readme updated for v1.0-stable

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)

.gitattributes

@@ -0,0 +1,8 @@
+# Always use Unix convention for new lines
+* text eol=lf
+
+# These files are binary and should be left untouched
+# (binary is a macro for -text -diff)
+*.jar	binary
+*.pdf	binary
+*.PDF	binary

.gitignore

@@ -0,0 +1,2 @@
+tmp/
+log/

.travis.yml

@@ -1,29 +0,0 @@
-
-language: generic
-sudo: required
-dist: trusty
-
-before_install:
-  - sudo add-apt-repository ppa:heyarje/libav-11 -y
-  - sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
-  - sudo add-apt-repository ppa:evl.ms/evil -y  # for a newer version (2.5.0) of pngquant
-  - sudo apt-get update -qq
-  - sudo apt-get install libleptonica-dev -y    # required to build jbig2enc
-  - sudo apt-get install zlib1g-dev -y          # required to build jbig2enc
- # - sudo apt-get install imagemagick -y         # required to convert logo to desktop icon
-
-script:
-  - export OCRMYPDF_VERSION=8.3.2
-  - bash build-appimage.sh
-  # remove previous installed libraries to ensure that the tests use the libraries of the AppImage
-  - sudo apt-get remove libleptonica-dev zlib1g-dev -y
-  - bash test/test-appimage.sh
-  - wget https://github.com/probonopd/uploadtool/raw/master/upload.sh
-
-after_success:
-  - bash upload.sh OCRmyPDF*.AppImage
-
-branches:
-  except:
-    # Do not build tags that we create when we upload to GitHub Releases
-    - /^(?i:continuous)/

COPYRIGHT.md

@@ -0,0 +1,17 @@
+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.

