ports/72948: New Port: textproc/treetagger

Yuichiro AIZAWA yaizawa at mdbl.sfc.keio.ac.jp
Thu Oct 21 01:50:29 UTC 2004


>Number:         72948
>Category:       ports
>Synopsis:       New Port: textproc/treetagger
>Confidential:   no
>Severity:       non-critical
>Priority:       low
>Responsible:    freebsd-ports-bugs
>State:          open
>Quarter:        
>Keywords:       
>Date-Required:
>Class:          change-request
>Submitter-Id:   current-users
>Arrival-Date:   Thu Oct 21 01:50:27 GMT 2004
>Closed-Date:
>Last-Modified:
>Originator:     Yuichiro AIZAWA
>Release:        FreeBSD 5.2.1-RELEASE-p11 i386
>Organization:
Graduate School of Media and Governance, Keio University
>Environment:
System: FreeBSD amaterasu.yaizawa.jp 5.2.1-RELEASE-p11 FreeBSD 5.2.1-RELEASE-p11 #8: Tue Oct 5 14:15:59 JST 2004 yaizawa at amaterasu.yaizawa.jp:/usr/obj/usr/src/sys/TP570 i386
>Description:
A language independent part-of-speech tagger
>How-To-Repeat:
>Fix:
# This is a shell archive.  Save it in a file, remove anything before
# this line, and then unpack it by entering "sh file".  Note, it may
# create directories; files and directories will be owned by you and
# have default permissions.
#
# This archive contains:
#
#	/usr/ports/textproc/treetagger/
#	/usr/ports/textproc/treetagger/files
#	/usr/ports/textproc/treetagger/files/patch-filter-german-tags
#	/usr/ports/textproc/treetagger/files/patch-lookup.perl
#	/usr/ports/textproc/treetagger/files/patch-tagger-chunker-english
#	/usr/ports/textproc/treetagger/files/patch-tagger-chunker-german
#	/usr/ports/textproc/treetagger/files/patch-tree-tagger-english
#	/usr/ports/textproc/treetagger/files/patch-tree-tagger-french
#	/usr/ports/textproc/treetagger/files/patch-tree-tagger-german
#	/usr/ports/textproc/treetagger/files/patch-tree-tagger-italian
#	/usr/ports/textproc/treetagger/files/patch-filter-chunker-output.perl
#	/usr/ports/textproc/treetagger/Makefile
#	/usr/ports/textproc/treetagger/distinfo
#	/usr/ports/textproc/treetagger/pkg-plist
#	/usr/ports/textproc/treetagger/pkg-descr
#
echo c - /usr/ports/textproc/treetagger/
mkdir -p /usr/ports/textproc/treetagger/ > /dev/null 2>&1
echo c - /usr/ports/textproc/treetagger/files
mkdir -p /usr/ports/textproc/treetagger/files > /dev/null 2>&1
echo x - /usr/ports/textproc/treetagger/files/patch-filter-german-tags
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-filter-german-tags << 'END-of-/usr/ports/textproc/treetagger/files/patch-filter-german-tags'
X*** cmd/filter-german-tags.orig	Mon Dec  3 17:45:09 2001
X--- cmd/filter-german-tags	Mon Jul 12 17:06:38 2004
X***************
X*** 3,9 ****
X  # Input format: word tag <lemma>
X  # lemma is optional, tag must be in the second position
X  
X! gawk 'BEGIN{OFS=FS="\t";getline;word=$1;tag=$2;lemma=$3}\
X  ((tag~"V.FIN" || tag~"V.INF")\
X  && $2~"^[$][.,]"\
X  && (word~"[erlu]n$" && word!~"[^aeiou]e*ten$") && word!~".zu.....") \
X--- 3,9 ----
X  # Input format: word tag <lemma>
X  # lemma is optional, tag must be in the second position
X  
X! %%GAWK%% 'BEGIN{OFS=FS="\t";getline;word=$1;tag=$2;lemma=$3}\
X  ((tag~"V.FIN" || tag~"V.INF")\
X  && $2~"^[$][.,]"\
X  && (word~"[erlu]n$" && word!~"[^aeiou]e*ten$") && word!~".zu.....") \
END-of-/usr/ports/textproc/treetagger/files/patch-filter-german-tags
echo x - /usr/ports/textproc/treetagger/files/patch-lookup.perl
