pkgsrc-Changes-HG archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

[pkgsrc/trunk]: pkgsrc/textproc Remove package. Apparently software without ...



details:   https://anonhg.NetBSD.org/pkgsrc/rev/d8397f058a8a
branches:  trunk
changeset: 448970:d8397f058a8a
user:      scole <scole%pkgsrc.org@localhost>
date:      Fri Mar 19 00:48:36 2021 +0000

description:
Remove package.  Apparently software without its own separate repository cannot be stored in pkgsrc

diffstat:

 textproc/Makefile                        |     3 +-
 textproc/split-thai/DESCR                |     8 -
 textproc/split-thai/Makefile             |    90 -
 textproc/split-thai/PLIST                |    11 -
 textproc/split-thai/distinfo             |     6 -
 textproc/split-thai/files/README.txt     |    94 -
 textproc/split-thai/files/pthai.el       |  1848 ------------------------------
 textproc/split-thai/files/sampledict.txt |    45 -
 textproc/split-thai/files/st-emacs       |    56 -
 textproc/split-thai/files/st-icu.cc      |   230 ---
 textproc/split-thai/files/st-swath       |    43 -
 textproc/split-thai/files/st-wordbreak   |   284 ----
 textproc/split-thai/files/tgrep          |   208 ---
 textproc/split-thai/files/words.abm      |     2 -
 14 files changed, 1 insertions(+), 2927 deletions(-)

diffs (truncated from 2994 to 300 lines):

diff -r 226f67c55b89 -r d8397f058a8a textproc/Makefile
--- a/textproc/Makefile Thu Mar 18 23:23:31 2021 +0000
+++ b/textproc/Makefile Fri Mar 19 00:48:36 2021 +0000
@@ -1,4 +1,4 @@
-# $NetBSD: Makefile,v 1.1201 2021/03/18 09:37:12 adam Exp $
+# $NetBSD: Makefile,v 1.1202 2021/03/19 00:48:36 scole Exp $
 #
 
