diff --git a/graphic/tesseract-deu/tesseract-deu.conf b/graphic/tesseract-deu/tesseract-deu.conf new file mode 100644 index 000000000..c588de45f --- /dev/null +++ b/graphic/tesseract-deu/tesseract-deu.conf @@ -0,0 +1,23 @@ +# --- SDE-COPYRIGHT-NOTE-BEGIN --- +# This copyright note is auto-generated by ./scripts/Create-CopyPatch. +# +# Filename: package/.../tesseract-deu/tesseract-deu.conf +# Copyright (C) 2012 The OpenSDE Project +# +# More information can be found in the files COPYING and README. +# +# 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; version 2 of the License. A copy of the +# GNU General Public License can be found in the file COPYING. +# --- SDE-COPYRIGHT-NOTE-END --- + +autoextract=0 + +pkgprefix -t tesseract-ocr + +tesseract_lang_install() { + bunzip2 -c $( match_source_file -p $pkg ) > $( pkgprefix -r datadir tesseract-ocr )/tessdata/deu.traineddata +} + +custmain='tesseract_lang_install' diff --git a/graphic/tesseract-deu/tesseract-deu.desc b/graphic/tesseract-deu/tesseract-deu.desc new file mode 100644 index 000000000..ec6ed77df --- /dev/null +++ b/graphic/tesseract-deu/tesseract-deu.desc @@ -0,0 +1,37 @@ +[COPY] --- SDE-COPYRIGHT-NOTE-BEGIN --- +[COPY] This copyright note is auto-generated by ./scripts/Create-CopyPatch. +[COPY] +[COPY] Filename: package/.../tesseract-deu/tesseract-deu.desc +[COPY] Copyright (C) 2012 The OpenSDE Project +[COPY] +[COPY] More information can be found in the files COPYING and README. +[COPY] +[COPY] This program is free software; you can redistribute it and/or modify +[COPY] it under the terms of the GNU General Public License as published by +[COPY] the Free Software Foundation; version 2 of the License. A copy of the +[COPY] GNU General Public License can be found in the file COPYING. +[COPY] --- SDE-COPYRIGHT-NOTE-END --- + +[I] tesseract-ocr language files for German + +[T] The Tesseract OCR engine was one of the top 3 engines in the 1995 UNLV +[T] Accuracy test. Between 1995 and 2006 it had little work done on it, but +[T] since then it has been improved extensively by Google and is probably one +[T] of the most accurate open source OCR engines available. Combined with the +[T] Leptonica Image Processing Library it can read a wide variety of image +[T] formats and convert them to text in over 40 languages. + +[U] http://tesseract-ocr.googlecode.com/ + +[A] Google Inc. +[A] HP Labs (original version) +[M] Christian Wiese + +[C] extra/tool + +[L] APL +[S] Stable +[V] 3.00 +[P] X -----5---9 800.000 + +[D] 543348914 tesseract-deu.traineddata.gz !http://tesseract-ocr.googlecode.com/files/deu.traineddata.gz