diff options
author | obo <obo@openoffice.org> | 2010-06-22 12:09:13 +0200 |
---|---|---|
committer | obo <obo@openoffice.org> | 2010-06-22 12:09:13 +0200 |
commit | 7a43ae9e8ebd1cdbd083f0994330d9314c5d4db3 (patch) | |
tree | 220571fe2e23163548401e14329c8352d2657757 | |
parent | b715c7db467a542baf092f616ba5b00c3b80ce3d (diff) | |
parent | a859e7e5b02891f615be95ee833f94e15a66ff44 (diff) |
CWS-TOOLING: integrate CWS mythes12
-rw-r--r-- | dictionaries/cs_CZ/makefile.mk | 2 | ||||
-rw-r--r-- | dictionaries/it_IT/makefile.mk | 2 | ||||
-rw-r--r-- | dictionaries/ne_NP/makefile.mk | 2 | ||||
-rw-r--r-- | dictionaries/prj/build.lst | 2 | ||||
-rw-r--r-- | dictionaries/ru_RU/makefile.mk | 2 | ||||
-rwxr-xr-x | dictionaries/util/th_gen_idx.pl | 109 |
6 files changed, 5 insertions, 114 deletions
diff --git a/dictionaries/cs_CZ/makefile.mk b/dictionaries/cs_CZ/makefile.mk index 174ae58..9ecb08d 100644 --- a/dictionaries/cs_CZ/makefile.mk +++ b/dictionaries/cs_CZ/makefile.mk @@ -82,4 +82,4 @@ $(COMPONENT_UNZIP_FILES) .SILENT .UPDATEALL : "$(COMPONENT_ZIP)" .ENDIF # "$(COMPONENT_UNZIP_FILES)"!="" $(EXTENSIONDIR)$/th_cs_CZ_v2.idx : "$(EXTENSIONDIR)$/th_cs_CZ_v2.dat" - $(PERL) $(PRJ)$/util$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_cs_CZ_v2.idx <$(EXTENSIONDIR)$/th_cs_CZ_v2.dat + $(PERL) $(SOLARBINDIR)$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_cs_CZ_v2.idx <$(EXTENSIONDIR)$/th_cs_CZ_v2.dat diff --git a/dictionaries/it_IT/makefile.mk b/dictionaries/it_IT/makefile.mk index 5109f00..2c53bdb 100644 --- a/dictionaries/it_IT/makefile.mk +++ b/dictionaries/it_IT/makefile.mk @@ -86,4 +86,4 @@ $(COMPONENT_UNZIP_FILES) .SILENT .UPDATEALL : "$(COMPONENT_ZIP)" .ENDIF # "$(COMPONENT_UNZIP_FILES)"!="" $(EXTENSIONDIR)$/th_it_IT_v2.idx : "$(EXTENSIONDIR)$/th_it_IT_v2.dat" - $(PERL) $(PRJ)$/util$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_it_IT_v2.idx <$(EXTENSIONDIR)$/th_it_IT_v2.dat + $(PERL) $(SOLARBINDIR)$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_it_IT_v2.idx <$(EXTENSIONDIR)$/th_it_IT_v2.dat diff --git a/dictionaries/ne_NP/makefile.mk b/dictionaries/ne_NP/makefile.mk index 7bcefa7..b3a7d67 100644 --- a/dictionaries/ne_NP/makefile.mk +++ b/dictionaries/ne_NP/makefile.mk @@ -84,4 +84,4 @@ $(COMPONENT_UNZIP_FILES) .SILENT .UPDATEALL : "$(COMPONENT_ZIP)" .ENDIF # "$(COMPONENT_UNZIP_FILES)"!="" $(EXTENSIONDIR)$/th_ne_NP_v2.idx : "$(EXTENSIONDIR)$/th_ne_NP_v2.dat" - $(PERL) $(PRJ)$/util$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_ne_NP_v2.idx <$(EXTENSIONDIR)$/th_ne_NP_v2.dat + $(PERL) $(SOLARBINDIR)$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_ne_NP_v2.idx <$(EXTENSIONDIR)$/th_ne_NP_v2.dat diff --git a/dictionaries/prj/build.lst b/dictionaries/prj/build.lst index fc01b81..6052a8a 100644 --- a/dictionaries/prj/build.lst +++ b/dictionaries/prj/build.lst @@ -1,4 +1,4 @@ -di dictionaries : soltools NULL +di dictionaries : soltools MYTHES:mythes NULL di dictionaries usr1 - all di_mkout NULL di dictionaries\af_ZA nmake - all di_af_ZA NULL di dictionaries\ca nmake - all di_ca NULL diff --git a/dictionaries/ru_RU/makefile.mk b/dictionaries/ru_RU/makefile.mk index 7f6f14a..a1da9d5 100644 --- a/dictionaries/ru_RU/makefile.mk +++ b/dictionaries/ru_RU/makefile.mk @@ -82,4 +82,4 @@ $(COMPONENT_UNZIP_FILES) .SILENT .UPDATEALL : "$(COMPONENT_ZIP)" .ENDIF # "$(COMPONENT_UNZIP_FILES)"!