X-Git-Url: https://git.distorted.org.uk/~mdw/termux-packages/blobdiff_plain/202a1fb5d3efb4affe66cabc1f5ed33de0db1d80..7c5fa0b8a793c371fcb0793ed1b9bfe581d7e7b3:/packages/tesseract/build.sh diff --git a/packages/tesseract/build.sh b/packages/tesseract/build.sh index 3f79ad76..38f765b2 100644 --- a/packages/tesseract/build.sh +++ b/packages/tesseract/build.sh @@ -1,16 +1,16 @@ TERMUX_PKG_HOMEPAGE=https://github.com/tesseract-ocr/tesseract TERMUX_PKG_DESCRIPTION="Tesseract is probably the most accurate open source OCR engine available" -TERMUX_PKG_VERSION=3.04.01 +TERMUX_PKG_VERSION=3.05.01 +TERMUX_PKG_REVISION=1 TERMUX_PKG_DEPENDS="libtool, libuuid, leptonica" TERMUX_PKG_SRCURL=https://github.com/tesseract-ocr/tesseract/archive/${TERMUX_PKG_VERSION}.tar.gz -TERMUX_PKG_FOLDERNAME=tesseract-${TERMUX_PKG_VERSION} +TERMUX_PKG_SHA256=05898f93c5d057fada49b9a116fc86ad9310ff1726a0f499c3e5211b3af47ec1 termux_step_pre_configure() { # http://blog.matt-swain.com/post/26419042500/installing-tesseract-ocr-on-mac-os-x-lion export LIBLEPT_HEADERSDIR=${TERMUX_PREFIX}/include/leptonica - cd $TERMUX_PKG_SRCDIR - perl -p -i -e 's|ADD_RT, true|ADD_RT, false|g' configure.ac + perl -p -i -e 's|ADD_RT], true|ADD_RT], false|g' configure.ac ./autogen.sh } @@ -18,13 +18,13 @@ termux_step_post_make_install() { # download english trained data cd "${TERMUX_PREFIX}/share/tessdata" rm -f eng.* - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.cube.bigrams - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.cube.fold - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.cube.lm - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.cube.nn - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.cube.params - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.cube.size - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.cube.word-freq - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.tesseract_cube.nn - wget https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata + for f in cube.{bigrams,fold,lm,nn,params,size,word-freq} tesseract_cube.nn traineddata; do + f=eng.$f + # From the tessdata README: "These language data files only work with + # Tesseract 4. They are based on the sources in tesseract-ocr/langdata on GitHub. + # Get language data files for Tesseract 3.04 or 3.05 from the 3.04 tree." + termux_download \ + https://raw.githubusercontent.com/tesseract-ocr/tessdata/3.04.00/$f \ + $f + done }