += '.pnm'
+            fix_pnm = True
+
+        with LeptonicaErrorTrap():
+            lept.pixWriteImpliedFormat(
+                filename.encode(sys.getfilesystemencoding()),
+                self.cpix, jpeg_quality, jpeg_progressive)
+
+        if fix_pnm:
+            from shutil import move
+            move(filename, filename[:-4])   # Remove .pnm suffix
+
+    def deskew(self, reduction_factor=0):
+        """Returns the deskewed pix object.
+
+        A clone of the original is returned when the algorithm cannot find a
+        skew angle with sufficient confidence.
+
+        reduction_factor -- amount to downsample (0 for default) when searching
+            for skew angle
+        """
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixDeskew(self.cpix, reduction_factor))
+
+    def scale(self, scalex, scaley):
+        "Returns the pix object rescaled according to the proportions given."
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixScale(self.cpix, scalex, scaley))
+
+    def rotate180(self):
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixRotate180(ffi.NULL, self.cpix))
+
+    def find_skew(self):
+        """Returns a tuple (deskew angle in degrees, confidence value).
+
+        Returns (None, None) if no angle is available.
+        """
+        with LeptonicaErrorTrap():
+            angle = ffi.new('float *', 0.0)
+            confidence = ffi.new('float *', 0.0)
+            result = lept.pixFindSkew(self.cpix, angle, confidence)
+            if result == 0:
+                return (angle[0], confidence[0])
+            else:
+                return (None, None)
+
+    @staticmethod
+    def correlation_binary(pix1, pix2):
+        if getLeptonicaVersion() < 'leptonica-1.72':
+            # Older versions of Leptonica (pre-1.72) have a buggy
+            # implementation of pixCorrelationBinary that overflows on larger
+            # images.
+            pix1_count = ffi.new('l_int32 *', 0)
+            pix2_count = ffi.new('l_int32 *', 0)
+            pixn_count = ffi.new('l_int32 *', 0)
+            tab8 = lept.makePixelSumTab8()  # Small memory leak on each call
+
+            lept.pixCountPixels(pix1.cpix, pix1_count, tab8)
+            lept.pixCountPixels(pix2.cpix, pix2_count, tab8)
+            pixn = Pix(lept.pixAnd(ffi.NULL, pix1.cpix, pix2.cpix))
+            lept.pixCountPixels(pixn.cpix, pixn_count, tab8)
+
+            # Python converts these int32s to larger units as needed
+            # to avoid overflow. Overflow happens easily here.
+            correlation = (
+                    (pixn_count[0] * pixn_count[0]) /
+                    (pix1_count[0] * pix2_count[0])
+                    )
+            return correlation
+        else:
+            correlation = ffi.new('float *', 0.0)
+            result = lept.pixCorrelationBinary(pix1.cpix, pix2.cpix,
+                                               correlation)
+            if result != 0:
+                raise LeptonicaError("Correlation failed")
+            return correlation[0]
+
+    @staticmethod
+    def _pix_destroy(pix):
+        ptr_to_pix = ffi.new('PIX **', pix)
+        lept.pixDestroy(ptr_to_pix)
+        # print('pix destroy ' + repr(pix))
+
+
+@lru_cache(maxsize=1)
+def getLeptonicaVersion():
+    """Get Leptonica version string.
+
+    Caveat: Leptonica expects the caller to free this memory.  We don't,
+    since that would involve binding to libc to access libc.free(),
+    a pointless effort to reclaim 100 bytes of memory.
+    """
+    return ffi.string(lept.getLeptonicaVersion()).decode()
+
+
+def deskew(infile, outfile, dpi):
+    try:
+        pix_source = Pix.read(infile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open file: %s" % infile)
+
+    if dpi < 150:
+        reduction_factor = 1  # Don't downsample too much if DPI is already low
+    else:
+        reduction_factor = 0  # Use default
+    pix_deskewed = pix_source.deskew(reduction_factor)
+
+    try:
+        pix_deskewed.write_implied_format(outfile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(
+        description="Python wrapper to access Leptonica")
+
+    subparsers = parser.add_subparsers(title='commands',
+                                       description='supported operations')
+
+    parser_deskew = subparsers.add_parser('deskew')
+    parser_deskew.add_argument('-r', '--dpi', dest='dpi', action='store',
+                               type=int, default=300, help='input resolution')
+    parser_deskew.add_argument('infile', help='image to deskew')
+    parser_deskew.add_argument('outfile', help='deskewed output image')
+    parser_deskew.set_defaults(func=deskew)
+
+    args = parser.parse_args()
+
+    if getLeptonicaVersion() != u'leptonica-1.69':
+        print("Unexpected leptonica version: %s" % getLeptonicaVersion())
+
+    args.func(args)
+
+
+def _test_output(mode, extension, im_format):
+    from PIL import Image
+    from tempfile import NamedTemporaryFile
+
+    with NamedTemporaryFile(prefix='test-lept-pnm', suffix=extension, delete=True) as tmpfile:
+        im = Image.new(mode=mode, size=(100, 100))
+        im.save(tmpfile)
+
+        pix = pixRead(tmpfile.name)
+        pixWriteImpliedFormat(tmpfile.name, pix)
+        pixDestroy(pix)
+
+        im_roundtrip = Image.open(tmpfile.name)
+        assert im_roundtrip.mode == im.mode, "leptonica mode differs"
+        assert im_roundtrip.format == im_format, \
+            "{0}: leptonica produced a {1}".format(
+                extension,
+                im_roundtrip.format)
+
+
+def test_pnm_output():
+    params = [['1', '.pbm', 'PPM'], ['L', '.pgm', 'PPM'],
+              ['RGB', '.ppm', 'PPM']]
+    for param in params:
+        _test_output(*param)
+
+
+def test_skew_angle():
+    from PIL import Image, ImageDraw
+    from tempfile import NamedTemporaryFile
+
+    im = Image.new(mode='1', size=(1000, 1000), color=1)
+
+    draw = ImageDraw.Draw(im)
+    for n in range(20):
+        draw.line([(50, 25 + 50*n), (950, 25 + 50*n)], width=1)
+    del draw
+
+    test_angles = [0.1 * ang for ang in range(1, 10)] + \
+                  [float(ang) for ang in range(1, 7)]
+    test_angles += [-ang for ang in test_angles]
+    test_angles = sorted(test_angles)
+
+    for rotate_angle in test_angles:
+        rotated_im = im.rotate(rotate_angle)
+        with NamedTemporaryFile(prefix='lept-skew', suffix='.png', delete=True) as tmpfile:
+            rotated_im.save(tmpfile)
+            pix = pixRead(tmpfile.name)
+            angle, confidence = pixFindSkew(pix)
+            print('{0} {1}  {2}'.format(rotate_angle, angle, confidence), file=sys.stderr)
+
+

ocrmypdf/lib/compile_leptonica.py

@@ -0,0 +1,64 @@
+from cffi import FFI
+
+ffi = FFI()
+ffi.set_source("ocrmypdf.lib._leptonica", None)
+ffi.cdef("""
+typedef signed char             l_int8;
+typedef unsigned char           l_uint8;
+typedef short                   l_int16;
+typedef unsigned short          l_uint16;
+typedef int                     l_int32;
+typedef unsigned int            l_uint32;
+typedef float                   l_float32;
+typedef double                  l_float64;
+typedef long long               l_int64;
+typedef unsigned long long      l_uint64;
+
+struct Pix
+{
+    l_uint32             w;           /* width in pixels                   */
+    l_uint32             h;           /* height in pixels                  */
+    l_uint32             d;           /* depth in bits (bpp)               */
+    l_uint32             spp;         /* number of samples per pixel       */
+    l_uint32             wpl;         /* 32-bit words/line                 */
+    l_uint32             refcount;    /* reference count (1 if no clones)  */
+    l_int32              xres;        /* image res (ppi) in x direction    */
+                                      /* (use 0 if unknown)                */
+    l_int32              yres;        /* image res (ppi) in y direction    */
+                                      /* (use 0 if unknown)                */
+    l_int32              informat;    /* input file format, IFF_*          */
+    l_int32              special;     /* special instructions for I/O, etc */
+    char                *text;        /* text string associated with pix   */
+    struct PixColormap  *colormap;    /* colormap (may be null)            */
+    l_uint32            *data;        /* the image data                    */
+};
+typedef struct Pix PIX;
+
+struct PixColormap
+{
+    void            *array;     /* colormap table (array of RGBA_QUAD)     */
+    l_int32          depth;     /* of pix (1, 2, 4 or 8 bpp)               */
+    l_int32          nalloc;    /* number of color entries allocated       */
+    l_int32          n;         /* number of color entries used            */
+};
+typedef struct PixColormap  PIXCMAP;
+""")
+
+ffi.cdef("""
+PIX * pixRead ( const char *filename );
+PIX * pixScale ( PIX *pixs, l_float32 scalex, l_float32 scaley );
+l_int32 pixFindSkew ( PIX *pixs, l_float32 *pangle, l_float32 *pconf );
+l_int32 pixWriteImpliedFormat ( const char *filename, PIX *pix, l_int32 quality, l_int32 progressive );
+void pixDestroy ( PIX **ppix );
+PIX * pixDeskew ( PIX *pixs, l_int32 redsearch );
+char * getLeptonicaVersion (  );
+l_int32 pixCorrelationBinary(PIX *pix1, PIX *pix2, l_float32 *pval);
+PIX *pixRotate180(PIX *pixd, PIX *pixs);
+
+l_int32 pixCountPixels ( PIX *pix, l_int32 *pcount, l_int32 *tab8 );
+PIX * pixAnd ( PIX *pixd, PIX *pixs1, PIX *pixs2 );
+l_int32 * makePixelSumTab8 ( void );
+""")
+
+if __name__ == '__main__':
+    ffi.compile()

ocrmypdf/pageinfo.py

@@ -0,0 +1,166 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from subprocess import Popen, PIPE
+from decimal import Decimal, getcontext
+import re
+import sys
+import PyPDF2 as pypdf
+
+
+FRIENDLY_COLORSPACE = {
+    '/DeviceGray': 'gray',
+    '/CalGray': 'gray',
+    '/DeviceRGB': 'rgb',
+    '/CalRGB': 'rgb',
+    '/DeviceCMYK': 'cmyk',
+    '/Lab': 'lab',
+    '/ICCBased': 'icc',
+    '/Indexed': 'index',
+    '/Separation': 'sep',
+    '/DeviceN': 'devn',
+    '/Pattern': '-'
+}
+
+FRIENDLY_ENCODING = {
+    '/CCITTFaxDecode': 'ccitt',
+    '/DCTDecode': 'jpeg',
+    '/JPXDecode': 'jpx',
+    '/JBIG2Decode': 'jbig2',
+}
+
+FRIENDLY_COMP = {
+    'gray': 1,
+    'rgb': 3,
+    'cmyk': 4,
+    'lab': 3,
+    'index': 1
+}
+
+
+def _page_has_inline_images(page):
+    # PDF always uses \r\n for separator regardless of platform
+    # Really basic heuristic that might trigger the odd false positive
+    # This is only finds the first image and is not quite spec compliant
+    try:
+        contents = page.getContents()
+        data = contents.getData()
+    except AttributeError:
+        # If we can't access the contents or data (empty page?) then there
+        # are no inline images
+        return False
+
+    begin_image, image_data, end_image = False, False, False
+    for data in re.split(b'\s+', data):
+        if data == b'BI':
+            begin_image = True
+        elif data == b'ID':
+            image_data = True
+        elif data == b'EI':
+            end_image = True
+        if all((begin_image, image_data, end_image)):
+            return True
+    return False
+
+
+def _find_page_images(page, pageinfo):
+    try:
+        page['/Resources']['/XObject']
+    except KeyError:
+        return
+
+    # Look for XObject (out of line images)
+    for xobj in page['/Resources']['/XObject']:
+        # PyPDF2 returns the keys as an iterator
+        pdfimage = page['/Resources']['/XObject'][xobj]
+        if pdfimage['/Subtype'] != '/Image':
+            continue
+        if '/ImageMask' in pdfimage:
+            if pdfimage['/ImageMask']:
+                continue
+        image = {}
+        image['width'] = pdfimage['/Width']
+        image['height'] = pdfimage['/Height']
+        image['bpc'] = pdfimage['/BitsPerComponent']
+        if '/Filter' in pdfimage:
+            filter_ = pdfimage['/Filter']
+            if isinstance(filter_, pypdf.generic.ArrayObject):
+                filter_ = filter_[0]
+            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
+        else:
+            image['enc'] = 'image'
+        if '/ColorSpace' in pdfimage:
+            cs = pdfimage['/ColorSpace']
+            if isinstance(cs, pypdf.generic.ArrayObject):
+                cs = cs[0]
+            image['color'] = FRIENDLY_COLORSPACE.get(cs, '-')
+        else:
+            image['color'] = 'jpx' if image['enc'] == 'jpx' else '?'
+
+        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
+        image['dpi_w'] = image['width'] / pageinfo['width_inches']
+        image['dpi_h'] = image['height'] / pageinfo['height_inches']
+        image['dpi'] = (image['dpi_w'] * image['dpi_h']) ** Decimal(0.5)
+        yield image
+
+
+def _page_has_text(pdf, page):
+    # Simple test
+    text = page.extractText()
+    if text.strip() != '':
+        return True
+
+    # More nuanced test to deal with quirks of Tesseract PDF generation
+    # Check if there's a Glyphless font
+    try:
+        font = page['/Resources']['/Font']
+    except KeyError:
+        pass
+    else:
+        font_objects = list(font.keys())
+        for font_object in font_objects:
+            basefont = font[font_object]['/BaseFont']
+            if basefont.endswith('GlyphLessFont'):
+                return True
+
+    return False
+
+
+def _pdf_get_pageinfo(infile, pageno: int):
+    pageinfo = {}
+    pageinfo['pageno'] = pageno
+    pageinfo['images'] = []
+
+    pdf = pypdf.PdfFileReader(infile)
+    page = pdf.pages[pageno]
+
+    pageinfo['has_text'] = _page_has_text(pdf, page)
+
+    width_pt = page.mediaBox.getWidth()
+    height_pt = page.mediaBox.getHeight()
+    pageinfo['width_inches'] = width_pt / Decimal(72.0)
+    pageinfo['height_inches'] = height_pt / Decimal(72.0)
+
+    pageinfo['images'] = [im for im in _find_page_images(page, pageinfo)]
+
+    # Look for inline images
+    if _page_has_inline_images(page):
+        raise NotImplementedError(
+            "Warning: input PDF contains inline images - not supported")
+
+    if pageinfo['images']:
+        xres = max(image['dpi_w'] for image in pageinfo['images'])
+        yres = max(image['dpi_h'] for image in pageinfo['images'])
+        pageinfo['xres'], pageinfo['yres'] = xres, yres
+        pageinfo['width_pixels'] = \
+            int(round(xres * pageinfo['width_inches']))
+        pageinfo['height_pixels'] = \
+            int(round(yres * pageinfo['height_inches']))
+
+    return pageinfo
+
+
+def pdf_get_all_pageinfo(infile):
+    pdf = pypdf.PdfFileReader(infile)
+    getcontext().prec = 6
+    return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]