OCRmyPDF.sh

@@ -0,0 +1,363 @@
+#!/bin/sh
+##############################################################################
+# Copyright (c) 2013: fritz-hh from Github (https://github.com/fritz-hh)
+##############################################################################
+
+TOOLNAME="OCRmyPDF"
+VERSION="v1.0-stable"
+
+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 from NAS4Free forum
+Version: $VERSION
+
+Usage: OCRmyPDF.sh  [-h] [-v] [-g] [-k] [-d] [-c] [-i] [-l language] [-C filename] inputfile outputfile
+
+-h : Display this help message
+-v : Increase the verbosity (this option can be used more than once)
+-k : Do not delete the temporary files
+-g : Activate debug mode:
+     - Generates a PDF file containing each page twice (once with the image, once without the image
+       but with the OCRed text as well as the detected bounding boxes)
+     - Set the verbosity to the highest possible
+     - Do not delete the temporary files
+-d : Deskew each page before performing OCR
+-c : Clean each page before performing OCR
+-i : Incorporate the cleaned image in the final PDF file (by default the original image	
+     image, or the deskewed image if the -d option is set, is incorporated)
+-l : Set the language of the PDF file in order to improve OCR results (default "eng")
+     Any language supported by tesseract is supported.
+-C : Pass an additional configuration file to the tesseract OCR engine.
+     (this option can be used more than once)
+     Note: The configuration file must be available in the "tessdata/configs" folder
+     of your tesseract installation
+inputfile  : PDF file to be OCRed
+outputfile : The PDF/A file to be generated 
+--------------------------------------------------------------------------------------
+EOF
+}
+
+
+#################################################
+# Get an absolute path from a relative path to a file
+#
+# Param1 : Relative path
+# Returns: 1 if the folder in which the file is located does not exist
+#          0 otherwise
+################################################# 
+absolutePath() {
+	local wdsave absolutepath 
+	wdsave="$(pwd)"
+	! cd "$(dirname "$1")" 1> /dev/null 2> /dev/null && return 1
+	absolutepath="$(pwd)/$(basename "$1")"
+	cd "$wdsave"
+	echo "$absolutepath"
+	return 0
+}
+
+
+
+# Initialization of constants
+EXIT_BAD_ARGS="1"		# possible exit codes
+EXIT_BAD_INPUT_FILE="2"
+EXIT_MISSING_DEPENDENCY="3"
+EXIT_INVALID_OUPUT_PDFA="4"
+EXIT_OTHER_ERROR="5"
+LOG_ERR="0"			# 0=only error messages
+LOG_INFO="1"			# 1=error messages and some infos
+LOG_DEBUG="2"			# 2=debug level logging
+SRC="./src"				# location of the source folder (except source of external tools like jhove)
+JHOVE="./jhove/bin/JhoveApp.jar"	# java SW for validating the final PDF/A
+JHOVE_CFG="./jhove/conf/jhove.conf"	# location of the jhove config file
+
+# Initialization the configuration parameters with default values
+VERBOSITY="$LOG_ERR"		# default verbosity level
+LAN="eng"			# default language of the PDF file (required to get good OCR results)
+KEEP_TMP="0"			# do not delete the temporary files (default)
+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)
+PDF_NOIMG="0"			# 0=no, 1=yes (generates each PDF page twice, with and without image)
+TESS_CFG_FILES=""		# list of additional configuration files to be used by tesseract
+
+# Parse optional command line arguments
+while getopts ":hvgkdcil:C:" opt; do
+	case $opt in
+		h) usage ; exit 0 ;;
+		v) VERBOSITY=$(($VERBOSITY+1)) ;;
+		k) KEEP_TMP="1" ;;
+		g) PDF_NOIMG="1"; VERBOSITY="10"; KEEP_TMP="1" ;;
+		d) PREPROCESS_DESKEW="1" ;;
+		c) PREPROCESS_CLEAN="1" ;;
+		i) PREPROCESS_CLEANTOPDF="1" ;;
+		l) LAN="$OPTARG" ;;
+		C) TESS_CFG_FILES="$OPTARG $TESS_CFG_FILES" ;;
+		\?)
+			echo "Invalid option: -$OPTARG" >&2
+			usage
+			exit $EXIT_BAD_ARGS ;;
+		:)
+			echo "Option -$OPTARG requires an argument" >&2
+			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)" >&2
+	usage
+	exit $EXIT_BAD_ARGS
+fi
+
+! absolutePath "$1" > /dev/null && echo "The folder in which the input file should be located does not exist. Exiting..." >&2 && 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..." >&2 && exit $EXIT_BAD_ARGS
+FILE_OUTPUT_PDFA="`absolutePath "$2"`"
+
+
+
+# set script path as working directory
+cd "`dirname $0`"
+
+[ $VERBOSITY -ge $LOG_INFO ] && echo "$TOOLNAME version: $VERSION"
+
