Anhang: xsane2tess4.sh
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 | #!/bin/bash # xsane2tess3 - tesseractOCR directly from xsane # Copyright (C) 2012-2019 Heinrich Schwietering # # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 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 General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. # # ############################################################################## # # xsane2tess4 0.1 # # *** tesseract made simple *** # # ############################################################################## # # xsane2tess is a TesseractOCR wrapper to be able to use tesseract with xsane # # # TEMP_DIR=/tmp/ # folder for temporary files (all files) ERRORLOG="xsane2tess4.log" # file where STDERR goes #TEST="testoutput.txt" if [[ -z "$1" ]] then echo "Usage: $0 [OPTIONS] xsane2tess4 scans images with TesseractOCR and outputs text in a file, a PDF or as hocr/html document OPTIONS: -i <file1> define input file (any image-format supported) -o <file2> define output-file (*.txt/hOCR/pdf) -l <lang> define language-data tesseract should use -e <config> filename for tesseract -f </path/to/Final> name and path for multiscan document Progress- & error-messages will be stored in this logfile: $TEMP_DIR$ERRORLOG xsane2tess depends on - XSane, http://www.xsane.org/ - TesseractOCR, http://code.google.com/p/tesseract-ocr/ - pdfunite from poppler-utils - econvert from exact-image Some coding was stolen from 'ocube' http://www.geocities.com/thierryguy/ocube.html This adaption is based on xsane2tess http://doc.ubuntu-fr.org/xsane2tess, Hints always welcome! heinrich (dot) schwietering (at) gmx (dot) de " exit fi # get options... while getopts ":i:o:l:c:f:" OPTION do case $OPTION in i ) # input filename (with path) FILE_PATH="$OPTARG" ;; o ) # output filename FILE_OUT="$OPTARG" ;; l ) # Language-selection LANG="$OPTARG" ;; c ) # use hocr configfile CONFILE="$OPTARG" ;; f ) # final name for multiscan ocr file FINAL="$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##*/.*}" echo "~~~+++~~~~+++~~~Start "$(date +%c) 1>&2 # convert input to png with 300 dpi; tesseract 4.xx can't recognise the # resölution of XSanes internal ppm file format, which leads to gigantic pdf files econvert -i "$IN_FILE" --resolution 300 -o IN_FILE.png 1>&2 # start OCR (tesseract expands output with *.txt/.html/.pdf) { if [[ "$CONFILE" == '' ]] then tesseract IN_FILE.png "$FILE_OUT" -l "$LANG" 1>&2 echo Tesseract used with -l "$LANG" 1>&2 else tesseract IN_FILE.png "$FILE_OUT" -l "$LANG" "$CONFILE" 1>&2 echo Tesseract used with -l "$LANG" and "$CONFILE" 1>&2 fi } { if [[ "$FINAL" != '' ]] then { if [[ "$CONFILE" == "" ]] then # check if final txt file is already existing { if [[ ! -a "$FINAL".txt ]] then # start final ocr txt file mv "$FILE_OUT".txt "$FINAL".txt 1>&2 echo "$FINAL.txt started" 1>&2 else mv "$FINAL".txt "$FINAL".new.txt cat "$FINAL".new.txt "$FILE_OUT".txt > "$FINAL".txt echo "$FILE_OUT. txt added to $FINAL.txt" 1>&2 rm "$FINAL".new.txt fi } else # check if final hocr/pdf file is already existing { if [[ ! -a "$FINAL"."$CONFILE" ]] then # start final hocr/pdf file mv "$FILE_OUT"."$CONFILE" "$FINAL"."$CONFILE" 1>&2 echo "$FINAL.$CONFILE started" 1>&2 else # add new file to existing one mv "$FINAL"."$CONFILE" "$FINAL".new."$CONFILE" { if [[ "$CONFILE" == "pdf" ]] then pdfunite "$FINAL".new."$CONFILE" "$FILE_OUT"."$CONFILE" "$FINAL"."$CONFILE" else cat "$FINAL".new."$CONFILE" "$FILE_OUT"."$CONFILE" > "$FINAL"."$CONFILE" fi } echo "$FILE_OUT"."$CONFILE" added to "$FINAL"."$CONFILE" 1>&2 rm "$FINAL".new."$CONFILE" fi } fi } rm $FILE_OUT else # STDOUT scanned text => FILE_OUT cat "$FILE_OUT".* fi } rm $FILE_OUT.* rm IN_FILE.png echo "~~~+++~~~~+++~~~Finished "$(date +%c) 1>&2 |
Wrapper-Skript für tesseract zu Nutzung aus XSane heraus