ocrmypdf/pdfa.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+#
+# Generate a PDFA_def.ps file for Ghostscript >= 9.14
+
+from __future__ import print_function, absolute_import, division
+from string import Template
+from subprocess import Popen, PIPE
+import os
+import codecs
+from . import get_program
+
+
+# This is a template written in PostScript which is needed to create PDF/A
+# files, from the Ghostscript documentation. Lines beginning with % are
+# comments. Python substitution variables have a '$' prefix.
+pdfa_def_template = u"""%!
+% This is a sample prefix file for creating a PDF/A document.
+% Feel free to modify entries marked with "Customize".
+% This assumes an ICC profile to reside in the file (ISO Coated sb.icc),
+% unless the user modifies the corresponding line below.
+
+% Define entries in the document Info dictionary :
+/ICCProfile ($icc_profile)
+def
+
+[ /Title <$title>
+  /Author <$author>
+  /Subject <$subject>
+  /Keywords <$keywords>
+  /Creator <$creator>
+  /DOCINFO pdfmark
+
+% Define an ICC profile :
+
+[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
+[{icc_PDFA}
+<<
+  /N currentpagedevice /ProcessColorModel known {
+    currentpagedevice /ProcessColorModel get dup /DeviceGray eq
+    {pop 1} {
+      /DeviceRGB eq
+      {3}{4} ifelse
+    } ifelse
+  } {
+    (ERROR, unable to determine ProcessColorModel) == flush
+  } ifelse
+>> /PUT pdfmark
+[{icc_PDFA} ICCProfile (r) file /PUT pdfmark
+
+% Define the output intent dictionary :
+
+[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
+[{OutputIntent_PDFA} <<
+  /Type /OutputIntent             % Must be so (the standard requires).
+  /S /GTS_PDFA1                   % Must be so (the standard requires).
+  /DestOutputProfile {icc_PDFA}            % Must be so (see above).
+  /OutputConditionIdentifier ($icc_identifier)
+>> /PUT pdfmark
+[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
+"""
+
+
+def encode_text_string(s: str) -> str:
+    '''Encode text string to hex string for use in a PDF
+
+    From PDF 32000-1:2008 a string object may be included in hexademical form
+    if it is enclosed in angle brackets.  For general Unicode the string should
+    be UTF-16 (big endian) with byte order marks.  A non-hexademical
+    representation is doable but this is preferable since it allows the output
+    Postscript file to be completely ASCII and no escaping of Postscript
+    characters is necessary.
+    '''
+    if s == '':
+        return ''
+    utf16_bytes = s.encode('utf-16be')
+    ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
+    ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
+    return ascii_hex_str
+
+
+def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
+    pdfmark_utf16 = {k: encode_text_string(v) for k, v in pdfmark.items()}
+
+    t = Template(pdfa_def_template)
+    result = t.substitute(icc_profile=icc_profile,
+                          icc_identifier=icc_identifier,
+                          title=pdfmark_utf16.get('title', ''),
+                          author=pdfmark_utf16.get('author', ''),
+                          subject=pdfmark_utf16.get('subject', ''),
+                          creator=pdfmark_utf16.get('creator', ''),
+                          keywords=pdfmark_utf16.get('keywords', ''))
+    return result
+
+
+def _get_postscript_icc_path():
+    "Parse Ghostscript's help message to find where iccprofiles are stored"
+
+    p_gs = Popen([get_program('gs'), '--help'], close_fds=True,
+                 universal_newlines=True,
+                 stdout=PIPE, stderr=PIPE)
+    out, _ = p_gs.communicate()
+    lines = out.splitlines()
+
+    def search_paths(lines):
+        seeking = True
+        for line in lines:
+            if seeking:
+                if line.startswith('Search path'):
+                    seeking = False
+                    continue
+            else:
+                if line.strip().startswith('/'):
+                    yield from (
+                        path.strip() for path in line.split(':')
+                        if path.strip() != '')
+    for root in search_paths(lines):
+        path = os.path.realpath(os.path.join(root, '../iccprofiles'))
+        if os.path.exists(path):
+            return path
+
+    raise FileNotFoundError("Could not find Ghostscript's iccprofiles")
+
+
+def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
+    if icc == 'sRGB':
+        icc_profile = os.path.join(_get_postscript_icc_path(), 'srgb.icc')
+    else:
+        raise NotImplementedError("Only supporting sRGB")
+
+    ps = _get_pdfa_def(icc_profile, icc, pdfmark)
+
+    # Since PostScript might not handle UTF-8 (it's hard to get a clear
+    # answer), insist on ascii
+    with open(target_filename, 'w', encoding='ascii') as f:
+        f.write(ps)

ocrmypdf/qpdf.py

@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from subprocess import CalledProcessError, check_output, STDOUT, check_call
+import sys
+import os
+
+from . import ExitCode, get_program
+
+
+def check(input_file, log):
+    args_qpdf = [
+        get_program('qpdf'),
+        '--check',
+        input_file
+    ]
+
+    try:
+        check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
+    except CalledProcessError as e:
+        if e.returncode == 2:
+            log.error("{0}: not a valid PDF, and could not repair it.".format(
+                    input_file))
+            log.error("Details:")
+            log.error(e.output)
+        elif e.returncode == 3:
+            log.info("qpdf --check returned warnings:")
+            log.info(e.output)
+        else:
+            log.warning(e.output)
+        return False
+    return True
+
+
+def repair(input_file, output_file, log):
+    args_qpdf = [
+        get_program('qpdf'), input_file, output_file
+    ]
+    try:
+        check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
+    except CalledProcessError as e:
+        if e.returncode == 3 and e.output.find("operation succeeded"):
+            log.debug('qpdf found and fixed errors: ' + e.output)
+            log.debug(e.output)
+            return
+
+        if e.returncode == 2 and e.output.find("invalid password"):
+            log.error("{0}: this PDF is password-protected - password must "
+                      "be removed for OCR".format(input_file))
+            sys.exit(ExitCode.input_file)
+        elif e.returncode == 2:
+            log.error("{0}: not a valid PDF, and could not repair it.".format(
+                      input_file))
+            log.error("Details: " + e.output)
+            sys.exit(ExitCode.input_file)
+        else:
+            log.error("{0}: unknown error".format(
+                      input_file))
+            log.error(e.output)
+            sys.exit(ExitCode.unknown)
+
+
+def get_npages(input_file, log):
+    try:
+        pages = check_output(
+            [get_program('qpdf'), '--show-npages', input_file],
+             universal_newlines=True, close_fds=True)
+    except CalledProcessError as e:
+        if e.returncode == 2 and e.output.find('No such file'):
+            log.error(e.output)
+            sys.exit(ExitCode.input_file)
+    return int(pages)
+
+
+def split_pages(input_file, work_folder, npages):
+    """Split multipage PDF into individual pages.
+
+    Incredibly enough, this multiple process approach is about 70 times
+    faster than using Ghostscript.
+    """
+    for n in range(int(npages)):
+        args_qpdf = [
+            get_program('qpdf'), input_file,
+            '--pages', input_file, '{0}'.format(n + 1), '--',
+            os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
+        ]
+        check_call(args_qpdf)

ocrmypdf/tesseract.py

@@ -0,0 +1,226 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+import sys
+import os
+import re
+import shutil
+from functools import lru_cache
+from . import ExitCode, get_program, page_number
+from collections import namedtuple
+
+from subprocess import Popen, PIPE, CalledProcessError, \
+    TimeoutExpired, check_output, STDOUT
+try:
+    from subprocess import DEVNULL
+except ImportError:
+    DEVNULL = open(os.devnull, 'wb')
+
+
+OrientationConfidence = namedtuple(
+    'OrientationConfidence',
+    ('angle', 'confidence'))
+
+HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+  <meta name='ocr-system' content='tesseract 3.02.02' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
+    <p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
+     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>'''
+
+
+@lru_cache(maxsize=1)
+def version():
+    args_tess = [
+        get_program('tesseract'),
+        '--version'
+    ]
+    try:
+        versions = check_output(
+                args_tess, close_fds=True, universal_newlines=True,
+                stderr=STDOUT)
+    except CalledProcessError:
+        print("Could not find Tesseract executable on system PATH.")
+        sys.exit(ExitCode.missing_dependency)
+
+    tesseract_version = re.match(r'tesseract\s(.+)', versions).group(1)
+    return tesseract_version
+
+
+@lru_cache(maxsize=1)
+def languages():
+    args_tess = [
+        get_program('tesseract'),
+        '--list-langs'
+    ]
+    try:
+        langs = check_output(
+                args_tess, close_fds=True, universal_newlines=True,
+                stderr=STDOUT)
+    except CalledProcessError as e:
+        print("Tesseract failed to report available languages.")
+        print("Output from Tesseract:")
+        print("-" * 40)
+        print(e.output)
+        sys.exit(ExitCode.missing_dependency)
+    return set(lang.strip() for lang in langs.splitlines()[1:])
+
+
+def get_orientation(input_file, language: list, timeout: float, log):
+    args_tesseract = [
+        get_program('tesseract'),
+        '-l', '+'.join(language),
+        '-psm', '0',
+        input_file,
+        'stdout'
+    ]
+
+    p = Popen(args_tesseract, close_fds=True, stdout=PIPE, stderr=STDOUT,
+              universal_newlines=True)
+    try:
+        stdout, _ = p.communicate(timeout=timeout)
+    except TimeoutExpired:
+        p.kill()
+        stdout, _ = p.communicate()
+        return OrientationConfidence(angle=0, confidence=0.0)
+    else:
+        osd = {}
+        for line in stdout.splitlines():
+            line = line.strip()
+            parts = line.split(':', maxsplit=2)
+            if len(parts) == 2:
+                osd[parts[0].strip()] = parts[1].strip()
+
+        oc = OrientationConfidence(
+            angle=int(osd['Orientation in degrees']),
+            confidence=float(osd['Orientation confidence']))
+        return oc
+
+
+def tesseract_log_output(log, stdout, input_file):
+    lines = stdout.splitlines()
+    prefix = "{0:4d}: [tesseract] ".format(page_number(input_file))
+    for line in lines:
+        if line.startswith("Tesseract Open Source"):
+            continue
+        elif line.startswith("Warning in pixReadMem"):
+            continue
+        elif 'diacritics' in line:
+            log.warning(prefix + "lots of diacritics - possibly poor OCR")
+        elif line.startswith('OSD: Weak margin'):
+            log.warning(prefix + "unsure about page orientation")
+        else:
+            log.info(prefix + line.strip())
+
+
+def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
+                  timeout: float, pageinfo_getter, pagesegmode: int, log):
+
+    badxml = os.path.splitext(output_hocr)[0] + '.badxml'
+
+    args_tesseract = [
+        get_program('tesseract'),
+        '-l', '+'.join(language)
+    ]
+
+    if pagesegmode is not None:
+        args_tesseract.extend(['-psm', str(pagesegmode)])
+
+    args_tesseract.extend([
+        input_file,
+        badxml,
+        'hocr'
+    ] + tessconfig)
+    p = Popen(args_tesseract, close_fds=True, stdout=PIPE, stderr=STDOUT,
+              universal_newlines=True)
+    try:
+        stdout, _ = p.communicate(timeout=timeout)
+    except TimeoutExpired:
+        p.kill()
+        stdout, _ = p.communicate()
+        # Generate a HOCR file with no recognized text if tesseract times out
+        # Temporary workaround to hocrTransform not being able to function if
+        # it does not have a valid hOCR file.
+        with open(output_hocr, 'w', encoding="utf-8") as f:
+            pageinfo = pageinfo_getter()
+            f.write(HOCR_TEMPLATE.format(
+                pageinfo['width_pixels'],
+                pageinfo['height_pixels']))
+    else:
+        tesseract_log_output(log, stdout, input_file)
+        if p.returncode != 0:
+            raise CalledProcessError(p.returncode, args_tesseract)
+
+        if os.path.exists(badxml + '.html'):
+            # Tesseract 3.02 appends suffix ".html" on its own (.badxml.html)
+            shutil.move(badxml + '.html', badxml)
+        elif os.path.exists(badxml + '.hocr'):
+            # Tesseract 3.03 appends suffix ".hocr" on its own (.badxml.hocr)
+            shutil.move(badxml + '.hocr', badxml)
+
+        # Tesseract 3.03 inserts source filename into hocr file without
+        # escaping it, creating invalid XML and breaking the parser.
+        # As a workaround, rewrite the hocr file, replacing the filename
+        # with a space.  Don't know if Tesseract 3.02 does the same.
+
+        regex_nested_single_quotes = re.compile(
+            r"""title='image "([^"]*)";""")
+        with open(badxml, mode='r', encoding='utf-8') as f_in, \
+                open(output_hocr, mode='w', encoding='utf-8') as f_out:
+            for line in f_in:
+                line = regex_nested_single_quotes.sub(
+                    r"""title='image " ";""", line)
+                f_out.write(line)
+
+
+def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
+                 tessconfig: list, timeout: float, pagesegmode: int, log):
+    '''Use Tesseract to render a PDF.
+
+    input_image -- image to analyze
+    skip_pdf -- if we time out, use this file as output
+    language -- list of languages to consider
+    tessconfig -- tesseract configuration
+    timeout -- timeout (seconds)
+    log -- logger object
+    '''
+
+    args_tesseract = [
+        get_program('tesseract'),
+        '-l', '+'.join(language)
+    ]
+
+    if pagesegmode is not None:
+        args_tesseract.extend(['-psm', str(pagesegmode)])
+
+    args_tesseract.extend([
+        input_image,
+        os.path.splitext(output_pdf)[0],  # Tesseract appends suffix
+        'pdf'
+    ] + tessconfig)
+    p = Popen(args_tesseract, close_fds=True, stdout=PIPE, stderr=STDOUT,
+              universal_newlines=True)
+
+    try:
+        stdout, _ = p.communicate()
+    except TimeoutExpired:
+        p.kill()
+        log.info("Tesseract - page timed out")
+        shutil.copy(skip_pdf, output_pdf)
+    else:
+        tesseract_log_output(log, stdout, input_image)