+# 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..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+! command -v pdfimages > /dev/null && echo "Please install poppler-utils. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+! command -v pdftoppm > /dev/null && echo "Please install poppler-utils. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+! command -v pdftk > /dev/null && echo "Please install pdftk. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+[ $PREPROCESS_CLEAN -eq 1 ] && ! command -v unpaper > /dev/null && echo "Please install unpaper. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+! command -v tesseract > /dev/null && echo "Please install tesseract and tesseract-data. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+! command -v python > /dev/null && echo "Please install python, and the python libraries: reportlab, lxml. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+! command -v gs > /dev/null && echo "Please install ghostcript. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+! command -v java > /dev/null && echo "Please install java. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
+
+
+
+
+# Initialize path to temporary files
+today=$(date +"%Y%m%d_%H%M")
+fld=$(basename "$FILE_INPUT_PDF" | sed 's/[.][^.]*//')
+TMP_FLD="./tmp/$today.filename.$fld"
+FILE_TMP="$TMP_FLD/tmp.txt"						# temporary file with a very short lifetime (may be used for several things)
+FILE_SIZE_PAGES="$TMP_FLD/page-sizes.txt"				# size in pt of the respective page of the input PDF file
+FILE_OUTPUT_PDF_CAT="${TMP_FLD}/ocred.pdf"				# concatenated OCRed PDF files
+FILE_OUTPUT_PDFA_WO_META="${TMP_FLD}/ocred-pdfa-wo-metadata.pdf"	# PDFA file before appending metadata
+FILE_VALIDATION_LOG="${TMP_FLD}/pdf_validation.log"			# log file containing the results of the validation of the PDF/A file
+
+# Create tmp folder
+[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Creating temporary folder: \"$TMP_FLD\""
+rm -r -f "${TMP_FLD}"
+mkdir -p "${TMP_FLD}"
+
+
+
+
+# get the size of each pdf page (width / height) in pt (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..." >&2 && exit $EXIT_BAD_INPUT_FILE
+# removing empty lines (last one should be) and prepend page # before each line
+sed '/^$/d' "$FILE_TMP" | awk '{printf "%04d %s\n", NR, $0}' > "$FILE_SIZE_PAGES"
+numpages=`tail -n 1 "$FILE_SIZE_PAGES" | cut -f1 -d" "`
+
+# Itterate the pages of the input pdf file
+while read pageSize ; do
+
+	page=`echo $pageSize | cut -f1 -d" "`
+	[ $VERBOSITY -ge $LOG_INFO ] && echo "Processing page $page / $numpages"
+	
+	# create the name of the required file
+	curOrigImg="$TMP_FLD/${page}_Image"			# original image available in the current PDF page 
+								# (the image file may have a different orientation than in the pdf file)
+	curHocr="$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}-debug-ocred.pdf"	# PDF file containing data required to find out if OCR worked correctly
+	
+	# get width / height of PDF page (in pt)
+	widthPDF=`echo $pageSize | cut -f2 -d" "`
+	heightPDF=`echo $pageSize | cut -f3 -d" "`
+	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: size ${heightPDF}x${widthPDF} (h*w in pt)"
+	# extract raw image from pdf file to compute resolution
+	# unfortunatelly 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"* | wc -l`
+	[ $nbImg -ne "1" ] && echo "Expecting exactly 1 image on page $page (found $nbImg). Exiting..." >&2 && exit $EXIT_BAD_INPUT_FILE
+	# Get characteristics of the extracted image
+	curImg=`ls -1 "$curOrigImg"*`
+	propCurImg=`identify -format "%w %h %[colorspace]" "$curImg"`
+	widthCurImg=`echo "$propCurImg" | cut -f1 -d" "`
+	heightCurImg=`echo "$propCurImg" | cut -f2 -d" "`
+	colorspaceCurImg=`echo "$propCurImg" | cut -f3 -d" "`
+	# switch height/width values if the image has not the right orientation
+	# we make here the assumption that vertical/horizontal dpi are equal
+	# we will check that later
+	if [ $((($heightPDF-$widthPDF)*($heightCurImg-$widthCurImg))) -lt 0 ]; then
+		[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Extracted image has wrong orientation. Inverting image height/width values"
+		tmpval=$heightCurImg
+		heightCurImg=$widthCurImg
+		widthCurImg=$tmpval
+	fi
+	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: size ${heightCurImg}x${widthCurImg} (h*w pixel)"	
+	# compute the resolution of the image
+	dpi_x=`echo "scale=5;$widthCurImg*72/$widthPDF" | bc`
+	dpi_y=`echo "scale=5;$heightCurImg*72/$heightPDF" | bc`
+	# compute the maximum allowed resolution difference that can be cause by:
+	# - the truncated PDF with/height in pt
+	# - the precision of dpi value
