# Created by: bf # $FreeBSD$ PORTNAME= tesseract-data PORTVERSION= 3.02 PORTREVISION= 2 CATEGORIES= graphics MASTER_SITES= GOOGLE_CODE DISTFILES= ${TESSERACT_LANGS_300:O:u:S|$|.traineddata.gz|} \ ${TESSERACT_LANGS_301:O:u:S|^|tesseract-ocr-3.01.|:S|$|.tar.gz|} \ ${TESSERACT_LANGS_302:O:u:S|^|tesseract-ocr-3.02.|:S|$|.tar.gz|} EXTRACT_ONLY= #empty MAINTAINER= ports@FreeBSD.org COMMENT= Trained language data for the Tesseract OCR engine LICENSE= APACHE20 DIST_SUBDIR= tesseract PROJECTHOST= tesseract-ocr NO_BUILD= yes LANGS_300= dan-frak deu-frak swe-frak LANGS_301= osd slk-frak LANGS_302= afr ara aze bel ben bul cat ces chi_sim chi_tra chr dan deu \ ell eng enm epo epo_alt equ est eus fin fra frk frm glg grc heb hin \ hrv hun ind isl ita ita_old jpn kan kor lav lit mal mkd mlt \ msa nld nor pol por ron rus slk slv spa spa_old sqi srp swa \ swe tam tel tgl tha tur ukr vie .if make(makesum) TESSERACT_LANGS= ${LANGS_300} ${LANGS_301} ${LANGS_302} .else TESSERACT_LANGS ?= ${LANGS_300} ${LANGS_301} ${LANGS_302} .endif .for l in ${TESSERACT_LANGS} .for n in 0 1 2 .if ${LANGS_30${n}:M${l}} TESSERACT_LANGS_30${n}+= ${LANGS_30${n}:M${l}} .endif .endfor .endfor DATADIR= ${PREFIX}/share/tessdata PORTDATA= ${TESSERACT_LANGS:O:u:S|$|.traineddata|} pre-fetch: @${ECHO_MSG} "" @${ECHO_MSG} "The choice of language data to be installed may" @${ECHO_MSG} "be overridden by defining TESSERACT_LANGS. " @${ECHO_MSG} "" do-install: @${MKDIR} ${STAGEDIR}${DATADIR} .for l in ${TESSERACT_LANGS_300:O:u:S|$|.traineddata|} @${GUNZIP_CMD} -c ${_DISTDIR}/${l}.gz > ${STAGEDIR}${DATADIR}/${l} .endfor .for n in 1 2 .for l in ${TESSERACT_LANGS_30${n}:O:u} @${TAR} --strip-components 2 -C ${STAGEDIR}${DATADIR} \ -xf ${_DISTDIR}/tesseract-ocr-3.0${n}.${l}.tar.gz *.traineddata .endfor .endfor @cd ${STAGEDIR}${DATADIR} ; ${CHMOD} ${BINMODE} ${PORTDATA} .include