ocrmypdf/unpaper.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+# unpaper documentation:
+# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+
+from subprocess import Popen, PIPE
+from tempfile import NamedTemporaryFile
+import sys
+import os
+from functools import lru_cache
+from . import ExitCode, get_program
+
+
+@lru_cache(maxsize=1)
+def version():
+    args_unpaper = [
+        get_program('unpaper'),
+        '--version'
+    ]
+    p_unpaper = Popen(args_unpaper, close_fds=True, universal_newlines=True,
+                      stdout=PIPE, stderr=PIPE)
+    version, _ = p_unpaper.communicate(timeout=5)
+
+    return version.strip()
+
+
+try:
+    from PIL import Image
+except ImportError:
+    print("Could not find Python3 imaging library", file=sys.stderr)
+    raise
+
+
+def run(input_file, output_file, dpi, log, mode_args):
+    args_unpaper = [
+        get_program('unpaper'),
+        '-v',
+        '--dpi', str(dpi)
+    ] + mode_args
+
+    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
+
+    im = Image.open(input_file)
+    if im.mode not in SUFFIXES.keys():
+        log.info("Converting image to other colorspace")
+        try:
+            if im.mode == 'P' and len(im.getcolors()) == 2:
+                im = im.convert(mode='1')
+            else:
+                im = im.convert(mode='RGB')
+        except IOError:
+            log.error(
+                    "Could not convert image with type " + im.mode)
+            sys.exit(ExitCode.missing_dependency)
+
+    try:
+        suffix = SUFFIXES[im.mode]
+    except KeyError:
+        log.error(
+                "Failed to convert image to a supported format.")
+        sys.exit(ExitCode.missing_dependency)
+
+    with NamedTemporaryFile(suffix=suffix) as input_pnm, \
+            NamedTemporaryFile(suffix=suffix, mode="r+b") as output_pnm:
+        im.save(input_pnm, format='PPM')
+        im.close()
+
+        os.unlink(output_pnm.name)
+
+        args_unpaper.extend([input_pnm.name, output_pnm.name])
+        p_unpaper = Popen(
+            args_unpaper, close_fds=True,
+            universal_newlines=True, stdout=PIPE, stderr=PIPE
+            )
+        out, err = p_unpaper.communicate()
+        log.debug(out)
+        log.debug(err)
+
+        Image.open(output_pnm.name).save(output_file)
+
+
+def deskew(input_file, output_file, dpi, log):
+    run(input_file, output_file, dpi, log, [
+        '--mask-scan-size', '100',  # don't blank out narrow columns
+        '--no-border-align',  # don't align visible content to borders
+        '--no-mask-center',   # don't center visible content within page
+        '--no-grayfilter',    # don't remove light gray areas
+        '--no-blackfilter',   # don't remove solid black areas
+        '--no-noisefilter',   # don't remove salt and pepper noise
+        '--no-blurfilter'     # don't remove blurry objects/debris
+    ])
+
+
+def clean(input_file, output_file, dpi, log):
+    run(input_file, output_file, dpi, log, [
+        '--mask-scan-size', '100',  # don't blank out narrow columns
+        '--no-border-align',  # don't align visible content to borders
+        '--no-mask-center',   # don't center visible content within page
+        '--no-grayfilter',    # don't remove light gray areas
+        '--no-blackfilter',   # don't remove solid black areas
+        '--no-deskew',        # don't deskew
+    ])