+	epsilon=`echo "scale=5;($widthCurImg*72/$widthPDF^2)+($heightCurImg*72/$heightPDF^2)+0.00002" | bc`	# max inaccuracy due to truncation of PDF size in pt
+	[ `echo "($dpi_x - $dpi_y) < $epsilon " | bc` -eq 0 -o `echo "($dpi_y - $dpi_x) < $epsilon " | bc` -eq 0 ] \
+		&& echo "Resolutions difference ($dpi_x/$dpi_y) higher than expected ($epsilon). Exiting..." >&2 && exit $EXIT_BAD_INPUT_FILE
+	dpi=`echo "scale=5;($dpi_x+$dpi_y)/2+0.5" | bc` # adding 0.5 is required for rounding
+	dpi=`echo "scale=0;$dpi/1" | bc`		# round to the nearest integer
+	
+	# Identify if page image should be saved as ppm (color) or pgm (gray)
+	ext="ppm"
+	opt=""		
+	if [ $colorspaceCurImg == "Gray" ]; then
+		ext="pgm"
+		opt="-gray"
+	fi
+	curImgPixmap="$TMP_FLD/$page.$ext"
+	curImgPixmapDeskewed="$TMP_FLD/$page.deskewed.$ext"
+	curImgPixmapClean="$TMP_FLD/$page.cleaned.$ext"
+	
+	# extract current page as image with right orientation and resoltution
+	[ $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..." >&2 && exit $EXIT_OTHER_ERROR
+
+	# if requested deskew image (without changing its size in pixel)
+	if [ "$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..." >&2 && exit $EXIT_OTHER_ERROR
+	else
+		cp "$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..." >&2 && exit $EXIT_OTHER_ERROR
+	else
+		cp "$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..." >&2 && exit $EXIT_OTHER_ERROR
+	mv "$curHocr.html" "$curHocr"
+
+	# embed text and image to new pdf file
+	if [ "$PREPROCESS_CLEANTOPDF" -eq "1" ]; then
+		image4finalPDF="$curImgPixmapClean"
+	else
+		image4finalPDF="$curImgPixmapDeskewed"	
+	fi
+	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Embedding text in PDF"
+	! python $SRC/hocrTransform.py -r $dpi -i "$image4finalPDF" "$curHocr" "$curOCRedPDF" \
+		&& echo "Could not create PDF file from \"$curHocr\". Exiting..." >&2 && 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)"
+		! python $SRC/hocrTransform.py -b -r $dpi "$curHocr" "$curOCRedPDFDebug" \
+			&& echo "Could not create PDF file from \"$curHocr\". Exiting..." >&2 && 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 [ $KEEP_TMP -eq 0 ]; then
+		rm "$curOrigImg"*.*
+		rm "$curHocr"
+		rm "$curImgPixmap"
+		rm "$curImgPixmapDeskewed"
+		rm "$curImgPixmapClean"
+	fi
+	
+done < "$FILE_SIZE_PAGES"
+
+
+
+
+# concatenate all pages
+[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Concatenating all pages"
+! pdftk "${TMP_FLD}/"*-ocred.pdf cat output "$FILE_OUTPUT_PDF_CAT" \
+	&& echo "Could not concatenate individual PDF pages (\"${TMP_FLD}/*-ocred.pdf\") to one file. Exiting..." >&2 && exit $EXIT_OTHER_ERROR
+
+# convert the pdf file to match PDF/A format
+[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Converting to PDF/A" 
+! gs -dQUIET -dPDFA -dBATCH -dNOPAUSE -dUseCIEColor \
+	-sProcessColorModel=DeviceCMYK -sDEVICE=pdfwrite -sPDFACompatibilityPolicy=2 \
+	-sOutputFile="$FILE_OUTPUT_PDFA" "$FILE_OUTPUT_PDF_CAT" 1> /dev/null 2> /dev/null \
+	&& echo "Could not convert PDF file \"$FILE_OUTPUT_PDF_CAT\" to PDF/A. Exiting..." >&2 && exit $EXIT_OTHER_ERROR
+
+# # Write metadata
+# # Needs to be done after converting to PDF/A, as gs does not preserve metadata
+# [ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Update metadata (creator, producer, and title)" 
+# title=`basename "$FILE_INPUT_PDF" | sed 's/[.][^.]*//' | \
+	# sed 's/_/ /g' | sed 's/-/ /g' | \
+	# sed 's/\([[:lower:]]\)\([[:upper:]]\)/\1 \2/g' | \
+	# sed 's/\([[:alpha:]]\)\([[:digit:]]\)/\1 \2/g' | \
+	# sed 's/\([[:digit:]]\)\([[:alpha:]]\)/\1 \2/g'`	# transform the file name (with extension) into distinct words
+# pdftk "$FILE_OUTPUT_PDFA_WO_META" update_info_utf8 - output "$FILE_OUTPUT_PDFA" << EOF
+# InfoBegin
+# InfoKey: Title
+# InfoValue: $title
+# InfoBegin
+# InfoKey: Creator
+# InfoValue: $TOOLNAME $VERSION
+# InfoBegin
+# InfoKey: Producer
+# InfoValue: ghostcript `gs --version`, pdftk
+# EOF
+
+# 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" > "$FILE_VALIDATION_LOG"
+grep -i "Status|Message" "$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' "$FILE_VALIDATION_LOG" >&2 && pdf_valid=0
+grep -i 'Status.*not valid' "$FILE_VALIDATION_LOG" >&2 && pdf_valid=0
+grep -i 'Status.*Not well-formed' "$FILE_VALIDATION_LOG" >&2 && pdf_valid=0
+! grep -i 'Profile:.*PDF/A-1' "$FILE_VALIDATION_LOG" > /dev/null && echo "PDF file profile is not PDF/A-1" >&2 && pdf_valid=0
+[ $pdf_valid -ne 1 ] && echo "Output file: The generated PDF/A file is INVALID" >&2
+[ $pdf_valid -ne 0 ] && [ $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_OUPUT_PDFA || exit 0

