Git-Url: http://git.frugalware.org/gitweb/gitweb.cgi?p=frugalware-current.git;a=commitdiff;h=8de017f90d65280d4273c040ffe942b9b2424bd5
commit 8de017f90d65280d4273c040ffe942b9b2424bd5 Author: Slown <[email protected]> Date: Sun Mar 25 18:19:43 2012 +0100 xsane2tess-1.0-1-i686 * new package diff --git a/source/apps-extra/xsane2tess/FrugalBuild b/source/apps-extra/xsane2tess/FrugalBuild new file mode 100644 index 0000000..abdad01 --- /dev/null +++ b/source/apps-extra/xsane2tess/FrugalBuild @@ -0,0 +1,21 @@ +# Compiling Time: 0 SBU +# Maintainer: Slown <[email protected]> + +pkgname=xsane2tess +pkgver=1.0 +pkgrel=1 +pkgdesc="Script for OCR with tesseract and xsane" +url="http://doc.ubuntu-fr.org/xsane2tess"; +depends=('tesseract-ocr' 'xsane' 'imagemagick') +groups=('apps-extra') +archs=('i686' 'x86_64') +install=$pkgname.install +up2date=$pkgver +source=(script) +_F_cd_path="." +sha1sums=('c6337510f61858627228929d9ea6b872cc02734b') + +build() { + Fcd + Fexe script /usr/bin/$pkgname +} diff --git a/source/apps-extra/xsane2tess/script b/source/apps-extra/xsane2tess/script new file mode 100644 index 0000000..3a3fee8 --- /dev/null +++ b/source/apps-extra/xsane2tess/script @@ -0,0 +1,87 @@ +#!/bin/bash +# +# +############################################################################## +# +# xsane2tess 1.0 +# +# *** tesseract made simple *** +# +# +############################################################################## +# +# xsane2tess is a TesseractOCR wrapper to be able to use tesseract with xsane +# +# +# +TEMP_DIR=/tmp/ # folder for temporary files (TIFF & tesseract data) +ERRORLOG="xsane2tess.log" # file where STDERR goes + +if [[ -z "$1" ]] +then + echo "Usage: $0 [OPTIONS] + + xsane2tess converts files to TIF, scans them with TesseractOCR + and outputs the text in a file. + + OPTIONS: + -i <file1> define input file (any image-format supported) + -o <file2> define output-file (*.txt) + -l <lang> define language-data tesseract should use + + Progress- & error-messages will be stored in this logfile: + $TEMP_DIR$ERRORLOG + + xsane2tess depends on + - ImageMagick http://www.imagemagick.org/ + - TesseractOCR http://code.google.com/p/tesseract-ocr/ + + Some coding was stolen from 'ocube' + http://www.geocities.com/thierryguy/ocube.html + " + exit +fi + + +# get options... +while getopts ":i:o:l:" OPTION +do + case $OPTION in + i) # input filename (with path) + FILE_PATH="$OPTARG" + ;; + o ) # output filename + FILE_OUT="$OPTARG" + ;; + l ) # Language-selection + TES_LANG="$OPTARG" + ;; + esac +done + +# redirect STDOUT to FILE_OUT +exec 1>>$FILE_OUT + +# redirect STDERR to ERRORLOG +exec 2>>$TEMP_DIR$ERRORLOG + +# strip path from FILE_PATH, use filename only +IN_FILE=${FILE_PATH##*/} + +TIF_FILE="$TEMP_DIR""${IN_FILE%.*}".tif +TXT_FILE="$TEMP_DIR""${IN_FILE%.*}" + +# converting image into TIFF (ImageMagick) +convert "$FILE_PATH" -compress none "$TIF_FILE" 1>&2 + +# start OCR (tesseract expands output with *.txt) +tesseract "$TIF_FILE" "$TXT_FILE" -l "$TES_LANG" 1>&2 + +# STDOUT scanned text => FILE_OUT +cat "$TXT_FILE".txt + +# delete graphic file after use +rm "$TIF_FILE" + +# delete tesseract output +rm "$TXT_FILE".txt diff --git a/source/apps-extra/xsane2tess/xsane2tess.install b/source/apps-extra/xsane2tess/xsane2tess.install new file mode 100644 index 0000000..7a03e35 --- /dev/null +++ b/source/apps-extra/xsane2tess/xsane2tess.install @@ -0,0 +1,5 @@ +post_install() { + + echo "In order to make it work, launch XSane, go to Preferences / OCR and enter in OCR command line : xsane2tess -l fra" + echo "replace fra by eng for english, deu for german, ita for italian, and so on. Language list : just look at /usr/share/tessdata/" +} _______________________________________________ Frugalware-git mailing list [email protected] http://frugalware.org/mailman/listinfo/frugalware-git