 COMMENT=       Text processing utilities (does not include desktop publishing)
@@ -1115,7 +1115,6 @@
 SUBDIR+=       sord
 SUBDIR+=       source-highlight
 SUBDIR+=       sphinxsearch
-SUBDIR+=       split-thai
 SUBDIR+=       stardic
 SUBDIR+=       stava
 SUBDIR+=       sub2srt
diff -r 226f67c55b89 -r d8397f058a8a textproc/split-thai/DESCR
--- a/textproc/split-thai/DESCR Thu Mar 18 23:23:31 2021 +0000
+++ /dev/null   Thu Jan 01 00:00:00 1970 +0000
@@ -1,8 +0,0 @@
-A collection of utilities to split Thai Unicode UTF-8 text by word
-boundaries, also known as word tokenization or word breaking.  The
-utilities use emacs, swath, perl, and a c++ icu-project program.  All
-use dictionary-based word splitting.
-
-Also included is a merged dictionary file of Thai words, a perl script
-to grep Thai UTF-8 words, and an emacs library that can split and play
-audio for Thai words.
diff -r 226f67c55b89 -r d8397f058a8a textproc/split-thai/Makefile
--- a/textproc/split-thai/Makefile      Thu Mar 18 23:23:31 2021 +0000
+++ /dev/null   Thu Jan 01 00:00:00 1970 +0000
@@ -1,90 +0,0 @@
-# $NetBSD: Makefile,v 1.14 2021/03/18 17:53:41 scole Exp $
-
-PKGNAME=       split-thai-2.0
-CATEGORIES=    textproc
-MAINTAINER=    scole%NetBSD.org@localhost
-COMMENT=       Utilities and an emacs library to split UTF-8 Thai text into words
-# pthai.el, other code, icu dict, swath dict
-LICENSE=       2-clause-bsd AND public-domain AND mit AND gnu-gpl-v2
-
-# xxx fetching a specific version of a file out of a github project
-EXTRACT_SUFX=  # none
-GITHUB_ICU_TAG=        61607c27732906d36c5bd4d23ecc092f89f53a2b
-DISTFILES=     thaidict-${GITHUB_ICU_TAG}.txt
-MASTER_SITES=  -${MASTER_SITE_GITHUB:=unicode-org/}/icu/raw/${GITHUB_ICU_TAG}/icu4c/source/data/brkitr/dictionaries/thaidict.txt
-
-USE_LANGUAGES= c++11   # darwin needed 11?
-
-USE_TOOLS=     pkg-config mkdir cp sh:run env awk cat sort uniq grep wc echo
-USE_TOOLS+=    perl:run
-BUILD_DEPENDS+=        libdatrie-[0-9]*:../../devel/libdatrie
-DEPENDS+=      emacs-[0-9]*:../../editors/emacs
-DEPENDS+=      swath-[0-9]*:../../textproc/swath
-DEPENDS+=      mpg123-[0-9]*:../../audio/mpg123
-
-REPLACE_PERL=  st-wordbreak tgrep
-REPLACE_SH=    st-swath
-
-UTF8_ENV=      env LC_ALL=C.UTF-8
-
-ST_SHARE_DIR=          share/split-thai
-ST_SHARE_BIN=          bin
-INSTALLATION_DIRS=     ${ST_SHARE_BIN} ${ST_SHARE_DIR}
-
-ST_SHARE_FILES=                README.txt pthai.el sampledict.txt words words.tri
-
-# xxx REPLACE_EMACS_SCRIPT
-SUBST_CLASSES+=                        st-emacs-app
-SUBST_STAGE.st-emacs-app=      pre-configure
-SUBST_MESSAGE.st-emacs-app=    Fixing emacs script paths.
-SUBST_FILES.st-emacs-app=      st-emacs
-SUBST_SED.st-emacs-app=                -e 's,!/bin/emacs,!${PREFIX}/bin/emacs,g'
-
-SUBST_CLASSES+=                        dictionary-app
-SUBST_STAGE.dictionary-app=    post-extract
-SUBST_MESSAGE.dictionary-app=  Fixing dictionary paths.
-SUBST_FILES.dictionary-app=    st-emacs st-swath st-wordbreak pthai.el
-SUBST_SED.dictionary-app=      -e 's,ST_SHARE_DIR,${PREFIX}/${ST_SHARE_DIR},g'
-SUBST_SED.dictionary-app+=     -e 's,ST_SHARE_BIN,${PREFIX}/${ST_SHARE_BIN},g'
-
-pre-extract:
-       mkdir -p ${WRKSRC}
-       cd files && cp README.txt pthai.el sampledict.txt \
-               st-emacs st-icu.cc st-swath st-wordbreak tgrep \
-               words.abm ${WRKSRC}
-
-pre-build:
-       cd ${WRKSRC} && ${UTF8_ENV} emacs --batch \
-               --eval='(setq pthai-bootstrap t)' \
-               --eval='(load-file "pthai.el")' \
-               --eval='(pthai-twt-table-save "thai-word-dict")'
-       cp ${WRKDIR}/${DISTFILES} ${WRKSRC}/icu-dict
-       cd ${PREFIX}/share/swath && \
-               ${UTF8_ENV} trietool swathdic list | \
-               awk '{print $$1}' > ${WRKSRC}/swath-dict
-       cd ${WRKSRC} && \
-               ${UTF8_ENV} cat icu-dict swath-dict thai-word-dict | \
-                       grep -v '#' | sort | uniq > words
-       cd ${WRKSRC} && \
-               ${UTF8_ENV} trietool words add-list -e utf-8 words
-.for i in thai-word-dict icu-dict swath-dict