README.md

@@ -1,40 +1,42 @@
-# OCRmyPDF-AppImage  [![Build Status](https://travis-ci.com/FPille/OCRmyPDF-AppImage.svg?branch=master)](https://travis-ci.com/FPille/OCRmyPDF-AppImage)
+OCRmyPDF
-[AppImage][APPIMAGE] for [OCRmyPDF][OCRMYPDF]
+========
 
-## Usage
+OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
-Download OCRmyPDF*.AppImage, make it executable and run it.
-```
-wget https://github.com/FPille/OCRmyPDF-AppImage/releases/download/continuous/OCRmyPDF-8.3.2-x86_64.AppImage
-chmod +x OCRmyPDF*.AppImage
-./OCRmyPDF*.AppImage --help
-```  
-  
-  Beside OCRmyPDF additional command line programs can be run with this AppImage like:
-* ghostscript
-* img2pdf
-* pngquant
-* python3.6
-* qpdf
-* tesseract
-* unpaper  
 
-Just use the program name as first parameter plus options:
+To get the script usage, call: ./OCmyPDF.sh -h
-```
-./OCRmyPDF*.AppImage tesseract -v
-tesseract 4.1.0
- leptonica-1.76.0
-  libjpeg 8d (libjpeg-turbo 1.3.0) : libpng 1.2.50 : libtiff 4.0.3 : zlib 1.2.11 : libwebp 0.4.0 : libopenjp2 2.3.0
- Found AVX2
- Found AVX
- Found SSE
-```
-Or create a symlink for the corresponding program:
-```
-ln -s OCRmyPDF*.AppImage tesseract
-./tesseract --list-langs
-```
 
+Features
+--------
 
-[APPIMAGE]: https://appimage.org
+- Generate a searchable PDF/A file from a PDF file containing only images
-[OCRMYPDF]: https://github.com/jbarlow83/OCRmyPDF
+- Place OCRed text accurately below the image to easy copy / paste
+- Keep the exact resolution of the original embedded images
+- If requested deskew and / or clean the image before performing OCR
+- Validate the generated file against the PDF/A specification using jhove
+- Provides debug mode to enable easy verification of the OCR results
 
+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/tags
+
+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

RELEASE_NOTES.md

@@ -0,0 +1,111 @@
+RELEASE NOTES
+=============
+
+Please always read this file before installing the package
+
+Download software here: https://github.com/fritz-hh/OCRmyPDF/tags
+
+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"

