mirror of
git://xwords.git.sourceforge.net/gitroot/xwords/xwords
synced 2024-11-16 07:48:07 +01:00
Break Czech into two "languages" as a way to support the two encodings in common use.
This commit is contained in:
parent
996e88a575
commit
5fd535d853
4 changed files with 133 additions and 4 deletions
|
@ -15,7 +15,7 @@
|
|||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
XWLANG=Czech
|
||||
XWLANG=Czech-CP1250
|
||||
LANGCODE=cs_CS
|
||||
|
||||
TARGET_TYPE ?= PALM
|
|
@ -30,11 +30,13 @@ LANGFILTER: | sort -u
|
|||
# presence of high-ascii means we must not pass -nosort
|
||||
D2DARGS: -term 10 -r
|
||||
|
||||
LANGINFO: <p>Czech has been tested so far with windows-1250 text
|
||||
LANGINFO: producing dictionaries that run on PalmOS.</p>
|
||||
LANGINFO: <p>This BYOD language works on Czech wordlists encoded in
|
||||
LANGINFO: windows-1250 and produces dictionaries that should work on
|
||||
LANGINFO: windows-1250-localized systems. If your Czech wordlist is
|
||||
LANGINFO: iso-8859-2-encoded, go back and choose Czech-ISO8859-2. </p>
|
||||
|
||||
# High bit means "official". Next 7 bits are an enum where
|
||||
# Czech==0x10. Low byte is padding.
|
||||
# Czech-CP1250==0x10. Low byte is padding.
|
||||
XLOC_HEADER:0x9000
|
||||
|
||||
#COUNT VAL FACE
|
43
xwords4/dawg/Czech-ISO8859-2/Makefile
Normal file
43
xwords4/dawg/Czech-ISO8859-2/Makefile
Normal file
|
@ -0,0 +1,43 @@
|
|||
# -*-mode: Makefile; coding: iso-8859-2; -*-
|
||||
# Copyright 2002-2008 by Eric House (xwords@eehouse.org). All rights reserved.
|
||||
#
|
||||
# This program is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU General Public License
|
||||
# as published by the Free Software Foundation; either version 2
|
||||
# of the License, or (at your option) any later version.
|
||||
#
|
||||
# This program 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 General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
XWLANG=Czech-ISO8859-2
|
||||
LANGCODE=cs_CS
|
||||
|
||||
TARGET_TYPE ?= PALM
|
||||
|
||||
include ../Makefile.2to8
|
||||
|
||||
include ../Makefile.langcommon
|
||||
|
||||
SOURCEDICT ?= $(XWDICTPATH)/$(XWLANG)/czech2_10_iso.dict.gz
|
||||
|
||||
$(XWLANG)Main.dict.gz: $(SOURCEDICT) Makefile
|
||||
export LC_ALL=$(LANGCODE); \
|
||||
zcat $< | \
|
||||
tr [aábcèdïeéìfghiíjklmnòoóprøs¹t»uúùvxyýz¾] [AÁBCÈDÏEÉÌFGHIÍJKLMNÒOÓPRØS©T«UÚÙVXYÝZ®] | \
|
||||
grep '^[AÁBCÈDÏEÉÌFGHIÍJKLMNÒOÓPRØS©T«UÚÙVXYÝZ®]\+$$' | \
|
||||
gzip -c > $@
|
||||
|
||||
# Everything but creating of the Main.dict file is inherited from the
|
||||
# "parent" Makefile.langcommon in the parent directory.
|
||||
|
||||
clean: clean_common
|
||||
rm -f $(XWLANG)Main.dict.gz *.bin $(XWLANG)*.pdb $(XWLANG)*.seb
|
||||
|
||||
help:
|
||||
@echo 'make [SOURCEDICT=$(XWDICTPATH)/$(XWLANG)/czech2_5.dict.gz]'
|
84
xwords4/dawg/Czech-ISO8859-2/info.txt
Normal file
84
xwords4/dawg/Czech-ISO8859-2/info.txt
Normal file
|
@ -0,0 +1,84 @@
|
|||
# -*- coding: iso-8859-2; mode: conf; -*-
|
||||
# Copyright 2002-2008 by Eric House (xwords@eehouse.org). All rights reserved.
|
||||
#
|
||||
# This program is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU General Public License
|
||||
# as published by the Free Software Foundation; either version 2
|
||||
# of the License, or (at your option) any later version.
|
||||
#
|
||||
# This program 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 General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with this program; if not, write to the Free Software
|
||||
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
|
||||
LANGCODE:cs_CZ
|
||||
CHARSET:iso-8859-2
|
||||
|
||||
# deal with DOS files
|
||||
LANGFILTER: tr -d '\r'
|
||||
# tr seems to work on systems that don't know the Czech locale, but
|
||||
# grep does not. So don't use grep, e.g. to eliminate words
|
||||
# containing letters not in our alphabet. Instead, pass the -r flag
|
||||
# via D2DARGS so they're dropped.
|
||||
LANGFILTER: | tr [aábcèdïeéìfghiíjklmnòoóprøs¹t»uúùvxyýz¾] [AÁBCÈDÏEÉÌFGHIÍJKLMNÒOÓPRØS©T«UÚÙVXYÝZ®]
|
||||
LANGFILTER: | sort -u
|
||||
|
||||
# presence of high-ascii means we must not pass -nosort
|
||||
D2DARGS: -term 10 -r
|
||||
|
||||
LANGINFO: <p>This BYOD language works on Czech wordlists encoded in
|
||||
LANGINFO: iso-8859-2 and produces dictionaries that should work on
|
||||
LANGINFO: iso-8859-2-localized systems. If your Czech wordlist is
|
||||
LANGINFO: windows-1250-encoded, go back and choose Czech-CP1250. </p>
|
||||
|
||||
# High bit means "official". Next 7 bits are an enum where
|
||||
# Czech-ISO8859-2==0x11. Low byte is padding.
|
||||
XLOC_HEADER:0x9100
|
||||
|
||||
#COUNT VAL FACE
|
||||
<BEGIN_TILES>
|
||||
2 0 {"_"}
|
||||
5 1 'A'
|
||||
2 2 'Á'
|
||||
2 3 'B'
|
||||
3 2 'C'
|
||||
1 4 'È'
|
||||
3 1 'D'
|
||||
1 8 'Ï'
|
||||
5 1 'E'
|
||||
2 3 'É'
|
||||
2 3 'Ì'
|
||||
1 5 'F'
|
||||
1 5 'G'
|
||||
3 2 'H'
|
||||
4 1 'I'
|
||||
3 2 'Í'
|
||||
2 2 'J'
|
||||
3 1 'K'
|
||||
3 1 'L'
|
||||
3 2 'M'
|
||||
5 1 'N'
|
||||
1 6 'Ò'
|
||||
6 1 'O'
|
||||
1 7 'Ó'
|
||||
3 1 'P'
|
||||
3 1 'R'
|
||||
2 4 'Ø'
|
||||
4 1 'S'
|
||||
2 4 '©'
|
||||
4 1 'T'
|
||||
1 7 '«'
|
||||
3 2 'U'
|
||||
1 5 'Ú'
|
||||
1 4 'Ù'
|
||||
4 1 'V'
|
||||
1 10 'X'
|
||||
2 2 'Y'
|
||||
2 4 'Ý'
|
||||
2 2 'Z'
|
||||
1 4 '®'
|
||||
<END_TILES>
|
Loading…
Reference in a new issue