pipeline.svg

@@ -0,0 +1,297 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Generated by graphviz version 2.38.0 (20140413.2041)
+ -->
+<!-- Title: Pipeline: Pages: 1 -->
+<svg width="1452pt" height="824pt"
+ viewBox="0.00 0.00 1452.00 824.08" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 820.083)">
+<title>Pipeline:</title>
+<polygon fill="white" stroke="none" points="-4,4 -4,-820.083 1448,-820.083 1448,4 -4,4"/>
+<g id="clust1" class="cluster"><title>clustertasks</title>
+<polygon fill="none" stroke="black" points="8,-8 8,-808.083 1436,-808.083 1436,-8 8,-8"/>
+<text text-anchor="middle" x="722" y="-780.083" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
+</g>
+<!-- t0 -->
+<g id="node1" class="node"><title>t0</title>
+<polygon fill="#efa03b" stroke="black" points="1256.54,-762.083 1033.46,-762.083 1029.46,-758.083 1029.46,-726.083 1252.54,-726.083 1256.54,-730.083 1256.54,-762.083"/>
+<polyline fill="none" stroke="black" points="1252.54,-758.083 1029.46,-758.083 "/>
+<polyline fill="none" stroke="black" points="1252.54,-758.083 1252.54,-726.083 "/>
+<polyline fill="none" stroke="black" points="1252.54,-758.083 1256.54,-762.083 "/>
+<text text-anchor="middle" x="1143" y="-738.083" font-family="Times,serif" font-size="20.00">repair_pdf</text>
+</g>
+<!-- t1 -->
+<g id="node2" class="node"><title>t1</title>
+<polygon fill="#efa03b" stroke="black" points="1234.11,-683.155 1030,-700.057 825.888,-683.155 826.078,-655.806 1233.92,-655.806 1234.11,-683.155"/>
+<polygon fill="none" stroke="black" points="1238.13,-686.834 1030,-704.069 821.866,-686.834 822.11,-651.808 1237.89,-651.808 1238.13,-686.834"/>
+<text text-anchor="middle" x="1030" y="-669.596" font-family="Times,serif" font-size="20.00">split_pages</text>
+</g>
+<!-- t0&#45;&gt;t1 -->
+<g id="edge1" class="edge"><title>t0&#45;&gt;t1</title>
+<path fill="none" stroke="#0044a0" d="M1113.9,-725.961C1103.58,-719.89 1091.66,-712.873 1080.09,-706.069"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1081.75,-702.982 1071.35,-700.927 1078.2,-709.015 1081.75,-702.982"/>
+</g>
+<!-- t14 -->
+<g id="node16" class="node"><title>t14</title>
+<polygon fill="#efa03b" stroke="black" points="1428.08,-625.109 1089.92,-625.109 1085.92,-621.109 1085.92,-589.109 1424.08,-589.109 1428.08,-593.109 1428.08,-625.109"/>
+<polyline fill="none" stroke="black" points="1424.08,-621.109 1085.92,-621.109 "/>
+<polyline fill="none" stroke="black" points="1424.08,-621.109 1424.08,-589.109 "/>
+<polyline fill="none" stroke="black" points="1424.08,-621.109 1428.08,-625.109 "/>
+<text text-anchor="middle" x="1257" y="-601.109" font-family="Times,serif" font-size="20.00">generate_postscript_stub</text>
+</g>
+<!-- t0&#45;&gt;t14 -->
+<g id="edge22" class="edge"><title>t0&#45;&gt;t14</title>
+<path fill="none" stroke="#0044a0" d="M1219.32,-726.004C1229.98,-720.592 1239.75,-713.466 1247,-704.083 1261.92,-684.78 1263.1,-656.385 1261.35,-635.486"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1264.8,-634.881 1260.22,-625.328 1257.84,-635.653 1264.8,-634.881"/>
+</g>
+<!-- t2 -->
+<g id="node3" class="node"><title>t2</title>
+<polygon fill="#efa03b" stroke="black" points="1029.88,-625.109 748.117,-625.109 744.117,-621.109 744.117,-589.109 1025.88,-589.109 1029.88,-593.109 1029.88,-625.109"/>
+<polyline fill="none" stroke="black" points="1025.88,-621.109 744.117,-621.109 "/>
+<polyline fill="none" stroke="black" points="1025.88,-621.109 1025.88,-589.109 "/>
+<polyline fill="none" stroke="black" points="1025.88,-621.109 1029.88,-625.109 "/>
+<text text-anchor="middle" x="887" y="-601.109" font-family="Times,serif" font-size="20.00">rasterize_preview</text>
+</g>
+<!-- t1&#45;&gt;t2 -->
+<g id="edge2" class="edge"><title>t1&#45;&gt;t2</title>
+<path fill="none" stroke="#0044a0" d="M980.788,-651.715C965.266,-644.498 948.187,-636.558 932.905,-629.452"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="934.195,-626.193 923.652,-625.15 931.244,-632.54 934.195,-626.193"/>
+</g>
+<!-- t3 -->
+<g id="node4" class="node"><title>t3</title>
+<polygon fill="#efa03b" stroke="black" points="1128.15,-567.109 893.852,-567.109 889.852,-563.109 889.852,-531.109 1124.15,-531.109 1128.15,-535.109 1128.15,-567.109"/>
+<polyline fill="none" stroke="black" points="1124.15,-563.109 889.852,-563.109 "/>
+<polyline fill="none" stroke="black" points="1124.15,-563.109 1124.15,-531.109 "/>
+<polyline fill="none" stroke="black" points="1124.15,-563.109 1128.15,-567.109 "/>
+<text text-anchor="middle" x="1009" y="-543.109" font-family="Times,serif" font-size="20.00">orient_page</text>
+</g>
+<!-- t1&#45;&gt;t3 -->
+<g id="edge4" class="edge"><title>t1&#45;&gt;t3</title>
+<path fill="none" stroke="#0044a0" d="M1037.63,-651.508C1042.21,-633.96 1045.92,-609.455 1039,-589.109 1037.4,-584.404 1034.98,-579.822 1032.19,-575.552"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1034.85,-573.258 1026.1,-567.282 1029.21,-577.409 1034.85,-573.258"/>
+</g>
+<!-- t2&#45;&gt;t3 -->
+<g id="edge3" class="edge"><title>t2&#45;&gt;t3</title>
+<path fill="none" stroke="#0044a0" d="M924.267,-589.003C936.328,-583.467 949.857,-577.257 962.502,-571.453"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="964.333,-574.463 971.961,-567.111 961.413,-568.102 964.333,-574.463"/>
+</g>
+<!-- t4 -->
+<g id="node5" class="node"><title>t4</title>
+<polygon fill="#efa03b" stroke="black" points="1027.3,-509.109 676.701,-509.109 672.701,-505.109 672.701,-473.109 1023.3,-473.109 1027.3,-477.109 1027.3,-509.109"/>
+<polyline fill="none" stroke="black" points="1023.3,-505.109 672.701,-505.109 "/>
+<polyline fill="none" stroke="black" points="1023.3,-505.109 1023.3,-473.109 "/>
+<polyline fill="none" stroke="black" points="1023.3,-505.109 1027.3,-509.109 "/>
+<text text-anchor="middle" x="850" y="-485.109" font-family="Times,serif" font-size="20.00">rasterize_with_ghostscript</text>
+</g>
+<!-- t3&#45;&gt;t4 -->
+<g id="edge5" class="edge"><title>t3&#45;&gt;t4</title>
+<path fill="none" stroke="#0044a0" d="M960.431,-531.003C943.787,-525.141 924.999,-518.524 907.704,-512.433"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="908.867,-509.132 898.272,-509.111 906.541,-515.734 908.867,-509.132"/>
+</g>
+<!-- t9 -->
+<g id="node11" class="node"><title>t9</title>
+<polygon fill="#efa03b" stroke="black" points="314.109,-277.109 19.8906,-277.109 15.8906,-273.109 15.8906,-241.109 310.109,-241.109 314.109,-245.109 314.109,-277.109"/>
+<polyline fill="none" stroke="black" points="310.109,-273.109 15.8906,-273.109 "/>
+<polyline fill="none" stroke="black" points="310.109,-273.109 310.109,-241.109 "/>
+<polyline fill="none" stroke="black" points="310.109,-273.109 314.109,-277.109 "/>
+<text text-anchor="middle" x="165" y="-253.109" font-family="Times,serif" font-size="20.00">select_image_layer</text>
+</g>
+<!-- t3&#45;&gt;t9 -->
+<g id="edge14" class="edge"><title>t3&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M889.675,-542.297C675.505,-530.255 248,-498.192 248,-434.109 248,-434.109 248,-434.109 248,-374.109 248,-337.597 219.83,-304.936 196.312,-284.031"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="198.437,-281.243 188.562,-277.404 193.888,-286.563 198.437,-281.243"/>
+</g>
+<!-- t15 -->
+<g id="node14" class="node"><title>t15</title>
+<polygon fill="#efa03b" stroke="black" points="1391.34,-451.109 1170.66,-451.109 1166.66,-447.109 1166.66,-415.109 1387.34,-415.109 1391.34,-419.109 1391.34,-451.109"/>
+<polyline fill="none" stroke="black" points="1387.34,-447.109 1166.66,-447.109 "/>
+<polyline fill="none" stroke="black" points="1387.34,-447.109 1387.34,-415.109 "/>
+<polyline fill="none" stroke="black" points="1387.34,-447.109 1391.34,-451.109 "/>
+<text text-anchor="middle" x="1279" y="-427.109" font-family="Times,serif" font-size="20.00">skip_page</text>
+</g>
+<!-- t3&#45;&gt;t15 -->
+<g id="edge19" class="edge"><title>t3&#45;&gt;t15</title>
+<path fill="none" stroke="#0044a0" d="M1060.32,-531.078C1078.95,-524.591 1100.07,-516.881 1119,-509.109 1159.3,-492.568 1204.11,-471.304 1236.04,-455.645"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1237.67,-458.74 1245.1,-451.181 1234.58,-452.461 1237.67,-458.74"/>
+</g>
+<!-- t13 -->
+<g id="node15" class="node"><title>t13</title>
+<polygon fill="#efa03b" stroke="black" points="1388.24,-277.109 1007.76,-277.109 1003.76,-273.109 1003.76,-241.109 1384.24,-241.109 1388.24,-245.109 1388.24,-277.109"/>
+<polyline fill="none" stroke="black" points="1384.24,-273.109 1003.76,-273.109 "/>
+<polyline fill="none" stroke="black" points="1384.24,-273.109 1384.24,-241.109 "/>
+<polyline fill="none" stroke="black" points="1384.24,-273.109 1388.24,-277.109 "/>
+<text text-anchor="middle" x="1196" y="-253.109" font-family="Times,serif" font-size="20.00">tesseract_ocr_and_render_pdf</text>
+</g>
+<!-- t3&#45;&gt;t13 -->
+<g id="edge21" class="edge"><title>t3&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M1040.79,-531.094C1071.69,-511.983 1114,-477.834 1114,-434.109 1114,-434.109 1114,-434.109 1114,-374.109 1114,-337.749 1141.83,-305.063 1165.07,-284.11"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1167.46,-286.664 1172.72,-277.466 1162.87,-281.377 1167.46,-286.664"/>
+</g>
+<!-- t5 -->
+<g id="node6" class="node"><title>t5</title>
+<polygon fill="#efa03b" stroke="black" points="830.742,-451.109 535.258,-451.109 531.258,-447.109 531.258,-415.109 826.742,-415.109 830.742,-419.109 830.742,-451.109"/>
+<polyline fill="none" stroke="black" points="826.742,-447.109 531.258,-447.109 "/>
+<polyline fill="none" stroke="black" points="826.742,-447.109 826.742,-415.109 "/>
+<polyline fill="none" stroke="black" points="826.742,-447.109 830.742,-451.109 "/>
+<text text-anchor="middle" x="681" y="-427.109" font-family="Times,serif" font-size="20.00">preprocess_deskew</text>
+</g>
+<!-- t4&#45;&gt;t5 -->
+<g id="edge6" class="edge"><title>t4&#45;&gt;t5</title>
+<path fill="none" stroke="#0044a0" d="M798.376,-473.003C780.521,-467.087 760.346,-460.402 741.823,-454.264"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="742.901,-450.934 732.308,-451.111 740.699,-457.579 742.901,-450.934"/>
+</g>
+<!-- t8 -->
+<g id="node10" class="node"><title>t8</title>
+<polygon fill="#efa03b" stroke="black" points="980.119,-335.109 665.881,-335.109 661.881,-331.109 661.881,-299.109 976.119,-299.109 980.119,-303.109 980.119,-335.109"/>
+<polyline fill="none" stroke="black" points="976.119,-331.109 661.881,-331.109 "/>
+<polyline fill="none" stroke="black" points="976.119,-331.109 976.119,-299.109 "/>
+<polyline fill="none" stroke="black" points="976.119,-331.109 980.119,-335.109 "/>
+<text text-anchor="middle" x="821" y="-311.109" font-family="Times,serif" font-size="20.00">select_image_for_pdf</text>
+</g>
+<!-- t4&#45;&gt;t8 -->
+<g id="edge12" class="edge"><title>t4&#45;&gt;t8</title>
+<path fill="none" stroke="#0044a0" d="M848.03,-473.087C846.196,-457.857 843.261,-434.941 840,-415.109 836.1,-391.393 830.78,-364.592 826.761,-345.181"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="830.152,-344.296 824.68,-335.224 823.3,-345.728 830.152,-344.296"/>
+</g>
+<!-- t6 -->
+<g id="node7" class="node"><title>t6</title>
+<polygon fill="#efa03b" stroke="black" points="801.95,-393.109 524.05,-393.109 520.05,-389.109 520.05,-357.109 797.95,-357.109 801.95,-361.109 801.95,-393.109"/>
+<polyline fill="none" stroke="black" points="797.95,-389.109 520.05,-389.109 "/>
+<polyline fill="none" stroke="black" points="797.95,-389.109 797.95,-357.109 "/>
+<polyline fill="none" stroke="black" points="797.95,-389.109 801.95,-393.109 "/>
+<text text-anchor="middle" x="661" y="-369.109" font-family="Times,serif" font-size="20.00">preprocess_clean</text>
+</g>
+<!-- t5&#45;&gt;t6 -->
+<g id="edge7" class="edge"><title>t5&#45;&gt;t6</title>
+<path fill="none" stroke="#0044a0" d="M674.891,-415.003C673.495,-411.095 671.979,-406.852 670.48,-402.652"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="673.731,-401.351 667.072,-393.111 667.139,-403.705 673.731,-401.351"/>
+</g>
+<!-- t5&#45;&gt;t8 -->
+<g id="edge11" class="edge"><title>t5&#45;&gt;t8</title>
+<path fill="none" stroke="#0044a0" d="M781.944,-415.046C792.967,-409.579 803.051,-402.434 811,-393.109 822.009,-380.195 824.454,-361.215 824.174,-345.581"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="827.659,-345.2 823.617,-335.407 820.669,-345.583 827.659,-345.2"/>
+</g>
+<!-- t7 -->
+<g id="node8" class="node"><title>t7</title>
+<polygon fill="#efa03b" stroke="black" points="643.666,-335.109 354.334,-335.109 350.334,-331.109 350.334,-299.109 639.666,-299.109 643.666,-303.109 643.666,-335.109"/>
+<polyline fill="none" stroke="black" points="639.666,-331.109 350.334,-331.109 "/>
+<polyline fill="none" stroke="black" points="639.666,-331.109 639.666,-299.109 "/>
+<polyline fill="none" stroke="black" points="639.666,-331.109 643.666,-335.109 "/>
+<text text-anchor="middle" x="497" y="-311.109" font-family="Times,serif" font-size="20.00">ocr_tesseract_hocr</text>
+</g>
+<!-- t6&#45;&gt;t7 -->
+<g id="edge8" class="edge"><title>t6&#45;&gt;t7</title>
+<path fill="none" stroke="#0044a0" d="M610.903,-357.003C593.736,-351.141 574.358,-344.524 556.518,-338.433"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="557.384,-335.03 546.79,-335.111 555.122,-341.654 557.384,-335.03"/>
+</g>
+<!-- t6&#45;&gt;t8 -->
+<g id="edge10" class="edge"><title>t6&#45;&gt;t8</title>
+<path fill="none" stroke="#0044a0" d="M709.875,-357.003C726.624,-351.141 745.529,-344.524 762.933,-338.433"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="764.142,-341.718 772.425,-335.111 761.83,-335.111 764.142,-341.718"/>
+</g>
+<!-- t10 -->
+<g id="node9" class="node"><title>t10</title>
+<polygon fill="#efa03b" stroke="black" points="620.109,-277.109 335.891,-277.109 331.891,-273.109 331.891,-241.109 616.109,-241.109 620.109,-245.109 620.109,-277.109"/>
+<polyline fill="none" stroke="black" points="616.109,-273.109 331.891,-273.109 "/>
+<polyline fill="none" stroke="black" points="616.109,-273.109 616.109,-241.109 "/>
+<polyline fill="none" stroke="black" points="616.109,-273.109 620.109,-277.109 "/>
+<text text-anchor="middle" x="476" y="-253.109" font-family="Times,serif" font-size="20.00">render_hocr_page</text>
+</g>
+<!-- t7&#45;&gt;t10 -->
+<g id="edge9" class="edge"><title>t7&#45;&gt;t10</title>
+<path fill="none" stroke="#0044a0" d="M490.585,-299.003C489.12,-295.095 487.528,-290.852 485.953,-286.652"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="489.164,-285.245 482.376,-277.111 482.61,-287.703 489.164,-285.245"/>
+</g>
+<!-- t11 -->
+<g id="node13" class="node"><title>t11</title>
+<polygon fill="#efa03b" stroke="black" points="985.486,-277.109 642.514,-277.109 638.514,-273.109 638.514,-241.109 981.486,-241.109 985.486,-245.109 985.486,-277.109"/>
+<polyline fill="none" stroke="black" points="981.486,-273.109 638.514,-273.109 "/>
+<polyline fill="none" stroke="black" points="981.486,-273.109 981.486,-241.109 "/>
+<polyline fill="none" stroke="black" points="981.486,-273.109 985.486,-277.109 "/>
+<text text-anchor="middle" x="812" y="-253.109" font-family="Times,serif" font-size="20.00">render_hocr_debug_page</text>
+</g>
+<!-- t7&#45;&gt;t11 -->
+<g id="edge18" class="edge"><title>t7&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M592.793,-299.079C628.531,-292.726 669.303,-285.478 705.912,-278.969"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="706.887,-282.351 716.12,-277.155 705.661,-275.459 706.887,-282.351"/>
+</g>
+<!-- t12 -->
+<g id="node12" class="node"><title>t12</title>
+<polygon fill="#efa03b" stroke="black" points="607.082,-219.109 348.918,-219.109 344.918,-215.109 344.918,-183.109 603.082,-183.109 607.082,-187.109 607.082,-219.109"/>
+<polyline fill="none" stroke="black" points="603.082,-215.109 344.918,-215.109 "/>
+<polyline fill="none" stroke="black" points="603.082,-215.109 603.082,-183.109 "/>
+<polyline fill="none" stroke="black" points="603.082,-215.109 607.082,-219.109 "/>
+<text text-anchor="middle" x="476" y="-195.109" font-family="Times,serif" font-size="20.00">add_text_layer</text>
+</g>
+<!-- t10&#45;&gt;t12 -->
+<g id="edge15" class="edge"><title>t10&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M476,-241.003C476,-237.312 476,-233.322 476,-229.352"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="479.5,-229.111 476,-219.111 472.5,-229.111 479.5,-229.111"/>
+</g>
+<!-- t8&#45;&gt;t9 -->
+<g id="edge13" class="edge"><title>t8&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M661.842,-299.864C658.871,-299.606 655.921,-299.354 653,-299.109 509.812,-287.095 471.159,-289.734 324.542,-277.219"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="324.526,-273.705 314.262,-276.332 323.924,-280.679 324.526,-273.705"/>
+</g>
+<!-- t8&#45;&gt;t11 -->
+<g id="edge17" class="edge"><title>t8&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M818.251,-299.003C817.64,-295.204 816.979,-291.087 816.322,-287.002"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="819.775,-286.429 814.732,-277.111 812.864,-287.539 819.775,-286.429"/>
+</g>
+<!-- t8&#45;&gt;t13 -->
+<g id="edge20" class="edge"><title>t8&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M935.04,-299.079C978.311,-292.618 1027.78,-285.23 1071.94,-278.636"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1072.48,-282.093 1081.86,-277.155 1071.45,-275.17 1072.48,-282.093"/>
+</g>
+<!-- t9&#45;&gt;t12 -->
+<g id="edge16" class="edge"><title>t9&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M259.577,-241.079C294.86,-234.726 335.115,-227.478 371.259,-220.969"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="372.116,-224.372 381.337,-219.155 370.875,-217.482 372.116,-224.372"/>
+</g>
+<!-- t16 -->
+<g id="node17" class="node"><title>t16</title>
+<polygon fill="#efa03b" stroke="black" points="1031.47,-105.333 1196,-78.005 1360.53,-105.333 1360.37,-149.551 1031.63,-149.551 1031.47,-105.333"/>
+<polygon fill="none" stroke="black" points="1027.46,-101.94 1196,-73.9453 1364.54,-101.94 1364.36,-153.556 1027.64,-153.556 1027.46,-101.94"/>
+<text text-anchor="middle" x="1196" y="-111.555" font-family="Times,serif" font-size="20.00">merge_pages</text>
+</g>
+<!-- t12&#45;&gt;t16 -->
+<g id="edge26" class="edge"><title>t12&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M607.222,-185.246C722.142,-172.229 890.172,-153.196 1017.34,-138.791"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1018.04,-142.235 1027.58,-137.632 1017.25,-135.279 1018.04,-142.235"/>
+</g>
+<!-- t11&#45;&gt;t16 -->
+<g id="edge27" class="edge"><title>t11&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M859.086,-240.997C916.223,-220.232 1014.29,-184.591 1089.94,-157.099"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1091.32,-160.323 1099.52,-153.618 1088.92,-153.744 1091.32,-160.323"/>
+</g>
+<!-- t15&#45;&gt;t16 -->
+<g id="edge23" class="edge"><title>t15&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1321.98,-414.938C1359.16,-396.916 1407,-364.681 1407,-318.109 1407,-318.109 1407,-318.109 1407,-258.109 1407,-211.469 1370.69,-179.509 1328.2,-158.076"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1329.57,-154.854 1319.04,-153.66 1326.53,-161.158 1329.57,-154.854"/>
+</g>
+<!-- t13&#45;&gt;t16 -->
+<g id="edge25" class="edge"><title>t13&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1196,-240.997C1196,-221.914 1196,-190.265 1196,-163.926"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1199.5,-163.759 1196,-153.759 1192.5,-163.759 1199.5,-163.759"/>
+</g>
+<!-- t14&#45;&gt;t16 -->
+<g id="edge24" class="edge"><title>t14&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1326.64,-588.956C1373.58,-572.748 1427,-543.103 1427,-492.109 1427,-492.109 1427,-492.109 1427,-258.109 1427,-220.539 1416.55,-207.537 1388,-183.109 1376.82,-173.542 1364.16,-165.377 1350.82,-158.413"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1351.99,-155.087 1341.47,-153.781 1348.88,-161.358 1351.99,-155.087"/>
+</g>
+<!-- t17 -->
+<g id="node18" class="node"><title>t17</title>
+<polygon fill="#efa03b" stroke="black" points="1310.18,-52 1085.82,-52 1081.82,-48 1081.82,-16 1306.18,-16 1310.18,-20 1310.18,-52"/>
+<polyline fill="none" stroke="black" points="1306.18,-48 1081.82,-48 "/>
+<polyline fill="none" stroke="black" points="1306.18,-48 1306.18,-16 "/>
+<polyline fill="none" stroke="black" points="1306.18,-48 1310.18,-52 "/>
+<text text-anchor="middle" x="1196" y="-28" font-family="Times,serif" font-size="20.00">copy_final</text>
+</g>
+<!-- t16&#45;&gt;t17 -->
+<g id="edge28" class="edge"><title>t16&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M1196,-73.8665C1196,-69.8921 1196,-65.942 1196,-62.1676"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1199.5,-62.1213 1196,-52.1214 1192.5,-62.1214 1199.5,-62.1213"/>
+</g>
+</g>
+</svg>

pytest.ini

@@ -0,0 +1,2 @@
+[pytest]
+norecursedirs = lib 

requirements.txt

@@ -0,0 +1,6 @@
+ruffus==2.6.3
+Pillow==3.1.1
+reportlab==3.2.0
+PyPDF2==1.25.1
+img2pdf==0.2
+cffi==1.5.2

