switch german to utf-8

This commit is contained in:
Eric House 2010-11-14 13:43:16 -08:00
parent 6f9ba42e21
commit ec464cf57f
2 changed files with 21 additions and 20 deletions

View file

@ -1,5 +1,6 @@
# -*- mode: makefile; coding: iso-8859-1; -*- # -*- mode: makefile; coding: utf-8; -*-
# Copyright 2002 by Eric House (xwords@eehouse.org). All rights reserved. # Copyright 2002 - 2010 by Eric House (xwords@eehouse.org). All
# rights reserved.
# #
# This program is free software; you can redistribute it and/or # This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License # modify it under the terms of the GNU General Public License
@ -17,7 +18,7 @@
XWLANG = German XWLANG = German
LANGCODE = de_DE LANGCODE = de_DE
ENC = ISO-8859-1 ENC = UTF-8
TARGET_TYPE ?= WINCE TARGET_TYPE ?= WINCE
@ -28,11 +29,11 @@ include ../Makefile.langcommon
SOURCEDICT ?= $(XWDICTPATH)/German/HansGerman.dict.gz SOURCEDICT ?= $(XWDICTPATH)/German/HansGerman.dict.gz
$(XWLANG)Main.dict.gz: $(SOURCEDICT) Makefile $(XWLANG)Main.dict.gz: $(SOURCEDICT) Makefile
zcat $< | tr [a-zäöü] [A-ZÄÖÜ] | \ zcat $< \
LANG=$(LANGCODE):$(ENC) sed -e 's/ß/SS/g' | \ | tr [a-zäöü] [A-ZÄÖÜ] \
LANG=$(LANGCODE):$(ENC) grep '[AEIOUÄÖÜ]' | \ | sed -e 's/ß/SS/g' \
LANG=$(LANGCODE):$(ENC) grep '^[A-ZÄÖÜ]\+$$' | \ | grep '^[A-ZÄÖÜ]*$$' \
gzip -c > $@ | gzip -c > $@
# Everything but creating of the Main.dict file is inherited from the # Everything but creating of the Main.dict file is inherited from the
# "parent" Makefile.langcommon in the parent directory. # "parent" Makefile.langcommon in the parent directory.

View file

@ -1,4 +1,6 @@
# Copyright 2002 by Eric House (xwords@eehouse.org). All rights reserved. # -*- mode: conf; coding: utf-8; -*-
# Copyright 2002 - 2010 by Eric House (xwords@eehouse.org). All
# rights reserved.
# #
# This program is free software; you can redistribute it and/or # This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License # modify it under the terms of the GNU General Public License
@ -15,17 +17,18 @@
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
LANGCODE:de_DE LANGCODE:de_DE
CHARSET: utf-8
# deal with DOS files # deal with DOS files
LANGFILTER: tr -d '\r' LANGFILTER: tr -d '\r'
# substitute for sharfes-s # substitute for sharfes-s
LANGFILTER: | sed -e 's/ß/SS/g' LANGFILTER: | sed -e 's/ß/SS/g'
# uppercase all # uppercase all
LANGFILTER: | tr [a-zäöü] [A-ZÄÖÜ] LANGFILTER: | tr [a-zäöü] [A-ZÄÖÜ]
# no words not containing a vowel # no words not containing a vowel
LANGFILTER: | grep '[AEIOUÄÖÜ]' LANGFILTER: | grep '[AEIOUÄÖÜ]'
# none with illegal chars # none with illegal chars
LANGFILTER: | grep '^[A-ZÄÖÜ]\+$' LANGFILTER: | grep '^[A-ZÄÖÜ]\+$'
# Until I can figure out how to force sort to use a locale's collation # Until I can figure out how to force sort to use a locale's collation
# rules we can't trust sort in the filtering rules above and so must # rules we can't trust sort in the filtering rules above and so must
@ -46,9 +49,8 @@ XLOC_HEADER:0x8300
<BEGIN_TILES> <BEGIN_TILES>
2 0 {"_"} 2 0 {"_"}
5 1 'A' 5 1 'A'
# A mit umlaut 1 6 'Ä'
1 6 196
2 3 'B' 2 3 'B'
2 4 'C' 2 4 'C'
4 1 'D' 4 1 'D'
@ -63,16 +65,14 @@ XLOC_HEADER:0x8300
4 3 'M' 4 3 'M'
9 1 'N' 9 1 'N'
3 2 'O' 3 2 'O'
# O mit umlaut 1 8 'Ö'
1 8 214
1 4 'P' 1 4 'P'
1 10 'Q' 1 10 'Q'
6 1 'R' 6 1 'R'
7 1 'S' 7 1 'S'
6 1 'T' 6 1 'T'
6 1 'U' 6 1 'U'
# U mit umlaut 1 6 'Ü'
1 6 220
1 6 'V' 1 6 'V'
1 3 'W' 1 3 'W'
1 8 'X' 1 8 'X'