="" $(EXTENSIONDIR)$/th_ru_RU_v2.idx : "$(EXTENSIONDIR)$/th_ru_RU_v2.dat" - $(PERL) $(PRJ)$/util$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_ru_RU_v2.idx <$(EXTENSIONDIR)$/th_ru_RU_v2.dat + $(PERL) $(SOLARBINDIR)$/th_gen_idx.pl -o $(EXTENSIONDIR)$/th_ru_RU_v2.idx <$(EXTENSIONDIR)$/th_ru_RU_v2.dat diff --git a/dictionaries/util/th_gen_idx.pl b/dictionaries/util/th_gen_idx.pl deleted file mode 100755 index b2d01e6..0000000 --- a/dictionaries/util/th_gen_idx.pl +++ /dev/null @@ -1,109 +0,0 @@ -: -eval 'exec perl -wS $0 ${1+"$@"}' - if 0; -#************************************************************************* -# -# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. -# -# Copyright 2000, 2010 Oracle and/or its affiliates. -# -# OpenOffice.org - a multi-platform office productivity suite -# -# This file is part of OpenOffice.org. -# -# OpenOffice.org is free software: you can redistribute it and/or modify -# it under the terms of the GNU Lesser General Public License version 3 -# only, as published by the Free Software Foundation. -# -# OpenOffice.org is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU Lesser General Public License version 3 for more details -# (a copy is included in the LICENSE file that accompanied this code). -# -# You should have received a copy of the GNU Lesser General Public License -# version 3 along with OpenOffice.org. If not, see -# <http://www.openoffice.org/license.html> -# for a copy of the LGPLv3 License. -# -#************************************************************************* - -sub by_entry { - my ($aent, $aoff) = split('\|',$a); - my ($bent, $boff) = split('\|',$b); - $aent cmp $bent; -} - -#FIXME: someone may want "infile" or even parameter parsing -sub get_outfile { - my $next_is_file = 0; - foreach ( @ARGV ) { - if ( $next_is_file ) { - return $_ - } - if ( $_ eq "-o" ) { - $next_is_file = 1; - } - } - return ""; -} - -sub usage { - print "usage:\n"; - print "$0 -o outfile < input\n"; - - exit 99; -} - -# main routine -my $ne = 0; # number of entries in index -my @tindex=(); # the index itself -my $foffset = 0; # file position offset into thesaurus -my $rec=""; # current string and related pieces -my $rl=0; # misc string length -my $entry=""; # current word being processed -my $nm=0; # number of meaning for the current word -my $meaning=""; # current meaning and synonyms -my $p; # misc uses -my $encoding; # encoding used by text file -my $outfile = ""; - -$outfile = get_outfile(); -usage() if ( $outfile eq "" ); - -# top line of thesaurus provides encoding -$encoding=<STDIN>; -$foffset = $foffset + length($encoding); -chomp($encoding); - -# read thesaurus line by line -# first line of every block is an entry and meaning count -while ($rec=<STDIN>){ - $rl = length($rec); - chomp($rec); - ($entry, $nm) = split('\|',$rec); - $p = 0; - while ($p < $nm) { - $meaning=<STDIN>; - $rl = $rl + length($meaning); - chomp($meaning); - $p++; - } - push(@tindex,"$entry|$foffset"); - $ne++; - $foffset = $foffset + $rl; -} - -# now we have all of the information -# so sort it and then output the encoding, count and index data -@tindex = sort by_entry @tindex; - -print "$outfile\n"; -open OUTFILE, ">$outfile" or die "ERROR: Can't open $outfile for writing!"; -print OUTFILE "$encoding\n"; -print OUTFILE "$ne\n"; -foreach $one (@tindex) { - print OUTFILE "$one\n"; -} -close OUTFILE; - |