setup.cfg

@@ -0,0 +1,4 @@
+[bdist_wheel]
+python-tag = py34
+[aliases]
+test=pytest

setup.py

@@ -0,0 +1,235 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from __future__ import print_function, unicode_literals
+
+import sys
+if sys.version_info < (3, 4):
+    print("Python 3.4 or newer is required")
+    sys.exit(1)
+
+from setuptools import setup  # nopep8
+from subprocess import STDOUT, check_output, CalledProcessError  # nopep8
+from collections.abc import Mapping  # nopep8
+import re  # nopep8
+
+
+missing_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.
+'''
+
+unknown_version = '''
+OCRmyPDF requires '{program}' {need_version} or higher.  Your system has
+'{program}' but we cannot tell what version is installed.  Contact the
+package maintainer.
+'''
+
+old_version = '''
+OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
+to have {found_version}.  Please update this program.
+'''
+
+okay_its_optional = '''
+This program is OPTIONAL, so installation of OCRmyPDF can proceed, but
+some functionality may be missing.
+'''
+
+not_okay_its_required = '''
+This program is REQUIRED for OCRmyPDF to work.  Installation will abort.
+'''
+
+osx_install_advice = '''
+If you have homebrew installed, try these command to install the missing
+packages:
+    brew update
+    brew upgrade
+    brew install {package}
+'''
+
+linux_install_advice = '''
+On systems with the aptitude package manager (Debian, Ubuntu), try these
+commands:
+    sudo apt-get update
+    sudo apt-get install {package}
+
+On RPM-based systems (Red Hat, Fedora), search for instructions on
+installing the RPM for {program}.
+'''
+
+
+def get_platform():
+    if sys.platform.startswith('freebsd'):
+        return 'freebsd'
+    elif sys.platform.startswith('linux'):
+        return 'linux'
+    return sys.platform
+
+
+def _error_trailer(program, package, optional, **kwargs):
+    if optional:
+        print(okay_its_optional.format(**locals()), file=sys.stderr)
+    else:
+        print(not_okay_its_required.format(**locals()), file=sys.stderr)
+
+    if isinstance(package, Mapping):
+        package = package[get_platform()]
+
+    if get_platform() == 'darwin':
+        print(osx_install_advice.format(**locals()), file=sys.stderr)
+    elif get_platform() == 'linux':
+        print(linux_install_advice.format(**locals()), file=sys.stderr)
+
+
+def error_missing_program(
+        program,
+        package,
+        optional
+        ):
+    print(missing_program.format(**locals()), file=sys.stderr)
+    _error_trailer(**locals())
+
+
+def error_unknown_version(
+        program,
+        package,
+        optional,
+        need_version
+        ):
+    print(unknown_version.format(**locals()), file=sys.stderr)
+    _error_trailer(**locals())
+
+
+def error_old_version(
+        program,
+        package,
+        optional,
+        need_version,
+        found_version
+        ):
+    print(old_version.format(**locals()), file=sys.stderr)
+    _error_trailer(**locals())
+
+
+def check_external_program(
+        program,
+        need_version,
+        package,
+        version_check_args=['--version'],
+        version_scrape_regex=re.compile(r'(\d+\.\d+(?:\.\d+)?)'),
+        optional=False):
+
+    print('Checking for {program} >= {need_version}...'.format(
+            program=program, need_version=need_version))
+    try:
+        result = check_output(
+                [program] + version_check_args,
+                universal_newlines=True, stderr=STDOUT)
+    except (CalledProcessError, FileNotFoundError):
+        error_missing_program(program, package, optional)
+        if not optional:
+            sys.exit(1)
+        print('Continuing install without {program}'.format(program=program))
+        return
+
+    try:
+        found_version = version_scrape_regex.search(result).group(1)
+    except AttributeError:
+        error_unknown_version(program, package, optional, need_version)
+        sys.exit(1)
+
+    if found_version < need_version:
+        error_old_version(program, package, optional, need_version,
+                          found_version)
+
+    print('Found {program} {found_version}'.format(
+            program=program, found_version=found_version))
+
+
+command = next((arg for arg in sys.argv[1:] if not arg.startswith('-')), '')
+
+
+if command.startswith('install') or \
+        command in ['check', 'test', 'nosetests', 'easy_install']:
+    check_external_program(
+        program='tesseract',
+        need_version='3.02.02',
+        package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'}
+    )
+    check_external_program(
+        program='gs',
+        need_version='9.14',
+        package='ghostscript'
+    )
+    check_external_program(
+        program='unpaper',
+        need_version='6.1',
+        package='unpaper',
+        optional=True
+    )
+    check_external_program(
+        program='qpdf',
+        need_version='5.0.0',
+        package='qpdf',
+        version_check_args=['--version']
+    )
+
+
+if 'upload' in sys.argv[1:]:
+    print('Use twine to upload the package - setup.py upload is insecure')
+    sys.exit(1)
+
+tests_require = open('test_requirements.txt').read().splitlines()
+
+setup(
+    name='ocrmypdf',
+    description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
+    url='https://github.com/jbarlow83/OCRmyPDF',
+    author='James R. Barlow',
+    author_email='jim@purplerock.ca',
+    license='Public Domain',
+    packages=['ocrmypdf'],
+    keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "Development Status :: 5 - Production/Stable",
+        "Environment :: Console",
+        "Intended Audience :: End Users/Desktop",
+        "Intended Audience :: Science/Research",
+        "Intended Audience :: System Administrators",
+        "License :: Public Domain",
+        "Operating System :: MacOS :: MacOS X",
+        "Operating System :: POSIX",
+        "Operating System :: POSIX :: BSD",
+        "Operating System :: POSIX :: Linux",
+        "Topic :: Scientific/Engineering :: Image Recognition",
+        "Topic :: Text Processing :: Indexing",
+        "Topic :: Text Processing :: Linguistic",
+        ],
+    setup_requires=[
+        'setuptools_scm',
+        'setuptools_scm_git_archive',
+        'cffi>=1.5.0',
+        'pytest-runner'
+    ],
+    use_scm_version={'version_scheme': 'post-release'},
+    cffi_modules=[
+        'ocrmypdf/lib/compile_leptonica.py:ffi'
+    ],
+    install_requires=[
+        'ruffus>=2.6.3',
+        'Pillow>=3.0.0',
+        'reportlab>=3.1.44',
+        'PyPDF2>=1.25.1',
+        'img2pdf>=0.2.0',
+        'cffi>=1.5.0'
+    ],
+    tests_require=tests_require,
+    entry_points={
+        'console_scripts': [
+            'ocrmypdf = ocrmypdf.main:run_pipeline'
+        ],
+    },
+    include_package_data=True,
+    zip_safe=False)

src/config.sh

@@ -1,32 +0,0 @@
-#####################################################################################
-# The following parameters might be changed by the user
-#####################################################################################
-
-DEFAULT_DPI=300				# dpi value used as fall back if the page dpi cannot be determined
-
-#####################################################################################
-# Do NOT change the following parameters
-#####################################################################################
-
-TOOLNAME="OCRmyPDF"
-VERSION="v2.2-stable"
-
-# possible exit codes
-EXIT_BAD_ARGS="1"
-EXIT_BAD_INPUT_FILE="2"
-EXIT_MISSING_DEPENDENCY="3"
-EXIT_INVALID_OUTPUT_PDFA="4"
-EXIT_FILE_ACCESS_ERROR="5"
-EXIT_OTHER_ERROR="15"
-
-# possible log levels
-LOG_ERR="0"				# only error messages
-LOG_WARN="1"				# error messages and warnings
-LOG_INFO="2"				# error messages, warnings and some infos
-LOG_DEBUG="3"				# debug level logging
-
-# various paths
-SRC="./src"				# location of the source folder (except source of external tools like jhove)
-OCR_PAGE="$SRC/ocrPage.sh"		# path to the script aimed at OCRing one page
-JHOVE="./jhove/bin/JhoveApp.jar"	# java SW for validating the final PDF/A
-JHOVE_CFG="./jhove/conf/jhove.conf"	# location of the jhove config file

src/hocrTransform.py

@@ -1,203 +0,0 @@
-#!/usr/local/bin/python2
-# coding: utf-8
-##############################################################################
-# Copyright (c) 2013-14: fritz-hh from Github (https://github.com/fritz-hh)
-#
-# Copyright (c) 2010: Jonathan Brinley from Github (https://github.com/jbrinley/HocrConverter)
-# Initial version by Jonathan Brinley, jonathanbrinley@gmail.com
-##############################################################################
-from reportlab.pdfgen.canvas import Canvas
-from reportlab.lib.units import inch
-from lxml import etree as ElementTree
-from PIL import Image
-import re, sys
-import argparse
-
-
-class hocrTransform():
-	"""
-	A class for converting documents from the hOCR format.
-	For details of the hOCR format, see:
-	http://docs.google.com/View?docid=dfxcv4vc_67g844kf
-	"""
-	def __init__(self, hocrFileName, dpi):
-		self.dpi = dpi
-		self.boxPattern = re.compile('bbox((\s+\d+){4})')
-
-		self.hocr = ElementTree.ElementTree()
-		self.hocr.parse(hocrFileName)
-
-		# if the hOCR file has a namespace, ElementTree requires its use to find elements
-		matches = re.match('({.*})html', self.hocr.getroot().tag)
-		self.xmlns = ''
-		if matches:
-			self.xmlns = matches.group(1)
-
-		# get dimension in pt (not pixel!!!!) of the OCRed image
-		self.width, self.height = None, None
-		for div in self.hocr.findall(".//%sdiv[@class='ocr_page']"%(self.xmlns)):
-			coords = self.element_coordinates(div)
-			self.width = self.px2pt(coords[2]-coords[0])
-			self.height = self.px2pt(coords[3]-coords[1])
-			break # there shouldn't be more than one, and if there is, we don't want it
-
-		# no width and heigh definition in the ocr_image element of the hocr file
-		if self.width is None:
-			print("No page dimension found in the hocr file")
-			sys.exit(1)
-
-	def __str__(self):
-		"""
-		Return the textual content of the HTML body
-		"""
-		if self.hocr is None:
-			return ''
-		body = self.hocr.find(".//%sbody"%(self.xmlns))
-		if body:
-			return self._get_element_text(body).encode('utf-8') # XML gives unicode
-		else:
-			return ''
-
-	def _get_element_text(self, element):
-		"""
-		Return the textual content of the element and its children
-		"""
-		text = ''
-		if element.text is not None:
-			text = text + element.text
-		for child in element.getchildren():
-			text = text + self._get_element_text(child)
-		if element.tail is not None:
-			text = text + element.tail
-		return text
-
-	def element_coordinates(self, element):
-		"""
-		Returns a tuple containing the coordinates of the bounding box around
-		an element
-		"""
-		out = (0,0,0,0)
-		if 'title' in element.attrib:
-			matches = self.boxPattern.search(element.attrib['title'])
-			if matches:
-				coords = matches.group(1).split()
-				out = (int(coords[0]),int(coords[1]),int(coords[2]),int(coords[3]))
-		return out
-
-	def px2pt(self, pxl):
-		"""
-		Returns the length in pt given length in pxl
-		"""
-		return float(pxl)/self.dpi*inch
-
-	def replace_unsupported_chars(self, str):
-		"""
-		Given an input string, returns the corresponding string that:
-		- is available in the helvetica facetype
-		- does not contain any ligature (to allow easy search in the PDF file)
-		"""		
-		# The 'u' before the character to replace indicates that it is a unicode character
-		str=str.replace(u"fl","fl")
-		str=str.replace(u"fi","fi")
-		return str
-		
-	def to_pdf(self, outFileName, imageFileName, showBoundingboxes, fontname="Helvetica"):
-		"""
-		Creates a PDF file with an image superimposed on top of the text.
-		Text is positioned according to the bounding box of the lines in
-		the hOCR file.
-		The image need not be identical to the image used to create the hOCR file.
-		It can have a lower resolution, different color mode, etc.
-		"""
-		# create the PDF file
-		pdf = Canvas(outFileName, pagesize=(self.width, self.height), pageCompression=1) # page size in points (1/72 in.)
-
-		# draw bounding box for each paragraph
-		pdf.setStrokeColorRGB(0,1,1)	# light blue for bounding box of paragraph
-		pdf.setFillColorRGB(0,1,1)	# light blue for bounding box of paragraph
-		pdf.setLineWidth(0)		# no line for bounding box
-		for elem in self.hocr.findall(".//%sp[@class='%s']" % (self.xmlns, "ocr_par")):
-
-			elemtxt=self._get_element_text(elem).rstrip()
-			if len(elemtxt) == 0:
-				continue
-
-			coords = self.element_coordinates(elem)
-			x1=self.px2pt(coords[0])
-			y1=self.px2pt(coords[1])
-			x2=self.px2pt(coords[2])
-			y2=self.px2pt(coords[3])
-
-			# draw the bbox border
-			if showBoundingboxes == True:
-				pdf.rect(x1, self.height-y2, x2-x1, y2-y1, fill=1)
-
-
-		# check if element with class 'ocrx_word' are available
-		# otherwise use 'ocr_line' as fallback
-		elemclass="ocr_line"
-		if self.hocr.find(".//%sspan[@class='ocrx_word']" %(self.xmlns)) is not None:
-			elemclass="ocrx_word"
-
-		# itterate all text elements
-		pdf.setStrokeColorRGB(1,0,0)	# light green for bounding box of word/line
-		pdf.setLineWidth(0.5)		# bounding box line width
-		pdf.setDash(6,3)		# bounding box is dashed
-		pdf.setFillColorRGB(0,0,0)	# text in black
-		for elem in self.hocr.findall(".//%sspan[@class='%s']" % (self.xmlns, elemclass)):
-
-			elemtxt=self._get_element_text(elem).rstrip()
-			
-			elemtxt=self.replace_unsupported_chars(elemtxt)
-			
-			if len(elemtxt) == 0:
-				continue
-
-			coords = self.element_coordinates(elem)
-			x1=self.px2pt(coords[0])
-			y1=self.px2pt(coords[1])
-			x2=self.px2pt(coords[2])
-			y2=self.px2pt(coords[3])
-
-			# draw the bbox border
-			if showBoundingboxes == True:
-				pdf.rect(x1, self.height-y2, x2-x1, y2-y1, fill=0)
-
-			text = pdf.beginText()
-			fontsize=self.px2pt(coords[3]-coords[1])
-			text.setFont(fontname, fontsize)
-
-			# set cursor to bottom left corner of bbox (adjust for dpi)
-			text.setTextOrigin(x1, self.height-y2)
-
-			# scale the width of the text to fill the width of the bbox
-			text.setHorizScale(100*(x2-x1)/pdf.stringWidth(elemtxt, fontname, fontsize))
-
-			# write the text to the page
-			text.textLine(elemtxt)
-			pdf.drawText(text)
-
-		# put the image on the page, scaled to fill the page
-		if imageFileName != None:
-			im = Image.open(imageFileName)
-			pdf.drawInlineImage(im, 0, 0, width=self.width, height=self.height)
-
-		# finish up the page and save it
-		pdf.showPage()
-		pdf.save()
-
-
-if __name__ == "__main__":
-	parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
-	parser.add_argument('-b', '--boundingboxes', action="store_true", default=False, help='Show bounding boxes borders')
-	parser.add_argument('-r', '--resolution', type=int, default=300, help='Resolution of the image that was OCRed')
-	parser.add_argument('-i', '--image', default=None, help='Path to the image to be placed above the text')
-	parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
-	parser.add_argument('outputfile', help='Path to the PDF file to be generated')
-	args = parser.parse_args()
-
-	hocr = hocrTransform(args.hocrfile, args.resolution)
-	hocr.to_pdf(args.outputfile, args.image, args.boundingboxes)
-
-
-

