Initial import of packages for GutenMark:

GutenMark is a tool for automatically creating high-quality HTML
or LaTeX markup from Project Gutenberg etexts.  In combination with
other freely-available conversion tools, GutenMark can convert
Project Gutenberg etexts into publication-quality Postscript or
PDF, for print-on-demand applications.  The goal is for this
conversion is completely automatic, without manual markup or editing.

5 files changed, 230 insertions, 0 deletions

diff --git a/textproc/GutenMark-words/DESCR b/textproc/GutenMark-words/DESCR
new file mode 100644
index 00000000000..8a24baa2373
--- /dev/null
+++ b/textproc/GutenMark-words/DESCR
@@ -0,0 +1,9 @@
+GutenMark is a tool for automatically creating high-quality HTML
+or LaTeX markup from Project Gutenberg etexts.  In combination with
+other freely-available conversion tools, GutenMark can convert
+Project Gutenberg etexts into publication-quality Postscript or
+PDF, for print-on-demand applications.  The goal is for this
+conversion is completely automatic, without manual markup or editing.
+
+This package contains word lists for GutenMark, which make
+the markup more accurate.
diff --git a/textproc/GutenMark-words/Makefile b/textproc/GutenMark-words/Makefile
new file mode 100644
index 00000000000..bf4b5737470
--- /dev/null
+++ b/textproc/GutenMark-words/Makefile
@@ -0,0 +1,42 @@
+# $NetBSD: Makefile,v 1.1.1.1 2002/12/05 15:02:24 wiz Exp $
+#
+
+DISTNAME=	GutenMark-words-20021124
+CATEGORIES=	textproc
+MASTER_SITES=	ftp://ftp.sandroid.org/GutenMark/Wordlists/
+DISTFILES=	${WORDLISTS} GutenMark.cfg
+
+MAINTAINER=	wiz@netbsd.org
+HOMEPAGE=	http://www.sandroid.org/GutenMark/
+COMMENT=	word lists for GutenMark
+
+WORDLISTS=	special.words.gz english.names.gz US.places.gz \
+		french.names.gz english.words.gz french.words.gz \
+		german2.words.gz german.words.gz latin.words.gz \
+		italian.words.gz spanish.words.gz NonUS.places.gz \
+		norwegian.words.gz gaelic.words.gz danish.words.gz \
+		swedish.words.gz finnish.words.gz nonenglish.words.gz
+SITES_GutenMark.cfg=http://www.sandroid.org/GutenMark/
+
+DIST_SUBDIR=	${DISTNAME}
+EXTRACT_ONLY=	# empty
+NO_CONFIGURE=	YES
+WRKSRC=		${WRKDIR}
+
+post-extract:
+	${CP} ${_DISTDIR}/GutenMark.cfg ${WRKDIR}/GutenMark.cfg.in
+
+do-build:
+	cd ${WRKDIR} && ${SED} "s|@@PREFIX@@|${PREFIX}|g" \
+		GutenMark.cfg.in > GutenMark.cfg
+
+do-install:
+	${INSTALL_DATA_DIR} ${PREFIX}/share/GutenMark
+	${INSTALL_DATA_DIR} ${PREFIX}/share/examples/GutenMark
+	for wl in ${WORDLISTS}; do \
+		${INSTALL_DATA} ${_DISTDIR}/$$wl ${PREFIX}/share/GutenMark; \
+	done
+	${INSTALL_DATA} ${WRKDIR}/GutenMark.cfg \
+		${PREFIX}/share/examples/GutenMark
+
+.include "../../mk/bsd.pkg.mk"
diff --git a/textproc/GutenMark-words/PLIST b/textproc/GutenMark-words/PLIST
new file mode 100644
index 00000000000..3ee476163b3
--- /dev/null
+++ b/textproc/GutenMark-words/PLIST
@@ -0,0 +1,22 @@