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-lookup.perl << 'END-of-/usr/ports/textproc/treetagger/files/patch-lookup.perl'
X*** cmd/lookup.perl.orig	Wed Jun  4 16:54:49 2003
X--- cmd/lookup.perl	Thu Jul  8 00:46:05 2004
X***************
X*** 1,4 ****
X! #!/usr/local/GNU/bin/perl
X  
X  # Usage: lookup.perl <file>*
X  # Perl script to be used prior to tagging
X--- 1,4 ----
X! #!%%PERL%%
X  
X  # Usage: lookup.perl <file>*
X  # Perl script to be used prior to tagging
END-of-/usr/ports/textproc/treetagger/files/patch-lookup.perl
echo x - /usr/ports/textproc/treetagger/files/patch-tagger-chunker-english
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-tagger-chunker-english << 'END-of-/usr/ports/textproc/treetagger/files/patch-tagger-chunker-english'
X*** cmd/tagger-chunker-english.orig	Wed Oct 30 16:56:01 2002
X--- cmd/tagger-chunker-english	Thu Jul  8 02:25:34 2004
X***************
X*** 2,10 ****
X  
X  # Set these paths appropriately
X  
X! BIN=./bin
X! CMD=./cmd
X! LIB=./lib
X  
X  TOKENIZER=${BIN}/separate-punctuation
X  ABBR_LIST=${LIB}/english-abbreviations
X--- 2,10 ----
X  
X  # Set these paths appropriately
X  
X! BIN=%%BINDIR%%
X! CMD=%%CMDDIR%%
X! LIB=%%LIBDIR%%
X  
X  TOKENIZER=${BIN}/separate-punctuation
X  ABBR_LIST=${LIB}/english-abbreviations
END-of-/usr/ports/textproc/treetagger/files/patch-tagger-chunker-english
echo x - /usr/ports/textproc/treetagger/files/patch-tagger-chunker-german
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-tagger-chunker-german << 'END-of-/usr/ports/textproc/treetagger/files/patch-tagger-chunker-german'
X*** cmd/tagger-chunker-german.orig	Mon Dec  3 17:51:51 2001
X--- cmd/tagger-chunker-german	Thu Jul  8 02:27:45 2004
X***************
X*** 2,10 ****
X  
X  # Set these paths appropriately
X  
X! BIN=./bin
X! CMD=./cmd
X! LIB=./lib
X  
X  GERMANTAGGER=${CMD}/tree-tagger-german
X  TAGGER=${BIN}/tree-tagger
X--- 2,10 ----
X  
X  # Set these paths appropriately
X  
X! BIN=%%BINDIR%%
X! CMD=%%CMDDIR%%
X! LIB=%%LIBDIR%%
X  
X  GERMANTAGGER=${CMD}/tree-tagger-german
X  TAGGER=${BIN}/tree-tagger
END-of-/usr/ports/textproc/treetagger/files/patch-tagger-chunker-german
echo x - /usr/ports/textproc/treetagger/files/patch-tree-tagger-english
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-tree-tagger-english << 'END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-english'
X*** cmd/tree-tagger-english.orig	Mon Dec  3 17:50:29 2001
X--- cmd/tree-tagger-english	Thu Jul  8 02:28:41 2004
X***************
X*** 2,10 ****
X  
X  # Set these paths appropriately
X  
X! BIN=./bin
X! CMD=./cmd
X! LIB=./lib
X  
X  TOKENIZER=${BIN}/separate-punctuation
X  TAGGER=${BIN}/tree-tagger
X--- 2,10 ----
X  
X  # Set these paths appropriately
X  
X! BIN=%%BINDIR%%
X! CMD=%%CMDDIR%%
X! LIB=%%LIBDIR%%
X  
X  TOKENIZER=${BIN}/separate-punctuation
X  TAGGER=${BIN}/tree-tagger
END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-english
echo x - /usr/ports/textproc/treetagger/files/patch-tree-tagger-french
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-tree-tagger-french << 'END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-french'
X*** cmd/tree-tagger-french.orig	Mon Dec  3 17:50:21 2001
X--- cmd/tree-tagger-french	Thu Jul  8 02:30:11 2004
X***************
X*** 14,21 ****
X  
X  # THESE VARIABLES HAVE TO BE SET:
X  
X! BIN=./bin
X! LIB=./lib
X  
X  # set your default options for the Tree Tagger