src/ocrPage.sh

@@ -1,227 +0,0 @@
-#!/bin/sh
-##############################################################################
-# Script aimed at OCRing a single page of a PDF file
-#
-# Copyright (c) 2013-14: fritz-hh from Github (https://github.com/fritz-hh)
-##############################################################################
-
-. "./src/config.sh"
-
-
-# Initialization of variables passed by arguments
-FILE_INPUT_PDF="$1"			# PDF file containing the page to be OCRed
-PAGE_INFO="$2"				# Various characteristics of the page to be OCRed
-NUM_PAGES="$3"				# Total number of page of the PDF file (required for logging)
-TMP_FLD="$4"				# Folder where the temporary files should be placed
-VERBOSITY="$5"				# Requested verbosity
-LAN="$6"				# Language of the file to be OCRed
-KEEP_TMP="$7"				# Keep the temporary files after processing (helpful for debugging)
-PREPROCESS_DESKEW="$8"			# Deskew the page to be OCRed
-PREPROCESS_CLEAN="$9"			# Clean the page to be OCRed
-PREPROCESS_CLEANTOPDF="${10}"		# Put the cleaned paged in the OCRed PDF
-OVERSAMPLING_DPI="${11}"		# Oversampling resolution in dpi
-PDF_NOIMG="${12}"			# Request to generate also a PDF page containing only the OCRed text but no image (helpful for debugging) 
-TESS_CFG_FILES="${13}"			# Specific configuration files to be used by Tesseract during OCRing
-FORCE_OCR="${14}"			# Force to OCR, even if the page already contains fonts
-
-
-
-################################## 
-# Detect the characteristics of the embedded image for 
-# the page number provided as parameter
-#
-# Param 1: page number
-# Param 2: PDF page width in pt
-# Param 3: PDF page height in pt
-# Param 4: temporary file path (Path of the file in which the output should be written)
-# Output:  A file containing the characteristics of the embedded image. File structure:
-#          DPI=<dpi>
-#          COLOR_SPACE=<colorspace>
-#          DEPTH=<colordepth>
-# Returns:
-#       - 0: if no error occurs
-#       - 1: in case the page already contains fonts (which should be the case for PDF generated from scanned pages) 
-#       - 2: in case the page contains more than one image
-##################################
-getImgInfo() {
-	local page widthPDF heightPDF curImgInfo nbImg curImg propCurImg widthCurImg heightCurImg colorspaceCurImg depthCurImg dpi
-
-	# page number
-	page="$1"
-	# width / height of PDF page (in pt)
-	widthPDF="$2"
-	heightPDF="$3"
-	# path of the file in which the output should be written
-	curImgInfo="$4"
-
-	
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Size ${heightPDF}x${widthPDF} (h*w in pt)"
-	
-	
-	# check if the page already contains fonts (which should not be the case for PDF based on scanned files
-	[ `pdffonts -f $page -l $page "${FILE_INPUT_PDF}" | wc -l` -gt 2 ] && echo "Page $page: Page already contains font data !!!" && return 1
-
-	
-	# extract raw image from pdf file to compute resolution
-	# unfortunately this image can have another orientation than in the pdf...
-	# so we will have to extract it again later using pdftoppm
-	pdfimages -f $page -l $page -j "$FILE_INPUT_PDF" "$curOrigImg" 1>&2	
-	# count number of extracted images 
-	nbImg=$((`ls -1 "$curOrigImg"* 2>/dev/null | wc -l`))
-	if [ $nbImg -ne "1" ]; then
-		[ $VERBOSITY -ge $LOG_WARN ] && echo "Page $page: Expecting exactly 1 image covering the whole page (found $nbImg). Cannot compute dpi value."
-		return 2
-	fi
-	# Get characteristics of the extracted image
-	curImg=`ls -1 "$curOrigImg"* 2>/dev/null`
-	propCurImg=`identify -format "%w %h %[colorspace] %[depth]" "$curImg"`
-	widthCurImg=`echo "$propCurImg" | cut -f1 -d" "`
-	heightCurImg=`echo "$propCurImg" | cut -f2 -d" "`
-	colorspaceCurImg=`echo "$propCurImg" | cut -f3 -d" "`
-	depthCurImg=`echo "$propCurImg" | cut -f4 -d" "`
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Size ${heightCurImg}x${widthCurImg} (in pixel)"	
-
-	# compute the resolution of the image (making the assumption that x & y resolution are equal)
-	# and round it to the nearest integer
-	dpi=`echo "scale=5;sqrt($widthCurImg*72*$heightCurImg*72/$widthPDF/$heightPDF)+0.5" | bc`
-	dpi=`echo "scale=0;$dpi/1" | bc`
-	
-	# save the image characteristics
-	echo "DPI=$dpi" > "$curImgInfo"
-	echo "COLOR_SPACE=$colorspaceCurImg" >> "$curImgInfo"
-	echo "DEPTH=$depthCurImg" >> "$curImgInfo"
-	
-	return 0
-}
-
-
-page=`echo $PAGE_INFO | cut -f1 -d" "`
-[ $VERBOSITY -ge $LOG_INFO ] && echo "Processing page $page / $NUM_PAGES"
-
-# get width / height of PDF page (in pt)
-widthPDF=`echo $PAGE_INFO | cut -f2 -d" "`
-heightPDF=`echo $PAGE_INFO | cut -f3 -d" "`
-
-# create the name of the required temporary files
-curOrigImg="$TMP_FLD/${page}.orig-img"				# original image available in the current PDF page 
-								# (the image file may have a different orientation than in the pdf file)
-curHocr="$TMP_FLD/${page}.hocr"					# hocr file to be generated by the OCR SW for the current page
-curOCRedPDF="$TMP_FLD/${page}.ocred.pdf"			# PDF file containing the image + the OCRed text for the current page
-curOCRedPDFDebug="$TMP_FLD/${page}.ocred.todebug.pdf"		# PDF file containing data required to find out if OCR worked correctly
-curImgInfo="$TMP_FLD/${page}.orig-img-info.txt"			# Detected characteristics of the embedded image
-
-
-# auto-detect the characteristics of the embedded image
-depthCurImg="8"			# default color depth
-colorspaceCurImg="sRGB"		# default color space
-dpi=$DEFAULT_DPI		# default resolution
-
-getImgInfo "$page" "$widthPDF" "$heightPDF" "$curImgInfo"
-ret_code="$?"
-
-# in case the page contains text do not OCR, unless the FORCE_OCR flag is set
-if ([ "$ret_code" -eq "1" ] && [ "$FORCE_OCR" -eq "0" ]); then
-	echo "Page $page: Exiting... (Use the -f option to force OCRing, even though fonts are available in the input file)" && exit $EXIT_BAD_INPUT_FILE
-elif ([ "$ret_code" -eq "1" ] && [ "$FORCE_OCR" -eq "1" ]); then
-	[ $VERBOSITY -ge $LOG_WARN ] && echo "Page $page: OCRing anyway, assuming a default resolution of $dpi dpi"
-# in case the page contains more than one image, warn the user but go on with default parameters
-elif [ "$ret_code" -eq "2" ]; then
-	[ $VERBOSITY -ge $LOG_WARN ] && echo "Page $page: Continuing anyway, assuming a default resolution of $dpi dpi"
-else
-	# read the image characteristics from the file
-	dpi=`cat "$curImgInfo" | grep "^DPI=" | cut -f2 -d"="`
-	colorspaceCurImg=`cat "$curImgInfo" | grep "^COLOR_SPACE=" | cut -f2 -d"="`
-	depthCurImg=`cat "$curImgInfo" | grep "^DEPTH=" | cut -f2 -d"="`
-fi
-
-# perform oversampling if the resolution is not sufficient to get good OCR results
-if [ "$dpi" -lt "$OVERSAMPLING_DPI" ]; then
-	[ $VERBOSITY -ge $LOG_WARN ] && echo "Page $page: Low image resolution detected ($dpi dpi). Performing oversampling ($OVERSAMPLING_DPI dpi) to try to get better OCR results." 
-	dpi="$OVERSAMPLING_DPI"
-elif [ "$dpi" -lt "200" ]; then
-	[ $VERBOSITY -ge $LOG_WARN ] && echo "Page $page: Low image resolution detected ($dpi dpi). If needed, please use the \"-o\" to try to get better OCR results." 
-fi
-	
-# Identify if page image should be saved as ppm (color), pgm (gray) or pbm (b&w)
-ext="ppm" 	# by default (color image) the extension of the extracted image is ppm
-opt=""		# by default (color image) no option as to be passed to pdftoppm
-if [ "$colorspaceCurImg" = "Gray" ] && [ "$depthCurImg" = "1" ]; then		# if monochrome (b&w)
-	ext="pbm"
-	opt="-mono"
-elif [ "$colorspaceCurImg" = "Gray" ]; then					# if gray
-	ext="pgm"
-	opt="-gray"
-fi
-curImgPixmap="$TMP_FLD/$page.$ext"
-curImgPixmapDeskewed="$TMP_FLD/$page.deskewed.$ext"
-curImgPixmapClean="$TMP_FLD/$page.cleaned.$ext"
-
-# extract current page as image with correct orientation and resolution
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Extracting image as $ext file (${dpi} dpi)"
-! pdftoppm -f $page -l $page -r $dpi $opt "$FILE_INPUT_PDF" > "$curImgPixmap" \
-	&& echo "Could not extract page $page as $ext from \"$FILE_INPUT_PDF\". Exiting..." && exit $EXIT_OTHER_ERROR
-
-# if requested deskew image (without changing its size in pixel)
-widthCurImg=$(($dpi*$widthPDF/72))
-heightCurImg=$(($dpi*$heightPDF/72))
-if [ "$PREPROCESS_DESKEW" -eq "1" ]; then
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Deskewing image"
-	! convert "$curImgPixmap" -deskew 40% -gravity center -extent ${widthCurImg}x${heightCurImg} "$curImgPixmapDeskewed" \
-		&& echo "Could not deskew \"$curImgPixmap\". Exiting..." && exit $EXIT_OTHER_ERROR
-else
-	ln -s `basename "$curImgPixmap"` "$curImgPixmapDeskewed"
-fi
-
-# if requested clean image with unpaper to get better OCR results
-if [ "$PREPROCESS_CLEAN" -eq "1" ]; then
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Cleaning image with unpaper"
-	! unpaper --dpi $dpi --mask-scan-size 100 \
-		--no-deskew --no-grayfilter --no-blackfilter --no-mask-center --no-border-align \
-		"$curImgPixmapDeskewed" "$curImgPixmapClean" 1> /dev/null \
-		&& echo "Could not clean \"$curImgPixmapDeskewed\". Exiting..." && exit $EXIT_OTHER_ERROR
-else
-	ln -s `basename "$curImgPixmapDeskewed"` "$curImgPixmapClean"
-fi
-
-# perform OCR
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Performing OCR"
-! tesseract -l "$LAN" "$curImgPixmapClean" "$curHocr" hocr $TESS_CFG_FILES 1> /dev/null 2> /dev/null \
-	&& echo "Could not OCR file \"$curImgPixmapClean\". Exiting..." && exit $EXIT_OTHER_ERROR
-# Tesseract names the output files differently in some distributions.
-if [ -e "$curHocr.html" ]; then
-	mv "$curHocr.html" "$curHocr"
-elif [ -e "$curHocr.hocr" ]; then
-	mv "$curHocr.hocr" "$curHocr"
-elif [ ! -e "$curHocr" ]; then
-	echo "\"$curHocr[.html|.hocr]\" not found. Exiting..." && exit $EXIT_OTHER_ERROR
-fi
-
-# embed text and image to new pdf file
-if [ "$PREPROCESS_CLEANTOPDF" -eq "1" ]; then
-	image4finalPDF="$curImgPixmapClean"
-else
-	image4finalPDF="$curImgPixmapDeskewed"	
-fi
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Embedding text in PDF"
-! python2 $SRC/hocrTransform.py -r $dpi -i "$image4finalPDF" "$curHocr" "$curOCRedPDF" \
-	&& echo "Could not create PDF file from \"$curHocr\". Exiting..." && exit $EXIT_OTHER_ERROR
-
-# if requested generate special debug PDF page with visible OCR text
-if [ $PDF_NOIMG -eq "1" ] ; then
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Embedding text in PDF (debug page)"
-	! python2 $SRC/hocrTransform.py -b -r $dpi "$curHocr" "$curOCRedPDFDebug" \
-		&& echo "Could not create PDF file from \"$curHocr\". Exiting..." && exit $EXIT_OTHER_ERROR	
-fi
-
-# delete temporary files created for the current page
-# to avoid using to much disk space in case of PDF files having many pages
-if [ $KEEP_TMP -eq 0 ]; then
-	rm -f "$curOrigImg"*
-	rm -f "$curHocr"
-	rm -f "$curImgPixmap"
-	rm -f "$curImgPixmapDeskewed"
-	rm -f "$curImgPixmapClean"
-	rm -f "$curImgInfo"
-fi
-
-exit 0

src/test/OCRmyPDF_severaltimes.sh

@@ -1,15 +0,0 @@
-#!/bin/sh
-#
-# Perform OCR several times in order to find how quicly the quality decreases
-
-cpt=1
-
-while [ $cpt -le 10 ] ; do
-
-	echo "------- Itteration $cpt ---------"
-
-	! ../../OCRmyPDF.sh -vv -l deu -k ../../tmp/ocred-$(($cpt-1)).pdf ../../tmp/ocred-$cpt.pdf && exit 1
-	
-	cpt=$(($cpt+1))
-	
-done

src/test/README.md

@@ -1,4 +0,0 @@
-Note
-====
-
-The file(s) located in this folder are aimed at testing the OCRmyPDF script

