5 files changed, 53 insertions, 0 deletions

diff --git a/textproc/Makefile b/textproc/Makefile
index 29c442d48ec5..da472152b078 100644
--- a/textproc/Makefile
+++ b/textproc/Makefile
@@ -444,6 +444,7 @@
     SUBDIR += p5-Lingua-Stem-Snowball-No
     SUBDIR += p5-Lingua-Stem-Snowball-Se
     SUBDIR += p5-Lingua-StopWords
+    SUBDIR += p5-Lingua-Treebank
     SUBDIR += p5-Lucene
     SUBDIR += p5-MARC
     SUBDIR += p5-MARC-Lint
diff --git a/textproc/p5-Lingua-Treebank/Makefile b/textproc/p5-Lingua-Treebank/Makefile
new file mode 100644
index 000000000000..981b744034b9
--- /dev/null
+++ b/textproc/p5-Lingua-Treebank/Makefile
@@ -0,0 +1,25 @@
+# New ports collection makefile for:	textproc/p5-Lingua-Treebank
+# Date created:				27 August 2008
+# Whom:					Cheng-Lung Sung <clsung@FreeBSD.org>
+#
+# $FreeBSD$
+#
+
+PORTNAME=	Lingua-Treebank
+PORTVERSION=	0.15
+CATEGORIES=	textproc perl5
+MASTER_SITES=	CPAN
+PKGNAMEPREFIX=	p5-
+
+MAINTAINER=	clsung@FreeBSD.org
+COMMENT=	Perl extension for manipulating the Penn Treebank format
+
+PERL_CONFIGURE=	yes
+
+MAN1=	get-words.1 list-edges.1 list-rewrites.1 \
+	tree-collapse.1 tree-inflate.1 vocabulary.1
+MAN3=	Lingua::Treebank.3 \
+	Lingua::Treebank::Const.3 \
+	Lingua::Treebank::HeadFinder.3
+
+.include <bsd.port.mk>
diff --git a/textproc/p5-Lingua-Treebank/distinfo b/textproc/p5-Lingua-Treebank/distinfo
new file mode 100644
index 000000000000..9dbbfc6cc0d3
--- /dev/null
+++ b/textproc/p5-Lingua-Treebank/distinfo
@@ -0,0 +1,3 @@
+MD5 (Lingua-Treebank-0.15.tar.gz) = 50eebbf2aa707987be36e21725201bb8
+SHA256 (Lingua-Treebank-0.15.tar.gz) = d203fbd1a6c9fa7630a31214a31bf37dc0bba220f0c9a0470dcdf6b65a1afe59
+SIZE (Lingua-Treebank-0.15.tar.gz) = 37330
diff --git a/textproc/p5-Lingua-Treebank/pkg-descr b/textproc/p5-Lingua-Treebank/pkg-descr
new file mode 100644
index 000000000000..b0069c93182a
--- /dev/null
+++ b/textproc/p5-Lingua-Treebank/pkg-descr
@@ -0,0 +1,10 @@
+This class knows how to read two treebank formats, the Penn format
+and the Chomsky Normal Form (CNF) format. These formats differ in
+how they handle terminal nodes. The Penn format places pre-terminal
+part of speech tags in the left-hand position of a
+parenthesis-delimited pair, just like it does non-terminal nodes.
+
+The CNF format attaches pre-terminal tags to the word with an
+underscore.
+
+WWW: http://search.cpan.org/dist/Lingua-Treebank/
diff --git a/textproc/p5-Lingua-Treebank/pkg-plist b/textproc/p5-Lingua-Treebank/pkg-plist
new file mode 100644
index 000000000000..f76dc86d9fb2
--- /dev/null
+++ b/textproc/p5-Lingua-Treebank/pkg-plist
@@ -0,0 +1,14 @@
+bin/list-rewrites
+bin/list-edges
+bin/tree-collapse
+bin/get-words
+bin/tree-inflate
+bin/vocabulary
+%%SITE_PERL%%/Lingua/Treebank.pm
+%%SITE_PERL%%/Lingua/Treebank/Const.pm
+%%SITE_PERL%%/Lingua/Treebank/HeadFinder.pm
+%%SITE_PERL%%/%%PERL_ARCH%%/auto/Lingua/Treebank/.packlist
+@dirrmtry %%SITE_PERL%%/%%PERL_ARCH%%/auto/Lingua/Treebank
+@dirrmtry %%SITE_PERL%%/%%PERL_ARCH%%/auto/Lingua
+@dirrmtry %%SITE_PERL%%/Lingua/Treebank
+@dirrmtry %%SITE_PERL%%/Lingua