+@comment $NetBSD: PLIST,v 1.1.1.1 2002/12/05 15:02:24 wiz Exp $
+share/GutenMark/NonUS.places.gz
+share/GutenMark/US.places.gz
+share/GutenMark/danish.words.gz
+share/GutenMark/english.names.gz
+share/GutenMark/english.words.gz
+share/GutenMark/finnish.words.gz
+share/GutenMark/french.names.gz
+share/GutenMark/french.words.gz
+share/GutenMark/gaelic.words.gz
+share/GutenMark/german.words.gz
+share/GutenMark/german2.words.gz
+share/GutenMark/italian.words.gz
+share/GutenMark/latin.words.gz
+share/GutenMark/nonenglish.words.gz
+share/GutenMark/norwegian.words.gz
+share/GutenMark/spanish.words.gz
+share/GutenMark/special.words.gz
+share/GutenMark/swedish.words.gz
+share/examples/GutenMark/GutenMark.cfg
+@dirrm share/examples/GutenMark
+@dirrm share/GutenMark
diff --git a/textproc/GutenMark-words/distinfo b/textproc/GutenMark-words/distinfo
new file mode 100644
index 00000000000..246ae4063d2
--- /dev/null
+++ b/textproc/GutenMark-words/distinfo
@@ -0,0 +1,41 @@
+$NetBSD: distinfo,v 1.1.1.1 2002/12/05 15:02:24 wiz Exp $
+
+SHA1 (GutenMark-words-20021124/special.words.gz) = 24705d1812d2fa68b1d39078744d69153d34ca20
+Size (GutenMark-words-20021124/special.words.gz) = 420 bytes
+SHA1 (GutenMark-words-20021124/english.names.gz) = 480dd0747c50fa0d3b9e4543e49f335e0fea875d
+Size (GutenMark-words-20021124/english.names.gz) = 348183 bytes
+SHA1 (GutenMark-words-20021124/US.places.gz) = 8d71cbfb881123d19859ff364ba605a521ce438a
+Size (GutenMark-words-20021124/US.places.gz) = 144299 bytes
+SHA1 (GutenMark-words-20021124/french.names.gz) = 27e362c79b327672b0c9b4cd948f412b5052f57a
+Size (GutenMark-words-20021124/french.names.gz) = 6876 bytes
+SHA1 (GutenMark-words-20021124/english.words.gz) = 95797740a3fc172615a208b316146c50b511384f
+Size (GutenMark-words-20021124/english.words.gz) = 448554 bytes
+SHA1 (GutenMark-words-20021124/french.words.gz) = e060f0d0f9408fa297f0c577dd65df01953f7856
+Size (GutenMark-words-20021124/french.words.gz) = 372628 bytes
+SHA1 (GutenMark-words-20021124/german2.words.gz) = 1372c9a8b8b7d4c207397487a6a53ef20c4db903
+Size (GutenMark-words-20021124/german2.words.gz) = 581858 bytes
+SHA1 (GutenMark-words-20021124/german.words.gz) = e231ecf410a5d59c3d1fb4f0ca2bde3d50491a7e
+Size (GutenMark-words-20021124/german.words.gz) = 209118 bytes
+SHA1 (GutenMark-words-20021124/latin.words.gz) = b9973022753762c79293a0e1620baad10d1731b1
+Size (GutenMark-words-20021124/latin.words.gz) = 194863 bytes
+SHA1 (GutenMark-words-20021124/italian.words.gz) = 3d9f0b6df3e19110b6b2292d5840b629d1d06757
+Size (GutenMark-words-20021124/italian.words.gz) = 382622 bytes
+SHA1 (GutenMark-words-20021124/spanish.words.gz) = c7d7947ce4fa5c8861f872328700c6fa78782328
+Size (GutenMark-words-20021124/spanish.words.gz) = 322164 bytes
+SHA1 (GutenMark-words-20021124/NonUS.places.gz) = 6947fe70bfaec6ee0b77c154cc36d1551c49c164
+Size (GutenMark-words-20021124/NonUS.places.gz) = 5992126 bytes