X  TAGGEROPTS="-token -lemma -sgml"
X--- 14,21 ----
X  
X  # THESE VARIABLES HAVE TO BE SET:
X  
X! BIN=%%BINDIR%%
X! LIB=%%LIBDIR%%
X  
X  # set your default options for the Tree Tagger
X  TAGGEROPTS="-token -lemma -sgml"
END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-french
echo x - /usr/ports/textproc/treetagger/files/patch-tree-tagger-german
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-tree-tagger-german << 'END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-german'
X*** cmd/tree-tagger-german.orig	Mon Dec  3 17:49:58 2001
X--- cmd/tree-tagger-german	Thu Jul  8 02:31:20 2004
X***************
X*** 2,10 ****
X  
X  # Set these paths appropriately
X  
X! BIN=./bin
X! CMD=./cmd
X! LIB=./lib
X  
X  TOKENIZER=${BIN}/separate-punctuation
X  TAGGER=${BIN}/tree-tagger
X--- 2,10 ----
X  
X  # Set these paths appropriately
X  
X! BIN=%%BINDIR%%
X! CMD=%%CMDDIR%%
X! LIB=%%LIBDIR%%
X  
X  TOKENIZER=${BIN}/separate-punctuation
X  TAGGER=${BIN}/tree-tagger
END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-german
echo x - /usr/ports/textproc/treetagger/files/patch-tree-tagger-italian
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-tree-tagger-italian << 'END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-italian'
X*** cmd/tree-tagger-italian.orig	Mon Dec  3 17:50:15 2001
X--- cmd/tree-tagger-italian	Thu Jul  8 02:32:09 2004
X***************
X*** 12,19 ****
X  
X  # THESE VARIABLES HAVE TO BE SET:
X  
X! BIN=./bin
X! LIB=./lib
X  
X  # set your default options for the Tree Tagger
X  TAGGEROPTS="-token -lemma -sgml"
X--- 12,19 ----
X  
X  # THESE VARIABLES HAVE TO BE SET:
X  
X! BIN=%%BINDIR%%
X! LIB=%%LIBDIR%%
X  
X  # set your default options for the Tree Tagger
X  TAGGEROPTS="-token -lemma -sgml"
END-of-/usr/ports/textproc/treetagger/files/patch-tree-tagger-italian
echo x - /usr/ports/textproc/treetagger/files/patch-filter-chunker-output.perl
sed 's/^X//' >/usr/ports/textproc/treetagger/files/patch-filter-chunker-output.perl << 'END-of-/usr/ports/textproc/treetagger/files/patch-filter-chunker-output.perl'
X*** cmd/filter-chunker-output.perl.orig	Wed Oct  8 17:25:15 2003
X--- cmd/filter-chunker-output.perl	Thu Jul  8 00:45:16 2004
X***************
X*** 1,4 ****
X! #!/usr/local/bin/perl
X  
X  use Getopt::Std;
X  getopts('t');
X--- 1,4 ----
X! #!%%PERL%%
X  
X  use Getopt::Std;
X  getopts('t');
END-of-/usr/ports/textproc/treetagger/files/patch-filter-chunker-output.perl
echo x - /usr/ports/textproc/treetagger/Makefile
sed 's/^X//' >/usr/ports/textproc/treetagger/Makefile << 'END-of-/usr/ports/textproc/treetagger/Makefile'
X# New ports collection makefile for: treetagger
X# Date created: 7 July 2004
X# Whom: Yuichiro AIZAWA <yaizawa at mdbl.sfc.keio.ac.jp>
X#
X# $FreeBSD$
X#
X
XPORTNAME=	treetagger
XPORTVERSION=	3.1
XCATEGORIES=	textproc
XMASTER_SITES=	ftp://ftp.ims.uni-stuttgart.de/pub/corpora/
XMASTER_SITES+=	http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/:treebanktag
XMASTER_SITES+=	http://www.ims.uni-stuttgart.de/%7eschmid/:frenchtag
XDISTFILES=	tagger-scripts.tar.gz
XDIST_SUBDIR=	treetagger
XEXTRACT_ONLY=	tagger-scripts.tar.gz
X
XMAINTAINER=	yaizawa at mdbl.sfc.keio.ac.jp
XCOMMENT=	A language independent part-of-speech tagger
X
XRESTRICTED=	no-commercial-use
XNO_CDROM=	"The licensee has no right to give the system to third parties without written permission from the licenser."