appimage/AppRun.sh

@@ -1,105 +0,0 @@
-#! /bin/bash
-
-HERE="$(dirname "$(readlink -f "${0}")")"
-
-export PATH="$HERE/usr/bin:$HERE/usr/local/bin:$HERE/usr/python/bin:$PATH"
-export LD_PRELOAD="$HERE/usr/lib/liblept.so.5"
-export LD_LIBRARY_PATH="$HERE/usr/lib:$HERE/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
-export TESSDATA_PREFIX="$HERE/usr/share/tesseract-ocr/4.00/tessdata"
-export GS_LIB="$HERE/usr/share/ghostscript/9.26/lib:$HERE/usr/share/ghostscript/9.26/Resource:$HERE/usr/share/ghostscript/9.26/Resource/Init"
-
-# Allow the AppImage to be symlinked to e.g., /usr/bin/commandname
-# or called with ./Some*.AppImage commandname ...
-# refer to https://github.com/AppImage/AppImageKit/wiki/Bundling-command-line-tools
-
-if [ ! -z "$APPIMAGE" ] ; then
-  BINARY_NAME=$(basename "$ARGV0")
-else
-  BINARY_NAME=$(basename "$0")
-  export APPDIR="$HERE"       # required for the wrapper scripts of linuxdeploy-plugin-python
-fi
-
-usage() {
-echo "
-==============================================================================
-                          AppImage for OCRmyPDF
-==============================================================================
-OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be
-searched or copy-pasted.
-
-usage:
-$ARGV0 [ocrmypdf] [--help] [--list-programs]
-                                 [--list-licenses] [--show-license]
-
-ocrmypdf                    execute OCRmyPDF
-
---help                      show this help message
-
---list-programs             list all programs contained in this AppImage
-
---list-licenses             list all licenses contained in this AppImage
-
---show-license [LICENSE]    show content of license file
-"
-}
-
-if [ "$1" == "--help" ] ; then
-    usage
-    exit $?
-fi
-
-if [ "$1" == "--list-programs" ] ; then
-    pushd "$HERE"
-    echo ""
-    echo "Run \"$ARGV0\" with one of the following arguments to run the respective program."
-    echo ""
-    find . -type f -perm /111 ! -path '*/lib/*' -execdir basename {} ";" | sort -u | column
-    echo ""
-    exit $?
-fi
-
-if [ "$1" == "--list-licenses" ] ; then
-    pushd "$HERE"
-    echo ""
-    echo "Run \"$ARGV0\" with one of the following arguments to display the respective license file."
-    echo ""
-    find . -type f \( ! -path '*/tesseract-ocr-*' -o -path '*/tesseract-ocr-eng/*' \) \
-        \( -iname "license*" -o -iname "*copyright*" -o -iname "*copying*" \) -printf "--show-license %P\n" | sort | column
-    echo ""
-    exit $?
-fi
-
-if [ "$1" == "--show-license" ] ; then
-    pushd "$HERE"
-    shift
-    if [ -f "$1" ] ; then
-        less -N "$1"
-        exit $?
-    else
-        echo "\"$1\" is not a valid license file path."
-        exit 1
-    fi
-fi
-
-if [ ! -z "$1" ] && [ -e "$HERE/bin/$1" ] ; then
-    MAIN="$HERE/bin/$1" ; shift
-elif [ ! -z "$1" ] && [ -e "$HERE/usr/bin/$1" ] ; then
-    MAIN="$HERE/usr/bin/$1" ; shift
-elif [ ! -z "$1" ] && [ -e "$HERE/usr/python/bin/$1" ] ; then
-    MAIN="$HERE/usr/python/bin/$1" ; shift
-elif [ ! -z "$1" ] && [ -e "$HERE/usr/local/bin/$1" ] ; then
-    MAIN="$HERE/usr/local/bin/$1" ; shift
-elif [ -e "$HERE/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/bin/$BINARY_NAME"
-elif [ -e "$HERE/usr/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/usr/bin/$BINARY_NAME"
-elif [ -e "$HERE/usr/python/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/usr/python/bin/$BINARY_NAME"
-elif [ -e "$HERE/usr/local/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/usr/local/bin/$BINARY_NAME"
-else
-    usage
-    exit $?
-fi
-
-exec "${MAIN}" "$@"