+SHA1 (GutenMark-words-20021124/norwegian.words.gz) = a68df9eba8d087074be1bdda7dc5a562cceb9e91
+Size (GutenMark-words-20021124/norwegian.words.gz) = 2078430 bytes
+SHA1 (GutenMark-words-20021124/gaelic.words.gz) = 38fb7331692497061bb3d38cb33830dee1d30da5
+Size (GutenMark-words-20021124/gaelic.words.gz) = 297906 bytes
+SHA1 (GutenMark-words-20021124/danish.words.gz) = 5485142949f519920383cdc9c896d263d5f1b0dd
+Size (GutenMark-words-20021124/danish.words.gz) = 557836 bytes
+SHA1 (GutenMark-words-20021124/swedish.words.gz) = a4ffcdedaab290b93eb65a0d59126f9c412ceed1
+Size (GutenMark-words-20021124/swedish.words.gz) = 254130 bytes
+SHA1 (GutenMark-words-20021124/finnish.words.gz) = 6a96e3ac7a5e185c9ca83982efd8610c87cf192d
+Size (GutenMark-words-20021124/finnish.words.gz) = 284898 bytes
+SHA1 (GutenMark-words-20021124/nonenglish.words.gz) = 8bf484886f757a4d67272284592a5b122112a0ee
+Size (GutenMark-words-20021124/nonenglish.words.gz) = 85 bytes
+SHA1 (GutenMark-words-20021124/GutenMark.cfg) = 5fda2882fcf2c92193bb18ab0f962a8fb82b8ae3
+Size (GutenMark-words-20021124/GutenMark.cfg) = 6289 bytes
+SHA1 (patch-aa) = 469d658e5582f48d87aef2075a862ffd3360982e
diff --git a/textproc/GutenMark-words/patches/patch-aa b/textproc/GutenMark-words/patches/patch-aa
new file mode 100644
index 00000000000..b02145aa423
--- /dev/null
+++ b/textproc/GutenMark-words/patches/patch-aa
@@ -0,0 +1,116 @@
+$NetBSD: patch-aa,v 1.1.1.1 2002/12/05 15:02:24 wiz Exp $
+
+--- GutenMark.cfg.in.orig	Thu Dec  5 15:36:43 2002
++++ GutenMark.cfg.in
+@@ -86,17 +86,17 @@
+ # but it is important for the labels used to match.  Also, if the language
+ # name is omitted, it will default to either "native" or "foreign". 
+ [english]
+-native=special.words.gz English
+-native=english.names.gz English
+-native=US.places.gz English
+-native=french.names.gz French
+-native=english.words.gz English
+-foreign=german2.words.gz German
+-foreign=german.words.gz German
+-foreign=french.words.gz French
+-foreign=latin.words.gz Latin
+-foreign=italian.words.gz Italian
+-foreign=spanish.words.gz Spanish
++native=@@PREFIX@@/share/GutenMark/special.words.gz English
++native=@@PREFIX@@/share/GutenMark/english.names.gz English
++native=@@PREFIX@@/share/GutenMark/US.places.gz English
++native=@@PREFIX@@/share/GutenMark/french.names.gz French
++native=@@PREFIX@@/share/GutenMark/english.words.gz English
++foreign=@@PREFIX@@/share/GutenMark/german2.words.gz German
++foreign=@@PREFIX@@/share/GutenMark/german.words.gz German
++foreign=@@PREFIX@@/share/GutenMark/french.words.gz French
++foreign=@@PREFIX@@/share/GutenMark/latin.words.gz Latin
++foreign=@@PREFIX@@/share/GutenMark/italian.words.gz Italian
++foreign=@@PREFIX@@/share/GutenMark/spanish.words.gz Spanish
+ 
+ # A BIG profile if you don't mind spending a little processing
+ # power to get a better result.  The NonUS.places.gz wordlist
+@@ -117,47 +117,47 @@ foreign=spanish.words.gz Spanish
+ # agency who has compiled the wordlist.