XNO_PACKAGE=	"The licensee has no right to give the system to third parties without written permission from the licenser."
X
XUSE_PERL5=	yes
XNO_BUILD=	yes
X
XOPTIONS+=	ENGLISH "Enable English Support" on
XOPTIONS+=	GERMAN  "Enable German Support"  on
XOPTIONS+=	FRENCH  "Enable French Support"  on
XOPTIONS+=	ITALIAN "Enable Italian Support" on
X
XPATCH_WRKSRC=	${WRKDIR}
XFILES_SUB=	PERL=${PERL} GAWK=${PREFIX}/bin/gawk \
X		BINDIR=${PREFIX}/bin CMDDIR=${PREFIX}/bin LIBDIR=${PREFIX}/lib
X
XONLY_FOR_ARCHS=	i386
X
XBINFILES+=	separate-punctuation \
X		train-tree-tagger    \
X		tree-tagger
X
X.include <bsd.port.pre.mk>
X
X.if ${ARCH} == "i386"
XUSE_LINUX=	yes
XDISTNAME=	tree-tagger-linux-${PORTVERSION}
XDISTFILES+=	${DISTNAME}.tar.gz
XEXTRACT_ONLY+=	${DISTNAME}.tar.gz
XSCRIPTFILES+=	filter-chunker-output.perl \
X		lookup.perl
X.if defined(WITH_ENGLISH)
XDISTFILES+=	english-par-linux-${PORTVERSION}.bin.gz
XDISTFILES+=	english-chunker-par-linux-${PORTVERSION}.bin.gz
XSCRIPTFILES+=	tagger-chunker-english \
X		tree-tagger-english
XPARFILES+=	english.par           \
X		english-chunker.par   \
X		english-abbreviations
X.endif
X.if defined(WITH_GERMAN)
XRUN_DEPENDS+=	${LOCALBASE}/bin/gawk:${PORTSDIR}/lang/gawk
XDISTFILES+=	german-par-linux-${PORTVERSION}.bin.gz
XDISTFILES+=	german-chunker-par-linux-${PORTVERSION}.bin.gz
XSCRIPTFILES+=	filter-german-tags    \
X		tagger-chunker-german \
X		tree-tagger-german
XPARFILES+=	german.par           \
X		german-chunker.par   \
X		german-abbreviations
X.endif
X.if defined(WITH_FRENCH)
XDISTFILES+=	french-par-linux-${PORTVERSION}.bin.gz
XSCRIPTFILES+=	tree-tagger-french
XPARFILES+=	french.par
X.endif
X.if defined(WITH_ITALIAN)
XDISTFILES+=	italian-par-linux-${PORTVERSION}.bin.gz
XSCRIPTFILES+=	tree-tagger-italian
XPARFILES+=	italian.par
X.endif
X.endif
X
X.if !defined(NOPORTDOCS)
XDISTFILES+=	tree-tagger1.pdf
XDISTFILES+=	tree-tagger2.pdf
XDOCFILES+=	FILES           \
X		LICENSE         \
X		README          \
X		README.script   \
X		doc/nemlap94.ps \
X		doc/sigdat95.ps
XEXTDOCFILES+=	tree-tagger1.pdf
XEXTDOCFILES+=	tree-tagger2.pdf
X.if defined(WITH_ENGLISH)
XDISTFILES+=	Penn-Treebank-Tagset.ps:treebanktag
XEXTDOCFILES+=	Penn-Treebank-Tagset.ps
X.endif
X.if defined(WITH_GERMAN)
XDISTFILES+=	stts_guide.ps.gz
XEXTDOCFILES+=	stts_guide.ps.gz
X.endif
X.if defined(WITH_FRENCH)
XDISTFILES+=	french-tagset.html:frenchtag