test_requirements.txt

@@ -0,0 +1 @@
+pytest>=2.7.2

tests/resources/README.rst

@@ -0,0 +1,60 @@
+These test files are used in OCRmyPDF's test suite. They do not necessarily produce OCR results
+at all and are not meant as examples of OCR output. Some are even invalid PDFs that might
+crash certain PDF viewers.
+
+
+Files derived from free sources
+===============================
+
+These test resources come from free sources, under either public domain or Creative Commons licenses.
+In some cases they were converted from one image format to another without other changes.
+
++---------------------+--------------------------------------------------------------------------------+
+| File                | Source                                                                         |
++=====================+================================================================================+
+| c02-22.pdf          | `Project Gutenberg`_, Adventures of Huckleberry Finn, page 22                  |
++---------------------+--------------------------------------------------------------------------------+
+| congress.jpg        | `US Congressional Records`_                                                    |
++---------------------+--------------------------------------------------------------------------------+
+| graph.pdf           | `Wikimedia: Pandas text analysis.png`_                                         |
++---------------------+--------------------------------------------------------------------------------+
+| LinnSequencer.jpg   | `Wikimedia: LinnSequencer`_ (Creative Commons Attribution-ShareAlike 3.0)      |
++---------------------+--------------------------------------------------------------------------------+
+
+
+Files generated for this project
+================================
+
+The following test resources were crafted specifically for this project, and can be used
+under the terms of the license in LICENSE.rst.
+
+- blank.pdf (a blank PDF page)
+- cmyk.pdf (a CMYK image created in Photoshop)
+- enormous.pdf (a very lage page)
+- francais.pdf (a page containing French accented characters)
+- invalid.pdf (a PDF file header followed by EOF marker)
+- missing_docinfo.pdf (PDF file with no /DocumentInfo section)
+
+
+Assemblies
+==========
+
+These test resources are assemblies from other previously mentioned files, released under the same license terms as their input files.
+
+- cardinal.pdf (four cardinal directions, rotated copies of LinnSequencer.jpg)
+- ccitt.pdf (LinnSequencer.jpg, converted to CCITT encoding)
+- graph_ocred.pdf (from graph.pdf)
+- jbig2.pdf (congress.jpg, converted to JBIG2 encoding)
+- multipage.pdf (from several other files)
+- palette.pdf (congress.jpg, converted to a 256-color palette)
+- skew.pdf (from c02-22.pdf)
+- skew-encrypted.pdf (skew.pdf with encrypted applied)
+
+
+.. _`Wikimedia: LinnSequencer`: https://upload.wikimedia.org/wikipedia/en/b/b7/LinnSequencer_hardware_MIDI_sequencer_brochure_page_2_300dpi.jpg
+
+.. _`Project Gutenberg`: https://www.gutenberg.org/files/76/76-h/76-h.htm#c2
+
+.. _`US Congressional Records`: http://www.baxleystamps.com/litho/meiji/courts_1871.jpg
+
+.. _`Wikimedia: Pandas text analysis.png`: https://en.wikipedia.org/wiki/File:Pandas_text_analysis.png

tests/resources/invalid.pdf

@@ -0,0 +1,3 @@
+%PDF-1.3
+This is not a valid PDF file
+%%EOF

tests/resources/missing_docinfo.pdf

@@ -0,0 +1,41 @@
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Outlines 2 0 R /PageMode /UseNone /Pages 3 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 0 /Type /Outlines >>
+endobj
+3 0 obj
+<< /Count 1 /Kids [ 4 0 R ] /Type /Pages >>
+endobj
+4 0 obj
+<< /Contents 5 0 R /MediaBox [ 0 0 595.2756 841.8898 ] /Parent 3 0 R /Resources << /Font 6 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ] >> /Rotate 0 /Trans << >> /Type /Page >>
+endobj
+5 0 obj
+<< /Length 104 /Filter /FlateDecode >>
+stream
+xœ-Œ1
+ƒ@{O1e´ˆûEI¢ Xþè⢉»[¨÷Wƒ<˜bž`ÎÉŸÖÃ[ÉA
+Ô!å³D;jMN/w*Æðªêyè4¯¸y™ú•É?Ñî~[\dX¢ý¥èÍ®’™…endstream
+endobj
+6 0 obj
+<< /F1 7 0 R >>
+endobj
+7 0 obj
+<< /BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font >>
+endobj
+xref
+0 8
+0000000000 65535 f 
+0000000015 00000 n 
+0000000099 00000 n 
+0000000145 00000 n 
+0000000204 00000 n 
+0000000403 00000 n 
+0000000578 00000 n 
+0000000609 00000 n 
+trailer << /Root 1 0 R /Size 8 /ID [<85bf6c3c41ed927eb43bdfdfff4c0cb5><0304c5f87e589cb7b06f6f52dc6e6707>] >>
+startxref
+716
+%%EOF

tests/spoof/qpdf_dummy_return2.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python3
+import sys
+
+
+def main():
+    print('qpdf dummy')
+    sys.exit(2)
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/tesseract_cache.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+import sys
+import os
+import hashlib
+import shutil
+import subprocess
+
+
+CACHE_PATH = os.path.abspath(os.path.join(
+        os.path.dirname(__file__), '..', 'cache'))
+
+
+def real_tesseract():
+    tess_args = ['tesseract'] + sys.argv[1:]
+    os.execvp("tesseract", tess_args)
+    return  # Not reachable
+
+def main():
+    operation = sys.argv[-1]
+    # For anything unexpected operation, defer to real tesseract binary
+    if operation != 'hocr' and operation != 'pdf' and operation != 'stdout':
+        real_tesseract()
+        return  # Not reachable
+
+    try:
+        os.makedirs(CACHE_PATH)
+    except FileExistsError:
+        pass
+
+    m = hashlib.sha1()
+
+    version = subprocess.check_output(
+        ['tesseract', '--version'],
+        stderr=subprocess.STDOUT)
+
+    m.update(version)
+    m.update(operation.encode())
+
+    try:
+        lang = sys.argv[sys.argv.index('-l') + 1]
+        m.update(lang.encode())
+    except ValueError:
+        pass
+    try:
+        psm = sys.argv[sys.argv.index('-psm') + 1]
+        m.update(psm.encode())
+    except ValueError:
+        pass
+
+    if operation == 'stdout' and psm != '0':
+        real_tesseract()
+        return
+
+    if operation == 'stdout':
+        input_file = sys.argv[-2]
+        output_file = 'stdout'
+    else:
+        input_file = sys.argv[-3]
+        output_file = sys.argv[-2]
+
+    if operation == 'hocr':
+        output_file += '.hocr'
+    elif operation == 'pdf':
+        output_file += '.pdf'
+
+    with open(input_file, 'rb') as f:
+        m.update(f.read())
+    cache_name = os.path.join(CACHE_PATH, m.hexdigest())
+    print(cache_name)
+    if os.path.exists(cache_name):
+        # Cache hit
+        print("Tesseract cache hit", file=sys.stderr)
+        if operation != 'stdout':
+            shutil.copy(cache_name, output_file)
+
+        # Replicate output
+        with open(cache_name + '.stdout', 'r') as f:
+            print(f.read(), end='')
+        with open(cache_name + '.stderr', 'r') as f:
+            print(f.read(), end='', file=sys.stderr)
+        sys.exit(0)
+
+    # Cache miss
+    print("Tesseract cache miss", file=sys.stderr)
+
+    # Call tesseract
+    p = subprocess.Popen(
+            ['tesseract'] + sys.argv[1:],
+            stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+            universal_newlines=True)
+    stdout, stderr = p.communicate()
+
+    with open(cache_name + '.stdout', 'w') as f:
+        f.write(stdout)
+    with open(cache_name + '.stderr', 'w') as f:
+        f.write(stderr)
+    print(stdout, end='')
+    print(stderr, end='', file=sys.stderr)
+
+    # Insert file into cache
+    if output_file != 'stdout':
+        if os.path.exists(output_file):
+            shutil.copy(output_file, cache_name)
+        else:
+            print("Could not find output file", file=sys.stderr)
+    else:
+        open(cache_name, 'w').close()
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/tesseract_noop.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+import sys
+import img2pdf
+from PIL import Image
+
+
+VERSION_STRING = '''tesseract 3.04.00
+ leptonica-1.72
+  libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5
+SPOOFED
+'''
+
+HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+  <meta name='ocr-system' content='tesseract 3.02.02' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
+    <p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
+     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>'''
+
+
+def main():
+    if sys.argv[1] == '--version':
+        print(VERSION_STRING, file=sys.stderr)
+        sys.exit(0)
+    elif sys.argv[1] == '--list-langs':
+        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 Image.open(inputf) as im, \
+                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]
+        pdf_bytes = img2pdf.convert([inputf], dpi=300)
+        with open(output + '.pdf', 'wb') as f:
+            f.write(pdf_bytes)
+    elif sys.argv[-1] == 'stdout':
+        inputf = sys.argv[-2]
+        print("""Orientation: 0
+Orientation in degrees: 0
+Orientation confidence: 100.00
+Script: 1
+Script confidence: 100.00""", file=sys.stderr)
+    else:
+        print("Spoof doesn't understand arguments", file=sys.stderr)
+        print(sys.argv, file=sys.stderr)
+        sys.exit(1)
+
+    sys.exit(0)
+
+
+if __name__ == '__main__':
+    main()

tests/test_hocrtransform.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from ocrmypdf import hocrtransform
+from ocrmypdf.tesseract import HOCR_TEMPLATE
+from reportlab.pdfgen.canvas import Canvas
+from PIL import Image
+from tempfile import NamedTemporaryFile
+from contextlib import suppress
+import os
+import shutil
+import pytest
+import img2pdf
+import pytest
+import sys
+
+
+if sys.version_info.major < 3:
+    print("Requires Python 3.4+")
+    sys.exit(1)
+
+TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
+SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
+PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
+OCRMYPDF = os.path.join(PROJECT_ROOT, 'OCRmyPDF.sh')
+TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
+TEST_OUTPUT = os.environ.get(
+    'OCRMYPDF_TEST_OUTPUT',
+    default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'hocrtransform'))
+
+
+def setup_module():
+    with suppress(FileNotFoundError):
+        shutil.rmtree(TEST_OUTPUT)
+    with suppress(FileExistsError):
+        os.makedirs(TEST_OUTPUT)
+    with open(_make_output('blank.hocr'), 'w') as f:
+        f.write(HOCR_TEMPLATE)
+
+
+def _make_input(input_basename):
+    return os.path.join(TEST_RESOURCES, input_basename)
+
+
+def _make_output(output_basename):
+    return os.path.join(TEST_OUTPUT, output_basename)
+
+
+def test_mono_image():
+    im = Image.new('1', (8, 8), 0)
+    for n in range(8):
+        im.putpixel((n, n), 1)
+    im.save(_make_output('mono.tif'), format='TIFF')
+
+    hocr = hocrtransform.HocrTransform(_make_output('blank.hocr'), 300)
+    hocr.to_pdf(_make_output('mono.pdf'), imageFileName=_make_output('mono.tif'))
+
+
+
+
+