+ 
+ [english_all]
+-native=special.words.gz English
+-native=english.names.gz English
+-native=US.places.gz English
+-native=french.names.gz French
+-native=NonUS.places.gz English
+-native=english.words.gz English
+-foreign=german2.words.gz German
+-foreign=german.words.gz German
+-foreign=french.words.gz French
+-foreign=latin.words.gz Latin
+-foreign=italian.words.gz Italian
+-foreign=spanish.words.gz Spanish
+-foreign=norwegian.words.gz Norwegian
+-foreign=gaelic.words.gz Gaelic
+-foreign=danish.words.gz Danish
+-foreign=swedish.words.gz Swedish
+-foreign=finnish.words.gz Finnish
++native=@@PREFIX@@/share/GutenMark/special.words.gz English
++native=@@PREFIX@@/share/GutenMark/english.names.gz English
++native=@@PREFIX@@/share/GutenMark/US.places.gz English
++native=@@PREFIX@@/share/GutenMark/french.names.gz French
++native=@@PREFIX@@/share/GutenMark/NonUS.places.gz English
++native=@@PREFIX@@/share/GutenMark/english.words.gz English
++foreign=@@PREFIX@@/share/GutenMark/german2.words.gz German
++foreign=@@PREFIX@@/share/GutenMark/german.words.gz German
++foreign=@@PREFIX@@/share/GutenMark/french.words.gz French
++foreign=@@PREFIX@@/share/GutenMark/latin.words.gz Latin
++foreign=@@PREFIX@@/share/GutenMark/italian.words.gz Italian
++foreign=@@PREFIX@@/share/GutenMark/spanish.words.gz Spanish
++foreign=@@PREFIX@@/share/GutenMark/norwegian.words.gz Norwegian
++foreign=@@PREFIX@@/share/GutenMark/gaelic.words.gz Gaelic
++foreign=@@PREFIX@@/share/GutenMark/danish.words.gz Danish
++foreign=@@PREFIX@@/share/GutenMark/swedish.words.gz Swedish
++foreign=@@PREFIX@@/share/GutenMark/finnish.words.gz Finnish
+ 
+ # A profile for testing the performance of uncompressed
+ # wordlists vs. compressed wordlists.
+ [test]
+-native=special.words
+-native=english.names
+-native=US.places
+-native=*.names
+-native=*.places
+-native=english.words
+-foreign=nonenglish.words
+-foreign=german2.words
+-foreign=german.words
+-foreign=french.words
+-foreign=latin.words
+-foreign=italian.words
+-foreign=*.words
++native=@@PREFIX@@/share/GutenMark/special.words
++native=@@PREFIX@@/share/GutenMark/english.names
++native=@@PREFIX@@/share/GutenMark/US.places
++native=@@PREFIX@@/share/GutenMark/*.names
++native=@@PREFIX@@/share/GutenMark/*.places
++native=@@PREFIX@@/share/GutenMark/english.words
++foreign=@@PREFIX@@/share/GutenMark/nonenglish.words
++foreign=@@PREFIX@@/share/GutenMark/german2.words
++foreign=@@PREFIX@@/share/GutenMark/german.words
++foreign=@@PREFIX@@/share/GutenMark/french.words
++foreign=@@PREFIX@@/share/GutenMark/latin.words
++foreign=@@PREFIX@@/share/GutenMark/italian.words
++foreign=@@PREFIX@@/share/GutenMark/*.words
+ 
+ # Here's a template, to act as a starting point for another profile:
+ [mylanguage]
+-native=mylanguage.names.gz
+-native=*.names.gz
+-native=*.places.gz
+-native=mylanguage.words.gz
+-foreign=*.words.gz
++native=@@PREFIX@@/share/GutenMark/mylanguage.names.gz
++native=@@PREFIX@@/share/GutenMark/*.names.gz
++native=@@PREFIX@@/share/GutenMark/*.places.gz
++native=@@PREFIX@@/share/GutenMark/mylanguage.words.gz
++foreign=@@PREFIX@@/share/GutenMark/*.words.gz
+ 
+