Release notes updated for v2.1-stable

Fixed typo

.gitignore

@@ -1,2 +1,3 @@
 tmp/
-log/
+log/
+*.pyc

OCRmyPDF.sh

@@ -4,7 +4,8 @@
 ##############################################################################
 
 # Import required scripts
-. "`dirname $0`/src/config.sh"
+BASEPATH="$(dirname $(readlink -f $0))"
+. "$BASEPATH/src/config.sh"
 
 # Set variables corresponding to the input parameters
 ARGUMENTS="$@"
@@ -39,10 +40,10 @@ Usage: OCRmyPDF.sh  [-h] [-v] [-g] [-k] [-d] [-c] [-i] [-o dpi] [-f] [-l languag
      an oversampled image having the latter dpi value. This can improve the OCR results but can lead to a larger output PDF file.
      (default: no oversampling performed)
 -f : Force to OCR the whole document, even if some page already contain font data 
-     (which should not be the case for PDF files built from scnanned images) 
+     (which should not be the case for PDF files built from scanned images) 
 -l : Set the language of the PDF file in order to improve OCR results (default "eng")
      Any language supported by tesseract is supported (Tesseract uses 3-character ISO 639-2 language codes)
-     Multiple languages may be specified, separated by plus characters.
+     Multiple languages may be specified, separated by '+' characters.
 -C : Pass an additional configuration file to the tesseract OCR engine.
      (this option can be used more than once)
      Note 1: The configuration file must be available in the "tessdata/configs" folder of your tesseract installation
@@ -111,8 +112,7 @@ done
 # Remove the optional arguments parsed above.
 shift $((OPTIND-1))
 
-# Check if the number of mandatory parameters
+# Check if the number of mandatory parameters provided is as expected
-# provided is as expected
 if [ "$#" -ne "2" ]; then
 	echo "Exactly two mandatory argument shall be provided ($# arguments provided)"
 	usage
@@ -129,7 +129,7 @@ FILE_OUTPUT_PDFA="`absolutePath "$2"`"
 
 
 # set script path as working directory
-cd "`dirname $0`"
+cd "$BASEPATH"
 
 [ $VERBOSITY -ge $LOG_DEBUG ] && echo "$TOOLNAME version: $VERSION"
 [ $VERBOSITY -ge $LOG_DEBUG ] && echo "Arguments: $ARGUMENTS"
@@ -146,28 +146,33 @@ cd "`dirname $0`"
 ! command -v python2 > /dev/null && echo "Please install python v2.x. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
 ! python2 -c 'import lxml' 2>/dev/null && echo "Please install the python library lxml. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
 ! python2 -c 'import reportlab' 2>/dev/null && echo "Please install the python library reportlab. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
-! command -v gs > /dev/null && echo "Please install ghostcript. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
+! command -v gs > /dev/null && echo "Please install ghostscript. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
 ! command -v java > /dev/null && echo "Please install java. Exiting..." && exit $EXIT_MISSING_DEPENDENCY
 
 
+
 # ensure the right tesseract version is installed
 # older versions are known to produce malformed hocr output and should not be used
-reqtessversion="3.02.02"
+# Even 3.02.01 fails in few cases (see issue #28). I decided to allow this version anyway because
+# 3.02.02 is not yet available for some widespread linux distributions
+reqtessversion="3.02.01"
 tessversion=`tesseract -v 2>&1 | grep "tesseract" | sed s/[^0-9.]//g`
-! [ $((`echo $tessversion | sed s/[.]//g`-`echo $reqtessversion | sed s/[.]//g`)) -ge 0 ] > /dev/null \
+tesstooold=$(echo "`echo $tessversion | sed s/[.]//2`-`echo $reqtessversion | sed s/[.]//2` < 0" | bc)
+[ "$tesstooold" -eq "1" ] \
 	&& echo "Please install tesseract ${reqtessversion} or newer (currently installed version is ${tessversion})" && exit $EXIT_MISSING_DEPENDENCY
+
 # ensure the right GNU parallel version is installed
 # older version do not support -q flag (required to escape special characters)
-reqparallelversion="20130222"
+reqparallelversion="20121122"
 parallelversion=`parallel --minversion 0`
 ! parallel --minversion "$reqparallelversion" > /dev/null \
 	&& echo "Please install GNU parallel ${reqparallelversion} or newer (currently installed version is ${parallelversion})" && exit $EXIT_MISSING_DEPENDENCY
 