XEXTDOCFILES+=	french-tagset.html
X.if ${ARCH} == "i386"
XDISTFILES+=	french-par-linux.info
X# This info file doesn't have enough information
X#INFO+=	french-par-linux
XINFOFILES+=	french-par-linux
X.endif
X.endif
X.if defined(WITH_ITALIAN)
XDISTFILES+=	italian-tagset.txt
XEXTDOCFILES+=	italian-tagset.txt
X.if ${ARCH} == "i386"
XDISTFILES+=	italian-par-linux.info
X# This info file doesn't have enough information
X#INFO+=	italian-par-linux
XINFOFILES+=	italian-par-linux
X.endif
X.endif
X.endif
X
Xpost-extract:
X.if ${ARCH} == "i386"
X.if defined(WITH_ENGLISH)
X	@${GZCAT} ${DISTDIR}/${DIST_SUBDIR}/english-par-linux-${PORTVERSION}.bin.gz \
X		> ${WRKDIR}/lib/english.par
X	@${GZCAT} ${DISTDIR}/${DIST_SUBDIR}/english-chunker-par-linux-${PORTVERSION}.bin.gz \
X		> ${WRKDIR}/lib/english-chunker.par
X.endif
X.if defined(WITH_GERMAN)
X	@${GZCAT} ${DISTDIR}/${DIST_SUBDIR}/german-par-linux-${PORTVERSION}.bin.gz \
X		> ${WRKDIR}/lib/german.par
X	@${GZCAT} ${DISTDIR}/${DIST_SUBDIR}/german-chunker-par-linux-${PORTVERSION}.bin.gz \
X		> ${WRKDIR}/lib/german-chunker.par
X.endif
X.if defined(WITH_FRENCH)
X	@${GZCAT} ${DISTDIR}/${DIST_SUBDIR}/french-par-linux-${PORTVERSION}.bin.gz \
X		> ${WRKDIR}/lib/french.par
X.endif
X.if defined(WITH_ITALIAN)
X	@${GZCAT} ${DISTDIR}/${DIST_SUBDIR}/italian-par-linux-${PORTVERSION}.bin.gz \
X		> ${WRKDIR}/lib/italian.par
X.endif
X.endif
X
Xpost-patch:
X	@${MKDIR} ${WRKDIR}/cmd.port/
X.for i in ${SCRIPTFILES}
X	@${SED} ${FILES_SUB:S/$/!g/:S/^/ -e s!%%/:S/=/%%!/} \
X		${WRKDIR}/cmd/$i > ${WRKDIR}/cmd.port/$i
X.endfor
X
Xdo-install:
X.for i in ${BINFILES}
X	${INSTALL_PROGRAM} ${WRKDIR}/bin/$i ${PREFIX}/bin/
X.endfor
X.for i in ${SCRIPTFILES}
X	${INSTALL_SCRIPT} ${WRKDIR}/cmd.port/$i ${PREFIX}/bin/
X.endfor
X.for i in ${PARFILES}
X	${INSTALL_DATA} ${WRKDIR}/lib/$i ${PREFIX}/lib/
X.endfor
X.if !defined(NOPORTDOCS)
X	${MKDIR} ${PREFIX}/share/doc/treetagger
X.for i in ${DOCFILES}
X	${INSTALL_DATA} ${WRKDIR}/$i ${PREFIX}/share/doc/treetagger/
X.endfor
X.for i in ${EXTDOCFILES}
X	${INSTALL_DATA} ${DISTDIR}/${DIST_SUBDIR}/$i ${PREFIX}/share/doc/treetagger/
X.endfor
X.for i in ${INFOFILES}
X	${INSTALL_DATA} ${DISTDIR}/${DIST_SUBDIR}/$i.info ${PREFIX}/share/doc/treetagger/
X.endfor
X.endif
X
Xpost-install:
X.if ${ARCH} == "i386"
X.for i in ${BINFILES}
X	${BRANDELF} -t Linux ${PREFIX}/bin/$i
X.endfor
