From 92667d0f40c859c8e03ef57dcd2b79961b9a9622 Mon Sep 17 00:00:00 2001 From: Nick White Date: Sun, 30 Oct 2011 12:30:07 +0000 Subject: Remove cuneform ocr script --- extras/mkocrpdf-cuneform.sh | 21 --------------------- 1 file changed, 21 deletions(-) delete mode 100644 extras/mkocrpdf-cuneform.sh diff --git a/extras/mkocrpdf-cuneform.sh b/extras/mkocrpdf-cuneform.sh deleted file mode 100644 index 94e10eb..0000000 --- a/extras/mkocrpdf-cuneform.sh +++ /dev/null @@ -1,21 +0,0 @@ -#!/bin/sh -# -# Makes a pdf with embedded text as extracted by cuneiform -# -# Requires imagemagick, pdftk, hocr2pdf and cuneiform - -for i in `ls *png` -do - a=`basename $i .png` - echo processing $a - - convert $i $a.bmp - cuneiform -f hocr -o $a.html $a.bmp - rm -f $a.bmp - - # hocr2pdf has a habit of segfaulting, so fall back to convert - hocr2pdf -i $i -o $a.pdf < $a.html || convert $i $a.pdf - rm -f $a.html -done - -pdftk *pdf cat output book.pdf -- cgit v1.2.3