-
 # ensure pdftoppm is provided by poppler-utils, not the older xpdf version
 ! pdftoppm -v 2>&1 | grep -q 'Poppler' && echo "Please remove xpdf and install poppler-utils. Exiting..." && $EXIT_MISSING_DEPENDENCY
 
 
+
 # Display the version of the tools if log level is LOG_DEBUG
 if [ $VERBOSITY -ge $LOG_DEBUG ]; then
 	echo "--------------------------------"
@@ -201,8 +206,19 @@ fi
 
 
 
-# Initialize path to temporary files using mktemp
+# check if the languages passed to tesseract are all supported
+for currentlan in `echo "$LAN" | sed 's/+/ /g'`; do
+	if ! tesseract --list-langs 2>&1 | grep "^$currentlan\$" > /dev/null; then
+		echo "The language \"$currentlan\" is not supported by tesseract."
+		tesseract --list-langs 2>&1 | tr '\n' ' '; echo
+		echo "Exiting..."
+		exit $EXIT_BAD_ARGS
+	fi
+done
 
+
+
+# Initialize path to temporary files using mktemp
 # Goal: save tmp file in a sub-folder of the $TMPDIR environment variable (or in "/tmp" if unset)
 # Unfortunately, Linux mktemp is not compatible with FreeBSD/OSX mktemp
 # Linux version requires no arg
@@ -277,4 +293,4 @@ END=`date +%s`
 [ $VERBOSITY -ge $LOG_DEBUG ] && echo "Script took $(($END-$START)) seconds"
 
 
-[ $pdf_valid -ne 1 ] && exit $EXIT_INVALID_OUPUT_PDFA || exit 0
+[ $pdf_valid -ne 1 ] && exit $EXIT_INVALID_OUTPUT_PDFA || exit 0

README.md

@@ -11,7 +11,7 @@ Main features
 - Generates a searchable PDF/A file from a PDF file containing only images
 - Places OCRed text accurately below the image to ease copy / paste
 - Keeps the exact resolution of the original embedded images
-    - or if requested oversample the images before OCRing so as to get better results 
+    - or if requested oversamples the images before OCRing so as to get better results 
 - If requested deskews and / or clean the image before performing OCR
 - Validates the generated file against the PDF/A specification using jhove
 - Provides debug mode to enable easy verification of the OCR results

