diff options
| author | Nick White <git@njw.me.uk> | 2011-10-30 12:30:07 +0000 |
|---|---|---|
| committer | Nick White <git@njw.me.uk> | 2011-10-30 12:30:07 +0000 |
| commit | 92667d0f40c859c8e03ef57dcd2b79961b9a9622 (patch) | |
| tree | cb4a2d38286cceed70ac243a21c6b3800db4e199 /extras/mkocrpdf-cuneform.sh | |
| parent | cd0c0a821361f5ee7c52ee60fb0ed5b758e53620 (diff) | |
Remove cuneform ocr script
Diffstat (limited to 'extras/mkocrpdf-cuneform.sh')
| -rw-r--r-- | extras/mkocrpdf-cuneform.sh | 21 |
1 files changed, 0 insertions, 21 deletions
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 |