X.endif
X
X.include <bsd.port.post.mk>
END-of-/usr/ports/textproc/treetagger/Makefile
echo x - /usr/ports/textproc/treetagger/distinfo
sed 's/^X//' >/usr/ports/textproc/treetagger/distinfo << 'END-of-/usr/ports/textproc/treetagger/distinfo'
XMD5 (treetagger/tagger-scripts.tar.gz) = 45ec968fcf861a67fcfdfa5de9121871
XSIZE (treetagger/tagger-scripts.tar.gz) = 11439
XMD5 (treetagger/install-tagger.sh) = 081e9ad161ce5f51cdc8eeb347d31773
XSIZE (treetagger/install-tagger.sh) = 5075
XMD5 (treetagger/tree-tagger-linux-3.1.tar.gz) = dc3c6f6c6d51b610eae3d7f0047f24bd
XSIZE (treetagger/tree-tagger-linux-3.1.tar.gz) = 821529
XMD5 (treetagger/english-par-linux-3.1.bin.gz) = 60d60b47b928b26282dd70ec836982a6
XSIZE (treetagger/english-par-linux-3.1.bin.gz) = 2945603
XMD5 (treetagger/english-chunker-par-linux-3.1.bin.gz) = cf85293b999fc2f1dd81cecf7acca3e1
XSIZE (treetagger/english-chunker-par-linux-3.1.bin.gz) = 3247005
XMD5 (treetagger/german-par-linux-3.1.bin.gz) = 14197d3765257df7a9edac94d876b3b0
XSIZE (treetagger/german-par-linux-3.1.bin.gz) = 6919126
XMD5 (treetagger/german-chunker-par-linux-3.1.bin.gz) = 2ad3b385a3766727d722f2e452deadfa
XSIZE (treetagger/german-chunker-par-linux-3.1.bin.gz) = 886503
XMD5 (treetagger/french-par-linux-3.1.bin.gz) = e9b8eb7f774dc1962cd12ae529b48bc0
XSIZE (treetagger/french-par-linux-3.1.bin.gz) = 2421562
XMD5 (treetagger/italian-par-linux-3.1.bin.gz) = 0da677102a71ea7296c839da715af484
XSIZE (treetagger/italian-par-linux-3.1.bin.gz) = 5495853
XMD5 (treetagger/Tagger-Licence) = 57475a3280d8c39054de950635ac6227
XSIZE (treetagger/Tagger-Licence) = 2307
XMD5 (treetagger/tree-tagger1.pdf) = d10675bc22f3eef7d45080937deefb8c
XSIZE (treetagger/tree-tagger1.pdf) = 191140
XMD5 (treetagger/tree-tagger2.pdf) = 26ea3560121e979f232b27dc6f250d5a
XSIZE (treetagger/tree-tagger2.pdf) = 187949
XMD5 (treetagger/Penn-Treebank-Tagset.ps) = c4beb12a42a6c72fe1d0550979a0359c
XSIZE (treetagger/Penn-Treebank-Tagset.ps) = 190071
XMD5 (treetagger/stts_guide.ps.gz) = 40e8cd9fa6f0b7a426903c756822233b
XSIZE (treetagger/stts_guide.ps.gz) = 178034
XMD5 (treetagger/french-tagset.html) = f61fdf6cd0d715d031e840fa366087a1
XSIZE (treetagger/french-tagset.html) = 1850
XMD5 (treetagger/french-par-linux.info) = 68583c84ee6af00f65ceeddd2f5a63fc
XSIZE (treetagger/french-par-linux.info) = 3163
XMD5 (treetagger/italian-tagset.txt) = de8a0d5d95c966b689b6cbcde30f0d77