RELEASE_NOTES.md

@@ -5,7 +5,7 @@ Please always read this file before installing the package
 
 Download software here: https://github.com/fritz-hh/OCRmyPDF/tags
 
-v2.0-rc2 (2014-01-16):
+v2.1-stable (2014-09-20):
 =======
 
 New features
@@ -16,6 +16,74 @@ New features
 Changes
 -------
 
+- None
+
+Fixes
+-----
+
+- Allow execution via simlink
+- Add support for tesseract 3.03
+- Add support for newer version of reportlab
+- Lowered minimum version of gnu parallel
+- Various typo
+
+Tested with
+-----------
+
+- Operating system: FreeBSD 9.1
+- Dependencies:
+   - parallel 20130222
+   - poppler-utils 0.22.2
+   - ImageMagick 6.8.0-7 2013-03-30
+   - Unpaper 0.3
+   - tesseract 3.02.02
+   - Python 2.7.3
+   - ghoscript (gs): 9.06
+   - java: openjdk version "1.7.0_17"
+
+v2.0-stable (2014-01-25):
+=======
+
+New features
+------------
+
+- Check if the language(s) passed using the -l option is supported by tesseract (fixes #60)
+
+Changes
+-------
+
+- Allow OCRmyPDF to be used with tesseract 3.02.01, even though OCR might fail for few PDF file (see issue #28). Rationale: For some linux distribution, no newer version than tesseract 3.02.01 is available
+
+Fixes
+-----
+
+- More robust algorithm for checking the version of the installed tesseract package
+
+Tested with
+-----------
+
+- Operating system: FreeBSD 9.1
+- Dependencies:
+   - parallel 20130222
+   - poppler-utils 0.22.2
+   - ImageMagick 6.8.0-7 2013-03-30
+   - Unpaper 0.3
+   - tesseract 3.02.02
+   - Python 2.7.3
+   - ghoscript (gs): 9.06
+   - java: openjdk version "1.7.0_17"
+
+v2.0-rc2 (2014-01-16):
+=======
+   
+New features
+------------
+
+- None
+
+Changes
+-------
+
 - Size reduction of final PDF file: (fixes #50)
    - Support for monochrome (Black&White) images (massive size reduction in final PDF: >80%)
    - Reduced size of grayscale images (by 13% on test PDF file)

src/config.sh

@@ -9,13 +9,13 @@ DEFAULT_DPI=300				# dpi value used as fall back if the page dpi cannot be deter
 #####################################################################################
 
 TOOLNAME="OCRmyPDF"
-VERSION="v2.0-rc2"
+VERSION="v2.1-stable"
 
 # possible exit codes
 EXIT_BAD_ARGS="1"
 EXIT_BAD_INPUT_FILE="2"
 EXIT_MISSING_DEPENDENCY="3"
-EXIT_INVALID_OUPUT_PDFA="4"
+EXIT_INVALID_OUTPUT_PDFA="4"
 EXIT_FILE_ACCESS_ERROR="5"
 EXIT_OTHER_ERROR="15"
 

src/hocrTransform.py

@@ -14,7 +14,6 @@ from PIL import Image
 import re, sys
 import argparse
 
-
 def monkeypatch_method(cls):
 	'''
 	Override a class method at runtime.
@@ -47,8 +46,13 @@ def PIL_imagedata(self):
 
 	from reportlab.lib.utils import import_zlib
 	from reportlab import rl_config
-	from reportlab.pdfbase.pdfutils import _AsciiBase85Encode, _chunker
+	from reportlab.pdfbase.pdfutils import _chunker
-
+	# in order to support both newer and older versions of reportlab
+	try:
+	    from reportlab.pdfbase.pdfutils import _AsciiBase85Encode
+	except ImportError:
+	    from reportlab.pdfbase.pdfutils import asciiBase85Encode as _AsciiBase85Encode
+	
 	self.source = 'PIL'
 	zlib = import_zlib()
 	if not zlib:

src/ocrPage.sh

@@ -187,7 +187,14 @@ fi
 [ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Performing OCR"
 ! tesseract -l "$LAN" "$curImgPixmapClean" "$curHocr" hocr $TESS_CFG_FILES 1> /dev/null 2> /dev/null \
 	&& echo "Could not OCR file \"$curImgPixmapClean\". Exiting..." && exit $EXIT_OTHER_ERROR
-mv "$curHocr.html" "$curHocr"
+# Tesseract names the output files differently in some distributions.
+if [ -e "$curHocr.html" ]; then
+	mv "$curHocr.html" "$curHocr"
+elif [ -e "$curHocr.hocr" ]; then
+	mv "$curHocr.hocr" "$curHocr"
+elif [ ! -e "$curHocr" ]; then
+	echo "\"$curHocr[.html|.hocr]\" not found. Exiting..." && exit $EXIT_OTHER_ERROR
+fi
 
 # embed text and image to new pdf file
 if [ "$PREPROCESS_CLEANTOPDF" -eq "1" ]; then