-       @${ECHO} `wc -l ${WRKSRC}/${i} | awk '{print $$1}'` words in ${i}
-.endfor
-       @${ECHO} `wc -l ${WRKSRC}/words | awk '{print $$1}'` \
-               unique words in combined dictionary
-
-do-build:
-       cd ${WRKSRC} && \
-               ${CXX} ${CPPFLAGS} -o st-icu st-icu.cc \
-               `pkg-config --libs --cflags icu-io`
-
-do-install:
-       ${INSTALL_SCRIPT} ${WRKSRC}/st-emacs ${WRKSRC}/st-swath \
-               ${WRKSRC}/st-wordbreak ${WRKSRC}/tgrep ${DESTDIR}${PREFIX}/bin
-       ${INSTALL_PROGRAM} ${WRKSRC}/st-icu ${DESTDIR}${PREFIX}/bin
-.for i in ${ST_SHARE_FILES}
-       ${INSTALL_DATA} ${WRKSRC}/${i} ${DESTDIR}${PREFIX}/share/split-thai
-.endfor
-
-.include "../../textproc/icu/buildlink3.mk"
-.include "../../mk/bsd.pkg.mk"
diff -r 226f67c55b89 -r d8397f058a8a textproc/split-thai/PLIST
--- a/textproc/split-thai/PLIST Thu Mar 18 23:23:31 2021 +0000
+++ /dev/null   Thu Jan 01 00:00:00 1970 +0000
@@ -1,11 +0,0 @@
-@comment $NetBSD: PLIST,v 1.5 2021/03/18 17:53:41 scole Exp $
-bin/st-emacs
-bin/st-icu
-bin/st-swath
-bin/st-wordbreak
-bin/tgrep
-share/split-thai/README.txt
-share/split-thai/pthai.el
-share/split-thai/sampledict.txt
-share/split-thai/words
-share/split-thai/words.tri
diff -r 226f67c55b89 -r d8397f058a8a textproc/split-thai/distinfo
--- a/textproc/split-thai/distinfo      Thu Mar 18 23:23:31 2021 +0000
+++ /dev/null   Thu Jan 01 00:00:00 1970 +0000
@@ -1,6 +0,0 @@
-$NetBSD: distinfo,v 1.1 2020/08/13 20:52:09 scole Exp $
-
-SHA1 (thaidict-61607c27732906d36c5bd4d23ecc092f89f53a2b.txt) = 2a2ad127cc279835cb4df04eb69401a0d4927774
-RMD160 (thaidict-61607c27732906d36c5bd4d23ecc092f89f53a2b.txt) = 0a6df7b7dd6ef502c5dd20020e37b2ca1a5514a2
-SHA512 (thaidict-61607c27732906d36c5bd4d23ecc092f89f53a2b.txt) = 88800fe2a453fc40f16ff54c21c852a8ea8e1496e42d5d187e5b5ac0ff58050830fc0816239e4f88cb23ed301f894d1ca52eb4676fd85c13c285cec815ae7c42
-Size (thaidict-61607c27732906d36c5bd4d23ecc092f89f53a2b.txt) = 493044 bytes
diff -r 226f67c55b89 -r d8397f058a8a textproc/split-thai/files/README.txt
--- a/textproc/split-thai/files/README.txt      Thu Mar 18 23:23:31 2021 +0000
+++ /dev/null   Thu Jan 01 00:00:00 1970 +0000
@@ -1,94 +0,0 @@
-NAME
-     st-emacs
-     st-icu
-     st-swath
-     st-wordbreak
-     tgrep
-     pthai.el
-
-SYNOPSIS
-     st-emacs|st-icu|st-swath|st-wordbreak [filename|text1 text2 ...|'blank']
-     tgrep [options] FILE ...
-
-DESCRIPTION
-     This package is a collection of utilities to separate Thai words
-     by spaces (word tokenization).  They can separate stdin, files,
-     or text as arguments.  It includes these utilities:
-
-     st-emacs:     emacs-script using emacs lisp thai-word library
-                   https://www.gnu.org/software/emacs/
-     st-icu:       basic C++ program using the ICU library
-                   http://site.icu-project.org/
-     st-swath:     sh script wrapper to simplfy args to the swath program
-                   https://linux.thai.net/projects/swath
-     st-wordbreak: perl script to brute-force separate thai words,
-                   see "st-wordbreak -h"
-
-     tgrep:        grep-like utility using perl, see "tgrep -h"
-
-     pthai.el:     emacs library for handling thai text in an emacs buffer,
-                   including word splitting
-     
-EXAMPLES
-      split one or more text strings:
-      # st-swath แมวและหมา
-      # st-swath "แมวหมา" พ่อและแม่
-      
-      read stdin:
-      # echo "แมวและหมา" | st-swath
-
-      read from a file:
-      # st-swath < thaifile.txt
-      # st-swath somefile.txt
-
-      They can also read directly from stdin:
-      # st-icu
-        แมวหมา   (typed in)
-        แมว หมา  (output line by line)
-
-      grep for thai words:
-      # grep แมว thaifile.txt
-
-ENVIRONMENT
-     You will most likely need to set the environment variables LC_ALL
-     or LC_CTYPE for proper unicode handling, e.g., en_US.UTF-8 or
-     C.UTF-8.  These tools are only setup to handle UTF-8 encodings.
-
-     A terminal capable of entering and displaying UTF-8, and some