build-appimage.sh

@@ -1,120 +0,0 @@
-#! /bin/bash
-
-set -x
-set -e
-
-# use RAM disk if possible
-if [ "$CI" == "" ] && [ -d /dev/shm ]; then
-    TEMP_BASE=/dev/shm
-else
-    TEMP_BASE=/tmp
-fi
-
-BUILD_DIR=$(mktemp -d -p "$TEMP_BASE" OCRmyPDF-AppImage-build-XXXXXX)
-
-cleanup () {
-    if [ -d "$BUILD_DIR" ]; then
-        rm -rf "$BUILD_DIR"
-    fi
-}
-
-trap cleanup EXIT
-
-# store repo root as variable
-REPO_ROOT=$(readlink -f "$(dirname "$(dirname "$0")")")
-OLD_CWD=$(readlink -f .)
-
-pushd "$BUILD_DIR"
-
-mkdir -p AppDir
-mkdir -p PackageDir
-mkdir -p jbig2
-
-# download linuxdeploy AppImage and linuxdeploy-plugin-python AppImage
-wget https://github.com/TheAssassin/linuxdeploy/releases/download/continuous/linuxdeploy-x86_64.AppImage
-# wget https://github.com/niess/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
-
-# use adapted linuxdeploy-plugin-python instead of the original one (otherwise OCRmyPDF breaks)
-wget https://github.com/FPille/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
-
-chmod +x linuxdeploy*.AppImage
-
-
-ARCH=$(uname -i)
-export ARCH
-
-
-# .desktop file
-cat > ocrmypdf.desktop <<\EOF
-[Desktop Entry]
-Name=ocrmypdf
-Type=Application
-Exec=ocrmypdf
-Icon=ocrmypdf
-Terminal=true
-Comment=OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
-Categories=Graphics;Scanning;OCR;
-EOF
-
-
-# download logo and convert it to desktop icon
-# requires Imagemagick (convert)
-wget https://raw.githubusercontent.com/jbarlow83/OCRmyPDF/master/docs/images/logo-social.png
-convert logo-social.png -resize 512x512\> -size 512x512 xc:white +swap -gravity center -composite ocrmypdf.png
-
-
-# download and intsall packages required by OCRmyPDF
-pushd PackageDir
-packages=(tesseract-ocr tesseract-ocr-all libavformat56 ghostscript qpdf pngquant)
-
-for i in "${packages[@]}"
-do
-    apt-get -d -o dir::cache="$PWD" -o Debug::NoLocking=1 --reinstall install "$i" -y
-done
-
-wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O unpaper_6.1-1.deb
-
-find . -type f -name \*.deb -exec dpkg-deb -X {} "$BUILD_DIR"/AppDir \;
-popd
-
-
-# compile and install jbig2
-# requires libleptonica-dev, zlib1g-dev
-wget -q https://github.com/agl/jbig2enc/archive/0.29.tar.gz -O - | \
-     tar xz -C jbig2 --strip-components=1
-pushd jbig2
-./autogen.sh
-./configure --prefix="$BUILD_DIR"/AppDir/usr
-make && make install
-popd
-
-pushd "$BUILD_DIR"/AppDir
-# add some tools to AppDir
-#cp -f   /usr/bin/column     ./usr/bin/
-#cp -f   /bin/less           ./usr/bin/
-
-# remove unnecessary data from AppDir
-[ -d bin ] && rm -rf ./bin
-[ -d etc ] && rm -rf ./etc
-[ -d var ] && rm -rf ./var
-popd
-
-
-# export LD_LIBRARY_PATH so that dependencies of shared libraries can be deployed by linuxdeploy-x86_64.AppImage
-export LD_LIBRARY_PATH="$BUILD_DIR/AppDir/usr/lib:$BUILD_DIR/AppDir/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
-
-#OCRMYPDF_VERSION=8.3.2   # exported in .travis.yml file
-export PIP_REQUIREMENTS="ocrmypdf==$OCRMYPDF_VERSION"
-export VERSION="$OCRMYPDF_VERSION"
-export OUTPUT=OCRmyPDF-"$VERSION"-"$ARCH".AppImage
-export PYTHON_SOURCE=https://www.python.org/ftp/python/3.6.8/Python-3.6.8.tgz
-
-./linuxdeploy-x86_64.AppImage --appdir AppDir --plugin python \
-    -d ocrmypdf.desktop -i ocrmypdf.png \
-    --custom-apprun "$REPO_ROOT"/appimage/AppRun.sh --output appimage
-
-
-# move AppImage back to old CWD
-mv "$OUTPUT" "$OLD_CWD"/
-
-popd

jhove/COPYING

@@ -0,0 +1,502 @@
+		  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

@@ -0,0 +1,17 @@
+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

@@ -0,0 +1,227 @@
+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. 1.9, 2012-12-17
+
+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

