dnrops
/
dictionaries
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

pt-BR thesaurus: remove idx file from source. 

idx fles are created in build.

Change-Id: I32cef18b22aad876d3caf4f3d00e776c5aa1e195
Reviewed-on: https://gerrit.libreoffice.org/c/dictionaries/+/129963
Reviewed-by: Rafael Lima <rafael.palma.lima@gmail.com>
Reviewed-by: Olivier Hallot <olivier.hallot@libreoffice.org>
Tested-by: Olivier Hallot <olivier.hallot@libreoffice.org>
This commit is contained in:
Olivier Hallot 2022-02-15 09:58:21 -03:00
parent 96ecbe7fb1
commit 86f503136b
3 changed files with 4 additions and 26541 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Dictionary_pt-BR.mk
View File

@ -13,8 +13,6 @@ $(eval $(call gb_Dictionary_add_root_files,dict-pt-BR,\
dictionaries/pt_BR/hyph_pt_BR.dic \
dictionaries/pt_BR/pt_BR.aff \
dictionaries/pt_BR/pt_BR.dic \
dictionaries/pt_BR/th_pt_BR.dat \
dictionaries/pt_BR/th_pt_BR.idx \
dictionaries/pt_BR/Lightproof.components \
dictionaries/pt_BR/Lightproof.py \
dictionaries/pt_BR/Linguistic.xcu \
@ -58,5 +56,9 @@ $(eval $(call gb_Dictionary_add_propertyfiles,dict-pt-BR,dialog,\
dictionaries/pt_BR/dialog/pt_BR_en_US.properties \
))
$(eval $(call gb_Dictionary_add_thesauri,dict-pt-BR,\
dictionaries/pt_BR/th_pt_BR.dat \
))
# vim: set noet sw=4 ts=4:

59
pt_BR/th_gen_idx.pl
View File

@ -1,59 +0,0 @@
#!/usr/bin/perl
# perl program to take a thesaurus structured text data file
# and create the proper sorted index file (.idx)
#
# typcially invoked as follows:
# cat th_en_US_new.dat | ./th_gen_idx.pl > th_en_US_new.idx
#
sub by_entry {
my ($aent, $aoff) = split('\|',$a);
my ($bent, $boff) = split('\|',$b);
$aent cmp $bent;
}
# 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
# 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 + $rl;
}
# now we have all of the information
# so sort it and then output the encoding, count and index data
@tindex = sort by_entry @tindex;
print STDOUT "$encoding\n";
print STDOUT "$ne\n";
foreach $one (@tindex) {
print STDOUT "$one\n";
}

26480
pt_BR/th_pt_BR.idx
View File

File diff suppressed because it is too large Load Diff