-     actual UTF-8 fonts installed on the system will also be needed.
-     
-EXIT STATUS
-     0 for success, non zero otherwise.  For tgrep, see "tgrep -h"
-
-NOTES
-     Note that it is not possible to split Thai words 100% accurately
-     without context and meaning.  All these programs use
-     dictionary-based word splitting.
-
-     Also included in the package is a combined thai word dictionary
-     and corresponding .tri file, and emacs lisp .el files for reading
-     and dumping out dictionary files.
-
-     st-emacs, st-swath, and st-wordbreak are setup to use the
-     combined dictionary with words from the emacs 'thai-word library,
-     swath dictionary words, and the icu thai library words.
-
-     st-icu uses its own built in library.  To customise the icu
-     dictionary, you apparently would have to modify
-     icu4c/source/data/brkitr/dictionaries/thaidict.txt and then
-     rebuild the whole library.
-
-     Also included in this package is an emacs library called "pthai"
-     (practice-thai).  It can do word splitting, play mp3 audio for
-     thai words and a few other things.
-     
-SEE ALSO
-     swath(1), libthai(1), emacs(1), locale(1), uconv(1), iconv(1)
-     trans(1) from pkgsrc/textproc/translate-shell
-
-BUGS
-     st-icu should also use the combined dictionary words.
-     thai text mixed with other languages may not be handled well when
-     splitting.
-     this file should be converted to proper manpages.
-     these utilities need better names.
diff -r 226f67c55b89 -r d8397f058a8a textproc/split-thai/files/pthai.el
--- a/textproc/split-thai/files/pthai.el        Thu Mar 18 23:23:31 2021 +0000
+++ /dev/null   Thu Jan 01 00:00:00 1970 +0000
@@ -1,1848 +0,0 @@
-;; Copyright (c) 2021 Sean Cole <scole%NetBSD.org@localhost>
-;; All rights reserved.
-;;
-;; Redistribution and use in source and binary forms, with or without
-;; modification, are permitted provided that the following conditions
-;; are met:
-;;
-;; 1. Redistributions of source code must retain the above copyright
-;;    notice, this list of conditions and the following disclaimer.
-;; 2. Redistributions in binary form must reproduce the above copyright
-;;    notice, this list of conditions and the following disclaimer in the
-;;    documentation and/or other materials provided with the distribution.
-;;
-;; THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-;; "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
-;; TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-;; PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS
-;; BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-;; CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-;; SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-;; INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-;; CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-;; ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-;; POSSIBILITY OF SUCH DAMAGE.
-
-;; utilities for working with thai text in emacs buffers.  includes
-;; functions to split/unsplit thai strings, thai time conversion,
-;; download and play mp3 audio for thai words from thai-language.com,
-;; clickthai-online.com, and thai2english.com, and currency
-;; conversions from x-rates.com.  Also, it can look up thai words if
-;; vocabulary files are created.  The 'customize interface is available
-;; for a few settings.
-;;
-;; HOW TO USE
-;; - in ~/.emacs/init.el, add library path and a require, e.g.:
-;;     (add-to-list 'load-path "ST_SHARE_DIR")
-;;     (require 'pthai)
-;;   or load module directly:
-;;     (load-file "ST_SHARE_DIR/pthai.el")
-;;
-;; - also in ~/.emacs/init.el, possibly bind keys to some commonly
-;;   used functions:
-;;     (global-set-key [f8] 'pthai-lookup)
-;;      (global-set-key [f9] 'pthai-say-word)
-;;      (global-set-key [f10] 'pthai-say-line)
-;; - 'customize can be used to set or add paths to words lists and
-;;   dictionaries
-;; - M-x apropos pthai for available functions
-;;
-;; TODO


Home | Main Index | Thread Index | Old Index