@@ -0,0 +1,25 @@
+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

@@ -0,0 +1,78 @@
+<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

@@ -0,0 +1,63 @@
+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

@@ -0,0 +1,47 @@
+<?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/1.4/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

@@ -0,0 +1,51 @@
+<?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/1.4/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

@@ -0,0 +1,45 @@
+<?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/1.4/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

@@ -0,0 +1,88 @@
+#!/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

@@ -0,0 +1,37 @@
+#!/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

@@ -0,0 +1,37 @@
+#!/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

@@ -0,0 +1,37 @@
+#!/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

@@ -0,0 +1,58 @@
+#!/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

@@ -0,0 +1,54 @@
+#!/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

@@ -0,0 +1,63 @@
+@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 JAVA_HOME="C:\Program Files\java\j2re1.4.1_02"
+SET JAVA=%JAVA_HOME%\bin\java
+
+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

@@ -0,0 +1,14 @@
+#!/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

@@ -0,0 +1,44 @@
+#!/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

@@ -0,0 +1,37 @@
+#!/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

@@ -0,0 +1,24 @@
+#!/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

src/hocrTransform.py

@@ -0,0 +1,183 @@
+##############################################################################
+# Copyright (c) 2013: 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
+import Image, 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
+		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 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()
+			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/test/OCRmyPDF_severaltimes.sh

@@ -0,0 +1,15 @@
+#!/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

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

tess-cfg/README.md

@@ -0,0 +1,10 @@
+Note
+====
+
+The file(s) located in this folder are tesseract configuration files.
+(Tesseract configuration files enable to tune the behaviour of tesseract)
+
+If needed, these files should be copied to the "tessdata/configs" folder of your tesseract installation.
+
+To request OCRmyPDF.sh to use a configuration file, please use the -C option
+

tess-cfg/no_ligature

@@ -0,0 +1 @@
+tessedit_char_blacklist fifl

test/test-appimage.sh

@@ -1,53 +0,0 @@
-#! /bin/bash
-
-set -x
-set -e
-
-chmod +x OCRmyPDF*.AppImage
-
-# run OCRmyPDF to test if the AppImage can ocr a test file
-run_appimage()
-{
-    echo ""
-    ./OCRmyPDF*.AppImage --help
-    echo ""
-    ./OCRmyPDF*.AppImage --list-programs
-    echo ""
-    ./OCRmyPDF*.AppImage --list-licenses
-    echo ""
-    ./OCRmyPDF*.AppImage ocrmypdf -l deu -s -d --jbig2-lossy --optimize 1 "$TRAVIS_BUILD_DIR"/test/test.pdf output.pdf
-    echo ""
-}
-
-
-# check AppImage for common issues
-run_appimagelint()
-{
-    wget https://github.com/TheAssassin/appimagelint/releases/download/continuous/appimagelint-x86_64.AppImage
-    chmod +x appimagelint-x86_64.AppImage
-    ./appimagelint-x86_64.AppImage OCRmyPDF*.AppImage
-}
-
-
-# extract the OCRmyPDF AppImage, install pytest & test requirements and run pytest
-run_pytest()
-{
-    git clone --depth=1 --branch "v$OCRMYPDF_VERSION" https://github.com/jbarlow83/OCRmyPDF.git
-    ./OCRmyPDF*.AppImage --appimage-extract
-
-    pushd squashfs-root
-    ./AppRun python3 -m pip install pytest
-    ./AppRun python3 -m pip install -r ../OCRmyPDF/requirements/test.txt
-    ./AppRun python3 -m pytest ../OCRmyPDF -n auto
-    popd
-}
-
-
-run_appimage
-
-run_appimagelint
-
-# run_pytest
-
-
-