XSIZE (treetagger/italian-tagset.txt) = 944
XMD5 (treetagger/italian-par-linux.info) = aab05ced686b3d7ec4de5ec144111f84
XSIZE (treetagger/italian-par-linux.info) = 1880
END-of-/usr/ports/textproc/treetagger/distinfo
echo x - /usr/ports/textproc/treetagger/pkg-plist
sed 's/^X//' >/usr/ports/textproc/treetagger/pkg-plist << 'END-of-/usr/ports/textproc/treetagger/pkg-plist'
Xbin/separate-punctuation
Xbin/train-tree-tagger
Xbin/tree-tagger
Xbin/filter-chunker-output.perl
Xbin/lookup.perl
Xbin/tagger-chunker-english
Xbin/tree-tagger-english
Xbin/filter-german-tags
Xbin/tagger-chunker-german
Xbin/tree-tagger-german
Xbin/tree-tagger-french
Xbin/tree-tagger-italian
Xlib/english-chunker.par
Xlib/english.par
Xlib/english-abbreviations
Xlib/german-chunker.par
Xlib/german.par
Xlib/german-abbreviations
Xlib/french.par
Xlib/italian.par
X%%PORTDOCS%%%%DOCSDIR%%/FILES
X%%PORTDOCS%%%%DOCSDIR%%/LICENSE
X%%PORTDOCS%%%%DOCSDIR%%/README
X%%PORTDOCS%%%%DOCSDIR%%/README.script
X%%PORTDOCS%%%%DOCSDIR%%/nemlap94.ps
X%%PORTDOCS%%%%DOCSDIR%%/sigdat95.ps
X%%PORTDOCS%%%%DOCSDIR%%/tree-tagger1.pdf
X%%PORTDOCS%%%%DOCSDIR%%/tree-tagger2.pdf
X%%PORTDOCS%%%%DOCSDIR%%/Penn-Treebank-Tagset.ps
X%%PORTDOCS%%%%DOCSDIR%%/stts_guide.ps.gz
X%%PORTDOCS%%%%DOCSDIR%%/french-tagset.html
X%%PORTDOCS%%%%DOCSDIR%%/italian-tagset.txt
X%%PORTDOCS%%%%DOCSDIR%%/french-par-linux.info
X%%PORTDOCS%%%%DOCSDIR%%/italian-par-linux.info
X%%PORTDOCS%%@dirrm %%DOCSDIR%%
END-of-/usr/ports/textproc/treetagger/pkg-plist
echo x - /usr/ports/textproc/treetagger/pkg-descr
sed 's/^X//' >/usr/ports/textproc/treetagger/pkg-descr << 'END-of-/usr/ports/textproc/treetagger/pkg-descr'
XThe TreeTagger is a tool for annotating text with part-of-speech and
Xlemma information which has been developed within the TC project at
Xthe Institute for Computational Linguistics of the University of
XStuttgart. The TreeTagger has been successfully used to tag German,
XEnglish, French, Italian, Greek and old French texts and is easily
Xadaptable to other languages if a lexicon and a manually tagged
Xtraining corpus are available.
X
XWWW: http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/
X
X- Yuichiro AIZAWA
Xyaizawa at mdbl.sfc.keio.ac.jp
END-of-/usr/ports/textproc/treetagger/pkg-descr
exit

>Release-Note:
>Audit-Trail:
>Unformatted:



More information about the freebsd-ports-bugs mailing list