tests/test_main.py

@@ -0,0 +1,441 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from __future__ import print_function
+from subprocess import Popen, PIPE, check_output, check_call
+import os
+import shutil
+from contextlib import suppress
+import sys
+import pytest
+from ocrmypdf.pageinfo import pdf_get_all_pageinfo
+import PyPDF2 as pypdf
+from ocrmypdf import ExitCode
+from ocrmypdf import leptonica
+
+
+if sys.version_info.major < 3:
+    print("Requires Python 3.4+")
+    sys.exit(1)
+
+TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
+SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
+PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
+OCRMYPDF = os.path.join(PROJECT_ROOT, 'OCRmyPDF.sh')
+TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
+TEST_OUTPUT = os.environ.get(
+    'OCRMYPDF_TEST_OUTPUT',
+    default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'main'))
+
+
+def setup_module():
+    with suppress(FileNotFoundError):
+        shutil.rmtree(TEST_OUTPUT)
+    with suppress(FileExistsError):
+        os.makedirs(TEST_OUTPUT)
+
+
+def run_ocrmypdf_sh(input_file, output_file, *args, env=None):
+    sh_args = ['sh', OCRMYPDF] + list(args) + [input_file, output_file]
+    sh = Popen(
+        sh_args, close_fds=True, stdout=PIPE, stderr=PIPE,
+        universal_newlines=True, env=env)
+    out, err = sh.communicate()
+    return sh, out, err
+
+
+def _infile(input_basename):
+    return os.path.join(TEST_RESOURCES, input_basename)
+
+
+def _outfile(output_basename):
+    return os.path.join(TEST_OUTPUT, os.path.basename(output_basename))
+
+
+def check_ocrmypdf(input_basename, output_basename, *args, env=None):
+    input_file = _infile(input_basename)
+    output_file = _outfile(output_basename)
+
+    sh, out, err = run_ocrmypdf_sh(input_file, output_file, *args, env=env)
+    if sh.returncode != 0:
+        print('stdout\n======')
+        print(out)
+        print('stderr\n======')
+        print(err)
+    assert sh.returncode == 0
+    assert os.path.exists(output_file), "Output file not created"
+    assert os.stat(output_file).st_size > 100, "PDF too small or empty"
+    return output_file
+
+
+def run_ocrmypdf_env(input_basename, output_basename, *args, env=None):
+    input_file = _infile(input_basename)
+    output_file = _outfile(output_basename)
+
+    if env is None:
+        env = os.environ
+
+    p_args = ['ocrmypdf'] + list(args) + [input_file, output_file]
+    p = Popen(
+        p_args, close_fds=True, stdout=PIPE, stderr=PIPE,
+        universal_newlines=True, env=env)
+    out, err = p.communicate()
+    return p, out, err
+
+
+@pytest.fixture
+def spoof_tesseract_noop():
+    env = os.environ.copy()
+    program = os.path.join(SPOOF_PATH, 'tesseract_noop.py')
+    check_call(['chmod', "+x", program])
+    env['OCRMYPDF_TESSERACT'] = program
+    return env
+
+
+@pytest.fixture
+def spoof_tesseract_cache():
+    env = os.environ.copy()
+    program = os.path.join(SPOOF_PATH, "tesseract_cache.py")
+    check_call(['chmod', '+x', program])
+    env['OCRMYPDF_TESSERACT'] = program
+    return env
+
+
+def test_quick(spoof_tesseract_noop):
+    check_ocrmypdf('c02-22.pdf', 'test_quick.pdf', env=spoof_tesseract_noop)
+
+
+def test_deskew(spoof_tesseract_noop):
+    # Run with deskew
+    deskewed_pdf = check_ocrmypdf(
+        'skew.pdf', 'test_deskew.pdf', '-d', '-v', '1', env=spoof_tesseract_noop)
+
+    # Now render as an image again and use Leptonica to find the skew angle
+    # to confirm that it was deskewed
+    from ocrmypdf.ghostscript import rasterize_pdf
+    import logging
+    log = logging.getLogger()
+
+    deskewed_png = _outfile('deskewed.png')
+
+    rasterize_pdf(
+        deskewed_pdf,
+        deskewed_png,
+        xres=150,
+        yres=150,
+        raster_device='pngmono',
+        log=log)
+
+    from ocrmypdf.leptonica import Pix
+    pix = Pix.read(deskewed_png)
+    skew_angle, skew_confidence = pix.find_skew()
+
+    print(skew_angle)
+    assert -0.5 < skew_angle < 0.5, "Deskewing failed"
+
+
+def test_clean(spoof_tesseract_noop):
+    check_ocrmypdf('skew.pdf', 'test_clean.pdf', '-c', env=spoof_tesseract_noop)
+
+
+@pytest.mark.parametrize("pdf,renderer", [
+    ('palette.pdf', 'hocr'),
+    ('palette.pdf', 'tesseract'),
+    ('cmyk.pdf', 'hocr'),
+    ('cmyk.pdf', 'tesseract'),
+    ('ccitt.pdf', 'hocr'),
+    ('ccitt.pdf', 'tesseract'),
+    ('jbig2.pdf', 'hocr'),
+    ('jbig2.pdf', 'tesseract')
+])
+def test_exotic_image(spoof_tesseract_cache, pdf, renderer):
+    check_ocrmypdf(
+        pdf,
+        'test_{0}_{1}.pdf'.format(pdf, renderer),
+        '-dc',
+        '-v', '1',
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+
+def test_preserve_metadata(spoof_tesseract_noop):
+    pdf_before = pypdf.PdfFileReader(_infile('graph.pdf'))
+
+    output = check_ocrmypdf('graph.pdf', 'test_metadata_preserve.pdf',
+                            env=spoof_tesseract_noop)
+
+    pdf_after = pypdf.PdfFileReader(output)
+
+    for key in ('/Title', '/Author'):
+        assert pdf_before.documentInfo[key] == pdf_after.documentInfo[key]
+
+
+def test_override_metadata(spoof_tesseract_noop):
+    input_file = _infile('c02-22.pdf')
+    output_file = _outfile('test_override_metadata.pdf')
+
+    german = 'Du siehst den Wald vor lauter Bäumen nicht.'
+    chinese = '孔子'
+    high_unicode = 'U+1030C is: 𐌌'
+
+    p, out, err = run_ocrmypdf_env(
+        input_file, output_file,
+        '--title', german,
+        '--author', chinese,
+        '--subject', high_unicode,
+        env=spoof_tesseract_noop)
+
+    assert p.returncode == ExitCode.ok
+
+    pdf = output_file
+
+    out_pdfinfo = check_output(['pdfinfo', pdf], universal_newlines=True)
+    lines_pdfinfo = out_pdfinfo.splitlines()
+    pdfinfo = {}
+    for line in lines_pdfinfo:
+        k, v = line.strip().split(':', maxsplit=1)
+        pdfinfo[k.strip()] = v.strip()
+
+    assert pdfinfo['Title'] == german
+    assert pdfinfo['Author'] == chinese
+    assert pdfinfo['Subject'] == high_unicode
+    assert pdfinfo.get('Keywords', '') == ''
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_oversample(spoof_tesseract_cache, renderer):
+    oversampled_pdf = check_ocrmypdf(
+        'skew.pdf', 'test_oversample_%s.pdf' % renderer, '--oversample', '350',
+        '-f',
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+    pdfinfo = pdf_get_all_pageinfo(oversampled_pdf)
+
+    print(pdfinfo[0]['xres'])
+    assert abs(pdfinfo[0]['xres'] - 350) < 1
+
+
+def test_repeat_ocr():
+    sh, _, _ = run_ocrmypdf_sh('graph_ocred.pdf', 'wontwork.pdf')
+    assert sh.returncode != 0
+
+
+def test_force_ocr(spoof_tesseract_cache):
+    out = check_ocrmypdf('graph_ocred.pdf', 'test_force.pdf', '-f',
+                         env=spoof_tesseract_cache)
+    pdfinfo = pdf_get_all_pageinfo(out)
+    assert pdfinfo[0]['has_text']
+
+
+def test_skip_ocr(spoof_tesseract_cache):
+    check_ocrmypdf('graph_ocred.pdf', 'test_skip.pdf', '-s',
+                   env=spoof_tesseract_cache)
+
+
+def test_argsfile(spoof_tesseract_noop):
+    with open(_outfile('test_argsfile.txt'), 'w') as argsfile:
+        print('--title', 'ArgsFile Test', '--author', 'Test Cases',
+              sep='\n', end='\n', file=argsfile)
+    check_ocrmypdf('graph.pdf', 'test_argsfile.pdf',
+                   '@' + _outfile('test_argsfile.txt'),
+                   env=spoof_tesseract_noop)
+
+
+def check_monochrome_correlation(
+        reference_pdf, reference_pageno, test_pdf, test_pageno):
+
+    import ocrmypdf.ghostscript as ghostscript
+    import logging
+
+    gslog = logging.getLogger()
+
+    reference_png = _outfile('{}.ref{:04d}.png'.format(
+        reference_pdf, reference_pageno))
+    test_png = _outfile('{}.test{:04d}.png'.format(
+        test_pdf, test_pageno))
+
+    def rasterize(pdf, pageno, png):
+        if os.path.exists(png):
+            print(png)
+            return
+        ghostscript.rasterize_pdf(
+            pdf,
+            png,
+            xres=100, yres=100,
+            raster_device='pngmono', log=gslog, pageno=pageno)
+
+    rasterize(reference_pdf, reference_pageno, reference_png)
+    rasterize(test_pdf, test_pageno, test_png)
+
+    pix_ref = leptonica.Pix.read(reference_png)
+    pix_test = leptonica.Pix.read(test_png)
+
+    return leptonica.Pix.correlation_binary(pix_ref, pix_test)
+
+
+def test_monochrome_correlation():
+    # Verify leptonica: check that an incorrect rotated image has poor
+    # correlation with reference
+    corr = check_monochrome_correlation(
+        reference_pdf=_infile('cardinal.pdf'),
+        reference_pageno=1,  # north facing page
+        test_pdf=_infile('cardinal.pdf'),
+        test_pageno=3,  # south facing page
+        )
+    assert corr < 0.10
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_autorotate(spoof_tesseract_cache, renderer):
+    import ocrmypdf.ghostscript as ghostscript
+    import logging
+
+    gslog = logging.getLogger()
+
+    # cardinal.pdf contains four copies of an image rotated in each cardinal
+    # direction - these ones are "burned in" not tagged with /Rotate
+    out = check_ocrmypdf('cardinal.pdf', 'test_autorotate_%s.pdf' % renderer,
+                         '-r', '-v', '1', env=spoof_tesseract_cache)
+    for n in range(1, 4+1):
+        correlation = check_monochrome_correlation(
+            reference_pdf=_infile('cardinal.pdf'),
+            reference_pageno=1,
+            test_pdf=out,
+            test_pageno=n)
+        assert correlation > 0.80
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_ocr_timeout(renderer):
+    out = check_ocrmypdf('skew.pdf', 'test_timeout_%s.pdf' % renderer,
+                         '--tesseract-timeout', '1.0')
+    pdfinfo = pdf_get_all_pageinfo(out)
+    assert not pdfinfo[0]['has_text']
+
+
+def test_skip_big(spoof_tesseract_cache):
+    out = check_ocrmypdf('enormous.pdf', 'test_enormous.pdf',
+                         '--skip-big', '10', env=spoof_tesseract_cache)
+    pdfinfo = pdf_get_all_pageinfo(out)
+    assert not pdfinfo[0]['has_text']
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_maximum_options(spoof_tesseract_cache, renderer):
+    check_ocrmypdf(
+        'multipage.pdf', 'test_multipage%s.pdf' % renderer,
+        '-d', '-c', '-i', '-g', '-f', '-k', '--oversample', '300',
+        '--skip-big', '10', '--title', 'Too Many Weird Files',
+        '--author', 'py.test', '--pdf-renderer', renderer,
+        env=spoof_tesseract_cache)
+
+
+def test_tesseract_missing_tessdata():
+    env = os.environ.copy()
+    env['TESSDATA_PREFIX'] = '/tmp'
+
+    p, _, err = run_ocrmypdf_env(
+        'graph_ocred.pdf', 'not_a_pdfa.pdf', '-v', '1', '--skip-text', env=env)
+    assert p.returncode == ExitCode.missing_dependency, err
+
+
+def test_invalid_input_pdf():
+    p, out, err = run_ocrmypdf_env(
+        'invalid.pdf', 'wont_be_created.pdf')
+    assert p.returncode == ExitCode.input_file, err
+
+
+def test_blank_input_pdf():
+    p, out, err = run_ocrmypdf_env(
+        'blank.pdf', 'still_blank.pdf')
+    assert p.returncode == ExitCode.ok
+
+
+def test_french(spoof_tesseract_cache):
+    p, out, err = run_ocrmypdf_env(
+        'francais.pdf', 'francais.pdf', '-l', 'fra', env=spoof_tesseract_cache)
+    assert p.returncode == ExitCode.ok, \
+        "This test may fail if Tesseract language packs are missing"
+
+
+def test_klingon():
+    p, out, err = run_ocrmypdf_env(
+        'francais.pdf', 'francais.pdf', '-l', 'klz')
+    assert p.returncode == ExitCode.bad_args
+
+
+def test_missing_docinfo(spoof_tesseract_noop):
+    p, out, err = run_ocrmypdf_env(
+        'missing_docinfo.pdf', 'missing_docinfo.pdf', '-l', 'eng', '-c',
+        env=spoof_tesseract_noop)
+    assert p.returncode == ExitCode.ok, err
+
+
+def test_uppercase_extension(spoof_tesseract_noop):
+    shutil.copy(_infile("skew.pdf"), _infile("UPPERCASE.PDF"))
+    try:
+        check_ocrmypdf("UPPERCASE.PDF", "UPPERCASE_OUT.PDF",
+                       env=spoof_tesseract_noop)
+    finally:
+        os.unlink(_infile("UPPERCASE.PDF"))
+
+
+def test_input_file_not_found():
+    input_file = "does not exist.pdf"
+    sh, out, err = run_ocrmypdf_sh(
+        _infile(input_file),
+        _outfile("will not happen.pdf"))
+    assert sh.returncode == ExitCode.input_file
+    assert (input_file in out or input_file in err)
+
+
+def test_input_file_not_a_pdf():
+    input_file = __file__  # Try to OCR this file
+    sh, out, err = run_ocrmypdf_sh(
+        _infile(input_file),
+        _outfile("will not happen.pdf"))
+    assert sh.returncode == ExitCode.input_file
+    assert (input_file in out or input_file in err)
+
+
+def test_qpdf_repair_fails():
+    env = os.environ.copy()
+    env['OCRMYPDF_QPDF'] = os.path.abspath('./spoof/qpdf_dummy_return2.py')
+    p, out, err = run_ocrmypdf_env(
+        '-v', '1',
+        'c02-22.pdf', 'wont_be_created.pdf', env=env)
+    print(out)
+    print(err)
+    assert p.returncode == ExitCode.input_file
+
+
+def test_encrypted():
+    p, out, err = run_ocrmypdf_env('skew-encrypted.pdf', 'wont_be_created.pdf')
+    assert p.returncode == ExitCode.input_file
+    assert out.find('password')
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_pagesegmode(renderer, spoof_tesseract_cache):
+    check_ocrmypdf(
+        'skew.pdf', 'test_psm_%s.pdf' % renderer,
+        '--tesseract-pagesegmode', '7',
+        '-v', '1',
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+
+

tests/test_pageinfo.py

@@ -0,0 +1,134 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from ocrmypdf import pageinfo
+from reportlab.pdfgen.canvas import Canvas
+from PIL import Image
+from tempfile import NamedTemporaryFile
+from contextlib import suppress
+import os
+import shutil
+import pytest
+import img2pdf
+import pytest
+import sys
+
+
+if sys.version_info.major < 3:
+    print("Requires Python 3.4+")
+    sys.exit(1)
+
+TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
+SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
+PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
+OCRMYPDF = os.path.join(PROJECT_ROOT, 'OCRmyPDF.sh')
+TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
+TEST_OUTPUT = os.environ.get(
+    'OCRMYPDF_TEST_OUTPUT',
+    default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'pageinfo'))
+
+
+def setup_module():
+    with suppress(FileNotFoundError):
+        shutil.rmtree(TEST_OUTPUT)
+    with suppress(FileExistsError):
+        os.makedirs(TEST_OUTPUT)
+
+
+def _make_input(input_basename):
+    return os.path.join(TEST_RESOURCES, input_basename)
+
+
+def _make_output(output_basename):
+    return os.path.join(TEST_OUTPUT, output_basename)
+
+
+def test_single_page_text():
+    filename = os.path.join(TEST_OUTPUT, 'text.pdf')
+    pdf = Canvas(filename, pagesize=(8*72, 6*72))
+    text = pdf.beginText()
+    text.setFont('Helvetica', 12)
+    text.setTextOrigin(1*72, 3*72)
+    text.textLine("Methink'st thou art a general offence and every"
+                  " man should beat thee.")
+    pdf.drawText(text)
+    pdf.showPage()
+    pdf.save()
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+
+    assert len(pdfinfo) == 1
+    page = pdfinfo[0]
+
+    assert page['has_text']
+    assert len(page['images']) == 0
+
+
+def test_single_page_image():
+    filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
+
+    with NamedTemporaryFile(mode='wb+', suffix='.png') as im_tmp:
+        im = Image.new('1', (8, 8), 0)
+        for n in range(8):
+            im.putpixel((n, n), 1)
+        im.save(im_tmp.name, format='PNG')
+
+        imgsize = ((img2pdf.ImgSize.dpi, 8), (img2pdf.ImgSize.dpi, 8))
+        layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
+
+        im_tmp.seek(0)
+        im_bytes = im_tmp.read()
+        pdf_bytes = img2pdf.convert(
+                im_bytes, producer="img2pdf", with_pdfrw=False,
+                layout_fun=layout_fun)
+
+        with open(filename, 'wb') as pdf:
+            pdf.write(pdf_bytes)
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+
+    assert len(pdfinfo) == 1
+    page = pdfinfo[0]
+
+    assert not page['has_text']
+    assert len(page['images']) == 1
+
+    pdfimage = page['images'][0]
+    assert pdfimage['width'] == 8
+    assert pdfimage['color'] == 'gray'
+
+    # While unexpected, this is correct
+    # PDF spec says /FlateDecode image must have /BitsPerComponent 8
+    # So mono images get upgraded to 8-bit
+    assert pdfimage['bpc'] == 8
+
+    # DPI in a 1"x1" is the image width
+    assert pdfimage['dpi_w'] == 8
+    assert pdfimage['dpi_h'] == 8
+
+
+def test_single_page_inline_image():
+    filename = os.path.join(TEST_OUTPUT, 'image-mono-inline.pdf')
+    pdf = Canvas(filename, pagesize=(8*72, 6*72))
+    with NamedTemporaryFile() as im_tmp:
+        im = Image.new('1', (8, 8), 0)
+        for n in range(8):
+            im.putpixel((n, n), 1)
+        im.save(im_tmp.name, format='PNG')
+        # Draw image in a 72x72 pt or 1"x1" area
+        pdf.drawInlineImage(im_tmp.name, 0, 0, width=72, height=72)
+        pdf.showPage()
+        pdf.save()
+
+    with pytest.raises(NotImplementedError):
+        pageinfo.pdf_get_all_pageinfo(filename)
+
+
+def test_jpeg():
+    filename = _make_input('c02-22.pdf')
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+
+    pdfimage = pdfinfo[0]['images'][0]
+    assert pdfimage['enc'] == 'jpeg'
+